Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,61 @@
+---
+library_name: transformers
+license: other
+base_model: Qwen/Qwen2.5-32B-Instruct
+tags:
+- llama-factory
+- full
+- generated_from_trainer
+model-index:
+- name: original
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# original
+
+This model is a fine-tuned version of [Qwen/Qwen2.5-32B-Instruct](https://huggingface.co/Qwen/Qwen2.5-32B-Instruct) on the Sky-T1 dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 2e-05
+- train_batch_size: 1
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 8
+- gradient_accumulation_steps: 12
+- total_train_batch_size: 96
+- total_eval_batch_size: 64
+- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 2.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.46.1
+- Pytorch 2.4.0a0+f70bd71a48.nv24.06
+- Datasets 3.1.0
+- Tokenizers 0.20.3

added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.9961919268849961,
+    "total_flos": 556668498083840.0,
+    "train_loss": 0.02458530199637107,
+    "train_runtime": 2561.7302,
+    "train_samples_per_second": 8.198,
+    "train_steps_per_second": 0.085
+}

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "Qwen/Qwen2.5-32B-Instruct",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 27648,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 70,
+  "model_type": "qwen2",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 64,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.1",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.05,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.46.1"
+}

model-00001-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b245bd3b9229a4d4e10da7029270afecf4850041cdded74d5a3089fcb4bac18d
+size 4891730992

model-00002-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e587f9f612203926ceb7c79843d0610de32a09451eb75f3c1fa3886e7784350a
+size 4876059352

model-00003-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58130b38e2c1736e7eb87172bcd91692b73a4558836bb66524b538fa1f0826fd
+size 4876059384

model-00004-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0888bb64b416868be371d95614078baff606c7d5a15476f3206284121347e834
+size 4876059416

model-00005-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:628103a62c9bd3a23f19c705731a73f684ebf5704a17c54d2266f0fcf045c906
+size 4876059416

model-00006-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6136cf8b901b3e2529ba0d9d1cd9e35b1b0b5cadfac05f000517f9e7f7d7f54f
+size 4876059416

model-00007-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04601dd403a52713b60ceb4d37377639acac31b771178bc186ca2f70cde8e883
+size 4876059416

model-00008-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af3f7533d26eedcd0273a2d6cd03f2008047b4ba7ad36f4a0ecc53dbb74867aa
+size 4876059416

model-00009-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a6ebb46f83b87c3d7bbf2f14d83c42476c6c1d4660609ab72f7cce8fa56e360
+size 4876059416

model-00010-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:985f42f4ab8552b70388494f3dc083db8742c99c2746437babd1ba98221ab9a3
+size 4876059416

model-00011-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49b64b3bdf3a44cb9a20b307e86fac1931ee7c23219ec39713c70d982ee8c6fd
+size 4876059416

model-00012-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3d186d0d5d365f8fe298dd187d360494e8b2c4f042415d26e354fee6dca0657
+size 4876059416

model-00013-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49ee9d22e66e12f529ae3e1f59728105c576488675000acf2e5baffd63ca0bfb
+size 4876059416

model-00014-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7cd2b3efdaddf4c33ddaab9f9871cd8e1fe8b9d0127130046beaf2e91f1c6ac3
+size 2123397800

model.safetensors.index.json

@@ -0,0 +1,778 @@
+{
+  "metadata": {
+    "total_size": 65527752704
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00014-of-00014.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00014.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00014.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00014.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00014.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00014.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00014.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00014.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00014.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00014.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.28.self_attn.k_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.28.self_attn.q_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.28.self_attn.v_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.29.self_attn.k_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.29.self_attn.q_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.29.self_attn.v_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00014.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00014.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00014.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.30.self_attn.k_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.30.self_attn.q_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.30.self_attn.v_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.31.self_attn.k_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.31.self_attn.q_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.31.self_attn.v_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.32.self_attn.k_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.32.self_attn.q_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.32.self_attn.v_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.33.self_attn.k_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.33.self_attn.q_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.33.self_attn.v_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.34.self_attn.k_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.34.self_attn.q_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.34.self_attn.v_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.35.self_attn.k_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.35.self_attn.q_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.35.self_attn.v_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.36.self_attn.k_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.36.self_attn.q_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.36.self_attn.v_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.37.self_attn.k_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.37.self_attn.q_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.37.self_attn.v_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.38.self_attn.k_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.38.self_attn.q_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.38.self_attn.v_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.39.self_attn.k_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.39.self_attn.q_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.39.self_attn.v_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.40.input_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.40.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.40.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.40.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.40.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.40.self_attn.k_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.40.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.40.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.40.self_attn.q_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.40.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.40.self_attn.v_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.40.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.41.input_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.41.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.41.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.41.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.41.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.41.self_attn.k_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.41.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.41.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.41.self_attn.q_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.41.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.41.self_attn.v_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.41.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.42.input_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.42.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.42.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.42.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.42.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.42.self_attn.k_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.42.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.42.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.42.self_attn.q_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.42.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.42.self_attn.v_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.42.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.43.input_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.43.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.43.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.43.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.43.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.43.self_attn.k_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.43.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.43.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.43.self_attn.q_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.43.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.43.self_attn.v_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.43.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.44.input_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.44.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.44.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.44.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.44.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.44.self_attn.k_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.44.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.44.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.44.self_attn.q_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.44.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.44.self_attn.v_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.44.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.45.input_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.45.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.45.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.45.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.45.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.45.self_attn.k_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.45.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.45.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.45.self_attn.q_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.45.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.45.self_attn.v_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.45.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.46.input_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.46.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.46.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.46.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.46.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.46.self_attn.k_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.46.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.46.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.46.self_attn.q_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.46.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.46.self_attn.v_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.46.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.47.input_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.47.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.47.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.47.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.47.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.47.self_attn.k_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.47.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.47.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.47.self_attn.q_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.47.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.47.self_attn.v_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.47.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.48.input_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.48.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.48.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.48.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.48.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.48.self_attn.k_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.48.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.48.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.48.self_attn.q_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.48.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.48.self_attn.v_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.48.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.49.input_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.49.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.49.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.49.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.49.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.49.self_attn.k_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.49.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.49.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.49.self_attn.q_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.49.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.49.self_attn.v_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.49.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.50.input_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.50.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.50.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.50.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.50.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.50.self_attn.k_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.50.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.50.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.50.self_attn.q_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.50.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.50.self_attn.v_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.50.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.51.input_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.51.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.51.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.51.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.51.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.51.self_attn.k_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.51.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.51.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.51.self_attn.q_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.51.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.51.self_attn.v_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.51.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.52.input_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.52.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.52.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.52.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.52.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.52.self_attn.k_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.52.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.52.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.52.self_attn.q_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.52.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.52.self_attn.v_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.52.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.53.input_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.53.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.53.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.53.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.53.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.53.self_attn.k_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.53.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.53.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.53.self_attn.q_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.53.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.53.self_attn.v_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.53.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.54.input_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.54.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.54.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.54.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.54.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.54.self_attn.k_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.54.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.54.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.54.self_attn.q_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.54.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.54.self_attn.v_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.54.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.55.input_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.55.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.55.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.55.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.55.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.55.self_attn.k_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.55.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.55.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.55.self_attn.q_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.55.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.55.self_attn.v_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.55.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.56.input_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.56.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.56.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.56.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.56.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.56.self_attn.k_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.56.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.56.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.56.self_attn.q_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.56.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.56.self_attn.v_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.56.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.57.input_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.57.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.57.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.57.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.57.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.57.self_attn.k_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.57.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.57.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.57.self_attn.q_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.57.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.57.self_attn.v_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.57.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.58.input_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.58.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.58.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.58.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.58.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.58.self_attn.k_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.58.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.58.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.58.self_attn.q_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.58.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.58.self_attn.v_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.58.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.59.input_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.59.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.59.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.59.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.59.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.59.self_attn.k_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.59.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.59.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.59.self_attn.q_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.59.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.59.self_attn.v_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.59.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.60.input_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.60.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.60.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.60.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.60.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.60.self_attn.k_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.60.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.60.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.60.self_attn.q_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.60.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.60.self_attn.v_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.60.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.61.input_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.61.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.61.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.61.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.61.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.61.self_attn.k_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.61.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.61.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.61.self_attn.q_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.61.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.61.self_attn.v_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.61.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.62.input_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.62.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.62.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.62.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.62.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.62.self_attn.k_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.62.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.62.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.62.self_attn.q_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.62.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.62.self_attn.v_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.62.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.63.input_layernorm.weight": "model-00014-of-00014.safetensors",
+    "model.layers.63.mlp.down_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.63.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.63.mlp.up_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.63.post_attention_layernorm.weight": "model-00014-of-00014.safetensors",
+    "model.layers.63.self_attn.k_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.63.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.63.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.63.self_attn.q_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.63.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.63.self_attn.v_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.63.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
+    "model.norm.weight": "model-00014-of-00014.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+size 11421896

tokenizer_config.json

@@ -0,0 +1,208 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.9961919268849961,
+    "total_flos": 556668498083840.0,
+    "train_loss": 0.02458530199637107,
+    "train_runtime": 2561.7302,
+    "train_samples_per_second": 8.198,
+    "train_steps_per_second": 0.085
+}

trainer_log.jsonl

@@ -0,0 +1,272 @@
+{"current_steps": 1, "total_steps": 218, "loss": 0.6539, "lr": 9.090909090909091e-07, "epoch": 0.00913937547600914, "percentage": 0.46, "elapsed_time": "0:02:12", "remaining_time": "7:59:04"}
+{"current_steps": 2, "total_steps": 218, "loss": 0.6614, "lr": 1.8181818181818183e-06, "epoch": 0.01827875095201828, "percentage": 0.92, "elapsed_time": "0:04:26", "remaining_time": "7:59:49"}
+{"current_steps": 3, "total_steps": 218, "loss": 0.6435, "lr": 2.7272727272727272e-06, "epoch": 0.027418126428027417, "percentage": 1.38, "elapsed_time": "0:06:29", "remaining_time": "7:45:02"}
+{"current_steps": 4, "total_steps": 218, "loss": 0.6529, "lr": 3.6363636363636366e-06, "epoch": 0.03655750190403656, "percentage": 1.83, "elapsed_time": "0:08:26", "remaining_time": "7:31:15"}
+{"current_steps": 5, "total_steps": 218, "loss": 0.6292, "lr": 4.5454545454545455e-06, "epoch": 0.0456968773800457, "percentage": 2.29, "elapsed_time": "0:10:32", "remaining_time": "7:29:23"}
+{"current_steps": 6, "total_steps": 218, "loss": 0.601, "lr": 5.4545454545454545e-06, "epoch": 0.05483625285605483, "percentage": 2.75, "elapsed_time": "0:12:51", "remaining_time": "7:34:14"}
+{"current_steps": 7, "total_steps": 218, "loss": 0.6009, "lr": 6.363636363636364e-06, "epoch": 0.06397562833206398, "percentage": 3.21, "elapsed_time": "0:14:59", "remaining_time": "7:31:59"}
+{"current_steps": 8, "total_steps": 218, "loss": 0.5875, "lr": 7.272727272727273e-06, "epoch": 0.07311500380807312, "percentage": 3.67, "elapsed_time": "0:16:55", "remaining_time": "7:24:05"}
+{"current_steps": 9, "total_steps": 218, "loss": 0.5787, "lr": 8.181818181818183e-06, "epoch": 0.08225437928408226, "percentage": 4.13, "elapsed_time": "0:19:03", "remaining_time": "7:22:45"}
+{"current_steps": 10, "total_steps": 218, "loss": 0.5362, "lr": 9.090909090909091e-06, "epoch": 0.0913937547600914, "percentage": 4.59, "elapsed_time": "0:21:29", "remaining_time": "7:26:56"}
+{"current_steps": 11, "total_steps": 218, "loss": 0.5214, "lr": 1e-05, "epoch": 0.10053313023610053, "percentage": 5.05, "elapsed_time": "0:23:36", "remaining_time": "7:24:11"}
+{"current_steps": 12, "total_steps": 218, "loss": 0.4938, "lr": 1.0909090909090909e-05, "epoch": 0.10967250571210967, "percentage": 5.5, "elapsed_time": "0:26:00", "remaining_time": "7:26:34"}
+{"current_steps": 13, "total_steps": 218, "loss": 0.4991, "lr": 1.181818181818182e-05, "epoch": 0.1188118811881188, "percentage": 5.96, "elapsed_time": "0:28:27", "remaining_time": "7:28:38"}
+{"current_steps": 14, "total_steps": 218, "loss": 0.4899, "lr": 1.2727272727272728e-05, "epoch": 0.12795125666412796, "percentage": 6.42, "elapsed_time": "0:30:48", "remaining_time": "7:28:49"}
+{"current_steps": 15, "total_steps": 218, "loss": 0.4892, "lr": 1.3636363636363637e-05, "epoch": 0.1370906321401371, "percentage": 6.88, "elapsed_time": "0:32:43", "remaining_time": "7:22:56"}
+{"current_steps": 16, "total_steps": 218, "loss": 0.4472, "lr": 1.4545454545454546e-05, "epoch": 0.14623000761614624, "percentage": 7.34, "elapsed_time": "0:34:46", "remaining_time": "7:19:06"}
+{"current_steps": 17, "total_steps": 218, "loss": 0.4735, "lr": 1.5454545454545454e-05, "epoch": 0.15536938309215537, "percentage": 7.8, "elapsed_time": "0:37:17", "remaining_time": "7:20:49"}
+{"current_steps": 18, "total_steps": 218, "loss": 0.4586, "lr": 1.6363636363636366e-05, "epoch": 0.16450875856816452, "percentage": 8.26, "elapsed_time": "0:39:33", "remaining_time": "7:19:31"}
+{"current_steps": 19, "total_steps": 218, "loss": 0.4289, "lr": 1.7272727272727274e-05, "epoch": 0.17364813404417365, "percentage": 8.72, "elapsed_time": "0:41:17", "remaining_time": "7:12:28"}
+{"current_steps": 20, "total_steps": 218, "loss": 0.4504, "lr": 1.8181818181818182e-05, "epoch": 0.1827875095201828, "percentage": 9.17, "elapsed_time": "0:43:16", "remaining_time": "7:08:23"}
+{"current_steps": 21, "total_steps": 218, "loss": 0.4207, "lr": 1.9090909090909094e-05, "epoch": 0.19192688499619193, "percentage": 9.63, "elapsed_time": "0:45:08", "remaining_time": "7:03:31"}
+{"current_steps": 22, "total_steps": 218, "loss": 0.4242, "lr": 2e-05, "epoch": 0.20106626047220105, "percentage": 10.09, "elapsed_time": "0:47:01", "remaining_time": "6:59:00"}
+{"current_steps": 23, "total_steps": 218, "loss": 0.4299, "lr": 1.9998715457999313e-05, "epoch": 0.2102056359482102, "percentage": 10.55, "elapsed_time": "0:48:49", "remaining_time": "6:53:53"}
+{"current_steps": 24, "total_steps": 218, "loss": 0.4141, "lr": 1.999486216200688e-05, "epoch": 0.21934501142421933, "percentage": 11.01, "elapsed_time": "0:51:04", "remaining_time": "6:52:54"}
+{"current_steps": 25, "total_steps": 218, "loss": 0.4336, "lr": 1.9988441101966807e-05, "epoch": 0.2284843869002285, "percentage": 11.47, "elapsed_time": "0:53:25", "remaining_time": "6:52:28"}
+{"current_steps": 26, "total_steps": 218, "loss": 0.4417, "lr": 1.9979453927503366e-05, "epoch": 0.2376237623762376, "percentage": 11.93, "elapsed_time": "0:55:43", "remaining_time": "6:51:28"}
+{"current_steps": 27, "total_steps": 218, "loss": 0.4268, "lr": 1.9967902947497158e-05, "epoch": 0.24676313785224677, "percentage": 12.39, "elapsed_time": "0:57:49", "remaining_time": "6:49:01"}
+{"current_steps": 28, "total_steps": 218, "loss": 0.4207, "lr": 1.9953791129491985e-05, "epoch": 0.2559025133282559, "percentage": 12.84, "elapsed_time": "1:00:14", "remaining_time": "6:48:47"}
+{"current_steps": 29, "total_steps": 218, "loss": 0.4033, "lr": 1.9937122098932428e-05, "epoch": 0.26504188880426505, "percentage": 13.3, "elapsed_time": "1:02:02", "remaining_time": "6:44:19"}
+{"current_steps": 30, "total_steps": 218, "loss": 0.4191, "lr": 1.991790013823246e-05, "epoch": 0.2741812642802742, "percentage": 13.76, "elapsed_time": "1:04:40", "remaining_time": "6:45:17"}
+{"current_steps": 31, "total_steps": 218, "loss": 0.415, "lr": 1.9896130185675263e-05, "epoch": 0.2833206397562833, "percentage": 14.22, "elapsed_time": "1:06:57", "remaining_time": "6:43:52"}
+{"current_steps": 32, "total_steps": 218, "loss": 0.4027, "lr": 1.9871817834144506e-05, "epoch": 0.2924600152322925, "percentage": 14.68, "elapsed_time": "1:09:07", "remaining_time": "6:41:46"}
+{"current_steps": 33, "total_steps": 218, "loss": 0.4118, "lr": 1.9844969329687526e-05, "epoch": 0.3015993907083016, "percentage": 15.14, "elapsed_time": "1:11:11", "remaining_time": "6:39:04"}
+{"current_steps": 34, "total_steps": 218, "loss": 0.3924, "lr": 1.9815591569910654e-05, "epoch": 0.31073876618431073, "percentage": 15.6, "elapsed_time": "1:12:57", "remaining_time": "6:34:49"}
+{"current_steps": 35, "total_steps": 218, "loss": 0.4114, "lr": 1.9783692102207156e-05, "epoch": 0.31987814166031986, "percentage": 16.06, "elapsed_time": "1:15:18", "remaining_time": "6:33:43"}
+{"current_steps": 36, "total_steps": 218, "loss": 0.3631, "lr": 1.9749279121818235e-05, "epoch": 0.32901751713632904, "percentage": 16.51, "elapsed_time": "1:17:14", "remaining_time": "6:30:29"}
+{"current_steps": 37, "total_steps": 218, "loss": 0.3643, "lr": 1.971236146972764e-05, "epoch": 0.33815689261233817, "percentage": 16.97, "elapsed_time": "1:19:38", "remaining_time": "6:29:36"}
+{"current_steps": 38, "total_steps": 218, "loss": 0.3636, "lr": 1.9672948630390296e-05, "epoch": 0.3472962680883473, "percentage": 17.43, "elapsed_time": "1:21:29", "remaining_time": "6:26:02"}
+{"current_steps": 39, "total_steps": 218, "loss": 0.4101, "lr": 1.9631050729295705e-05, "epoch": 0.3564356435643564, "percentage": 17.89, "elapsed_time": "1:23:50", "remaining_time": "6:24:50"}
+{"current_steps": 40, "total_steps": 218, "loss": 0.3854, "lr": 1.9586678530366607e-05, "epoch": 0.3655750190403656, "percentage": 18.35, "elapsed_time": "1:26:04", "remaining_time": "6:23:04"}
+{"current_steps": 41, "total_steps": 218, "loss": 0.3693, "lr": 1.953984343319364e-05, "epoch": 0.3747143945163747, "percentage": 18.81, "elapsed_time": "1:28:05", "remaining_time": "6:20:15"}
+{"current_steps": 42, "total_steps": 218, "loss": 0.3894, "lr": 1.949055747010669e-05, "epoch": 0.38385376999238385, "percentage": 19.27, "elapsed_time": "1:30:29", "remaining_time": "6:19:13"}
+{"current_steps": 43, "total_steps": 218, "loss": 0.3918, "lr": 1.9438833303083677e-05, "epoch": 0.392993145468393, "percentage": 19.72, "elapsed_time": "1:32:38", "remaining_time": "6:17:02"}
+{"current_steps": 44, "total_steps": 218, "loss": 0.3635, "lr": 1.9384684220497605e-05, "epoch": 0.4021325209444021, "percentage": 20.18, "elapsed_time": "1:34:02", "remaining_time": "6:11:53"}
+{"current_steps": 45, "total_steps": 218, "loss": 0.401, "lr": 1.932812413370265e-05, "epoch": 0.4112718964204113, "percentage": 20.64, "elapsed_time": "1:36:20", "remaining_time": "6:10:23"}
+{"current_steps": 46, "total_steps": 218, "loss": 0.3688, "lr": 1.926916757346022e-05, "epoch": 0.4204112718964204, "percentage": 21.1, "elapsed_time": "1:38:15", "remaining_time": "6:07:25"}
+{"current_steps": 47, "total_steps": 218, "loss": 0.3618, "lr": 1.9207829686205882e-05, "epoch": 0.42955064737242954, "percentage": 21.56, "elapsed_time": "1:40:13", "remaining_time": "6:04:39"}
+{"current_steps": 48, "total_steps": 218, "loss": 0.3808, "lr": 1.9144126230158127e-05, "epoch": 0.43869002284843867, "percentage": 22.02, "elapsed_time": "1:42:00", "remaining_time": "6:01:15"}
+{"current_steps": 49, "total_steps": 218, "loss": 0.3625, "lr": 1.9078073571269922e-05, "epoch": 0.44782939832444785, "percentage": 22.48, "elapsed_time": "1:43:58", "remaining_time": "5:58:35"}
+{"current_steps": 1, "total_steps": 218, "loss": 0.6539, "lr": 9.090909090909091e-07, "epoch": 0.00913937547600914, "percentage": 0.46, "elapsed_time": "0:02:11", "remaining_time": "7:53:54"}
+{"current_steps": 2, "total_steps": 218, "loss": 0.6614, "lr": 1.8181818181818183e-06, "epoch": 0.01827875095201828, "percentage": 0.92, "elapsed_time": "0:04:23", "remaining_time": "7:54:31"}
+{"current_steps": 3, "total_steps": 218, "loss": 0.6435, "lr": 2.7272727272727272e-06, "epoch": 0.027418126428027417, "percentage": 1.38, "elapsed_time": "0:06:24", "remaining_time": "7:39:26"}
+{"current_steps": 4, "total_steps": 218, "loss": 0.6528, "lr": 3.6363636363636366e-06, "epoch": 0.03655750190403656, "percentage": 1.83, "elapsed_time": "0:08:19", "remaining_time": "7:25:15"}
+{"current_steps": 5, "total_steps": 218, "loss": 0.6292, "lr": 4.5454545454545455e-06, "epoch": 0.0456968773800457, "percentage": 2.29, "elapsed_time": "0:10:25", "remaining_time": "7:23:46"}
+{"current_steps": 6, "total_steps": 218, "loss": 0.6013, "lr": 5.4545454545454545e-06, "epoch": 0.05483625285605483, "percentage": 2.75, "elapsed_time": "0:12:41", "remaining_time": "7:28:25"}
+{"current_steps": 7, "total_steps": 218, "loss": 0.6013, "lr": 6.363636363636364e-06, "epoch": 0.06397562833206398, "percentage": 3.21, "elapsed_time": "0:14:47", "remaining_time": "7:25:47"}
+{"current_steps": 8, "total_steps": 218, "loss": 0.588, "lr": 7.272727272727273e-06, "epoch": 0.07311500380807312, "percentage": 3.67, "elapsed_time": "0:16:40", "remaining_time": "7:17:52"}
+{"current_steps": 9, "total_steps": 218, "loss": 0.5794, "lr": 8.181818181818183e-06, "epoch": 0.08225437928408226, "percentage": 4.13, "elapsed_time": "0:18:47", "remaining_time": "7:16:18"}
+{"current_steps": 10, "total_steps": 218, "loss": 0.5403, "lr": 9.090909090909091e-06, "epoch": 0.0913937547600914, "percentage": 4.59, "elapsed_time": "0:21:10", "remaining_time": "7:20:28"}
+{"current_steps": 11, "total_steps": 218, "loss": 0.526, "lr": 1e-05, "epoch": 0.10053313023610053, "percentage": 5.05, "elapsed_time": "0:23:15", "remaining_time": "7:17:43"}
+{"current_steps": 12, "total_steps": 218, "loss": 0.5001, "lr": 1.0909090909090909e-05, "epoch": 0.10967250571210967, "percentage": 5.5, "elapsed_time": "0:25:38", "remaining_time": "7:20:13"}
+{"current_steps": 13, "total_steps": 218, "loss": 0.5017, "lr": 1.181818181818182e-05, "epoch": 0.1188118811881188, "percentage": 5.96, "elapsed_time": "0:28:02", "remaining_time": "7:22:19"}
+{"current_steps": 14, "total_steps": 218, "loss": 0.4927, "lr": 1.2727272727272728e-05, "epoch": 0.12795125666412796, "percentage": 6.42, "elapsed_time": "0:30:22", "remaining_time": "7:22:39"}
+{"current_steps": 15, "total_steps": 218, "loss": 0.4917, "lr": 1.3636363636363637e-05, "epoch": 0.1370906321401371, "percentage": 6.88, "elapsed_time": "0:32:16", "remaining_time": "7:16:51"}
+{"current_steps": 16, "total_steps": 218, "loss": 0.4444, "lr": 1.4545454545454546e-05, "epoch": 0.14623000761614624, "percentage": 7.34, "elapsed_time": "0:34:17", "remaining_time": "7:12:51"}
+{"current_steps": 17, "total_steps": 218, "loss": 0.4665, "lr": 1.5454545454545454e-05, "epoch": 0.15536938309215537, "percentage": 7.8, "elapsed_time": "0:36:45", "remaining_time": "7:14:37"}
+{"current_steps": 18, "total_steps": 218, "loss": 0.454, "lr": 1.6363636363636366e-05, "epoch": 0.16450875856816452, "percentage": 8.26, "elapsed_time": "0:39:00", "remaining_time": "7:13:30"}
+{"current_steps": 19, "total_steps": 218, "loss": 0.4245, "lr": 1.7272727272727274e-05, "epoch": 0.17364813404417365, "percentage": 8.72, "elapsed_time": "0:40:43", "remaining_time": "7:06:29"}
+{"current_steps": 20, "total_steps": 218, "loss": 0.4473, "lr": 1.8181818181818182e-05, "epoch": 0.1827875095201828, "percentage": 9.17, "elapsed_time": "0:42:39", "remaining_time": "7:02:22"}
+{"current_steps": 21, "total_steps": 218, "loss": 0.4181, "lr": 1.9090909090909094e-05, "epoch": 0.19192688499619193, "percentage": 9.63, "elapsed_time": "0:44:30", "remaining_time": "6:57:29"}
+{"current_steps": 22, "total_steps": 218, "loss": 0.4225, "lr": 2e-05, "epoch": 0.20106626047220105, "percentage": 10.09, "elapsed_time": "0:46:22", "remaining_time": "6:53:07"}
+{"current_steps": 23, "total_steps": 218, "loss": 0.4286, "lr": 1.9998715457999313e-05, "epoch": 0.2102056359482102, "percentage": 10.55, "elapsed_time": "0:48:07", "remaining_time": "6:48:00"}
+{"current_steps": 24, "total_steps": 218, "loss": 0.4125, "lr": 1.999486216200688e-05, "epoch": 0.21934501142421933, "percentage": 11.01, "elapsed_time": "0:50:21", "remaining_time": "6:47:04"}
+{"current_steps": 25, "total_steps": 218, "loss": 0.4321, "lr": 1.9988441101966807e-05, "epoch": 0.2284843869002285, "percentage": 11.47, "elapsed_time": "0:52:41", "remaining_time": "6:46:42"}
+{"current_steps": 26, "total_steps": 218, "loss": 0.4401, "lr": 1.9979453927503366e-05, "epoch": 0.2376237623762376, "percentage": 11.93, "elapsed_time": "0:54:57", "remaining_time": "6:45:49"}
+{"current_steps": 27, "total_steps": 218, "loss": 0.4255, "lr": 1.9967902947497158e-05, "epoch": 0.24676313785224677, "percentage": 12.39, "elapsed_time": "0:57:01", "remaining_time": "6:43:24"}
+{"current_steps": 28, "total_steps": 218, "loss": 0.42, "lr": 1.9953791129491985e-05, "epoch": 0.2559025133282559, "percentage": 12.84, "elapsed_time": "0:59:24", "remaining_time": "6:43:10"}
+{"current_steps": 29, "total_steps": 218, "loss": 0.4023, "lr": 1.9937122098932428e-05, "epoch": 0.26504188880426505, "percentage": 13.3, "elapsed_time": "1:01:11", "remaining_time": "6:38:47"}
+{"current_steps": 30, "total_steps": 218, "loss": 0.4182, "lr": 1.991790013823246e-05, "epoch": 0.2741812642802742, "percentage": 13.76, "elapsed_time": "1:03:47", "remaining_time": "6:39:45"}
+{"current_steps": 31, "total_steps": 218, "loss": 0.4142, "lr": 1.9896130185675263e-05, "epoch": 0.2833206397562833, "percentage": 14.22, "elapsed_time": "1:06:02", "remaining_time": "6:38:20"}
+{"current_steps": 32, "total_steps": 218, "loss": 0.402, "lr": 1.9871817834144506e-05, "epoch": 0.2924600152322925, "percentage": 14.68, "elapsed_time": "1:08:10", "remaining_time": "6:36:16"}
+{"current_steps": 33, "total_steps": 218, "loss": 0.4112, "lr": 1.9844969329687526e-05, "epoch": 0.3015993907083016, "percentage": 15.14, "elapsed_time": "1:10:12", "remaining_time": "6:33:36"}
+{"current_steps": 34, "total_steps": 218, "loss": 0.3917, "lr": 1.9815591569910654e-05, "epoch": 0.31073876618431073, "percentage": 15.6, "elapsed_time": "1:11:56", "remaining_time": "6:29:21"}
+{"current_steps": 35, "total_steps": 218, "loss": 0.4108, "lr": 1.9783692102207156e-05, "epoch": 0.31987814166031986, "percentage": 16.06, "elapsed_time": "1:14:16", "remaining_time": "6:28:19"}
+{"current_steps": 36, "total_steps": 218, "loss": 0.3623, "lr": 1.9749279121818235e-05, "epoch": 0.32901751713632904, "percentage": 16.51, "elapsed_time": "1:16:10", "remaining_time": "6:25:07"}
+{"current_steps": 37, "total_steps": 218, "loss": 0.3637, "lr": 1.971236146972764e-05, "epoch": 0.33815689261233817, "percentage": 16.97, "elapsed_time": "1:18:33", "remaining_time": "6:24:17"}
+{"current_steps": 38, "total_steps": 218, "loss": 0.3627, "lr": 1.9672948630390296e-05, "epoch": 0.3472962680883473, "percentage": 17.43, "elapsed_time": "1:20:22", "remaining_time": "6:20:44"}
+{"current_steps": 39, "total_steps": 218, "loss": 0.4095, "lr": 1.9631050729295705e-05, "epoch": 0.3564356435643564, "percentage": 17.89, "elapsed_time": "1:22:41", "remaining_time": "6:19:31"}
+{"current_steps": 40, "total_steps": 218, "loss": 0.3846, "lr": 1.9586678530366607e-05, "epoch": 0.3655750190403656, "percentage": 18.35, "elapsed_time": "1:24:53", "remaining_time": "6:17:44"}
+{"current_steps": 41, "total_steps": 218, "loss": 0.3688, "lr": 1.953984343319364e-05, "epoch": 0.3747143945163747, "percentage": 18.81, "elapsed_time": "1:26:51", "remaining_time": "6:14:58"}
+{"current_steps": 42, "total_steps": 218, "loss": 0.3885, "lr": 1.949055747010669e-05, "epoch": 0.38385376999238385, "percentage": 19.27, "elapsed_time": "1:29:13", "remaining_time": "6:13:55"}
+{"current_steps": 43, "total_steps": 218, "loss": 0.3908, "lr": 1.9438833303083677e-05, "epoch": 0.392993145468393, "percentage": 19.72, "elapsed_time": "1:31:20", "remaining_time": "6:11:44"}
+{"current_steps": 44, "total_steps": 218, "loss": 0.3628, "lr": 1.9384684220497605e-05, "epoch": 0.4021325209444021, "percentage": 20.18, "elapsed_time": "1:32:43", "remaining_time": "6:06:40"}
+{"current_steps": 45, "total_steps": 218, "loss": 0.4, "lr": 1.932812413370265e-05, "epoch": 0.4112718964204113, "percentage": 20.64, "elapsed_time": "1:34:59", "remaining_time": "6:05:12"}
+{"current_steps": 46, "total_steps": 218, "loss": 0.3682, "lr": 1.926916757346022e-05, "epoch": 0.4204112718964204, "percentage": 21.1, "elapsed_time": "1:36:52", "remaining_time": "6:02:14"}
+{"current_steps": 47, "total_steps": 218, "loss": 0.3611, "lr": 1.9207829686205882e-05, "epoch": 0.42955064737242954, "percentage": 21.56, "elapsed_time": "1:38:49", "remaining_time": "5:59:32"}
+{"current_steps": 48, "total_steps": 218, "loss": 0.38, "lr": 1.9144126230158127e-05, "epoch": 0.43869002284843867, "percentage": 22.02, "elapsed_time": "1:40:33", "remaining_time": "5:56:09"}
+{"current_steps": 49, "total_steps": 218, "loss": 0.3617, "lr": 1.9078073571269922e-05, "epoch": 0.44782939832444785, "percentage": 22.48, "elapsed_time": "1:42:30", "remaining_time": "5:53:32"}
+{"current_steps": 50, "total_steps": 218, "loss": 0.3647, "lr": 1.900968867902419e-05, "epoch": 0.456968773800457, "percentage": 22.94, "elapsed_time": "1:45:03", "remaining_time": "5:53:00"}
+{"current_steps": 51, "total_steps": 218, "loss": 0.3712, "lr": 1.8938989122074195e-05, "epoch": 0.4661081492764661, "percentage": 23.39, "elapsed_time": "1:50:31", "remaining_time": "6:01:55"}
+{"current_steps": 52, "total_steps": 218, "loss": 0.3846, "lr": 1.8865993063730003e-05, "epoch": 0.4752475247524752, "percentage": 23.85, "elapsed_time": "1:52:45", "remaining_time": "5:59:57"}
+{"current_steps": 53, "total_steps": 218, "loss": 0.3888, "lr": 1.8790719257292175e-05, "epoch": 0.4843869002284844, "percentage": 24.31, "elapsed_time": "1:55:26", "remaining_time": "5:59:22"}
+{"current_steps": 54, "total_steps": 218, "loss": 0.3819, "lr": 1.8713187041233896e-05, "epoch": 0.49352627570449353, "percentage": 24.77, "elapsed_time": "1:57:50", "remaining_time": "5:57:52"}
+{"current_steps": 55, "total_steps": 218, "loss": 0.3617, "lr": 1.8633416334232754e-05, "epoch": 0.5026656511805027, "percentage": 25.23, "elapsed_time": "1:59:50", "remaining_time": "5:55:09"}
+{"current_steps": 56, "total_steps": 218, "loss": 0.388, "lr": 1.8551427630053464e-05, "epoch": 0.5118050266565118, "percentage": 25.69, "elapsed_time": "2:01:56", "remaining_time": "5:52:45"}
+{"current_steps": 57, "total_steps": 218, "loss": 0.347, "lr": 1.8467241992282842e-05, "epoch": 0.5209444021325209, "percentage": 26.15, "elapsed_time": "2:04:08", "remaining_time": "5:50:37"}
+{"current_steps": 58, "total_steps": 218, "loss": 0.3736, "lr": 1.8380881048918406e-05, "epoch": 0.5300837776085301, "percentage": 26.61, "elapsed_time": "2:07:00", "remaining_time": "5:50:21"}
+{"current_steps": 59, "total_steps": 218, "loss": 0.3512, "lr": 1.8292366986811952e-05, "epoch": 0.5392231530845393, "percentage": 27.06, "elapsed_time": "2:09:12", "remaining_time": "5:48:12"}
+{"current_steps": 60, "total_steps": 218, "loss": 0.368, "lr": 1.820172254596956e-05, "epoch": 0.5483625285605483, "percentage": 27.52, "elapsed_time": "2:11:19", "remaining_time": "5:45:49"}
+{"current_steps": 61, "total_steps": 218, "loss": 0.3564, "lr": 1.8108971013709512e-05, "epoch": 0.5575019040365575, "percentage": 27.98, "elapsed_time": "2:12:49", "remaining_time": "5:41:50"}
+{"current_steps": 62, "total_steps": 218, "loss": 0.3577, "lr": 1.8014136218679566e-05, "epoch": 0.5666412795125666, "percentage": 28.44, "elapsed_time": "2:14:51", "remaining_time": "5:39:18"}
+{"current_steps": 63, "total_steps": 218, "loss": 0.3557, "lr": 1.79172425247352e-05, "epoch": 0.5757806549885758, "percentage": 28.9, "elapsed_time": "2:17:01", "remaining_time": "5:37:06"}
+{"current_steps": 64, "total_steps": 218, "loss": 0.355, "lr": 1.78183148246803e-05, "epoch": 0.584920030464585, "percentage": 29.36, "elapsed_time": "2:19:13", "remaining_time": "5:35:01"}
+{"current_steps": 65, "total_steps": 218, "loss": 0.3674, "lr": 1.771737853387202e-05, "epoch": 0.594059405940594, "percentage": 29.82, "elapsed_time": "2:21:52", "remaining_time": "5:33:56"}
+{"current_steps": 66, "total_steps": 218, "loss": 0.3697, "lr": 1.7614459583691346e-05, "epoch": 0.6031987814166032, "percentage": 30.28, "elapsed_time": "2:23:59", "remaining_time": "5:31:37"}
+{"current_steps": 67, "total_steps": 218, "loss": 0.3642, "lr": 1.7509584414881114e-05, "epoch": 0.6123381568926123, "percentage": 30.73, "elapsed_time": "2:26:42", "remaining_time": "5:30:38"}
+{"current_steps": 68, "total_steps": 218, "loss": 0.3709, "lr": 1.7402779970753156e-05, "epoch": 0.6214775323686215, "percentage": 31.19, "elapsed_time": "2:29:21", "remaining_time": "5:29:29"}
+{"current_steps": 69, "total_steps": 218, "loss": 0.3777, "lr": 1.7294073690266343e-05, "epoch": 0.6306169078446306, "percentage": 31.65, "elapsed_time": "2:31:15", "remaining_time": "5:26:37"}
+{"current_steps": 70, "total_steps": 218, "loss": 0.363, "lr": 1.7183493500977277e-05, "epoch": 0.6397562833206397, "percentage": 32.11, "elapsed_time": "2:33:31", "remaining_time": "5:24:35"}
+{"current_steps": 71, "total_steps": 218, "loss": 0.3622, "lr": 1.7071067811865477e-05, "epoch": 0.6488956587966489, "percentage": 32.57, "elapsed_time": "2:36:21", "remaining_time": "5:23:44"}
+{"current_steps": 72, "total_steps": 218, "loss": 0.3548, "lr": 1.6956825506034866e-05, "epoch": 0.6580350342726581, "percentage": 33.03, "elapsed_time": "2:38:11", "remaining_time": "5:20:46"}
+{"current_steps": 73, "total_steps": 218, "loss": 0.3542, "lr": 1.6840795933293464e-05, "epoch": 0.6671744097486672, "percentage": 33.49, "elapsed_time": "2:40:21", "remaining_time": "5:18:31"}
+{"current_steps": 74, "total_steps": 218, "loss": 0.352, "lr": 1.672300890261317e-05, "epoch": 0.6763137852246763, "percentage": 33.94, "elapsed_time": "2:42:15", "remaining_time": "5:15:45"}
+{"current_steps": 75, "total_steps": 218, "loss": 0.349, "lr": 1.6603494674471595e-05, "epoch": 0.6854531607006854, "percentage": 34.4, "elapsed_time": "2:44:46", "remaining_time": "5:14:10"}
+{"current_steps": 76, "total_steps": 218, "loss": 0.3724, "lr": 1.6482283953077887e-05, "epoch": 0.6945925361766946, "percentage": 34.86, "elapsed_time": "2:46:37", "remaining_time": "5:11:18"}
+{"current_steps": 77, "total_steps": 218, "loss": 0.351, "lr": 1.635940787848455e-05, "epoch": 0.7037319116527038, "percentage": 35.32, "elapsed_time": "2:48:19", "remaining_time": "5:08:13"}
+{"current_steps": 78, "total_steps": 218, "loss": 0.3545, "lr": 1.6234898018587336e-05, "epoch": 0.7128712871287128, "percentage": 35.78, "elapsed_time": "2:50:33", "remaining_time": "5:06:08"}
+{"current_steps": 79, "total_steps": 218, "loss": 0.3457, "lr": 1.6108786361015145e-05, "epoch": 0.722010662604722, "percentage": 36.24, "elapsed_time": "2:52:16", "remaining_time": "5:03:06"}
+{"current_steps": 80, "total_steps": 218, "loss": 0.3836, "lr": 1.598110530491216e-05, "epoch": 0.7311500380807312, "percentage": 36.7, "elapsed_time": "2:54:56", "remaining_time": "5:01:46"}
+{"current_steps": 81, "total_steps": 218, "loss": 0.3657, "lr": 1.5851887652614238e-05, "epoch": 0.7402894135567403, "percentage": 37.16, "elapsed_time": "2:56:52", "remaining_time": "4:59:10"}
+{"current_steps": 82, "total_steps": 218, "loss": 0.378, "lr": 1.5721166601221697e-05, "epoch": 0.7494287890327495, "percentage": 37.61, "elapsed_time": "2:59:08", "remaining_time": "4:57:06"}
+{"current_steps": 83, "total_steps": 218, "loss": 0.3493, "lr": 1.5588975734070717e-05, "epoch": 0.7585681645087585, "percentage": 38.07, "elapsed_time": "3:00:54", "remaining_time": "4:54:15"}
+{"current_steps": 84, "total_steps": 218, "loss": 0.3632, "lr": 1.5455349012105488e-05, "epoch": 0.7677075399847677, "percentage": 38.53, "elapsed_time": "3:03:07", "remaining_time": "4:52:07"}
+{"current_steps": 85, "total_steps": 218, "loss": 0.3601, "lr": 1.5320320765153367e-05, "epoch": 0.7768469154607769, "percentage": 38.99, "elapsed_time": "3:05:36", "remaining_time": "4:50:24"}
+{"current_steps": 86, "total_steps": 218, "loss": 0.3614, "lr": 1.5183925683105254e-05, "epoch": 0.785986290936786, "percentage": 39.45, "elapsed_time": "3:07:49", "remaining_time": "4:48:16"}
+{"current_steps": 87, "total_steps": 218, "loss": 0.3585, "lr": 1.504619880700346e-05, "epoch": 0.7951256664127951, "percentage": 39.91, "elapsed_time": "3:09:26", "remaining_time": "4:45:14"}
+{"current_steps": 88, "total_steps": 218, "loss": 0.3538, "lr": 1.4907175520039381e-05, "epoch": 0.8042650418888042, "percentage": 40.37, "elapsed_time": "3:11:59", "remaining_time": "4:43:37"}
+{"current_steps": 89, "total_steps": 218, "loss": 0.3529, "lr": 1.4766891538463255e-05, "epoch": 0.8134044173648134, "percentage": 40.83, "elapsed_time": "3:13:47", "remaining_time": "4:40:53"}
+{"current_steps": 90, "total_steps": 218, "loss": 0.3488, "lr": 1.4625382902408356e-05, "epoch": 0.8225437928408226, "percentage": 41.28, "elapsed_time": "3:15:54", "remaining_time": "4:38:37"}
+{"current_steps": 91, "total_steps": 218, "loss": 0.343, "lr": 1.448268596663197e-05, "epoch": 0.8316831683168316, "percentage": 41.74, "elapsed_time": "3:18:02", "remaining_time": "4:36:23"}
+{"current_steps": 92, "total_steps": 218, "loss": 0.3577, "lr": 1.4338837391175582e-05, "epoch": 0.8408225437928408, "percentage": 42.2, "elapsed_time": "3:20:35", "remaining_time": "4:34:43"}
+{"current_steps": 93, "total_steps": 218, "loss": 0.3437, "lr": 1.419387413194657e-05, "epoch": 0.84996191926885, "percentage": 42.66, "elapsed_time": "3:22:19", "remaining_time": "4:31:56"}
+{"current_steps": 94, "total_steps": 218, "loss": 0.3504, "lr": 1.4047833431223938e-05, "epoch": 0.8591012947448591, "percentage": 43.12, "elapsed_time": "3:24:41", "remaining_time": "4:30:00"}
+{"current_steps": 95, "total_steps": 218, "loss": 0.3517, "lr": 1.390075280809047e-05, "epoch": 0.8682406702208683, "percentage": 43.58, "elapsed_time": "3:26:44", "remaining_time": "4:27:40"}
+{"current_steps": 96, "total_steps": 218, "loss": 0.3507, "lr": 1.3752670048793744e-05, "epoch": 0.8773800456968773, "percentage": 44.04, "elapsed_time": "3:28:51", "remaining_time": "4:25:25"}
+{"current_steps": 97, "total_steps": 218, "loss": 0.3563, "lr": 1.3603623197038536e-05, "epoch": 0.8865194211728865, "percentage": 44.5, "elapsed_time": "3:30:53", "remaining_time": "4:23:04"}
+{"current_steps": 98, "total_steps": 218, "loss": 0.3648, "lr": 1.3453650544213078e-05, "epoch": 0.8956587966488957, "percentage": 44.95, "elapsed_time": "3:33:30", "remaining_time": "4:21:26"}
+{"current_steps": 99, "total_steps": 218, "loss": 0.3407, "lr": 1.3302790619551673e-05, "epoch": 0.9047981721249048, "percentage": 45.41, "elapsed_time": "3:35:24", "remaining_time": "4:18:55"}
+{"current_steps": 100, "total_steps": 218, "loss": 0.355, "lr": 1.315108218023621e-05, "epoch": 0.913937547600914, "percentage": 45.87, "elapsed_time": "3:37:22", "remaining_time": "4:16:29"}
+{"current_steps": 101, "total_steps": 218, "loss": 0.3581, "lr": 1.2998564201439117e-05, "epoch": 0.9230769230769231, "percentage": 46.33, "elapsed_time": "3:42:09", "remaining_time": "4:17:20"}
+{"current_steps": 101, "total_steps": 218, "loss": 0.3581, "lr": 1.2998564201439117e-05, "epoch": 0.9230769230769231, "percentage": 46.33, "elapsed_time": "0:01:56", "remaining_time": "0:02:14"}
+{"current_steps": 102, "total_steps": 218, "loss": 0.3549, "lr": 1.2845275866310325e-05, "epoch": 0.9322162985529322, "percentage": 46.79, "elapsed_time": "0:04:17", "remaining_time": "0:04:52"}
+{"current_steps": 103, "total_steps": 218, "loss": 0.3503, "lr": 1.2691256555910769e-05, "epoch": 0.9413556740289414, "percentage": 47.25, "elapsed_time": "0:06:05", "remaining_time": "0:06:48"}
+{"current_steps": 104, "total_steps": 218, "loss": 0.3678, "lr": 1.2536545839095074e-05, "epoch": 0.9504950495049505, "percentage": 47.71, "elapsed_time": "0:08:39", "remaining_time": "0:09:28"}
+{"current_steps": 105, "total_steps": 218, "loss": 0.3529, "lr": 1.2381183462345983e-05, "epoch": 0.9596344249809596, "percentage": 48.17, "elapsed_time": "0:10:44", "remaining_time": "0:11:33"}
+{"current_steps": 106, "total_steps": 218, "loss": 0.3513, "lr": 1.2225209339563144e-05, "epoch": 0.9687738004569688, "percentage": 48.62, "elapsed_time": "0:13:03", "remaining_time": "0:13:47"}
+{"current_steps": 107, "total_steps": 218, "loss": 0.3508, "lr": 1.206866354180891e-05, "epoch": 0.9779131759329779, "percentage": 49.08, "elapsed_time": "0:15:30", "remaining_time": "0:16:04"}
+{"current_steps": 108, "total_steps": 218, "loss": 0.3553, "lr": 1.1911586287013726e-05, "epoch": 0.9870525514089871, "percentage": 49.54, "elapsed_time": "0:17:44", "remaining_time": "0:18:04"}
+{"current_steps": 109, "total_steps": 218, "loss": 0.3504, "lr": 1.1754017929643818e-05, "epoch": 0.9961919268849961, "percentage": 50.0, "elapsed_time": "0:19:26", "remaining_time": "0:19:26"}
+{"current_steps": 110, "total_steps": 218, "loss": 0.504, "lr": 1.1595998950333794e-05, "epoch": 1.0053313023610053, "percentage": 50.46, "elapsed_time": "0:21:31", "remaining_time": "0:21:08"}
+{"current_steps": 111, "total_steps": 218, "loss": 0.3248, "lr": 1.143756994548682e-05, "epoch": 1.0144706778370145, "percentage": 50.92, "elapsed_time": "0:23:55", "remaining_time": "0:23:04"}
+{"current_steps": 112, "total_steps": 218, "loss": 0.3143, "lr": 1.1278771616845061e-05, "epoch": 1.0236100533130237, "percentage": 51.38, "elapsed_time": "0:26:20", "remaining_time": "0:24:56"}
+{"current_steps": 113, "total_steps": 218, "loss": 0.3108, "lr": 1.1119644761033079e-05, "epoch": 1.0327494287890326, "percentage": 51.83, "elapsed_time": "0:29:06", "remaining_time": "0:27:02"}
+{"current_steps": 114, "total_steps": 218, "loss": 0.3024, "lr": 1.0960230259076819e-05, "epoch": 1.0418888042650418, "percentage": 52.29, "elapsed_time": "0:31:15", "remaining_time": "0:28:31"}
+{"current_steps": 115, "total_steps": 218, "loss": 0.3275, "lr": 1.0800569065900935e-05, "epoch": 1.051028179741051, "percentage": 52.75, "elapsed_time": "0:33:50", "remaining_time": "0:30:18"}
+{"current_steps": 116, "total_steps": 218, "loss": 0.2905, "lr": 1.064070219980713e-05, "epoch": 1.0601675552170602, "percentage": 53.21, "elapsed_time": "0:35:42", "remaining_time": "0:31:23"}
+{"current_steps": 117, "total_steps": 218, "loss": 0.2874, "lr": 1.0480670731936209e-05, "epoch": 1.0693069306930694, "percentage": 53.67, "elapsed_time": "0:38:07", "remaining_time": "0:32:54"}
+{"current_steps": 118, "total_steps": 218, "loss": 0.2786, "lr": 1.0320515775716556e-05, "epoch": 1.0784463061690786, "percentage": 54.13, "elapsed_time": "0:40:14", "remaining_time": "0:34:06"}
+{"current_steps": 119, "total_steps": 218, "loss": 0.3472, "lr": 1.0160278476301739e-05, "epoch": 1.0875856816450875, "percentage": 54.59, "elapsed_time": "0:42:29", "remaining_time": "0:35:21"}
+{"current_steps": 120, "total_steps": 218, "loss": 0.3031, "lr": 1e-05, "epoch": 1.0967250571210967, "percentage": 55.05, "elapsed_time": "0:44:55", "remaining_time": "0:36:41"}
+{"current_steps": 121, "total_steps": 218, "loss": 0.2416, "lr": 9.839721523698265e-06, "epoch": 1.1058644325971059, "percentage": 55.5, "elapsed_time": "0:46:25", "remaining_time": "0:37:12"}
+{"current_steps": 122, "total_steps": 218, "loss": 0.329, "lr": 9.67948422428345e-06, "epoch": 1.115003808073115, "percentage": 55.96, "elapsed_time": "0:48:44", "remaining_time": "0:38:21"}
+{"current_steps": 123, "total_steps": 218, "loss": 0.3184, "lr": 9.519329268063795e-06, "epoch": 1.1241431835491242, "percentage": 56.42, "elapsed_time": "0:51:10", "remaining_time": "0:39:31"}
+{"current_steps": 124, "total_steps": 218, "loss": 0.287, "lr": 9.359297800192873e-06, "epoch": 1.1332825590251332, "percentage": 56.88, "elapsed_time": "0:53:06", "remaining_time": "0:40:15"}
+{"current_steps": 125, "total_steps": 218, "loss": 0.2848, "lr": 9.199430934099068e-06, "epoch": 1.1424219345011424, "percentage": 57.34, "elapsed_time": "0:55:00", "remaining_time": "0:40:55"}
+{"current_steps": 126, "total_steps": 218, "loss": 0.2797, "lr": 9.039769740923183e-06, "epoch": 1.1515613099771516, "percentage": 57.8, "elapsed_time": "0:57:20", "remaining_time": "0:41:51"}
+{"current_steps": 127, "total_steps": 218, "loss": 0.2905, "lr": 8.880355238966923e-06, "epoch": 1.1607006854531607, "percentage": 58.26, "elapsed_time": "0:59:17", "remaining_time": "0:42:29"}
+{"current_steps": 128, "total_steps": 218, "loss": 0.2996, "lr": 8.721228383154939e-06, "epoch": 1.16984006092917, "percentage": 58.72, "elapsed_time": "1:02:14", "remaining_time": "0:43:45"}
+{"current_steps": 129, "total_steps": 218, "loss": 0.2955, "lr": 8.562430054513184e-06, "epoch": 1.178979436405179, "percentage": 59.17, "elapsed_time": "1:04:37", "remaining_time": "0:44:35"}
+{"current_steps": 130, "total_steps": 218, "loss": 0.2981, "lr": 8.404001049666211e-06, "epoch": 1.188118811881188, "percentage": 59.63, "elapsed_time": "1:06:37", "remaining_time": "0:45:06"}
+{"current_steps": 131, "total_steps": 218, "loss": 0.2779, "lr": 8.245982070356186e-06, "epoch": 1.1972581873571972, "percentage": 60.09, "elapsed_time": "1:08:59", "remaining_time": "0:45:49"}
+{"current_steps": 132, "total_steps": 218, "loss": 0.296, "lr": 8.08841371298628e-06, "epoch": 1.2063975628332064, "percentage": 60.55, "elapsed_time": "1:11:15", "remaining_time": "0:46:25"}
+{"current_steps": 133, "total_steps": 218, "loss": 0.3203, "lr": 7.931336458191092e-06, "epoch": 1.2155369383092156, "percentage": 61.01, "elapsed_time": "1:13:19", "remaining_time": "0:46:51"}
+{"current_steps": 134, "total_steps": 218, "loss": 0.2915, "lr": 7.774790660436857e-06, "epoch": 1.2246763137852246, "percentage": 61.47, "elapsed_time": "1:15:20", "remaining_time": "0:47:13"}
+{"current_steps": 135, "total_steps": 218, "loss": 0.2997, "lr": 7.618816537654018e-06, "epoch": 1.2338156892612338, "percentage": 61.93, "elapsed_time": "1:17:42", "remaining_time": "0:47:46"}
+{"current_steps": 136, "total_steps": 218, "loss": 0.2625, "lr": 7.463454160904928e-06, "epoch": 1.242955064737243, "percentage": 62.39, "elapsed_time": "1:19:56", "remaining_time": "0:48:12"}
+{"current_steps": 137, "total_steps": 218, "loss": 0.3042, "lr": 7.308743444089232e-06, "epoch": 1.2520944402132521, "percentage": 62.84, "elapsed_time": "1:22:07", "remaining_time": "0:48:33"}
+{"current_steps": 138, "total_steps": 218, "loss": 0.2775, "lr": 7.154724133689677e-06, "epoch": 1.2612338156892613, "percentage": 63.3, "elapsed_time": "1:24:28", "remaining_time": "0:48:58"}
+{"current_steps": 139, "total_steps": 218, "loss": 0.2996, "lr": 7.001435798560884e-06, "epoch": 1.2703731911652705, "percentage": 63.76, "elapsed_time": "1:26:51", "remaining_time": "0:49:22"}
+{"current_steps": 140, "total_steps": 218, "loss": 0.2816, "lr": 6.848917819763794e-06, "epoch": 1.2795125666412794, "percentage": 64.22, "elapsed_time": "1:29:02", "remaining_time": "0:49:36"}
+{"current_steps": 141, "total_steps": 218, "loss": 0.3098, "lr": 6.697209380448333e-06, "epoch": 1.2886519421172886, "percentage": 64.68, "elapsed_time": "1:31:00", "remaining_time": "0:49:41"}
+{"current_steps": 142, "total_steps": 218, "loss": 0.341, "lr": 6.546349455786926e-06, "epoch": 1.2977913175932978, "percentage": 65.14, "elapsed_time": "1:32:51", "remaining_time": "0:49:41"}
+{"current_steps": 143, "total_steps": 218, "loss": 0.2959, "lr": 6.396376802961468e-06, "epoch": 1.306930693069307, "percentage": 65.6, "elapsed_time": "1:35:01", "remaining_time": "0:49:50"}
+{"current_steps": 144, "total_steps": 218, "loss": 0.2829, "lr": 6.24732995120626e-06, "epoch": 1.316070068545316, "percentage": 66.06, "elapsed_time": "1:36:59", "remaining_time": "0:49:50"}
+{"current_steps": 145, "total_steps": 218, "loss": 0.281, "lr": 6.099247191909532e-06, "epoch": 1.3252094440213251, "percentage": 66.51, "elapsed_time": "1:38:46", "remaining_time": "0:49:43"}
+{"current_steps": 146, "total_steps": 218, "loss": 0.3167, "lr": 5.952166568776062e-06, "epoch": 1.3343488194973343, "percentage": 66.97, "elapsed_time": "1:41:17", "remaining_time": "0:49:57"}
+{"current_steps": 147, "total_steps": 218, "loss": 0.2687, "lr": 5.806125868053433e-06, "epoch": 1.3434881949733435, "percentage": 67.43, "elapsed_time": "1:43:11", "remaining_time": "0:49:50"}
+{"current_steps": 148, "total_steps": 218, "loss": 0.2788, "lr": 5.66116260882442e-06, "epoch": 1.3526275704493527, "percentage": 67.89, "elapsed_time": "1:45:01", "remaining_time": "0:49:40"}
+{"current_steps": 149, "total_steps": 218, "loss": 0.3039, "lr": 5.517314033368031e-06, "epoch": 1.3617669459253618, "percentage": 68.35, "elapsed_time": "1:47:17", "remaining_time": "0:49:40"}
+{"current_steps": 150, "total_steps": 218, "loss": 0.3076, "lr": 5.37461709759165e-06, "epoch": 1.370906321401371, "percentage": 68.81, "elapsed_time": "1:49:21", "remaining_time": "0:49:34"}
+{"current_steps": 151, "total_steps": 218, "loss": 0.3041, "lr": 5.233108461536749e-06, "epoch": 1.38004569687738, "percentage": 69.27, "elapsed_time": "1:54:49", "remaining_time": "0:50:56"}
+{"current_steps": 152, "total_steps": 218, "loss": 0.31, "lr": 5.092824479960625e-06, "epoch": 1.3891850723533892, "percentage": 69.72, "elapsed_time": "1:57:27", "remaining_time": "0:51:00"}
+{"current_steps": 153, "total_steps": 218, "loss": 0.3212, "lr": 4.9538011929965436e-06, "epoch": 1.3983244478293984, "percentage": 70.18, "elapsed_time": "1:59:51", "remaining_time": "0:50:55"}
+{"current_steps": 154, "total_steps": 218, "loss": 0.2922, "lr": 4.81607431689475e-06, "epoch": 1.4074638233054075, "percentage": 70.64, "elapsed_time": "2:01:50", "remaining_time": "0:50:38"}
+{"current_steps": 155, "total_steps": 218, "loss": 0.3107, "lr": 4.679679234846636e-06, "epoch": 1.4166031987814165, "percentage": 71.1, "elapsed_time": "2:04:01", "remaining_time": "0:50:24"}
+{"current_steps": 156, "total_steps": 218, "loss": 0.2697, "lr": 4.544650987894514e-06, "epoch": 1.4257425742574257, "percentage": 71.56, "elapsed_time": "2:05:49", "remaining_time": "0:50:00"}
+{"current_steps": 157, "total_steps": 218, "loss": 0.2905, "lr": 4.411024265929283e-06, "epoch": 1.4348819497334349, "percentage": 72.02, "elapsed_time": "2:07:43", "remaining_time": "0:49:37"}
+{"current_steps": 158, "total_steps": 218, "loss": 0.2548, "lr": 4.278833398778306e-06, "epoch": 1.444021325209444, "percentage": 72.48, "elapsed_time": "2:09:55", "remaining_time": "0:49:20"}
+{"current_steps": 159, "total_steps": 218, "loss": 0.3296, "lr": 4.148112347385762e-06, "epoch": 1.4531607006854532, "percentage": 72.94, "elapsed_time": "2:12:18", "remaining_time": "0:49:05"}
+{"current_steps": 160, "total_steps": 218, "loss": 0.2928, "lr": 4.01889469508784e-06, "epoch": 1.4623000761614624, "percentage": 73.39, "elapsed_time": "2:14:14", "remaining_time": "0:48:39"}
+{"current_steps": 161, "total_steps": 218, "loss": 0.3121, "lr": 3.891213638984858e-06, "epoch": 1.4714394516374714, "percentage": 73.85, "elapsed_time": "2:16:24", "remaining_time": "0:48:17"}
+{"current_steps": 162, "total_steps": 218, "loss": 0.267, "lr": 3.7651019814126656e-06, "epoch": 1.4805788271134805, "percentage": 74.31, "elapsed_time": "2:18:28", "remaining_time": "0:47:52"}
+{"current_steps": 163, "total_steps": 218, "loss": 0.3175, "lr": 3.6405921215154492e-06, "epoch": 1.4897182025894897, "percentage": 74.77, "elapsed_time": "2:20:44", "remaining_time": "0:47:29"}
+{"current_steps": 164, "total_steps": 218, "loss": 0.2985, "lr": 3.5177160469221184e-06, "epoch": 1.498857578065499, "percentage": 75.23, "elapsed_time": "2:23:12", "remaining_time": "0:47:09"}
+{"current_steps": 165, "total_steps": 218, "loss": 0.2619, "lr": 3.3965053255284085e-06, "epoch": 1.5079969535415079, "percentage": 75.69, "elapsed_time": "2:25:21", "remaining_time": "0:46:41"}
+{"current_steps": 166, "total_steps": 218, "loss": 0.3191, "lr": 3.2769910973868314e-06, "epoch": 1.517136329017517, "percentage": 76.15, "elapsed_time": "2:27:22", "remaining_time": "0:46:09"}
+{"current_steps": 167, "total_steps": 218, "loss": 0.2744, "lr": 3.1592040667065393e-06, "epoch": 1.5262757044935262, "percentage": 76.61, "elapsed_time": "2:29:21", "remaining_time": "0:45:36"}
+{"current_steps": 168, "total_steps": 218, "loss": 0.3138, "lr": 3.0431744939651365e-06, "epoch": 1.5354150799695354, "percentage": 77.06, "elapsed_time": "2:31:48", "remaining_time": "0:45:10"}
+{"current_steps": 169, "total_steps": 218, "loss": 0.2748, "lr": 2.9289321881345257e-06, "epoch": 1.5445544554455446, "percentage": 77.52, "elapsed_time": "2:33:40", "remaining_time": "0:44:33"}
+{"current_steps": 170, "total_steps": 218, "loss": 0.2931, "lr": 2.8165064990227255e-06, "epoch": 1.5536938309215538, "percentage": 77.98, "elapsed_time": "2:35:43", "remaining_time": "0:43:58"}
+{"current_steps": 171, "total_steps": 218, "loss": 0.3322, "lr": 2.7059263097336595e-06, "epoch": 1.562833206397563, "percentage": 78.44, "elapsed_time": "2:38:36", "remaining_time": "0:43:35"}
+{"current_steps": 172, "total_steps": 218, "loss": 0.3208, "lr": 2.597220029246846e-06, "epoch": 1.5719725818735721, "percentage": 78.9, "elapsed_time": "2:40:54", "remaining_time": "0:43:02"}
+{"current_steps": 173, "total_steps": 218, "loss": 0.2542, "lr": 2.490415585118887e-06, "epoch": 1.581111957349581, "percentage": 79.36, "elapsed_time": "2:42:38", "remaining_time": "0:42:18"}
+{"current_steps": 174, "total_steps": 218, "loss": 0.3102, "lr": 2.3855404163086558e-06, "epoch": 1.5902513328255903, "percentage": 79.82, "elapsed_time": "2:44:20", "remaining_time": "0:41:33"}
+{"current_steps": 175, "total_steps": 218, "loss": 0.2608, "lr": 2.282621466127982e-06, "epoch": 1.5993907083015992, "percentage": 80.28, "elapsed_time": "2:46:04", "remaining_time": "0:40:48"}
+{"current_steps": 176, "total_steps": 218, "loss": 0.2785, "lr": 2.1816851753197023e-06, "epoch": 1.6085300837776084, "percentage": 80.73, "elapsed_time": "2:47:55", "remaining_time": "0:40:04"}
+{"current_steps": 177, "total_steps": 218, "loss": 0.3116, "lr": 2.082757475264804e-06, "epoch": 1.6176694592536176, "percentage": 81.19, "elapsed_time": "2:50:17", "remaining_time": "0:39:26"}
+{"current_steps": 178, "total_steps": 218, "loss": 0.256, "lr": 1.9858637813204352e-06, "epoch": 1.6268088347296268, "percentage": 81.65, "elapsed_time": "2:52:24", "remaining_time": "0:38:44"}
+{"current_steps": 179, "total_steps": 218, "loss": 0.3598, "lr": 1.8910289862904917e-06, "epoch": 1.635948210205636, "percentage": 82.11, "elapsed_time": "2:55:15", "remaining_time": "0:38:10"}
+{"current_steps": 180, "total_steps": 218, "loss": 0.2526, "lr": 1.7982774540304404e-06, "epoch": 1.6450875856816451, "percentage": 82.57, "elapsed_time": "2:56:54", "remaining_time": "0:37:20"}
+{"current_steps": 181, "total_steps": 218, "loss": 0.2885, "lr": 1.7076330131880525e-06, "epoch": 1.6542269611576543, "percentage": 83.03, "elapsed_time": "2:59:11", "remaining_time": "0:36:37"}
+{"current_steps": 182, "total_steps": 218, "loss": 0.3314, "lr": 1.6191189510815942e-06, "epoch": 1.6633663366336635, "percentage": 83.49, "elapsed_time": "3:02:02", "remaining_time": "0:36:00"}
+{"current_steps": 183, "total_steps": 218, "loss": 0.2691, "lr": 1.5327580077171589e-06, "epoch": 1.6725057121096725, "percentage": 83.94, "elapsed_time": "3:04:22", "remaining_time": "0:35:15"}
+{"current_steps": 184, "total_steps": 218, "loss": 0.3184, "lr": 1.4485723699465392e-06, "epoch": 1.6816450875856817, "percentage": 84.4, "elapsed_time": "3:06:23", "remaining_time": "0:34:26"}
+{"current_steps": 185, "total_steps": 218, "loss": 0.2783, "lr": 1.3665836657672493e-06, "epoch": 1.6907844630616908, "percentage": 84.86, "elapsed_time": "3:08:16", "remaining_time": "0:33:35"}
+{"current_steps": 186, "total_steps": 218, "loss": 0.3252, "lr": 1.286812958766106e-06, "epoch": 1.6999238385376998, "percentage": 85.32, "elapsed_time": "3:10:55", "remaining_time": "0:32:50"}
+{"current_steps": 187, "total_steps": 218, "loss": 0.2988, "lr": 1.209280742707828e-06, "epoch": 1.709063214013709, "percentage": 85.78, "elapsed_time": "3:12:53", "remaining_time": "0:31:58"}
+{"current_steps": 188, "total_steps": 218, "loss": 0.3029, "lr": 1.134006936269999e-06, "epoch": 1.7182025894897182, "percentage": 86.24, "elapsed_time": "3:14:40", "remaining_time": "0:31:03"}
+{"current_steps": 189, "total_steps": 218, "loss": 0.2904, "lr": 1.0610108779258043e-06, "epoch": 1.7273419649657273, "percentage": 86.7, "elapsed_time": "3:16:52", "remaining_time": "0:30:12"}
+{"current_steps": 190, "total_steps": 218, "loss": 0.3059, "lr": 9.903113209758098e-07, "epoch": 1.7364813404417365, "percentage": 87.16, "elapsed_time": "3:18:52", "remaining_time": "0:29:18"}
+{"current_steps": 191, "total_steps": 218, "loss": 0.292, "lr": 9.2192642873008e-07, "epoch": 1.7456207159177457, "percentage": 87.61, "elapsed_time": "3:21:02", "remaining_time": "0:28:25"}
+{"current_steps": 192, "total_steps": 218, "loss": 0.287, "lr": 8.558737698418762e-07, "epoch": 1.7547600913937549, "percentage": 88.07, "elapsed_time": "3:23:20", "remaining_time": "0:27:32"}
+{"current_steps": 193, "total_steps": 218, "loss": 0.2916, "lr": 7.921703137941172e-07, "epoch": 1.763899466869764, "percentage": 88.53, "elapsed_time": "3:25:14", "remaining_time": "0:26:35"}
+{"current_steps": 194, "total_steps": 218, "loss": 0.2847, "lr": 7.308324265397837e-07, "epoch": 1.773038842345773, "percentage": 88.99, "elapsed_time": "3:27:19", "remaining_time": "0:25:38"}
+{"current_steps": 195, "total_steps": 218, "loss": 0.2842, "lr": 6.718758662973524e-07, "epoch": 1.7821782178217822, "percentage": 89.45, "elapsed_time": "3:29:48", "remaining_time": "0:24:44"}
+{"current_steps": 196, "total_steps": 218, "loss": 0.3169, "lr": 6.153157795023956e-07, "epoch": 1.7913175932977912, "percentage": 89.91, "elapsed_time": "3:32:19", "remaining_time": "0:23:49"}
+{"current_steps": 197, "total_steps": 218, "loss": 0.3155, "lr": 5.611666969163243e-07, "epoch": 1.8004569687738003, "percentage": 90.37, "elapsed_time": "3:34:51", "remaining_time": "0:22:54"}
+{"current_steps": 198, "total_steps": 218, "loss": 0.2952, "lr": 5.094425298933136e-07, "epoch": 1.8095963442498095, "percentage": 90.83, "elapsed_time": "3:37:09", "remaining_time": "0:21:56"}
+{"current_steps": 199, "total_steps": 218, "loss": 0.3076, "lr": 4.6015656680636234e-07, "epoch": 1.8187357197258187, "percentage": 91.28, "elapsed_time": "3:39:26", "remaining_time": "0:20:57"}
+{"current_steps": 200, "total_steps": 218, "loss": 0.3001, "lr": 4.133214696333943e-07, "epoch": 1.827875095201828, "percentage": 91.74, "elapsed_time": "3:41:43", "remaining_time": "0:19:57"}
+{"current_steps": 201, "total_steps": 218, "loss": 0.2858, "lr": 3.6894927070429744e-07, "epoch": 1.837014470677837, "percentage": 92.2, "elapsed_time": "3:46:32", "remaining_time": "0:19:09"}
+{"current_steps": 202, "total_steps": 218, "loss": 0.3157, "lr": 3.2705136960970554e-07, "epoch": 1.8461538461538463, "percentage": 92.66, "elapsed_time": "3:48:47", "remaining_time": "0:18:07"}
+{"current_steps": 203, "total_steps": 218, "loss": 0.29, "lr": 2.8763853027236277e-07, "epoch": 1.8552932216298554, "percentage": 93.12, "elapsed_time": "3:50:51", "remaining_time": "0:17:03"}
+{"current_steps": 201, "total_steps": 218, "loss": 0.3034, "lr": 3.6894927070429744e-07, "epoch": 1.8408225437928407, "percentage": 92.2, "elapsed_time": "0:01:57", "remaining_time": "0:00:09"}
+{"current_steps": 202, "total_steps": 218, "loss": 0.2986, "lr": 3.2705136960970554e-07, "epoch": 1.84996191926885, "percentage": 92.66, "elapsed_time": "0:04:20", "remaining_time": "0:00:20"}
+{"current_steps": 203, "total_steps": 218, "loss": 0.3022, "lr": 2.8763853027236277e-07, "epoch": 1.859101294744859, "percentage": 93.12, "elapsed_time": "0:06:09", "remaining_time": "0:00:27"}
+{"current_steps": 204, "total_steps": 218, "loss": 0.2878, "lr": 2.507208781817638e-07, "epoch": 1.8682406702208683, "percentage": 93.58, "elapsed_time": "0:08:06", "remaining_time": "0:00:33"}
+{"current_steps": 205, "total_steps": 218, "loss": 0.2957, "lr": 2.1630789779284677e-07, "epoch": 1.8773800456968774, "percentage": 94.04, "elapsed_time": "0:10:05", "remaining_time": "0:00:38"}
+{"current_steps": 206, "total_steps": 218, "loss": 0.2913, "lr": 1.844084300893456e-07, "epoch": 1.8865194211728866, "percentage": 94.5, "elapsed_time": "0:12:30", "remaining_time": "0:00:43"}
+{"current_steps": 207, "total_steps": 218, "loss": 0.3051, "lr": 1.55030670312476e-07, "epoch": 1.8956587966488958, "percentage": 94.95, "elapsed_time": "0:14:56", "remaining_time": "0:00:47"}
+{"current_steps": 208, "total_steps": 218, "loss": 0.2968, "lr": 1.2818216585549824e-07, "epoch": 1.9047981721249048, "percentage": 95.41, "elapsed_time": "0:17:32", "remaining_time": "0:00:50"}
+{"current_steps": 209, "total_steps": 218, "loss": 0.3034, "lr": 1.0386981432474075e-07, "epoch": 1.913937547600914, "percentage": 95.87, "elapsed_time": "0:19:45", "remaining_time": "0:00:51"}
+{"current_steps": 210, "total_steps": 218, "loss": 0.2934, "lr": 8.209986176753947e-08, "epoch": 1.9230769230769231, "percentage": 96.33, "elapsed_time": "0:21:48", "remaining_time": "0:00:49"}
+{"current_steps": 211, "total_steps": 218, "loss": 0.3107, "lr": 6.287790106757396e-08, "epoch": 1.932216298552932, "percentage": 96.79, "elapsed_time": "0:24:16", "remaining_time": "0:00:48"}
+{"current_steps": 212, "total_steps": 218, "loss": 0.2925, "lr": 4.6208870508017703e-08, "epoch": 1.9413556740289413, "percentage": 97.25, "elapsed_time": "0:26:17", "remaining_time": "0:00:44"}
+{"current_steps": 213, "total_steps": 218, "loss": 0.2911, "lr": 3.2097052502843005e-08, "epoch": 1.9504950495049505, "percentage": 97.71, "elapsed_time": "0:28:52", "remaining_time": "0:00:40"}
+{"current_steps": 214, "total_steps": 218, "loss": 0.2823, "lr": 2.054607249663665e-08, "epoch": 1.9596344249809596, "percentage": 98.17, "elapsed_time": "0:30:48", "remaining_time": "0:00:34"}
+{"current_steps": 215, "total_steps": 218, "loss": 0.3068, "lr": 1.1558898033191545e-08, "epoch": 1.9687738004569688, "percentage": 98.62, "elapsed_time": "0:33:09", "remaining_time": "0:00:27"}
+{"current_steps": 216, "total_steps": 218, "loss": 0.3039, "lr": 5.137837993121064e-09, "epoch": 1.977913175932978, "percentage": 99.08, "elapsed_time": "0:35:12", "remaining_time": "0:00:19"}
+{"current_steps": 217, "total_steps": 218, "loss": 0.2965, "lr": 1.2845420006879494e-09, "epoch": 1.9870525514089872, "percentage": 99.54, "elapsed_time": "0:37:23", "remaining_time": "0:00:10"}
+{"current_steps": 218, "total_steps": 218, "loss": 0.298, "lr": 0.0, "epoch": 1.9961919268849961, "percentage": 100.0, "elapsed_time": "0:39:40", "remaining_time": "0:00:00"}
+{"current_steps": 218, "total_steps": 218, "epoch": 1.9961919268849961, "percentage": 100.0, "elapsed_time": "0:42:40", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,1568 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.9961919268849961,
+  "eval_steps": 500,
+  "global_step": 218,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.00913937547600914,
+      "grad_norm": 3.0662612915039062,
+      "learning_rate": 9.090909090909091e-07,
+      "loss": 0.6539,
+      "step": 1
+    },
+    {
+      "epoch": 0.01827875095201828,
+      "grad_norm": 3.0926544666290283,
+      "learning_rate": 1.8181818181818183e-06,
+      "loss": 0.6614,
+      "step": 2
+    },
+    {
+      "epoch": 0.027418126428027417,
+      "grad_norm": 3.0256407260894775,
+      "learning_rate": 2.7272727272727272e-06,
+      "loss": 0.6435,
+      "step": 3
+    },
+    {
+      "epoch": 0.03655750190403656,
+      "grad_norm": 2.8626863956451416,
+      "learning_rate": 3.6363636363636366e-06,
+      "loss": 0.6528,
+      "step": 4
+    },
+    {
+      "epoch": 0.0456968773800457,
+      "grad_norm": 2.3245227336883545,
+      "learning_rate": 4.5454545454545455e-06,
+      "loss": 0.6292,
+      "step": 5
+    },
+    {
+      "epoch": 0.05483625285605483,
+      "grad_norm": 1.6400835514068604,
+      "learning_rate": 5.4545454545454545e-06,
+      "loss": 0.6013,
+      "step": 6
+    },
+    {
+      "epoch": 0.06397562833206398,
+      "grad_norm": 1.4912341833114624,
+      "learning_rate": 6.363636363636364e-06,
+      "loss": 0.6013,
+      "step": 7
+    },
+    {
+      "epoch": 0.07311500380807312,
+      "grad_norm": 1.28671395778656,
+      "learning_rate": 7.272727272727273e-06,
+      "loss": 0.588,
+      "step": 8
+    },
+    {
+      "epoch": 0.08225437928408226,
+      "grad_norm": 2.198812246322632,
+      "learning_rate": 8.181818181818183e-06,
+      "loss": 0.5794,
+      "step": 9
+    },
+    {
+      "epoch": 0.0913937547600914,
+      "grad_norm": 0.9983230233192444,
+      "learning_rate": 9.090909090909091e-06,
+      "loss": 0.5403,
+      "step": 10
+    },
+    {
+      "epoch": 0.10053313023610053,
+      "grad_norm": 1.5041189193725586,
+      "learning_rate": 1e-05,
+      "loss": 0.526,
+      "step": 11
+    },
+    {
+      "epoch": 0.10967250571210967,
+      "grad_norm": 1.1437222957611084,
+      "learning_rate": 1.0909090909090909e-05,
+      "loss": 0.5001,
+      "step": 12
+    },
+    {
+      "epoch": 0.1188118811881188,
+      "grad_norm": 0.75607830286026,
+      "learning_rate": 1.181818181818182e-05,
+      "loss": 0.5017,
+      "step": 13
+    },
+    {
+      "epoch": 0.12795125666412796,
+      "grad_norm": 1.0801345109939575,
+      "learning_rate": 1.2727272727272728e-05,
+      "loss": 0.4927,
+      "step": 14
+    },
+    {
+      "epoch": 0.1370906321401371,
+      "grad_norm": 1.3382116556167603,
+      "learning_rate": 1.3636363636363637e-05,
+      "loss": 0.4917,
+      "step": 15
+    },
+    {
+      "epoch": 0.14623000761614624,
+      "grad_norm": 0.9588184952735901,
+      "learning_rate": 1.4545454545454546e-05,
+      "loss": 0.4444,
+      "step": 16
+    },
+    {
+      "epoch": 0.15536938309215537,
+      "grad_norm": 0.7174947261810303,
+      "learning_rate": 1.5454545454545454e-05,
+      "loss": 0.4665,
+      "step": 17
+    },
+    {
+      "epoch": 0.16450875856816452,
+      "grad_norm": 0.6924068331718445,
+      "learning_rate": 1.6363636363636366e-05,
+      "loss": 0.454,
+      "step": 18
+    },
+    {
+      "epoch": 0.17364813404417365,
+      "grad_norm": 0.8726766109466553,
+      "learning_rate": 1.7272727272727274e-05,
+      "loss": 0.4245,
+      "step": 19
+    },
+    {
+      "epoch": 0.1827875095201828,
+      "grad_norm": 0.9118347764015198,
+      "learning_rate": 1.8181818181818182e-05,
+      "loss": 0.4473,
+      "step": 20
+    },
+    {
+      "epoch": 0.19192688499619193,
+      "grad_norm": 0.6092010736465454,
+      "learning_rate": 1.9090909090909094e-05,
+      "loss": 0.4181,
+      "step": 21
+    },
+    {
+      "epoch": 0.20106626047220105,
+      "grad_norm": 0.7477689981460571,
+      "learning_rate": 2e-05,
+      "loss": 0.4225,
+      "step": 22
+    },
+    {
+      "epoch": 0.2102056359482102,
+      "grad_norm": 0.7922837138175964,
+      "learning_rate": 1.9998715457999313e-05,
+      "loss": 0.4286,
+      "step": 23
+    },
+    {
+      "epoch": 0.21934501142421933,
+      "grad_norm": 0.6749143600463867,
+      "learning_rate": 1.999486216200688e-05,
+      "loss": 0.4125,
+      "step": 24
+    },
+    {
+      "epoch": 0.2284843869002285,
+      "grad_norm": 0.6132336258888245,
+      "learning_rate": 1.9988441101966807e-05,
+      "loss": 0.4321,
+      "step": 25
+    },
+    {
+      "epoch": 0.2376237623762376,
+      "grad_norm": 0.6256394982337952,
+      "learning_rate": 1.9979453927503366e-05,
+      "loss": 0.4401,
+      "step": 26
+    },
+    {
+      "epoch": 0.24676313785224677,
+      "grad_norm": 0.5225641131401062,
+      "learning_rate": 1.9967902947497158e-05,
+      "loss": 0.4255,
+      "step": 27
+    },
+    {
+      "epoch": 0.2559025133282559,
+      "grad_norm": 0.4767383635044098,
+      "learning_rate": 1.9953791129491985e-05,
+      "loss": 0.42,
+      "step": 28
+    },
+    {
+      "epoch": 0.26504188880426505,
+      "grad_norm": 0.5424817204475403,
+      "learning_rate": 1.9937122098932428e-05,
+      "loss": 0.4023,
+      "step": 29
+    },
+    {
+      "epoch": 0.2741812642802742,
+      "grad_norm": 0.5565168857574463,
+      "learning_rate": 1.991790013823246e-05,
+      "loss": 0.4182,
+      "step": 30
+    },
+    {
+      "epoch": 0.2833206397562833,
+      "grad_norm": 0.4491325318813324,
+      "learning_rate": 1.9896130185675263e-05,
+      "loss": 0.4142,
+      "step": 31
+    },
+    {
+      "epoch": 0.2924600152322925,
+      "grad_norm": 0.465501606464386,
+      "learning_rate": 1.9871817834144506e-05,
+      "loss": 0.402,
+      "step": 32
+    },
+    {
+      "epoch": 0.3015993907083016,
+      "grad_norm": 0.43807297945022583,
+      "learning_rate": 1.9844969329687526e-05,
+      "loss": 0.4112,
+      "step": 33
+    },
+    {
+      "epoch": 0.31073876618431073,
+      "grad_norm": 0.4875776469707489,
+      "learning_rate": 1.9815591569910654e-05,
+      "loss": 0.3917,
+      "step": 34
+    },
+    {
+      "epoch": 0.31987814166031986,
+      "grad_norm": 0.48279792070388794,
+      "learning_rate": 1.9783692102207156e-05,
+      "loss": 0.4108,
+      "step": 35
+    },
+    {
+      "epoch": 0.32901751713632904,
+      "grad_norm": 0.4583301544189453,
+      "learning_rate": 1.9749279121818235e-05,
+      "loss": 0.3623,
+      "step": 36
+    },
+    {
+      "epoch": 0.33815689261233817,
+      "grad_norm": 0.3826312720775604,
+      "learning_rate": 1.971236146972764e-05,
+      "loss": 0.3637,
+      "step": 37
+    },
+    {
+      "epoch": 0.3472962680883473,
+      "grad_norm": 0.32831740379333496,
+      "learning_rate": 1.9672948630390296e-05,
+      "loss": 0.3627,
+      "step": 38
+    },
+    {
+      "epoch": 0.3564356435643564,
+      "grad_norm": 0.4264345169067383,
+      "learning_rate": 1.9631050729295705e-05,
+      "loss": 0.4095,
+      "step": 39
+    },
+    {
+      "epoch": 0.3655750190403656,
+      "grad_norm": 0.37228643894195557,
+      "learning_rate": 1.9586678530366607e-05,
+      "loss": 0.3846,
+      "step": 40
+    },
+    {
+      "epoch": 0.3747143945163747,
+      "grad_norm": 0.2934049665927887,
+      "learning_rate": 1.953984343319364e-05,
+      "loss": 0.3688,
+      "step": 41
+    },
+    {
+      "epoch": 0.38385376999238385,
+      "grad_norm": 0.30369582772254944,
+      "learning_rate": 1.949055747010669e-05,
+      "loss": 0.3885,
+      "step": 42
+    },
+    {
+      "epoch": 0.392993145468393,
+      "grad_norm": 0.3635307848453522,
+      "learning_rate": 1.9438833303083677e-05,
+      "loss": 0.3908,
+      "step": 43
+    },
+    {
+      "epoch": 0.4021325209444021,
+      "grad_norm": 0.3347395360469818,
+      "learning_rate": 1.9384684220497605e-05,
+      "loss": 0.3628,
+      "step": 44
+    },
+    {
+      "epoch": 0.4112718964204113,
+      "grad_norm": 0.3150138258934021,
+      "learning_rate": 1.932812413370265e-05,
+      "loss": 0.4,
+      "step": 45
+    },
+    {
+      "epoch": 0.4204112718964204,
+      "grad_norm": 0.2996457815170288,
+      "learning_rate": 1.926916757346022e-05,
+      "loss": 0.3682,
+      "step": 46
+    },
+    {
+      "epoch": 0.42955064737242954,
+      "grad_norm": 0.3075307607650757,
+      "learning_rate": 1.9207829686205882e-05,
+      "loss": 0.3611,
+      "step": 47
+    },
+    {
+      "epoch": 0.43869002284843867,
+      "grad_norm": 0.3118605613708496,
+      "learning_rate": 1.9144126230158127e-05,
+      "loss": 0.38,
+      "step": 48
+    },
+    {
+      "epoch": 0.44782939832444785,
+      "grad_norm": 0.32702377438545227,
+      "learning_rate": 1.9078073571269922e-05,
+      "loss": 0.3617,
+      "step": 49
+    },
+    {
+      "epoch": 0.456968773800457,
+      "grad_norm": 0.29042407870292664,
+      "learning_rate": 1.900968867902419e-05,
+      "loss": 0.3647,
+      "step": 50
+    },
+    {
+      "epoch": 0.4661081492764661,
+      "grad_norm": 0.32697346806526184,
+      "learning_rate": 1.8938989122074195e-05,
+      "loss": 0.3712,
+      "step": 51
+    },
+    {
+      "epoch": 0.4752475247524752,
+      "grad_norm": 0.3000766634941101,
+      "learning_rate": 1.8865993063730003e-05,
+      "loss": 0.3846,
+      "step": 52
+    },
+    {
+      "epoch": 0.4843869002284844,
+      "grad_norm": 0.3716011047363281,
+      "learning_rate": 1.8790719257292175e-05,
+      "loss": 0.3888,
+      "step": 53
+    },
+    {
+      "epoch": 0.49352627570449353,
+      "grad_norm": 0.3023267984390259,
+      "learning_rate": 1.8713187041233896e-05,
+      "loss": 0.3819,
+      "step": 54
+    },
+    {
+      "epoch": 0.5026656511805027,
+      "grad_norm": 0.33082687854766846,
+      "learning_rate": 1.8633416334232754e-05,
+      "loss": 0.3617,
+      "step": 55
+    },
+    {
+      "epoch": 0.5118050266565118,
+      "grad_norm": 0.3457026481628418,
+      "learning_rate": 1.8551427630053464e-05,
+      "loss": 0.388,
+      "step": 56
+    },
+    {
+      "epoch": 0.5209444021325209,
+      "grad_norm": 0.30542826652526855,
+      "learning_rate": 1.8467241992282842e-05,
+      "loss": 0.347,
+      "step": 57
+    },
+    {
+      "epoch": 0.5300837776085301,
+      "grad_norm": 0.345498651266098,
+      "learning_rate": 1.8380881048918406e-05,
+      "loss": 0.3736,
+      "step": 58
+    },
+    {
+      "epoch": 0.5392231530845393,
+      "grad_norm": 0.35136133432388306,
+      "learning_rate": 1.8292366986811952e-05,
+      "loss": 0.3512,
+      "step": 59
+    },
+    {
+      "epoch": 0.5483625285605483,
+      "grad_norm": 0.2956295609474182,
+      "learning_rate": 1.820172254596956e-05,
+      "loss": 0.368,
+      "step": 60
+    },
+    {
+      "epoch": 0.5575019040365575,
+      "grad_norm": 0.33257603645324707,
+      "learning_rate": 1.8108971013709512e-05,
+      "loss": 0.3564,
+      "step": 61
+    },
+    {
+      "epoch": 0.5666412795125666,
+      "grad_norm": 0.2967292368412018,
+      "learning_rate": 1.8014136218679566e-05,
+      "loss": 0.3577,
+      "step": 62
+    },
+    {
+      "epoch": 0.5757806549885758,
+      "grad_norm": 0.3108254075050354,
+      "learning_rate": 1.79172425247352e-05,
+      "loss": 0.3557,
+      "step": 63
+    },
+    {
+      "epoch": 0.584920030464585,
+      "grad_norm": 0.3251456916332245,
+      "learning_rate": 1.78183148246803e-05,
+      "loss": 0.355,
+      "step": 64
+    },
+    {
+      "epoch": 0.594059405940594,
+      "grad_norm": 0.2736187279224396,
+      "learning_rate": 1.771737853387202e-05,
+      "loss": 0.3674,
+      "step": 65
+    },
+    {
+      "epoch": 0.6031987814166032,
+      "grad_norm": 0.3374134600162506,
+      "learning_rate": 1.7614459583691346e-05,
+      "loss": 0.3697,
+      "step": 66
+    },
+    {
+      "epoch": 0.6123381568926123,
+      "grad_norm": 0.2792860269546509,
+      "learning_rate": 1.7509584414881114e-05,
+      "loss": 0.3642,
+      "step": 67
+    },
+    {
+      "epoch": 0.6214775323686215,
+      "grad_norm": 0.31335848569869995,
+      "learning_rate": 1.7402779970753156e-05,
+      "loss": 0.3709,
+      "step": 68
+    },
+    {
+      "epoch": 0.6306169078446306,
+      "grad_norm": 0.31955182552337646,
+      "learning_rate": 1.7294073690266343e-05,
+      "loss": 0.3777,
+      "step": 69
+    },
+    {
+      "epoch": 0.6397562833206397,
+      "grad_norm": 0.2629980444908142,
+      "learning_rate": 1.7183493500977277e-05,
+      "loss": 0.363,
+      "step": 70
+    },
+    {
+      "epoch": 0.6488956587966489,
+      "grad_norm": 0.3005543053150177,
+      "learning_rate": 1.7071067811865477e-05,
+      "loss": 0.3622,
+      "step": 71
+    },
+    {
+      "epoch": 0.6580350342726581,
+      "grad_norm": 0.27785226702690125,
+      "learning_rate": 1.6956825506034866e-05,
+      "loss": 0.3548,
+      "step": 72
+    },
+    {
+      "epoch": 0.6671744097486672,
+      "grad_norm": 0.31932327151298523,
+      "learning_rate": 1.6840795933293464e-05,
+      "loss": 0.3542,
+      "step": 73
+    },
+    {
+      "epoch": 0.6763137852246763,
+      "grad_norm": 0.3696252703666687,
+      "learning_rate": 1.672300890261317e-05,
+      "loss": 0.352,
+      "step": 74
+    },
+    {
+      "epoch": 0.6854531607006854,
+      "grad_norm": 0.2692716121673584,
+      "learning_rate": 1.6603494674471595e-05,
+      "loss": 0.349,
+      "step": 75
+    },
+    {
+      "epoch": 0.6945925361766946,
+      "grad_norm": 0.35122308135032654,
+      "learning_rate": 1.6482283953077887e-05,
+      "loss": 0.3724,
+      "step": 76
+    },
+    {
+      "epoch": 0.7037319116527038,
+      "grad_norm": 0.3385901153087616,
+      "learning_rate": 1.635940787848455e-05,
+      "loss": 0.351,
+      "step": 77
+    },
+    {
+      "epoch": 0.7128712871287128,
+      "grad_norm": 0.28408318758010864,
+      "learning_rate": 1.6234898018587336e-05,
+      "loss": 0.3545,
+      "step": 78
+    },
+    {
+      "epoch": 0.722010662604722,
+      "grad_norm": 0.32605817914009094,
+      "learning_rate": 1.6108786361015145e-05,
+      "loss": 0.3457,
+      "step": 79
+    },
+    {
+      "epoch": 0.7311500380807312,
+      "grad_norm": 0.2926092743873596,
+      "learning_rate": 1.598110530491216e-05,
+      "loss": 0.3836,
+      "step": 80
+    },
+    {
+      "epoch": 0.7402894135567403,
+      "grad_norm": 0.3354974389076233,
+      "learning_rate": 1.5851887652614238e-05,
+      "loss": 0.3657,
+      "step": 81
+    },
+    {
+      "epoch": 0.7494287890327495,
+      "grad_norm": 0.3095051646232605,
+      "learning_rate": 1.5721166601221697e-05,
+      "loss": 0.378,
+      "step": 82
+    },
+    {
+      "epoch": 0.7585681645087585,
+      "grad_norm": 0.31830886006355286,
+      "learning_rate": 1.5588975734070717e-05,
+      "loss": 0.3493,
+      "step": 83
+    },
+    {
+      "epoch": 0.7677075399847677,
+      "grad_norm": 0.28574857115745544,
+      "learning_rate": 1.5455349012105488e-05,
+      "loss": 0.3632,
+      "step": 84
+    },
+    {
+      "epoch": 0.7768469154607769,
+      "grad_norm": 0.2779458463191986,
+      "learning_rate": 1.5320320765153367e-05,
+      "loss": 0.3601,
+      "step": 85
+    },
+    {
+      "epoch": 0.785986290936786,
+      "grad_norm": 0.2946210205554962,
+      "learning_rate": 1.5183925683105254e-05,
+      "loss": 0.3614,
+      "step": 86
+    },
+    {
+      "epoch": 0.7951256664127951,
+      "grad_norm": 0.29695403575897217,
+      "learning_rate": 1.504619880700346e-05,
+      "loss": 0.3585,
+      "step": 87
+    },
+    {
+      "epoch": 0.8042650418888042,
+      "grad_norm": 0.31594327092170715,
+      "learning_rate": 1.4907175520039381e-05,
+      "loss": 0.3538,
+      "step": 88
+    },
+    {
+      "epoch": 0.8134044173648134,
+      "grad_norm": 0.2952496409416199,
+      "learning_rate": 1.4766891538463255e-05,
+      "loss": 0.3529,
+      "step": 89
+    },
+    {
+      "epoch": 0.8225437928408226,
+      "grad_norm": 0.3008720576763153,
+      "learning_rate": 1.4625382902408356e-05,
+      "loss": 0.3488,
+      "step": 90
+    },
+    {
+      "epoch": 0.8316831683168316,
+      "grad_norm": 0.27587708830833435,
+      "learning_rate": 1.448268596663197e-05,
+      "loss": 0.343,
+      "step": 91
+    },
+    {
+      "epoch": 0.8408225437928408,
+      "grad_norm": 0.2870708405971527,
+      "learning_rate": 1.4338837391175582e-05,
+      "loss": 0.3577,
+      "step": 92
+    },
+    {
+      "epoch": 0.84996191926885,
+      "grad_norm": 0.2745375335216522,
+      "learning_rate": 1.419387413194657e-05,
+      "loss": 0.3437,
+      "step": 93
+    },
+    {
+      "epoch": 0.8591012947448591,
+      "grad_norm": 0.30285215377807617,
+      "learning_rate": 1.4047833431223938e-05,
+      "loss": 0.3504,
+      "step": 94
+    },
+    {
+      "epoch": 0.8682406702208683,
+      "grad_norm": 0.331877738237381,
+      "learning_rate": 1.390075280809047e-05,
+      "loss": 0.3517,
+      "step": 95
+    },
+    {
+      "epoch": 0.8773800456968773,
+      "grad_norm": 0.28984907269477844,
+      "learning_rate": 1.3752670048793744e-05,
+      "loss": 0.3507,
+      "step": 96
+    },
+    {
+      "epoch": 0.8865194211728865,
+      "grad_norm": 0.27279210090637207,
+      "learning_rate": 1.3603623197038536e-05,
+      "loss": 0.3563,
+      "step": 97
+    },
+    {
+      "epoch": 0.8956587966488957,
+      "grad_norm": 0.2931230664253235,
+      "learning_rate": 1.3453650544213078e-05,
+      "loss": 0.3648,
+      "step": 98
+    },
+    {
+      "epoch": 0.9047981721249048,
+      "grad_norm": 0.304097443819046,
+      "learning_rate": 1.3302790619551673e-05,
+      "loss": 0.3407,
+      "step": 99
+    },
+    {
+      "epoch": 0.913937547600914,
+      "grad_norm": 0.27398836612701416,
+      "learning_rate": 1.315108218023621e-05,
+      "loss": 0.355,
+      "step": 100
+    },
+    {
+      "epoch": 0.9230769230769231,
+      "grad_norm": 0.28750985860824585,
+      "learning_rate": 1.2998564201439117e-05,
+      "loss": 0.3581,
+      "step": 101
+    },
+    {
+      "epoch": 0.9322162985529322,
+      "grad_norm": 0.2681604027748108,
+      "learning_rate": 1.2845275866310325e-05,
+      "loss": 0.3549,
+      "step": 102
+    },
+    {
+      "epoch": 0.9413556740289414,
+      "grad_norm": 0.26904138922691345,
+      "learning_rate": 1.2691256555910769e-05,
+      "loss": 0.3503,
+      "step": 103
+    },
+    {
+      "epoch": 0.9504950495049505,
+      "grad_norm": 0.26759082078933716,
+      "learning_rate": 1.2536545839095074e-05,
+      "loss": 0.3678,
+      "step": 104
+    },
+    {
+      "epoch": 0.9596344249809596,
+      "grad_norm": 0.2824430465698242,
+      "learning_rate": 1.2381183462345983e-05,
+      "loss": 0.3529,
+      "step": 105
+    },
+    {
+      "epoch": 0.9687738004569688,
+      "grad_norm": 0.29599159955978394,
+      "learning_rate": 1.2225209339563144e-05,
+      "loss": 0.3513,
+      "step": 106
+    },
+    {
+      "epoch": 0.9779131759329779,
+      "grad_norm": 0.2748142182826996,
+      "learning_rate": 1.206866354180891e-05,
+      "loss": 0.3508,
+      "step": 107
+    },
+    {
+      "epoch": 0.9870525514089871,
+      "grad_norm": 0.27814149856567383,
+      "learning_rate": 1.1911586287013726e-05,
+      "loss": 0.3553,
+      "step": 108
+    },
+    {
+      "epoch": 0.9961919268849961,
+      "grad_norm": 0.3061699867248535,
+      "learning_rate": 1.1754017929643818e-05,
+      "loss": 0.3504,
+      "step": 109
+    },
+    {
+      "epoch": 1.0053313023610053,
+      "grad_norm": 0.42901527881622314,
+      "learning_rate": 1.1595998950333794e-05,
+      "loss": 0.504,
+      "step": 110
+    },
+    {
+      "epoch": 1.0144706778370145,
+      "grad_norm": 0.3380506634712219,
+      "learning_rate": 1.143756994548682e-05,
+      "loss": 0.3248,
+      "step": 111
+    },
+    {
+      "epoch": 1.0236100533130237,
+      "grad_norm": 0.27545130252838135,
+      "learning_rate": 1.1278771616845061e-05,
+      "loss": 0.3143,
+      "step": 112
+    },
+    {
+      "epoch": 1.0327494287890326,
+      "grad_norm": 0.30115991830825806,
+      "learning_rate": 1.1119644761033079e-05,
+      "loss": 0.3108,
+      "step": 113
+    },
+    {
+      "epoch": 1.0418888042650418,
+      "grad_norm": 0.33423128724098206,
+      "learning_rate": 1.0960230259076819e-05,
+      "loss": 0.3024,
+      "step": 114
+    },
+    {
+      "epoch": 1.051028179741051,
+      "grad_norm": 0.37499961256980896,
+      "learning_rate": 1.0800569065900935e-05,
+      "loss": 0.3275,
+      "step": 115
+    },
+    {
+      "epoch": 1.0601675552170602,
+      "grad_norm": 0.3214980363845825,
+      "learning_rate": 1.064070219980713e-05,
+      "loss": 0.2905,
+      "step": 116
+    },
+    {
+      "epoch": 1.0693069306930694,
+      "grad_norm": 0.343065470457077,
+      "learning_rate": 1.0480670731936209e-05,
+      "loss": 0.2874,
+      "step": 117
+    },
+    {
+      "epoch": 1.0784463061690786,
+      "grad_norm": 0.30497705936431885,
+      "learning_rate": 1.0320515775716556e-05,
+      "loss": 0.2786,
+      "step": 118
+    },
+    {
+      "epoch": 1.0875856816450875,
+      "grad_norm": 0.3317449390888214,
+      "learning_rate": 1.0160278476301739e-05,
+      "loss": 0.3472,
+      "step": 119
+    },
+    {
+      "epoch": 1.0967250571210967,
+      "grad_norm": 0.32423466444015503,
+      "learning_rate": 1e-05,
+      "loss": 0.3031,
+      "step": 120
+    },
+    {
+      "epoch": 1.1058644325971059,
+      "grad_norm": 0.288601815700531,
+      "learning_rate": 9.839721523698265e-06,
+      "loss": 0.2416,
+      "step": 121
+    },
+    {
+      "epoch": 1.115003808073115,
+      "grad_norm": 0.33957648277282715,
+      "learning_rate": 9.67948422428345e-06,
+      "loss": 0.329,
+      "step": 122
+    },
+    {
+      "epoch": 1.1241431835491242,
+      "grad_norm": 0.31219515204429626,
+      "learning_rate": 9.519329268063795e-06,
+      "loss": 0.3184,
+      "step": 123
+    },
+    {
+      "epoch": 1.1332825590251332,
+      "grad_norm": 0.2770800292491913,
+      "learning_rate": 9.359297800192873e-06,
+      "loss": 0.287,
+      "step": 124
+    },
+    {
+      "epoch": 1.1424219345011424,
+      "grad_norm": 0.29623621702194214,
+      "learning_rate": 9.199430934099068e-06,
+      "loss": 0.2848,
+      "step": 125
+    },
+    {
+      "epoch": 1.1515613099771516,
+      "grad_norm": 0.3068810999393463,
+      "learning_rate": 9.039769740923183e-06,
+      "loss": 0.2797,
+      "step": 126
+    },
+    {
+      "epoch": 1.1607006854531607,
+      "grad_norm": 0.2660495936870575,
+      "learning_rate": 8.880355238966923e-06,
+      "loss": 0.2905,
+      "step": 127
+    },
+    {
+      "epoch": 1.16984006092917,
+      "grad_norm": 0.31384557485580444,
+      "learning_rate": 8.721228383154939e-06,
+      "loss": 0.2996,
+      "step": 128
+    },
+    {
+      "epoch": 1.178979436405179,
+      "grad_norm": 0.26587456464767456,
+      "learning_rate": 8.562430054513184e-06,
+      "loss": 0.2955,
+      "step": 129
+    },
+    {
+      "epoch": 1.188118811881188,
+      "grad_norm": 0.2939557731151581,
+      "learning_rate": 8.404001049666211e-06,
+      "loss": 0.2981,
+      "step": 130
+    },
+    {
+      "epoch": 1.1972581873571972,
+      "grad_norm": 0.3092159330844879,
+      "learning_rate": 8.245982070356186e-06,
+      "loss": 0.2779,
+      "step": 131
+    },
+    {
+      "epoch": 1.2063975628332064,
+      "grad_norm": 0.263584703207016,
+      "learning_rate": 8.08841371298628e-06,
+      "loss": 0.296,
+      "step": 132
+    },
+    {
+      "epoch": 1.2155369383092156,
+      "grad_norm": 0.3118206262588501,
+      "learning_rate": 7.931336458191092e-06,
+      "loss": 0.3203,
+      "step": 133
+    },
+    {
+      "epoch": 1.2246763137852246,
+      "grad_norm": 0.278341680765152,
+      "learning_rate": 7.774790660436857e-06,
+      "loss": 0.2915,
+      "step": 134
+    },
+    {
+      "epoch": 1.2338156892612338,
+      "grad_norm": 0.27913302183151245,
+      "learning_rate": 7.618816537654018e-06,
+      "loss": 0.2997,
+      "step": 135
+    },
+    {
+      "epoch": 1.242955064737243,
+      "grad_norm": 0.2791356146335602,
+      "learning_rate": 7.463454160904928e-06,
+      "loss": 0.2625,
+      "step": 136
+    },
+    {
+      "epoch": 1.2520944402132521,
+      "grad_norm": 0.2794390022754669,
+      "learning_rate": 7.308743444089232e-06,
+      "loss": 0.3042,
+      "step": 137
+    },
+    {
+      "epoch": 1.2612338156892613,
+      "grad_norm": 0.2647666335105896,
+      "learning_rate": 7.154724133689677e-06,
+      "loss": 0.2775,
+      "step": 138
+    },
+    {
+      "epoch": 1.2703731911652705,
+      "grad_norm": 0.3084835708141327,
+      "learning_rate": 7.001435798560884e-06,
+      "loss": 0.2996,
+      "step": 139
+    },
+    {
+      "epoch": 1.2795125666412794,
+      "grad_norm": 0.33654364943504333,
+      "learning_rate": 6.848917819763794e-06,
+      "loss": 0.2816,
+      "step": 140
+    },
+    {
+      "epoch": 1.2886519421172886,
+      "grad_norm": 0.26153555512428284,
+      "learning_rate": 6.697209380448333e-06,
+      "loss": 0.3098,
+      "step": 141
+    },
+    {
+      "epoch": 1.2977913175932978,
+      "grad_norm": 0.35121041536331177,
+      "learning_rate": 6.546349455786926e-06,
+      "loss": 0.341,
+      "step": 142
+    },
+    {
+      "epoch": 1.306930693069307,
+      "grad_norm": 0.2708624601364136,
+      "learning_rate": 6.396376802961468e-06,
+      "loss": 0.2959,
+      "step": 143
+    },
+    {
+      "epoch": 1.316070068545316,
+      "grad_norm": 0.2626864016056061,
+      "learning_rate": 6.24732995120626e-06,
+      "loss": 0.2829,
+      "step": 144
+    },
+    {
+      "epoch": 1.3252094440213251,
+      "grad_norm": 0.29574039578437805,
+      "learning_rate": 6.099247191909532e-06,
+      "loss": 0.281,
+      "step": 145
+    },
+    {
+      "epoch": 1.3343488194973343,
+      "grad_norm": 0.26153430342674255,
+      "learning_rate": 5.952166568776062e-06,
+      "loss": 0.3167,
+      "step": 146
+    },
+    {
+      "epoch": 1.3434881949733435,
+      "grad_norm": 0.2655847668647766,
+      "learning_rate": 5.806125868053433e-06,
+      "loss": 0.2687,
+      "step": 147
+    },
+    {
+      "epoch": 1.3526275704493527,
+      "grad_norm": 0.2613089382648468,
+      "learning_rate": 5.66116260882442e-06,
+      "loss": 0.2788,
+      "step": 148
+    },
+    {
+      "epoch": 1.3617669459253618,
+      "grad_norm": 0.27271604537963867,
+      "learning_rate": 5.517314033368031e-06,
+      "loss": 0.3039,
+      "step": 149
+    },
+    {
+      "epoch": 1.370906321401371,
+      "grad_norm": 0.28087660670280457,
+      "learning_rate": 5.37461709759165e-06,
+      "loss": 0.3076,
+      "step": 150
+    },
+    {
+      "epoch": 1.38004569687738,
+      "grad_norm": 0.2736712098121643,
+      "learning_rate": 5.233108461536749e-06,
+      "loss": 0.3041,
+      "step": 151
+    },
+    {
+      "epoch": 1.3891850723533892,
+      "grad_norm": 0.2977502942085266,
+      "learning_rate": 5.092824479960625e-06,
+      "loss": 0.31,
+      "step": 152
+    },
+    {
+      "epoch": 1.3983244478293984,
+      "grad_norm": 0.3099557161331177,
+      "learning_rate": 4.9538011929965436e-06,
+      "loss": 0.3212,
+      "step": 153
+    },
+    {
+      "epoch": 1.4074638233054075,
+      "grad_norm": 0.3034738004207611,
+      "learning_rate": 4.81607431689475e-06,
+      "loss": 0.2922,
+      "step": 154
+    },
+    {
+      "epoch": 1.4166031987814165,
+      "grad_norm": 0.2969326674938202,
+      "learning_rate": 4.679679234846636e-06,
+      "loss": 0.3107,
+      "step": 155
+    },
+    {
+      "epoch": 1.4257425742574257,
+      "grad_norm": 0.32106441259384155,
+      "learning_rate": 4.544650987894514e-06,
+      "loss": 0.2697,
+      "step": 156
+    },
+    {
+      "epoch": 1.4348819497334349,
+      "grad_norm": 0.2815849483013153,
+      "learning_rate": 4.411024265929283e-06,
+      "loss": 0.2905,
+      "step": 157
+    },
+    {
+      "epoch": 1.444021325209444,
+      "grad_norm": 0.29976797103881836,
+      "learning_rate": 4.278833398778306e-06,
+      "loss": 0.2548,
+      "step": 158
+    },
+    {
+      "epoch": 1.4531607006854532,
+      "grad_norm": 0.3238127827644348,
+      "learning_rate": 4.148112347385762e-06,
+      "loss": 0.3296,
+      "step": 159
+    },
+    {
+      "epoch": 1.4623000761614624,
+      "grad_norm": 0.3087165355682373,
+      "learning_rate": 4.01889469508784e-06,
+      "loss": 0.2928,
+      "step": 160
+    },
+    {
+      "epoch": 1.4714394516374714,
+      "grad_norm": 0.3463199734687805,
+      "learning_rate": 3.891213638984858e-06,
+      "loss": 0.3121,
+      "step": 161
+    },
+    {
+      "epoch": 1.4805788271134805,
+      "grad_norm": 0.25795602798461914,
+      "learning_rate": 3.7651019814126656e-06,
+      "loss": 0.267,
+      "step": 162
+    },
+    {
+      "epoch": 1.4897182025894897,
+      "grad_norm": 0.3257160186767578,
+      "learning_rate": 3.6405921215154492e-06,
+      "loss": 0.3175,
+      "step": 163
+    },
+    {
+      "epoch": 1.498857578065499,
+      "grad_norm": 0.3168756365776062,
+      "learning_rate": 3.5177160469221184e-06,
+      "loss": 0.2985,
+      "step": 164
+    },
+    {
+      "epoch": 1.5079969535415079,
+      "grad_norm": 0.27244633436203003,
+      "learning_rate": 3.3965053255284085e-06,
+      "loss": 0.2619,
+      "step": 165
+    },
+    {
+      "epoch": 1.517136329017517,
+      "grad_norm": 0.3427713215351105,
+      "learning_rate": 3.2769910973868314e-06,
+      "loss": 0.3191,
+      "step": 166
+    },
+    {
+      "epoch": 1.5262757044935262,
+      "grad_norm": 0.2740377187728882,
+      "learning_rate": 3.1592040667065393e-06,
+      "loss": 0.2744,
+      "step": 167
+    },
+    {
+      "epoch": 1.5354150799695354,
+      "grad_norm": 0.3417263925075531,
+      "learning_rate": 3.0431744939651365e-06,
+      "loss": 0.3138,
+      "step": 168
+    },
+    {
+      "epoch": 1.5445544554455446,
+      "grad_norm": 0.2803570032119751,
+      "learning_rate": 2.9289321881345257e-06,
+      "loss": 0.2748,
+      "step": 169
+    },
+    {
+      "epoch": 1.5536938309215538,
+      "grad_norm": 0.34591829776763916,
+      "learning_rate": 2.8165064990227255e-06,
+      "loss": 0.2931,
+      "step": 170
+    },
+    {
+      "epoch": 1.562833206397563,
+      "grad_norm": 0.30100783705711365,
+      "learning_rate": 2.7059263097336595e-06,
+      "loss": 0.3322,
+      "step": 171
+    },
+    {
+      "epoch": 1.5719725818735721,
+      "grad_norm": 0.30982816219329834,
+      "learning_rate": 2.597220029246846e-06,
+      "loss": 0.3208,
+      "step": 172
+    },
+    {
+      "epoch": 1.581111957349581,
+      "grad_norm": 0.2882677912712097,
+      "learning_rate": 2.490415585118887e-06,
+      "loss": 0.2542,
+      "step": 173
+    },
+    {
+      "epoch": 1.5902513328255903,
+      "grad_norm": 0.2950691878795624,
+      "learning_rate": 2.3855404163086558e-06,
+      "loss": 0.3102,
+      "step": 174
+    },
+    {
+      "epoch": 1.5993907083015992,
+      "grad_norm": 0.2920461595058441,
+      "learning_rate": 2.282621466127982e-06,
+      "loss": 0.2608,
+      "step": 175
+    },
+    {
+      "epoch": 1.6085300837776084,
+      "grad_norm": 0.29719457030296326,
+      "learning_rate": 2.1816851753197023e-06,
+      "loss": 0.2785,
+      "step": 176
+    },
+    {
+      "epoch": 1.6176694592536176,
+      "grad_norm": 0.30973735451698303,
+      "learning_rate": 2.082757475264804e-06,
+      "loss": 0.3116,
+      "step": 177
+    },
+    {
+      "epoch": 1.6268088347296268,
+      "grad_norm": 0.2760176956653595,
+      "learning_rate": 1.9858637813204352e-06,
+      "loss": 0.256,
+      "step": 178
+    },
+    {
+      "epoch": 1.635948210205636,
+      "grad_norm": 0.37629491090774536,
+      "learning_rate": 1.8910289862904917e-06,
+      "loss": 0.3598,
+      "step": 179
+    },
+    {
+      "epoch": 1.6450875856816451,
+      "grad_norm": 0.22734475135803223,
+      "learning_rate": 1.7982774540304404e-06,
+      "loss": 0.2526,
+      "step": 180
+    },
+    {
+      "epoch": 1.6542269611576543,
+      "grad_norm": 0.31396934390068054,
+      "learning_rate": 1.7076330131880525e-06,
+      "loss": 0.2885,
+      "step": 181
+    },
+    {
+      "epoch": 1.6633663366336635,
+      "grad_norm": 0.32990527153015137,
+      "learning_rate": 1.6191189510815942e-06,
+      "loss": 0.3314,
+      "step": 182
+    },
+    {
+      "epoch": 1.6725057121096725,
+      "grad_norm": 0.26883870363235474,
+      "learning_rate": 1.5327580077171589e-06,
+      "loss": 0.2691,
+      "step": 183
+    },
+    {
+      "epoch": 1.6816450875856817,
+      "grad_norm": 0.2914712131023407,
+      "learning_rate": 1.4485723699465392e-06,
+      "loss": 0.3184,
+      "step": 184
+    },
+    {
+      "epoch": 1.6907844630616908,
+      "grad_norm": 0.2758725881576538,
+      "learning_rate": 1.3665836657672493e-06,
+      "loss": 0.2783,
+      "step": 185
+    },
+    {
+      "epoch": 1.6999238385376998,
+      "grad_norm": 0.3416280150413513,
+      "learning_rate": 1.286812958766106e-06,
+      "loss": 0.3252,
+      "step": 186
+    },
+    {
+      "epoch": 1.709063214013709,
+      "grad_norm": 0.30903884768486023,
+      "learning_rate": 1.209280742707828e-06,
+      "loss": 0.2988,
+      "step": 187
+    },
+    {
+      "epoch": 1.7182025894897182,
+      "grad_norm": 0.2973853349685669,
+      "learning_rate": 1.134006936269999e-06,
+      "loss": 0.3029,
+      "step": 188
+    },
+    {
+      "epoch": 1.7273419649657273,
+      "grad_norm": 0.29858219623565674,
+      "learning_rate": 1.0610108779258043e-06,
+      "loss": 0.2904,
+      "step": 189
+    },
+    {
+      "epoch": 1.7364813404417365,
+      "grad_norm": 0.28917691111564636,
+      "learning_rate": 9.903113209758098e-07,
+      "loss": 0.3059,
+      "step": 190
+    },
+    {
+      "epoch": 1.7456207159177457,
+      "grad_norm": 0.2837529480457306,
+      "learning_rate": 9.2192642873008e-07,
+      "loss": 0.292,
+      "step": 191
+    },
+    {
+      "epoch": 1.7547600913937549,
+      "grad_norm": 0.27116718888282776,
+      "learning_rate": 8.558737698418762e-07,
+      "loss": 0.287,
+      "step": 192
+    },
+    {
+      "epoch": 1.763899466869764,
+      "grad_norm": 0.2641710042953491,
+      "learning_rate": 7.921703137941172e-07,
+      "loss": 0.2916,
+      "step": 193
+    },
+    {
+      "epoch": 1.773038842345773,
+      "grad_norm": 0.27609920501708984,
+      "learning_rate": 7.308324265397837e-07,
+      "loss": 0.2847,
+      "step": 194
+    },
+    {
+      "epoch": 1.7821782178217822,
+      "grad_norm": 0.2574136555194855,
+      "learning_rate": 6.718758662973524e-07,
+      "loss": 0.2842,
+      "step": 195
+    },
+    {
+      "epoch": 1.7913175932977912,
+      "grad_norm": 0.26150667667388916,
+      "learning_rate": 6.153157795023956e-07,
+      "loss": 0.3169,
+      "step": 196
+    },
+    {
+      "epoch": 1.8004569687738003,
+      "grad_norm": 0.26446864008903503,
+      "learning_rate": 5.611666969163243e-07,
+      "loss": 0.3155,
+      "step": 197
+    },
+    {
+      "epoch": 1.8095963442498095,
+      "grad_norm": 0.2812100946903229,
+      "learning_rate": 5.094425298933136e-07,
+      "loss": 0.2952,
+      "step": 198
+    },
+    {
+      "epoch": 1.8187357197258187,
+      "grad_norm": 0.29095372557640076,
+      "learning_rate": 4.6015656680636234e-07,
+      "loss": 0.3076,
+      "step": 199
+    },
+    {
+      "epoch": 1.827875095201828,
+      "grad_norm": 0.3154431879520416,
+      "learning_rate": 4.133214696333943e-07,
+      "loss": 0.3001,
+      "step": 200
+    },
+    {
+      "epoch": 1.8408225437928407,
+      "grad_norm": 0.26161229610443115,
+      "learning_rate": 3.6894927070429744e-07,
+      "loss": 0.3034,
+      "step": 201
+    },
+    {
+      "epoch": 1.84996191926885,
+      "grad_norm": 0.275260329246521,
+      "learning_rate": 3.2705136960970554e-07,
+      "loss": 0.2986,
+      "step": 202
+    },
+    {
+      "epoch": 1.859101294744859,
+      "grad_norm": 0.28469160199165344,
+      "learning_rate": 2.8763853027236277e-07,
+      "loss": 0.3022,
+      "step": 203
+    },
+    {
+      "epoch": 1.8682406702208683,
+      "grad_norm": 0.28028687834739685,
+      "learning_rate": 2.507208781817638e-07,
+      "loss": 0.2878,
+      "step": 204
+    },
+    {
+      "epoch": 1.8773800456968774,
+      "grad_norm": 0.27624866366386414,
+      "learning_rate": 2.1630789779284677e-07,
+      "loss": 0.2957,
+      "step": 205
+    },
+    {
+      "epoch": 1.8865194211728866,
+      "grad_norm": 0.25148093700408936,
+      "learning_rate": 1.844084300893456e-07,
+      "loss": 0.2913,
+      "step": 206
+    },
+    {
+      "epoch": 1.8956587966488958,
+      "grad_norm": 0.3340187966823578,
+      "learning_rate": 1.55030670312476e-07,
+      "loss": 0.3051,
+      "step": 207
+    },
+    {
+      "epoch": 1.9047981721249048,
+      "grad_norm": 0.28733426332473755,
+      "learning_rate": 1.2818216585549824e-07,
+      "loss": 0.2968,
+      "step": 208
+    },
+    {
+      "epoch": 1.913937547600914,
+      "grad_norm": 0.2607288062572479,
+      "learning_rate": 1.0386981432474075e-07,
+      "loss": 0.3034,
+      "step": 209
+    },
+    {
+      "epoch": 1.9230769230769231,
+      "grad_norm": 0.27604418992996216,
+      "learning_rate": 8.209986176753947e-08,
+      "loss": 0.2934,
+      "step": 210
+    },
+    {
+      "epoch": 1.932216298552932,
+      "grad_norm": 0.26872286200523376,
+      "learning_rate": 6.287790106757396e-08,
+      "loss": 0.3107,
+      "step": 211
+    },
+    {
+      "epoch": 1.9413556740289413,
+      "grad_norm": 0.2715740203857422,
+      "learning_rate": 4.6208870508017703e-08,
+      "loss": 0.2925,
+      "step": 212
+    },
+    {
+      "epoch": 1.9504950495049505,
+      "grad_norm": 0.24944356083869934,
+      "learning_rate": 3.2097052502843005e-08,
+      "loss": 0.2911,
+      "step": 213
+    },
+    {
+      "epoch": 1.9596344249809596,
+      "grad_norm": 0.2840694487094879,
+      "learning_rate": 2.054607249663665e-08,
+      "loss": 0.2823,
+      "step": 214
+    },
+    {
+      "epoch": 1.9687738004569688,
+      "grad_norm": 0.28054678440093994,
+      "learning_rate": 1.1558898033191545e-08,
+      "loss": 0.3068,
+      "step": 215
+    },
+    {
+      "epoch": 1.977913175932978,
+      "grad_norm": 0.3040056526660919,
+      "learning_rate": 5.137837993121064e-09,
+      "loss": 0.3039,
+      "step": 216
+    },
+    {
+      "epoch": 1.9870525514089872,
+      "grad_norm": 0.2787896990776062,
+      "learning_rate": 1.2845420006879494e-09,
+      "loss": 0.2965,
+      "step": 217
+    },
+    {
+      "epoch": 1.9961919268849961,
+      "grad_norm": 0.2908172905445099,
+      "learning_rate": 0.0,
+      "loss": 0.298,
+      "step": 218
+    },
+    {
+      "epoch": 1.9961919268849961,
+      "step": 218,
+      "total_flos": 556668498083840.0,
+      "train_loss": 0.02458530199637107,
+      "train_runtime": 2561.7302,
+      "train_samples_per_second": 8.198,
+      "train_steps_per_second": 0.085
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 218,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 50,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 556668498083840.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2cb3d178ce69f8fa6231204575a0f9729dc529615c77ec4db66dba6098a9acc
+size 7544