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 +1,60 @@
+---
+library_name: transformers
+license: other
+base_model: Qwen/Qwen2.5-7B-Instruct
+tags:
+- llama-factory
+- full
+- generated_from_trainer
+model-index:
+- name: mlfoundations-dev_code-stratos-verified-scaled-0.5_stratos_7b
+  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. -->
+
+# mlfoundations-dev_code-stratos-verified-scaled-0.5_stratos_7b
+
+This model is a fine-tuned version of [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct) on the mlfoundations-dev/code-stratos-verified-scaled-0.5 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: 1e-05
+- train_batch_size: 1
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 96
+- total_train_batch_size: 96
+- total_eval_batch_size: 768
+- 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: 3.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.46.1
+- Pytorch 2.5.0a0+b465a5843b.nv24.09
+- Datasets 3.0.2
+- 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": 3.0,
+    "total_flos": 489026734391296.0,
+    "train_loss": 0.5917462170697175,
+    "train_runtime": 8001.2912,
+    "train_samples_per_second": 3.731,
+    "train_steps_per_second": 0.039
+}

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "/leonardo_work/EUHPC_E03_068/marianna/models/Qwen/Qwen2.5-7B-Instruct",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "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-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83be24083bae9f081bab80e4862286191f43d3f7612a2ddebd1fb336483d30e5
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8466c32c4c028c94817d8aa1a7410780d167ab300fd4930b0d7f34ddb29ef823
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7e46956b380d78a64dec4668e12b53de89850338ee63093213a02d925a2e1ff
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2348b8a6358edb6bb36e588c3df63b47b93dd621e5f96f92844453749a49160c
+size 1089994880

model.safetensors.index.json

@@ -0,0 +1,346 @@
+{
+  "metadata": {
+    "total_size": 15231233024
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00004-of-00004.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.norm.weight": "model-00003-of-00004.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": 3.0,
+    "total_flos": 489026734391296.0,
+    "train_loss": 0.5917462170697175,
+    "train_runtime": 8001.2912,
+    "train_samples_per_second": 3.731,
+    "train_steps_per_second": 0.039
+}

trainer_log.jsonl

@@ -0,0 +1,315 @@
+{"current_steps": 1, "total_steps": 312, "loss": 1.0619, "lr": 3.125e-07, "epoch": 0.009615384615384616, "percentage": 0.32, "elapsed_time": "0:00:19", "remaining_time": "1:43:12"}
+{"current_steps": 2, "total_steps": 312, "loss": 1.0454, "lr": 6.25e-07, "epoch": 0.019230769230769232, "percentage": 0.64, "elapsed_time": "0:00:33", "remaining_time": "1:26:19"}
+{"current_steps": 1, "total_steps": 312, "loss": 1.0619, "lr": 3.125e-07, "epoch": 0.009615384615384616, "percentage": 0.32, "elapsed_time": "0:02:49", "remaining_time": "14:37:45"}
+{"current_steps": 2, "total_steps": 312, "loss": 1.0454, "lr": 6.25e-07, "epoch": 0.019230769230769232, "percentage": 0.64, "elapsed_time": "0:03:02", "remaining_time": "7:51:07"}
+{"current_steps": 3, "total_steps": 312, "loss": 1.0873, "lr": 9.375000000000001e-07, "epoch": 0.028846153846153848, "percentage": 0.96, "elapsed_time": "0:03:14", "remaining_time": "5:33:21"}
+{"current_steps": 4, "total_steps": 312, "loss": 1.054, "lr": 1.25e-06, "epoch": 0.038461538461538464, "percentage": 1.28, "elapsed_time": "0:03:28", "remaining_time": "4:27:59"}
+{"current_steps": 5, "total_steps": 312, "loss": 1.0342, "lr": 1.5625e-06, "epoch": 0.04807692307692308, "percentage": 1.6, "elapsed_time": "0:03:44", "remaining_time": "3:49:39"}
+{"current_steps": 6, "total_steps": 312, "loss": 1.0297, "lr": 1.8750000000000003e-06, "epoch": 0.057692307692307696, "percentage": 1.92, "elapsed_time": "0:03:56", "remaining_time": "3:20:50"}
+{"current_steps": 7, "total_steps": 312, "loss": 0.9876, "lr": 2.1875000000000002e-06, "epoch": 0.0673076923076923, "percentage": 2.24, "elapsed_time": "0:04:08", "remaining_time": "3:00:46"}
+{"current_steps": 8, "total_steps": 312, "loss": 0.994, "lr": 2.5e-06, "epoch": 0.07692307692307693, "percentage": 2.56, "elapsed_time": "0:04:22", "remaining_time": "2:46:01"}
+{"current_steps": 9, "total_steps": 312, "loss": 0.934, "lr": 2.8125e-06, "epoch": 0.08653846153846154, "percentage": 2.88, "elapsed_time": "0:04:34", "remaining_time": "2:34:15"}
+{"current_steps": 10, "total_steps": 312, "loss": 0.9542, "lr": 3.125e-06, "epoch": 0.09615384615384616, "percentage": 3.21, "elapsed_time": "0:04:47", "remaining_time": "2:24:49"}
+{"current_steps": 11, "total_steps": 312, "loss": 0.9282, "lr": 3.4375e-06, "epoch": 0.10576923076923077, "percentage": 3.53, "elapsed_time": "0:05:01", "remaining_time": "2:17:25"}
+{"current_steps": 12, "total_steps": 312, "loss": 0.8984, "lr": 3.7500000000000005e-06, "epoch": 0.11538461538461539, "percentage": 3.85, "elapsed_time": "0:05:13", "remaining_time": "2:10:44"}
+{"current_steps": 13, "total_steps": 312, "loss": 0.9081, "lr": 4.0625000000000005e-06, "epoch": 0.125, "percentage": 4.17, "elapsed_time": "0:05:25", "remaining_time": "2:04:56"}
+{"current_steps": 14, "total_steps": 312, "loss": 0.8815, "lr": 4.3750000000000005e-06, "epoch": 0.1346153846153846, "percentage": 4.49, "elapsed_time": "0:05:41", "remaining_time": "2:01:02"}
+{"current_steps": 15, "total_steps": 312, "loss": 0.8703, "lr": 4.6875000000000004e-06, "epoch": 0.14423076923076922, "percentage": 4.81, "elapsed_time": "0:05:53", "remaining_time": "1:56:37"}
+{"current_steps": 16, "total_steps": 312, "loss": 0.8433, "lr": 5e-06, "epoch": 0.15384615384615385, "percentage": 5.13, "elapsed_time": "0:06:05", "remaining_time": "1:52:41"}
+{"current_steps": 17, "total_steps": 312, "loss": 0.8102, "lr": 5.3125e-06, "epoch": 0.16346153846153846, "percentage": 5.45, "elapsed_time": "0:06:18", "remaining_time": "1:49:20"}
+{"current_steps": 18, "total_steps": 312, "loss": 0.799, "lr": 5.625e-06, "epoch": 0.17307692307692307, "percentage": 5.77, "elapsed_time": "0:06:29", "remaining_time": "1:46:02"}
+{"current_steps": 19, "total_steps": 312, "loss": 0.7913, "lr": 5.9375e-06, "epoch": 0.18269230769230768, "percentage": 6.09, "elapsed_time": "0:06:41", "remaining_time": "1:43:18"}
+{"current_steps": 20, "total_steps": 312, "loss": 0.7863, "lr": 6.25e-06, "epoch": 0.19230769230769232, "percentage": 6.41, "elapsed_time": "0:06:55", "remaining_time": "1:41:07"}
+{"current_steps": 21, "total_steps": 312, "loss": 0.7495, "lr": 6.5625e-06, "epoch": 0.20192307692307693, "percentage": 6.73, "elapsed_time": "0:07:08", "remaining_time": "1:38:51"}
+{"current_steps": 22, "total_steps": 312, "loss": 0.7596, "lr": 6.875e-06, "epoch": 0.21153846153846154, "percentage": 7.05, "elapsed_time": "0:10:16", "remaining_time": "2:15:27"}
+{"current_steps": 23, "total_steps": 312, "loss": 0.7542, "lr": 7.1875e-06, "epoch": 0.22115384615384615, "percentage": 7.37, "elapsed_time": "0:10:29", "remaining_time": "2:11:52"}
+{"current_steps": 24, "total_steps": 312, "loss": 0.7316, "lr": 7.500000000000001e-06, "epoch": 0.23076923076923078, "percentage": 7.69, "elapsed_time": "0:10:42", "remaining_time": "2:08:29"}
+{"current_steps": 25, "total_steps": 312, "loss": 0.7273, "lr": 7.8125e-06, "epoch": 0.2403846153846154, "percentage": 8.01, "elapsed_time": "0:10:59", "remaining_time": "2:06:08"}
+{"current_steps": 26, "total_steps": 312, "loss": 0.7273, "lr": 8.125000000000001e-06, "epoch": 0.25, "percentage": 8.33, "elapsed_time": "0:11:12", "remaining_time": "2:03:17"}
+{"current_steps": 27, "total_steps": 312, "loss": 0.713, "lr": 8.4375e-06, "epoch": 0.25961538461538464, "percentage": 8.65, "elapsed_time": "0:11:25", "remaining_time": "2:00:33"}
+{"current_steps": 28, "total_steps": 312, "loss": 0.7092, "lr": 8.750000000000001e-06, "epoch": 0.2692307692307692, "percentage": 8.97, "elapsed_time": "0:11:38", "remaining_time": "1:58:07"}
+{"current_steps": 29, "total_steps": 312, "loss": 0.6919, "lr": 9.0625e-06, "epoch": 0.27884615384615385, "percentage": 9.29, "elapsed_time": "0:11:51", "remaining_time": "1:55:44"}
+{"current_steps": 30, "total_steps": 312, "loss": 0.7106, "lr": 9.375000000000001e-06, "epoch": 0.28846153846153844, "percentage": 9.62, "elapsed_time": "0:12:05", "remaining_time": "1:53:44"}
+{"current_steps": 31, "total_steps": 312, "loss": 0.6971, "lr": 9.6875e-06, "epoch": 0.2980769230769231, "percentage": 9.94, "elapsed_time": "0:12:18", "remaining_time": "1:51:37"}
+{"current_steps": 32, "total_steps": 312, "loss": 0.6849, "lr": 1e-05, "epoch": 0.3076923076923077, "percentage": 10.26, "elapsed_time": "0:12:32", "remaining_time": "1:49:41"}
+{"current_steps": 33, "total_steps": 312, "loss": 0.6753, "lr": 9.999685283773504e-06, "epoch": 0.3173076923076923, "percentage": 10.58, "elapsed_time": "0:12:45", "remaining_time": "1:47:54"}
+{"current_steps": 34, "total_steps": 312, "loss": 0.6717, "lr": 9.998741174712534e-06, "epoch": 0.3269230769230769, "percentage": 10.9, "elapsed_time": "0:12:59", "remaining_time": "1:46:09"}
+{"current_steps": 35, "total_steps": 312, "loss": 0.6735, "lr": 9.997167791667668e-06, "epoch": 0.33653846153846156, "percentage": 11.22, "elapsed_time": "0:16:05", "remaining_time": "2:07:25"}
+{"current_steps": 36, "total_steps": 312, "loss": 0.6842, "lr": 9.994965332706574e-06, "epoch": 0.34615384615384615, "percentage": 11.54, "elapsed_time": "0:16:18", "remaining_time": "2:05:04"}
+{"current_steps": 37, "total_steps": 312, "loss": 0.6787, "lr": 9.992134075089085e-06, "epoch": 0.3557692307692308, "percentage": 11.86, "elapsed_time": "0:19:27", "remaining_time": "2:24:39"}
+{"current_steps": 38, "total_steps": 312, "loss": 0.6834, "lr": 9.98867437523228e-06, "epoch": 0.36538461538461536, "percentage": 12.18, "elapsed_time": "0:19:42", "remaining_time": "2:22:03"}
+{"current_steps": 39, "total_steps": 312, "loss": 0.6566, "lr": 9.984586668665641e-06, "epoch": 0.375, "percentage": 12.5, "elapsed_time": "0:19:54", "remaining_time": "2:19:21"}
+{"current_steps": 40, "total_steps": 312, "loss": 0.6797, "lr": 9.979871469976197e-06, "epoch": 0.38461538461538464, "percentage": 12.82, "elapsed_time": "0:20:59", "remaining_time": "2:22:47"}
+{"current_steps": 41, "total_steps": 312, "loss": 0.6739, "lr": 9.974529372743762e-06, "epoch": 0.3942307692307692, "percentage": 13.14, "elapsed_time": "0:23:38", "remaining_time": "2:36:18"}
+{"current_steps": 42, "total_steps": 312, "loss": 0.6335, "lr": 9.968561049466214e-06, "epoch": 0.40384615384615385, "percentage": 13.46, "elapsed_time": "0:23:51", "remaining_time": "2:33:21"}
+{"current_steps": 43, "total_steps": 312, "loss": 0.6466, "lr": 9.961967251474823e-06, "epoch": 0.41346153846153844, "percentage": 13.78, "elapsed_time": "0:24:04", "remaining_time": "2:30:33"}
+{"current_steps": 44, "total_steps": 312, "loss": 0.6509, "lr": 9.954748808839675e-06, "epoch": 0.4230769230769231, "percentage": 14.1, "elapsed_time": "0:24:17", "remaining_time": "2:27:55"}
+{"current_steps": 45, "total_steps": 312, "loss": 0.6494, "lr": 9.946906630265184e-06, "epoch": 0.4326923076923077, "percentage": 14.42, "elapsed_time": "0:24:31", "remaining_time": "2:25:30"}
+{"current_steps": 46, "total_steps": 312, "loss": 0.6479, "lr": 9.938441702975689e-06, "epoch": 0.4423076923076923, "percentage": 14.74, "elapsed_time": "0:24:44", "remaining_time": "2:23:05"}
+{"current_steps": 47, "total_steps": 312, "loss": 0.6611, "lr": 9.92935509259118e-06, "epoch": 0.4519230769230769, "percentage": 15.06, "elapsed_time": "0:24:57", "remaining_time": "2:20:45"}
+{"current_steps": 48, "total_steps": 312, "loss": 0.654, "lr": 9.91964794299315e-06, "epoch": 0.46153846153846156, "percentage": 15.38, "elapsed_time": "0:25:12", "remaining_time": "2:18:37"}
+{"current_steps": 49, "total_steps": 312, "loss": 0.6473, "lr": 9.909321476180594e-06, "epoch": 0.47115384615384615, "percentage": 15.71, "elapsed_time": "0:25:25", "remaining_time": "2:16:28"}
+{"current_steps": 50, "total_steps": 312, "loss": 0.649, "lr": 9.898376992116179e-06, "epoch": 0.4807692307692308, "percentage": 16.03, "elapsed_time": "0:25:39", "remaining_time": "2:14:26"}
+{"current_steps": 51, "total_steps": 312, "loss": 0.6413, "lr": 9.886815868562596e-06, "epoch": 0.49038461538461536, "percentage": 16.35, "elapsed_time": "0:25:52", "remaining_time": "2:12:26"}
+{"current_steps": 52, "total_steps": 312, "loss": 0.6328, "lr": 9.874639560909118e-06, "epoch": 0.5, "percentage": 16.67, "elapsed_time": "0:26:06", "remaining_time": "2:10:31"}
+{"current_steps": 53, "total_steps": 312, "loss": 0.6433, "lr": 9.861849601988384e-06, "epoch": 0.5096153846153846, "percentage": 16.99, "elapsed_time": "0:26:18", "remaining_time": "2:08:35"}
+{"current_steps": 54, "total_steps": 312, "loss": 0.6201, "lr": 9.848447601883436e-06, "epoch": 0.5192307692307693, "percentage": 17.31, "elapsed_time": "0:26:31", "remaining_time": "2:06:45"}
+{"current_steps": 55, "total_steps": 312, "loss": 0.6382, "lr": 9.834435247725032e-06, "epoch": 0.5288461538461539, "percentage": 17.63, "elapsed_time": "0:26:44", "remaining_time": "2:04:57"}
+{"current_steps": 56, "total_steps": 312, "loss": 0.627, "lr": 9.819814303479268e-06, "epoch": 0.5384615384615384, "percentage": 17.95, "elapsed_time": "0:26:59", "remaining_time": "2:03:21"}
+{"current_steps": 57, "total_steps": 312, "loss": 0.6139, "lr": 9.804586609725499e-06, "epoch": 0.5480769230769231, "percentage": 18.27, "elapsed_time": "0:27:12", "remaining_time": "2:01:41"}
+{"current_steps": 58, "total_steps": 312, "loss": 0.6335, "lr": 9.788754083424654e-06, "epoch": 0.5576923076923077, "percentage": 18.59, "elapsed_time": "0:27:25", "remaining_time": "2:00:05"}
+{"current_steps": 59, "total_steps": 312, "loss": 0.6308, "lr": 9.772318717677905e-06, "epoch": 0.5673076923076923, "percentage": 18.91, "elapsed_time": "0:27:38", "remaining_time": "1:58:32"}
+{"current_steps": 60, "total_steps": 312, "loss": 0.6124, "lr": 9.755282581475769e-06, "epoch": 0.5769230769230769, "percentage": 19.23, "elapsed_time": "0:27:51", "remaining_time": "1:56:59"}
+{"current_steps": 61, "total_steps": 312, "loss": 0.641, "lr": 9.737647819437645e-06, "epoch": 0.5865384615384616, "percentage": 19.55, "elapsed_time": "0:28:03", "remaining_time": "1:55:28"}
+{"current_steps": 62, "total_steps": 312, "loss": 0.6286, "lr": 9.719416651541839e-06, "epoch": 0.5961538461538461, "percentage": 19.87, "elapsed_time": "0:28:18", "remaining_time": "1:54:07"}
+{"current_steps": 63, "total_steps": 312, "loss": 0.6267, "lr": 9.700591372846096e-06, "epoch": 0.6057692307692307, "percentage": 20.19, "elapsed_time": "0:28:31", "remaining_time": "1:52:46"}
+{"current_steps": 64, "total_steps": 312, "loss": 0.6215, "lr": 9.681174353198687e-06, "epoch": 0.6153846153846154, "percentage": 20.51, "elapsed_time": "0:28:45", "remaining_time": "1:51:25"}
+{"current_steps": 65, "total_steps": 312, "loss": 0.6195, "lr": 9.661168036940071e-06, "epoch": 0.625, "percentage": 20.83, "elapsed_time": "0:28:58", "remaining_time": "1:50:07"}
+{"current_steps": 66, "total_steps": 312, "loss": 0.618, "lr": 9.640574942595195e-06, "epoch": 0.6346153846153846, "percentage": 21.15, "elapsed_time": "0:29:11", "remaining_time": "1:48:48"}
+{"current_steps": 67, "total_steps": 312, "loss": 0.6229, "lr": 9.619397662556434e-06, "epoch": 0.6442307692307693, "percentage": 21.47, "elapsed_time": "0:29:25", "remaining_time": "1:47:35"}
+{"current_steps": 68, "total_steps": 312, "loss": 0.6329, "lr": 9.597638862757255e-06, "epoch": 0.6538461538461539, "percentage": 21.79, "elapsed_time": "0:29:39", "remaining_time": "1:46:24"}
+{"current_steps": 69, "total_steps": 312, "loss": 0.6304, "lr": 9.5753012823366e-06, "epoch": 0.6634615384615384, "percentage": 22.12, "elapsed_time": "0:29:51", "remaining_time": "1:45:10"}
+{"current_steps": 70, "total_steps": 312, "loss": 0.6304, "lr": 9.552387733294081e-06, "epoch": 0.6730769230769231, "percentage": 22.44, "elapsed_time": "0:30:07", "remaining_time": "1:44:07"}
+{"current_steps": 71, "total_steps": 312, "loss": 0.6207, "lr": 9.528901100135971e-06, "epoch": 0.6826923076923077, "percentage": 22.76, "elapsed_time": "0:30:21", "remaining_time": "1:43:01"}
+{"current_steps": 72, "total_steps": 312, "loss": 0.6081, "lr": 9.504844339512096e-06, "epoch": 0.6923076923076923, "percentage": 23.08, "elapsed_time": "0:30:36", "remaining_time": "1:42:02"}
+{"current_steps": 73, "total_steps": 312, "loss": 0.615, "lr": 9.480220479843627e-06, "epoch": 0.7019230769230769, "percentage": 23.4, "elapsed_time": "0:30:51", "remaining_time": "1:41:02"}
+{"current_steps": 74, "total_steps": 312, "loss": 0.6149, "lr": 9.45503262094184e-06, "epoch": 0.7115384615384616, "percentage": 23.72, "elapsed_time": "0:31:04", "remaining_time": "1:39:55"}
+{"current_steps": 75, "total_steps": 312, "loss": 0.6255, "lr": 9.4292839336179e-06, "epoch": 0.7211538461538461, "percentage": 24.04, "elapsed_time": "0:31:17", "remaining_time": "1:38:54"}
+{"current_steps": 76, "total_steps": 312, "loss": 0.6112, "lr": 9.40297765928369e-06, "epoch": 0.7307692307692307, "percentage": 24.36, "elapsed_time": "0:31:33", "remaining_time": "1:38:00"}
+{"current_steps": 77, "total_steps": 312, "loss": 0.6422, "lr": 9.376117109543769e-06, "epoch": 0.7403846153846154, "percentage": 24.68, "elapsed_time": "0:31:47", "remaining_time": "1:37:01"}
+{"current_steps": 78, "total_steps": 312, "loss": 0.62, "lr": 9.348705665778479e-06, "epoch": 0.75, "percentage": 25.0, "elapsed_time": "0:32:01", "remaining_time": "1:36:04"}
+{"current_steps": 79, "total_steps": 312, "loss": 0.6203, "lr": 9.320746778718274e-06, "epoch": 0.7596153846153846, "percentage": 25.32, "elapsed_time": "0:32:14", "remaining_time": "1:35:05"}
+{"current_steps": 80, "total_steps": 312, "loss": 0.6171, "lr": 9.292243968009332e-06, "epoch": 0.7692307692307693, "percentage": 25.64, "elapsed_time": "0:32:27", "remaining_time": "1:34:07"}
+{"current_steps": 81, "total_steps": 312, "loss": 0.6134, "lr": 9.263200821770462e-06, "epoch": 0.7788461538461539, "percentage": 25.96, "elapsed_time": "0:32:39", "remaining_time": "1:33:09"}
+{"current_steps": 82, "total_steps": 312, "loss": 0.6129, "lr": 9.233620996141421e-06, "epoch": 0.7884615384615384, "percentage": 26.28, "elapsed_time": "0:32:53", "remaining_time": "1:32:14"}
+{"current_steps": 83, "total_steps": 312, "loss": 0.618, "lr": 9.203508214822652e-06, "epoch": 0.7980769230769231, "percentage": 26.6, "elapsed_time": "0:33:06", "remaining_time": "1:31:20"}
+{"current_steps": 84, "total_steps": 312, "loss": 0.6082, "lr": 9.172866268606514e-06, "epoch": 0.8076923076923077, "percentage": 26.92, "elapsed_time": "0:33:19", "remaining_time": "1:30:27"}
+{"current_steps": 85, "total_steps": 312, "loss": 0.5974, "lr": 9.141699014900084e-06, "epoch": 0.8173076923076923, "percentage": 27.24, "elapsed_time": "0:33:32", "remaining_time": "1:29:35"}
+{"current_steps": 86, "total_steps": 312, "loss": 0.6157, "lr": 9.110010377239552e-06, "epoch": 0.8269230769230769, "percentage": 27.56, "elapsed_time": "0:33:45", "remaining_time": "1:28:43"}
+{"current_steps": 87, "total_steps": 312, "loss": 0.6301, "lr": 9.077804344796302e-06, "epoch": 0.8365384615384616, "percentage": 27.88, "elapsed_time": "0:34:00", "remaining_time": "1:27:56"}
+{"current_steps": 88, "total_steps": 312, "loss": 0.6226, "lr": 9.045084971874738e-06, "epoch": 0.8461538461538461, "percentage": 28.21, "elapsed_time": "0:34:12", "remaining_time": "1:27:04"}
+{"current_steps": 89, "total_steps": 312, "loss": 0.6, "lr": 9.011856377401891e-06, "epoch": 0.8557692307692307, "percentage": 28.53, "elapsed_time": "0:34:25", "remaining_time": "1:26:15"}
+{"current_steps": 90, "total_steps": 312, "loss": 0.6245, "lr": 8.978122744408905e-06, "epoch": 0.8653846153846154, "percentage": 28.85, "elapsed_time": "0:34:39", "remaining_time": "1:25:29"}
+{"current_steps": 91, "total_steps": 312, "loss": 0.6095, "lr": 8.943888319504456e-06, "epoch": 0.875, "percentage": 29.17, "elapsed_time": "0:34:54", "remaining_time": "1:24:45"}
+{"current_steps": 92, "total_steps": 312, "loss": 0.6093, "lr": 8.90915741234015e-06, "epoch": 0.8846153846153846, "percentage": 29.49, "elapsed_time": "0:35:07", "remaining_time": "1:23:59"}
+{"current_steps": 93, "total_steps": 312, "loss": 0.6067, "lr": 8.873934395068006e-06, "epoch": 0.8942307692307693, "percentage": 29.81, "elapsed_time": "0:35:20", "remaining_time": "1:23:12"}
+{"current_steps": 94, "total_steps": 312, "loss": 0.6219, "lr": 8.838223701790057e-06, "epoch": 0.9038461538461539, "percentage": 30.13, "elapsed_time": "0:35:33", "remaining_time": "1:22:28"}
+{"current_steps": 95, "total_steps": 312, "loss": 0.5999, "lr": 8.802029828000157e-06, "epoch": 0.9134615384615384, "percentage": 30.45, "elapsed_time": "0:35:45", "remaining_time": "1:21:40"}
+{"current_steps": 96, "total_steps": 312, "loss": 0.6132, "lr": 8.765357330018056e-06, "epoch": 0.9230769230769231, "percentage": 30.77, "elapsed_time": "0:35:57", "remaining_time": "1:20:54"}
+{"current_steps": 97, "total_steps": 312, "loss": 0.6014, "lr": 8.728210824415829e-06, "epoch": 0.9326923076923077, "percentage": 31.09, "elapsed_time": "0:36:09", "remaining_time": "1:20:09"}
+{"current_steps": 98, "total_steps": 312, "loss": 0.6062, "lr": 8.690594987436705e-06, "epoch": 0.9423076923076923, "percentage": 31.41, "elapsed_time": "0:36:23", "remaining_time": "1:19:28"}
+{"current_steps": 99, "total_steps": 312, "loss": 0.6101, "lr": 8.652514554406388e-06, "epoch": 0.9519230769230769, "percentage": 31.73, "elapsed_time": "0:36:35", "remaining_time": "1:18:44"}
+{"current_steps": 100, "total_steps": 312, "loss": 0.6134, "lr": 8.613974319136959e-06, "epoch": 0.9615384615384616, "percentage": 32.05, "elapsed_time": "0:36:49", "remaining_time": "1:18:03"}
+{"current_steps": 101, "total_steps": 312, "loss": 0.599, "lr": 8.574979133323378e-06, "epoch": 0.9711538461538461, "percentage": 32.37, "elapsed_time": "0:37:28", "remaining_time": "1:18:17"}
+{"current_steps": 102, "total_steps": 312, "loss": 0.6111, "lr": 8.535533905932739e-06, "epoch": 0.9807692307692307, "percentage": 32.69, "elapsed_time": "0:37:42", "remaining_time": "1:17:38"}
+{"current_steps": 103, "total_steps": 312, "loss": 0.5939, "lr": 8.495643602586287e-06, "epoch": 0.9903846153846154, "percentage": 33.01, "elapsed_time": "0:37:56", "remaining_time": "1:16:59"}
+{"current_steps": 104, "total_steps": 312, "loss": 0.6095, "lr": 8.455313244934324e-06, "epoch": 1.0, "percentage": 33.33, "elapsed_time": "0:38:09", "remaining_time": "1:16:18"}
+{"current_steps": 105, "total_steps": 312, "loss": 0.5796, "lr": 8.414547910024035e-06, "epoch": 1.0096153846153846, "percentage": 33.65, "elapsed_time": "0:38:20", "remaining_time": "1:15:34"}
+{"current_steps": 106, "total_steps": 312, "loss": 0.5544, "lr": 8.373352729660373e-06, "epoch": 1.0192307692307692, "percentage": 33.97, "elapsed_time": "0:38:33", "remaining_time": "1:14:56"}
+{"current_steps": 107, "total_steps": 312, "loss": 0.5746, "lr": 8.331732889760021e-06, "epoch": 1.0288461538461537, "percentage": 34.29, "elapsed_time": "0:38:46", "remaining_time": "1:14:17"}
+{"current_steps": 108, "total_steps": 312, "loss": 0.552, "lr": 8.289693629698564e-06, "epoch": 1.0384615384615385, "percentage": 34.62, "elapsed_time": "0:39:00", "remaining_time": "1:13:40"}
+{"current_steps": 109, "total_steps": 312, "loss": 0.5587, "lr": 8.247240241650918e-06, "epoch": 1.0480769230769231, "percentage": 34.94, "elapsed_time": "0:39:12", "remaining_time": "1:13:01"}
+{"current_steps": 110, "total_steps": 312, "loss": 0.5603, "lr": 8.204378069925121e-06, "epoch": 1.0576923076923077, "percentage": 35.26, "elapsed_time": "0:39:25", "remaining_time": "1:12:23"}
+{"current_steps": 111, "total_steps": 312, "loss": 0.5683, "lr": 8.16111251028955e-06, "epoch": 1.0673076923076923, "percentage": 35.58, "elapsed_time": "0:39:38", "remaining_time": "1:11:46"}
+{"current_steps": 112, "total_steps": 312, "loss": 0.5687, "lr": 8.117449009293668e-06, "epoch": 1.0769230769230769, "percentage": 35.9, "elapsed_time": "0:39:51", "remaining_time": "1:11:10"}
+{"current_steps": 113, "total_steps": 312, "loss": 0.5493, "lr": 8.073393063582386e-06, "epoch": 1.0865384615384615, "percentage": 36.22, "elapsed_time": "0:40:04", "remaining_time": "1:10:34"}
+{"current_steps": 114, "total_steps": 312, "loss": 0.5628, "lr": 8.0289502192041e-06, "epoch": 1.0961538461538463, "percentage": 36.54, "elapsed_time": "0:40:16", "remaining_time": "1:09:57"}
+{"current_steps": 115, "total_steps": 312, "loss": 0.5859, "lr": 7.984126070912519e-06, "epoch": 1.1057692307692308, "percentage": 36.86, "elapsed_time": "0:40:29", "remaining_time": "1:09:22"}
+{"current_steps": 116, "total_steps": 312, "loss": 0.55, "lr": 7.938926261462366e-06, "epoch": 1.1153846153846154, "percentage": 37.18, "elapsed_time": "0:40:43", "remaining_time": "1:08:49"}
+{"current_steps": 117, "total_steps": 312, "loss": 0.5868, "lr": 7.89335648089903e-06, "epoch": 1.125, "percentage": 37.5, "elapsed_time": "0:40:58", "remaining_time": "1:08:17"}
+{"current_steps": 118, "total_steps": 312, "loss": 0.5477, "lr": 7.84742246584226e-06, "epoch": 1.1346153846153846, "percentage": 37.82, "elapsed_time": "0:41:11", "remaining_time": "1:07:42"}
+{"current_steps": 119, "total_steps": 312, "loss": 0.5579, "lr": 7.801129998764014e-06, "epoch": 1.1442307692307692, "percentage": 38.14, "elapsed_time": "0:41:24", "remaining_time": "1:07:09"}
+{"current_steps": 120, "total_steps": 312, "loss": 0.5689, "lr": 7.754484907260513e-06, "epoch": 1.1538461538461537, "percentage": 38.46, "elapsed_time": "0:41:38", "remaining_time": "1:06:37"}
+{"current_steps": 121, "total_steps": 312, "loss": 0.5714, "lr": 7.70749306331863e-06, "epoch": 1.1634615384615385, "percentage": 38.78, "elapsed_time": "0:41:51", "remaining_time": "1:06:04"}
+{"current_steps": 122, "total_steps": 312, "loss": 0.5655, "lr": 7.660160382576683e-06, "epoch": 1.1730769230769231, "percentage": 39.1, "elapsed_time": "0:42:05", "remaining_time": "1:05:33"}
+{"current_steps": 123, "total_steps": 312, "loss": 0.566, "lr": 7.612492823579744e-06, "epoch": 1.1826923076923077, "percentage": 39.42, "elapsed_time": "0:42:18", "remaining_time": "1:05:01"}
+{"current_steps": 124, "total_steps": 312, "loss": 0.5569, "lr": 7.564496387029532e-06, "epoch": 1.1923076923076923, "percentage": 39.74, "elapsed_time": "0:42:30", "remaining_time": "1:04:26"}
+{"current_steps": 125, "total_steps": 312, "loss": 0.5745, "lr": 7.516177115029002e-06, "epoch": 1.2019230769230769, "percentage": 40.06, "elapsed_time": "0:42:43", "remaining_time": "1:03:55"}
+{"current_steps": 126, "total_steps": 312, "loss": 0.5762, "lr": 7.467541090321735e-06, "epoch": 1.2115384615384615, "percentage": 40.38, "elapsed_time": "0:45:18", "remaining_time": "1:06:53"}
+{"current_steps": 127, "total_steps": 312, "loss": 0.5908, "lr": 7.4185944355261996e-06, "epoch": 1.2211538461538463, "percentage": 40.71, "elapsed_time": "0:45:31", "remaining_time": "1:06:19"}
+{"current_steps": 128, "total_steps": 312, "loss": 0.5605, "lr": 7.369343312364994e-06, "epoch": 1.2307692307692308, "percentage": 41.03, "elapsed_time": "0:45:43", "remaining_time": "1:05:43"}
+{"current_steps": 129, "total_steps": 312, "loss": 0.5707, "lr": 7.319793920889171e-06, "epoch": 1.2403846153846154, "percentage": 41.35, "elapsed_time": "0:45:56", "remaining_time": "1:05:09"}
+{"current_steps": 130, "total_steps": 312, "loss": 0.5698, "lr": 7.269952498697734e-06, "epoch": 1.25, "percentage": 41.67, "elapsed_time": "0:46:09", "remaining_time": "1:04:37"}
+{"current_steps": 131, "total_steps": 312, "loss": 0.5591, "lr": 7.219825320152411e-06, "epoch": 1.2596153846153846, "percentage": 41.99, "elapsed_time": "0:46:22", "remaining_time": "1:04:04"}
+{"current_steps": 132, "total_steps": 312, "loss": 0.5639, "lr": 7.169418695587791e-06, "epoch": 1.2692307692307692, "percentage": 42.31, "elapsed_time": "0:46:35", "remaining_time": "1:03:31"}
+{"current_steps": 133, "total_steps": 312, "loss": 0.5547, "lr": 7.118738970516944e-06, "epoch": 1.2788461538461537, "percentage": 42.63, "elapsed_time": "0:46:46", "remaining_time": "1:02:57"}
+{"current_steps": 134, "total_steps": 312, "loss": 0.5705, "lr": 7.067792524832604e-06, "epoch": 1.2884615384615383, "percentage": 42.95, "elapsed_time": "0:46:58", "remaining_time": "1:02:23"}
+{"current_steps": 135, "total_steps": 312, "loss": 0.5538, "lr": 7.016585772004026e-06, "epoch": 1.2980769230769231, "percentage": 43.27, "elapsed_time": "0:47:10", "remaining_time": "1:01:50"}
+{"current_steps": 136, "total_steps": 312, "loss": 0.5609, "lr": 6.965125158269619e-06, "epoch": 1.3076923076923077, "percentage": 43.59, "elapsed_time": "0:47:22", "remaining_time": "1:01:18"}
+{"current_steps": 137, "total_steps": 312, "loss": 0.5609, "lr": 6.913417161825449e-06, "epoch": 1.3173076923076923, "percentage": 43.91, "elapsed_time": "0:47:35", "remaining_time": "1:00:47"}
+{"current_steps": 138, "total_steps": 312, "loss": 0.5614, "lr": 6.8614682920097265e-06, "epoch": 1.3269230769230769, "percentage": 44.23, "elapsed_time": "0:47:48", "remaining_time": "1:00:16"}
+{"current_steps": 139, "total_steps": 312, "loss": 0.5687, "lr": 6.809285088483361e-06, "epoch": 1.3365384615384617, "percentage": 44.55, "elapsed_time": "0:48:02", "remaining_time": "0:59:48"}
+{"current_steps": 140, "total_steps": 312, "loss": 0.5595, "lr": 6.7568741204067145e-06, "epoch": 1.3461538461538463, "percentage": 44.87, "elapsed_time": "0:48:15", "remaining_time": "0:59:17"}
+{"current_steps": 141, "total_steps": 312, "loss": 0.5651, "lr": 6.704241985612625e-06, "epoch": 1.3557692307692308, "percentage": 45.19, "elapsed_time": "0:48:28", "remaining_time": "0:58:47"}
+{"current_steps": 142, "total_steps": 312, "loss": 0.5651, "lr": 6.651395309775837e-06, "epoch": 1.3653846153846154, "percentage": 45.51, "elapsed_time": "0:48:41", "remaining_time": "0:58:18"}
+{"current_steps": 143, "total_steps": 312, "loss": 0.5513, "lr": 6.598340745578908e-06, "epoch": 1.375, "percentage": 45.83, "elapsed_time": "0:48:54", "remaining_time": "0:57:47"}
+{"current_steps": 144, "total_steps": 312, "loss": 0.5445, "lr": 6.545084971874738e-06, "epoch": 1.3846153846153846, "percentage": 46.15, "elapsed_time": "0:49:17", "remaining_time": "0:57:30"}
+{"current_steps": 145, "total_steps": 312, "loss": 0.5613, "lr": 6.491634692845781e-06, "epoch": 1.3942307692307692, "percentage": 46.47, "elapsed_time": "0:49:34", "remaining_time": "0:57:05"}
+{"current_steps": 146, "total_steps": 312, "loss": 0.5872, "lr": 6.437996637160086e-06, "epoch": 1.4038461538461537, "percentage": 46.79, "elapsed_time": "0:49:46", "remaining_time": "0:56:35"}
+{"current_steps": 147, "total_steps": 312, "loss": 0.5705, "lr": 6.384177557124247e-06, "epoch": 1.4134615384615383, "percentage": 47.12, "elapsed_time": "0:49:59", "remaining_time": "0:56:06"}
+{"current_steps": 148, "total_steps": 312, "loss": 0.5652, "lr": 6.330184227833376e-06, "epoch": 1.4230769230769231, "percentage": 47.44, "elapsed_time": "0:50:13", "remaining_time": "0:55:38"}
+{"current_steps": 149, "total_steps": 312, "loss": 0.5534, "lr": 6.276023446318214e-06, "epoch": 1.4326923076923077, "percentage": 47.76, "elapsed_time": "0:50:25", "remaining_time": "0:55:10"}
+{"current_steps": 150, "total_steps": 312, "loss": 0.5449, "lr": 6.2217020306894705e-06, "epoch": 1.4423076923076923, "percentage": 48.08, "elapsed_time": "0:50:39", "remaining_time": "0:54:42"}
+{"current_steps": 151, "total_steps": 312, "loss": 0.5382, "lr": 6.1672268192795285e-06, "epoch": 1.4519230769230769, "percentage": 48.4, "elapsed_time": "0:50:51", "remaining_time": "0:54:13"}
+{"current_steps": 152, "total_steps": 312, "loss": 0.5447, "lr": 6.112604669781572e-06, "epoch": 1.4615384615384617, "percentage": 48.72, "elapsed_time": "0:51:03", "remaining_time": "0:53:45"}
+{"current_steps": 153, "total_steps": 312, "loss": 0.5586, "lr": 6.057842458386315e-06, "epoch": 1.4711538461538463, "percentage": 49.04, "elapsed_time": "0:51:16", "remaining_time": "0:53:16"}
+{"current_steps": 154, "total_steps": 312, "loss": 0.5621, "lr": 6.002947078916365e-06, "epoch": 1.4807692307692308, "percentage": 49.36, "elapsed_time": "0:51:30", "remaining_time": "0:52:50"}
+{"current_steps": 155, "total_steps": 312, "loss": 0.5517, "lr": 5.947925441958393e-06, "epoch": 1.4903846153846154, "percentage": 49.68, "elapsed_time": "0:51:42", "remaining_time": "0:52:22"}
+{"current_steps": 156, "total_steps": 312, "loss": 0.5713, "lr": 5.892784473993184e-06, "epoch": 1.5, "percentage": 50.0, "elapsed_time": "0:51:55", "remaining_time": "0:51:55"}
+{"current_steps": 157, "total_steps": 312, "loss": 0.5507, "lr": 5.837531116523683e-06, "epoch": 1.5096153846153846, "percentage": 50.32, "elapsed_time": "0:52:08", "remaining_time": "0:51:28"}
+{"current_steps": 158, "total_steps": 312, "loss": 0.5472, "lr": 5.782172325201155e-06, "epoch": 1.5192307692307692, "percentage": 50.64, "elapsed_time": "0:52:22", "remaining_time": "0:51:02"}
+{"current_steps": 159, "total_steps": 312, "loss": 0.5566, "lr": 5.726715068949564e-06, "epoch": 1.5288461538461537, "percentage": 50.96, "elapsed_time": "0:52:36", "remaining_time": "0:50:37"}
+{"current_steps": 160, "total_steps": 312, "loss": 0.5324, "lr": 5.671166329088278e-06, "epoch": 1.5384615384615383, "percentage": 51.28, "elapsed_time": "0:52:49", "remaining_time": "0:50:10"}
+{"current_steps": 161, "total_steps": 312, "loss": 0.5681, "lr": 5.615533098453215e-06, "epoch": 1.5480769230769231, "percentage": 51.6, "elapsed_time": "0:53:01", "remaining_time": "0:49:44"}
+{"current_steps": 162, "total_steps": 312, "loss": 0.5689, "lr": 5.559822380516539e-06, "epoch": 1.5576923076923077, "percentage": 51.92, "elapsed_time": "0:53:14", "remaining_time": "0:49:17"}
+{"current_steps": 163, "total_steps": 312, "loss": 0.559, "lr": 5.504041188505022e-06, "epoch": 1.5673076923076923, "percentage": 52.24, "elapsed_time": "0:53:27", "remaining_time": "0:48:52"}
+{"current_steps": 164, "total_steps": 312, "loss": 0.5607, "lr": 5.448196544517168e-06, "epoch": 1.5769230769230769, "percentage": 52.56, "elapsed_time": "0:53:39", "remaining_time": "0:48:25"}
+{"current_steps": 165, "total_steps": 312, "loss": 0.558, "lr": 5.392295478639226e-06, "epoch": 1.5865384615384617, "percentage": 52.88, "elapsed_time": "0:53:51", "remaining_time": "0:47:59"}
+{"current_steps": 166, "total_steps": 312, "loss": 0.5576, "lr": 5.336345028060199e-06, "epoch": 1.5961538461538463, "percentage": 53.21, "elapsed_time": "0:54:04", "remaining_time": "0:47:33"}
+{"current_steps": 167, "total_steps": 312, "loss": 0.536, "lr": 5.2803522361859596e-06, "epoch": 1.6057692307692308, "percentage": 53.53, "elapsed_time": "0:54:19", "remaining_time": "0:47:10"}
+{"current_steps": 168, "total_steps": 312, "loss": 0.5529, "lr": 5.224324151752575e-06, "epoch": 1.6153846153846154, "percentage": 53.85, "elapsed_time": "0:55:55", "remaining_time": "0:47:55"}
+{"current_steps": 169, "total_steps": 312, "loss": 0.5571, "lr": 5.168267827938971e-06, "epoch": 1.625, "percentage": 54.17, "elapsed_time": "0:58:07", "remaining_time": "0:49:10"}
+{"current_steps": 170, "total_steps": 312, "loss": 0.547, "lr": 5.112190321479026e-06, "epoch": 1.6346153846153846, "percentage": 54.49, "elapsed_time": "0:59:01", "remaining_time": "0:49:18"}
+{"current_steps": 171, "total_steps": 312, "loss": 0.5339, "lr": 5.05609869177323e-06, "epoch": 1.6442307692307692, "percentage": 54.81, "elapsed_time": "0:59:15", "remaining_time": "0:48:51"}
+{"current_steps": 172, "total_steps": 312, "loss": 0.5534, "lr": 5e-06, "epoch": 1.6538461538461537, "percentage": 55.13, "elapsed_time": "0:59:28", "remaining_time": "0:48:24"}
+{"current_steps": 173, "total_steps": 312, "loss": 0.5417, "lr": 4.943901308226771e-06, "epoch": 1.6634615384615383, "percentage": 55.45, "elapsed_time": "1:01:07", "remaining_time": "0:49:06"}
+{"current_steps": 174, "total_steps": 312, "loss": 0.5713, "lr": 4.887809678520976e-06, "epoch": 1.6730769230769231, "percentage": 55.77, "elapsed_time": "1:01:20", "remaining_time": "0:48:38"}
+{"current_steps": 175, "total_steps": 312, "loss": 0.5618, "lr": 4.831732172061032e-06, "epoch": 1.6826923076923077, "percentage": 56.09, "elapsed_time": "1:01:34", "remaining_time": "0:48:12"}
+{"current_steps": 176, "total_steps": 312, "loss": 0.5711, "lr": 4.775675848247427e-06, "epoch": 1.6923076923076923, "percentage": 56.41, "elapsed_time": "1:04:28", "remaining_time": "0:49:49"}
+{"current_steps": 177, "total_steps": 312, "loss": 0.5585, "lr": 4.719647763814041e-06, "epoch": 1.7019230769230769, "percentage": 56.73, "elapsed_time": "1:04:42", "remaining_time": "0:49:21"}
+{"current_steps": 178, "total_steps": 312, "loss": 0.5547, "lr": 4.663654971939802e-06, "epoch": 1.7115384615384617, "percentage": 57.05, "elapsed_time": "1:04:55", "remaining_time": "0:48:52"}
+{"current_steps": 179, "total_steps": 312, "loss": 0.5493, "lr": 4.6077045213607765e-06, "epoch": 1.7211538461538463, "percentage": 57.37, "elapsed_time": "1:05:55", "remaining_time": "0:48:59"}
+{"current_steps": 180, "total_steps": 312, "loss": 0.5551, "lr": 4.551803455482833e-06, "epoch": 1.7307692307692308, "percentage": 57.69, "elapsed_time": "1:07:51", "remaining_time": "0:49:45"}
+{"current_steps": 181, "total_steps": 312, "loss": 0.5573, "lr": 4.4959588114949785e-06, "epoch": 1.7403846153846154, "percentage": 58.01, "elapsed_time": "1:08:04", "remaining_time": "0:49:16"}
+{"current_steps": 182, "total_steps": 312, "loss": 0.553, "lr": 4.4401776194834615e-06, "epoch": 1.75, "percentage": 58.33, "elapsed_time": "1:08:18", "remaining_time": "0:48:47"}
+{"current_steps": 183, "total_steps": 312, "loss": 0.5784, "lr": 4.384466901546786e-06, "epoch": 1.7596153846153846, "percentage": 58.65, "elapsed_time": "1:08:32", "remaining_time": "0:48:18"}
+{"current_steps": 184, "total_steps": 312, "loss": 0.5558, "lr": 4.3288336709117246e-06, "epoch": 1.7692307692307692, "percentage": 58.97, "elapsed_time": "1:08:45", "remaining_time": "0:47:49"}
+{"current_steps": 185, "total_steps": 312, "loss": 0.5512, "lr": 4.273284931050438e-06, "epoch": 1.7788461538461537, "percentage": 59.29, "elapsed_time": "1:08:58", "remaining_time": "0:47:21"}
+{"current_steps": 186, "total_steps": 312, "loss": 0.5564, "lr": 4.217827674798845e-06, "epoch": 1.7884615384615383, "percentage": 59.62, "elapsed_time": "1:09:11", "remaining_time": "0:46:52"}
+{"current_steps": 187, "total_steps": 312, "loss": 0.5574, "lr": 4.162468883476319e-06, "epoch": 1.7980769230769231, "percentage": 59.94, "elapsed_time": "1:09:24", "remaining_time": "0:46:24"}
+{"current_steps": 188, "total_steps": 312, "loss": 0.5426, "lr": 4.107215526006818e-06, "epoch": 1.8076923076923077, "percentage": 60.26, "elapsed_time": "1:09:38", "remaining_time": "0:45:55"}
+{"current_steps": 189, "total_steps": 312, "loss": 0.5633, "lr": 4.052074558041608e-06, "epoch": 1.8173076923076923, "percentage": 60.58, "elapsed_time": "1:09:50", "remaining_time": "0:45:27"}
+{"current_steps": 190, "total_steps": 312, "loss": 0.5825, "lr": 3.997052921083637e-06, "epoch": 1.8269230769230769, "percentage": 60.9, "elapsed_time": "1:10:04", "remaining_time": "0:44:59"}
+{"current_steps": 191, "total_steps": 312, "loss": 0.5554, "lr": 3.9421575416136866e-06, "epoch": 1.8365384615384617, "percentage": 61.22, "elapsed_time": "1:10:17", "remaining_time": "0:44:31"}
+{"current_steps": 192, "total_steps": 312, "loss": 0.5454, "lr": 3.887395330218429e-06, "epoch": 1.8461538461538463, "percentage": 61.54, "elapsed_time": "1:10:30", "remaining_time": "0:44:04"}
+{"current_steps": 193, "total_steps": 312, "loss": 0.5568, "lr": 3.832773180720475e-06, "epoch": 1.8557692307692308, "percentage": 61.86, "elapsed_time": "1:10:45", "remaining_time": "0:43:37"}
+{"current_steps": 194, "total_steps": 312, "loss": 0.5574, "lr": 3.778297969310529e-06, "epoch": 1.8653846153846154, "percentage": 62.18, "elapsed_time": "1:10:59", "remaining_time": "0:43:10"}
+{"current_steps": 195, "total_steps": 312, "loss": 0.5534, "lr": 3.723976553681787e-06, "epoch": 1.875, "percentage": 62.5, "elapsed_time": "1:11:13", "remaining_time": "0:42:43"}
+{"current_steps": 196, "total_steps": 312, "loss": 0.5635, "lr": 3.669815772166625e-06, "epoch": 1.8846153846153846, "percentage": 62.82, "elapsed_time": "1:11:25", "remaining_time": "0:42:16"}
+{"current_steps": 197, "total_steps": 312, "loss": 0.5561, "lr": 3.6158224428757538e-06, "epoch": 1.8942307692307692, "percentage": 63.14, "elapsed_time": "1:11:37", "remaining_time": "0:41:48"}
+{"current_steps": 198, "total_steps": 312, "loss": 0.5563, "lr": 3.562003362839914e-06, "epoch": 1.9038461538461537, "percentage": 63.46, "elapsed_time": "1:11:52", "remaining_time": "0:41:22"}
+{"current_steps": 199, "total_steps": 312, "loss": 0.5522, "lr": 3.50836530715422e-06, "epoch": 1.9134615384615383, "percentage": 63.78, "elapsed_time": "1:12:05", "remaining_time": "0:40:56"}
+{"current_steps": 200, "total_steps": 312, "loss": 0.5593, "lr": 3.4549150281252635e-06, "epoch": 1.9230769230769231, "percentage": 64.1, "elapsed_time": "1:15:20", "remaining_time": "0:42:11"}
+{"current_steps": 201, "total_steps": 312, "loss": 0.5606, "lr": 3.4016592544210937e-06, "epoch": 1.9326923076923077, "percentage": 64.42, "elapsed_time": "1:16:06", "remaining_time": "0:42:01"}
+{"current_steps": 202, "total_steps": 312, "loss": 0.5724, "lr": 3.3486046902241663e-06, "epoch": 1.9423076923076923, "percentage": 64.74, "elapsed_time": "1:16:23", "remaining_time": "0:41:35"}
+{"current_steps": 203, "total_steps": 312, "loss": 0.5296, "lr": 3.295758014387375e-06, "epoch": 1.9519230769230769, "percentage": 65.06, "elapsed_time": "1:16:35", "remaining_time": "0:41:07"}
+{"current_steps": 204, "total_steps": 312, "loss": 0.5358, "lr": 3.2431258795932863e-06, "epoch": 1.9615384615384617, "percentage": 65.38, "elapsed_time": "1:16:48", "remaining_time": "0:40:39"}
+{"current_steps": 205, "total_steps": 312, "loss": 0.5427, "lr": 3.1907149115166403e-06, "epoch": 1.9711538461538463, "percentage": 65.71, "elapsed_time": "1:17:01", "remaining_time": "0:40:12"}
+{"current_steps": 206, "total_steps": 312, "loss": 0.5494, "lr": 3.1385317079902743e-06, "epoch": 1.9807692307692308, "percentage": 66.03, "elapsed_time": "1:17:16", "remaining_time": "0:39:45"}
+{"current_steps": 207, "total_steps": 312, "loss": 0.557, "lr": 3.0865828381745515e-06, "epoch": 1.9903846153846154, "percentage": 66.35, "elapsed_time": "1:17:28", "remaining_time": "0:39:18"}
+{"current_steps": 208, "total_steps": 312, "loss": 0.5498, "lr": 3.0348748417303826e-06, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "1:17:41", "remaining_time": "0:38:50"}
+{"current_steps": 209, "total_steps": 312, "loss": 0.5271, "lr": 2.9834142279959754e-06, "epoch": 2.0096153846153846, "percentage": 66.99, "elapsed_time": "1:17:54", "remaining_time": "0:38:23"}
+{"current_steps": 210, "total_steps": 312, "loss": 0.5306, "lr": 2.932207475167398e-06, "epoch": 2.019230769230769, "percentage": 67.31, "elapsed_time": "1:18:08", "remaining_time": "0:37:57"}
+{"current_steps": 211, "total_steps": 312, "loss": 0.5352, "lr": 2.8812610294830568e-06, "epoch": 2.0288461538461537, "percentage": 67.63, "elapsed_time": "1:18:21", "remaining_time": "0:37:30"}
+{"current_steps": 212, "total_steps": 312, "loss": 0.5146, "lr": 2.83058130441221e-06, "epoch": 2.0384615384615383, "percentage": 67.95, "elapsed_time": "1:18:34", "remaining_time": "0:37:03"}
+{"current_steps": 213, "total_steps": 312, "loss": 0.5203, "lr": 2.7801746798475905e-06, "epoch": 2.048076923076923, "percentage": 68.27, "elapsed_time": "1:18:46", "remaining_time": "0:36:37"}
+{"current_steps": 214, "total_steps": 312, "loss": 0.519, "lr": 2.7300475013022666e-06, "epoch": 2.0576923076923075, "percentage": 68.59, "elapsed_time": "1:19:01", "remaining_time": "0:36:11"}
+{"current_steps": 215, "total_steps": 312, "loss": 0.5243, "lr": 2.6802060791108304e-06, "epoch": 2.0673076923076925, "percentage": 68.91, "elapsed_time": "1:19:14", "remaining_time": "0:35:44"}
+{"current_steps": 216, "total_steps": 312, "loss": 0.5097, "lr": 2.6306566876350072e-06, "epoch": 2.076923076923077, "percentage": 69.23, "elapsed_time": "1:19:27", "remaining_time": "0:35:18"}
+{"current_steps": 217, "total_steps": 312, "loss": 0.5133, "lr": 2.5814055644738013e-06, "epoch": 2.0865384615384617, "percentage": 69.55, "elapsed_time": "1:19:39", "remaining_time": "0:34:52"}
+{"current_steps": 218, "total_steps": 312, "loss": 0.5249, "lr": 2.532458909678266e-06, "epoch": 2.0961538461538463, "percentage": 69.87, "elapsed_time": "1:19:53", "remaining_time": "0:34:26"}
+{"current_steps": 219, "total_steps": 312, "loss": 0.5082, "lr": 2.483822884971e-06, "epoch": 2.105769230769231, "percentage": 70.19, "elapsed_time": "1:20:08", "remaining_time": "0:34:01"}
+{"current_steps": 220, "total_steps": 312, "loss": 0.509, "lr": 2.43550361297047e-06, "epoch": 2.1153846153846154, "percentage": 70.51, "elapsed_time": "1:20:20", "remaining_time": "0:33:35"}
+{"current_steps": 221, "total_steps": 312, "loss": 0.5439, "lr": 2.387507176420256e-06, "epoch": 2.125, "percentage": 70.83, "elapsed_time": "1:20:33", "remaining_time": "0:33:10"}
+{"current_steps": 222, "total_steps": 312, "loss": 0.5229, "lr": 2.339839617423318e-06, "epoch": 2.1346153846153846, "percentage": 71.15, "elapsed_time": "1:20:45", "remaining_time": "0:32:44"}
+{"current_steps": 223, "total_steps": 312, "loss": 0.518, "lr": 2.2925069366813718e-06, "epoch": 2.144230769230769, "percentage": 71.47, "elapsed_time": "1:20:59", "remaining_time": "0:32:19"}
+{"current_steps": 224, "total_steps": 312, "loss": 0.5353, "lr": 2.245515092739488e-06, "epoch": 2.1538461538461537, "percentage": 71.79, "elapsed_time": "1:21:12", "remaining_time": "0:31:54"}
+{"current_steps": 225, "total_steps": 312, "loss": 0.5129, "lr": 2.1988700012359865e-06, "epoch": 2.1634615384615383, "percentage": 72.12, "elapsed_time": "1:23:38", "remaining_time": "0:32:20"}
+{"current_steps": 226, "total_steps": 312, "loss": 0.5032, "lr": 2.1525775341577404e-06, "epoch": 2.173076923076923, "percentage": 72.44, "elapsed_time": "1:24:32", "remaining_time": "0:32:10"}
+{"current_steps": 227, "total_steps": 312, "loss": 0.5279, "lr": 2.1066435191009717e-06, "epoch": 2.1826923076923075, "percentage": 72.76, "elapsed_time": "1:26:32", "remaining_time": "0:32:24"}
+{"current_steps": 228, "total_steps": 312, "loss": 0.4976, "lr": 2.061073738537635e-06, "epoch": 2.1923076923076925, "percentage": 73.08, "elapsed_time": "1:27:01", "remaining_time": "0:32:03"}
+{"current_steps": 229, "total_steps": 312, "loss": 0.5322, "lr": 2.0158739290874822e-06, "epoch": 2.201923076923077, "percentage": 73.4, "elapsed_time": "1:27:15", "remaining_time": "0:31:37"}
+{"current_steps": 230, "total_steps": 312, "loss": 0.5343, "lr": 1.971049780795901e-06, "epoch": 2.2115384615384617, "percentage": 73.72, "elapsed_time": "1:30:22", "remaining_time": "0:32:13"}
+{"current_steps": 231, "total_steps": 312, "loss": 0.5191, "lr": 1.9266069364176144e-06, "epoch": 2.2211538461538463, "percentage": 74.04, "elapsed_time": "1:32:07", "remaining_time": "0:32:18"}
+{"current_steps": 232, "total_steps": 312, "loss": 0.5067, "lr": 1.8825509907063328e-06, "epoch": 2.230769230769231, "percentage": 74.36, "elapsed_time": "1:32:51", "remaining_time": "0:32:01"}
+{"current_steps": 233, "total_steps": 312, "loss": 0.5168, "lr": 1.838887489710452e-06, "epoch": 2.2403846153846154, "percentage": 74.68, "elapsed_time": "1:38:09", "remaining_time": "0:33:16"}
+{"current_steps": 234, "total_steps": 312, "loss": 0.512, "lr": 1.7956219300748796e-06, "epoch": 2.25, "percentage": 75.0, "elapsed_time": "1:39:17", "remaining_time": "0:33:05"}
+{"current_steps": 235, "total_steps": 312, "loss": 0.5021, "lr": 1.7527597583490825e-06, "epoch": 2.2596153846153846, "percentage": 75.32, "elapsed_time": "1:41:10", "remaining_time": "0:33:09"}
+{"current_steps": 236, "total_steps": 312, "loss": 0.5182, "lr": 1.7103063703014372e-06, "epoch": 2.269230769230769, "percentage": 75.64, "elapsed_time": "1:42:18", "remaining_time": "0:32:56"}
+{"current_steps": 237, "total_steps": 312, "loss": 0.5173, "lr": 1.6682671102399806e-06, "epoch": 2.2788461538461537, "percentage": 75.96, "elapsed_time": "1:43:41", "remaining_time": "0:32:48"}
+{"current_steps": 238, "total_steps": 312, "loss": 0.4935, "lr": 1.6266472703396286e-06, "epoch": 2.2884615384615383, "percentage": 76.28, "elapsed_time": "1:43:53", "remaining_time": "0:32:18"}
+{"current_steps": 239, "total_steps": 312, "loss": 0.526, "lr": 1.5854520899759656e-06, "epoch": 2.298076923076923, "percentage": 76.6, "elapsed_time": "1:44:06", "remaining_time": "0:31:47"}
+{"current_steps": 240, "total_steps": 312, "loss": 0.5167, "lr": 1.544686755065677e-06, "epoch": 2.3076923076923075, "percentage": 76.92, "elapsed_time": "1:44:18", "remaining_time": "0:31:17"}
+{"current_steps": 241, "total_steps": 312, "loss": 0.508, "lr": 1.5043563974137132e-06, "epoch": 2.3173076923076925, "percentage": 77.24, "elapsed_time": "1:44:30", "remaining_time": "0:30:47"}
+{"current_steps": 242, "total_steps": 312, "loss": 0.5225, "lr": 1.4644660940672628e-06, "epoch": 2.326923076923077, "percentage": 77.56, "elapsed_time": "1:44:42", "remaining_time": "0:30:17"}
+{"current_steps": 243, "total_steps": 312, "loss": 0.5046, "lr": 1.4250208666766235e-06, "epoch": 2.3365384615384617, "percentage": 77.88, "elapsed_time": "1:44:54", "remaining_time": "0:29:47"}
+{"current_steps": 244, "total_steps": 312, "loss": 0.5249, "lr": 1.3860256808630429e-06, "epoch": 2.3461538461538463, "percentage": 78.21, "elapsed_time": "1:45:06", "remaining_time": "0:29:17"}
+{"current_steps": 245, "total_steps": 312, "loss": 0.5211, "lr": 1.3474854455936126e-06, "epoch": 2.355769230769231, "percentage": 78.53, "elapsed_time": "1:46:04", "remaining_time": "0:29:00"}
+{"current_steps": 246, "total_steps": 312, "loss": 0.527, "lr": 1.3094050125632973e-06, "epoch": 2.3653846153846154, "percentage": 78.85, "elapsed_time": "1:47:51", "remaining_time": "0:28:56"}
+{"current_steps": 247, "total_steps": 312, "loss": 0.513, "lr": 1.2717891755841722e-06, "epoch": 2.375, "percentage": 79.17, "elapsed_time": "1:48:04", "remaining_time": "0:28:26"}
+{"current_steps": 248, "total_steps": 312, "loss": 0.5166, "lr": 1.234642669981946e-06, "epoch": 2.3846153846153846, "percentage": 79.49, "elapsed_time": "1:48:18", "remaining_time": "0:27:56"}
+{"current_steps": 249, "total_steps": 312, "loss": 0.5247, "lr": 1.1979701719998454e-06, "epoch": 2.394230769230769, "percentage": 79.81, "elapsed_time": "1:48:32", "remaining_time": "0:27:27"}
+{"current_steps": 250, "total_steps": 312, "loss": 0.5176, "lr": 1.1617762982099446e-06, "epoch": 2.4038461538461537, "percentage": 80.13, "elapsed_time": "1:48:45", "remaining_time": "0:26:58"}
+{"current_steps": 251, "total_steps": 312, "loss": 0.5139, "lr": 1.1260656049319957e-06, "epoch": 2.4134615384615383, "percentage": 80.45, "elapsed_time": "1:48:58", "remaining_time": "0:26:29"}
+{"current_steps": 252, "total_steps": 312, "loss": 0.5071, "lr": 1.0908425876598512e-06, "epoch": 2.423076923076923, "percentage": 80.77, "elapsed_time": "1:49:55", "remaining_time": "0:26:10"}
+{"current_steps": 253, "total_steps": 312, "loss": 0.5284, "lr": 1.0561116804955451e-06, "epoch": 2.4326923076923075, "percentage": 81.09, "elapsed_time": "1:50:07", "remaining_time": "0:25:40"}
+{"current_steps": 254, "total_steps": 312, "loss": 0.5352, "lr": 1.0218772555910955e-06, "epoch": 2.4423076923076925, "percentage": 81.41, "elapsed_time": "1:51:59", "remaining_time": "0:25:34"}
+{"current_steps": 255, "total_steps": 312, "loss": 0.5265, "lr": 9.881436225981107e-07, "epoch": 2.451923076923077, "percentage": 81.73, "elapsed_time": "1:52:10", "remaining_time": "0:25:04"}
+{"current_steps": 256, "total_steps": 312, "loss": 0.5255, "lr": 9.549150281252633e-07, "epoch": 2.4615384615384617, "percentage": 82.05, "elapsed_time": "1:52:25", "remaining_time": "0:24:35"}
+{"current_steps": 257, "total_steps": 312, "loss": 0.5072, "lr": 9.221956552036992e-07, "epoch": 2.4711538461538463, "percentage": 82.37, "elapsed_time": "1:52:39", "remaining_time": "0:24:06"}
+{"current_steps": 258, "total_steps": 312, "loss": 0.5319, "lr": 8.899896227604509e-07, "epoch": 2.480769230769231, "percentage": 82.69, "elapsed_time": "1:52:51", "remaining_time": "0:23:37"}
+{"current_steps": 259, "total_steps": 312, "loss": 0.5309, "lr": 8.58300985099918e-07, "epoch": 2.4903846153846154, "percentage": 83.01, "elapsed_time": "1:53:03", "remaining_time": "0:23:08"}
+{"current_steps": 260, "total_steps": 312, "loss": 0.5007, "lr": 8.271337313934869e-07, "epoch": 2.5, "percentage": 83.33, "elapsed_time": "1:53:16", "remaining_time": "0:22:39"}
+{"current_steps": 261, "total_steps": 312, "loss": 0.5209, "lr": 7.964917851773496e-07, "epoch": 2.5096153846153846, "percentage": 83.65, "elapsed_time": "1:54:07", "remaining_time": "0:22:18"}
+{"current_steps": 262, "total_steps": 312, "loss": 0.4987, "lr": 7.663790038585794e-07, "epoch": 2.519230769230769, "percentage": 83.97, "elapsed_time": "1:55:03", "remaining_time": "0:21:57"}
+{"current_steps": 263, "total_steps": 312, "loss": 0.5446, "lr": 7.367991782295392e-07, "epoch": 2.5288461538461537, "percentage": 84.29, "elapsed_time": "1:56:14", "remaining_time": "0:21:39"}
+{"current_steps": 264, "total_steps": 312, "loss": 0.513, "lr": 7.077560319906696e-07, "epoch": 2.5384615384615383, "percentage": 84.62, "elapsed_time": "1:56:25", "remaining_time": "0:21:10"}
+{"current_steps": 265, "total_steps": 312, "loss": 0.5108, "lr": 6.792532212817271e-07, "epoch": 2.5480769230769234, "percentage": 84.94, "elapsed_time": "1:56:37", "remaining_time": "0:20:41"}
+{"current_steps": 266, "total_steps": 312, "loss": 0.5043, "lr": 6.512943342215234e-07, "epoch": 2.5576923076923075, "percentage": 85.26, "elapsed_time": "1:56:51", "remaining_time": "0:20:12"}
+{"current_steps": 267, "total_steps": 312, "loss": 0.5117, "lr": 6.238828904562316e-07, "epoch": 2.5673076923076925, "percentage": 85.58, "elapsed_time": "1:57:03", "remaining_time": "0:19:43"}
+{"current_steps": 268, "total_steps": 312, "loss": 0.4988, "lr": 5.9702234071631e-07, "epoch": 2.5769230769230766, "percentage": 85.9, "elapsed_time": "1:57:15", "remaining_time": "0:19:15"}
+{"current_steps": 269, "total_steps": 312, "loss": 0.5036, "lr": 5.707160663821009e-07, "epoch": 2.5865384615384617, "percentage": 86.22, "elapsed_time": "1:57:28", "remaining_time": "0:18:46"}
+{"current_steps": 270, "total_steps": 312, "loss": 0.5149, "lr": 5.449673790581611e-07, "epoch": 2.5961538461538463, "percentage": 86.54, "elapsed_time": "1:57:40", "remaining_time": "0:18:18"}
+{"current_steps": 271, "total_steps": 312, "loss": 0.5032, "lr": 5.197795201563744e-07, "epoch": 2.605769230769231, "percentage": 86.86, "elapsed_time": "1:57:52", "remaining_time": "0:17:50"}
+{"current_steps": 272, "total_steps": 312, "loss": 0.5278, "lr": 4.951556604879049e-07, "epoch": 2.6153846153846154, "percentage": 87.18, "elapsed_time": "1:58:05", "remaining_time": "0:17:22"}
+{"current_steps": 273, "total_steps": 312, "loss": 0.5148, "lr": 4.710988998640298e-07, "epoch": 2.625, "percentage": 87.5, "elapsed_time": "1:58:18", "remaining_time": "0:16:54"}
+{"current_steps": 274, "total_steps": 312, "loss": 0.5019, "lr": 4.4761226670592074e-07, "epoch": 2.6346153846153846, "percentage": 87.82, "elapsed_time": "1:58:31", "remaining_time": "0:16:26"}
+{"current_steps": 275, "total_steps": 312, "loss": 0.5278, "lr": 4.2469871766340096e-07, "epoch": 2.644230769230769, "percentage": 88.14, "elapsed_time": "1:58:45", "remaining_time": "0:15:58"}
+{"current_steps": 276, "total_steps": 312, "loss": 0.5235, "lr": 4.0236113724274716e-07, "epoch": 2.6538461538461537, "percentage": 88.46, "elapsed_time": "1:58:57", "remaining_time": "0:15:30"}
+{"current_steps": 277, "total_steps": 312, "loss": 0.5084, "lr": 3.8060233744356634e-07, "epoch": 2.6634615384615383, "percentage": 88.78, "elapsed_time": "2:00:43", "remaining_time": "0:15:15"}
+{"current_steps": 278, "total_steps": 312, "loss": 0.5213, "lr": 3.5942505740480583e-07, "epoch": 2.6730769230769234, "percentage": 89.1, "elapsed_time": "2:02:01", "remaining_time": "0:14:55"}
+{"current_steps": 279, "total_steps": 312, "loss": 0.5282, "lr": 3.3883196305992906e-07, "epoch": 2.6826923076923075, "percentage": 89.42, "elapsed_time": "2:02:14", "remaining_time": "0:14:27"}
+{"current_steps": 280, "total_steps": 312, "loss": 0.5129, "lr": 3.18825646801314e-07, "epoch": 2.6923076923076925, "percentage": 89.74, "elapsed_time": "2:02:27", "remaining_time": "0:13:59"}
+{"current_steps": 281, "total_steps": 312, "loss": 0.4986, "lr": 2.9940862715390483e-07, "epoch": 2.7019230769230766, "percentage": 90.06, "elapsed_time": "2:02:39", "remaining_time": "0:13:31"}
+{"current_steps": 282, "total_steps": 312, "loss": 0.518, "lr": 2.8058334845816214e-07, "epoch": 2.7115384615384617, "percentage": 90.38, "elapsed_time": "2:02:51", "remaining_time": "0:13:04"}
+{"current_steps": 283, "total_steps": 312, "loss": 0.5168, "lr": 2.6235218056235633e-07, "epoch": 2.7211538461538463, "percentage": 90.71, "elapsed_time": "2:03:05", "remaining_time": "0:12:36"}
+{"current_steps": 284, "total_steps": 312, "loss": 0.5167, "lr": 2.447174185242324e-07, "epoch": 2.730769230769231, "percentage": 91.03, "elapsed_time": "2:03:17", "remaining_time": "0:12:09"}
+{"current_steps": 285, "total_steps": 312, "loss": 0.5098, "lr": 2.276812823220964e-07, "epoch": 2.7403846153846154, "percentage": 91.35, "elapsed_time": "2:03:30", "remaining_time": "0:11:42"}
+{"current_steps": 286, "total_steps": 312, "loss": 0.5397, "lr": 2.1124591657534776e-07, "epoch": 2.75, "percentage": 91.67, "elapsed_time": "2:04:18", "remaining_time": "0:11:18"}
+{"current_steps": 287, "total_steps": 312, "loss": 0.5334, "lr": 1.9541339027450256e-07, "epoch": 2.7596153846153846, "percentage": 91.99, "elapsed_time": "2:04:29", "remaining_time": "0:10:50"}
+{"current_steps": 288, "total_steps": 312, "loss": 0.5207, "lr": 1.801856965207338e-07, "epoch": 2.769230769230769, "percentage": 92.31, "elapsed_time": "2:05:57", "remaining_time": "0:10:29"}
+{"current_steps": 289, "total_steps": 312, "loss": 0.528, "lr": 1.6556475227496816e-07, "epoch": 2.7788461538461537, "percentage": 92.63, "elapsed_time": "2:07:48", "remaining_time": "0:10:10"}
+{"current_steps": 290, "total_steps": 312, "loss": 0.4973, "lr": 1.5155239811656562e-07, "epoch": 2.7884615384615383, "percentage": 92.95, "elapsed_time": "2:08:00", "remaining_time": "0:09:42"}
+{"current_steps": 291, "total_steps": 312, "loss": 0.5276, "lr": 1.3815039801161723e-07, "epoch": 2.7980769230769234, "percentage": 93.27, "elapsed_time": "2:08:12", "remaining_time": "0:09:15"}
+{"current_steps": 292, "total_steps": 312, "loss": 0.505, "lr": 1.253604390908819e-07, "epoch": 2.8076923076923075, "percentage": 93.59, "elapsed_time": "2:08:24", "remaining_time": "0:08:47"}
+{"current_steps": 293, "total_steps": 312, "loss": 0.525, "lr": 1.1318413143740436e-07, "epoch": 2.8173076923076925, "percentage": 93.91, "elapsed_time": "2:08:35", "remaining_time": "0:08:20"}
+{"current_steps": 294, "total_steps": 312, "loss": 0.5264, "lr": 1.0162300788382263e-07, "epoch": 2.8269230769230766, "percentage": 94.23, "elapsed_time": "2:08:49", "remaining_time": "0:07:53"}
+{"current_steps": 295, "total_steps": 312, "loss": 0.5295, "lr": 9.0678523819408e-08, "epoch": 2.8365384615384617, "percentage": 94.55, "elapsed_time": "2:09:02", "remaining_time": "0:07:26"}
+{"current_steps": 296, "total_steps": 312, "loss": 0.5167, "lr": 8.035205700685167e-08, "epoch": 2.8461538461538463, "percentage": 94.87, "elapsed_time": "2:09:12", "remaining_time": "0:06:59"}
+{"current_steps": 297, "total_steps": 312, "loss": 0.4976, "lr": 7.064490740882057e-08, "epoch": 2.855769230769231, "percentage": 95.19, "elapsed_time": "2:09:24", "remaining_time": "0:06:32"}
+{"current_steps": 298, "total_steps": 312, "loss": 0.5158, "lr": 6.15582970243117e-08, "epoch": 2.8653846153846154, "percentage": 95.51, "elapsed_time": "2:09:38", "remaining_time": "0:06:05"}
+{"current_steps": 299, "total_steps": 312, "loss": 0.5027, "lr": 5.3093369734816824e-08, "epoch": 2.875, "percentage": 95.83, "elapsed_time": "2:09:51", "remaining_time": "0:05:38"}
+{"current_steps": 300, "total_steps": 312, "loss": 0.5145, "lr": 4.52511911603265e-08, "epoch": 2.8846153846153846, "percentage": 96.15, "elapsed_time": "2:10:05", "remaining_time": "0:05:12"}
+{"current_steps": 301, "total_steps": 312, "loss": 0.5336, "lr": 3.8032748525179684e-08, "epoch": 2.894230769230769, "percentage": 96.47, "elapsed_time": "2:10:42", "remaining_time": "0:04:46"}
+{"current_steps": 302, "total_steps": 312, "loss": 0.5152, "lr": 3.143895053378698e-08, "epoch": 2.9038461538461537, "percentage": 96.79, "elapsed_time": "2:10:53", "remaining_time": "0:04:20"}
+{"current_steps": 303, "total_steps": 312, "loss": 0.5023, "lr": 2.547062725623828e-08, "epoch": 2.9134615384615383, "percentage": 97.12, "elapsed_time": "2:11:05", "remaining_time": "0:03:53"}
+{"current_steps": 304, "total_steps": 312, "loss": 0.5332, "lr": 2.012853002380466e-08, "epoch": 2.9230769230769234, "percentage": 97.44, "elapsed_time": "2:11:18", "remaining_time": "0:03:27"}
+{"current_steps": 305, "total_steps": 312, "loss": 0.5028, "lr": 1.541333133436018e-08, "epoch": 2.9326923076923075, "percentage": 97.76, "elapsed_time": "2:11:30", "remaining_time": "0:03:01"}
+{"current_steps": 306, "total_steps": 312, "loss": 0.5202, "lr": 1.132562476771959e-08, "epoch": 2.9423076923076925, "percentage": 98.08, "elapsed_time": "2:11:42", "remaining_time": "0:02:34"}
+{"current_steps": 307, "total_steps": 312, "loss": 0.5138, "lr": 7.865924910916977e-09, "epoch": 2.9519230769230766, "percentage": 98.4, "elapsed_time": "2:11:54", "remaining_time": "0:02:08"}
+{"current_steps": 308, "total_steps": 312, "loss": 0.5177, "lr": 5.034667293427053e-09, "epoch": 2.9615384615384617, "percentage": 98.72, "elapsed_time": "2:12:05", "remaining_time": "0:01:42"}
+{"current_steps": 309, "total_steps": 312, "loss": 0.512, "lr": 2.8322083323334417e-09, "epoch": 2.9711538461538463, "percentage": 99.04, "elapsed_time": "2:12:17", "remaining_time": "0:01:17"}
+{"current_steps": 310, "total_steps": 312, "loss": 0.5214, "lr": 1.2588252874673469e-09, "epoch": 2.980769230769231, "percentage": 99.36, "elapsed_time": "2:12:30", "remaining_time": "0:00:51"}
+{"current_steps": 311, "total_steps": 312, "loss": 0.5239, "lr": 3.147162264971471e-10, "epoch": 2.9903846153846154, "percentage": 99.68, "elapsed_time": "2:12:43", "remaining_time": "0:00:25"}
+{"current_steps": 312, "total_steps": 312, "loss": 0.5068, "lr": 0.0, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "2:12:55", "remaining_time": "0:00:00"}
+{"current_steps": 312, "total_steps": 312, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "2:13:19", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,2226 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 312,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.009615384615384616,
+      "grad_norm": 7.120902061462402,
+      "learning_rate": 3.125e-07,
+      "loss": 1.0619,
+      "step": 1
+    },
+    {
+      "epoch": 0.019230769230769232,
+      "grad_norm": 7.164572238922119,
+      "learning_rate": 6.25e-07,
+      "loss": 1.0454,
+      "step": 2
+    },
+    {
+      "epoch": 0.028846153846153848,
+      "grad_norm": 7.609449863433838,
+      "learning_rate": 9.375000000000001e-07,
+      "loss": 1.0873,
+      "step": 3
+    },
+    {
+      "epoch": 0.038461538461538464,
+      "grad_norm": 6.978214740753174,
+      "learning_rate": 1.25e-06,
+      "loss": 1.054,
+      "step": 4
+    },
+    {
+      "epoch": 0.04807692307692308,
+      "grad_norm": 6.851968765258789,
+      "learning_rate": 1.5625e-06,
+      "loss": 1.0342,
+      "step": 5
+    },
+    {
+      "epoch": 0.057692307692307696,
+      "grad_norm": 6.298832416534424,
+      "learning_rate": 1.8750000000000003e-06,
+      "loss": 1.0297,
+      "step": 6
+    },
+    {
+      "epoch": 0.0673076923076923,
+      "grad_norm": 5.126293659210205,
+      "learning_rate": 2.1875000000000002e-06,
+      "loss": 0.9876,
+      "step": 7
+    },
+    {
+      "epoch": 0.07692307692307693,
+      "grad_norm": 4.865529537200928,
+      "learning_rate": 2.5e-06,
+      "loss": 0.994,
+      "step": 8
+    },
+    {
+      "epoch": 0.08653846153846154,
+      "grad_norm": 3.1541359424591064,
+      "learning_rate": 2.8125e-06,
+      "loss": 0.934,
+      "step": 9
+    },
+    {
+      "epoch": 0.09615384615384616,
+      "grad_norm": 3.0584819316864014,
+      "learning_rate": 3.125e-06,
+      "loss": 0.9542,
+      "step": 10
+    },
+    {
+      "epoch": 0.10576923076923077,
+      "grad_norm": 2.6357908248901367,
+      "learning_rate": 3.4375e-06,
+      "loss": 0.9282,
+      "step": 11
+    },
+    {
+      "epoch": 0.11538461538461539,
+      "grad_norm": 3.6711061000823975,
+      "learning_rate": 3.7500000000000005e-06,
+      "loss": 0.8984,
+      "step": 12
+    },
+    {
+      "epoch": 0.125,
+      "grad_norm": 4.1532087326049805,
+      "learning_rate": 4.0625000000000005e-06,
+      "loss": 0.9081,
+      "step": 13
+    },
+    {
+      "epoch": 0.1346153846153846,
+      "grad_norm": 3.8308780193328857,
+      "learning_rate": 4.3750000000000005e-06,
+      "loss": 0.8815,
+      "step": 14
+    },
+    {
+      "epoch": 0.14423076923076922,
+      "grad_norm": 3.487043619155884,
+      "learning_rate": 4.6875000000000004e-06,
+      "loss": 0.8703,
+      "step": 15
+    },
+    {
+      "epoch": 0.15384615384615385,
+      "grad_norm": 2.434431314468384,
+      "learning_rate": 5e-06,
+      "loss": 0.8433,
+      "step": 16
+    },
+    {
+      "epoch": 0.16346153846153846,
+      "grad_norm": 2.0722246170043945,
+      "learning_rate": 5.3125e-06,
+      "loss": 0.8102,
+      "step": 17
+    },
+    {
+      "epoch": 0.17307692307692307,
+      "grad_norm": 1.800662636756897,
+      "learning_rate": 5.625e-06,
+      "loss": 0.799,
+      "step": 18
+    },
+    {
+      "epoch": 0.18269230769230768,
+      "grad_norm": 1.525373935699463,
+      "learning_rate": 5.9375e-06,
+      "loss": 0.7913,
+      "step": 19
+    },
+    {
+      "epoch": 0.19230769230769232,
+      "grad_norm": 1.42585289478302,
+      "learning_rate": 6.25e-06,
+      "loss": 0.7863,
+      "step": 20
+    },
+    {
+      "epoch": 0.20192307692307693,
+      "grad_norm": 1.2194604873657227,
+      "learning_rate": 6.5625e-06,
+      "loss": 0.7495,
+      "step": 21
+    },
+    {
+      "epoch": 0.21153846153846154,
+      "grad_norm": 1.333568811416626,
+      "learning_rate": 6.875e-06,
+      "loss": 0.7596,
+      "step": 22
+    },
+    {
+      "epoch": 0.22115384615384615,
+      "grad_norm": 1.3491787910461426,
+      "learning_rate": 7.1875e-06,
+      "loss": 0.7542,
+      "step": 23
+    },
+    {
+      "epoch": 0.23076923076923078,
+      "grad_norm": 1.1451213359832764,
+      "learning_rate": 7.500000000000001e-06,
+      "loss": 0.7316,
+      "step": 24
+    },
+    {
+      "epoch": 0.2403846153846154,
+      "grad_norm": 0.946185827255249,
+      "learning_rate": 7.8125e-06,
+      "loss": 0.7273,
+      "step": 25
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 1.0927560329437256,
+      "learning_rate": 8.125000000000001e-06,
+      "loss": 0.7273,
+      "step": 26
+    },
+    {
+      "epoch": 0.25961538461538464,
+      "grad_norm": 1.0100075006484985,
+      "learning_rate": 8.4375e-06,
+      "loss": 0.713,
+      "step": 27
+    },
+    {
+      "epoch": 0.2692307692307692,
+      "grad_norm": 0.974131166934967,
+      "learning_rate": 8.750000000000001e-06,
+      "loss": 0.7092,
+      "step": 28
+    },
+    {
+      "epoch": 0.27884615384615385,
+      "grad_norm": 0.8509518504142761,
+      "learning_rate": 9.0625e-06,
+      "loss": 0.6919,
+      "step": 29
+    },
+    {
+      "epoch": 0.28846153846153844,
+      "grad_norm": 1.0555082559585571,
+      "learning_rate": 9.375000000000001e-06,
+      "loss": 0.7106,
+      "step": 30
+    },
+    {
+      "epoch": 0.2980769230769231,
+      "grad_norm": 1.0715065002441406,
+      "learning_rate": 9.6875e-06,
+      "loss": 0.6971,
+      "step": 31
+    },
+    {
+      "epoch": 0.3076923076923077,
+      "grad_norm": 0.8515343070030212,
+      "learning_rate": 1e-05,
+      "loss": 0.6849,
+      "step": 32
+    },
+    {
+      "epoch": 0.3173076923076923,
+      "grad_norm": 0.8755481839179993,
+      "learning_rate": 9.999685283773504e-06,
+      "loss": 0.6753,
+      "step": 33
+    },
+    {
+      "epoch": 0.3269230769230769,
+      "grad_norm": 1.0232303142547607,
+      "learning_rate": 9.998741174712534e-06,
+      "loss": 0.6717,
+      "step": 34
+    },
+    {
+      "epoch": 0.33653846153846156,
+      "grad_norm": 0.8989684581756592,
+      "learning_rate": 9.997167791667668e-06,
+      "loss": 0.6735,
+      "step": 35
+    },
+    {
+      "epoch": 0.34615384615384615,
+      "grad_norm": 1.0147842168807983,
+      "learning_rate": 9.994965332706574e-06,
+      "loss": 0.6842,
+      "step": 36
+    },
+    {
+      "epoch": 0.3557692307692308,
+      "grad_norm": 0.8389028310775757,
+      "learning_rate": 9.992134075089085e-06,
+      "loss": 0.6787,
+      "step": 37
+    },
+    {
+      "epoch": 0.36538461538461536,
+      "grad_norm": 0.7984700202941895,
+      "learning_rate": 9.98867437523228e-06,
+      "loss": 0.6834,
+      "step": 38
+    },
+    {
+      "epoch": 0.375,
+      "grad_norm": 1.041527509689331,
+      "learning_rate": 9.984586668665641e-06,
+      "loss": 0.6566,
+      "step": 39
+    },
+    {
+      "epoch": 0.38461538461538464,
+      "grad_norm": 0.7439405918121338,
+      "learning_rate": 9.979871469976197e-06,
+      "loss": 0.6797,
+      "step": 40
+    },
+    {
+      "epoch": 0.3942307692307692,
+      "grad_norm": 0.743121325969696,
+      "learning_rate": 9.974529372743762e-06,
+      "loss": 0.6739,
+      "step": 41
+    },
+    {
+      "epoch": 0.40384615384615385,
+      "grad_norm": 0.7846362590789795,
+      "learning_rate": 9.968561049466214e-06,
+      "loss": 0.6335,
+      "step": 42
+    },
+    {
+      "epoch": 0.41346153846153844,
+      "grad_norm": 0.7163788676261902,
+      "learning_rate": 9.961967251474823e-06,
+      "loss": 0.6466,
+      "step": 43
+    },
+    {
+      "epoch": 0.4230769230769231,
+      "grad_norm": 0.6745060086250305,
+      "learning_rate": 9.954748808839675e-06,
+      "loss": 0.6509,
+      "step": 44
+    },
+    {
+      "epoch": 0.4326923076923077,
+      "grad_norm": 0.6187793612480164,
+      "learning_rate": 9.946906630265184e-06,
+      "loss": 0.6494,
+      "step": 45
+    },
+    {
+      "epoch": 0.4423076923076923,
+      "grad_norm": 0.6987949013710022,
+      "learning_rate": 9.938441702975689e-06,
+      "loss": 0.6479,
+      "step": 46
+    },
+    {
+      "epoch": 0.4519230769230769,
+      "grad_norm": 0.7417098879814148,
+      "learning_rate": 9.92935509259118e-06,
+      "loss": 0.6611,
+      "step": 47
+    },
+    {
+      "epoch": 0.46153846153846156,
+      "grad_norm": 0.7351352572441101,
+      "learning_rate": 9.91964794299315e-06,
+      "loss": 0.654,
+      "step": 48
+    },
+    {
+      "epoch": 0.47115384615384615,
+      "grad_norm": 0.6541791558265686,
+      "learning_rate": 9.909321476180594e-06,
+      "loss": 0.6473,
+      "step": 49
+    },
+    {
+      "epoch": 0.4807692307692308,
+      "grad_norm": 0.8029395937919617,
+      "learning_rate": 9.898376992116179e-06,
+      "loss": 0.649,
+      "step": 50
+    },
+    {
+      "epoch": 0.49038461538461536,
+      "grad_norm": 0.7245095372200012,
+      "learning_rate": 9.886815868562596e-06,
+      "loss": 0.6413,
+      "step": 51
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.7668218612670898,
+      "learning_rate": 9.874639560909118e-06,
+      "loss": 0.6328,
+      "step": 52
+    },
+    {
+      "epoch": 0.5096153846153846,
+      "grad_norm": 0.9320131540298462,
+      "learning_rate": 9.861849601988384e-06,
+      "loss": 0.6433,
+      "step": 53
+    },
+    {
+      "epoch": 0.5192307692307693,
+      "grad_norm": 0.6532019376754761,
+      "learning_rate": 9.848447601883436e-06,
+      "loss": 0.6201,
+      "step": 54
+    },
+    {
+      "epoch": 0.5288461538461539,
+      "grad_norm": 0.8737635612487793,
+      "learning_rate": 9.834435247725032e-06,
+      "loss": 0.6382,
+      "step": 55
+    },
+    {
+      "epoch": 0.5384615384615384,
+      "grad_norm": 0.7610065937042236,
+      "learning_rate": 9.819814303479268e-06,
+      "loss": 0.627,
+      "step": 56
+    },
+    {
+      "epoch": 0.5480769230769231,
+      "grad_norm": 0.606206476688385,
+      "learning_rate": 9.804586609725499e-06,
+      "loss": 0.6139,
+      "step": 57
+    },
+    {
+      "epoch": 0.5576923076923077,
+      "grad_norm": 0.7713996171951294,
+      "learning_rate": 9.788754083424654e-06,
+      "loss": 0.6335,
+      "step": 58
+    },
+    {
+      "epoch": 0.5673076923076923,
+      "grad_norm": 0.7641143202781677,
+      "learning_rate": 9.772318717677905e-06,
+      "loss": 0.6308,
+      "step": 59
+    },
+    {
+      "epoch": 0.5769230769230769,
+      "grad_norm": 0.687099814414978,
+      "learning_rate": 9.755282581475769e-06,
+      "loss": 0.6124,
+      "step": 60
+    },
+    {
+      "epoch": 0.5865384615384616,
+      "grad_norm": 0.8211157321929932,
+      "learning_rate": 9.737647819437645e-06,
+      "loss": 0.641,
+      "step": 61
+    },
+    {
+      "epoch": 0.5961538461538461,
+      "grad_norm": 0.6129670739173889,
+      "learning_rate": 9.719416651541839e-06,
+      "loss": 0.6286,
+      "step": 62
+    },
+    {
+      "epoch": 0.6057692307692307,
+      "grad_norm": 0.7806887626647949,
+      "learning_rate": 9.700591372846096e-06,
+      "loss": 0.6267,
+      "step": 63
+    },
+    {
+      "epoch": 0.6153846153846154,
+      "grad_norm": 0.7048196792602539,
+      "learning_rate": 9.681174353198687e-06,
+      "loss": 0.6215,
+      "step": 64
+    },
+    {
+      "epoch": 0.625,
+      "grad_norm": 0.6329473853111267,
+      "learning_rate": 9.661168036940071e-06,
+      "loss": 0.6195,
+      "step": 65
+    },
+    {
+      "epoch": 0.6346153846153846,
+      "grad_norm": 0.6297646760940552,
+      "learning_rate": 9.640574942595195e-06,
+      "loss": 0.618,
+      "step": 66
+    },
+    {
+      "epoch": 0.6442307692307693,
+      "grad_norm": 0.5605977773666382,
+      "learning_rate": 9.619397662556434e-06,
+      "loss": 0.6229,
+      "step": 67
+    },
+    {
+      "epoch": 0.6538461538461539,
+      "grad_norm": 0.6335819959640503,
+      "learning_rate": 9.597638862757255e-06,
+      "loss": 0.6329,
+      "step": 68
+    },
+    {
+      "epoch": 0.6634615384615384,
+      "grad_norm": 0.6819554567337036,
+      "learning_rate": 9.5753012823366e-06,
+      "loss": 0.6304,
+      "step": 69
+    },
+    {
+      "epoch": 0.6730769230769231,
+      "grad_norm": 0.6619697213172913,
+      "learning_rate": 9.552387733294081e-06,
+      "loss": 0.6304,
+      "step": 70
+    },
+    {
+      "epoch": 0.6826923076923077,
+      "grad_norm": 0.5414342284202576,
+      "learning_rate": 9.528901100135971e-06,
+      "loss": 0.6207,
+      "step": 71
+    },
+    {
+      "epoch": 0.6923076923076923,
+      "grad_norm": 0.6086860299110413,
+      "learning_rate": 9.504844339512096e-06,
+      "loss": 0.6081,
+      "step": 72
+    },
+    {
+      "epoch": 0.7019230769230769,
+      "grad_norm": 0.6108078956604004,
+      "learning_rate": 9.480220479843627e-06,
+      "loss": 0.615,
+      "step": 73
+    },
+    {
+      "epoch": 0.7115384615384616,
+      "grad_norm": 0.5954450368881226,
+      "learning_rate": 9.45503262094184e-06,
+      "loss": 0.6149,
+      "step": 74
+    },
+    {
+      "epoch": 0.7211538461538461,
+      "grad_norm": 0.7406807541847229,
+      "learning_rate": 9.4292839336179e-06,
+      "loss": 0.6255,
+      "step": 75
+    },
+    {
+      "epoch": 0.7307692307692307,
+      "grad_norm": 0.6158877015113831,
+      "learning_rate": 9.40297765928369e-06,
+      "loss": 0.6112,
+      "step": 76
+    },
+    {
+      "epoch": 0.7403846153846154,
+      "grad_norm": 0.6299143433570862,
+      "learning_rate": 9.376117109543769e-06,
+      "loss": 0.6422,
+      "step": 77
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 0.5767729878425598,
+      "learning_rate": 9.348705665778479e-06,
+      "loss": 0.62,
+      "step": 78
+    },
+    {
+      "epoch": 0.7596153846153846,
+      "grad_norm": 0.5848022699356079,
+      "learning_rate": 9.320746778718274e-06,
+      "loss": 0.6203,
+      "step": 79
+    },
+    {
+      "epoch": 0.7692307692307693,
+      "grad_norm": 0.6434866786003113,
+      "learning_rate": 9.292243968009332e-06,
+      "loss": 0.6171,
+      "step": 80
+    },
+    {
+      "epoch": 0.7788461538461539,
+      "grad_norm": 0.6166576147079468,
+      "learning_rate": 9.263200821770462e-06,
+      "loss": 0.6134,
+      "step": 81
+    },
+    {
+      "epoch": 0.7884615384615384,
+      "grad_norm": 0.6476818919181824,
+      "learning_rate": 9.233620996141421e-06,
+      "loss": 0.6129,
+      "step": 82
+    },
+    {
+      "epoch": 0.7980769230769231,
+      "grad_norm": 0.5329578518867493,
+      "learning_rate": 9.203508214822652e-06,
+      "loss": 0.618,
+      "step": 83
+    },
+    {
+      "epoch": 0.8076923076923077,
+      "grad_norm": 0.6584686636924744,
+      "learning_rate": 9.172866268606514e-06,
+      "loss": 0.6082,
+      "step": 84
+    },
+    {
+      "epoch": 0.8173076923076923,
+      "grad_norm": 0.5995557308197021,
+      "learning_rate": 9.141699014900084e-06,
+      "loss": 0.5974,
+      "step": 85
+    },
+    {
+      "epoch": 0.8269230769230769,
+      "grad_norm": 0.6057348847389221,
+      "learning_rate": 9.110010377239552e-06,
+      "loss": 0.6157,
+      "step": 86
+    },
+    {
+      "epoch": 0.8365384615384616,
+      "grad_norm": 0.5697214007377625,
+      "learning_rate": 9.077804344796302e-06,
+      "loss": 0.6301,
+      "step": 87
+    },
+    {
+      "epoch": 0.8461538461538461,
+      "grad_norm": 0.6759421229362488,
+      "learning_rate": 9.045084971874738e-06,
+      "loss": 0.6226,
+      "step": 88
+    },
+    {
+      "epoch": 0.8557692307692307,
+      "grad_norm": 0.6390875577926636,
+      "learning_rate": 9.011856377401891e-06,
+      "loss": 0.6,
+      "step": 89
+    },
+    {
+      "epoch": 0.8653846153846154,
+      "grad_norm": 0.6852766871452332,
+      "learning_rate": 8.978122744408905e-06,
+      "loss": 0.6245,
+      "step": 90
+    },
+    {
+      "epoch": 0.875,
+      "grad_norm": 0.7117474675178528,
+      "learning_rate": 8.943888319504456e-06,
+      "loss": 0.6095,
+      "step": 91
+    },
+    {
+      "epoch": 0.8846153846153846,
+      "grad_norm": 0.5599138140678406,
+      "learning_rate": 8.90915741234015e-06,
+      "loss": 0.6093,
+      "step": 92
+    },
+    {
+      "epoch": 0.8942307692307693,
+      "grad_norm": 0.7238919138908386,
+      "learning_rate": 8.873934395068006e-06,
+      "loss": 0.6067,
+      "step": 93
+    },
+    {
+      "epoch": 0.9038461538461539,
+      "grad_norm": 0.6798980236053467,
+      "learning_rate": 8.838223701790057e-06,
+      "loss": 0.6219,
+      "step": 94
+    },
+    {
+      "epoch": 0.9134615384615384,
+      "grad_norm": 0.6069248914718628,
+      "learning_rate": 8.802029828000157e-06,
+      "loss": 0.5999,
+      "step": 95
+    },
+    {
+      "epoch": 0.9230769230769231,
+      "grad_norm": 0.6400412917137146,
+      "learning_rate": 8.765357330018056e-06,
+      "loss": 0.6132,
+      "step": 96
+    },
+    {
+      "epoch": 0.9326923076923077,
+      "grad_norm": 0.681963324546814,
+      "learning_rate": 8.728210824415829e-06,
+      "loss": 0.6014,
+      "step": 97
+    },
+    {
+      "epoch": 0.9423076923076923,
+      "grad_norm": 0.692444384098053,
+      "learning_rate": 8.690594987436705e-06,
+      "loss": 0.6062,
+      "step": 98
+    },
+    {
+      "epoch": 0.9519230769230769,
+      "grad_norm": 0.7312707901000977,
+      "learning_rate": 8.652514554406388e-06,
+      "loss": 0.6101,
+      "step": 99
+    },
+    {
+      "epoch": 0.9615384615384616,
+      "grad_norm": 0.6820095181465149,
+      "learning_rate": 8.613974319136959e-06,
+      "loss": 0.6134,
+      "step": 100
+    },
+    {
+      "epoch": 0.9711538461538461,
+      "grad_norm": 0.7500239014625549,
+      "learning_rate": 8.574979133323378e-06,
+      "loss": 0.599,
+      "step": 101
+    },
+    {
+      "epoch": 0.9807692307692307,
+      "grad_norm": 0.6154950261116028,
+      "learning_rate": 8.535533905932739e-06,
+      "loss": 0.6111,
+      "step": 102
+    },
+    {
+      "epoch": 0.9903846153846154,
+      "grad_norm": 0.6534649133682251,
+      "learning_rate": 8.495643602586287e-06,
+      "loss": 0.5939,
+      "step": 103
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.6529111862182617,
+      "learning_rate": 8.455313244934324e-06,
+      "loss": 0.6095,
+      "step": 104
+    },
+    {
+      "epoch": 1.0096153846153846,
+      "grad_norm": 0.7005321383476257,
+      "learning_rate": 8.414547910024035e-06,
+      "loss": 0.5796,
+      "step": 105
+    },
+    {
+      "epoch": 1.0192307692307692,
+      "grad_norm": 0.5535159111022949,
+      "learning_rate": 8.373352729660373e-06,
+      "loss": 0.5544,
+      "step": 106
+    },
+    {
+      "epoch": 1.0288461538461537,
+      "grad_norm": 0.6195758581161499,
+      "learning_rate": 8.331732889760021e-06,
+      "loss": 0.5746,
+      "step": 107
+    },
+    {
+      "epoch": 1.0384615384615385,
+      "grad_norm": 0.5932073593139648,
+      "learning_rate": 8.289693629698564e-06,
+      "loss": 0.552,
+      "step": 108
+    },
+    {
+      "epoch": 1.0480769230769231,
+      "grad_norm": 0.6266739964485168,
+      "learning_rate": 8.247240241650918e-06,
+      "loss": 0.5587,
+      "step": 109
+    },
+    {
+      "epoch": 1.0576923076923077,
+      "grad_norm": 0.6072287559509277,
+      "learning_rate": 8.204378069925121e-06,
+      "loss": 0.5603,
+      "step": 110
+    },
+    {
+      "epoch": 1.0673076923076923,
+      "grad_norm": 0.5796938538551331,
+      "learning_rate": 8.16111251028955e-06,
+      "loss": 0.5683,
+      "step": 111
+    },
+    {
+      "epoch": 1.0769230769230769,
+      "grad_norm": 0.5911115407943726,
+      "learning_rate": 8.117449009293668e-06,
+      "loss": 0.5687,
+      "step": 112
+    },
+    {
+      "epoch": 1.0865384615384615,
+      "grad_norm": 0.5715712308883667,
+      "learning_rate": 8.073393063582386e-06,
+      "loss": 0.5493,
+      "step": 113
+    },
+    {
+      "epoch": 1.0961538461538463,
+      "grad_norm": 0.5958821773529053,
+      "learning_rate": 8.0289502192041e-06,
+      "loss": 0.5628,
+      "step": 114
+    },
+    {
+      "epoch": 1.1057692307692308,
+      "grad_norm": 0.5040147304534912,
+      "learning_rate": 7.984126070912519e-06,
+      "loss": 0.5859,
+      "step": 115
+    },
+    {
+      "epoch": 1.1153846153846154,
+      "grad_norm": 0.6042008996009827,
+      "learning_rate": 7.938926261462366e-06,
+      "loss": 0.55,
+      "step": 116
+    },
+    {
+      "epoch": 1.125,
+      "grad_norm": 0.562238872051239,
+      "learning_rate": 7.89335648089903e-06,
+      "loss": 0.5868,
+      "step": 117
+    },
+    {
+      "epoch": 1.1346153846153846,
+      "grad_norm": 0.5125684142112732,
+      "learning_rate": 7.84742246584226e-06,
+      "loss": 0.5477,
+      "step": 118
+    },
+    {
+      "epoch": 1.1442307692307692,
+      "grad_norm": 0.5927157998085022,
+      "learning_rate": 7.801129998764014e-06,
+      "loss": 0.5579,
+      "step": 119
+    },
+    {
+      "epoch": 1.1538461538461537,
+      "grad_norm": 0.6060910224914551,
+      "learning_rate": 7.754484907260513e-06,
+      "loss": 0.5689,
+      "step": 120
+    },
+    {
+      "epoch": 1.1634615384615385,
+      "grad_norm": 0.5392307043075562,
+      "learning_rate": 7.70749306331863e-06,
+      "loss": 0.5714,
+      "step": 121
+    },
+    {
+      "epoch": 1.1730769230769231,
+      "grad_norm": 0.5618191957473755,
+      "learning_rate": 7.660160382576683e-06,
+      "loss": 0.5655,
+      "step": 122
+    },
+    {
+      "epoch": 1.1826923076923077,
+      "grad_norm": 0.4931347370147705,
+      "learning_rate": 7.612492823579744e-06,
+      "loss": 0.566,
+      "step": 123
+    },
+    {
+      "epoch": 1.1923076923076923,
+      "grad_norm": 0.576999843120575,
+      "learning_rate": 7.564496387029532e-06,
+      "loss": 0.5569,
+      "step": 124
+    },
+    {
+      "epoch": 1.2019230769230769,
+      "grad_norm": 0.5783012509346008,
+      "learning_rate": 7.516177115029002e-06,
+      "loss": 0.5745,
+      "step": 125
+    },
+    {
+      "epoch": 1.2115384615384615,
+      "grad_norm": 0.49014097452163696,
+      "learning_rate": 7.467541090321735e-06,
+      "loss": 0.5762,
+      "step": 126
+    },
+    {
+      "epoch": 1.2211538461538463,
+      "grad_norm": 0.572468101978302,
+      "learning_rate": 7.4185944355261996e-06,
+      "loss": 0.5908,
+      "step": 127
+    },
+    {
+      "epoch": 1.2307692307692308,
+      "grad_norm": 0.5665020942687988,
+      "learning_rate": 7.369343312364994e-06,
+      "loss": 0.5605,
+      "step": 128
+    },
+    {
+      "epoch": 1.2403846153846154,
+      "grad_norm": 0.505368709564209,
+      "learning_rate": 7.319793920889171e-06,
+      "loss": 0.5707,
+      "step": 129
+    },
+    {
+      "epoch": 1.25,
+      "grad_norm": 0.5062214136123657,
+      "learning_rate": 7.269952498697734e-06,
+      "loss": 0.5698,
+      "step": 130
+    },
+    {
+      "epoch": 1.2596153846153846,
+      "grad_norm": 0.5319931507110596,
+      "learning_rate": 7.219825320152411e-06,
+      "loss": 0.5591,
+      "step": 131
+    },
+    {
+      "epoch": 1.2692307692307692,
+      "grad_norm": 0.5520954132080078,
+      "learning_rate": 7.169418695587791e-06,
+      "loss": 0.5639,
+      "step": 132
+    },
+    {
+      "epoch": 1.2788461538461537,
+      "grad_norm": 0.5157988667488098,
+      "learning_rate": 7.118738970516944e-06,
+      "loss": 0.5547,
+      "step": 133
+    },
+    {
+      "epoch": 1.2884615384615383,
+      "grad_norm": 0.5376039743423462,
+      "learning_rate": 7.067792524832604e-06,
+      "loss": 0.5705,
+      "step": 134
+    },
+    {
+      "epoch": 1.2980769230769231,
+      "grad_norm": 0.5486722588539124,
+      "learning_rate": 7.016585772004026e-06,
+      "loss": 0.5538,
+      "step": 135
+    },
+    {
+      "epoch": 1.3076923076923077,
+      "grad_norm": 0.549052357673645,
+      "learning_rate": 6.965125158269619e-06,
+      "loss": 0.5609,
+      "step": 136
+    },
+    {
+      "epoch": 1.3173076923076923,
+      "grad_norm": 0.5674235820770264,
+      "learning_rate": 6.913417161825449e-06,
+      "loss": 0.5609,
+      "step": 137
+    },
+    {
+      "epoch": 1.3269230769230769,
+      "grad_norm": 0.5145401954650879,
+      "learning_rate": 6.8614682920097265e-06,
+      "loss": 0.5614,
+      "step": 138
+    },
+    {
+      "epoch": 1.3365384615384617,
+      "grad_norm": 0.49938759207725525,
+      "learning_rate": 6.809285088483361e-06,
+      "loss": 0.5687,
+      "step": 139
+    },
+    {
+      "epoch": 1.3461538461538463,
+      "grad_norm": 0.5386798977851868,
+      "learning_rate": 6.7568741204067145e-06,
+      "loss": 0.5595,
+      "step": 140
+    },
+    {
+      "epoch": 1.3557692307692308,
+      "grad_norm": 0.5430698990821838,
+      "learning_rate": 6.704241985612625e-06,
+      "loss": 0.5651,
+      "step": 141
+    },
+    {
+      "epoch": 1.3653846153846154,
+      "grad_norm": 0.5340512990951538,
+      "learning_rate": 6.651395309775837e-06,
+      "loss": 0.5651,
+      "step": 142
+    },
+    {
+      "epoch": 1.375,
+      "grad_norm": 0.540773332118988,
+      "learning_rate": 6.598340745578908e-06,
+      "loss": 0.5513,
+      "step": 143
+    },
+    {
+      "epoch": 1.3846153846153846,
+      "grad_norm": 0.5508561134338379,
+      "learning_rate": 6.545084971874738e-06,
+      "loss": 0.5445,
+      "step": 144
+    },
+    {
+      "epoch": 1.3942307692307692,
+      "grad_norm": 0.5029264092445374,
+      "learning_rate": 6.491634692845781e-06,
+      "loss": 0.5613,
+      "step": 145
+    },
+    {
+      "epoch": 1.4038461538461537,
+      "grad_norm": 0.5184585452079773,
+      "learning_rate": 6.437996637160086e-06,
+      "loss": 0.5872,
+      "step": 146
+    },
+    {
+      "epoch": 1.4134615384615383,
+      "grad_norm": 0.4843497574329376,
+      "learning_rate": 6.384177557124247e-06,
+      "loss": 0.5705,
+      "step": 147
+    },
+    {
+      "epoch": 1.4230769230769231,
+      "grad_norm": 0.5138295888900757,
+      "learning_rate": 6.330184227833376e-06,
+      "loss": 0.5652,
+      "step": 148
+    },
+    {
+      "epoch": 1.4326923076923077,
+      "grad_norm": 0.46365150809288025,
+      "learning_rate": 6.276023446318214e-06,
+      "loss": 0.5534,
+      "step": 149
+    },
+    {
+      "epoch": 1.4423076923076923,
+      "grad_norm": 0.5488097667694092,
+      "learning_rate": 6.2217020306894705e-06,
+      "loss": 0.5449,
+      "step": 150
+    },
+    {
+      "epoch": 1.4519230769230769,
+      "grad_norm": 0.5190027952194214,
+      "learning_rate": 6.1672268192795285e-06,
+      "loss": 0.5382,
+      "step": 151
+    },
+    {
+      "epoch": 1.4615384615384617,
+      "grad_norm": 0.5642440915107727,
+      "learning_rate": 6.112604669781572e-06,
+      "loss": 0.5447,
+      "step": 152
+    },
+    {
+      "epoch": 1.4711538461538463,
+      "grad_norm": 0.5329025983810425,
+      "learning_rate": 6.057842458386315e-06,
+      "loss": 0.5586,
+      "step": 153
+    },
+    {
+      "epoch": 1.4807692307692308,
+      "grad_norm": 0.45776233077049255,
+      "learning_rate": 6.002947078916365e-06,
+      "loss": 0.5621,
+      "step": 154
+    },
+    {
+      "epoch": 1.4903846153846154,
+      "grad_norm": 0.5593656897544861,
+      "learning_rate": 5.947925441958393e-06,
+      "loss": 0.5517,
+      "step": 155
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 0.49384182691574097,
+      "learning_rate": 5.892784473993184e-06,
+      "loss": 0.5713,
+      "step": 156
+    },
+    {
+      "epoch": 1.5096153846153846,
+      "grad_norm": 0.4902636706829071,
+      "learning_rate": 5.837531116523683e-06,
+      "loss": 0.5507,
+      "step": 157
+    },
+    {
+      "epoch": 1.5192307692307692,
+      "grad_norm": 0.46203383803367615,
+      "learning_rate": 5.782172325201155e-06,
+      "loss": 0.5472,
+      "step": 158
+    },
+    {
+      "epoch": 1.5288461538461537,
+      "grad_norm": 0.5147026181221008,
+      "learning_rate": 5.726715068949564e-06,
+      "loss": 0.5566,
+      "step": 159
+    },
+    {
+      "epoch": 1.5384615384615383,
+      "grad_norm": 0.5166094303131104,
+      "learning_rate": 5.671166329088278e-06,
+      "loss": 0.5324,
+      "step": 160
+    },
+    {
+      "epoch": 1.5480769230769231,
+      "grad_norm": 0.552338182926178,
+      "learning_rate": 5.615533098453215e-06,
+      "loss": 0.5681,
+      "step": 161
+    },
+    {
+      "epoch": 1.5576923076923077,
+      "grad_norm": 0.4641529619693756,
+      "learning_rate": 5.559822380516539e-06,
+      "loss": 0.5689,
+      "step": 162
+    },
+    {
+      "epoch": 1.5673076923076923,
+      "grad_norm": 0.4713779389858246,
+      "learning_rate": 5.504041188505022e-06,
+      "loss": 0.559,
+      "step": 163
+    },
+    {
+      "epoch": 1.5769230769230769,
+      "grad_norm": 0.5102840662002563,
+      "learning_rate": 5.448196544517168e-06,
+      "loss": 0.5607,
+      "step": 164
+    },
+    {
+      "epoch": 1.5865384615384617,
+      "grad_norm": 0.4957525432109833,
+      "learning_rate": 5.392295478639226e-06,
+      "loss": 0.558,
+      "step": 165
+    },
+    {
+      "epoch": 1.5961538461538463,
+      "grad_norm": 0.497121125459671,
+      "learning_rate": 5.336345028060199e-06,
+      "loss": 0.5576,
+      "step": 166
+    },
+    {
+      "epoch": 1.6057692307692308,
+      "grad_norm": 0.48833945393562317,
+      "learning_rate": 5.2803522361859596e-06,
+      "loss": 0.536,
+      "step": 167
+    },
+    {
+      "epoch": 1.6153846153846154,
+      "grad_norm": 0.5146234631538391,
+      "learning_rate": 5.224324151752575e-06,
+      "loss": 0.5529,
+      "step": 168
+    },
+    {
+      "epoch": 1.625,
+      "grad_norm": 0.47272878885269165,
+      "learning_rate": 5.168267827938971e-06,
+      "loss": 0.5571,
+      "step": 169
+    },
+    {
+      "epoch": 1.6346153846153846,
+      "grad_norm": 0.4539564251899719,
+      "learning_rate": 5.112190321479026e-06,
+      "loss": 0.547,
+      "step": 170
+    },
+    {
+      "epoch": 1.6442307692307692,
+      "grad_norm": 0.4633065164089203,
+      "learning_rate": 5.05609869177323e-06,
+      "loss": 0.5339,
+      "step": 171
+    },
+    {
+      "epoch": 1.6538461538461537,
+      "grad_norm": 0.5187256932258606,
+      "learning_rate": 5e-06,
+      "loss": 0.5534,
+      "step": 172
+    },
+    {
+      "epoch": 1.6634615384615383,
+      "grad_norm": 0.46274110674858093,
+      "learning_rate": 4.943901308226771e-06,
+      "loss": 0.5417,
+      "step": 173
+    },
+    {
+      "epoch": 1.6730769230769231,
+      "grad_norm": 0.5410740375518799,
+      "learning_rate": 4.887809678520976e-06,
+      "loss": 0.5713,
+      "step": 174
+    },
+    {
+      "epoch": 1.6826923076923077,
+      "grad_norm": 0.43668749928474426,
+      "learning_rate": 4.831732172061032e-06,
+      "loss": 0.5618,
+      "step": 175
+    },
+    {
+      "epoch": 1.6923076923076923,
+      "grad_norm": 0.4682793617248535,
+      "learning_rate": 4.775675848247427e-06,
+      "loss": 0.5711,
+      "step": 176
+    },
+    {
+      "epoch": 1.7019230769230769,
+      "grad_norm": 0.5237061381340027,
+      "learning_rate": 4.719647763814041e-06,
+      "loss": 0.5585,
+      "step": 177
+    },
+    {
+      "epoch": 1.7115384615384617,
+      "grad_norm": 0.49530908465385437,
+      "learning_rate": 4.663654971939802e-06,
+      "loss": 0.5547,
+      "step": 178
+    },
+    {
+      "epoch": 1.7211538461538463,
+      "grad_norm": 0.47508153319358826,
+      "learning_rate": 4.6077045213607765e-06,
+      "loss": 0.5493,
+      "step": 179
+    },
+    {
+      "epoch": 1.7307692307692308,
+      "grad_norm": 0.5441533923149109,
+      "learning_rate": 4.551803455482833e-06,
+      "loss": 0.5551,
+      "step": 180
+    },
+    {
+      "epoch": 1.7403846153846154,
+      "grad_norm": 0.4742332994937897,
+      "learning_rate": 4.4959588114949785e-06,
+      "loss": 0.5573,
+      "step": 181
+    },
+    {
+      "epoch": 1.75,
+      "grad_norm": 0.44225630164146423,
+      "learning_rate": 4.4401776194834615e-06,
+      "loss": 0.553,
+      "step": 182
+    },
+    {
+      "epoch": 1.7596153846153846,
+      "grad_norm": 0.4576217234134674,
+      "learning_rate": 4.384466901546786e-06,
+      "loss": 0.5784,
+      "step": 183
+    },
+    {
+      "epoch": 1.7692307692307692,
+      "grad_norm": 0.4958183467388153,
+      "learning_rate": 4.3288336709117246e-06,
+      "loss": 0.5558,
+      "step": 184
+    },
+    {
+      "epoch": 1.7788461538461537,
+      "grad_norm": 0.48444077372550964,
+      "learning_rate": 4.273284931050438e-06,
+      "loss": 0.5512,
+      "step": 185
+    },
+    {
+      "epoch": 1.7884615384615383,
+      "grad_norm": 0.4511057138442993,
+      "learning_rate": 4.217827674798845e-06,
+      "loss": 0.5564,
+      "step": 186
+    },
+    {
+      "epoch": 1.7980769230769231,
+      "grad_norm": 0.42453262209892273,
+      "learning_rate": 4.162468883476319e-06,
+      "loss": 0.5574,
+      "step": 187
+    },
+    {
+      "epoch": 1.8076923076923077,
+      "grad_norm": 0.43282291293144226,
+      "learning_rate": 4.107215526006818e-06,
+      "loss": 0.5426,
+      "step": 188
+    },
+    {
+      "epoch": 1.8173076923076923,
+      "grad_norm": 0.5064551830291748,
+      "learning_rate": 4.052074558041608e-06,
+      "loss": 0.5633,
+      "step": 189
+    },
+    {
+      "epoch": 1.8269230769230769,
+      "grad_norm": 0.4565158188343048,
+      "learning_rate": 3.997052921083637e-06,
+      "loss": 0.5825,
+      "step": 190
+    },
+    {
+      "epoch": 1.8365384615384617,
+      "grad_norm": 0.4503186047077179,
+      "learning_rate": 3.9421575416136866e-06,
+      "loss": 0.5554,
+      "step": 191
+    },
+    {
+      "epoch": 1.8461538461538463,
+      "grad_norm": 0.4373958110809326,
+      "learning_rate": 3.887395330218429e-06,
+      "loss": 0.5454,
+      "step": 192
+    },
+    {
+      "epoch": 1.8557692307692308,
+      "grad_norm": 0.46611514687538147,
+      "learning_rate": 3.832773180720475e-06,
+      "loss": 0.5568,
+      "step": 193
+    },
+    {
+      "epoch": 1.8653846153846154,
+      "grad_norm": 0.42608413100242615,
+      "learning_rate": 3.778297969310529e-06,
+      "loss": 0.5574,
+      "step": 194
+    },
+    {
+      "epoch": 1.875,
+      "grad_norm": 0.4223165214061737,
+      "learning_rate": 3.723976553681787e-06,
+      "loss": 0.5534,
+      "step": 195
+    },
+    {
+      "epoch": 1.8846153846153846,
+      "grad_norm": 0.4573526084423065,
+      "learning_rate": 3.669815772166625e-06,
+      "loss": 0.5635,
+      "step": 196
+    },
+    {
+      "epoch": 1.8942307692307692,
+      "grad_norm": 0.4243670701980591,
+      "learning_rate": 3.6158224428757538e-06,
+      "loss": 0.5561,
+      "step": 197
+    },
+    {
+      "epoch": 1.9038461538461537,
+      "grad_norm": 0.41425010561943054,
+      "learning_rate": 3.562003362839914e-06,
+      "loss": 0.5563,
+      "step": 198
+    },
+    {
+      "epoch": 1.9134615384615383,
+      "grad_norm": 0.4524295926094055,
+      "learning_rate": 3.50836530715422e-06,
+      "loss": 0.5522,
+      "step": 199
+    },
+    {
+      "epoch": 1.9230769230769231,
+      "grad_norm": 0.48653334379196167,
+      "learning_rate": 3.4549150281252635e-06,
+      "loss": 0.5593,
+      "step": 200
+    },
+    {
+      "epoch": 1.9326923076923077,
+      "grad_norm": 0.4305264949798584,
+      "learning_rate": 3.4016592544210937e-06,
+      "loss": 0.5606,
+      "step": 201
+    },
+    {
+      "epoch": 1.9423076923076923,
+      "grad_norm": 0.4900025725364685,
+      "learning_rate": 3.3486046902241663e-06,
+      "loss": 0.5724,
+      "step": 202
+    },
+    {
+      "epoch": 1.9519230769230769,
+      "grad_norm": 0.573262095451355,
+      "learning_rate": 3.295758014387375e-06,
+      "loss": 0.5296,
+      "step": 203
+    },
+    {
+      "epoch": 1.9615384615384617,
+      "grad_norm": 0.46434977650642395,
+      "learning_rate": 3.2431258795932863e-06,
+      "loss": 0.5358,
+      "step": 204
+    },
+    {
+      "epoch": 1.9711538461538463,
+      "grad_norm": 0.4425696134567261,
+      "learning_rate": 3.1907149115166403e-06,
+      "loss": 0.5427,
+      "step": 205
+    },
+    {
+      "epoch": 1.9807692307692308,
+      "grad_norm": 0.49864649772644043,
+      "learning_rate": 3.1385317079902743e-06,
+      "loss": 0.5494,
+      "step": 206
+    },
+    {
+      "epoch": 1.9903846153846154,
+      "grad_norm": 0.4962822496891022,
+      "learning_rate": 3.0865828381745515e-06,
+      "loss": 0.557,
+      "step": 207
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.49204355478286743,
+      "learning_rate": 3.0348748417303826e-06,
+      "loss": 0.5498,
+      "step": 208
+    },
+    {
+      "epoch": 2.0096153846153846,
+      "grad_norm": 0.4751799404621124,
+      "learning_rate": 2.9834142279959754e-06,
+      "loss": 0.5271,
+      "step": 209
+    },
+    {
+      "epoch": 2.019230769230769,
+      "grad_norm": 0.43008437752723694,
+      "learning_rate": 2.932207475167398e-06,
+      "loss": 0.5306,
+      "step": 210
+    },
+    {
+      "epoch": 2.0288461538461537,
+      "grad_norm": 0.48447534441947937,
+      "learning_rate": 2.8812610294830568e-06,
+      "loss": 0.5352,
+      "step": 211
+    },
+    {
+      "epoch": 2.0384615384615383,
+      "grad_norm": 0.4532342851161957,
+      "learning_rate": 2.83058130441221e-06,
+      "loss": 0.5146,
+      "step": 212
+    },
+    {
+      "epoch": 2.048076923076923,
+      "grad_norm": 0.446346253156662,
+      "learning_rate": 2.7801746798475905e-06,
+      "loss": 0.5203,
+      "step": 213
+    },
+    {
+      "epoch": 2.0576923076923075,
+      "grad_norm": 0.4176790714263916,
+      "learning_rate": 2.7300475013022666e-06,
+      "loss": 0.519,
+      "step": 214
+    },
+    {
+      "epoch": 2.0673076923076925,
+      "grad_norm": 0.42237284779548645,
+      "learning_rate": 2.6802060791108304e-06,
+      "loss": 0.5243,
+      "step": 215
+    },
+    {
+      "epoch": 2.076923076923077,
+      "grad_norm": 0.43146151304244995,
+      "learning_rate": 2.6306566876350072e-06,
+      "loss": 0.5097,
+      "step": 216
+    },
+    {
+      "epoch": 2.0865384615384617,
+      "grad_norm": 0.44543007016181946,
+      "learning_rate": 2.5814055644738013e-06,
+      "loss": 0.5133,
+      "step": 217
+    },
+    {
+      "epoch": 2.0961538461538463,
+      "grad_norm": 0.4214424192905426,
+      "learning_rate": 2.532458909678266e-06,
+      "loss": 0.5249,
+      "step": 218
+    },
+    {
+      "epoch": 2.105769230769231,
+      "grad_norm": 0.4157821238040924,
+      "learning_rate": 2.483822884971e-06,
+      "loss": 0.5082,
+      "step": 219
+    },
+    {
+      "epoch": 2.1153846153846154,
+      "grad_norm": 0.4027000367641449,
+      "learning_rate": 2.43550361297047e-06,
+      "loss": 0.509,
+      "step": 220
+    },
+    {
+      "epoch": 2.125,
+      "grad_norm": 0.40891340374946594,
+      "learning_rate": 2.387507176420256e-06,
+      "loss": 0.5439,
+      "step": 221
+    },
+    {
+      "epoch": 2.1346153846153846,
+      "grad_norm": 0.42513319849967957,
+      "learning_rate": 2.339839617423318e-06,
+      "loss": 0.5229,
+      "step": 222
+    },
+    {
+      "epoch": 2.144230769230769,
+      "grad_norm": 0.4521211087703705,
+      "learning_rate": 2.2925069366813718e-06,
+      "loss": 0.518,
+      "step": 223
+    },
+    {
+      "epoch": 2.1538461538461537,
+      "grad_norm": 0.4449746012687683,
+      "learning_rate": 2.245515092739488e-06,
+      "loss": 0.5353,
+      "step": 224
+    },
+    {
+      "epoch": 2.1634615384615383,
+      "grad_norm": 0.45328670740127563,
+      "learning_rate": 2.1988700012359865e-06,
+      "loss": 0.5129,
+      "step": 225
+    },
+    {
+      "epoch": 2.173076923076923,
+      "grad_norm": 0.46686699986457825,
+      "learning_rate": 2.1525775341577404e-06,
+      "loss": 0.5032,
+      "step": 226
+    },
+    {
+      "epoch": 2.1826923076923075,
+      "grad_norm": 0.3987773060798645,
+      "learning_rate": 2.1066435191009717e-06,
+      "loss": 0.5279,
+      "step": 227
+    },
+    {
+      "epoch": 2.1923076923076925,
+      "grad_norm": 0.47221437096595764,
+      "learning_rate": 2.061073738537635e-06,
+      "loss": 0.4976,
+      "step": 228
+    },
+    {
+      "epoch": 2.201923076923077,
+      "grad_norm": 0.45039865374565125,
+      "learning_rate": 2.0158739290874822e-06,
+      "loss": 0.5322,
+      "step": 229
+    },
+    {
+      "epoch": 2.2115384615384617,
+      "grad_norm": 0.42744478583335876,
+      "learning_rate": 1.971049780795901e-06,
+      "loss": 0.5343,
+      "step": 230
+    },
+    {
+      "epoch": 2.2211538461538463,
+      "grad_norm": 0.37364616990089417,
+      "learning_rate": 1.9266069364176144e-06,
+      "loss": 0.5191,
+      "step": 231
+    },
+    {
+      "epoch": 2.230769230769231,
+      "grad_norm": 0.4516580104827881,
+      "learning_rate": 1.8825509907063328e-06,
+      "loss": 0.5067,
+      "step": 232
+    },
+    {
+      "epoch": 2.2403846153846154,
+      "grad_norm": 0.41889938712120056,
+      "learning_rate": 1.838887489710452e-06,
+      "loss": 0.5168,
+      "step": 233
+    },
+    {
+      "epoch": 2.25,
+      "grad_norm": 0.4030407965183258,
+      "learning_rate": 1.7956219300748796e-06,
+      "loss": 0.512,
+      "step": 234
+    },
+    {
+      "epoch": 2.2596153846153846,
+      "grad_norm": 0.4093243181705475,
+      "learning_rate": 1.7527597583490825e-06,
+      "loss": 0.5021,
+      "step": 235
+    },
+    {
+      "epoch": 2.269230769230769,
+      "grad_norm": 0.40421709418296814,
+      "learning_rate": 1.7103063703014372e-06,
+      "loss": 0.5182,
+      "step": 236
+    },
+    {
+      "epoch": 2.2788461538461537,
+      "grad_norm": 0.40137532353401184,
+      "learning_rate": 1.6682671102399806e-06,
+      "loss": 0.5173,
+      "step": 237
+    },
+    {
+      "epoch": 2.2884615384615383,
+      "grad_norm": 0.4341326653957367,
+      "learning_rate": 1.6266472703396286e-06,
+      "loss": 0.4935,
+      "step": 238
+    },
+    {
+      "epoch": 2.298076923076923,
+      "grad_norm": 0.3878624141216278,
+      "learning_rate": 1.5854520899759656e-06,
+      "loss": 0.526,
+      "step": 239
+    },
+    {
+      "epoch": 2.3076923076923075,
+      "grad_norm": 0.38479188084602356,
+      "learning_rate": 1.544686755065677e-06,
+      "loss": 0.5167,
+      "step": 240
+    },
+    {
+      "epoch": 2.3173076923076925,
+      "grad_norm": 0.3775184154510498,
+      "learning_rate": 1.5043563974137132e-06,
+      "loss": 0.508,
+      "step": 241
+    },
+    {
+      "epoch": 2.326923076923077,
+      "grad_norm": 0.40884026885032654,
+      "learning_rate": 1.4644660940672628e-06,
+      "loss": 0.5225,
+      "step": 242
+    },
+    {
+      "epoch": 2.3365384615384617,
+      "grad_norm": 0.3940774202346802,
+      "learning_rate": 1.4250208666766235e-06,
+      "loss": 0.5046,
+      "step": 243
+    },
+    {
+      "epoch": 2.3461538461538463,
+      "grad_norm": 0.3791804015636444,
+      "learning_rate": 1.3860256808630429e-06,
+      "loss": 0.5249,
+      "step": 244
+    },
+    {
+      "epoch": 2.355769230769231,
+      "grad_norm": 0.41370531916618347,
+      "learning_rate": 1.3474854455936126e-06,
+      "loss": 0.5211,
+      "step": 245
+    },
+    {
+      "epoch": 2.3653846153846154,
+      "grad_norm": 0.38043004274368286,
+      "learning_rate": 1.3094050125632973e-06,
+      "loss": 0.527,
+      "step": 246
+    },
+    {
+      "epoch": 2.375,
+      "grad_norm": 0.3982435464859009,
+      "learning_rate": 1.2717891755841722e-06,
+      "loss": 0.513,
+      "step": 247
+    },
+    {
+      "epoch": 2.3846153846153846,
+      "grad_norm": 0.36393943428993225,
+      "learning_rate": 1.234642669981946e-06,
+      "loss": 0.5166,
+      "step": 248
+    },
+    {
+      "epoch": 2.394230769230769,
+      "grad_norm": 0.3941881060600281,
+      "learning_rate": 1.1979701719998454e-06,
+      "loss": 0.5247,
+      "step": 249
+    },
+    {
+      "epoch": 2.4038461538461537,
+      "grad_norm": 0.3887317180633545,
+      "learning_rate": 1.1617762982099446e-06,
+      "loss": 0.5176,
+      "step": 250
+    },
+    {
+      "epoch": 2.4134615384615383,
+      "grad_norm": 0.38710084557533264,
+      "learning_rate": 1.1260656049319957e-06,
+      "loss": 0.5139,
+      "step": 251
+    },
+    {
+      "epoch": 2.423076923076923,
+      "grad_norm": 0.4177461564540863,
+      "learning_rate": 1.0908425876598512e-06,
+      "loss": 0.5071,
+      "step": 252
+    },
+    {
+      "epoch": 2.4326923076923075,
+      "grad_norm": 0.41076067090034485,
+      "learning_rate": 1.0561116804955451e-06,
+      "loss": 0.5284,
+      "step": 253
+    },
+    {
+      "epoch": 2.4423076923076925,
+      "grad_norm": 0.3909740149974823,
+      "learning_rate": 1.0218772555910955e-06,
+      "loss": 0.5352,
+      "step": 254
+    },
+    {
+      "epoch": 2.451923076923077,
+      "grad_norm": 0.38169676065444946,
+      "learning_rate": 9.881436225981107e-07,
+      "loss": 0.5265,
+      "step": 255
+    },
+    {
+      "epoch": 2.4615384615384617,
+      "grad_norm": 0.37473157048225403,
+      "learning_rate": 9.549150281252633e-07,
+      "loss": 0.5255,
+      "step": 256
+    },
+    {
+      "epoch": 2.4711538461538463,
+      "grad_norm": 0.3663051724433899,
+      "learning_rate": 9.221956552036992e-07,
+      "loss": 0.5072,
+      "step": 257
+    },
+    {
+      "epoch": 2.480769230769231,
+      "grad_norm": 0.360029011964798,
+      "learning_rate": 8.899896227604509e-07,
+      "loss": 0.5319,
+      "step": 258
+    },
+    {
+      "epoch": 2.4903846153846154,
+      "grad_norm": 0.40786483883857727,
+      "learning_rate": 8.58300985099918e-07,
+      "loss": 0.5309,
+      "step": 259
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 0.4109921455383301,
+      "learning_rate": 8.271337313934869e-07,
+      "loss": 0.5007,
+      "step": 260
+    },
+    {
+      "epoch": 2.5096153846153846,
+      "grad_norm": 0.4578860402107239,
+      "learning_rate": 7.964917851773496e-07,
+      "loss": 0.5209,
+      "step": 261
+    },
+    {
+      "epoch": 2.519230769230769,
+      "grad_norm": 0.3682916760444641,
+      "learning_rate": 7.663790038585794e-07,
+      "loss": 0.4987,
+      "step": 262
+    },
+    {
+      "epoch": 2.5288461538461537,
+      "grad_norm": 0.34660568833351135,
+      "learning_rate": 7.367991782295392e-07,
+      "loss": 0.5446,
+      "step": 263
+    },
+    {
+      "epoch": 2.5384615384615383,
+      "grad_norm": 0.366674542427063,
+      "learning_rate": 7.077560319906696e-07,
+      "loss": 0.513,
+      "step": 264
+    },
+    {
+      "epoch": 2.5480769230769234,
+      "grad_norm": 0.3877011239528656,
+      "learning_rate": 6.792532212817271e-07,
+      "loss": 0.5108,
+      "step": 265
+    },
+    {
+      "epoch": 2.5576923076923075,
+      "grad_norm": 0.37091997265815735,
+      "learning_rate": 6.512943342215234e-07,
+      "loss": 0.5043,
+      "step": 266
+    },
+    {
+      "epoch": 2.5673076923076925,
+      "grad_norm": 0.35695940256118774,
+      "learning_rate": 6.238828904562316e-07,
+      "loss": 0.5117,
+      "step": 267
+    },
+    {
+      "epoch": 2.5769230769230766,
+      "grad_norm": 0.391635000705719,
+      "learning_rate": 5.9702234071631e-07,
+      "loss": 0.4988,
+      "step": 268
+    },
+    {
+      "epoch": 2.5865384615384617,
+      "grad_norm": 0.3883398473262787,
+      "learning_rate": 5.707160663821009e-07,
+      "loss": 0.5036,
+      "step": 269
+    },
+    {
+      "epoch": 2.5961538461538463,
+      "grad_norm": 0.36026155948638916,
+      "learning_rate": 5.449673790581611e-07,
+      "loss": 0.5149,
+      "step": 270
+    },
+    {
+      "epoch": 2.605769230769231,
+      "grad_norm": 0.41427090764045715,
+      "learning_rate": 5.197795201563744e-07,
+      "loss": 0.5032,
+      "step": 271
+    },
+    {
+      "epoch": 2.6153846153846154,
+      "grad_norm": 0.3335127830505371,
+      "learning_rate": 4.951556604879049e-07,
+      "loss": 0.5278,
+      "step": 272
+    },
+    {
+      "epoch": 2.625,
+      "grad_norm": 0.3611414134502411,
+      "learning_rate": 4.710988998640298e-07,
+      "loss": 0.5148,
+      "step": 273
+    },
+    {
+      "epoch": 2.6346153846153846,
+      "grad_norm": 0.37885385751724243,
+      "learning_rate": 4.4761226670592074e-07,
+      "loss": 0.5019,
+      "step": 274
+    },
+    {
+      "epoch": 2.644230769230769,
+      "grad_norm": 0.3800183832645416,
+      "learning_rate": 4.2469871766340096e-07,
+      "loss": 0.5278,
+      "step": 275
+    },
+    {
+      "epoch": 2.6538461538461537,
+      "grad_norm": 0.3709475100040436,
+      "learning_rate": 4.0236113724274716e-07,
+      "loss": 0.5235,
+      "step": 276
+    },
+    {
+      "epoch": 2.6634615384615383,
+      "grad_norm": 0.3726697564125061,
+      "learning_rate": 3.8060233744356634e-07,
+      "loss": 0.5084,
+      "step": 277
+    },
+    {
+      "epoch": 2.6730769230769234,
+      "grad_norm": 0.4129122793674469,
+      "learning_rate": 3.5942505740480583e-07,
+      "loss": 0.5213,
+      "step": 278
+    },
+    {
+      "epoch": 2.6826923076923075,
+      "grad_norm": 0.36773934960365295,
+      "learning_rate": 3.3883196305992906e-07,
+      "loss": 0.5282,
+      "step": 279
+    },
+    {
+      "epoch": 2.6923076923076925,
+      "grad_norm": 0.3664220869541168,
+      "learning_rate": 3.18825646801314e-07,
+      "loss": 0.5129,
+      "step": 280
+    },
+    {
+      "epoch": 2.7019230769230766,
+      "grad_norm": 0.37792733311653137,
+      "learning_rate": 2.9940862715390483e-07,
+      "loss": 0.4986,
+      "step": 281
+    },
+    {
+      "epoch": 2.7115384615384617,
+      "grad_norm": 0.3562301993370056,
+      "learning_rate": 2.8058334845816214e-07,
+      "loss": 0.518,
+      "step": 282
+    },
+    {
+      "epoch": 2.7211538461538463,
+      "grad_norm": 0.3533957302570343,
+      "learning_rate": 2.6235218056235633e-07,
+      "loss": 0.5168,
+      "step": 283
+    },
+    {
+      "epoch": 2.730769230769231,
+      "grad_norm": 0.35810333490371704,
+      "learning_rate": 2.447174185242324e-07,
+      "loss": 0.5167,
+      "step": 284
+    },
+    {
+      "epoch": 2.7403846153846154,
+      "grad_norm": 0.37440261244773865,
+      "learning_rate": 2.276812823220964e-07,
+      "loss": 0.5098,
+      "step": 285
+    },
+    {
+      "epoch": 2.75,
+      "grad_norm": 0.3287203311920166,
+      "learning_rate": 2.1124591657534776e-07,
+      "loss": 0.5397,
+      "step": 286
+    },
+    {
+      "epoch": 2.7596153846153846,
+      "grad_norm": 0.34640252590179443,
+      "learning_rate": 1.9541339027450256e-07,
+      "loss": 0.5334,
+      "step": 287
+    },
+    {
+      "epoch": 2.769230769230769,
+      "grad_norm": 0.3535205125808716,
+      "learning_rate": 1.801856965207338e-07,
+      "loss": 0.5207,
+      "step": 288
+    },
+    {
+      "epoch": 2.7788461538461537,
+      "grad_norm": 0.35911622643470764,
+      "learning_rate": 1.6556475227496816e-07,
+      "loss": 0.528,
+      "step": 289
+    },
+    {
+      "epoch": 2.7884615384615383,
+      "grad_norm": 0.37213701009750366,
+      "learning_rate": 1.5155239811656562e-07,
+      "loss": 0.4973,
+      "step": 290
+    },
+    {
+      "epoch": 2.7980769230769234,
+      "grad_norm": 0.3440645933151245,
+      "learning_rate": 1.3815039801161723e-07,
+      "loss": 0.5276,
+      "step": 291
+    },
+    {
+      "epoch": 2.8076923076923075,
+      "grad_norm": 0.3481317162513733,
+      "learning_rate": 1.253604390908819e-07,
+      "loss": 0.505,
+      "step": 292
+    },
+    {
+      "epoch": 2.8173076923076925,
+      "grad_norm": 0.35088083148002625,
+      "learning_rate": 1.1318413143740436e-07,
+      "loss": 0.525,
+      "step": 293
+    },
+    {
+      "epoch": 2.8269230769230766,
+      "grad_norm": 0.3465360105037689,
+      "learning_rate": 1.0162300788382263e-07,
+      "loss": 0.5264,
+      "step": 294
+    },
+    {
+      "epoch": 2.8365384615384617,
+      "grad_norm": 0.3661733865737915,
+      "learning_rate": 9.0678523819408e-08,
+      "loss": 0.5295,
+      "step": 295
+    },
+    {
+      "epoch": 2.8461538461538463,
+      "grad_norm": 0.3409578204154968,
+      "learning_rate": 8.035205700685167e-08,
+      "loss": 0.5167,
+      "step": 296
+    },
+    {
+      "epoch": 2.855769230769231,
+      "grad_norm": 0.36257433891296387,
+      "learning_rate": 7.064490740882057e-08,
+      "loss": 0.4976,
+      "step": 297
+    },
+    {
+      "epoch": 2.8653846153846154,
+      "grad_norm": 0.3648744523525238,
+      "learning_rate": 6.15582970243117e-08,
+      "loss": 0.5158,
+      "step": 298
+    },
+    {
+      "epoch": 2.875,
+      "grad_norm": 0.3494463860988617,
+      "learning_rate": 5.3093369734816824e-08,
+      "loss": 0.5027,
+      "step": 299
+    },
+    {
+      "epoch": 2.8846153846153846,
+      "grad_norm": 0.39388546347618103,
+      "learning_rate": 4.52511911603265e-08,
+      "loss": 0.5145,
+      "step": 300
+    },
+    {
+      "epoch": 2.894230769230769,
+      "grad_norm": 0.3406028151512146,
+      "learning_rate": 3.8032748525179684e-08,
+      "loss": 0.5336,
+      "step": 301
+    },
+    {
+      "epoch": 2.9038461538461537,
+      "grad_norm": 0.34781765937805176,
+      "learning_rate": 3.143895053378698e-08,
+      "loss": 0.5152,
+      "step": 302
+    },
+    {
+      "epoch": 2.9134615384615383,
+      "grad_norm": 0.35940438508987427,
+      "learning_rate": 2.547062725623828e-08,
+      "loss": 0.5023,
+      "step": 303
+    },
+    {
+      "epoch": 2.9230769230769234,
+      "grad_norm": 0.3313487768173218,
+      "learning_rate": 2.012853002380466e-08,
+      "loss": 0.5332,
+      "step": 304
+    },
+    {
+      "epoch": 2.9326923076923075,
+      "grad_norm": 0.3401786983013153,
+      "learning_rate": 1.541333133436018e-08,
+      "loss": 0.5028,
+      "step": 305
+    },
+    {
+      "epoch": 2.9423076923076925,
+      "grad_norm": 0.36166515946388245,
+      "learning_rate": 1.132562476771959e-08,
+      "loss": 0.5202,
+      "step": 306
+    },
+    {
+      "epoch": 2.9519230769230766,
+      "grad_norm": 0.37917229533195496,
+      "learning_rate": 7.865924910916977e-09,
+      "loss": 0.5138,
+      "step": 307
+    },
+    {
+      "epoch": 2.9615384615384617,
+      "grad_norm": 0.36633941531181335,
+      "learning_rate": 5.034667293427053e-09,
+      "loss": 0.5177,
+      "step": 308
+    },
+    {
+      "epoch": 2.9711538461538463,
+      "grad_norm": 0.3561273217201233,
+      "learning_rate": 2.8322083323334417e-09,
+      "loss": 0.512,
+      "step": 309
+    },
+    {
+      "epoch": 2.980769230769231,
+      "grad_norm": 0.33336392045021057,
+      "learning_rate": 1.2588252874673469e-09,
+      "loss": 0.5214,
+      "step": 310
+    },
+    {
+      "epoch": 2.9903846153846154,
+      "grad_norm": 0.3431507647037506,
+      "learning_rate": 3.147162264971471e-10,
+      "loss": 0.5239,
+      "step": 311
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.3575623333454132,
+      "learning_rate": 0.0,
+      "loss": 0.5068,
+      "step": 312
+    },
+    {
+      "epoch": 3.0,
+      "step": 312,
+      "total_flos": 489026734391296.0,
+      "train_loss": 0.5917462170697175,
+      "train_runtime": 8001.2912,
+      "train_samples_per_second": 3.731,
+      "train_steps_per_second": 0.039
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 312,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 489026734391296.0,
+  "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 sha256:014672caa4d052b941c6b5f42d6a46b1788c396b9e4be22a98c65e56b49b3991
+size 7672