End of training

README.md

@@ -0,0 +1,180 @@
+---
+library_name: peft
+license: apache-2.0
+base_model: JackFram/llama-68m
+tags:
+- axolotl
+- generated_from_trainer
+model-index:
+- name: 655b7e56-a0e0-4ba4-bced-282ddab29d01
+  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. -->
+
+[<img src="https://raw.githubusercontent.com/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl)
+<details><summary>See axolotl config</summary>
+
+axolotl version: `0.4.1`
+```yaml
+adapter: lora
+base_model: JackFram/llama-68m
+bf16: auto
+chat_template: llama3
+cosine_min_lr_ratio: 0.1
+data_processes: 16
+dataset_prepared_path: null
+datasets:
+- data_files:
+  - 1c65ab1e74a5a571_train_data.json
+  ds_type: json
+  format: custom
+  path: /workspace/input_data/1c65ab1e74a5a571_train_data.json
+  type:
+    field_instruction: instruction
+    field_output: output
+    format: '{instruction}'
+    no_input_format: '{instruction}'
+    system_format: '{system}'
+    system_prompt: ''
+debug: null
+deepspeed: null
+device_map: '{'''':torch.cuda.current_device()}'
+do_eval: true
+early_stopping_patience: 1
+eval_batch_size: 6
+eval_sample_packing: false
+eval_steps: 25
+evaluation_strategy: steps
+flash_attention: true
+fp16: null
+fsdp: null
+fsdp_config: null
+gradient_accumulation_steps: 5
+gradient_checkpointing: true
+group_by_length: true
+hub_model_id: null
+hub_repo: stevemonite
+hub_strategy: checkpoint
+hub_token: null
+learning_rate: 0.0001
+load_in_4bit: false
+load_in_8bit: false
+local_rank: null
+logging_steps: 1
+lora_alpha: 32
+lora_dropout: 0.05
+lora_fan_in_fan_out: null
+lora_model_dir: null
+lora_r: 16
+lora_target_linear: true
+lora_target_modules:
+- q_proj
+- v_proj
+lr_scheduler: cosine
+max_grad_norm: 1.0
+max_memory:
+  0: 70GiB
+max_steps: 937
+micro_batch_size: 6
+mlflow_experiment_name: /tmp/1c65ab1e74a5a571_train_data.json
+model_type: AutoModelForCausalLM
+num_epochs: 4
+optim_args:
+  adam_beta1: 0.9
+  adam_beta2: 0.95
+  adam_epsilon: 1e-5
+optimizer: adamw_torch
+output_dir: miner_id_24
+pad_to_sequence_len: true
+resume_from_checkpoint: null
+s2_attention: null
+sample_packing: false
+save_steps: 50
+save_strategy: steps
+sequence_len: 2048
+special_tokens:
+  pad_token: </s>
+strict: false
+tf32: false
+tokenizer_type: AutoTokenizer
+torch_compile: false
+train_on_inputs: false
+trust_remote_code: true
+val_set_size: 50
+wandb_entity: sn56-miner
+wandb_mode: disabled
+wandb_name: null
+wandb_project: god
+wandb_run: 6hrh
+wandb_runid: null
+warmup_raio: 0.03
+warmup_ratio: 0.05
+weight_decay: 0.01
+xformers_attention: null
+
+```
+
+</details><br>
+
+# 655b7e56-a0e0-4ba4-bced-282ddab29d01
+
+This model is a fine-tuned version of [JackFram/llama-68m](https://huggingface.co/JackFram/llama-68m) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.7751
+
+## 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: 0.0001
+- train_batch_size: 6
+- eval_batch_size: 6
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 4
+- gradient_accumulation_steps: 5
+- total_train_batch_size: 120
+- total_eval_batch_size: 24
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=adam_beta1=0.9,adam_beta2=0.95,adam_epsilon=1e-5
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 46
+- training_steps: 937
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 3.2093        | 0.0006 | 1    | 1.9845          |
+| 1.8359        | 0.0152 | 25   | 1.7007          |
+| 1.3987        | 0.0304 | 50   | 1.2663          |
+| 1.1211        | 0.0456 | 75   | 1.0244          |
+| 1.032         | 0.0608 | 100  | 0.9011          |
+| 1.015         | 0.0761 | 125  | 0.8608          |
+| 0.929         | 0.0913 | 150  | 0.8001          |
+| 0.8793        | 0.1065 | 175  | 0.7929          |
+| 0.8785        | 0.1217 | 200  | 0.7700          |
+| 0.9214        | 0.1369 | 225  | 0.7751          |
+
+
+### Framework versions
+
+- PEFT 0.13.2
+- Transformers 4.46.0
+- Pytorch 2.5.0+cu124
+- Datasets 3.0.1
+- Tokenizers 0.20.1

adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "JackFram/llama-68m",
+  "bias": "none",
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "k_proj",
+    "v_proj",
+    "q_proj",
+    "gate_proj",
+    "down_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66b5e47d82e6ee850d0b0f6536b761f1fa577056015007340c9e9ef02e3cc263
+size 2271170

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aeb699b560ace51d4c71ee5f33b6d2026b066ed85be77eebbbec0d97d16a0536
+size 2264640

config.json

@@ -0,0 +1,32 @@
+{
+  "_attn_implementation_autoset": true,
+  "_name_or_path": "JackFram/llama-68m",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "max_position_embeddings": 2048,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 2,
+  "num_key_value_heads": 12,
+  "pad_token_id": 1,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.46.0",
+  "use_cache": false,
+  "vocab_size": 32000
+}

last-checkpoint/README.md

@@ -0,0 +1,202 @@
+---
+base_model: JackFram/llama-68m
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.13.2

last-checkpoint/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "JackFram/llama-68m",
+  "bias": "none",
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "k_proj",
+    "v_proj",
+    "q_proj",
+    "gate_proj",
+    "down_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

last-checkpoint/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aeb699b560ace51d4c71ee5f33b6d2026b066ed85be77eebbbec0d97d16a0536
+size 2264640

last-checkpoint/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:024d136383a8d12e2ba5262398c982b5f8c36bff56906381a784438ecc96273c
+size 4545930

last-checkpoint/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86ad5ef13236794cd5f52fa4e26cccf4500e9f1374d7630804e4cb42d661b86c
+size 14960

last-checkpoint/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:856eafe529be5acf06ee252d056ee1ce8fa21260d80f21ef1756c1c5f9026773
+size 15024

last-checkpoint/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0cfd9d3e25f5e836e6f84c6cae8f701a5f707917227611dfc1dfc8d496a082fd
+size 15024

last-checkpoint/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eeb374aa29ef28c88c82d9b6171c383ed6b9f84220e589f6d60ddd6d1de29d5e
+size 15024

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:047c3e796f6293936627c07b676305e522cc9842903ab1cbcd2ab7e8b47ad5b9
+size 1064

last-checkpoint/special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

last-checkpoint/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

last-checkpoint/tokenizer_config.json

@@ -0,0 +1,44 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false,
+  "use_fast": true
+}

last-checkpoint/trainer_state.json

@@ -0,0 +1,1514 @@
+{
+  "best_metric": 0.770029604434967,
+  "best_model_checkpoint": "miner_id_24/checkpoint-200",
+  "epoch": 0.12168410805548795,
+  "eval_steps": 25,
+  "global_step": 200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0006084205402774398,
+      "grad_norm": 3.7732460498809814,
+      "learning_rate": 2.173913043478261e-06,
+      "loss": 3.2093,
+      "step": 1
+    },
+    {
+      "epoch": 0.0006084205402774398,
+      "eval_loss": 1.9844963550567627,
+      "eval_runtime": 0.0679,
+      "eval_samples_per_second": 736.566,
+      "eval_steps_per_second": 44.194,
+      "step": 1
+    },
+    {
+      "epoch": 0.0012168410805548796,
+      "grad_norm": 4.146840572357178,
+      "learning_rate": 4.347826086956522e-06,
+      "loss": 2.2685,
+      "step": 2
+    },
+    {
+      "epoch": 0.0018252616208323193,
+      "grad_norm": 3.805527448654175,
+      "learning_rate": 6.521739130434783e-06,
+      "loss": 2.0894,
+      "step": 3
+    },
+    {
+      "epoch": 0.002433682161109759,
+      "grad_norm": 3.5490667819976807,
+      "learning_rate": 8.695652173913044e-06,
+      "loss": 1.9026,
+      "step": 4
+    },
+    {
+      "epoch": 0.003042102701387199,
+      "grad_norm": 3.1814687252044678,
+      "learning_rate": 1.0869565217391305e-05,
+      "loss": 1.9351,
+      "step": 5
+    },
+    {
+      "epoch": 0.0036505232416646385,
+      "grad_norm": 3.0306947231292725,
+      "learning_rate": 1.3043478260869566e-05,
+      "loss": 1.9283,
+      "step": 6
+    },
+    {
+      "epoch": 0.004258943781942078,
+      "grad_norm": 3.2333295345306396,
+      "learning_rate": 1.5217391304347828e-05,
+      "loss": 1.9199,
+      "step": 7
+    },
+    {
+      "epoch": 0.004867364322219518,
+      "grad_norm": 2.786118745803833,
+      "learning_rate": 1.739130434782609e-05,
+      "loss": 1.9464,
+      "step": 8
+    },
+    {
+      "epoch": 0.005475784862496958,
+      "grad_norm": 3.1137781143188477,
+      "learning_rate": 1.956521739130435e-05,
+      "loss": 1.8952,
+      "step": 9
+    },
+    {
+      "epoch": 0.006084205402774398,
+      "grad_norm": 3.2737996578216553,
+      "learning_rate": 2.173913043478261e-05,
+      "loss": 1.8745,
+      "step": 10
+    },
+    {
+      "epoch": 0.006692625943051838,
+      "grad_norm": 3.218707799911499,
+      "learning_rate": 2.391304347826087e-05,
+      "loss": 1.9421,
+      "step": 11
+    },
+    {
+      "epoch": 0.007301046483329277,
+      "grad_norm": 3.402679204940796,
+      "learning_rate": 2.608695652173913e-05,
+      "loss": 2.0349,
+      "step": 12
+    },
+    {
+      "epoch": 0.007909467023606717,
+      "grad_norm": 2.8429970741271973,
+      "learning_rate": 2.826086956521739e-05,
+      "loss": 4.0381,
+      "step": 13
+    },
+    {
+      "epoch": 0.008517887563884156,
+      "grad_norm": 4.92161750793457,
+      "learning_rate": 3.0434782608695656e-05,
+      "loss": 2.315,
+      "step": 14
+    },
+    {
+      "epoch": 0.009126308104161596,
+      "grad_norm": 4.043981075286865,
+      "learning_rate": 3.260869565217392e-05,
+      "loss": 2.028,
+      "step": 15
+    },
+    {
+      "epoch": 0.009734728644439037,
+      "grad_norm": 3.5905041694641113,
+      "learning_rate": 3.478260869565218e-05,
+      "loss": 2.034,
+      "step": 16
+    },
+    {
+      "epoch": 0.010343149184716476,
+      "grad_norm": 3.121873378753662,
+      "learning_rate": 3.695652173913043e-05,
+      "loss": 1.9274,
+      "step": 17
+    },
+    {
+      "epoch": 0.010951569724993915,
+      "grad_norm": 3.123685836791992,
+      "learning_rate": 3.91304347826087e-05,
+      "loss": 1.9217,
+      "step": 18
+    },
+    {
+      "epoch": 0.011559990265271356,
+      "grad_norm": 2.93074107170105,
+      "learning_rate": 4.130434782608696e-05,
+      "loss": 1.6898,
+      "step": 19
+    },
+    {
+      "epoch": 0.012168410805548795,
+      "grad_norm": 3.0180726051330566,
+      "learning_rate": 4.347826086956522e-05,
+      "loss": 1.6951,
+      "step": 20
+    },
+    {
+      "epoch": 0.012776831345826235,
+      "grad_norm": 2.9282548427581787,
+      "learning_rate": 4.565217391304348e-05,
+      "loss": 1.7592,
+      "step": 21
+    },
+    {
+      "epoch": 0.013385251886103676,
+      "grad_norm": 2.5757176876068115,
+      "learning_rate": 4.782608695652174e-05,
+      "loss": 1.753,
+      "step": 22
+    },
+    {
+      "epoch": 0.013993672426381115,
+      "grad_norm": 2.7244386672973633,
+      "learning_rate": 5e-05,
+      "loss": 1.7478,
+      "step": 23
+    },
+    {
+      "epoch": 0.014602092966658554,
+      "grad_norm": 2.9556708335876465,
+      "learning_rate": 5.217391304347826e-05,
+      "loss": 1.7354,
+      "step": 24
+    },
+    {
+      "epoch": 0.015210513506935993,
+      "grad_norm": 2.826549530029297,
+      "learning_rate": 5.4347826086956524e-05,
+      "loss": 1.8359,
+      "step": 25
+    },
+    {
+      "epoch": 0.015210513506935993,
+      "eval_loss": 1.7007235288619995,
+      "eval_runtime": 0.0651,
+      "eval_samples_per_second": 767.794,
+      "eval_steps_per_second": 46.068,
+      "step": 25
+    },
+    {
+      "epoch": 0.015818934047213434,
+      "grad_norm": 4.59504508972168,
+      "learning_rate": 5.652173913043478e-05,
+      "loss": 2.9356,
+      "step": 26
+    },
+    {
+      "epoch": 0.016427354587490874,
+      "grad_norm": 4.431028842926025,
+      "learning_rate": 5.869565217391305e-05,
+      "loss": 1.7887,
+      "step": 27
+    },
+    {
+      "epoch": 0.017035775127768313,
+      "grad_norm": 3.4355099201202393,
+      "learning_rate": 6.086956521739131e-05,
+      "loss": 1.6548,
+      "step": 28
+    },
+    {
+      "epoch": 0.017644195668045752,
+      "grad_norm": 2.5302505493164062,
+      "learning_rate": 6.304347826086957e-05,
+      "loss": 1.6289,
+      "step": 29
+    },
+    {
+      "epoch": 0.01825261620832319,
+      "grad_norm": 1.6945921182632446,
+      "learning_rate": 6.521739130434783e-05,
+      "loss": 1.4231,
+      "step": 30
+    },
+    {
+      "epoch": 0.018861036748600634,
+      "grad_norm": 1.6188069581985474,
+      "learning_rate": 6.73913043478261e-05,
+      "loss": 1.4109,
+      "step": 31
+    },
+    {
+      "epoch": 0.019469457288878073,
+      "grad_norm": 1.2194888591766357,
+      "learning_rate": 6.956521739130436e-05,
+      "loss": 1.4766,
+      "step": 32
+    },
+    {
+      "epoch": 0.020077877829155513,
+      "grad_norm": 1.0816359519958496,
+      "learning_rate": 7.17391304347826e-05,
+      "loss": 1.5166,
+      "step": 33
+    },
+    {
+      "epoch": 0.020686298369432952,
+      "grad_norm": 1.0028973817825317,
+      "learning_rate": 7.391304347826086e-05,
+      "loss": 1.5929,
+      "step": 34
+    },
+    {
+      "epoch": 0.02129471890971039,
+      "grad_norm": 0.9615126848220825,
+      "learning_rate": 7.608695652173914e-05,
+      "loss": 1.3961,
+      "step": 35
+    },
+    {
+      "epoch": 0.02190313944998783,
+      "grad_norm": 1.0823183059692383,
+      "learning_rate": 7.82608695652174e-05,
+      "loss": 1.4874,
+      "step": 36
+    },
+    {
+      "epoch": 0.022511559990265273,
+      "grad_norm": 1.1442559957504272,
+      "learning_rate": 8.043478260869566e-05,
+      "loss": 1.5171,
+      "step": 37
+    },
+    {
+      "epoch": 0.023119980530542712,
+      "grad_norm": 3.612239360809326,
+      "learning_rate": 8.260869565217392e-05,
+      "loss": 3.3537,
+      "step": 38
+    },
+    {
+      "epoch": 0.02372840107082015,
+      "grad_norm": 3.0585246086120605,
+      "learning_rate": 8.478260869565218e-05,
+      "loss": 1.571,
+      "step": 39
+    },
+    {
+      "epoch": 0.02433682161109759,
+      "grad_norm": 2.00331711769104,
+      "learning_rate": 8.695652173913044e-05,
+      "loss": 1.5134,
+      "step": 40
+    },
+    {
+      "epoch": 0.02494524215137503,
+      "grad_norm": 1.4210355281829834,
+      "learning_rate": 8.91304347826087e-05,
+      "loss": 1.2967,
+      "step": 41
+    },
+    {
+      "epoch": 0.02555366269165247,
+      "grad_norm": 1.2288633584976196,
+      "learning_rate": 9.130434782608696e-05,
+      "loss": 1.4348,
+      "step": 42
+    },
+    {
+      "epoch": 0.02616208323192991,
+      "grad_norm": 1.157564640045166,
+      "learning_rate": 9.347826086956522e-05,
+      "loss": 1.3196,
+      "step": 43
+    },
+    {
+      "epoch": 0.02677050377220735,
+      "grad_norm": 1.2825106382369995,
+      "learning_rate": 9.565217391304348e-05,
+      "loss": 1.349,
+      "step": 44
+    },
+    {
+      "epoch": 0.02737892431248479,
+      "grad_norm": 1.2434223890304565,
+      "learning_rate": 9.782608695652174e-05,
+      "loss": 1.3314,
+      "step": 45
+    },
+    {
+      "epoch": 0.02798734485276223,
+      "grad_norm": 1.429315447807312,
+      "learning_rate": 0.0001,
+      "loss": 1.3863,
+      "step": 46
+    },
+    {
+      "epoch": 0.02859576539303967,
+      "grad_norm": 0.9383629560470581,
+      "learning_rate": 9.999972027814122e-05,
+      "loss": 1.3054,
+      "step": 47
+    },
+    {
+      "epoch": 0.029204185933317108,
+      "grad_norm": 0.7935044765472412,
+      "learning_rate": 9.999888111604245e-05,
+      "loss": 1.298,
+      "step": 48
+    },
+    {
+      "epoch": 0.029812606473594547,
+      "grad_norm": 0.859842836856842,
+      "learning_rate": 9.999748252413618e-05,
+      "loss": 1.3098,
+      "step": 49
+    },
+    {
+      "epoch": 0.030421027013871987,
+      "grad_norm": 1.2138994932174683,
+      "learning_rate": 9.999552451980984e-05,
+      "loss": 1.3987,
+      "step": 50
+    },
+    {
+      "epoch": 0.030421027013871987,
+      "eval_loss": 1.2663160562515259,
+      "eval_runtime": 0.064,
+      "eval_samples_per_second": 781.103,
+      "eval_steps_per_second": 46.866,
+      "step": 50
+    },
+    {
+      "epoch": 0.03102944755414943,
+      "grad_norm": 3.1896111965179443,
+      "learning_rate": 9.999300712740551e-05,
+      "loss": 2.1177,
+      "step": 51
+    },
+    {
+      "epoch": 0.03163786809442687,
+      "grad_norm": 1.8031097650527954,
+      "learning_rate": 9.998993037821958e-05,
+      "loss": 1.281,
+      "step": 52
+    },
+    {
+      "epoch": 0.03224628863470431,
+      "grad_norm": 1.3828022480010986,
+      "learning_rate": 9.998629431050251e-05,
+      "loss": 1.286,
+      "step": 53
+    },
+    {
+      "epoch": 0.03285470917498175,
+      "grad_norm": 1.2959613800048828,
+      "learning_rate": 9.998209896945815e-05,
+      "loss": 1.3098,
+      "step": 54
+    },
+    {
+      "epoch": 0.033463129715259186,
+      "grad_norm": 0.9320961236953735,
+      "learning_rate": 9.997734440724333e-05,
+      "loss": 1.2237,
+      "step": 55
+    },
+    {
+      "epoch": 0.034071550255536626,
+      "grad_norm": 0.7311733961105347,
+      "learning_rate": 9.997203068296719e-05,
+      "loss": 1.1421,
+      "step": 56
+    },
+    {
+      "epoch": 0.034679970795814065,
+      "grad_norm": 0.7125067710876465,
+      "learning_rate": 9.996615786269035e-05,
+      "loss": 1.2081,
+      "step": 57
+    },
+    {
+      "epoch": 0.035288391336091504,
+      "grad_norm": 0.6830151677131653,
+      "learning_rate": 9.995972601942424e-05,
+      "loss": 1.2123,
+      "step": 58
+    },
+    {
+      "epoch": 0.03589681187636894,
+      "grad_norm": 0.6575762629508972,
+      "learning_rate": 9.995273523313003e-05,
+      "loss": 1.1829,
+      "step": 59
+    },
+    {
+      "epoch": 0.03650523241664638,
+      "grad_norm": 0.8578693866729736,
+      "learning_rate": 9.994518559071775e-05,
+      "loss": 1.1763,
+      "step": 60
+    },
+    {
+      "epoch": 0.03711365295692383,
+      "grad_norm": 0.8111445307731628,
+      "learning_rate": 9.993707718604522e-05,
+      "loss": 1.1614,
+      "step": 61
+    },
+    {
+      "epoch": 0.03772207349720127,
+      "grad_norm": 0.9371657967567444,
+      "learning_rate": 9.992841011991676e-05,
+      "loss": 1.2245,
+      "step": 62
+    },
+    {
+      "epoch": 0.03833049403747871,
+      "grad_norm": 2.6930816173553467,
+      "learning_rate": 9.991918450008206e-05,
+      "loss": 2.285,
+      "step": 63
+    },
+    {
+      "epoch": 0.03893891457775615,
+      "grad_norm": 1.746653437614441,
+      "learning_rate": 9.99094004412348e-05,
+      "loss": 1.301,
+      "step": 64
+    },
+    {
+      "epoch": 0.039547335118033586,
+      "grad_norm": 1.1019763946533203,
+      "learning_rate": 9.98990580650112e-05,
+      "loss": 1.1406,
+      "step": 65
+    },
+    {
+      "epoch": 0.040155755658311025,
+      "grad_norm": 1.0221314430236816,
+      "learning_rate": 9.988815749998852e-05,
+      "loss": 1.0963,
+      "step": 66
+    },
+    {
+      "epoch": 0.040764176198588464,
+      "grad_norm": 0.7163240313529968,
+      "learning_rate": 9.987669888168351e-05,
+      "loss": 1.0621,
+      "step": 67
+    },
+    {
+      "epoch": 0.041372596738865904,
+      "grad_norm": 1.0129799842834473,
+      "learning_rate": 9.986468235255065e-05,
+      "loss": 1.0655,
+      "step": 68
+    },
+    {
+      "epoch": 0.04198101727914334,
+      "grad_norm": 1.0162873268127441,
+      "learning_rate": 9.985210806198042e-05,
+      "loss": 1.1478,
+      "step": 69
+    },
+    {
+      "epoch": 0.04258943781942078,
+      "grad_norm": 0.6798834204673767,
+      "learning_rate": 9.983897616629744e-05,
+      "loss": 1.0584,
+      "step": 70
+    },
+    {
+      "epoch": 0.04319785835969822,
+      "grad_norm": 0.82222980260849,
+      "learning_rate": 9.982528682875851e-05,
+      "loss": 1.0776,
+      "step": 71
+    },
+    {
+      "epoch": 0.04380627889997566,
+      "grad_norm": 0.8663562536239624,
+      "learning_rate": 9.981104021955063e-05,
+      "loss": 1.073,
+      "step": 72
+    },
+    {
+      "epoch": 0.0444146994402531,
+      "grad_norm": 1.122699499130249,
+      "learning_rate": 9.979623651578881e-05,
+      "loss": 1.0509,
+      "step": 73
+    },
+    {
+      "epoch": 0.045023119980530546,
+      "grad_norm": 1.1595953702926636,
+      "learning_rate": 9.978087590151393e-05,
+      "loss": 1.1094,
+      "step": 74
+    },
+    {
+      "epoch": 0.045631540520807985,
+      "grad_norm": 1.62815523147583,
+      "learning_rate": 9.976495856769038e-05,
+      "loss": 1.1211,
+      "step": 75
+    },
+    {
+      "epoch": 0.045631540520807985,
+      "eval_loss": 1.0243722200393677,
+      "eval_runtime": 0.0649,
+      "eval_samples_per_second": 770.624,
+      "eval_steps_per_second": 46.237,
+      "step": 75
+    },
+    {
+      "epoch": 0.046239961061085424,
+      "grad_norm": 2.726969003677368,
+      "learning_rate": 9.97484847122038e-05,
+      "loss": 2.205,
+      "step": 76
+    },
+    {
+      "epoch": 0.046848381601362864,
+      "grad_norm": 2.2901804447174072,
+      "learning_rate": 9.973145453985854e-05,
+      "loss": 1.1102,
+      "step": 77
+    },
+    {
+      "epoch": 0.0474568021416403,
+      "grad_norm": 2.2033584117889404,
+      "learning_rate": 9.971386826237507e-05,
+      "loss": 1.0353,
+      "step": 78
+    },
+    {
+      "epoch": 0.04806522268191774,
+      "grad_norm": 2.2385048866271973,
+      "learning_rate": 9.969572609838744e-05,
+      "loss": 1.0281,
+      "step": 79
+    },
+    {
+      "epoch": 0.04867364322219518,
+      "grad_norm": 1.700537919998169,
+      "learning_rate": 9.967702827344057e-05,
+      "loss": 1.0513,
+      "step": 80
+    },
+    {
+      "epoch": 0.04928206376247262,
+      "grad_norm": 1.1010593175888062,
+      "learning_rate": 9.965777501998734e-05,
+      "loss": 1.0073,
+      "step": 81
+    },
+    {
+      "epoch": 0.04989048430275006,
+      "grad_norm": 0.7716583609580994,
+      "learning_rate": 9.963796657738579e-05,
+      "loss": 1.0205,
+      "step": 82
+    },
+    {
+      "epoch": 0.0504989048430275,
+      "grad_norm": 0.7150983810424805,
+      "learning_rate": 9.961760319189612e-05,
+      "loss": 0.924,
+      "step": 83
+    },
+    {
+      "epoch": 0.05110732538330494,
+      "grad_norm": 0.9970099925994873,
+      "learning_rate": 9.959668511667762e-05,
+      "loss": 1.0786,
+      "step": 84
+    },
+    {
+      "epoch": 0.05171574592358238,
+      "grad_norm": 1.10440194606781,
+      "learning_rate": 9.957521261178554e-05,
+      "loss": 1.0916,
+      "step": 85
+    },
+    {
+      "epoch": 0.05232416646385982,
+      "grad_norm": 1.2334967851638794,
+      "learning_rate": 9.95531859441678e-05,
+      "loss": 1.0281,
+      "step": 86
+    },
+    {
+      "epoch": 0.05293258700413726,
+      "grad_norm": 1.5450046062469482,
+      "learning_rate": 9.953060538766178e-05,
+      "loss": 0.9459,
+      "step": 87
+    },
+    {
+      "epoch": 0.0535410075444147,
+      "grad_norm": 2.800281524658203,
+      "learning_rate": 9.950747122299084e-05,
+      "loss": 2.3543,
+      "step": 88
+    },
+    {
+      "epoch": 0.05414942808469214,
+      "grad_norm": 1.7520790100097656,
+      "learning_rate": 9.948378373776079e-05,
+      "loss": 1.0488,
+      "step": 89
+    },
+    {
+      "epoch": 0.05475784862496958,
+      "grad_norm": 1.148888111114502,
+      "learning_rate": 9.945954322645642e-05,
+      "loss": 0.8649,
+      "step": 90
+    },
+    {
+      "epoch": 0.05536626916524702,
+      "grad_norm": 0.883175253868103,
+      "learning_rate": 9.943474999043775e-05,
+      "loss": 0.9496,
+      "step": 91
+    },
+    {
+      "epoch": 0.05597468970552446,
+      "grad_norm": 1.041022539138794,
+      "learning_rate": 9.940940433793637e-05,
+      "loss": 0.9575,
+      "step": 92
+    },
+    {
+      "epoch": 0.0565831102458019,
+      "grad_norm": 0.8950981497764587,
+      "learning_rate": 9.938350658405152e-05,
+      "loss": 0.8507,
+      "step": 93
+    },
+    {
+      "epoch": 0.05719153078607934,
+      "grad_norm": 0.8415868282318115,
+      "learning_rate": 9.935705705074617e-05,
+      "loss": 0.9419,
+      "step": 94
+    },
+    {
+      "epoch": 0.05779995132635678,
+      "grad_norm": 0.8708381652832031,
+      "learning_rate": 9.933005606684317e-05,
+      "loss": 1.0413,
+      "step": 95
+    },
+    {
+      "epoch": 0.058408371866634216,
+      "grad_norm": 1.0290625095367432,
+      "learning_rate": 9.930250396802094e-05,
+      "loss": 0.9954,
+      "step": 96
+    },
+    {
+      "epoch": 0.059016792406911656,
+      "grad_norm": 0.8220187425613403,
+      "learning_rate": 9.927440109680946e-05,
+      "loss": 0.987,
+      "step": 97
+    },
+    {
+      "epoch": 0.059625212947189095,
+      "grad_norm": 0.8632601499557495,
+      "learning_rate": 9.924574780258596e-05,
+      "loss": 0.9248,
+      "step": 98
+    },
+    {
+      "epoch": 0.060233633487466534,
+      "grad_norm": 1.202643632888794,
+      "learning_rate": 9.921654444157054e-05,
+      "loss": 0.9264,
+      "step": 99
+    },
+    {
+      "epoch": 0.06084205402774397,
+      "grad_norm": 1.6064764261245728,
+      "learning_rate": 9.91867913768218e-05,
+      "loss": 1.032,
+      "step": 100
+    },
+    {
+      "epoch": 0.06084205402774397,
+      "eval_loss": 0.901063084602356,
+      "eval_runtime": 0.0644,
+      "eval_samples_per_second": 776.142,
+      "eval_steps_per_second": 46.569,
+      "step": 100
+    },
+    {
+      "epoch": 0.06145047456802142,
+      "grad_norm": 2.1135504245758057,
+      "learning_rate": 9.915648897823232e-05,
+      "loss": 1.8061,
+      "step": 101
+    },
+    {
+      "epoch": 0.06205889510829886,
+      "grad_norm": 1.5115822553634644,
+      "learning_rate": 9.912563762252399e-05,
+      "loss": 0.9178,
+      "step": 102
+    },
+    {
+      "epoch": 0.06266731564857629,
+      "grad_norm": 1.3775817155838013,
+      "learning_rate": 9.909423769324343e-05,
+      "loss": 0.8464,
+      "step": 103
+    },
+    {
+      "epoch": 0.06327573618885374,
+      "grad_norm": 1.1930534839630127,
+      "learning_rate": 9.906228958075717e-05,
+      "loss": 0.9817,
+      "step": 104
+    },
+    {
+      "epoch": 0.06388415672913117,
+      "grad_norm": 1.158815622329712,
+      "learning_rate": 9.902979368224675e-05,
+      "loss": 0.9052,
+      "step": 105
+    },
+    {
+      "epoch": 0.06449257726940862,
+      "grad_norm": 0.8110672831535339,
+      "learning_rate": 9.899675040170388e-05,
+      "loss": 0.8699,
+      "step": 106
+    },
+    {
+      "epoch": 0.06510099780968605,
+      "grad_norm": 0.6599923372268677,
+      "learning_rate": 9.896316014992537e-05,
+      "loss": 0.8528,
+      "step": 107
+    },
+    {
+      "epoch": 0.0657094183499635,
+      "grad_norm": 0.7083361744880676,
+      "learning_rate": 9.892902334450798e-05,
+      "loss": 0.9154,
+      "step": 108
+    },
+    {
+      "epoch": 0.06631783889024094,
+      "grad_norm": 1.0131536722183228,
+      "learning_rate": 9.889434040984332e-05,
+      "loss": 0.9124,
+      "step": 109
+    },
+    {
+      "epoch": 0.06692625943051837,
+      "grad_norm": 1.1790049076080322,
+      "learning_rate": 9.885911177711248e-05,
+      "loss": 0.8958,
+      "step": 110
+    },
+    {
+      "epoch": 0.06753467997079582,
+      "grad_norm": 1.2120789289474487,
+      "learning_rate": 9.882333788428073e-05,
+      "loss": 0.8547,
+      "step": 111
+    },
+    {
+      "epoch": 0.06814310051107325,
+      "grad_norm": 1.194826364517212,
+      "learning_rate": 9.878701917609207e-05,
+      "loss": 0.9218,
+      "step": 112
+    },
+    {
+      "epoch": 0.0687515210513507,
+      "grad_norm": 2.966965913772583,
+      "learning_rate": 9.875015610406369e-05,
+      "loss": 2.5956,
+      "step": 113
+    },
+    {
+      "epoch": 0.06935994159162813,
+      "grad_norm": 1.3608638048171997,
+      "learning_rate": 9.871274912648033e-05,
+      "loss": 0.9144,
+      "step": 114
+    },
+    {
+      "epoch": 0.06996836213190558,
+      "grad_norm": 1.4627468585968018,
+      "learning_rate": 9.867479870838862e-05,
+      "loss": 0.9815,
+      "step": 115
+    },
+    {
+      "epoch": 0.07057678267218301,
+      "grad_norm": 1.1806144714355469,
+      "learning_rate": 9.863630532159132e-05,
+      "loss": 0.7937,
+      "step": 116
+    },
+    {
+      "epoch": 0.07118520321246045,
+      "grad_norm": 1.0851095914840698,
+      "learning_rate": 9.859726944464137e-05,
+      "loss": 0.8003,
+      "step": 117
+    },
+    {
+      "epoch": 0.07179362375273789,
+      "grad_norm": 1.126287579536438,
+      "learning_rate": 9.855769156283603e-05,
+      "loss": 0.9241,
+      "step": 118
+    },
+    {
+      "epoch": 0.07240204429301533,
+      "grad_norm": 0.6791806817054749,
+      "learning_rate": 9.851757216821079e-05,
+      "loss": 0.9201,
+      "step": 119
+    },
+    {
+      "epoch": 0.07301046483329277,
+      "grad_norm": 0.7268375158309937,
+      "learning_rate": 9.847691175953328e-05,
+      "loss": 0.8126,
+      "step": 120
+    },
+    {
+      "epoch": 0.07361888537357021,
+      "grad_norm": 0.8680149912834167,
+      "learning_rate": 9.843571084229707e-05,
+      "loss": 0.8912,
+      "step": 121
+    },
+    {
+      "epoch": 0.07422730591384766,
+      "grad_norm": 1.042919397354126,
+      "learning_rate": 9.839396992871535e-05,
+      "loss": 0.9064,
+      "step": 122
+    },
+    {
+      "epoch": 0.07483572645412509,
+      "grad_norm": 1.2081691026687622,
+      "learning_rate": 9.835168953771461e-05,
+      "loss": 0.9376,
+      "step": 123
+    },
+    {
+      "epoch": 0.07544414699440254,
+      "grad_norm": 1.1437644958496094,
+      "learning_rate": 9.830887019492818e-05,
+      "loss": 0.9418,
+      "step": 124
+    },
+    {
+      "epoch": 0.07605256753467997,
+      "grad_norm": 1.2367491722106934,
+      "learning_rate": 9.826551243268966e-05,
+      "loss": 1.015,
+      "step": 125
+    },
+    {
+      "epoch": 0.07605256753467997,
+      "eval_loss": 0.8607701063156128,
+      "eval_runtime": 0.0636,
+      "eval_samples_per_second": 785.848,
+      "eval_steps_per_second": 47.151,
+      "step": 125
+    },
+    {
+      "epoch": 0.07666098807495741,
+      "grad_norm": 2.4859538078308105,
+      "learning_rate": 9.82216167900263e-05,
+      "loss": 1.8291,
+      "step": 126
+    },
+    {
+      "epoch": 0.07726940861523485,
+      "grad_norm": 1.4214491844177246,
+      "learning_rate": 9.81771838126524e-05,
+      "loss": 1.0467,
+      "step": 127
+    },
+    {
+      "epoch": 0.0778778291555123,
+      "grad_norm": 1.3560972213745117,
+      "learning_rate": 9.813221405296237e-05,
+      "loss": 1.0159,
+      "step": 128
+    },
+    {
+      "epoch": 0.07848624969578973,
+      "grad_norm": 1.501007080078125,
+      "learning_rate": 9.8086708070024e-05,
+      "loss": 0.8479,
+      "step": 129
+    },
+    {
+      "epoch": 0.07909467023606717,
+      "grad_norm": 1.5460386276245117,
+      "learning_rate": 9.804066642957143e-05,
+      "loss": 0.9617,
+      "step": 130
+    },
+    {
+      "epoch": 0.0797030907763446,
+      "grad_norm": 1.2963954210281372,
+      "learning_rate": 9.799408970399813e-05,
+      "loss": 0.8346,
+      "step": 131
+    },
+    {
+      "epoch": 0.08031151131662205,
+      "grad_norm": 0.8653491139411926,
+      "learning_rate": 9.79469784723498e-05,
+      "loss": 0.8009,
+      "step": 132
+    },
+    {
+      "epoch": 0.08091993185689948,
+      "grad_norm": 1.0787755250930786,
+      "learning_rate": 9.789933332031717e-05,
+      "loss": 0.9501,
+      "step": 133
+    },
+    {
+      "epoch": 0.08152835239717693,
+      "grad_norm": 1.0019638538360596,
+      "learning_rate": 9.78511548402287e-05,
+      "loss": 0.841,
+      "step": 134
+    },
+    {
+      "epoch": 0.08213677293745437,
+      "grad_norm": 1.1226329803466797,
+      "learning_rate": 9.780244363104323e-05,
+      "loss": 0.8492,
+      "step": 135
+    },
+    {
+      "epoch": 0.08274519347773181,
+      "grad_norm": 1.269909381866455,
+      "learning_rate": 9.775320029834254e-05,
+      "loss": 0.854,
+      "step": 136
+    },
+    {
+      "epoch": 0.08335361401800925,
+      "grad_norm": 1.76808762550354,
+      "learning_rate": 9.770342545432383e-05,
+      "loss": 0.8746,
+      "step": 137
+    },
+    {
+      "epoch": 0.08396203455828669,
+      "grad_norm": 3.7219080924987793,
+      "learning_rate": 9.765311971779204e-05,
+      "loss": 2.2368,
+      "step": 138
+    },
+    {
+      "epoch": 0.08457045509856413,
+      "grad_norm": 1.7717487812042236,
+      "learning_rate": 9.760228371415227e-05,
+      "loss": 1.0042,
+      "step": 139
+    },
+    {
+      "epoch": 0.08517887563884156,
+      "grad_norm": 1.4473094940185547,
+      "learning_rate": 9.75509180754019e-05,
+      "loss": 0.8678,
+      "step": 140
+    },
+    {
+      "epoch": 0.08578729617911901,
+      "grad_norm": 1.3099236488342285,
+      "learning_rate": 9.749902344012279e-05,
+      "loss": 0.7265,
+      "step": 141
+    },
+    {
+      "epoch": 0.08639571671939644,
+      "grad_norm": 1.1434625387191772,
+      "learning_rate": 9.744660045347336e-05,
+      "loss": 0.7999,
+      "step": 142
+    },
+    {
+      "epoch": 0.08700413725967389,
+      "grad_norm": 1.1469634771347046,
+      "learning_rate": 9.73936497671805e-05,
+      "loss": 0.8769,
+      "step": 143
+    },
+    {
+      "epoch": 0.08761255779995132,
+      "grad_norm": 1.1170365810394287,
+      "learning_rate": 9.734017203953149e-05,
+      "loss": 0.8353,
+      "step": 144
+    },
+    {
+      "epoch": 0.08822097834022877,
+      "grad_norm": 0.7087867259979248,
+      "learning_rate": 9.728616793536588e-05,
+      "loss": 0.8558,
+      "step": 145
+    },
+    {
+      "epoch": 0.0888293988805062,
+      "grad_norm": 0.7099660634994507,
+      "learning_rate": 9.723163812606716e-05,
+      "loss": 0.7829,
+      "step": 146
+    },
+    {
+      "epoch": 0.08943781942078365,
+      "grad_norm": 1.0997332334518433,
+      "learning_rate": 9.71765832895544e-05,
+      "loss": 0.8654,
+      "step": 147
+    },
+    {
+      "epoch": 0.09004623996106109,
+      "grad_norm": 1.0360599756240845,
+      "learning_rate": 9.712100411027391e-05,
+      "loss": 0.8817,
+      "step": 148
+    },
+    {
+      "epoch": 0.09065466050133852,
+      "grad_norm": 1.460658311843872,
+      "learning_rate": 9.70649012791906e-05,
+      "loss": 0.8495,
+      "step": 149
+    },
+    {
+      "epoch": 0.09126308104161597,
+      "grad_norm": 1.6194958686828613,
+      "learning_rate": 9.700827549377955e-05,
+      "loss": 0.929,
+      "step": 150
+    },
+    {
+      "epoch": 0.09126308104161597,
+      "eval_loss": 0.8000746369361877,
+      "eval_runtime": 0.0648,
+      "eval_samples_per_second": 771.193,
+      "eval_steps_per_second": 46.272,
+      "step": 150
+    },
+    {
+      "epoch": 0.0918715015818934,
+      "grad_norm": 2.0881123542785645,
+      "learning_rate": 9.695112745801716e-05,
+      "loss": 1.903,
+      "step": 151
+    },
+    {
+      "epoch": 0.09247992212217085,
+      "grad_norm": 1.1570873260498047,
+      "learning_rate": 9.689345788237256e-05,
+      "loss": 0.9427,
+      "step": 152
+    },
+    {
+      "epoch": 0.09308834266244828,
+      "grad_norm": 0.8610666990280151,
+      "learning_rate": 9.683526748379864e-05,
+      "loss": 0.8573,
+      "step": 153
+    },
+    {
+      "epoch": 0.09369676320272573,
+      "grad_norm": 0.8190277218818665,
+      "learning_rate": 9.677655698572326e-05,
+      "loss": 0.6991,
+      "step": 154
+    },
+    {
+      "epoch": 0.09430518374300316,
+      "grad_norm": 0.8921626210212708,
+      "learning_rate": 9.671732711804022e-05,
+      "loss": 0.7823,
+      "step": 155
+    },
+    {
+      "epoch": 0.0949136042832806,
+      "grad_norm": 0.6367238759994507,
+      "learning_rate": 9.665757861710008e-05,
+      "loss": 0.8343,
+      "step": 156
+    },
+    {
+      "epoch": 0.09552202482355804,
+      "grad_norm": 0.533492922782898,
+      "learning_rate": 9.659731222570114e-05,
+      "loss": 0.8161,
+      "step": 157
+    },
+    {
+      "epoch": 0.09613044536383548,
+      "grad_norm": 0.7728853821754456,
+      "learning_rate": 9.653652869308019e-05,
+      "loss": 0.925,
+      "step": 158
+    },
+    {
+      "epoch": 0.09673886590411292,
+      "grad_norm": 0.7567634582519531,
+      "learning_rate": 9.647522877490312e-05,
+      "loss": 0.8247,
+      "step": 159
+    },
+    {
+      "epoch": 0.09734728644439036,
+      "grad_norm": 0.6781755685806274,
+      "learning_rate": 9.641341323325554e-05,
+      "loss": 0.8119,
+      "step": 160
+    },
+    {
+      "epoch": 0.09795570698466781,
+      "grad_norm": 0.9459850788116455,
+      "learning_rate": 9.635108283663343e-05,
+      "loss": 0.7861,
+      "step": 161
+    },
+    {
+      "epoch": 0.09856412752494524,
+      "grad_norm": 0.8214953541755676,
+      "learning_rate": 9.628823835993338e-05,
+      "loss": 0.8647,
+      "step": 162
+    },
+    {
+      "epoch": 0.09917254806522269,
+      "grad_norm": 2.5658833980560303,
+      "learning_rate": 9.622488058444314e-05,
+      "loss": 2.3544,
+      "step": 163
+    },
+    {
+      "epoch": 0.09978096860550012,
+      "grad_norm": 1.3964160680770874,
+      "learning_rate": 9.61610102978318e-05,
+      "loss": 0.8933,
+      "step": 164
+    },
+    {
+      "epoch": 0.10038938914577757,
+      "grad_norm": 1.2962576150894165,
+      "learning_rate": 9.609662829414005e-05,
+      "loss": 0.7469,
+      "step": 165
+    },
+    {
+      "epoch": 0.100997809686055,
+      "grad_norm": 1.0267356634140015,
+      "learning_rate": 9.603173537377026e-05,
+      "loss": 0.8354,
+      "step": 166
+    },
+    {
+      "epoch": 0.10160623022633244,
+      "grad_norm": 0.7708994150161743,
+      "learning_rate": 9.59663323434766e-05,
+      "loss": 0.9245,
+      "step": 167
+    },
+    {
+      "epoch": 0.10221465076660988,
+      "grad_norm": 0.5819109678268433,
+      "learning_rate": 9.590042001635495e-05,
+      "loss": 0.8,
+      "step": 168
+    },
+    {
+      "epoch": 0.10282307130688732,
+      "grad_norm": 0.5333255529403687,
+      "learning_rate": 9.583399921183276e-05,
+      "loss": 0.798,
+      "step": 169
+    },
+    {
+      "epoch": 0.10343149184716476,
+      "grad_norm": 0.9702023267745972,
+      "learning_rate": 9.5767070755659e-05,
+      "loss": 0.9434,
+      "step": 170
+    },
+    {
+      "epoch": 0.1040399123874422,
+      "grad_norm": 0.9722750186920166,
+      "learning_rate": 9.569963547989376e-05,
+      "loss": 0.8818,
+      "step": 171
+    },
+    {
+      "epoch": 0.10464833292771963,
+      "grad_norm": 1.0027716159820557,
+      "learning_rate": 9.563169422289797e-05,
+      "loss": 0.7531,
+      "step": 172
+    },
+    {
+      "epoch": 0.10525675346799708,
+      "grad_norm": 0.7870794534683228,
+      "learning_rate": 9.556324782932292e-05,
+      "loss": 0.8253,
+      "step": 173
+    },
+    {
+      "epoch": 0.10586517400827453,
+      "grad_norm": 0.7732038497924805,
+      "learning_rate": 9.549429715009983e-05,
+      "loss": 0.8425,
+      "step": 174
+    },
+    {
+      "epoch": 0.10647359454855196,
+      "grad_norm": 1.3445314168930054,
+      "learning_rate": 9.542484304242927e-05,
+      "loss": 0.8793,
+      "step": 175
+    },
+    {
+      "epoch": 0.10647359454855196,
+      "eval_loss": 0.7928541302680969,
+      "eval_runtime": 0.0638,
+      "eval_samples_per_second": 783.396,
+      "eval_steps_per_second": 47.004,
+      "step": 175
+    },
+    {
+      "epoch": 0.1070820150888294,
+      "grad_norm": 3.020885705947876,
+      "learning_rate": 9.535488636977042e-05,
+      "loss": 1.6845,
+      "step": 176
+    },
+    {
+      "epoch": 0.10769043562910684,
+      "grad_norm": 2.2240676879882812,
+      "learning_rate": 9.528442800183043e-05,
+      "loss": 0.8827,
+      "step": 177
+    },
+    {
+      "epoch": 0.10829885616938428,
+      "grad_norm": 1.7883273363113403,
+      "learning_rate": 9.521346881455356e-05,
+      "loss": 0.7705,
+      "step": 178
+    },
+    {
+      "epoch": 0.10890727670966172,
+      "grad_norm": 1.2515283823013306,
+      "learning_rate": 9.514200969011025e-05,
+      "loss": 0.7441,
+      "step": 179
+    },
+    {
+      "epoch": 0.10951569724993916,
+      "grad_norm": 0.8652520179748535,
+      "learning_rate": 9.507005151688627e-05,
+      "loss": 0.725,
+      "step": 180
+    },
+    {
+      "epoch": 0.1101241177902166,
+      "grad_norm": 0.6205310225486755,
+      "learning_rate": 9.499759518947156e-05,
+      "loss": 0.7823,
+      "step": 181
+    },
+    {
+      "epoch": 0.11073253833049404,
+      "grad_norm": 0.6425133943557739,
+      "learning_rate": 9.492464160864917e-05,
+      "loss": 0.7767,
+      "step": 182
+    },
+    {
+      "epoch": 0.11134095887077147,
+      "grad_norm": 1.1534785032272339,
+      "learning_rate": 9.485119168138405e-05,
+      "loss": 0.8115,
+      "step": 183
+    },
+    {
+      "epoch": 0.11194937941104892,
+      "grad_norm": 1.0528301000595093,
+      "learning_rate": 9.477724632081176e-05,
+      "loss": 0.7672,
+      "step": 184
+    },
+    {
+      "epoch": 0.11255779995132635,
+      "grad_norm": 1.1875839233398438,
+      "learning_rate": 9.470280644622713e-05,
+      "loss": 0.8329,
+      "step": 185
+    },
+    {
+      "epoch": 0.1131662204916038,
+      "grad_norm": 1.0731632709503174,
+      "learning_rate": 9.462787298307285e-05,
+      "loss": 0.8891,
+      "step": 186
+    },
+    {
+      "epoch": 0.11377464103188123,
+      "grad_norm": 1.1598612070083618,
+      "learning_rate": 9.455244686292789e-05,
+      "loss": 0.7696,
+      "step": 187
+    },
+    {
+      "epoch": 0.11438306157215868,
+      "grad_norm": 3.4111616611480713,
+      "learning_rate": 9.447652902349602e-05,
+      "loss": 1.4939,
+      "step": 188
+    },
+    {
+      "epoch": 0.11499148211243612,
+      "grad_norm": 1.8949023485183716,
+      "learning_rate": 9.44001204085941e-05,
+      "loss": 0.8453,
+      "step": 189
+    },
+    {
+      "epoch": 0.11559990265271355,
+      "grad_norm": 1.656935214996338,
+      "learning_rate": 9.432322196814033e-05,
+      "loss": 0.7722,
+      "step": 190
+    },
+    {
+      "epoch": 0.116208323192991,
+      "grad_norm": 1.8966083526611328,
+      "learning_rate": 9.424583465814249e-05,
+      "loss": 0.7714,
+      "step": 191
+    },
+    {
+      "epoch": 0.11681674373326843,
+      "grad_norm": 1.4729326963424683,
+      "learning_rate": 9.4167959440686e-05,
+      "loss": 0.8103,
+      "step": 192
+    },
+    {
+      "epoch": 0.11742516427354588,
+      "grad_norm": 1.2855483293533325,
+      "learning_rate": 9.408959728392199e-05,
+      "loss": 0.751,
+      "step": 193
+    },
+    {
+      "epoch": 0.11803358481382331,
+      "grad_norm": 0.6022900938987732,
+      "learning_rate": 9.401074916205528e-05,
+      "loss": 0.7532,
+      "step": 194
+    },
+    {
+      "epoch": 0.11864200535410076,
+      "grad_norm": 0.6037607789039612,
+      "learning_rate": 9.393141605533224e-05,
+      "loss": 0.683,
+      "step": 195
+    },
+    {
+      "epoch": 0.11925042589437819,
+      "grad_norm": 1.0040525197982788,
+      "learning_rate": 9.385159895002859e-05,
+      "loss": 0.7185,
+      "step": 196
+    },
+    {
+      "epoch": 0.11985884643465564,
+      "grad_norm": 1.1619277000427246,
+      "learning_rate": 9.37712988384372e-05,
+      "loss": 0.934,
+      "step": 197
+    },
+    {
+      "epoch": 0.12046726697493307,
+      "grad_norm": 1.2666449546813965,
+      "learning_rate": 9.369051671885566e-05,
+      "loss": 0.8437,
+      "step": 198
+    },
+    {
+      "epoch": 0.12107568751521051,
+      "grad_norm": 1.3021451234817505,
+      "learning_rate": 9.360925359557397e-05,
+      "loss": 0.7939,
+      "step": 199
+    },
+    {
+      "epoch": 0.12168410805548795,
+      "grad_norm": 1.3136470317840576,
+      "learning_rate": 9.3527510478862e-05,
+      "loss": 0.8785,
+      "step": 200
+    },
+    {
+      "epoch": 0.12168410805548795,
+      "eval_loss": 0.770029604434967,
+      "eval_runtime": 0.0645,
+      "eval_samples_per_second": 775.029,
+      "eval_steps_per_second": 46.502,
+      "step": 200
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 937,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 50,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 1,
+        "early_stopping_threshold": 0.0
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 0
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.3040284166258688e+16,
+  "train_batch_size": 6,
+  "trial_name": null,
+  "trial_params": null
+}

last-checkpoint/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1c7f758a168c682ec156a053181a1d73670ecd00a5ef4c804eab91ecc0c3217
+size 6776

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,44 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false,
+  "use_fast": true
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1c7f758a168c682ec156a053181a1d73670ecd00a5ef4c804eab91ecc0c3217
+size 6776