End of training

README.md

@@ -0,0 +1,178 @@
+---
+library_name: peft
+license: apache-2.0
+base_model: JackFram/llama-160m
+tags:
+- axolotl
+- generated_from_trainer
+model-index:
+- name: f9eb2fff-bae0-49b0-89c5-624fc71c75d0
+  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-160m
+bf16: auto
+chat_template: llama3
+cosine_min_lr_ratio: 0.1
+data_processes: 16
+dataset_prepared_path: null
+datasets:
+- data_files:
+  - a176eebac3e98bce_train_data.json
+  ds_type: json
+  format: custom
+  path: /workspace/input_data/a176eebac3e98bce_train_data.json
+  type:
+    field_input: "\uD310\uACB0\uC694\uC9C0"
+    field_instruction: "\uBC95\uC6D0\uBA85"
+    field_output: "\uD310\uACB0\uC720\uD615"
+    format: '{instruction} {input}'
+    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: 1
+eval_sample_packing: false
+eval_steps: 25
+evaluation_strategy: steps
+flash_attention: true
+fp16: null
+fsdp: null
+fsdp_config: null
+gradient_accumulation_steps: 64
+gradient_checkpointing: true
+group_by_length: true
+hub_model_id: sn56b1/f9eb2fff-bae0-49b0-89c5-624fc71c75d0
+hub_repo: stevemonite
+hub_strategy: checkpoint
+hub_token: null
+learning_rate: 0.0003
+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: 1200
+micro_batch_size: 1
+mlflow_experiment_name: /tmp/a176eebac3e98bce_train_data.json
+model_type: AutoModelForCausalLM
+num_epochs: 2
+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: f9eb2fff-bae0-49b0-89c5-624fc71c75d0
+wandb_project: god
+wandb_run: v0xl
+wandb_runid: f9eb2fff-bae0-49b0-89c5-624fc71c75d0
+warmup_raio: 0.03
+warmup_ratio: 0.03
+weight_decay: 0.01
+xformers_attention: null
+
+```
+
+</details><br>
+
+# f9eb2fff-bae0-49b0-89c5-624fc71c75d0
+
+This model is a fine-tuned version of [JackFram/llama-160m](https://huggingface.co/JackFram/llama-160m) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.2604
+
+## 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: 0.0003
+- train_batch_size: 1
+- eval_batch_size: 1
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 4
+- gradient_accumulation_steps: 64
+- total_train_batch_size: 256
+- total_eval_batch_size: 4
+- 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: 20
+- training_steps: 668
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 7.3791        | 0.0030 | 1    | 5.1000          |
+| 0.8964        | 0.0749 | 25   | 1.0535          |
+| 0.1023        | 0.1499 | 50   | 0.3284          |
+| 0.0862        | 0.2248 | 75   | 0.1645          |
+| 0.0421        | 0.2997 | 100  | 0.1421          |
+| 0.0401        | 0.3747 | 125  | 0.1297          |
+| 0.0459        | 0.4496 | 150  | 0.2604          |
+
+
+### 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-160m",
+  "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",
+    "o_proj",
+    "v_proj",
+    "k_proj",
+    "q_proj",
+    "down_proj",
+    "gate_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 sha256:902e1bd91f6ca7c84eb4cc5f09bc41460c3b294412c37de08109f7a6d0074b1c
+size 13626282

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18fc12de5654e0323293b5dd1ac28814fb994a9658fb252a535bc41258c43b46
+size 13587864

config.json

@@ -0,0 +1,31 @@
+{
+  "_attn_implementation_autoset": true,
+  "_name_or_path": "JackFram/llama-160m",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "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": 12,
+  "num_key_value_heads": 12,
+  "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-160m
+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-160m",
+  "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",
+    "o_proj",
+    "v_proj",
+    "k_proj",
+    "q_proj",
+    "down_proj",
+    "gate_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:ba13959f6cd207bdf12c64122f952291693563848f8b8c1cc4a1ca3762addfe3
+size 13587864

last-checkpoint/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:150eeb9db3c24cdacef19c4cb9526dee2bf01a997cfd73cd097231633997a73b
+size 27273018

last-checkpoint/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da2fcad6cd81bb97d0061e263e1a1cdbb08b9ec3a021caeb1339fbf78256db76
+size 15024

last-checkpoint/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f087b0a80be905d15bf4096528ebfb18cb89ccbf6b9eb78dac1d9a3823c111c8
+size 15024

last-checkpoint/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:def1ba2fc2803d327de014a2798b289b94491b993e12c279b943920162e3e860
+size 15024

last-checkpoint/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29f110bfb6c78dd11c3ef89591341a1beec9719bd9c484f380587fc8d405ee41
+size 15024

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0ce7eb31f33da60fb4a65f0698e2d0c23b798eb451451afdf0be495be03e58f
+size 1064

last-checkpoint/special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "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": false,
+    "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 +1,43 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "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": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

last-checkpoint/trainer_state.json

@@ -0,0 +1,1148 @@
+{
+  "best_metric": 0.14205443859100342,
+  "best_model_checkpoint": "miner_id_24/checkpoint-100",
+  "epoch": 0.44958553833185033,
+  "eval_steps": 25,
+  "global_step": 150,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0029972369222123355,
+      "grad_norm": 7.602510929107666,
+      "learning_rate": 1.4999999999999999e-05,
+      "loss": 7.3791,
+      "step": 1
+    },
+    {
+      "epoch": 0.0029972369222123355,
+      "eval_loss": 5.100011348724365,
+      "eval_runtime": 0.2905,
+      "eval_samples_per_second": 172.095,
+      "eval_steps_per_second": 44.745,
+      "step": 1
+    },
+    {
+      "epoch": 0.005994473844424671,
+      "grad_norm": 5.811465263366699,
+      "learning_rate": 2.9999999999999997e-05,
+      "loss": 5.2052,
+      "step": 2
+    },
+    {
+      "epoch": 0.008991710766637007,
+      "grad_norm": 6.1456217765808105,
+      "learning_rate": 4.4999999999999996e-05,
+      "loss": 5.0327,
+      "step": 3
+    },
+    {
+      "epoch": 0.011988947688849342,
+      "grad_norm": 5.857211112976074,
+      "learning_rate": 5.9999999999999995e-05,
+      "loss": 4.9457,
+      "step": 4
+    },
+    {
+      "epoch": 0.014986184611061678,
+      "grad_norm": 5.512299537658691,
+      "learning_rate": 7.5e-05,
+      "loss": 4.8063,
+      "step": 5
+    },
+    {
+      "epoch": 0.017983421533274015,
+      "grad_norm": 5.282471179962158,
+      "learning_rate": 8.999999999999999e-05,
+      "loss": 4.7355,
+      "step": 6
+    },
+    {
+      "epoch": 0.02098065845548635,
+      "grad_norm": 4.267989158630371,
+      "learning_rate": 0.00010499999999999999,
+      "loss": 4.4458,
+      "step": 7
+    },
+    {
+      "epoch": 0.023977895377698684,
+      "grad_norm": 3.799853801727295,
+      "learning_rate": 0.00011999999999999999,
+      "loss": 4.2302,
+      "step": 8
+    },
+    {
+      "epoch": 0.02697513229991102,
+      "grad_norm": 3.506157875061035,
+      "learning_rate": 0.000135,
+      "loss": 3.857,
+      "step": 9
+    },
+    {
+      "epoch": 0.029972369222123357,
+      "grad_norm": 3.8407812118530273,
+      "learning_rate": 0.00015,
+      "loss": 3.749,
+      "step": 10
+    },
+    {
+      "epoch": 0.03296960614433569,
+      "grad_norm": 4.470568656921387,
+      "learning_rate": 0.000165,
+      "loss": 3.4078,
+      "step": 11
+    },
+    {
+      "epoch": 0.03596684306654803,
+      "grad_norm": 4.822042465209961,
+      "learning_rate": 0.00017999999999999998,
+      "loss": 3.0358,
+      "step": 12
+    },
+    {
+      "epoch": 0.038964079988760364,
+      "grad_norm": 5.060558795928955,
+      "learning_rate": 0.000195,
+      "loss": 4.5688,
+      "step": 13
+    },
+    {
+      "epoch": 0.0419613169109727,
+      "grad_norm": 4.888822078704834,
+      "learning_rate": 0.00020999999999999998,
+      "loss": 3.6099,
+      "step": 14
+    },
+    {
+      "epoch": 0.04495855383318503,
+      "grad_norm": 3.4810433387756348,
+      "learning_rate": 0.000225,
+      "loss": 2.4291,
+      "step": 15
+    },
+    {
+      "epoch": 0.04795579075539737,
+      "grad_norm": 3.577241897583008,
+      "learning_rate": 0.00023999999999999998,
+      "loss": 2.1686,
+      "step": 16
+    },
+    {
+      "epoch": 0.0509530276776097,
+      "grad_norm": 3.595766544342041,
+      "learning_rate": 0.00025499999999999996,
+      "loss": 1.9973,
+      "step": 17
+    },
+    {
+      "epoch": 0.05395026459982204,
+      "grad_norm": 4.025913715362549,
+      "learning_rate": 0.00027,
+      "loss": 1.9723,
+      "step": 18
+    },
+    {
+      "epoch": 0.05694750152203437,
+      "grad_norm": 2.864335536956787,
+      "learning_rate": 0.000285,
+      "loss": 1.9312,
+      "step": 19
+    },
+    {
+      "epoch": 0.05994473844424671,
+      "grad_norm": 3.9801218509674072,
+      "learning_rate": 0.0003,
+      "loss": 1.8875,
+      "step": 20
+    },
+    {
+      "epoch": 0.06294197536645904,
+      "grad_norm": 3.2217376232147217,
+      "learning_rate": 0.00029999841345404617,
+      "loss": 1.5763,
+      "step": 21
+    },
+    {
+      "epoch": 0.06593921228867138,
+      "grad_norm": 19.193851470947266,
+      "learning_rate": 0.0002999936538534755,
+      "loss": 1.8067,
+      "step": 22
+    },
+    {
+      "epoch": 0.06893644921088371,
+      "grad_norm": 25.025583267211914,
+      "learning_rate": 0.0002999857213101595,
+      "loss": 1.4576,
+      "step": 23
+    },
+    {
+      "epoch": 0.07193368613309606,
+      "grad_norm": 4.855524063110352,
+      "learning_rate": 0.00029997461601054764,
+      "loss": 1.0614,
+      "step": 24
+    },
+    {
+      "epoch": 0.0749309230553084,
+      "grad_norm": 3.3954389095306396,
+      "learning_rate": 0.00029996033821566326,
+      "loss": 0.8964,
+      "step": 25
+    },
+    {
+      "epoch": 0.0749309230553084,
+      "eval_loss": 1.0534682273864746,
+      "eval_runtime": 0.2881,
+      "eval_samples_per_second": 173.557,
+      "eval_steps_per_second": 45.125,
+      "step": 25
+    },
+    {
+      "epoch": 0.07792815997752073,
+      "grad_norm": 12.105545997619629,
+      "learning_rate": 0.0002999428882610971,
+      "loss": 3.0311,
+      "step": 26
+    },
+    {
+      "epoch": 0.08092539689973306,
+      "grad_norm": 3.334498882293701,
+      "learning_rate": 0.00029992226655699945,
+      "loss": 1.2946,
+      "step": 27
+    },
+    {
+      "epoch": 0.0839226338219454,
+      "grad_norm": 2.8498733043670654,
+      "learning_rate": 0.00029989847358807104,
+      "loss": 1.1872,
+      "step": 28
+    },
+    {
+      "epoch": 0.08691987074415773,
+      "grad_norm": 2.367673873901367,
+      "learning_rate": 0.0002998715099135508,
+      "loss": 1.0292,
+      "step": 29
+    },
+    {
+      "epoch": 0.08991710766637007,
+      "grad_norm": 8.79304313659668,
+      "learning_rate": 0.00029984137616720325,
+      "loss": 1.2032,
+      "step": 30
+    },
+    {
+      "epoch": 0.0929143445885824,
+      "grad_norm": 8.142653465270996,
+      "learning_rate": 0.00029980807305730374,
+      "loss": 1.2389,
+      "step": 31
+    },
+    {
+      "epoch": 0.09591158151079474,
+      "grad_norm": 4.5038628578186035,
+      "learning_rate": 0.0002997716013666212,
+      "loss": 1.0933,
+      "step": 32
+    },
+    {
+      "epoch": 0.09890881843300707,
+      "grad_norm": 2.439879894256592,
+      "learning_rate": 0.0002997319619524003,
+      "loss": 0.922,
+      "step": 33
+    },
+    {
+      "epoch": 0.1019060553552194,
+      "grad_norm": 2.002732992172241,
+      "learning_rate": 0.0002996891557463412,
+      "loss": 0.8141,
+      "step": 34
+    },
+    {
+      "epoch": 0.10490329227743174,
+      "grad_norm": 1.9198921918869019,
+      "learning_rate": 0.00029964318375457725,
+      "loss": 0.5868,
+      "step": 35
+    },
+    {
+      "epoch": 0.10790052919964407,
+      "grad_norm": 1.1390972137451172,
+      "learning_rate": 0.00029959404705765186,
+      "loss": 0.4158,
+      "step": 36
+    },
+    {
+      "epoch": 0.11089776612185641,
+      "grad_norm": 0.9061455130577087,
+      "learning_rate": 0.00029954174681049296,
+      "loss": 0.3104,
+      "step": 37
+    },
+    {
+      "epoch": 0.11389500304406874,
+      "grad_norm": 3.6855151653289795,
+      "learning_rate": 0.0002994862842423856,
+      "loss": 1.3318,
+      "step": 38
+    },
+    {
+      "epoch": 0.11689223996628108,
+      "grad_norm": 2.992558717727661,
+      "learning_rate": 0.00029942766065694333,
+      "loss": 1.0331,
+      "step": 39
+    },
+    {
+      "epoch": 0.11988947688849343,
+      "grad_norm": 2.762493133544922,
+      "learning_rate": 0.00029936587743207736,
+      "loss": 0.7132,
+      "step": 40
+    },
+    {
+      "epoch": 0.12288671381070576,
+      "grad_norm": 2.2291383743286133,
+      "learning_rate": 0.00029930093601996446,
+      "loss": 0.5774,
+      "step": 41
+    },
+    {
+      "epoch": 0.12588395073291808,
+      "grad_norm": 1.1489959955215454,
+      "learning_rate": 0.0002992328379470125,
+      "loss": 0.5567,
+      "step": 42
+    },
+    {
+      "epoch": 0.12888118765513043,
+      "grad_norm": 6.168476104736328,
+      "learning_rate": 0.00029916158481382474,
+      "loss": 0.6131,
+      "step": 43
+    },
+    {
+      "epoch": 0.13187842457734275,
+      "grad_norm": 5.408211708068848,
+      "learning_rate": 0.0002990871782951623,
+      "loss": 0.6638,
+      "step": 44
+    },
+    {
+      "epoch": 0.1348756614995551,
+      "grad_norm": 1.5306873321533203,
+      "learning_rate": 0.0002990096201399045,
+      "loss": 0.5488,
+      "step": 45
+    },
+    {
+      "epoch": 0.13787289842176742,
+      "grad_norm": 1.8623676300048828,
+      "learning_rate": 0.00029892891217100817,
+      "loss": 0.4659,
+      "step": 46
+    },
+    {
+      "epoch": 0.14087013534397977,
+      "grad_norm": 1.6640721559524536,
+      "learning_rate": 0.0002988450562854644,
+      "loss": 0.4368,
+      "step": 47
+    },
+    {
+      "epoch": 0.14386737226619212,
+      "grad_norm": 0.3559802174568176,
+      "learning_rate": 0.0002987580544542541,
+      "loss": 0.0507,
+      "step": 48
+    },
+    {
+      "epoch": 0.14686460918840444,
+      "grad_norm": 0.4540441334247589,
+      "learning_rate": 0.0002986679087223018,
+      "loss": 0.087,
+      "step": 49
+    },
+    {
+      "epoch": 0.1498618461106168,
+      "grad_norm": 0.8076233267784119,
+      "learning_rate": 0.00029857462120842744,
+      "loss": 0.1023,
+      "step": 50
+    },
+    {
+      "epoch": 0.1498618461106168,
+      "eval_loss": 0.3283706307411194,
+      "eval_runtime": 0.2882,
+      "eval_samples_per_second": 173.489,
+      "eval_steps_per_second": 45.107,
+      "step": 50
+    },
+    {
+      "epoch": 0.1528590830328291,
+      "grad_norm": 4.228235721588135,
+      "learning_rate": 0.0002984781941052967,
+      "loss": 1.0819,
+      "step": 51
+    },
+    {
+      "epoch": 0.15585631995504146,
+      "grad_norm": 3.424924612045288,
+      "learning_rate": 0.0002983786296793692,
+      "loss": 0.5749,
+      "step": 52
+    },
+    {
+      "epoch": 0.15885355687725378,
+      "grad_norm": 3.9904696941375732,
+      "learning_rate": 0.00029827593027084546,
+      "loss": 0.5831,
+      "step": 53
+    },
+    {
+      "epoch": 0.16185079379946612,
+      "grad_norm": 2.694119930267334,
+      "learning_rate": 0.00029817009829361196,
+      "loss": 0.4457,
+      "step": 54
+    },
+    {
+      "epoch": 0.16484803072167845,
+      "grad_norm": 1.2387803792953491,
+      "learning_rate": 0.00029806113623518407,
+      "loss": 0.3431,
+      "step": 55
+    },
+    {
+      "epoch": 0.1678452676438908,
+      "grad_norm": 1.6821039915084839,
+      "learning_rate": 0.0002979490466566481,
+      "loss": 0.3905,
+      "step": 56
+    },
+    {
+      "epoch": 0.17084250456610311,
+      "grad_norm": 0.6684949994087219,
+      "learning_rate": 0.00029783383219260037,
+      "loss": 0.3056,
+      "step": 57
+    },
+    {
+      "epoch": 0.17383974148831546,
+      "grad_norm": 0.7967026233673096,
+      "learning_rate": 0.0002977154955510861,
+      "loss": 0.3333,
+      "step": 58
+    },
+    {
+      "epoch": 0.17683697841052778,
+      "grad_norm": 0.5187807083129883,
+      "learning_rate": 0.0002975940395135351,
+      "loss": 0.2867,
+      "step": 59
+    },
+    {
+      "epoch": 0.17983421533274013,
+      "grad_norm": 7.2272138595581055,
+      "learning_rate": 0.00029746946693469693,
+      "loss": 1.0056,
+      "step": 60
+    },
+    {
+      "epoch": 0.18283145225495245,
+      "grad_norm": 8.9348726272583,
+      "learning_rate": 0.00029734178074257325,
+      "loss": 0.7786,
+      "step": 61
+    },
+    {
+      "epoch": 0.1858286891771648,
+      "grad_norm": 8.19704532623291,
+      "learning_rate": 0.0002972109839383494,
+      "loss": 0.3928,
+      "step": 62
+    },
+    {
+      "epoch": 0.18882592609937715,
+      "grad_norm": 4.3927483558654785,
+      "learning_rate": 0.00029707707959632386,
+      "loss": 0.7528,
+      "step": 63
+    },
+    {
+      "epoch": 0.19182316302158947,
+      "grad_norm": 2.271043539047241,
+      "learning_rate": 0.0002969400708638358,
+      "loss": 0.4877,
+      "step": 64
+    },
+    {
+      "epoch": 0.19482039994380182,
+      "grad_norm": 1.3864595890045166,
+      "learning_rate": 0.000296799960961191,
+      "loss": 0.2625,
+      "step": 65
+    },
+    {
+      "epoch": 0.19781763686601414,
+      "grad_norm": 2.2087323665618896,
+      "learning_rate": 0.00029665675318158656,
+      "loss": 0.2945,
+      "step": 66
+    },
+    {
+      "epoch": 0.2008148737882265,
+      "grad_norm": 3.766403913497925,
+      "learning_rate": 0.00029651045089103316,
+      "loss": 0.3807,
+      "step": 67
+    },
+    {
+      "epoch": 0.2038121107104388,
+      "grad_norm": 2.598832368850708,
+      "learning_rate": 0.0002963610575282762,
+      "loss": 0.3149,
+      "step": 68
+    },
+    {
+      "epoch": 0.20680934763265116,
+      "grad_norm": 0.677237331867218,
+      "learning_rate": 0.0002962085766047146,
+      "loss": 0.346,
+      "step": 69
+    },
+    {
+      "epoch": 0.20980658455486348,
+      "grad_norm": 0.5142577886581421,
+      "learning_rate": 0.00029605301170431867,
+      "loss": 0.2855,
+      "step": 70
+    },
+    {
+      "epoch": 0.21280382147707583,
+      "grad_norm": 0.5518949031829834,
+      "learning_rate": 0.00029589436648354566,
+      "loss": 0.3163,
+      "step": 71
+    },
+    {
+      "epoch": 0.21580105839928815,
+      "grad_norm": 0.336823046207428,
+      "learning_rate": 0.00029573264467125377,
+      "loss": 0.16,
+      "step": 72
+    },
+    {
+      "epoch": 0.2187982953215005,
+      "grad_norm": 0.2474360167980194,
+      "learning_rate": 0.0002955678500686147,
+      "loss": 0.0297,
+      "step": 73
+    },
+    {
+      "epoch": 0.22179553224371282,
+      "grad_norm": 0.18458165228366852,
+      "learning_rate": 0.0002953999865490242,
+      "loss": 0.0609,
+      "step": 74
+    },
+    {
+      "epoch": 0.22479276916592517,
+      "grad_norm": 0.36120983958244324,
+      "learning_rate": 0.0002952290580580109,
+      "loss": 0.0862,
+      "step": 75
+    },
+    {
+      "epoch": 0.22479276916592517,
+      "eval_loss": 0.16452732682228088,
+      "eval_runtime": 0.2888,
+      "eval_samples_per_second": 173.11,
+      "eval_steps_per_second": 45.009,
+      "step": 75
+    },
+    {
+      "epoch": 0.2277900060881375,
+      "grad_norm": 1.3333512544631958,
+      "learning_rate": 0.0002950550686131438,
+      "loss": 0.6146,
+      "step": 76
+    },
+    {
+      "epoch": 0.23078724301034984,
+      "grad_norm": 1.2993559837341309,
+      "learning_rate": 0.00029487802230393777,
+      "loss": 0.2574,
+      "step": 77
+    },
+    {
+      "epoch": 0.23378447993256216,
+      "grad_norm": 1.2781016826629639,
+      "learning_rate": 0.00029469792329175725,
+      "loss": 0.2978,
+      "step": 78
+    },
+    {
+      "epoch": 0.2367817168547745,
+      "grad_norm": 5.145886421203613,
+      "learning_rate": 0.0002945147758097187,
+      "loss": 0.3251,
+      "step": 79
+    },
+    {
+      "epoch": 0.23977895377698685,
+      "grad_norm": 5.573575019836426,
+      "learning_rate": 0.00029432858416259097,
+      "loss": 0.3483,
+      "step": 80
+    },
+    {
+      "epoch": 0.24277619069919917,
+      "grad_norm": 2.6032469272613525,
+      "learning_rate": 0.0002941393527266941,
+      "loss": 0.306,
+      "step": 81
+    },
+    {
+      "epoch": 0.24577342762141152,
+      "grad_norm": 0.6271111965179443,
+      "learning_rate": 0.00029394708594979657,
+      "loss": 0.318,
+      "step": 82
+    },
+    {
+      "epoch": 0.24877066454362384,
+      "grad_norm": 0.5439050793647766,
+      "learning_rate": 0.0002937517883510106,
+      "loss": 0.2547,
+      "step": 83
+    },
+    {
+      "epoch": 0.25176790146583616,
+      "grad_norm": 0.5188155770301819,
+      "learning_rate": 0.0002935534645206861,
+      "loss": 0.2402,
+      "step": 84
+    },
+    {
+      "epoch": 0.25476513838804854,
+      "grad_norm": 1.3832889795303345,
+      "learning_rate": 0.00029335211912030247,
+      "loss": 0.147,
+      "step": 85
+    },
+    {
+      "epoch": 0.25776237531026086,
+      "grad_norm": 0.20522421598434448,
+      "learning_rate": 0.0002931477568823596,
+      "loss": 0.0365,
+      "step": 86
+    },
+    {
+      "epoch": 0.2607596122324732,
+      "grad_norm": 0.07317493855953217,
+      "learning_rate": 0.00029294038261026595,
+      "loss": 0.0178,
+      "step": 87
+    },
+    {
+      "epoch": 0.2637568491546855,
+      "grad_norm": 5.754029273986816,
+      "learning_rate": 0.0002927300011782263,
+      "loss": 0.5049,
+      "step": 88
+    },
+    {
+      "epoch": 0.2667540860768979,
+      "grad_norm": 1.9069617986679077,
+      "learning_rate": 0.0002925166175311266,
+      "loss": 0.297,
+      "step": 89
+    },
+    {
+      "epoch": 0.2697513229991102,
+      "grad_norm": 1.4803589582443237,
+      "learning_rate": 0.0002923002366844182,
+      "loss": 0.2419,
+      "step": 90
+    },
+    {
+      "epoch": 0.2727485599213225,
+      "grad_norm": 1.1726033687591553,
+      "learning_rate": 0.0002920808637239998,
+      "loss": 0.2449,
+      "step": 91
+    },
+    {
+      "epoch": 0.27574579684353484,
+      "grad_norm": 1.1483900547027588,
+      "learning_rate": 0.00029185850380609757,
+      "loss": 0.2845,
+      "step": 92
+    },
+    {
+      "epoch": 0.2787430337657472,
+      "grad_norm": 0.6498438715934753,
+      "learning_rate": 0.00029163316215714477,
+      "loss": 0.3168,
+      "step": 93
+    },
+    {
+      "epoch": 0.28174027068795954,
+      "grad_norm": 3.8744821548461914,
+      "learning_rate": 0.00029140484407365807,
+      "loss": 0.3098,
+      "step": 94
+    },
+    {
+      "epoch": 0.28473750761017186,
+      "grad_norm": 5.238924026489258,
+      "learning_rate": 0.00029117355492211345,
+      "loss": 0.3747,
+      "step": 95
+    },
+    {
+      "epoch": 0.28773474453238423,
+      "grad_norm": 4.835148334503174,
+      "learning_rate": 0.0002909393001388201,
+      "loss": 0.311,
+      "step": 96
+    },
+    {
+      "epoch": 0.29073198145459656,
+      "grad_norm": 3.1126749515533447,
+      "learning_rate": 0.00029070208522979246,
+      "loss": 0.1933,
+      "step": 97
+    },
+    {
+      "epoch": 0.2937292183768089,
+      "grad_norm": 0.31741341948509216,
+      "learning_rate": 0.000290461915770621,
+      "loss": 0.0311,
+      "step": 98
+    },
+    {
+      "epoch": 0.2967264552990212,
+      "grad_norm": 0.13816803693771362,
+      "learning_rate": 0.00029021879740634106,
+      "loss": 0.0489,
+      "step": 99
+    },
+    {
+      "epoch": 0.2997236922212336,
+      "grad_norm": 0.16050726175308228,
+      "learning_rate": 0.0002899727358513002,
+      "loss": 0.0421,
+      "step": 100
+    },
+    {
+      "epoch": 0.2997236922212336,
+      "eval_loss": 0.14205443859100342,
+      "eval_runtime": 0.2881,
+      "eval_samples_per_second": 173.58,
+      "eval_steps_per_second": 45.131,
+      "step": 100
+    },
+    {
+      "epoch": 0.3027209291434459,
+      "grad_norm": 4.475709438323975,
+      "learning_rate": 0.0002897237368890237,
+      "loss": 0.7248,
+      "step": 101
+    },
+    {
+      "epoch": 0.3057181660656582,
+      "grad_norm": 1.3565483093261719,
+      "learning_rate": 0.00028947180637207894,
+      "loss": 0.2832,
+      "step": 102
+    },
+    {
+      "epoch": 0.30871540298787054,
+      "grad_norm": 1.5489473342895508,
+      "learning_rate": 0.0002892169502219377,
+      "loss": 0.3576,
+      "step": 103
+    },
+    {
+      "epoch": 0.3117126399100829,
+      "grad_norm": 1.2731544971466064,
+      "learning_rate": 0.00028895917442883697,
+      "loss": 0.2847,
+      "step": 104
+    },
+    {
+      "epoch": 0.31470987683229523,
+      "grad_norm": 0.5488539934158325,
+      "learning_rate": 0.000288698485051638,
+      "loss": 0.2249,
+      "step": 105
+    },
+    {
+      "epoch": 0.31770711375450755,
+      "grad_norm": 0.6603264808654785,
+      "learning_rate": 0.0002884348882176842,
+      "loss": 0.2748,
+      "step": 106
+    },
+    {
+      "epoch": 0.3207043506767199,
+      "grad_norm": 1.190644383430481,
+      "learning_rate": 0.0002881683901226569,
+      "loss": 0.264,
+      "step": 107
+    },
+    {
+      "epoch": 0.32370158759893225,
+      "grad_norm": 3.849586248397827,
+      "learning_rate": 0.00028789899703042976,
+      "loss": 0.2899,
+      "step": 108
+    },
+    {
+      "epoch": 0.32669882452114457,
+      "grad_norm": 2.8036534786224365,
+      "learning_rate": 0.00028762671527292165,
+      "loss": 0.2266,
+      "step": 109
+    },
+    {
+      "epoch": 0.3296960614433569,
+      "grad_norm": 1.1855659484863281,
+      "learning_rate": 0.00028735155124994774,
+      "loss": 0.1432,
+      "step": 110
+    },
+    {
+      "epoch": 0.33269329836556927,
+      "grad_norm": 0.14694784581661224,
+      "learning_rate": 0.0002870735114290689,
+      "loss": 0.0225,
+      "step": 111
+    },
+    {
+      "epoch": 0.3356905352877816,
+      "grad_norm": 0.08722022920846939,
+      "learning_rate": 0.0002867926023454401,
+      "loss": 0.0243,
+      "step": 112
+    },
+    {
+      "epoch": 0.3386877722099939,
+      "grad_norm": 1.4064624309539795,
+      "learning_rate": 0.00028650883060165634,
+      "loss": 0.4202,
+      "step": 113
+    },
+    {
+      "epoch": 0.34168500913220623,
+      "grad_norm": 1.0942851305007935,
+      "learning_rate": 0.00028622220286759787,
+      "loss": 0.2193,
+      "step": 114
+    },
+    {
+      "epoch": 0.3446822460544186,
+      "grad_norm": 1.4071762561798096,
+      "learning_rate": 0.0002859327258802732,
+      "loss": 0.2772,
+      "step": 115
+    },
+    {
+      "epoch": 0.3476794829766309,
+      "grad_norm": 1.451495885848999,
+      "learning_rate": 0.0002856404064436606,
+      "loss": 0.3247,
+      "step": 116
+    },
+    {
+      "epoch": 0.35067671989884325,
+      "grad_norm": 0.8838515281677246,
+      "learning_rate": 0.0002853452514285487,
+      "loss": 0.2307,
+      "step": 117
+    },
+    {
+      "epoch": 0.35367395682105557,
+      "grad_norm": 0.43812039494514465,
+      "learning_rate": 0.0002850472677723743,
+      "loss": 0.2225,
+      "step": 118
+    },
+    {
+      "epoch": 0.35667119374326794,
+      "grad_norm": 1.919777274131775,
+      "learning_rate": 0.0002847464624790599,
+      "loss": 0.2529,
+      "step": 119
+    },
+    {
+      "epoch": 0.35966843066548027,
+      "grad_norm": 3.364579916000366,
+      "learning_rate": 0.00028444284261884876,
+      "loss": 0.2957,
+      "step": 120
+    },
+    {
+      "epoch": 0.3626656675876926,
+      "grad_norm": 3.1780946254730225,
+      "learning_rate": 0.0002841364153281389,
+      "loss": 0.2983,
+      "step": 121
+    },
+    {
+      "epoch": 0.3656629045099049,
+      "grad_norm": 1.9313762187957764,
+      "learning_rate": 0.000283827187809315,
+      "loss": 0.1741,
+      "step": 122
+    },
+    {
+      "epoch": 0.3686601414321173,
+      "grad_norm": 0.2901758849620819,
+      "learning_rate": 0.0002835151673305797,
+      "loss": 0.0191,
+      "step": 123
+    },
+    {
+      "epoch": 0.3716573783543296,
+      "grad_norm": 0.18410703539848328,
+      "learning_rate": 0.00028320036122578225,
+      "loss": 0.0579,
+      "step": 124
+    },
+    {
+      "epoch": 0.3746546152765419,
+      "grad_norm": 0.06442587822675705,
+      "learning_rate": 0.0002828827768942464,
+      "loss": 0.0401,
+      "step": 125
+    },
+    {
+      "epoch": 0.3746546152765419,
+      "eval_loss": 0.12974713742733002,
+      "eval_runtime": 0.2912,
+      "eval_samples_per_second": 171.727,
+      "eval_steps_per_second": 44.649,
+      "step": 125
+    },
+    {
+      "epoch": 0.3776518521987543,
+      "grad_norm": 5.953274726867676,
+      "learning_rate": 0.00028256242180059644,
+      "loss": 0.5857,
+      "step": 126
+    },
+    {
+      "epoch": 0.3806490891209666,
+      "grad_norm": 1.0578787326812744,
+      "learning_rate": 0.0002822393034745815,
+      "loss": 0.1907,
+      "step": 127
+    },
+    {
+      "epoch": 0.38364632604317894,
+      "grad_norm": 1.2669620513916016,
+      "learning_rate": 0.0002819134295108992,
+      "loss": 0.2632,
+      "step": 128
+    },
+    {
+      "epoch": 0.38664356296539126,
+      "grad_norm": 1.2083393335342407,
+      "learning_rate": 0.0002815848075690163,
+      "loss": 0.2581,
+      "step": 129
+    },
+    {
+      "epoch": 0.38964079988760364,
+      "grad_norm": 0.6875675916671753,
+      "learning_rate": 0.00028125344537298933,
+      "loss": 0.2141,
+      "step": 130
+    },
+    {
+      "epoch": 0.39263803680981596,
+      "grad_norm": 0.6001489162445068,
+      "learning_rate": 0.00028091935071128274,
+      "loss": 0.2624,
+      "step": 131
+    },
+    {
+      "epoch": 0.3956352737320283,
+      "grad_norm": 0.28877830505371094,
+      "learning_rate": 0.00028058253143658596,
+      "loss": 0.2115,
+      "step": 132
+    },
+    {
+      "epoch": 0.3986325106542406,
+      "grad_norm": 0.8344032168388367,
+      "learning_rate": 0.0002802429954656287,
+      "loss": 0.234,
+      "step": 133
+    },
+    {
+      "epoch": 0.401629747576453,
+      "grad_norm": 2.311697244644165,
+      "learning_rate": 0.00027990075077899494,
+      "loss": 0.173,
+      "step": 134
+    },
+    {
+      "epoch": 0.4046269844986653,
+      "grad_norm": 0.9839431643486023,
+      "learning_rate": 0.0002795558054209354,
+      "loss": 0.0744,
+      "step": 135
+    },
+    {
+      "epoch": 0.4076242214208776,
+      "grad_norm": 0.23247428238391876,
+      "learning_rate": 0.0002792081674991785,
+      "loss": 0.0324,
+      "step": 136
+    },
+    {
+      "epoch": 0.41062145834308994,
+      "grad_norm": 0.11418312788009644,
+      "learning_rate": 0.00027885784518473955,
+      "loss": 0.0338,
+      "step": 137
+    },
+    {
+      "epoch": 0.4136186952653023,
+      "grad_norm": 2.2888922691345215,
+      "learning_rate": 0.0002785048467117289,
+      "loss": 0.3951,
+      "step": 138
+    },
+    {
+      "epoch": 0.41661593218751464,
+      "grad_norm": 1.3474727869033813,
+      "learning_rate": 0.00027814918037715846,
+      "loss": 0.2827,
+      "step": 139
+    },
+    {
+      "epoch": 0.41961316910972696,
+      "grad_norm": 0.958093523979187,
+      "learning_rate": 0.0002777908545407464,
+      "loss": 0.2105,
+      "step": 140
+    },
+    {
+      "epoch": 0.4226104060319393,
+      "grad_norm": 1.1106938123703003,
+      "learning_rate": 0.00027742987762472104,
+      "loss": 0.2451,
+      "step": 141
+    },
+    {
+      "epoch": 0.42560764295415165,
+      "grad_norm": 0.991568386554718,
+      "learning_rate": 0.0002770662581136226,
+      "loss": 0.2107,
+      "step": 142
+    },
+    {
+      "epoch": 0.428604879876364,
+      "grad_norm": 0.7932851314544678,
+      "learning_rate": 0.0002767000045541039,
+      "loss": 0.2097,
+      "step": 143
+    },
+    {
+      "epoch": 0.4316021167985763,
+      "grad_norm": 0.4382745623588562,
+      "learning_rate": 0.0002763311255547294,
+      "loss": 0.2098,
+      "step": 144
+    },
+    {
+      "epoch": 0.4345993537207887,
+      "grad_norm": 0.4467020034790039,
+      "learning_rate": 0.0002759596297857729,
+      "loss": 0.2249,
+      "step": 145
+    },
+    {
+      "epoch": 0.437596590643001,
+      "grad_norm": 0.7452898025512695,
+      "learning_rate": 0.0002755855259790139,
+      "loss": 0.2022,
+      "step": 146
+    },
+    {
+      "epoch": 0.4405938275652133,
+      "grad_norm": 0.8051543831825256,
+      "learning_rate": 0.000275208822927532,
+      "loss": 0.2018,
+      "step": 147
+    },
+    {
+      "epoch": 0.44359106448742563,
+      "grad_norm": 0.4602643847465515,
+      "learning_rate": 0.00027482952948550056,
+      "loss": 0.0265,
+      "step": 148
+    },
+    {
+      "epoch": 0.446588301409638,
+      "grad_norm": 0.16789375245571136,
+      "learning_rate": 0.00027444765456797863,
+      "loss": 0.0358,
+      "step": 149
+    },
+    {
+      "epoch": 0.44958553833185033,
+      "grad_norm": 0.2375824749469757,
+      "learning_rate": 0.000274063207150701,
+      "loss": 0.0459,
+      "step": 150
+    },
+    {
+      "epoch": 0.44958553833185033,
+      "eval_loss": 0.26043474674224854,
+      "eval_runtime": 0.2878,
+      "eval_samples_per_second": 173.721,
+      "eval_steps_per_second": 45.167,
+      "step": 150
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 668,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 50,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 1,
+        "early_stopping_threshold": 0.0
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 1
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 6.90057513051095e+16,
+  "train_batch_size": 1,
+  "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:cf86ea560d2053a5b479f98b88d008830c6e22c0c722396b6e3ab6eff3733725
+size 6840

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "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": false,
+    "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 +1,43 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "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": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf86ea560d2053a5b479f98b88d008830c6e22c0c722396b6e3ab6eff3733725
+size 6840