Upload TinyLlama chess eval model

README.md

@@ -0,0 +1,96 @@
+---
+library_name: peft
+license: apache-2.0
+base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
+tags:
+- generated_from_trainer
+datasets:
+- dsaunders23/ChessAlpacaPrediction
+model-index:
+- name: outputs/mymodel
+  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: `0.8.0.dev0`
+```yaml
+base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
+datasets:
+  - path: dsaunders23/ChessAlpacaPrediction
+    type: alpaca
+output_dir: ./outputs/mymodel
+
+sequence_len: 4096
+adapter: lora
+
+lora_r: 8
+lora_alpha: 16
+lora_dropout: 0.05
+lora_target_modules:
+  - q_proj
+  - v_proj
+  - k_proj
+  - o_proj
+  - gate_proj
+  - down_proj
+  - up_proj
+
+gradient_accumulation_steps: 1
+micro_batch_size: 16
+num_epochs: 1
+optimizer: adamw_bnb_8bit
+learning_rate: 0.0002
+load_in_8bit: true
+train_on_inputs: false
+bf16: auto
+
+```
+
+</details><br>
+
+# outputs/mymodel
+
+This model is a fine-tuned version of [TinyLlama/TinyLlama-1.1B-Chat-v1.0](https://huggingface.co/TinyLlama/TinyLlama-1.1B-Chat-v1.0) on the dsaunders23/ChessAlpacaPrediction dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 0.0002
+- train_batch_size: 16
+- eval_batch_size: 16
+- seed: 42
+- optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 3
+- num_epochs: 1.0
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.14.0
+- Transformers 4.49.0
+- Pytorch 2.5.1+cu124
+- Datasets 3.2.0
+- Tokenizers 0.21.0

adapter_config.json

@@ -0,0 +1,37 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "TinyLlama/TinyLlama-1.1B-Chat-v1.0",
+  "bias": "none",
+  "eva_config": null,
+  "exclude_modules": null,
+  "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": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "v_proj",
+    "o_proj",
+    "q_proj",
+    "gate_proj",
+    "down_proj",
+    "k_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:834aa01d3a27c481518b8eb0670306ea14dd35884712f4af347d7e8713cbc7d1
+size 25271744

checkpoint-242/README.md

@@ -0,0 +1,202 @@
+---
+base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
+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 0.14.0

checkpoint-242/adapter_config.json

@@ -0,0 +1,37 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "TinyLlama/TinyLlama-1.1B-Chat-v1.0",
+  "bias": "none",
+  "eva_config": null,
+  "exclude_modules": null,
+  "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": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "down_proj",
+    "v_proj",
+    "k_proj",
+    "o_proj",
+    "up_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-242/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8988b279ceed041b49d6696eb4849dc7764ae0a1783dbaa8f2b3ae72e771fd0
+size 25271744

checkpoint-242/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cda84e7dc66fd006a7e5db700db9fac64d1e038d9a076b5502b2a82389377c7c
+size 13685516

checkpoint-242/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd919faa08944c698a3f9ac10339b1cd07038ae87ff6b3366876c1204571e079
+size 14244

checkpoint-242/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26e0e13ba36eccb93aa31dc1658c17534123aefc1a1837dbb8255129bf68b872
+size 1064

checkpoint-242/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
+  }
+}

checkpoint-242/tokenizer.model

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

checkpoint-242/tokenizer_config.json

@@ -0,0 +1,44 @@
+{
+  "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": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n'  + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "legacy": false,
+  "model_max_length": 2048,
+  "pad_token": "</s>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

checkpoint-242/trainer_state.json

@@ -0,0 +1,880 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 242,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01652892561983471,
+      "grad_norm": 12.011792182922363,
+      "learning_rate": 2.857142857142857e-05,
+      "loss": 4.7518,
+      "step": 2
+    },
+    {
+      "epoch": 0.03305785123966942,
+      "grad_norm": 12.689871788024902,
+      "learning_rate": 5.714285714285714e-05,
+      "loss": 4.687,
+      "step": 4
+    },
+    {
+      "epoch": 0.049586776859504134,
+      "grad_norm": 11.848198890686035,
+      "learning_rate": 8.571428571428571e-05,
+      "loss": 4.4922,
+      "step": 6
+    },
+    {
+      "epoch": 0.06611570247933884,
+      "grad_norm": 10.378408432006836,
+      "learning_rate": 0.00011428571428571428,
+      "loss": 3.4839,
+      "step": 8
+    },
+    {
+      "epoch": 0.08264462809917356,
+      "grad_norm": 9.543920516967773,
+      "learning_rate": 0.00014285714285714287,
+      "loss": 2.4164,
+      "step": 10
+    },
+    {
+      "epoch": 0.09917355371900827,
+      "grad_norm": 5.602456092834473,
+      "learning_rate": 0.00017142857142857143,
+      "loss": 1.838,
+      "step": 12
+    },
+    {
+      "epoch": 0.11570247933884298,
+      "grad_norm": 1.7414193153381348,
+      "learning_rate": 0.0002,
+      "loss": 1.4404,
+      "step": 14
+    },
+    {
+      "epoch": 0.1322314049586777,
+      "grad_norm": 1.0191770792007446,
+      "learning_rate": 0.0001999910643210378,
+      "loss": 1.3474,
+      "step": 16
+    },
+    {
+      "epoch": 0.1487603305785124,
+      "grad_norm": 3.509352922439575,
+      "learning_rate": 0.0001999642588810784,
+      "loss": 1.3789,
+      "step": 18
+    },
+    {
+      "epoch": 0.1652892561983471,
+      "grad_norm": 2.426680088043213,
+      "learning_rate": 0.00019991958847061784,
+      "loss": 1.2245,
+      "step": 20
+    },
+    {
+      "epoch": 0.18181818181818182,
+      "grad_norm": 0.8060101270675659,
+      "learning_rate": 0.00019985706107286514,
+      "loss": 1.2259,
+      "step": 22
+    },
+    {
+      "epoch": 0.19834710743801653,
+      "grad_norm": 1.6215940713882446,
+      "learning_rate": 0.00019977668786231534,
+      "loss": 1.1992,
+      "step": 24
+    },
+    {
+      "epoch": 0.21487603305785125,
+      "grad_norm": 2.476259231567383,
+      "learning_rate": 0.0001996784832027525,
+      "loss": 1.2782,
+      "step": 26
+    },
+    {
+      "epoch": 0.23140495867768596,
+      "grad_norm": 2.04018235206604,
+      "learning_rate": 0.00019956246464468294,
+      "loss": 1.23,
+      "step": 28
+    },
+    {
+      "epoch": 0.24793388429752067,
+      "grad_norm": 1.8799017667770386,
+      "learning_rate": 0.00019942865292219838,
+      "loss": 1.2164,
+      "step": 30
+    },
+    {
+      "epoch": 0.2644628099173554,
+      "grad_norm": 1.2413148880004883,
+      "learning_rate": 0.00019927707194927066,
+      "loss": 1.2924,
+      "step": 32
+    },
+    {
+      "epoch": 0.2809917355371901,
+      "grad_norm": 1.8723937273025513,
+      "learning_rate": 0.000199107748815478,
+      "loss": 1.2302,
+      "step": 34
+    },
+    {
+      "epoch": 0.2975206611570248,
+      "grad_norm": 1.393110752105713,
+      "learning_rate": 0.00019892071378116376,
+      "loss": 1.2276,
+      "step": 36
+    },
+    {
+      "epoch": 0.3140495867768595,
+      "grad_norm": 1.1459721326828003,
+      "learning_rate": 0.0001987160002720283,
+      "loss": 1.1504,
+      "step": 38
+    },
+    {
+      "epoch": 0.3305785123966942,
+      "grad_norm": 1.4680942296981812,
+      "learning_rate": 0.00019849364487315558,
+      "loss": 1.1623,
+      "step": 40
+    },
+    {
+      "epoch": 0.34710743801652894,
+      "grad_norm": 1.8715866804122925,
+      "learning_rate": 0.0001982536873224748,
+      "loss": 1.2155,
+      "step": 42
+    },
+    {
+      "epoch": 0.36363636363636365,
+      "grad_norm": 0.871064305305481,
+      "learning_rate": 0.0001979961705036587,
+      "loss": 1.1594,
+      "step": 44
+    },
+    {
+      "epoch": 0.38016528925619836,
+      "grad_norm": 0.8239800930023193,
+      "learning_rate": 0.00019772114043845965,
+      "loss": 1.1501,
+      "step": 46
+    },
+    {
+      "epoch": 0.39669421487603307,
+      "grad_norm": 0.9587319493293762,
+      "learning_rate": 0.0001974286462784851,
+      "loss": 1.1195,
+      "step": 48
+    },
+    {
+      "epoch": 0.4132231404958678,
+      "grad_norm": 1.1645926237106323,
+      "learning_rate": 0.0001971187402964132,
+      "loss": 1.1417,
+      "step": 50
+    },
+    {
+      "epoch": 0.4297520661157025,
+      "grad_norm": 0.576813817024231,
+      "learning_rate": 0.00019679147787665126,
+      "loss": 1.1445,
+      "step": 52
+    },
+    {
+      "epoch": 0.4462809917355372,
+      "grad_norm": 1.0733133554458618,
+      "learning_rate": 0.00019644691750543767,
+      "loss": 1.0979,
+      "step": 54
+    },
+    {
+      "epoch": 0.4628099173553719,
+      "grad_norm": 0.5801639556884766,
+      "learning_rate": 0.00019608512076038962,
+      "loss": 1.0977,
+      "step": 56
+    },
+    {
+      "epoch": 0.4793388429752066,
+      "grad_norm": 1.6796538829803467,
+      "learning_rate": 0.00019570615229949842,
+      "loss": 1.1925,
+      "step": 58
+    },
+    {
+      "epoch": 0.49586776859504134,
+      "grad_norm": 1.0563887357711792,
+      "learning_rate": 0.00019531007984957408,
+      "loss": 1.0657,
+      "step": 60
+    },
+    {
+      "epoch": 0.512396694214876,
+      "grad_norm": 0.9109811186790466,
+      "learning_rate": 0.00019489697419414182,
+      "loss": 1.1098,
+      "step": 62
+    },
+    {
+      "epoch": 0.5289256198347108,
+      "grad_norm": 0.7321667671203613,
+      "learning_rate": 0.0001944669091607919,
+      "loss": 1.0929,
+      "step": 64
+    },
+    {
+      "epoch": 0.5454545454545454,
+      "grad_norm": 0.685366690158844,
+      "learning_rate": 0.00019401996160798573,
+      "loss": 1.1242,
+      "step": 66
+    },
+    {
+      "epoch": 0.5619834710743802,
+      "grad_norm": 0.8959838151931763,
+      "learning_rate": 0.0001935562114113202,
+      "loss": 1.181,
+      "step": 68
+    },
+    {
+      "epoch": 0.5785123966942148,
+      "grad_norm": 0.9717262983322144,
+      "learning_rate": 0.00019307574144925287,
+      "loss": 1.2295,
+      "step": 70
+    },
+    {
+      "epoch": 0.5950413223140496,
+      "grad_norm": 1.0358582735061646,
+      "learning_rate": 0.00019257863758829035,
+      "loss": 1.1431,
+      "step": 72
+    },
+    {
+      "epoch": 0.6115702479338843,
+      "grad_norm": 0.7998526096343994,
+      "learning_rate": 0.00019206498866764288,
+      "loss": 1.1032,
+      "step": 74
+    },
+    {
+      "epoch": 0.628099173553719,
+      "grad_norm": 1.1496188640594482,
+      "learning_rate": 0.0001915348864833476,
+      "loss": 1.057,
+      "step": 76
+    },
+    {
+      "epoch": 0.6446280991735537,
+      "grad_norm": 0.652406632900238,
+      "learning_rate": 0.00019098842577186314,
+      "loss": 1.146,
+      "step": 78
+    },
+    {
+      "epoch": 0.6611570247933884,
+      "grad_norm": 0.9454944729804993,
+      "learning_rate": 0.00019042570419313925,
+      "loss": 1.1543,
+      "step": 80
+    },
+    {
+      "epoch": 0.6776859504132231,
+      "grad_norm": 0.7456652522087097,
+      "learning_rate": 0.00018984682231316333,
+      "loss": 1.1189,
+      "step": 82
+    },
+    {
+      "epoch": 0.6942148760330579,
+      "grad_norm": 0.7312512397766113,
+      "learning_rate": 0.00018925188358598813,
+      "loss": 1.0873,
+      "step": 84
+    },
+    {
+      "epoch": 0.7107438016528925,
+      "grad_norm": 0.8474765419960022,
+      "learning_rate": 0.000188640994335243,
+      "loss": 1.1698,
+      "step": 86
+    },
+    {
+      "epoch": 0.7272727272727273,
+      "grad_norm": 0.6979633569717407,
+      "learning_rate": 0.0001880142637351325,
+      "loss": 1.1417,
+      "step": 88
+    },
+    {
+      "epoch": 0.743801652892562,
+      "grad_norm": 0.5989161133766174,
+      "learning_rate": 0.00018737180379092537,
+      "loss": 1.0479,
+      "step": 90
+    },
+    {
+      "epoch": 0.7603305785123967,
+      "grad_norm": 0.5765272378921509,
+      "learning_rate": 0.00018671372931893773,
+      "loss": 1.1336,
+      "step": 92
+    },
+    {
+      "epoch": 0.7768595041322314,
+      "grad_norm": 0.6709849834442139,
+      "learning_rate": 0.00018604015792601396,
+      "loss": 1.1157,
+      "step": 94
+    },
+    {
+      "epoch": 0.7933884297520661,
+      "grad_norm": 0.8181343674659729,
+      "learning_rate": 0.00018535120998850848,
+      "loss": 1.0927,
+      "step": 96
+    },
+    {
+      "epoch": 0.8099173553719008,
+      "grad_norm": 0.6146332621574402,
+      "learning_rate": 0.00018464700863077312,
+      "loss": 1.0739,
+      "step": 98
+    },
+    {
+      "epoch": 0.8264462809917356,
+      "grad_norm": 0.9904415011405945,
+      "learning_rate": 0.00018392767970315313,
+      "loss": 1.0331,
+      "step": 100
+    },
+    {
+      "epoch": 0.8429752066115702,
+      "grad_norm": 0.6186695694923401,
+      "learning_rate": 0.0001831933517594957,
+      "loss": 1.0513,
+      "step": 102
+    },
+    {
+      "epoch": 0.859504132231405,
+      "grad_norm": 1.1912785768508911,
+      "learning_rate": 0.00018244415603417603,
+      "loss": 1.1567,
+      "step": 104
+    },
+    {
+      "epoch": 0.8760330578512396,
+      "grad_norm": 1.3681318759918213,
+      "learning_rate": 0.00018168022641864377,
+      "loss": 1.1497,
+      "step": 106
+    },
+    {
+      "epoch": 0.8925619834710744,
+      "grad_norm": 0.619476318359375,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 1.1546,
+      "step": 108
+    },
+    {
+      "epoch": 0.9090909090909091,
+      "grad_norm": 0.7421219348907471,
+      "learning_rate": 0.00018010871422407236,
+      "loss": 1.1458,
+      "step": 110
+    },
+    {
+      "epoch": 0.9256198347107438,
+      "grad_norm": 0.6569286584854126,
+      "learning_rate": 0.00017930141249560233,
+      "loss": 1.12,
+      "step": 112
+    },
+    {
+      "epoch": 0.9421487603305785,
+      "grad_norm": 0.4168110191822052,
+      "learning_rate": 0.0001784799385278661,
+      "loss": 1.1682,
+      "step": 114
+    },
+    {
+      "epoch": 0.9586776859504132,
+      "grad_norm": 0.5620162487030029,
+      "learning_rate": 0.00017764443912941672,
+      "loss": 1.1828,
+      "step": 116
+    },
+    {
+      "epoch": 0.9752066115702479,
+      "grad_norm": 0.8095484375953674,
+      "learning_rate": 0.00017679506361534215,
+      "loss": 1.1953,
+      "step": 118
+    },
+    {
+      "epoch": 0.9917355371900827,
+      "grad_norm": 0.7646257281303406,
+      "learning_rate": 0.0001759319637805806,
+      "loss": 1.2148,
+      "step": 120
+    },
+    {
+      "epoch": 1.0082644628099173,
+      "grad_norm": 0.5254501104354858,
+      "learning_rate": 0.00017505529387279277,
+      "loss": 1.1359,
+      "step": 122
+    },
+    {
+      "epoch": 1.024793388429752,
+      "grad_norm": 0.6001765727996826,
+      "learning_rate": 0.00017416521056479577,
+      "loss": 1.1336,
+      "step": 124
+    },
+    {
+      "epoch": 1.0413223140495869,
+      "grad_norm": 0.35407504439353943,
+      "learning_rate": 0.00017326187292656333,
+      "loss": 1.1833,
+      "step": 126
+    },
+    {
+      "epoch": 1.0578512396694215,
+      "grad_norm": 0.414528489112854,
+      "learning_rate": 0.00017234544239679806,
+      "loss": 1.1301,
+      "step": 128
+    },
+    {
+      "epoch": 1.0743801652892562,
+      "grad_norm": 0.46355852484703064,
+      "learning_rate": 0.00017141608275408006,
+      "loss": 1.213,
+      "step": 130
+    },
+    {
+      "epoch": 1.0909090909090908,
+      "grad_norm": 0.5040593147277832,
+      "learning_rate": 0.00017047396008759754,
+      "loss": 1.132,
+      "step": 132
+    },
+    {
+      "epoch": 1.1074380165289257,
+      "grad_norm": 0.4813704192638397,
+      "learning_rate": 0.00016951924276746425,
+      "loss": 1.0831,
+      "step": 134
+    },
+    {
+      "epoch": 1.1239669421487604,
+      "grad_norm": 0.5174686312675476,
+      "learning_rate": 0.00016855210141462963,
+      "loss": 1.0514,
+      "step": 136
+    },
+    {
+      "epoch": 1.140495867768595,
+      "grad_norm": 0.4712466299533844,
+      "learning_rate": 0.00016757270887038654,
+      "loss": 1.1334,
+      "step": 138
+    },
+    {
+      "epoch": 1.1570247933884297,
+      "grad_norm": 0.5912173390388489,
+      "learning_rate": 0.00016658124016548197,
+      "loss": 1.1011,
+      "step": 140
+    },
+    {
+      "epoch": 1.1735537190082646,
+      "grad_norm": 0.6392802000045776,
+      "learning_rate": 0.00016557787248883696,
+      "loss": 1.1361,
+      "step": 142
+    },
+    {
+      "epoch": 1.1900826446280992,
+      "grad_norm": 0.7376368045806885,
+      "learning_rate": 0.00016456278515588024,
+      "loss": 1.109,
+      "step": 144
+    },
+    {
+      "epoch": 1.2066115702479339,
+      "grad_norm": 0.5020875930786133,
+      "learning_rate": 0.00016353615957650236,
+      "loss": 1.0925,
+      "step": 146
+    },
+    {
+      "epoch": 1.2231404958677685,
+      "grad_norm": 0.8081740736961365,
+      "learning_rate": 0.00016249817922263517,
+      "loss": 1.047,
+      "step": 148
+    },
+    {
+      "epoch": 1.2396694214876034,
+      "grad_norm": 0.6371219754219055,
+      "learning_rate": 0.00016144902959546286,
+      "loss": 1.113,
+      "step": 150
+    },
+    {
+      "epoch": 1.256198347107438,
+      "grad_norm": 0.7588189840316772,
+      "learning_rate": 0.00016038889819227045,
+      "loss": 1.1179,
+      "step": 152
+    },
+    {
+      "epoch": 1.2727272727272727,
+      "grad_norm": 0.6286205053329468,
+      "learning_rate": 0.00015931797447293552,
+      "loss": 1.1209,
+      "step": 154
+    },
+    {
+      "epoch": 1.2892561983471074,
+      "grad_norm": 0.797656238079071,
+      "learning_rate": 0.00015823644982606905,
+      "loss": 1.1698,
+      "step": 156
+    },
+    {
+      "epoch": 1.3057851239669422,
+      "grad_norm": 0.5368632078170776,
+      "learning_rate": 0.00015714451753481168,
+      "loss": 1.1973,
+      "step": 158
+    },
+    {
+      "epoch": 1.322314049586777,
+      "grad_norm": 0.4135212302207947,
+      "learning_rate": 0.00015604237274229147,
+      "loss": 1.1452,
+      "step": 160
+    },
+    {
+      "epoch": 1.3388429752066116,
+      "grad_norm": 0.5289668440818787,
+      "learning_rate": 0.00015493021241674918,
+      "loss": 1.1954,
+      "step": 162
+    },
+    {
+      "epoch": 1.3553719008264462,
+      "grad_norm": 0.4092061221599579,
+      "learning_rate": 0.00015380823531633729,
+      "loss": 1.1226,
+      "step": 164
+    },
+    {
+      "epoch": 1.3719008264462809,
+      "grad_norm": 0.7049645781517029,
+      "learning_rate": 0.00015267664195359917,
+      "loss": 1.0948,
+      "step": 166
+    },
+    {
+      "epoch": 1.3884297520661157,
+      "grad_norm": 0.47164198756217957,
+      "learning_rate": 0.00015153563455963499,
+      "loss": 1.0977,
+      "step": 168
+    },
+    {
+      "epoch": 1.4049586776859504,
+      "grad_norm": 0.7871695160865784,
+      "learning_rate": 0.00015038541704796003,
+      "loss": 1.1674,
+      "step": 170
+    },
+    {
+      "epoch": 1.421487603305785,
+      "grad_norm": 0.5381121635437012,
+      "learning_rate": 0.00014922619497806277,
+      "loss": 1.1415,
+      "step": 172
+    },
+    {
+      "epoch": 1.43801652892562,
+      "grad_norm": 0.39419299364089966,
+      "learning_rate": 0.00014805817551866838,
+      "loss": 1.0747,
+      "step": 174
+    },
+    {
+      "epoch": 1.4545454545454546,
+      "grad_norm": 0.38382914662361145,
+      "learning_rate": 0.00014688156741071514,
+      "loss": 1.1278,
+      "step": 176
+    },
+    {
+      "epoch": 1.4710743801652892,
+      "grad_norm": 0.32674962282180786,
+      "learning_rate": 0.00014569658093004935,
+      "loss": 0.9774,
+      "step": 178
+    },
+    {
+      "epoch": 1.487603305785124,
+      "grad_norm": 0.5443088412284851,
+      "learning_rate": 0.00014450342784984633,
+      "loss": 1.034,
+      "step": 180
+    },
+    {
+      "epoch": 1.5041322314049586,
+      "grad_norm": 0.6682401895523071,
+      "learning_rate": 0.00014330232140276366,
+      "loss": 1.1732,
+      "step": 182
+    },
+    {
+      "epoch": 1.5206611570247934,
+      "grad_norm": 0.5696044564247131,
+      "learning_rate": 0.0001420934762428335,
+      "loss": 1.0384,
+      "step": 184
+    },
+    {
+      "epoch": 1.537190082644628,
+      "grad_norm": 0.6782551407814026,
+      "learning_rate": 0.0001408771084071012,
+      "loss": 1.1107,
+      "step": 186
+    },
+    {
+      "epoch": 1.553719008264463,
+      "grad_norm": 0.8336123824119568,
+      "learning_rate": 0.00013965343527701628,
+      "loss": 1.0737,
+      "step": 188
+    },
+    {
+      "epoch": 1.5702479338842976,
+      "grad_norm": 0.539226233959198,
+      "learning_rate": 0.00013842267553958371,
+      "loss": 1.1665,
+      "step": 190
+    },
+    {
+      "epoch": 1.5867768595041323,
+      "grad_norm": 0.566620409488678,
+      "learning_rate": 0.00013718504914828135,
+      "loss": 1.1333,
+      "step": 192
+    },
+    {
+      "epoch": 1.603305785123967,
+      "grad_norm": 0.4735005795955658,
+      "learning_rate": 0.00013594077728375128,
+      "loss": 1.1709,
+      "step": 194
+    },
+    {
+      "epoch": 1.6198347107438016,
+      "grad_norm": 0.534383237361908,
+      "learning_rate": 0.00013469008231427207,
+      "loss": 1.0783,
+      "step": 196
+    },
+    {
+      "epoch": 1.6363636363636362,
+      "grad_norm": 0.8410363793373108,
+      "learning_rate": 0.0001334331877560182,
+      "loss": 1.0708,
+      "step": 198
+    },
+    {
+      "epoch": 1.6528925619834711,
+      "grad_norm": 0.6392219662666321,
+      "learning_rate": 0.00013217031823311488,
+      "loss": 1.0329,
+      "step": 200
+    },
+    {
+      "epoch": 1.6694214876033058,
+      "grad_norm": 0.5770404934883118,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 1.0404,
+      "step": 202
+    },
+    {
+      "epoch": 1.6859504132231407,
+      "grad_norm": 0.6814575791358948,
+      "learning_rate": 0.00012962755808856342,
+      "loss": 1.0702,
+      "step": 204
+    },
+    {
+      "epoch": 1.7024793388429753,
+      "grad_norm": 0.673312783241272,
+      "learning_rate": 0.0001283481218926818,
+      "loss": 1.0529,
+      "step": 206
+    },
+    {
+      "epoch": 1.71900826446281,
+      "grad_norm": 0.6180073618888855,
+      "learning_rate": 0.0001270636195024719,
+      "loss": 1.0257,
+      "step": 208
+    },
+    {
+      "epoch": 1.7355371900826446,
+      "grad_norm": 0.5565724968910217,
+      "learning_rate": 0.00012577428047595344,
+      "loss": 1.1102,
+      "step": 210
+    },
+    {
+      "epoch": 1.7520661157024793,
+      "grad_norm": 0.5586270689964294,
+      "learning_rate": 0.00012448033523551865,
+      "loss": 1.0277,
+      "step": 212
+    },
+    {
+      "epoch": 1.768595041322314,
+      "grad_norm": 0.542448878288269,
+      "learning_rate": 0.00012318201502675285,
+      "loss": 1.0988,
+      "step": 214
+    },
+    {
+      "epoch": 1.7851239669421488,
+      "grad_norm": 0.513042151927948,
+      "learning_rate": 0.0001218795518771075,
+      "loss": 1.0828,
+      "step": 216
+    },
+    {
+      "epoch": 1.8016528925619835,
+      "grad_norm": 0.7613060474395752,
+      "learning_rate": 0.00012057317855443395,
+      "loss": 1.1962,
+      "step": 218
+    },
+    {
+      "epoch": 1.8181818181818183,
+      "grad_norm": 0.7522129416465759,
+      "learning_rate": 0.00011926312852538455,
+      "loss": 1.1339,
+      "step": 220
+    },
+    {
+      "epoch": 1.834710743801653,
+      "grad_norm": 0.4655594825744629,
+      "learning_rate": 0.00011794963591368893,
+      "loss": 1.0967,
+      "step": 222
+    },
+    {
+      "epoch": 1.8512396694214877,
+      "grad_norm": 0.5036570429801941,
+      "learning_rate": 0.00011663293545831302,
+      "loss": 1.0361,
+      "step": 224
+    },
+    {
+      "epoch": 1.8677685950413223,
+      "grad_norm": 0.43016380071640015,
+      "learning_rate": 0.00011531326247150803,
+      "loss": 1.1281,
+      "step": 226
+    },
+    {
+      "epoch": 1.884297520661157,
+      "grad_norm": 0.5184316635131836,
+      "learning_rate": 0.00011399085279675687,
+      "loss": 1.2083,
+      "step": 228
+    },
+    {
+      "epoch": 1.9008264462809916,
+      "grad_norm": 0.6556355357170105,
+      "learning_rate": 0.0001126659427666257,
+      "loss": 1.0266,
+      "step": 230
+    },
+    {
+      "epoch": 1.9173553719008265,
+      "grad_norm": 0.515681803226471,
+      "learning_rate": 0.00011133876916052821,
+      "loss": 1.0472,
+      "step": 232
+    },
+    {
+      "epoch": 1.9338842975206612,
+      "grad_norm": 0.4592064321041107,
+      "learning_rate": 0.00011000956916240985,
+      "loss": 1.054,
+      "step": 234
+    },
+    {
+      "epoch": 1.950413223140496,
+      "grad_norm": 0.5623230338096619,
+      "learning_rate": 0.00010867858031835975,
+      "loss": 1.1571,
+      "step": 236
+    },
+    {
+      "epoch": 1.9669421487603307,
+      "grad_norm": 0.5241667032241821,
+      "learning_rate": 0.00010734604049415822,
+      "loss": 1.0985,
+      "step": 238
+    },
+    {
+      "epoch": 1.9834710743801653,
+      "grad_norm": 0.54905104637146,
+      "learning_rate": 0.00010601218783276672,
+      "loss": 1.1088,
+      "step": 240
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.8823345303535461,
+      "learning_rate": 0.00010467726071176853,
+      "loss": 1.0991,
+      "step": 242
+    }
+  ],
+  "logging_steps": 2,
+  "max_steps": 484,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4578676410679296.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-242/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41c7adf20314e4e98465f263bb56b062cceb30de0bf8fa4d85b668c720a84502
+size 6456

checkpoint-312/README.md

@@ -0,0 +1,202 @@
+---
+base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
+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 0.14.0

checkpoint-312/adapter_config.json

@@ -0,0 +1,37 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "TinyLlama/TinyLlama-1.1B-Chat-v1.0",
+  "bias": "none",
+  "eva_config": null,
+  "exclude_modules": null,
+  "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": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "up_proj",
+    "k_proj",
+    "gate_proj",
+    "down_proj",
+    "o_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-312/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca4f470e10d3a1cadc4968b0acb37416dd9cbb615291d7d8b989df2f74b716df
+size 25271744

checkpoint-312/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c71f3b563c3f684bb4165e33eef2c6e2a25979d1a2364e57b99556cc49549f5
+size 13685836

checkpoint-312/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0b07ad1b89c33b892be1932a91fb2298ab424a36a237cfbf9776d684f2df198
+size 14244

checkpoint-312/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07515c2b046d99c3743a994e794dd47b173671b79b64b92ecc764813da2c450b
+size 1064

checkpoint-312/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
+  }
+}

checkpoint-312/tokenizer.model

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

checkpoint-312/tokenizer_config.json

@@ -0,0 +1,44 @@
+{
+  "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": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n'  + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "legacy": false,
+  "model_max_length": 2048,
+  "pad_token": "</s>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

checkpoint-312/trainer_state.json

@@ -0,0 +1,2217 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 312,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.003205128205128205,
+      "grad_norm": 13.91187858581543,
+      "learning_rate": 2.2222222222222223e-05,
+      "loss": 4.8108,
+      "step": 1
+    },
+    {
+      "epoch": 0.00641025641025641,
+      "grad_norm": 14.33206558227539,
+      "learning_rate": 4.4444444444444447e-05,
+      "loss": 4.8801,
+      "step": 2
+    },
+    {
+      "epoch": 0.009615384615384616,
+      "grad_norm": 14.014120101928711,
+      "learning_rate": 6.666666666666667e-05,
+      "loss": 4.8164,
+      "step": 3
+    },
+    {
+      "epoch": 0.01282051282051282,
+      "grad_norm": 13.723206520080566,
+      "learning_rate": 8.888888888888889e-05,
+      "loss": 4.7503,
+      "step": 4
+    },
+    {
+      "epoch": 0.016025641025641024,
+      "grad_norm": 14.325286865234375,
+      "learning_rate": 0.00011111111111111112,
+      "loss": 4.3225,
+      "step": 5
+    },
+    {
+      "epoch": 0.019230769230769232,
+      "grad_norm": 13.791594505310059,
+      "learning_rate": 0.00013333333333333334,
+      "loss": 3.3933,
+      "step": 6
+    },
+    {
+      "epoch": 0.022435897435897436,
+      "grad_norm": 10.824278831481934,
+      "learning_rate": 0.00015555555555555556,
+      "loss": 2.8485,
+      "step": 7
+    },
+    {
+      "epoch": 0.02564102564102564,
+      "grad_norm": 9.639212608337402,
+      "learning_rate": 0.00017777777777777779,
+      "loss": 2.2245,
+      "step": 8
+    },
+    {
+      "epoch": 0.028846153846153848,
+      "grad_norm": 7.029407501220703,
+      "learning_rate": 0.0002,
+      "loss": 1.6899,
+      "step": 9
+    },
+    {
+      "epoch": 0.03205128205128205,
+      "grad_norm": 5.85064697265625,
+      "learning_rate": 0.00019999462497359466,
+      "loss": 1.4971,
+      "step": 10
+    },
+    {
+      "epoch": 0.035256410256410256,
+      "grad_norm": 3.8360719680786133,
+      "learning_rate": 0.0001999785004721968,
+      "loss": 1.159,
+      "step": 11
+    },
+    {
+      "epoch": 0.038461538461538464,
+      "grad_norm": 1.9359312057495117,
+      "learning_rate": 0.00019995162822919883,
+      "loss": 0.9306,
+      "step": 12
+    },
+    {
+      "epoch": 0.041666666666666664,
+      "grad_norm": 2.1098594665527344,
+      "learning_rate": 0.00019991401113338104,
+      "loss": 0.9273,
+      "step": 13
+    },
+    {
+      "epoch": 0.04487179487179487,
+      "grad_norm": 3.5646820068359375,
+      "learning_rate": 0.00019986565322860115,
+      "loss": 0.9156,
+      "step": 14
+    },
+    {
+      "epoch": 0.04807692307692308,
+      "grad_norm": 2.836466073989868,
+      "learning_rate": 0.00019980655971335945,
+      "loss": 0.8981,
+      "step": 15
+    },
+    {
+      "epoch": 0.05128205128205128,
+      "grad_norm": 2.151491641998291,
+      "learning_rate": 0.00019973673694024,
+      "loss": 0.8187,
+      "step": 16
+    },
+    {
+      "epoch": 0.05448717948717949,
+      "grad_norm": 2.594736337661743,
+      "learning_rate": 0.0001996561924152278,
+      "loss": 0.8162,
+      "step": 17
+    },
+    {
+      "epoch": 0.057692307692307696,
+      "grad_norm": 4.105694770812988,
+      "learning_rate": 0.0001995649347969019,
+      "loss": 0.8538,
+      "step": 18
+    },
+    {
+      "epoch": 0.060897435897435896,
+      "grad_norm": 2.181260585784912,
+      "learning_rate": 0.00019946297389550433,
+      "loss": 0.8083,
+      "step": 19
+    },
+    {
+      "epoch": 0.0641025641025641,
+      "grad_norm": 1.9404771327972412,
+      "learning_rate": 0.0001993503206718859,
+      "loss": 0.8117,
+      "step": 20
+    },
+    {
+      "epoch": 0.0673076923076923,
+      "grad_norm": 1.6177146434783936,
+      "learning_rate": 0.00019922698723632767,
+      "loss": 0.668,
+      "step": 21
+    },
+    {
+      "epoch": 0.07051282051282051,
+      "grad_norm": 2.5855164527893066,
+      "learning_rate": 0.00019909298684723904,
+      "loss": 0.9246,
+      "step": 22
+    },
+    {
+      "epoch": 0.07371794871794872,
+      "grad_norm": 0.7814646363258362,
+      "learning_rate": 0.00019894833390973266,
+      "loss": 0.7877,
+      "step": 23
+    },
+    {
+      "epoch": 0.07692307692307693,
+      "grad_norm": 1.592220664024353,
+      "learning_rate": 0.0001987930439740757,
+      "loss": 0.8776,
+      "step": 24
+    },
+    {
+      "epoch": 0.08012820512820513,
+      "grad_norm": 3.1788816452026367,
+      "learning_rate": 0.0001986271337340182,
+      "loss": 0.943,
+      "step": 25
+    },
+    {
+      "epoch": 0.08333333333333333,
+      "grad_norm": 0.8750837445259094,
+      "learning_rate": 0.0001984506210249986,
+      "loss": 0.9156,
+      "step": 26
+    },
+    {
+      "epoch": 0.08653846153846154,
+      "grad_norm": 1.8515149354934692,
+      "learning_rate": 0.00019826352482222638,
+      "loss": 0.8454,
+      "step": 27
+    },
+    {
+      "epoch": 0.08974358974358974,
+      "grad_norm": 1.592309594154358,
+      "learning_rate": 0.0001980658652386421,
+      "loss": 0.939,
+      "step": 28
+    },
+    {
+      "epoch": 0.09294871794871795,
+      "grad_norm": 1.8106122016906738,
+      "learning_rate": 0.00019785766352275542,
+      "loss": 0.9646,
+      "step": 29
+    },
+    {
+      "epoch": 0.09615384615384616,
+      "grad_norm": 1.220379114151001,
+      "learning_rate": 0.00019763894205636072,
+      "loss": 0.8782,
+      "step": 30
+    },
+    {
+      "epoch": 0.09935897435897435,
+      "grad_norm": 1.5412297248840332,
+      "learning_rate": 0.00019740972435213115,
+      "loss": 0.7935,
+      "step": 31
+    },
+    {
+      "epoch": 0.10256410256410256,
+      "grad_norm": 1.016067385673523,
+      "learning_rate": 0.00019717003505109095,
+      "loss": 0.905,
+      "step": 32
+    },
+    {
+      "epoch": 0.10576923076923077,
+      "grad_norm": 0.7788788080215454,
+      "learning_rate": 0.00019691989991996663,
+      "loss": 0.7594,
+      "step": 33
+    },
+    {
+      "epoch": 0.10897435897435898,
+      "grad_norm": 1.0361382961273193,
+      "learning_rate": 0.00019665934584841682,
+      "loss": 0.8002,
+      "step": 34
+    },
+    {
+      "epoch": 0.11217948717948718,
+      "grad_norm": 0.8088793158531189,
+      "learning_rate": 0.00019638840084614182,
+      "loss": 0.8022,
+      "step": 35
+    },
+    {
+      "epoch": 0.11538461538461539,
+      "grad_norm": 1.6871492862701416,
+      "learning_rate": 0.00019610709403987246,
+      "loss": 0.9974,
+      "step": 36
+    },
+    {
+      "epoch": 0.11858974358974358,
+      "grad_norm": 0.8181275725364685,
+      "learning_rate": 0.000195815455670239,
+      "loss": 0.8345,
+      "step": 37
+    },
+    {
+      "epoch": 0.12179487179487179,
+      "grad_norm": 1.2367571592330933,
+      "learning_rate": 0.0001955135170885202,
+      "loss": 0.9184,
+      "step": 38
+    },
+    {
+      "epoch": 0.125,
+      "grad_norm": 0.8114968538284302,
+      "learning_rate": 0.00019520131075327298,
+      "loss": 0.7724,
+      "step": 39
+    },
+    {
+      "epoch": 0.1282051282051282,
+      "grad_norm": 0.9863741993904114,
+      "learning_rate": 0.00019487887022684336,
+      "loss": 0.7895,
+      "step": 40
+    },
+    {
+      "epoch": 0.13141025641025642,
+      "grad_norm": 0.8909745216369629,
+      "learning_rate": 0.00019454623017175812,
+      "loss": 0.8602,
+      "step": 41
+    },
+    {
+      "epoch": 0.1346153846153846,
+      "grad_norm": 1.0723499059677124,
+      "learning_rate": 0.0001942034263469989,
+      "loss": 0.8249,
+      "step": 42
+    },
+    {
+      "epoch": 0.13782051282051283,
+      "grad_norm": 2.3453705310821533,
+      "learning_rate": 0.00019385049560415794,
+      "loss": 0.8398,
+      "step": 43
+    },
+    {
+      "epoch": 0.14102564102564102,
+      "grad_norm": 2.1112656593322754,
+      "learning_rate": 0.00019348747588347637,
+      "loss": 0.8648,
+      "step": 44
+    },
+    {
+      "epoch": 0.14423076923076922,
+      "grad_norm": 0.7072998285293579,
+      "learning_rate": 0.00019311440620976597,
+      "loss": 0.7766,
+      "step": 45
+    },
+    {
+      "epoch": 0.14743589743589744,
+      "grad_norm": 1.122727632522583,
+      "learning_rate": 0.00019273132668821364,
+      "loss": 0.8375,
+      "step": 46
+    },
+    {
+      "epoch": 0.15064102564102563,
+      "grad_norm": 0.43819618225097656,
+      "learning_rate": 0.00019233827850007027,
+      "loss": 0.7336,
+      "step": 47
+    },
+    {
+      "epoch": 0.15384615384615385,
+      "grad_norm": 0.6066083908081055,
+      "learning_rate": 0.00019193530389822363,
+      "loss": 0.7079,
+      "step": 48
+    },
+    {
+      "epoch": 0.15705128205128205,
+      "grad_norm": 0.9152003526687622,
+      "learning_rate": 0.0001915224462026563,
+      "loss": 0.8533,
+      "step": 49
+    },
+    {
+      "epoch": 0.16025641025641027,
+      "grad_norm": 1.2656763792037964,
+      "learning_rate": 0.0001910997497957885,
+      "loss": 0.8655,
+      "step": 50
+    },
+    {
+      "epoch": 0.16346153846153846,
+      "grad_norm": 0.5455206036567688,
+      "learning_rate": 0.00019066726011770726,
+      "loss": 0.7714,
+      "step": 51
+    },
+    {
+      "epoch": 0.16666666666666666,
+      "grad_norm": 0.77585369348526,
+      "learning_rate": 0.00019022502366128135,
+      "loss": 0.8717,
+      "step": 52
+    },
+    {
+      "epoch": 0.16987179487179488,
+      "grad_norm": 0.5681566596031189,
+      "learning_rate": 0.0001897730879671634,
+      "loss": 0.8441,
+      "step": 53
+    },
+    {
+      "epoch": 0.17307692307692307,
+      "grad_norm": 1.26576566696167,
+      "learning_rate": 0.00018931150161867916,
+      "loss": 0.9617,
+      "step": 54
+    },
+    {
+      "epoch": 0.1762820512820513,
+      "grad_norm": 0.49213504791259766,
+      "learning_rate": 0.0001888403142366049,
+      "loss": 0.8874,
+      "step": 55
+    },
+    {
+      "epoch": 0.1794871794871795,
+      "grad_norm": 0.5622470378875732,
+      "learning_rate": 0.00018835957647383303,
+      "loss": 0.7956,
+      "step": 56
+    },
+    {
+      "epoch": 0.18269230769230768,
+      "grad_norm": 0.945149302482605,
+      "learning_rate": 0.00018786934000992688,
+      "loss": 0.8357,
+      "step": 57
+    },
+    {
+      "epoch": 0.1858974358974359,
+      "grad_norm": 0.5550402998924255,
+      "learning_rate": 0.00018736965754556528,
+      "loss": 0.8787,
+      "step": 58
+    },
+    {
+      "epoch": 0.1891025641025641,
+      "grad_norm": 0.841452419757843,
+      "learning_rate": 0.00018686058279687698,
+      "loss": 0.8429,
+      "step": 59
+    },
+    {
+      "epoch": 0.19230769230769232,
+      "grad_norm": 0.45196735858917236,
+      "learning_rate": 0.00018634217048966637,
+      "loss": 0.8261,
+      "step": 60
+    },
+    {
+      "epoch": 0.1955128205128205,
+      "grad_norm": 0.9931226372718811,
+      "learning_rate": 0.0001858144763535302,
+      "loss": 0.8594,
+      "step": 61
+    },
+    {
+      "epoch": 0.1987179487179487,
+      "grad_norm": 0.7350529432296753,
+      "learning_rate": 0.00018527755711586678,
+      "loss": 0.8443,
+      "step": 62
+    },
+    {
+      "epoch": 0.20192307692307693,
+      "grad_norm": 0.5463083386421204,
+      "learning_rate": 0.00018473147049577774,
+      "loss": 0.7869,
+      "step": 63
+    },
+    {
+      "epoch": 0.20512820512820512,
+      "grad_norm": 1.1669566631317139,
+      "learning_rate": 0.00018417627519786315,
+      "loss": 0.9341,
+      "step": 64
+    },
+    {
+      "epoch": 0.20833333333333334,
+      "grad_norm": 0.588135302066803,
+      "learning_rate": 0.00018361203090591071,
+      "loss": 0.7736,
+      "step": 65
+    },
+    {
+      "epoch": 0.21153846153846154,
+      "grad_norm": 0.5148831605911255,
+      "learning_rate": 0.00018303879827647975,
+      "loss": 0.8559,
+      "step": 66
+    },
+    {
+      "epoch": 0.21474358974358973,
+      "grad_norm": 0.6593618392944336,
+      "learning_rate": 0.00018245663893238075,
+      "loss": 0.7974,
+      "step": 67
+    },
+    {
+      "epoch": 0.21794871794871795,
+      "grad_norm": 0.6366052627563477,
+      "learning_rate": 0.00018186561545605054,
+      "loss": 0.7543,
+      "step": 68
+    },
+    {
+      "epoch": 0.22115384615384615,
+      "grad_norm": 0.5705471634864807,
+      "learning_rate": 0.00018126579138282503,
+      "loss": 0.8161,
+      "step": 69
+    },
+    {
+      "epoch": 0.22435897435897437,
+      "grad_norm": 0.5039474368095398,
+      "learning_rate": 0.00018065723119410884,
+      "loss": 0.8071,
+      "step": 70
+    },
+    {
+      "epoch": 0.22756410256410256,
+      "grad_norm": 0.7973775267601013,
+      "learning_rate": 0.0001800400003104436,
+      "loss": 0.7785,
+      "step": 71
+    },
+    {
+      "epoch": 0.23076923076923078,
+      "grad_norm": 0.9587669372558594,
+      "learning_rate": 0.00017941416508447536,
+      "loss": 0.8423,
+      "step": 72
+    },
+    {
+      "epoch": 0.23397435897435898,
+      "grad_norm": 0.4499201476573944,
+      "learning_rate": 0.00017877979279382135,
+      "loss": 0.8052,
+      "step": 73
+    },
+    {
+      "epoch": 0.23717948717948717,
+      "grad_norm": 0.9492788910865784,
+      "learning_rate": 0.0001781369516338378,
+      "loss": 0.9093,
+      "step": 74
+    },
+    {
+      "epoch": 0.2403846153846154,
+      "grad_norm": 0.6145200133323669,
+      "learning_rate": 0.000177485710710289,
+      "loss": 0.8359,
+      "step": 75
+    },
+    {
+      "epoch": 0.24358974358974358,
+      "grad_norm": 0.5011272430419922,
+      "learning_rate": 0.00017682614003191807,
+      "loss": 0.8054,
+      "step": 76
+    },
+    {
+      "epoch": 0.2467948717948718,
+      "grad_norm": 1.112430453300476,
+      "learning_rate": 0.0001761583105029213,
+      "loss": 0.8851,
+      "step": 77
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 0.8186496496200562,
+      "learning_rate": 0.00017548229391532572,
+      "loss": 0.757,
+      "step": 78
+    },
+    {
+      "epoch": 0.2532051282051282,
+      "grad_norm": 1.00787353515625,
+      "learning_rate": 0.00017479816294127152,
+      "loss": 0.8089,
+      "step": 79
+    },
+    {
+      "epoch": 0.2564102564102564,
+      "grad_norm": 0.9003360271453857,
+      "learning_rate": 0.0001741059911251997,
+      "loss": 0.9457,
+      "step": 80
+    },
+    {
+      "epoch": 0.25961538461538464,
+      "grad_norm": 1.0145341157913208,
+      "learning_rate": 0.00017340585287594604,
+      "loss": 0.796,
+      "step": 81
+    },
+    {
+      "epoch": 0.26282051282051283,
+      "grad_norm": 1.2034144401550293,
+      "learning_rate": 0.00017269782345874203,
+      "loss": 0.8504,
+      "step": 82
+    },
+    {
+      "epoch": 0.266025641025641,
+      "grad_norm": 0.5833753347396851,
+      "learning_rate": 0.00017198197898712404,
+      "loss": 0.819,
+      "step": 83
+    },
+    {
+      "epoch": 0.2692307692307692,
+      "grad_norm": 0.47029227018356323,
+      "learning_rate": 0.00017125839641475072,
+      "loss": 0.7965,
+      "step": 84
+    },
+    {
+      "epoch": 0.2724358974358974,
+      "grad_norm": 0.6297673583030701,
+      "learning_rate": 0.00017052715352713075,
+      "loss": 0.7564,
+      "step": 85
+    },
+    {
+      "epoch": 0.27564102564102566,
+      "grad_norm": 0.7019922137260437,
+      "learning_rate": 0.00016978832893326074,
+      "loss": 0.8576,
+      "step": 86
+    },
+    {
+      "epoch": 0.27884615384615385,
+      "grad_norm": 0.7785760760307312,
+      "learning_rate": 0.0001690420020571747,
+      "loss": 0.8872,
+      "step": 87
+    },
+    {
+      "epoch": 0.28205128205128205,
+      "grad_norm": 0.47651761770248413,
+      "learning_rate": 0.00016828825312940592,
+      "loss": 0.8333,
+      "step": 88
+    },
+    {
+      "epoch": 0.28525641025641024,
+      "grad_norm": 0.5962091684341431,
+      "learning_rate": 0.00016752716317836229,
+      "loss": 0.9013,
+      "step": 89
+    },
+    {
+      "epoch": 0.28846153846153844,
+      "grad_norm": 0.4600299596786499,
+      "learning_rate": 0.00016675881402161536,
+      "loss": 0.8245,
+      "step": 90
+    },
+    {
+      "epoch": 0.2916666666666667,
+      "grad_norm": 0.5112613439559937,
+      "learning_rate": 0.00016598328825710533,
+      "loss": 0.8138,
+      "step": 91
+    },
+    {
+      "epoch": 0.2948717948717949,
+      "grad_norm": 0.7249051332473755,
+      "learning_rate": 0.00016520066925426144,
+      "loss": 0.8401,
+      "step": 92
+    },
+    {
+      "epoch": 0.2980769230769231,
+      "grad_norm": 0.6219087839126587,
+      "learning_rate": 0.0001644110411450398,
+      "loss": 0.7938,
+      "step": 93
+    },
+    {
+      "epoch": 0.30128205128205127,
+      "grad_norm": 0.4909549951553345,
+      "learning_rate": 0.00016361448881487914,
+      "loss": 0.8425,
+      "step": 94
+    },
+    {
+      "epoch": 0.30448717948717946,
+      "grad_norm": 0.45718565583229065,
+      "learning_rate": 0.0001628110978935756,
+      "loss": 0.8709,
+      "step": 95
+    },
+    {
+      "epoch": 0.3076923076923077,
+      "grad_norm": 0.7159481048583984,
+      "learning_rate": 0.00016200095474607753,
+      "loss": 0.8469,
+      "step": 96
+    },
+    {
+      "epoch": 0.3108974358974359,
+      "grad_norm": 0.6644757986068726,
+      "learning_rate": 0.0001611841464632011,
+      "loss": 0.8352,
+      "step": 97
+    },
+    {
+      "epoch": 0.3141025641025641,
+      "grad_norm": 0.40486231446266174,
+      "learning_rate": 0.00016036076085226814,
+      "loss": 0.7915,
+      "step": 98
+    },
+    {
+      "epoch": 0.3173076923076923,
+      "grad_norm": 0.588192880153656,
+      "learning_rate": 0.0001595308864276666,
+      "loss": 0.8802,
+      "step": 99
+    },
+    {
+      "epoch": 0.32051282051282054,
+      "grad_norm": 0.2998511493206024,
+      "learning_rate": 0.0001586946124013354,
+      "loss": 0.7983,
+      "step": 100
+    },
+    {
+      "epoch": 0.32371794871794873,
+      "grad_norm": 0.5495243072509766,
+      "learning_rate": 0.00015785202867317407,
+      "loss": 0.806,
+      "step": 101
+    },
+    {
+      "epoch": 0.3269230769230769,
+      "grad_norm": 0.3516915738582611,
+      "learning_rate": 0.00015700322582137827,
+      "loss": 0.8455,
+      "step": 102
+    },
+    {
+      "epoch": 0.3301282051282051,
+      "grad_norm": 0.6122769117355347,
+      "learning_rate": 0.0001561482950927029,
+      "loss": 0.8538,
+      "step": 103
+    },
+    {
+      "epoch": 0.3333333333333333,
+      "grad_norm": 0.5758071541786194,
+      "learning_rate": 0.00015528732839265272,
+      "loss": 0.7786,
+      "step": 104
+    },
+    {
+      "epoch": 0.33653846153846156,
+      "grad_norm": 0.606889009475708,
+      "learning_rate": 0.00015442041827560274,
+      "loss": 0.8535,
+      "step": 105
+    },
+    {
+      "epoch": 0.33974358974358976,
+      "grad_norm": 0.5758721232414246,
+      "learning_rate": 0.00015354765793484834,
+      "loss": 0.8368,
+      "step": 106
+    },
+    {
+      "epoch": 0.34294871794871795,
+      "grad_norm": 0.41782525181770325,
+      "learning_rate": 0.000152669141192587,
+      "loss": 0.8372,
+      "step": 107
+    },
+    {
+      "epoch": 0.34615384615384615,
+      "grad_norm": 0.44819149374961853,
+      "learning_rate": 0.00015178496248983254,
+      "loss": 0.7807,
+      "step": 108
+    },
+    {
+      "epoch": 0.34935897435897434,
+      "grad_norm": 0.42602694034576416,
+      "learning_rate": 0.00015089521687626243,
+      "loss": 0.7363,
+      "step": 109
+    },
+    {
+      "epoch": 0.3525641025641026,
+      "grad_norm": 0.5617648363113403,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 0.8311,
+      "step": 110
+    },
+    {
+      "epoch": 0.3557692307692308,
+      "grad_norm": 0.38159874081611633,
+      "learning_rate": 0.00014909940809733222,
+      "loss": 0.7536,
+      "step": 111
+    },
+    {
+      "epoch": 0.358974358974359,
+      "grad_norm": 0.3874197006225586,
+      "learning_rate": 0.00014819353798236427,
+      "loss": 0.8124,
+      "step": 112
+    },
+    {
+      "epoch": 0.36217948717948717,
+      "grad_norm": 0.3920519948005676,
+      "learning_rate": 0.00014728248703661182,
+      "loss": 0.7821,
+      "step": 113
+    },
+    {
+      "epoch": 0.36538461538461536,
+      "grad_norm": 0.31610092520713806,
+      "learning_rate": 0.00014636635319853275,
+      "loss": 0.8025,
+      "step": 114
+    },
+    {
+      "epoch": 0.3685897435897436,
+      "grad_norm": 0.9610485434532166,
+      "learning_rate": 0.00014544523495299842,
+      "loss": 0.8597,
+      "step": 115
+    },
+    {
+      "epoch": 0.3717948717948718,
+      "grad_norm": 0.6983340978622437,
+      "learning_rate": 0.0001445192313207067,
+      "loss": 0.8763,
+      "step": 116
+    },
+    {
+      "epoch": 0.375,
+      "grad_norm": 0.37733662128448486,
+      "learning_rate": 0.00014358844184753712,
+      "loss": 0.787,
+      "step": 117
+    },
+    {
+      "epoch": 0.3782051282051282,
+      "grad_norm": 0.6264870166778564,
+      "learning_rate": 0.00014265296659384956,
+      "loss": 0.6865,
+      "step": 118
+    },
+    {
+      "epoch": 0.3814102564102564,
+      "grad_norm": 0.6618545651435852,
+      "learning_rate": 0.0001417129061237278,
+      "loss": 0.8416,
+      "step": 119
+    },
+    {
+      "epoch": 0.38461538461538464,
+      "grad_norm": 0.5489368438720703,
+      "learning_rate": 0.00014076836149416887,
+      "loss": 0.8113,
+      "step": 120
+    },
+    {
+      "epoch": 0.38782051282051283,
+      "grad_norm": 0.5143547654151917,
+      "learning_rate": 0.00013981943424421932,
+      "loss": 0.7212,
+      "step": 121
+    },
+    {
+      "epoch": 0.391025641025641,
+      "grad_norm": 0.3641842007637024,
+      "learning_rate": 0.00013886622638405952,
+      "loss": 0.7081,
+      "step": 122
+    },
+    {
+      "epoch": 0.3942307692307692,
+      "grad_norm": 0.5204703211784363,
+      "learning_rate": 0.00013790884038403795,
+      "loss": 0.8671,
+      "step": 123
+    },
+    {
+      "epoch": 0.3974358974358974,
+      "grad_norm": 0.6415024995803833,
+      "learning_rate": 0.00013694737916365517,
+      "loss": 0.7905,
+      "step": 124
+    },
+    {
+      "epoch": 0.40064102564102566,
+      "grad_norm": 0.5021610260009766,
+      "learning_rate": 0.0001359819460805001,
+      "loss": 0.8396,
+      "step": 125
+    },
+    {
+      "epoch": 0.40384615384615385,
+      "grad_norm": 0.6839991211891174,
+      "learning_rate": 0.00013501264491913906,
+      "loss": 0.8807,
+      "step": 126
+    },
+    {
+      "epoch": 0.40705128205128205,
+      "grad_norm": 0.3714783787727356,
+      "learning_rate": 0.00013403957987995882,
+      "loss": 0.7946,
+      "step": 127
+    },
+    {
+      "epoch": 0.41025641025641024,
+      "grad_norm": 0.5053361654281616,
+      "learning_rate": 0.00013306285556796495,
+      "loss": 0.8481,
+      "step": 128
+    },
+    {
+      "epoch": 0.41346153846153844,
+      "grad_norm": 0.5429531335830688,
+      "learning_rate": 0.00013208257698153677,
+      "loss": 0.7554,
+      "step": 129
+    },
+    {
+      "epoch": 0.4166666666666667,
+      "grad_norm": 0.3953702449798584,
+      "learning_rate": 0.00013109884950114007,
+      "loss": 0.8,
+      "step": 130
+    },
+    {
+      "epoch": 0.4198717948717949,
+      "grad_norm": 0.6481508016586304,
+      "learning_rate": 0.00013011177887799845,
+      "loss": 0.8627,
+      "step": 131
+    },
+    {
+      "epoch": 0.4230769230769231,
+      "grad_norm": 0.7805072069168091,
+      "learning_rate": 0.00012912147122272523,
+      "loss": 0.8365,
+      "step": 132
+    },
+    {
+      "epoch": 0.42628205128205127,
+      "grad_norm": 0.6625213027000427,
+      "learning_rate": 0.00012812803299391628,
+      "loss": 0.8348,
+      "step": 133
+    },
+    {
+      "epoch": 0.42948717948717946,
+      "grad_norm": 0.5890776515007019,
+      "learning_rate": 0.0001271315709867059,
+      "loss": 0.8482,
+      "step": 134
+    },
+    {
+      "epoch": 0.4326923076923077,
+      "grad_norm": 0.8653396964073181,
+      "learning_rate": 0.00012613219232128608,
+      "loss": 0.7627,
+      "step": 135
+    },
+    {
+      "epoch": 0.4358974358974359,
+      "grad_norm": 0.4106805920600891,
+      "learning_rate": 0.00012513000443139112,
+      "loss": 0.8412,
+      "step": 136
+    },
+    {
+      "epoch": 0.4391025641025641,
+      "grad_norm": 0.9956967234611511,
+      "learning_rate": 0.00012412511505274844,
+      "loss": 0.9127,
+      "step": 137
+    },
+    {
+      "epoch": 0.4423076923076923,
+      "grad_norm": 0.46844878792762756,
+      "learning_rate": 0.000123117632211497,
+      "loss": 0.774,
+      "step": 138
+    },
+    {
+      "epoch": 0.44551282051282054,
+      "grad_norm": 0.966278612613678,
+      "learning_rate": 0.0001221076642125742,
+      "loss": 0.8659,
+      "step": 139
+    },
+    {
+      "epoch": 0.44871794871794873,
+      "grad_norm": 0.5847793221473694,
+      "learning_rate": 0.00012109531962807332,
+      "loss": 0.7507,
+      "step": 140
+    },
+    {
+      "epoch": 0.4519230769230769,
+      "grad_norm": 0.5927683115005493,
+      "learning_rate": 0.00012008070728557186,
+      "loss": 0.8908,
+      "step": 141
+    },
+    {
+      "epoch": 0.4551282051282051,
+      "grad_norm": 0.42794185876846313,
+      "learning_rate": 0.00011906393625643244,
+      "loss": 0.7478,
+      "step": 142
+    },
+    {
+      "epoch": 0.4583333333333333,
+      "grad_norm": 0.6426613926887512,
+      "learning_rate": 0.00011804511584407763,
+      "loss": 0.7498,
+      "step": 143
+    },
+    {
+      "epoch": 0.46153846153846156,
+      "grad_norm": 0.40398654341697693,
+      "learning_rate": 0.00011702435557223987,
+      "loss": 0.7539,
+      "step": 144
+    },
+    {
+      "epoch": 0.46474358974358976,
+      "grad_norm": 0.4018569886684418,
+      "learning_rate": 0.00011600176517318741,
+      "loss": 0.8294,
+      "step": 145
+    },
+    {
+      "epoch": 0.46794871794871795,
+      "grad_norm": 0.33486562967300415,
+      "learning_rate": 0.00011497745457592816,
+      "loss": 0.8322,
+      "step": 146
+    },
+    {
+      "epoch": 0.47115384615384615,
+      "grad_norm": 0.539478063583374,
+      "learning_rate": 0.00011395153389439233,
+      "loss": 0.8697,
+      "step": 147
+    },
+    {
+      "epoch": 0.47435897435897434,
+      "grad_norm": 0.4381621479988098,
+      "learning_rate": 0.0001129241134155949,
+      "loss": 0.8216,
+      "step": 148
+    },
+    {
+      "epoch": 0.4775641025641026,
+      "grad_norm": 1.0025720596313477,
+      "learning_rate": 0.00011189530358778005,
+      "loss": 0.9283,
+      "step": 149
+    },
+    {
+      "epoch": 0.4807692307692308,
+      "grad_norm": 0.6928549408912659,
+      "learning_rate": 0.00011086521500854745,
+      "loss": 0.8163,
+      "step": 150
+    },
+    {
+      "epoch": 0.483974358974359,
+      "grad_norm": 0.3628673851490021,
+      "learning_rate": 0.00010983395841296348,
+      "loss": 0.7866,
+      "step": 151
+    },
+    {
+      "epoch": 0.48717948717948717,
+      "grad_norm": 0.6659094095230103,
+      "learning_rate": 0.00010880164466165674,
+      "loss": 0.767,
+      "step": 152
+    },
+    {
+      "epoch": 0.49038461538461536,
+      "grad_norm": 0.4747048318386078,
+      "learning_rate": 0.00010776838472890065,
+      "loss": 0.7455,
+      "step": 153
+    },
+    {
+      "epoch": 0.4935897435897436,
+      "grad_norm": 0.5610392093658447,
+      "learning_rate": 0.00010673428969068364,
+      "loss": 0.7943,
+      "step": 154
+    },
+    {
+      "epoch": 0.4967948717948718,
+      "grad_norm": 0.8494670391082764,
+      "learning_rate": 0.00010569947071276847,
+      "loss": 0.8778,
+      "step": 155
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.4916403293609619,
+      "learning_rate": 0.00010466403903874176,
+      "loss": 0.7698,
+      "step": 156
+    },
+    {
+      "epoch": 0.5032051282051282,
+      "grad_norm": 1.1345371007919312,
+      "learning_rate": 0.00010362810597805526,
+      "loss": 0.9339,
+      "step": 157
+    },
+    {
+      "epoch": 0.5064102564102564,
+      "grad_norm": 0.8065443634986877,
+      "learning_rate": 0.00010259178289406011,
+      "loss": 0.7978,
+      "step": 158
+    },
+    {
+      "epoch": 0.5096153846153846,
+      "grad_norm": 1.3246110677719116,
+      "learning_rate": 0.0001015551811920351,
+      "loss": 0.9917,
+      "step": 159
+    },
+    {
+      "epoch": 0.5128205128205128,
+      "grad_norm": 0.5924827456474304,
+      "learning_rate": 0.00010051841230721065,
+      "loss": 0.8334,
+      "step": 160
+    },
+    {
+      "epoch": 0.5160256410256411,
+      "grad_norm": 0.5810033679008484,
+      "learning_rate": 9.948158769278939e-05,
+      "loss": 0.8431,
+      "step": 161
+    },
+    {
+      "epoch": 0.5192307692307693,
+      "grad_norm": 0.517737627029419,
+      "learning_rate": 9.844481880796491e-05,
+      "loss": 0.8149,
+      "step": 162
+    },
+    {
+      "epoch": 0.5224358974358975,
+      "grad_norm": 0.6809769868850708,
+      "learning_rate": 9.740821710593989e-05,
+      "loss": 0.9241,
+      "step": 163
+    },
+    {
+      "epoch": 0.5256410256410257,
+      "grad_norm": 0.5955147743225098,
+      "learning_rate": 9.637189402194476e-05,
+      "loss": 0.761,
+      "step": 164
+    },
+    {
+      "epoch": 0.5288461538461539,
+      "grad_norm": 0.6794393062591553,
+      "learning_rate": 9.533596096125825e-05,
+      "loss": 0.8291,
+      "step": 165
+    },
+    {
+      "epoch": 0.532051282051282,
+      "grad_norm": 0.6929296255111694,
+      "learning_rate": 9.430052928723153e-05,
+      "loss": 0.7753,
+      "step": 166
+    },
+    {
+      "epoch": 0.5352564102564102,
+      "grad_norm": 0.6990981698036194,
+      "learning_rate": 9.326571030931637e-05,
+      "loss": 0.8932,
+      "step": 167
+    },
+    {
+      "epoch": 0.5384615384615384,
+      "grad_norm": 0.591814398765564,
+      "learning_rate": 9.223161527109937e-05,
+      "loss": 0.8114,
+      "step": 168
+    },
+    {
+      "epoch": 0.5416666666666666,
+      "grad_norm": 0.6408451199531555,
+      "learning_rate": 9.119835533834331e-05,
+      "loss": 0.7942,
+      "step": 169
+    },
+    {
+      "epoch": 0.5448717948717948,
+      "grad_norm": 0.6977259516716003,
+      "learning_rate": 9.016604158703654e-05,
+      "loss": 0.912,
+      "step": 170
+    },
+    {
+      "epoch": 0.5480769230769231,
+      "grad_norm": 0.604136049747467,
+      "learning_rate": 8.913478499145254e-05,
+      "loss": 0.789,
+      "step": 171
+    },
+    {
+      "epoch": 0.5512820512820513,
+      "grad_norm": 0.5467025637626648,
+      "learning_rate": 8.810469641222001e-05,
+      "loss": 0.7825,
+      "step": 172
+    },
+    {
+      "epoch": 0.5544871794871795,
+      "grad_norm": 0.7560824155807495,
+      "learning_rate": 8.707588658440511e-05,
+      "loss": 0.7609,
+      "step": 173
+    },
+    {
+      "epoch": 0.5576923076923077,
+      "grad_norm": 0.9269303679466248,
+      "learning_rate": 8.604846610560771e-05,
+      "loss": 0.8706,
+      "step": 174
+    },
+    {
+      "epoch": 0.5608974358974359,
+      "grad_norm": 0.7465280294418335,
+      "learning_rate": 8.502254542407186e-05,
+      "loss": 0.7986,
+      "step": 175
+    },
+    {
+      "epoch": 0.5641025641025641,
+      "grad_norm": 0.8691240549087524,
+      "learning_rate": 8.399823482681262e-05,
+      "loss": 0.7843,
+      "step": 176
+    },
+    {
+      "epoch": 0.5673076923076923,
+      "grad_norm": 0.59829181432724,
+      "learning_rate": 8.297564442776014e-05,
+      "loss": 0.7441,
+      "step": 177
+    },
+    {
+      "epoch": 0.5705128205128205,
+      "grad_norm": 0.9093548655509949,
+      "learning_rate": 8.195488415592238e-05,
+      "loss": 0.8501,
+      "step": 178
+    },
+    {
+      "epoch": 0.5737179487179487,
+      "grad_norm": 0.8965813517570496,
+      "learning_rate": 8.093606374356759e-05,
+      "loss": 0.8309,
+      "step": 179
+    },
+    {
+      "epoch": 0.5769230769230769,
+      "grad_norm": 0.7008676528930664,
+      "learning_rate": 7.991929271442817e-05,
+      "loss": 0.6563,
+      "step": 180
+    },
+    {
+      "epoch": 0.5801282051282052,
+      "grad_norm": 0.8001984357833862,
+      "learning_rate": 7.89046803719267e-05,
+      "loss": 0.8305,
+      "step": 181
+    },
+    {
+      "epoch": 0.5833333333333334,
+      "grad_norm": 0.8418125510215759,
+      "learning_rate": 7.789233578742582e-05,
+      "loss": 0.8296,
+      "step": 182
+    },
+    {
+      "epoch": 0.5865384615384616,
+      "grad_norm": 0.8208316564559937,
+      "learning_rate": 7.688236778850306e-05,
+      "loss": 0.7777,
+      "step": 183
+    },
+    {
+      "epoch": 0.5897435897435898,
+      "grad_norm": 0.8942621946334839,
+      "learning_rate": 7.587488494725157e-05,
+      "loss": 0.9101,
+      "step": 184
+    },
+    {
+      "epoch": 0.592948717948718,
+      "grad_norm": 0.6328911781311035,
+      "learning_rate": 7.48699955686089e-05,
+      "loss": 0.7004,
+      "step": 185
+    },
+    {
+      "epoch": 0.5961538461538461,
+      "grad_norm": 0.5853061079978943,
+      "learning_rate": 7.386780767871397e-05,
+      "loss": 0.8373,
+      "step": 186
+    },
+    {
+      "epoch": 0.5993589743589743,
+      "grad_norm": 0.9095894694328308,
+      "learning_rate": 7.286842901329412e-05,
+      "loss": 0.833,
+      "step": 187
+    },
+    {
+      "epoch": 0.6025641025641025,
+      "grad_norm": 0.562564492225647,
+      "learning_rate": 7.187196700608373e-05,
+      "loss": 0.7822,
+      "step": 188
+    },
+    {
+      "epoch": 0.6057692307692307,
+      "grad_norm": 0.812235951423645,
+      "learning_rate": 7.087852877727481e-05,
+      "loss": 0.823,
+      "step": 189
+    },
+    {
+      "epoch": 0.6089743589743589,
+      "grad_norm": 0.9851651191711426,
+      "learning_rate": 6.988822112200156e-05,
+      "loss": 0.8251,
+      "step": 190
+    },
+    {
+      "epoch": 0.6121794871794872,
+      "grad_norm": 0.9343296885490417,
+      "learning_rate": 6.890115049885994e-05,
+      "loss": 0.7613,
+      "step": 191
+    },
+    {
+      "epoch": 0.6153846153846154,
+      "grad_norm": 0.6352812647819519,
+      "learning_rate": 6.791742301846326e-05,
+      "loss": 0.7761,
+      "step": 192
+    },
+    {
+      "epoch": 0.6185897435897436,
+      "grad_norm": 1.490954041481018,
+      "learning_rate": 6.693714443203507e-05,
+      "loss": 1.0911,
+      "step": 193
+    },
+    {
+      "epoch": 0.6217948717948718,
+      "grad_norm": 0.7327432036399841,
+      "learning_rate": 6.59604201200412e-05,
+      "loss": 0.7859,
+      "step": 194
+    },
+    {
+      "epoch": 0.625,
+      "grad_norm": 0.7584162950515747,
+      "learning_rate": 6.498735508086093e-05,
+      "loss": 0.6795,
+      "step": 195
+    },
+    {
+      "epoch": 0.6282051282051282,
+      "grad_norm": 0.9393740892410278,
+      "learning_rate": 6.40180539194999e-05,
+      "loss": 0.7382,
+      "step": 196
+    },
+    {
+      "epoch": 0.6314102564102564,
+      "grad_norm": 1.4272030591964722,
+      "learning_rate": 6.305262083634488e-05,
+      "loss": 0.8325,
+      "step": 197
+    },
+    {
+      "epoch": 0.6346153846153846,
+      "grad_norm": 1.7151983976364136,
+      "learning_rate": 6.209115961596208e-05,
+      "loss": 0.9443,
+      "step": 198
+    },
+    {
+      "epoch": 0.6378205128205128,
+      "grad_norm": 0.856202244758606,
+      "learning_rate": 6.113377361594049e-05,
+      "loss": 0.7448,
+      "step": 199
+    },
+    {
+      "epoch": 0.6410256410256411,
+      "grad_norm": 1.3806068897247314,
+      "learning_rate": 6.018056575578075e-05,
+      "loss": 0.9231,
+      "step": 200
+    },
+    {
+      "epoch": 0.6442307692307693,
+      "grad_norm": 0.8063072562217712,
+      "learning_rate": 5.923163850583113e-05,
+      "loss": 0.7305,
+      "step": 201
+    },
+    {
+      "epoch": 0.6474358974358975,
+      "grad_norm": 1.1578689813613892,
+      "learning_rate": 5.828709387627218e-05,
+      "loss": 0.7892,
+      "step": 202
+    },
+    {
+      "epoch": 0.6506410256410257,
+      "grad_norm": 0.881730854511261,
+      "learning_rate": 5.73470334061505e-05,
+      "loss": 0.7162,
+      "step": 203
+    },
+    {
+      "epoch": 0.6538461538461539,
+      "grad_norm": 0.9713548421859741,
+      "learning_rate": 5.6411558152462894e-05,
+      "loss": 0.7252,
+      "step": 204
+    },
+    {
+      "epoch": 0.657051282051282,
+      "grad_norm": 1.12835693359375,
+      "learning_rate": 5.54807686792933e-05,
+      "loss": 0.7446,
+      "step": 205
+    },
+    {
+      "epoch": 0.6602564102564102,
+      "grad_norm": 1.3624720573425293,
+      "learning_rate": 5.4554765047001613e-05,
+      "loss": 0.7664,
+      "step": 206
+    },
+    {
+      "epoch": 0.6634615384615384,
+      "grad_norm": 1.169715166091919,
+      "learning_rate": 5.363364680146725e-05,
+      "loss": 0.7936,
+      "step": 207
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 1.94355309009552,
+      "learning_rate": 5.271751296338823e-05,
+      "loss": 0.8667,
+      "step": 208
+    },
+    {
+      "epoch": 0.6698717948717948,
+      "grad_norm": 1.5784542560577393,
+      "learning_rate": 5.180646201763577e-05,
+      "loss": 0.8658,
+      "step": 209
+    },
+    {
+      "epoch": 0.6730769230769231,
+      "grad_norm": 0.9312598705291748,
+      "learning_rate": 5.090059190266779e-05,
+      "loss": 0.7996,
+      "step": 210
+    },
+    {
+      "epoch": 0.6762820512820513,
+      "grad_norm": 0.9065409302711487,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 0.7893,
+      "step": 211
+    },
+    {
+      "epoch": 0.6794871794871795,
+      "grad_norm": 1.3561393022537231,
+      "learning_rate": 4.9104783123737566e-05,
+      "loss": 0.8413,
+      "step": 212
+    },
+    {
+      "epoch": 0.6826923076923077,
+      "grad_norm": 0.8747413158416748,
+      "learning_rate": 4.821503751016746e-05,
+      "loss": 0.799,
+      "step": 213
+    },
+    {
+      "epoch": 0.6858974358974359,
+      "grad_norm": 0.8541598916053772,
+      "learning_rate": 4.733085880741301e-05,
+      "loss": 0.7965,
+      "step": 214
+    },
+    {
+      "epoch": 0.6891025641025641,
+      "grad_norm": 1.1472944021224976,
+      "learning_rate": 4.645234206515171e-05,
+      "loss": 0.7915,
+      "step": 215
+    },
+    {
+      "epoch": 0.6923076923076923,
+      "grad_norm": 1.0317872762680054,
+      "learning_rate": 4.5579581724397255e-05,
+      "loss": 0.8,
+      "step": 216
+    },
+    {
+      "epoch": 0.6955128205128205,
+      "grad_norm": 1.4401482343673706,
+      "learning_rate": 4.471267160734731e-05,
+      "loss": 0.7188,
+      "step": 217
+    },
+    {
+      "epoch": 0.6987179487179487,
+      "grad_norm": 0.7811070680618286,
+      "learning_rate": 4.385170490729712e-05,
+      "loss": 0.8123,
+      "step": 218
+    },
+    {
+      "epoch": 0.7019230769230769,
+      "grad_norm": 1.1124131679534912,
+      "learning_rate": 4.2996774178621736e-05,
+      "loss": 0.9242,
+      "step": 219
+    },
+    {
+      "epoch": 0.7051282051282052,
+      "grad_norm": 0.9388600587844849,
+      "learning_rate": 4.2147971326825966e-05,
+      "loss": 0.8065,
+      "step": 220
+    },
+    {
+      "epoch": 0.7083333333333334,
+      "grad_norm": 0.8694519400596619,
+      "learning_rate": 4.130538759866457e-05,
+      "loss": 0.8012,
+      "step": 221
+    },
+    {
+      "epoch": 0.7115384615384616,
+      "grad_norm": 0.756574809551239,
+      "learning_rate": 4.046911357233343e-05,
+      "loss": 0.6749,
+      "step": 222
+    },
+    {
+      "epoch": 0.7147435897435898,
+      "grad_norm": 0.8523420095443726,
+      "learning_rate": 3.963923914773187e-05,
+      "loss": 0.7184,
+      "step": 223
+    },
+    {
+      "epoch": 0.717948717948718,
+      "grad_norm": 0.8101953864097595,
+      "learning_rate": 3.8815853536798904e-05,
+      "loss": 0.8064,
+      "step": 224
+    },
+    {
+      "epoch": 0.7211538461538461,
+      "grad_norm": 0.9404911994934082,
+      "learning_rate": 3.79990452539225e-05,
+      "loss": 0.7452,
+      "step": 225
+    },
+    {
+      "epoch": 0.7243589743589743,
+      "grad_norm": 0.8205745220184326,
+      "learning_rate": 3.7188902106424416e-05,
+      "loss": 0.7859,
+      "step": 226
+    },
+    {
+      "epoch": 0.7275641025641025,
+      "grad_norm": 0.9722088575363159,
+      "learning_rate": 3.638551118512089e-05,
+      "loss": 0.7248,
+      "step": 227
+    },
+    {
+      "epoch": 0.7307692307692307,
+      "grad_norm": 0.7296696901321411,
+      "learning_rate": 3.558895885496023e-05,
+      "loss": 0.7329,
+      "step": 228
+    },
+    {
+      "epoch": 0.7339743589743589,
+      "grad_norm": 1.253202199935913,
+      "learning_rate": 3.479933074573858e-05,
+      "loss": 0.8777,
+      "step": 229
+    },
+    {
+      "epoch": 0.7371794871794872,
+      "grad_norm": 1.1534240245819092,
+      "learning_rate": 3.401671174289469e-05,
+      "loss": 0.7485,
+      "step": 230
+    },
+    {
+      "epoch": 0.7403846153846154,
+      "grad_norm": 1.1224077939987183,
+      "learning_rate": 3.324118597838464e-05,
+      "loss": 0.7728,
+      "step": 231
+    },
+    {
+      "epoch": 0.7435897435897436,
+      "grad_norm": 0.8976945281028748,
+      "learning_rate": 3.2472836821637744e-05,
+      "loss": 0.7541,
+      "step": 232
+    },
+    {
+      "epoch": 0.7467948717948718,
+      "grad_norm": 0.840302050113678,
+      "learning_rate": 3.1711746870594086e-05,
+      "loss": 0.6973,
+      "step": 233
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 0.988998293876648,
+      "learning_rate": 3.0957997942825336e-05,
+      "loss": 0.6981,
+      "step": 234
+    },
+    {
+      "epoch": 0.7532051282051282,
+      "grad_norm": 1.0511542558670044,
+      "learning_rate": 3.021167106673928e-05,
+      "loss": 0.6618,
+      "step": 235
+    },
+    {
+      "epoch": 0.7564102564102564,
+      "grad_norm": 1.1155120134353638,
+      "learning_rate": 2.9472846472869298e-05,
+      "loss": 0.7775,
+      "step": 236
+    },
+    {
+      "epoch": 0.7596153846153846,
+      "grad_norm": 1.064674735069275,
+      "learning_rate": 2.874160358524931e-05,
+      "loss": 0.747,
+      "step": 237
+    },
+    {
+      "epoch": 0.7628205128205128,
+      "grad_norm": 1.1070621013641357,
+      "learning_rate": 2.8018021012875994e-05,
+      "loss": 0.8083,
+      "step": 238
+    },
+    {
+      "epoch": 0.7660256410256411,
+      "grad_norm": 0.8089228868484497,
+      "learning_rate": 2.7302176541257986e-05,
+      "loss": 0.7037,
+      "step": 239
+    },
+    {
+      "epoch": 0.7692307692307693,
+      "grad_norm": 0.7307572960853577,
+      "learning_rate": 2.659414712405398e-05,
+      "loss": 0.7206,
+      "step": 240
+    },
+    {
+      "epoch": 0.7724358974358975,
+      "grad_norm": 1.0370497703552246,
+      "learning_rate": 2.5894008874800325e-05,
+      "loss": 0.7379,
+      "step": 241
+    },
+    {
+      "epoch": 0.7756410256410257,
+      "grad_norm": 1.3511935472488403,
+      "learning_rate": 2.5201837058728505e-05,
+      "loss": 0.7198,
+      "step": 242
+    },
+    {
+      "epoch": 0.7788461538461539,
+      "grad_norm": 0.8478284478187561,
+      "learning_rate": 2.451770608467432e-05,
+      "loss": 0.8123,
+      "step": 243
+    },
+    {
+      "epoch": 0.782051282051282,
+      "grad_norm": 1.0344876050949097,
+      "learning_rate": 2.3841689497078746e-05,
+      "loss": 0.7769,
+      "step": 244
+    },
+    {
+      "epoch": 0.7852564102564102,
+      "grad_norm": 1.0734611749649048,
+      "learning_rate": 2.3173859968081944e-05,
+      "loss": 0.7204,
+      "step": 245
+    },
+    {
+      "epoch": 0.7884615384615384,
+      "grad_norm": 1.7516003847122192,
+      "learning_rate": 2.251428928971102e-05,
+      "loss": 0.7088,
+      "step": 246
+    },
+    {
+      "epoch": 0.7916666666666666,
+      "grad_norm": 1.0216751098632812,
+      "learning_rate": 2.1863048366162208e-05,
+      "loss": 0.7828,
+      "step": 247
+    },
+    {
+      "epoch": 0.7948717948717948,
+      "grad_norm": 1.4974614381790161,
+      "learning_rate": 2.1220207206178688e-05,
+      "loss": 0.8549,
+      "step": 248
+    },
+    {
+      "epoch": 0.7980769230769231,
+      "grad_norm": 1.2746527194976807,
+      "learning_rate": 2.058583491552465e-05,
+      "loss": 0.7863,
+      "step": 249
+    },
+    {
+      "epoch": 0.8012820512820513,
+      "grad_norm": 1.0694308280944824,
+      "learning_rate": 1.995999968955641e-05,
+      "loss": 0.7612,
+      "step": 250
+    },
+    {
+      "epoch": 0.8044871794871795,
+      "grad_norm": 1.4098316431045532,
+      "learning_rate": 1.9342768805891178e-05,
+      "loss": 0.7792,
+      "step": 251
+    },
+    {
+      "epoch": 0.8076923076923077,
+      "grad_norm": 0.9499948024749756,
+      "learning_rate": 1.8734208617174988e-05,
+      "loss": 0.8431,
+      "step": 252
+    },
+    {
+      "epoch": 0.8108974358974359,
+      "grad_norm": 1.0735160112380981,
+      "learning_rate": 1.8134384543949478e-05,
+      "loss": 0.6933,
+      "step": 253
+    },
+    {
+      "epoch": 0.8141025641025641,
+      "grad_norm": 1.3675204515457153,
+      "learning_rate": 1.754336106761927e-05,
+      "loss": 0.7038,
+      "step": 254
+    },
+    {
+      "epoch": 0.8173076923076923,
+      "grad_norm": 1.0891550779342651,
+      "learning_rate": 1.696120172352025e-05,
+      "loss": 0.6681,
+      "step": 255
+    },
+    {
+      "epoch": 0.8205128205128205,
+      "grad_norm": 1.0907151699066162,
+      "learning_rate": 1.6387969094089316e-05,
+      "loss": 0.8043,
+      "step": 256
+    },
+    {
+      "epoch": 0.8237179487179487,
+      "grad_norm": 0.935387134552002,
+      "learning_rate": 1.5823724802136865e-05,
+      "loss": 0.8365,
+      "step": 257
+    },
+    {
+      "epoch": 0.8269230769230769,
+      "grad_norm": 0.8595330715179443,
+      "learning_rate": 1.526852950422226e-05,
+      "loss": 0.7014,
+      "step": 258
+    },
+    {
+      "epoch": 0.8301282051282052,
+      "grad_norm": 1.1038745641708374,
+      "learning_rate": 1.4722442884133214e-05,
+      "loss": 0.7596,
+      "step": 259
+    },
+    {
+      "epoch": 0.8333333333333334,
+      "grad_norm": 1.1582711935043335,
+      "learning_rate": 1.4185523646469822e-05,
+      "loss": 0.6689,
+      "step": 260
+    },
+    {
+      "epoch": 0.8365384615384616,
+      "grad_norm": 1.1454054117202759,
+      "learning_rate": 1.3657829510333654e-05,
+      "loss": 0.8129,
+      "step": 261
+    },
+    {
+      "epoch": 0.8397435897435898,
+      "grad_norm": 1.1534847021102905,
+      "learning_rate": 1.3139417203123027e-05,
+      "loss": 0.6611,
+      "step": 262
+    },
+    {
+      "epoch": 0.842948717948718,
+      "grad_norm": 1.1782026290893555,
+      "learning_rate": 1.263034245443473e-05,
+      "loss": 0.7166,
+      "step": 263
+    },
+    {
+      "epoch": 0.8461538461538461,
+      "grad_norm": 1.3515312671661377,
+      "learning_rate": 1.2130659990073146e-05,
+      "loss": 0.789,
+      "step": 264
+    },
+    {
+      "epoch": 0.8493589743589743,
+      "grad_norm": 1.0562694072723389,
+      "learning_rate": 1.1640423526166988e-05,
+      "loss": 0.7457,
+      "step": 265
+    },
+    {
+      "epoch": 0.8525641025641025,
+      "grad_norm": 1.0518815517425537,
+      "learning_rate": 1.1159685763395111e-05,
+      "loss": 0.7977,
+      "step": 266
+    },
+    {
+      "epoch": 0.8557692307692307,
+      "grad_norm": 1.1951806545257568,
+      "learning_rate": 1.0688498381320855e-05,
+      "loss": 0.7813,
+      "step": 267
+    },
+    {
+      "epoch": 0.8589743589743589,
+      "grad_norm": 1.2347551584243774,
+      "learning_rate": 1.0226912032836611e-05,
+      "loss": 0.6702,
+      "step": 268
+    },
+    {
+      "epoch": 0.8621794871794872,
+      "grad_norm": 2.0265257358551025,
+      "learning_rate": 9.774976338718677e-06,
+      "loss": 0.9113,
+      "step": 269
+    },
+    {
+      "epoch": 0.8653846153846154,
+      "grad_norm": 1.1159110069274902,
+      "learning_rate": 9.332739882292752e-06,
+      "loss": 0.7241,
+      "step": 270
+    },
+    {
+      "epoch": 0.8685897435897436,
+      "grad_norm": 1.0101889371871948,
+      "learning_rate": 8.900250204211514e-06,
+      "loss": 0.7407,
+      "step": 271
+    },
+    {
+      "epoch": 0.8717948717948718,
+      "grad_norm": 1.1704083681106567,
+      "learning_rate": 8.47755379734373e-06,
+      "loss": 0.6598,
+      "step": 272
+    },
+    {
+      "epoch": 0.875,
+      "grad_norm": 0.9426171779632568,
+      "learning_rate": 8.064696101776358e-06,
+      "loss": 0.7204,
+      "step": 273
+    },
+    {
+      "epoch": 0.8782051282051282,
+      "grad_norm": 1.2830696105957031,
+      "learning_rate": 7.661721499929753e-06,
+      "loss": 0.7574,
+      "step": 274
+    },
+    {
+      "epoch": 0.8814102564102564,
+      "grad_norm": 1.5801949501037598,
+      "learning_rate": 7.2686733117863784e-06,
+      "loss": 0.7968,
+      "step": 275
+    },
+    {
+      "epoch": 0.8846153846153846,
+      "grad_norm": 1.4336384534835815,
+      "learning_rate": 6.8855937902340576e-06,
+      "loss": 0.6974,
+      "step": 276
+    },
+    {
+      "epoch": 0.8878205128205128,
+      "grad_norm": 0.9879603385925293,
+      "learning_rate": 6.512524116523633e-06,
+      "loss": 0.634,
+      "step": 277
+    },
+    {
+      "epoch": 0.8910256410256411,
+      "grad_norm": 1.2858949899673462,
+      "learning_rate": 6.149504395842087e-06,
+      "loss": 0.7762,
+      "step": 278
+    },
+    {
+      "epoch": 0.8942307692307693,
+      "grad_norm": 1.6432108879089355,
+      "learning_rate": 5.7965736530010916e-06,
+      "loss": 0.821,
+      "step": 279
+    },
+    {
+      "epoch": 0.8974358974358975,
+      "grad_norm": 1.3427728414535522,
+      "learning_rate": 5.453769828241872e-06,
+      "loss": 0.7391,
+      "step": 280
+    },
+    {
+      "epoch": 0.9006410256410257,
+      "grad_norm": 1.405120849609375,
+      "learning_rate": 5.121129773156663e-06,
+      "loss": 0.7824,
+      "step": 281
+    },
+    {
+      "epoch": 0.9038461538461539,
+      "grad_norm": 1.232499122619629,
+      "learning_rate": 4.798689246727006e-06,
+      "loss": 0.7732,
+      "step": 282
+    },
+    {
+      "epoch": 0.907051282051282,
+      "grad_norm": 1.4786527156829834,
+      "learning_rate": 4.486482911479839e-06,
+      "loss": 0.7186,
+      "step": 283
+    },
+    {
+      "epoch": 0.9102564102564102,
+      "grad_norm": 1.3841599225997925,
+      "learning_rate": 4.184544329761009e-06,
+      "loss": 0.7316,
+      "step": 284
+    },
+    {
+      "epoch": 0.9134615384615384,
+      "grad_norm": 1.110377550125122,
+      "learning_rate": 3.892905960127546e-06,
+      "loss": 0.7166,
+      "step": 285
+    },
+    {
+      "epoch": 0.9166666666666666,
+      "grad_norm": 1.2394565343856812,
+      "learning_rate": 3.611599153858214e-06,
+      "loss": 0.6894,
+      "step": 286
+    },
+    {
+      "epoch": 0.9198717948717948,
+      "grad_norm": 2.2001726627349854,
+      "learning_rate": 3.3406541515832003e-06,
+      "loss": 0.8162,
+      "step": 287
+    },
+    {
+      "epoch": 0.9230769230769231,
+      "grad_norm": 1.696381688117981,
+      "learning_rate": 3.0801000800333877e-06,
+      "loss": 0.6764,
+      "step": 288
+    },
+    {
+      "epoch": 0.9262820512820513,
+      "grad_norm": 1.1135708093643188,
+      "learning_rate": 2.8299649489090475e-06,
+      "loss": 0.7059,
+      "step": 289
+    },
+    {
+      "epoch": 0.9294871794871795,
+      "grad_norm": 1.3587653636932373,
+      "learning_rate": 2.590275647868867e-06,
+      "loss": 0.7251,
+      "step": 290
+    },
+    {
+      "epoch": 0.9326923076923077,
+      "grad_norm": 1.686203956604004,
+      "learning_rate": 2.3610579436393e-06,
+      "loss": 0.6625,
+      "step": 291
+    },
+    {
+      "epoch": 0.9358974358974359,
+      "grad_norm": 1.2855104207992554,
+      "learning_rate": 2.1423364772445887e-06,
+      "loss": 0.7562,
+      "step": 292
+    },
+    {
+      "epoch": 0.9391025641025641,
+      "grad_norm": 1.6745336055755615,
+      "learning_rate": 1.9341347613579087e-06,
+      "loss": 0.7244,
+      "step": 293
+    },
+    {
+      "epoch": 0.9423076923076923,
+      "grad_norm": 1.2314362525939941,
+      "learning_rate": 1.7364751777736332e-06,
+      "loss": 0.6981,
+      "step": 294
+    },
+    {
+      "epoch": 0.9455128205128205,
+      "grad_norm": 0.9058342576026917,
+      "learning_rate": 1.5493789750014031e-06,
+      "loss": 0.7398,
+      "step": 295
+    },
+    {
+      "epoch": 0.9487179487179487,
+      "grad_norm": 1.4387075901031494,
+      "learning_rate": 1.3728662659818204e-06,
+      "loss": 0.6769,
+      "step": 296
+    },
+    {
+      "epoch": 0.9519230769230769,
+      "grad_norm": 1.3964595794677734,
+      "learning_rate": 1.2069560259243328e-06,
+      "loss": 0.685,
+      "step": 297
+    },
+    {
+      "epoch": 0.9551282051282052,
+      "grad_norm": 1.1776217222213745,
+      "learning_rate": 1.0516660902673448e-06,
+      "loss": 0.7934,
+      "step": 298
+    },
+    {
+      "epoch": 0.9583333333333334,
+      "grad_norm": 1.2884339094161987,
+      "learning_rate": 9.070131527609604e-07,
+      "loss": 0.6712,
+      "step": 299
+    },
+    {
+      "epoch": 0.9615384615384616,
+      "grad_norm": 1.7066468000411987,
+      "learning_rate": 7.730127636723539e-07,
+      "loss": 0.6243,
+      "step": 300
+    },
+    {
+      "epoch": 0.9647435897435898,
+      "grad_norm": 0.9889491200447083,
+      "learning_rate": 6.496793281141056e-07,
+      "loss": 0.6915,
+      "step": 301
+    },
+    {
+      "epoch": 0.967948717948718,
+      "grad_norm": 0.9342219233512878,
+      "learning_rate": 5.370261044956971e-07,
+      "loss": 0.7163,
+      "step": 302
+    },
+    {
+      "epoch": 0.9711538461538461,
+      "grad_norm": 1.2161084413528442,
+      "learning_rate": 4.3506520309813947e-07,
+      "loss": 0.6957,
+      "step": 303
+    },
+    {
+      "epoch": 0.9743589743589743,
+      "grad_norm": 1.4092503786087036,
+      "learning_rate": 3.4380758477219333e-07,
+      "loss": 0.7295,
+      "step": 304
+    },
+    {
+      "epoch": 0.9775641025641025,
+      "grad_norm": 1.5113911628723145,
+      "learning_rate": 2.6326305976001055e-07,
+      "loss": 0.6846,
+      "step": 305
+    },
+    {
+      "epoch": 0.9807692307692307,
+      "grad_norm": 1.2269924879074097,
+      "learning_rate": 1.9344028664056713e-07,
+      "loss": 0.7242,
+      "step": 306
+    },
+    {
+      "epoch": 0.9839743589743589,
+      "grad_norm": 1.3103538751602173,
+      "learning_rate": 1.3434677139885222e-07,
+      "loss": 0.6923,
+      "step": 307
+    },
+    {
+      "epoch": 0.9871794871794872,
+      "grad_norm": 1.182924747467041,
+      "learning_rate": 8.598886661895788e-08,
+      "loss": 0.693,
+      "step": 308
+    },
+    {
+      "epoch": 0.9903846153846154,
+      "grad_norm": 1.258489966392517,
+      "learning_rate": 4.837177080119215e-08,
+      "loss": 0.7017,
+      "step": 309
+    },
+    {
+      "epoch": 0.9935897435897436,
+      "grad_norm": 1.2968997955322266,
+      "learning_rate": 2.1499527803214846e-08,
+      "loss": 0.7148,
+      "step": 310
+    },
+    {
+      "epoch": 0.9967948717948718,
+      "grad_norm": 1.3392126560211182,
+      "learning_rate": 5.375026405352035e-09,
+      "loss": 0.7221,
+      "step": 311
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.7223619222640991,
+      "learning_rate": 0.0,
+      "loss": 0.5389,
+      "step": 312
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 312,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3978364611723264.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-312/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8381fa317ea32919a2925037ed9df681449cd986caf35e43c8ea133a79d4cc2
+size 6456

checkpoint-363/README.md

@@ -0,0 +1,202 @@
+---
+base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
+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 0.14.0

checkpoint-363/adapter_config.json

@@ -0,0 +1,37 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "TinyLlama/TinyLlama-1.1B-Chat-v1.0",
+  "bias": "none",
+  "eva_config": null,
+  "exclude_modules": null,
+  "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": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "down_proj",
+    "v_proj",
+    "k_proj",
+    "o_proj",
+    "up_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-363/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa819f5afaaf986d91b55dff514533e38e7e6f1208309d3e7737646b55f6c00c
+size 25271744

checkpoint-363/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc66ed55f5edb45f17b75f7a2e0a00db8a6b7afa50e8f5163e5c32a42c413ebe
+size 13685836

checkpoint-363/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63905123f21867a969842b3650d5858830a9f958f6d66a0ec0ae5af10dcfc123
+size 14244

checkpoint-363/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a3cdfee7f940157d7e68d9516390e12b7802eca5630eddbc7a6e04bf73df963
+size 1064

checkpoint-363/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
+  }
+}

checkpoint-363/tokenizer.model

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

checkpoint-363/tokenizer_config.json

@@ -0,0 +1,44 @@
+{
+  "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": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n'  + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "legacy": false,
+  "model_max_length": 2048,
+  "pad_token": "</s>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

checkpoint-363/trainer_state.json

@@ -0,0 +1,1300 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 363,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01652892561983471,
+      "grad_norm": 12.011792182922363,
+      "learning_rate": 2.857142857142857e-05,
+      "loss": 4.7518,
+      "step": 2
+    },
+    {
+      "epoch": 0.03305785123966942,
+      "grad_norm": 12.689871788024902,
+      "learning_rate": 5.714285714285714e-05,
+      "loss": 4.687,
+      "step": 4
+    },
+    {
+      "epoch": 0.049586776859504134,
+      "grad_norm": 11.848198890686035,
+      "learning_rate": 8.571428571428571e-05,
+      "loss": 4.4922,
+      "step": 6
+    },
+    {
+      "epoch": 0.06611570247933884,
+      "grad_norm": 10.378408432006836,
+      "learning_rate": 0.00011428571428571428,
+      "loss": 3.4839,
+      "step": 8
+    },
+    {
+      "epoch": 0.08264462809917356,
+      "grad_norm": 9.543920516967773,
+      "learning_rate": 0.00014285714285714287,
+      "loss": 2.4164,
+      "step": 10
+    },
+    {
+      "epoch": 0.09917355371900827,
+      "grad_norm": 5.602456092834473,
+      "learning_rate": 0.00017142857142857143,
+      "loss": 1.838,
+      "step": 12
+    },
+    {
+      "epoch": 0.11570247933884298,
+      "grad_norm": 1.7414193153381348,
+      "learning_rate": 0.0002,
+      "loss": 1.4404,
+      "step": 14
+    },
+    {
+      "epoch": 0.1322314049586777,
+      "grad_norm": 1.0191770792007446,
+      "learning_rate": 0.0001999910643210378,
+      "loss": 1.3474,
+      "step": 16
+    },
+    {
+      "epoch": 0.1487603305785124,
+      "grad_norm": 3.509352922439575,
+      "learning_rate": 0.0001999642588810784,
+      "loss": 1.3789,
+      "step": 18
+    },
+    {
+      "epoch": 0.1652892561983471,
+      "grad_norm": 2.426680088043213,
+      "learning_rate": 0.00019991958847061784,
+      "loss": 1.2245,
+      "step": 20
+    },
+    {
+      "epoch": 0.18181818181818182,
+      "grad_norm": 0.8060101270675659,
+      "learning_rate": 0.00019985706107286514,
+      "loss": 1.2259,
+      "step": 22
+    },
+    {
+      "epoch": 0.19834710743801653,
+      "grad_norm": 1.6215940713882446,
+      "learning_rate": 0.00019977668786231534,
+      "loss": 1.1992,
+      "step": 24
+    },
+    {
+      "epoch": 0.21487603305785125,
+      "grad_norm": 2.476259231567383,
+      "learning_rate": 0.0001996784832027525,
+      "loss": 1.2782,
+      "step": 26
+    },
+    {
+      "epoch": 0.23140495867768596,
+      "grad_norm": 2.04018235206604,
+      "learning_rate": 0.00019956246464468294,
+      "loss": 1.23,
+      "step": 28
+    },
+    {
+      "epoch": 0.24793388429752067,
+      "grad_norm": 1.8799017667770386,
+      "learning_rate": 0.00019942865292219838,
+      "loss": 1.2164,
+      "step": 30
+    },
+    {
+      "epoch": 0.2644628099173554,
+      "grad_norm": 1.2413148880004883,
+      "learning_rate": 0.00019927707194927066,
+      "loss": 1.2924,
+      "step": 32
+    },
+    {
+      "epoch": 0.2809917355371901,
+      "grad_norm": 1.8723937273025513,
+      "learning_rate": 0.000199107748815478,
+      "loss": 1.2302,
+      "step": 34
+    },
+    {
+      "epoch": 0.2975206611570248,
+      "grad_norm": 1.393110752105713,
+      "learning_rate": 0.00019892071378116376,
+      "loss": 1.2276,
+      "step": 36
+    },
+    {
+      "epoch": 0.3140495867768595,
+      "grad_norm": 1.1459721326828003,
+      "learning_rate": 0.0001987160002720283,
+      "loss": 1.1504,
+      "step": 38
+    },
+    {
+      "epoch": 0.3305785123966942,
+      "grad_norm": 1.4680942296981812,
+      "learning_rate": 0.00019849364487315558,
+      "loss": 1.1623,
+      "step": 40
+    },
+    {
+      "epoch": 0.34710743801652894,
+      "grad_norm": 1.8715866804122925,
+      "learning_rate": 0.0001982536873224748,
+      "loss": 1.2155,
+      "step": 42
+    },
+    {
+      "epoch": 0.36363636363636365,
+      "grad_norm": 0.871064305305481,
+      "learning_rate": 0.0001979961705036587,
+      "loss": 1.1594,
+      "step": 44
+    },
+    {
+      "epoch": 0.38016528925619836,
+      "grad_norm": 0.8239800930023193,
+      "learning_rate": 0.00019772114043845965,
+      "loss": 1.1501,
+      "step": 46
+    },
+    {
+      "epoch": 0.39669421487603307,
+      "grad_norm": 0.9587319493293762,
+      "learning_rate": 0.0001974286462784851,
+      "loss": 1.1195,
+      "step": 48
+    },
+    {
+      "epoch": 0.4132231404958678,
+      "grad_norm": 1.1645926237106323,
+      "learning_rate": 0.0001971187402964132,
+      "loss": 1.1417,
+      "step": 50
+    },
+    {
+      "epoch": 0.4297520661157025,
+      "grad_norm": 0.576813817024231,
+      "learning_rate": 0.00019679147787665126,
+      "loss": 1.1445,
+      "step": 52
+    },
+    {
+      "epoch": 0.4462809917355372,
+      "grad_norm": 1.0733133554458618,
+      "learning_rate": 0.00019644691750543767,
+      "loss": 1.0979,
+      "step": 54
+    },
+    {
+      "epoch": 0.4628099173553719,
+      "grad_norm": 0.5801639556884766,
+      "learning_rate": 0.00019608512076038962,
+      "loss": 1.0977,
+      "step": 56
+    },
+    {
+      "epoch": 0.4793388429752066,
+      "grad_norm": 1.6796538829803467,
+      "learning_rate": 0.00019570615229949842,
+      "loss": 1.1925,
+      "step": 58
+    },
+    {
+      "epoch": 0.49586776859504134,
+      "grad_norm": 1.0563887357711792,
+      "learning_rate": 0.00019531007984957408,
+      "loss": 1.0657,
+      "step": 60
+    },
+    {
+      "epoch": 0.512396694214876,
+      "grad_norm": 0.9109811186790466,
+      "learning_rate": 0.00019489697419414182,
+      "loss": 1.1098,
+      "step": 62
+    },
+    {
+      "epoch": 0.5289256198347108,
+      "grad_norm": 0.7321667671203613,
+      "learning_rate": 0.0001944669091607919,
+      "loss": 1.0929,
+      "step": 64
+    },
+    {
+      "epoch": 0.5454545454545454,
+      "grad_norm": 0.685366690158844,
+      "learning_rate": 0.00019401996160798573,
+      "loss": 1.1242,
+      "step": 66
+    },
+    {
+      "epoch": 0.5619834710743802,
+      "grad_norm": 0.8959838151931763,
+      "learning_rate": 0.0001935562114113202,
+      "loss": 1.181,
+      "step": 68
+    },
+    {
+      "epoch": 0.5785123966942148,
+      "grad_norm": 0.9717262983322144,
+      "learning_rate": 0.00019307574144925287,
+      "loss": 1.2295,
+      "step": 70
+    },
+    {
+      "epoch": 0.5950413223140496,
+      "grad_norm": 1.0358582735061646,
+      "learning_rate": 0.00019257863758829035,
+      "loss": 1.1431,
+      "step": 72
+    },
+    {
+      "epoch": 0.6115702479338843,
+      "grad_norm": 0.7998526096343994,
+      "learning_rate": 0.00019206498866764288,
+      "loss": 1.1032,
+      "step": 74
+    },
+    {
+      "epoch": 0.628099173553719,
+      "grad_norm": 1.1496188640594482,
+      "learning_rate": 0.0001915348864833476,
+      "loss": 1.057,
+      "step": 76
+    },
+    {
+      "epoch": 0.6446280991735537,
+      "grad_norm": 0.652406632900238,
+      "learning_rate": 0.00019098842577186314,
+      "loss": 1.146,
+      "step": 78
+    },
+    {
+      "epoch": 0.6611570247933884,
+      "grad_norm": 0.9454944729804993,
+      "learning_rate": 0.00019042570419313925,
+      "loss": 1.1543,
+      "step": 80
+    },
+    {
+      "epoch": 0.6776859504132231,
+      "grad_norm": 0.7456652522087097,
+      "learning_rate": 0.00018984682231316333,
+      "loss": 1.1189,
+      "step": 82
+    },
+    {
+      "epoch": 0.6942148760330579,
+      "grad_norm": 0.7312512397766113,
+      "learning_rate": 0.00018925188358598813,
+      "loss": 1.0873,
+      "step": 84
+    },
+    {
+      "epoch": 0.7107438016528925,
+      "grad_norm": 0.8474765419960022,
+      "learning_rate": 0.000188640994335243,
+      "loss": 1.1698,
+      "step": 86
+    },
+    {
+      "epoch": 0.7272727272727273,
+      "grad_norm": 0.6979633569717407,
+      "learning_rate": 0.0001880142637351325,
+      "loss": 1.1417,
+      "step": 88
+    },
+    {
+      "epoch": 0.743801652892562,
+      "grad_norm": 0.5989161133766174,
+      "learning_rate": 0.00018737180379092537,
+      "loss": 1.0479,
+      "step": 90
+    },
+    {
+      "epoch": 0.7603305785123967,
+      "grad_norm": 0.5765272378921509,
+      "learning_rate": 0.00018671372931893773,
+      "loss": 1.1336,
+      "step": 92
+    },
+    {
+      "epoch": 0.7768595041322314,
+      "grad_norm": 0.6709849834442139,
+      "learning_rate": 0.00018604015792601396,
+      "loss": 1.1157,
+      "step": 94
+    },
+    {
+      "epoch": 0.7933884297520661,
+      "grad_norm": 0.8181343674659729,
+      "learning_rate": 0.00018535120998850848,
+      "loss": 1.0927,
+      "step": 96
+    },
+    {
+      "epoch": 0.8099173553719008,
+      "grad_norm": 0.6146332621574402,
+      "learning_rate": 0.00018464700863077312,
+      "loss": 1.0739,
+      "step": 98
+    },
+    {
+      "epoch": 0.8264462809917356,
+      "grad_norm": 0.9904415011405945,
+      "learning_rate": 0.00018392767970315313,
+      "loss": 1.0331,
+      "step": 100
+    },
+    {
+      "epoch": 0.8429752066115702,
+      "grad_norm": 0.6186695694923401,
+      "learning_rate": 0.0001831933517594957,
+      "loss": 1.0513,
+      "step": 102
+    },
+    {
+      "epoch": 0.859504132231405,
+      "grad_norm": 1.1912785768508911,
+      "learning_rate": 0.00018244415603417603,
+      "loss": 1.1567,
+      "step": 104
+    },
+    {
+      "epoch": 0.8760330578512396,
+      "grad_norm": 1.3681318759918213,
+      "learning_rate": 0.00018168022641864377,
+      "loss": 1.1497,
+      "step": 106
+    },
+    {
+      "epoch": 0.8925619834710744,
+      "grad_norm": 0.619476318359375,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 1.1546,
+      "step": 108
+    },
+    {
+      "epoch": 0.9090909090909091,
+      "grad_norm": 0.7421219348907471,
+      "learning_rate": 0.00018010871422407236,
+      "loss": 1.1458,
+      "step": 110
+    },
+    {
+      "epoch": 0.9256198347107438,
+      "grad_norm": 0.6569286584854126,
+      "learning_rate": 0.00017930141249560233,
+      "loss": 1.12,
+      "step": 112
+    },
+    {
+      "epoch": 0.9421487603305785,
+      "grad_norm": 0.4168110191822052,
+      "learning_rate": 0.0001784799385278661,
+      "loss": 1.1682,
+      "step": 114
+    },
+    {
+      "epoch": 0.9586776859504132,
+      "grad_norm": 0.5620162487030029,
+      "learning_rate": 0.00017764443912941672,
+      "loss": 1.1828,
+      "step": 116
+    },
+    {
+      "epoch": 0.9752066115702479,
+      "grad_norm": 0.8095484375953674,
+      "learning_rate": 0.00017679506361534215,
+      "loss": 1.1953,
+      "step": 118
+    },
+    {
+      "epoch": 0.9917355371900827,
+      "grad_norm": 0.7646257281303406,
+      "learning_rate": 0.0001759319637805806,
+      "loss": 1.2148,
+      "step": 120
+    },
+    {
+      "epoch": 1.0082644628099173,
+      "grad_norm": 0.5254501104354858,
+      "learning_rate": 0.00017505529387279277,
+      "loss": 1.1359,
+      "step": 122
+    },
+    {
+      "epoch": 1.024793388429752,
+      "grad_norm": 0.6001765727996826,
+      "learning_rate": 0.00017416521056479577,
+      "loss": 1.1336,
+      "step": 124
+    },
+    {
+      "epoch": 1.0413223140495869,
+      "grad_norm": 0.35407504439353943,
+      "learning_rate": 0.00017326187292656333,
+      "loss": 1.1833,
+      "step": 126
+    },
+    {
+      "epoch": 1.0578512396694215,
+      "grad_norm": 0.414528489112854,
+      "learning_rate": 0.00017234544239679806,
+      "loss": 1.1301,
+      "step": 128
+    },
+    {
+      "epoch": 1.0743801652892562,
+      "grad_norm": 0.46355852484703064,
+      "learning_rate": 0.00017141608275408006,
+      "loss": 1.213,
+      "step": 130
+    },
+    {
+      "epoch": 1.0909090909090908,
+      "grad_norm": 0.5040593147277832,
+      "learning_rate": 0.00017047396008759754,
+      "loss": 1.132,
+      "step": 132
+    },
+    {
+      "epoch": 1.1074380165289257,
+      "grad_norm": 0.4813704192638397,
+      "learning_rate": 0.00016951924276746425,
+      "loss": 1.0831,
+      "step": 134
+    },
+    {
+      "epoch": 1.1239669421487604,
+      "grad_norm": 0.5174686312675476,
+      "learning_rate": 0.00016855210141462963,
+      "loss": 1.0514,
+      "step": 136
+    },
+    {
+      "epoch": 1.140495867768595,
+      "grad_norm": 0.4712466299533844,
+      "learning_rate": 0.00016757270887038654,
+      "loss": 1.1334,
+      "step": 138
+    },
+    {
+      "epoch": 1.1570247933884297,
+      "grad_norm": 0.5912173390388489,
+      "learning_rate": 0.00016658124016548197,
+      "loss": 1.1011,
+      "step": 140
+    },
+    {
+      "epoch": 1.1735537190082646,
+      "grad_norm": 0.6392802000045776,
+      "learning_rate": 0.00016557787248883696,
+      "loss": 1.1361,
+      "step": 142
+    },
+    {
+      "epoch": 1.1900826446280992,
+      "grad_norm": 0.7376368045806885,
+      "learning_rate": 0.00016456278515588024,
+      "loss": 1.109,
+      "step": 144
+    },
+    {
+      "epoch": 1.2066115702479339,
+      "grad_norm": 0.5020875930786133,
+      "learning_rate": 0.00016353615957650236,
+      "loss": 1.0925,
+      "step": 146
+    },
+    {
+      "epoch": 1.2231404958677685,
+      "grad_norm": 0.8081740736961365,
+      "learning_rate": 0.00016249817922263517,
+      "loss": 1.047,
+      "step": 148
+    },
+    {
+      "epoch": 1.2396694214876034,
+      "grad_norm": 0.6371219754219055,
+      "learning_rate": 0.00016144902959546286,
+      "loss": 1.113,
+      "step": 150
+    },
+    {
+      "epoch": 1.256198347107438,
+      "grad_norm": 0.7588189840316772,
+      "learning_rate": 0.00016038889819227045,
+      "loss": 1.1179,
+      "step": 152
+    },
+    {
+      "epoch": 1.2727272727272727,
+      "grad_norm": 0.6286205053329468,
+      "learning_rate": 0.00015931797447293552,
+      "loss": 1.1209,
+      "step": 154
+    },
+    {
+      "epoch": 1.2892561983471074,
+      "grad_norm": 0.797656238079071,
+      "learning_rate": 0.00015823644982606905,
+      "loss": 1.1698,
+      "step": 156
+    },
+    {
+      "epoch": 1.3057851239669422,
+      "grad_norm": 0.5368632078170776,
+      "learning_rate": 0.00015714451753481168,
+      "loss": 1.1973,
+      "step": 158
+    },
+    {
+      "epoch": 1.322314049586777,
+      "grad_norm": 0.4135212302207947,
+      "learning_rate": 0.00015604237274229147,
+      "loss": 1.1452,
+      "step": 160
+    },
+    {
+      "epoch": 1.3388429752066116,
+      "grad_norm": 0.5289668440818787,
+      "learning_rate": 0.00015493021241674918,
+      "loss": 1.1954,
+      "step": 162
+    },
+    {
+      "epoch": 1.3553719008264462,
+      "grad_norm": 0.4092061221599579,
+      "learning_rate": 0.00015380823531633729,
+      "loss": 1.1226,
+      "step": 164
+    },
+    {
+      "epoch": 1.3719008264462809,
+      "grad_norm": 0.7049645781517029,
+      "learning_rate": 0.00015267664195359917,
+      "loss": 1.0948,
+      "step": 166
+    },
+    {
+      "epoch": 1.3884297520661157,
+      "grad_norm": 0.47164198756217957,
+      "learning_rate": 0.00015153563455963499,
+      "loss": 1.0977,
+      "step": 168
+    },
+    {
+      "epoch": 1.4049586776859504,
+      "grad_norm": 0.7871695160865784,
+      "learning_rate": 0.00015038541704796003,
+      "loss": 1.1674,
+      "step": 170
+    },
+    {
+      "epoch": 1.421487603305785,
+      "grad_norm": 0.5381121635437012,
+      "learning_rate": 0.00014922619497806277,
+      "loss": 1.1415,
+      "step": 172
+    },
+    {
+      "epoch": 1.43801652892562,
+      "grad_norm": 0.39419299364089966,
+      "learning_rate": 0.00014805817551866838,
+      "loss": 1.0747,
+      "step": 174
+    },
+    {
+      "epoch": 1.4545454545454546,
+      "grad_norm": 0.38382914662361145,
+      "learning_rate": 0.00014688156741071514,
+      "loss": 1.1278,
+      "step": 176
+    },
+    {
+      "epoch": 1.4710743801652892,
+      "grad_norm": 0.32674962282180786,
+      "learning_rate": 0.00014569658093004935,
+      "loss": 0.9774,
+      "step": 178
+    },
+    {
+      "epoch": 1.487603305785124,
+      "grad_norm": 0.5443088412284851,
+      "learning_rate": 0.00014450342784984633,
+      "loss": 1.034,
+      "step": 180
+    },
+    {
+      "epoch": 1.5041322314049586,
+      "grad_norm": 0.6682401895523071,
+      "learning_rate": 0.00014330232140276366,
+      "loss": 1.1732,
+      "step": 182
+    },
+    {
+      "epoch": 1.5206611570247934,
+      "grad_norm": 0.5696044564247131,
+      "learning_rate": 0.0001420934762428335,
+      "loss": 1.0384,
+      "step": 184
+    },
+    {
+      "epoch": 1.537190082644628,
+      "grad_norm": 0.6782551407814026,
+      "learning_rate": 0.0001408771084071012,
+      "loss": 1.1107,
+      "step": 186
+    },
+    {
+      "epoch": 1.553719008264463,
+      "grad_norm": 0.8336123824119568,
+      "learning_rate": 0.00013965343527701628,
+      "loss": 1.0737,
+      "step": 188
+    },
+    {
+      "epoch": 1.5702479338842976,
+      "grad_norm": 0.539226233959198,
+      "learning_rate": 0.00013842267553958371,
+      "loss": 1.1665,
+      "step": 190
+    },
+    {
+      "epoch": 1.5867768595041323,
+      "grad_norm": 0.566620409488678,
+      "learning_rate": 0.00013718504914828135,
+      "loss": 1.1333,
+      "step": 192
+    },
+    {
+      "epoch": 1.603305785123967,
+      "grad_norm": 0.4735005795955658,
+      "learning_rate": 0.00013594077728375128,
+      "loss": 1.1709,
+      "step": 194
+    },
+    {
+      "epoch": 1.6198347107438016,
+      "grad_norm": 0.534383237361908,
+      "learning_rate": 0.00013469008231427207,
+      "loss": 1.0783,
+      "step": 196
+    },
+    {
+      "epoch": 1.6363636363636362,
+      "grad_norm": 0.8410363793373108,
+      "learning_rate": 0.0001334331877560182,
+      "loss": 1.0708,
+      "step": 198
+    },
+    {
+      "epoch": 1.6528925619834711,
+      "grad_norm": 0.6392219662666321,
+      "learning_rate": 0.00013217031823311488,
+      "loss": 1.0329,
+      "step": 200
+    },
+    {
+      "epoch": 1.6694214876033058,
+      "grad_norm": 0.5770404934883118,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 1.0404,
+      "step": 202
+    },
+    {
+      "epoch": 1.6859504132231407,
+      "grad_norm": 0.6814575791358948,
+      "learning_rate": 0.00012962755808856342,
+      "loss": 1.0702,
+      "step": 204
+    },
+    {
+      "epoch": 1.7024793388429753,
+      "grad_norm": 0.673312783241272,
+      "learning_rate": 0.0001283481218926818,
+      "loss": 1.0529,
+      "step": 206
+    },
+    {
+      "epoch": 1.71900826446281,
+      "grad_norm": 0.6180073618888855,
+      "learning_rate": 0.0001270636195024719,
+      "loss": 1.0257,
+      "step": 208
+    },
+    {
+      "epoch": 1.7355371900826446,
+      "grad_norm": 0.5565724968910217,
+      "learning_rate": 0.00012577428047595344,
+      "loss": 1.1102,
+      "step": 210
+    },
+    {
+      "epoch": 1.7520661157024793,
+      "grad_norm": 0.5586270689964294,
+      "learning_rate": 0.00012448033523551865,
+      "loss": 1.0277,
+      "step": 212
+    },
+    {
+      "epoch": 1.768595041322314,
+      "grad_norm": 0.542448878288269,
+      "learning_rate": 0.00012318201502675285,
+      "loss": 1.0988,
+      "step": 214
+    },
+    {
+      "epoch": 1.7851239669421488,
+      "grad_norm": 0.513042151927948,
+      "learning_rate": 0.0001218795518771075,
+      "loss": 1.0828,
+      "step": 216
+    },
+    {
+      "epoch": 1.8016528925619835,
+      "grad_norm": 0.7613060474395752,
+      "learning_rate": 0.00012057317855443395,
+      "loss": 1.1962,
+      "step": 218
+    },
+    {
+      "epoch": 1.8181818181818183,
+      "grad_norm": 0.7522129416465759,
+      "learning_rate": 0.00011926312852538455,
+      "loss": 1.1339,
+      "step": 220
+    },
+    {
+      "epoch": 1.834710743801653,
+      "grad_norm": 0.4655594825744629,
+      "learning_rate": 0.00011794963591368893,
+      "loss": 1.0967,
+      "step": 222
+    },
+    {
+      "epoch": 1.8512396694214877,
+      "grad_norm": 0.5036570429801941,
+      "learning_rate": 0.00011663293545831302,
+      "loss": 1.0361,
+      "step": 224
+    },
+    {
+      "epoch": 1.8677685950413223,
+      "grad_norm": 0.43016380071640015,
+      "learning_rate": 0.00011531326247150803,
+      "loss": 1.1281,
+      "step": 226
+    },
+    {
+      "epoch": 1.884297520661157,
+      "grad_norm": 0.5184316635131836,
+      "learning_rate": 0.00011399085279675687,
+      "loss": 1.2083,
+      "step": 228
+    },
+    {
+      "epoch": 1.9008264462809916,
+      "grad_norm": 0.6556355357170105,
+      "learning_rate": 0.0001126659427666257,
+      "loss": 1.0266,
+      "step": 230
+    },
+    {
+      "epoch": 1.9173553719008265,
+      "grad_norm": 0.515681803226471,
+      "learning_rate": 0.00011133876916052821,
+      "loss": 1.0472,
+      "step": 232
+    },
+    {
+      "epoch": 1.9338842975206612,
+      "grad_norm": 0.4592064321041107,
+      "learning_rate": 0.00011000956916240985,
+      "loss": 1.054,
+      "step": 234
+    },
+    {
+      "epoch": 1.950413223140496,
+      "grad_norm": 0.5623230338096619,
+      "learning_rate": 0.00010867858031835975,
+      "loss": 1.1571,
+      "step": 236
+    },
+    {
+      "epoch": 1.9669421487603307,
+      "grad_norm": 0.5241667032241821,
+      "learning_rate": 0.00010734604049415822,
+      "loss": 1.0985,
+      "step": 238
+    },
+    {
+      "epoch": 1.9834710743801653,
+      "grad_norm": 0.54905104637146,
+      "learning_rate": 0.00010601218783276672,
+      "loss": 1.1088,
+      "step": 240
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.8823345303535461,
+      "learning_rate": 0.00010467726071176853,
+      "loss": 1.0991,
+      "step": 242
+    },
+    {
+      "epoch": 2.0165289256198347,
+      "grad_norm": 0.5789780020713806,
+      "learning_rate": 0.00010334149770076747,
+      "loss": 1.1429,
+      "step": 244
+    },
+    {
+      "epoch": 2.0330578512396693,
+      "grad_norm": 0.6136715412139893,
+      "learning_rate": 0.00010200513751875227,
+      "loss": 1.0347,
+      "step": 246
+    },
+    {
+      "epoch": 2.049586776859504,
+      "grad_norm": 0.6462894082069397,
+      "learning_rate": 0.00010066841899143425,
+      "loss": 1.1008,
+      "step": 248
+    },
+    {
+      "epoch": 2.0661157024793386,
+      "grad_norm": 0.7272156476974487,
+      "learning_rate": 9.93315810085658e-05,
+      "loss": 1.1642,
+      "step": 250
+    },
+    {
+      "epoch": 2.0826446280991737,
+      "grad_norm": 0.5664356350898743,
+      "learning_rate": 9.799486248124775e-05,
+      "loss": 1.0799,
+      "step": 252
+    },
+    {
+      "epoch": 2.0991735537190084,
+      "grad_norm": 0.559697687625885,
+      "learning_rate": 9.665850229923258e-05,
+      "loss": 1.0536,
+      "step": 254
+    },
+    {
+      "epoch": 2.115702479338843,
+      "grad_norm": 0.7208287715911865,
+      "learning_rate": 9.532273928823151e-05,
+      "loss": 1.0595,
+      "step": 256
+    },
+    {
+      "epoch": 2.1322314049586777,
+      "grad_norm": 0.6985677480697632,
+      "learning_rate": 9.398781216723331e-05,
+      "loss": 1.0626,
+      "step": 258
+    },
+    {
+      "epoch": 2.1487603305785123,
+      "grad_norm": 0.7583006024360657,
+      "learning_rate": 9.26539595058418e-05,
+      "loss": 0.9919,
+      "step": 260
+    },
+    {
+      "epoch": 2.165289256198347,
+      "grad_norm": 0.6283029317855835,
+      "learning_rate": 9.132141968164026e-05,
+      "loss": 1.1292,
+      "step": 262
+    },
+    {
+      "epoch": 2.1818181818181817,
+      "grad_norm": 1.4162311553955078,
+      "learning_rate": 8.999043083759017e-05,
+      "loss": 1.1834,
+      "step": 264
+    },
+    {
+      "epoch": 2.1983471074380168,
+      "grad_norm": 0.5169870853424072,
+      "learning_rate": 8.866123083947182e-05,
+      "loss": 1.049,
+      "step": 266
+    },
+    {
+      "epoch": 2.2148760330578514,
+      "grad_norm": 0.9136308431625366,
+      "learning_rate": 8.733405723337432e-05,
+      "loss": 1.1336,
+      "step": 268
+    },
+    {
+      "epoch": 2.231404958677686,
+      "grad_norm": 0.6882078647613525,
+      "learning_rate": 8.600914720324316e-05,
+      "loss": 1.0953,
+      "step": 270
+    },
+    {
+      "epoch": 2.2479338842975207,
+      "grad_norm": 0.505447506904602,
+      "learning_rate": 8.4686737528492e-05,
+      "loss": 1.1014,
+      "step": 272
+    },
+    {
+      "epoch": 2.2644628099173554,
+      "grad_norm": 0.40685173869132996,
+      "learning_rate": 8.336706454168701e-05,
+      "loss": 1.0878,
+      "step": 274
+    },
+    {
+      "epoch": 2.28099173553719,
+      "grad_norm": 0.5715451836585999,
+      "learning_rate": 8.20503640863111e-05,
+      "loss": 1.0555,
+      "step": 276
+    },
+    {
+      "epoch": 2.2975206611570247,
+      "grad_norm": 0.5256667733192444,
+      "learning_rate": 8.073687147461547e-05,
+      "loss": 1.0678,
+      "step": 278
+    },
+    {
+      "epoch": 2.3140495867768593,
+      "grad_norm": 0.46319133043289185,
+      "learning_rate": 7.942682144556604e-05,
+      "loss": 1.0699,
+      "step": 280
+    },
+    {
+      "epoch": 2.330578512396694,
+      "grad_norm": 0.6000749468803406,
+      "learning_rate": 7.812044812289249e-05,
+      "loss": 1.1389,
+      "step": 282
+    },
+    {
+      "epoch": 2.347107438016529,
+      "grad_norm": 0.5024062395095825,
+      "learning_rate": 7.681798497324716e-05,
+      "loss": 1.1033,
+      "step": 284
+    },
+    {
+      "epoch": 2.3636363636363638,
+      "grad_norm": 0.6761860251426697,
+      "learning_rate": 7.55196647644814e-05,
+      "loss": 1.0665,
+      "step": 286
+    },
+    {
+      "epoch": 2.3801652892561984,
+      "grad_norm": 0.7175805568695068,
+      "learning_rate": 7.422571952404663e-05,
+      "loss": 1.0511,
+      "step": 288
+    },
+    {
+      "epoch": 2.396694214876033,
+      "grad_norm": 0.6883595585823059,
+      "learning_rate": 7.293638049752812e-05,
+      "loss": 1.0765,
+      "step": 290
+    },
+    {
+      "epoch": 2.4132231404958677,
+      "grad_norm": 0.6382430791854858,
+      "learning_rate": 7.165187810731823e-05,
+      "loss": 1.1036,
+      "step": 292
+    },
+    {
+      "epoch": 2.4297520661157024,
+      "grad_norm": 0.9323483109474182,
+      "learning_rate": 7.037244191143661e-05,
+      "loss": 1.1113,
+      "step": 294
+    },
+    {
+      "epoch": 2.446280991735537,
+      "grad_norm": 0.9768907427787781,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 1.0983,
+      "step": 296
+    },
+    {
+      "epoch": 2.462809917355372,
+      "grad_norm": 0.6783613562583923,
+      "learning_rate": 6.782968176688514e-05,
+      "loss": 1.1141,
+      "step": 298
+    },
+    {
+      "epoch": 2.479338842975207,
+      "grad_norm": 0.753887951374054,
+      "learning_rate": 6.656681224398183e-05,
+      "loss": 1.1234,
+      "step": 300
+    },
+    {
+      "epoch": 2.4958677685950414,
+      "grad_norm": 0.6788628697395325,
+      "learning_rate": 6.530991768572794e-05,
+      "loss": 1.0407,
+      "step": 302
+    },
+    {
+      "epoch": 2.512396694214876,
+      "grad_norm": 0.6727221012115479,
+      "learning_rate": 6.405922271624874e-05,
+      "loss": 1.091,
+      "step": 304
+    },
+    {
+      "epoch": 2.5289256198347108,
+      "grad_norm": 0.7418019771575928,
+      "learning_rate": 6.281495085171869e-05,
+      "loss": 1.0884,
+      "step": 306
+    },
+    {
+      "epoch": 2.5454545454545454,
+      "grad_norm": 0.7063189148902893,
+      "learning_rate": 6.15773244604163e-05,
+      "loss": 1.0218,
+      "step": 308
+    },
+    {
+      "epoch": 2.56198347107438,
+      "grad_norm": 1.0706840753555298,
+      "learning_rate": 6.0346564722983736e-05,
+      "loss": 1.0873,
+      "step": 310
+    },
+    {
+      "epoch": 2.5785123966942147,
+      "grad_norm": 0.683253288269043,
+      "learning_rate": 5.912289159289883e-05,
+      "loss": 1.0346,
+      "step": 312
+    },
+    {
+      "epoch": 2.5950413223140494,
+      "grad_norm": 0.5816308856010437,
+      "learning_rate": 5.790652375716652e-05,
+      "loss": 1.0113,
+      "step": 314
+    },
+    {
+      "epoch": 2.6115702479338845,
+      "grad_norm": 0.7935141324996948,
+      "learning_rate": 5.6697678597236356e-05,
+      "loss": 1.1771,
+      "step": 316
+    },
+    {
+      "epoch": 2.628099173553719,
+      "grad_norm": 0.6827735900878906,
+      "learning_rate": 5.549657215015367e-05,
+      "loss": 1.0899,
+      "step": 318
+    },
+    {
+      "epoch": 2.644628099173554,
+      "grad_norm": 0.5408580899238586,
+      "learning_rate": 5.430341906995065e-05,
+      "loss": 1.1056,
+      "step": 320
+    },
+    {
+      "epoch": 2.6611570247933884,
+      "grad_norm": 0.6996527910232544,
+      "learning_rate": 5.31184325892849e-05,
+      "loss": 1.0494,
+      "step": 322
+    },
+    {
+      "epoch": 2.677685950413223,
+      "grad_norm": 0.6700767874717712,
+      "learning_rate": 5.1941824481331626e-05,
+      "loss": 1.1206,
+      "step": 324
+    },
+    {
+      "epoch": 2.6942148760330578,
+      "grad_norm": 0.7690112590789795,
+      "learning_rate": 5.077380502193725e-05,
+      "loss": 1.1541,
+      "step": 326
+    },
+    {
+      "epoch": 2.7107438016528924,
+      "grad_norm": 0.7921670079231262,
+      "learning_rate": 4.961458295203999e-05,
+      "loss": 1.0684,
+      "step": 328
+    },
+    {
+      "epoch": 2.7272727272727275,
+      "grad_norm": 0.6989784240722656,
+      "learning_rate": 4.8464365440365044e-05,
+      "loss": 1.0097,
+      "step": 330
+    },
+    {
+      "epoch": 2.7438016528925617,
+      "grad_norm": 0.6038585901260376,
+      "learning_rate": 4.7323358046400844e-05,
+      "loss": 1.0751,
+      "step": 332
+    },
+    {
+      "epoch": 2.760330578512397,
+      "grad_norm": 0.8160024881362915,
+      "learning_rate": 4.6191764683662744e-05,
+      "loss": 0.9734,
+      "step": 334
+    },
+    {
+      "epoch": 2.7768595041322315,
+      "grad_norm": 0.7741029858589172,
+      "learning_rate": 4.506978758325081e-05,
+      "loss": 1.1186,
+      "step": 336
+    },
+    {
+      "epoch": 2.793388429752066,
+      "grad_norm": 0.8177542090415955,
+      "learning_rate": 4.395762725770852e-05,
+      "loss": 1.1538,
+      "step": 338
+    },
+    {
+      "epoch": 2.809917355371901,
+      "grad_norm": 0.7617602944374084,
+      "learning_rate": 4.285548246518837e-05,
+      "loss": 1.1162,
+      "step": 340
+    },
+    {
+      "epoch": 2.8264462809917354,
+      "grad_norm": 0.6426255106925964,
+      "learning_rate": 4.176355017393099e-05,
+      "loss": 1.0404,
+      "step": 342
+    },
+    {
+      "epoch": 2.84297520661157,
+      "grad_norm": 0.6394379138946533,
+      "learning_rate": 4.0682025527064486e-05,
+      "loss": 1.1107,
+      "step": 344
+    },
+    {
+      "epoch": 2.8595041322314048,
+      "grad_norm": 0.6632633209228516,
+      "learning_rate": 3.961110180772955e-05,
+      "loss": 1.1085,
+      "step": 346
+    },
+    {
+      "epoch": 2.87603305785124,
+      "grad_norm": 0.5437737703323364,
+      "learning_rate": 3.8550970404537144e-05,
+      "loss": 1.0072,
+      "step": 348
+    },
+    {
+      "epoch": 2.8925619834710745,
+      "grad_norm": 0.8178601264953613,
+      "learning_rate": 3.750182077736486e-05,
+      "loss": 1.0606,
+      "step": 350
+    },
+    {
+      "epoch": 2.909090909090909,
+      "grad_norm": 0.8268756866455078,
+      "learning_rate": 3.646384042349764e-05,
+      "loss": 0.9642,
+      "step": 352
+    },
+    {
+      "epoch": 2.925619834710744,
+      "grad_norm": 1.064460277557373,
+      "learning_rate": 3.543721484411976e-05,
+      "loss": 1.0881,
+      "step": 354
+    },
+    {
+      "epoch": 2.9421487603305785,
+      "grad_norm": 0.7875952124595642,
+      "learning_rate": 3.442212751116305e-05,
+      "loss": 1.0141,
+      "step": 356
+    },
+    {
+      "epoch": 2.958677685950413,
+      "grad_norm": 0.6071433424949646,
+      "learning_rate": 3.3418759834518056e-05,
+      "loss": 1.0692,
+      "step": 358
+    },
+    {
+      "epoch": 2.975206611570248,
+      "grad_norm": 0.6311193704605103,
+      "learning_rate": 3.24272911296135e-05,
+      "loss": 0.9481,
+      "step": 360
+    },
+    {
+      "epoch": 2.991735537190083,
+      "grad_norm": 0.7501534223556519,
+      "learning_rate": 3.1447898585370384e-05,
+      "loss": 1.1183,
+      "step": 362
+    }
+  ],
+  "logging_steps": 2,
+  "max_steps": 484,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 6858422416834560.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-363/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41c7adf20314e4e98465f263bb56b062cceb30de0bf8fa4d85b668c720a84502
+size 6456

checkpoint-484/README.md

@@ -0,0 +1,202 @@
+---
+base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
+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 0.14.0

checkpoint-484/adapter_config.json

@@ -0,0 +1,37 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "TinyLlama/TinyLlama-1.1B-Chat-v1.0",
+  "bias": "none",
+  "eva_config": null,
+  "exclude_modules": null,
+  "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": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "down_proj",
+    "v_proj",
+    "k_proj",
+    "o_proj",
+    "up_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-484/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7fe424a4de02d7bbd037f66fdfa874457df9673741824c6c8c7dce80527da55c
+size 25271744

checkpoint-484/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f83c5d25655b3897a8e1bace7994f0312ba565ffe9c2f2c15888cec7bfac0686
+size 13685836

checkpoint-484/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef0fa4de13c24e8107d077d830c61aa7c6410c4cd4d9f472aaeb4a44800c77ff
+size 14244

checkpoint-484/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c16c78b962934cb2d4fb81e707fc4c46873b51a6b49f76873cdca14ac338be13
+size 1064

checkpoint-484/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
+  }
+}

checkpoint-484/tokenizer.model

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

checkpoint-484/tokenizer_config.json

@@ -0,0 +1,44 @@
+{
+  "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": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n'  + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "legacy": false,
+  "model_max_length": 2048,
+  "pad_token": "</s>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

checkpoint-484/trainer_state.json

@@ -0,0 +1,1727 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 484,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01652892561983471,
+      "grad_norm": 12.011792182922363,
+      "learning_rate": 2.857142857142857e-05,
+      "loss": 4.7518,
+      "step": 2
+    },
+    {
+      "epoch": 0.03305785123966942,
+      "grad_norm": 12.689871788024902,
+      "learning_rate": 5.714285714285714e-05,
+      "loss": 4.687,
+      "step": 4
+    },
+    {
+      "epoch": 0.049586776859504134,
+      "grad_norm": 11.848198890686035,
+      "learning_rate": 8.571428571428571e-05,
+      "loss": 4.4922,
+      "step": 6
+    },
+    {
+      "epoch": 0.06611570247933884,
+      "grad_norm": 10.378408432006836,
+      "learning_rate": 0.00011428571428571428,
+      "loss": 3.4839,
+      "step": 8
+    },
+    {
+      "epoch": 0.08264462809917356,
+      "grad_norm": 9.543920516967773,
+      "learning_rate": 0.00014285714285714287,
+      "loss": 2.4164,
+      "step": 10
+    },
+    {
+      "epoch": 0.09917355371900827,
+      "grad_norm": 5.602456092834473,
+      "learning_rate": 0.00017142857142857143,
+      "loss": 1.838,
+      "step": 12
+    },
+    {
+      "epoch": 0.11570247933884298,
+      "grad_norm": 1.7414193153381348,
+      "learning_rate": 0.0002,
+      "loss": 1.4404,
+      "step": 14
+    },
+    {
+      "epoch": 0.1322314049586777,
+      "grad_norm": 1.0191770792007446,
+      "learning_rate": 0.0001999910643210378,
+      "loss": 1.3474,
+      "step": 16
+    },
+    {
+      "epoch": 0.1487603305785124,
+      "grad_norm": 3.509352922439575,
+      "learning_rate": 0.0001999642588810784,
+      "loss": 1.3789,
+      "step": 18
+    },
+    {
+      "epoch": 0.1652892561983471,
+      "grad_norm": 2.426680088043213,
+      "learning_rate": 0.00019991958847061784,
+      "loss": 1.2245,
+      "step": 20
+    },
+    {
+      "epoch": 0.18181818181818182,
+      "grad_norm": 0.8060101270675659,
+      "learning_rate": 0.00019985706107286514,
+      "loss": 1.2259,
+      "step": 22
+    },
+    {
+      "epoch": 0.19834710743801653,
+      "grad_norm": 1.6215940713882446,
+      "learning_rate": 0.00019977668786231534,
+      "loss": 1.1992,
+      "step": 24
+    },
+    {
+      "epoch": 0.21487603305785125,
+      "grad_norm": 2.476259231567383,
+      "learning_rate": 0.0001996784832027525,
+      "loss": 1.2782,
+      "step": 26
+    },
+    {
+      "epoch": 0.23140495867768596,
+      "grad_norm": 2.04018235206604,
+      "learning_rate": 0.00019956246464468294,
+      "loss": 1.23,
+      "step": 28
+    },
+    {
+      "epoch": 0.24793388429752067,
+      "grad_norm": 1.8799017667770386,
+      "learning_rate": 0.00019942865292219838,
+      "loss": 1.2164,
+      "step": 30
+    },
+    {
+      "epoch": 0.2644628099173554,
+      "grad_norm": 1.2413148880004883,
+      "learning_rate": 0.00019927707194927066,
+      "loss": 1.2924,
+      "step": 32
+    },
+    {
+      "epoch": 0.2809917355371901,
+      "grad_norm": 1.8723937273025513,
+      "learning_rate": 0.000199107748815478,
+      "loss": 1.2302,
+      "step": 34
+    },
+    {
+      "epoch": 0.2975206611570248,
+      "grad_norm": 1.393110752105713,
+      "learning_rate": 0.00019892071378116376,
+      "loss": 1.2276,
+      "step": 36
+    },
+    {
+      "epoch": 0.3140495867768595,
+      "grad_norm": 1.1459721326828003,
+      "learning_rate": 0.0001987160002720283,
+      "loss": 1.1504,
+      "step": 38
+    },
+    {
+      "epoch": 0.3305785123966942,
+      "grad_norm": 1.4680942296981812,
+      "learning_rate": 0.00019849364487315558,
+      "loss": 1.1623,
+      "step": 40
+    },
+    {
+      "epoch": 0.34710743801652894,
+      "grad_norm": 1.8715866804122925,
+      "learning_rate": 0.0001982536873224748,
+      "loss": 1.2155,
+      "step": 42
+    },
+    {
+      "epoch": 0.36363636363636365,
+      "grad_norm": 0.871064305305481,
+      "learning_rate": 0.0001979961705036587,
+      "loss": 1.1594,
+      "step": 44
+    },
+    {
+      "epoch": 0.38016528925619836,
+      "grad_norm": 0.8239800930023193,
+      "learning_rate": 0.00019772114043845965,
+      "loss": 1.1501,
+      "step": 46
+    },
+    {
+      "epoch": 0.39669421487603307,
+      "grad_norm": 0.9587319493293762,
+      "learning_rate": 0.0001974286462784851,
+      "loss": 1.1195,
+      "step": 48
+    },
+    {
+      "epoch": 0.4132231404958678,
+      "grad_norm": 1.1645926237106323,
+      "learning_rate": 0.0001971187402964132,
+      "loss": 1.1417,
+      "step": 50
+    },
+    {
+      "epoch": 0.4297520661157025,
+      "grad_norm": 0.576813817024231,
+      "learning_rate": 0.00019679147787665126,
+      "loss": 1.1445,
+      "step": 52
+    },
+    {
+      "epoch": 0.4462809917355372,
+      "grad_norm": 1.0733133554458618,
+      "learning_rate": 0.00019644691750543767,
+      "loss": 1.0979,
+      "step": 54
+    },
+    {
+      "epoch": 0.4628099173553719,
+      "grad_norm": 0.5801639556884766,
+      "learning_rate": 0.00019608512076038962,
+      "loss": 1.0977,
+      "step": 56
+    },
+    {
+      "epoch": 0.4793388429752066,
+      "grad_norm": 1.6796538829803467,
+      "learning_rate": 0.00019570615229949842,
+      "loss": 1.1925,
+      "step": 58
+    },
+    {
+      "epoch": 0.49586776859504134,
+      "grad_norm": 1.0563887357711792,
+      "learning_rate": 0.00019531007984957408,
+      "loss": 1.0657,
+      "step": 60
+    },
+    {
+      "epoch": 0.512396694214876,
+      "grad_norm": 0.9109811186790466,
+      "learning_rate": 0.00019489697419414182,
+      "loss": 1.1098,
+      "step": 62
+    },
+    {
+      "epoch": 0.5289256198347108,
+      "grad_norm": 0.7321667671203613,
+      "learning_rate": 0.0001944669091607919,
+      "loss": 1.0929,
+      "step": 64
+    },
+    {
+      "epoch": 0.5454545454545454,
+      "grad_norm": 0.685366690158844,
+      "learning_rate": 0.00019401996160798573,
+      "loss": 1.1242,
+      "step": 66
+    },
+    {
+      "epoch": 0.5619834710743802,
+      "grad_norm": 0.8959838151931763,
+      "learning_rate": 0.0001935562114113202,
+      "loss": 1.181,
+      "step": 68
+    },
+    {
+      "epoch": 0.5785123966942148,
+      "grad_norm": 0.9717262983322144,
+      "learning_rate": 0.00019307574144925287,
+      "loss": 1.2295,
+      "step": 70
+    },
+    {
+      "epoch": 0.5950413223140496,
+      "grad_norm": 1.0358582735061646,
+      "learning_rate": 0.00019257863758829035,
+      "loss": 1.1431,
+      "step": 72
+    },
+    {
+      "epoch": 0.6115702479338843,
+      "grad_norm": 0.7998526096343994,
+      "learning_rate": 0.00019206498866764288,
+      "loss": 1.1032,
+      "step": 74
+    },
+    {
+      "epoch": 0.628099173553719,
+      "grad_norm": 1.1496188640594482,
+      "learning_rate": 0.0001915348864833476,
+      "loss": 1.057,
+      "step": 76
+    },
+    {
+      "epoch": 0.6446280991735537,
+      "grad_norm": 0.652406632900238,
+      "learning_rate": 0.00019098842577186314,
+      "loss": 1.146,
+      "step": 78
+    },
+    {
+      "epoch": 0.6611570247933884,
+      "grad_norm": 0.9454944729804993,
+      "learning_rate": 0.00019042570419313925,
+      "loss": 1.1543,
+      "step": 80
+    },
+    {
+      "epoch": 0.6776859504132231,
+      "grad_norm": 0.7456652522087097,
+      "learning_rate": 0.00018984682231316333,
+      "loss": 1.1189,
+      "step": 82
+    },
+    {
+      "epoch": 0.6942148760330579,
+      "grad_norm": 0.7312512397766113,
+      "learning_rate": 0.00018925188358598813,
+      "loss": 1.0873,
+      "step": 84
+    },
+    {
+      "epoch": 0.7107438016528925,
+      "grad_norm": 0.8474765419960022,
+      "learning_rate": 0.000188640994335243,
+      "loss": 1.1698,
+      "step": 86
+    },
+    {
+      "epoch": 0.7272727272727273,
+      "grad_norm": 0.6979633569717407,
+      "learning_rate": 0.0001880142637351325,
+      "loss": 1.1417,
+      "step": 88
+    },
+    {
+      "epoch": 0.743801652892562,
+      "grad_norm": 0.5989161133766174,
+      "learning_rate": 0.00018737180379092537,
+      "loss": 1.0479,
+      "step": 90
+    },
+    {
+      "epoch": 0.7603305785123967,
+      "grad_norm": 0.5765272378921509,
+      "learning_rate": 0.00018671372931893773,
+      "loss": 1.1336,
+      "step": 92
+    },
+    {
+      "epoch": 0.7768595041322314,
+      "grad_norm": 0.6709849834442139,
+      "learning_rate": 0.00018604015792601396,
+      "loss": 1.1157,
+      "step": 94
+    },
+    {
+      "epoch": 0.7933884297520661,
+      "grad_norm": 0.8181343674659729,
+      "learning_rate": 0.00018535120998850848,
+      "loss": 1.0927,
+      "step": 96
+    },
+    {
+      "epoch": 0.8099173553719008,
+      "grad_norm": 0.6146332621574402,
+      "learning_rate": 0.00018464700863077312,
+      "loss": 1.0739,
+      "step": 98
+    },
+    {
+      "epoch": 0.8264462809917356,
+      "grad_norm": 0.9904415011405945,
+      "learning_rate": 0.00018392767970315313,
+      "loss": 1.0331,
+      "step": 100
+    },
+    {
+      "epoch": 0.8429752066115702,
+      "grad_norm": 0.6186695694923401,
+      "learning_rate": 0.0001831933517594957,
+      "loss": 1.0513,
+      "step": 102
+    },
+    {
+      "epoch": 0.859504132231405,
+      "grad_norm": 1.1912785768508911,
+      "learning_rate": 0.00018244415603417603,
+      "loss": 1.1567,
+      "step": 104
+    },
+    {
+      "epoch": 0.8760330578512396,
+      "grad_norm": 1.3681318759918213,
+      "learning_rate": 0.00018168022641864377,
+      "loss": 1.1497,
+      "step": 106
+    },
+    {
+      "epoch": 0.8925619834710744,
+      "grad_norm": 0.619476318359375,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 1.1546,
+      "step": 108
+    },
+    {
+      "epoch": 0.9090909090909091,
+      "grad_norm": 0.7421219348907471,
+      "learning_rate": 0.00018010871422407236,
+      "loss": 1.1458,
+      "step": 110
+    },
+    {
+      "epoch": 0.9256198347107438,
+      "grad_norm": 0.6569286584854126,
+      "learning_rate": 0.00017930141249560233,
+      "loss": 1.12,
+      "step": 112
+    },
+    {
+      "epoch": 0.9421487603305785,
+      "grad_norm": 0.4168110191822052,
+      "learning_rate": 0.0001784799385278661,
+      "loss": 1.1682,
+      "step": 114
+    },
+    {
+      "epoch": 0.9586776859504132,
+      "grad_norm": 0.5620162487030029,
+      "learning_rate": 0.00017764443912941672,
+      "loss": 1.1828,
+      "step": 116
+    },
+    {
+      "epoch": 0.9752066115702479,
+      "grad_norm": 0.8095484375953674,
+      "learning_rate": 0.00017679506361534215,
+      "loss": 1.1953,
+      "step": 118
+    },
+    {
+      "epoch": 0.9917355371900827,
+      "grad_norm": 0.7646257281303406,
+      "learning_rate": 0.0001759319637805806,
+      "loss": 1.2148,
+      "step": 120
+    },
+    {
+      "epoch": 1.0082644628099173,
+      "grad_norm": 0.5254501104354858,
+      "learning_rate": 0.00017505529387279277,
+      "loss": 1.1359,
+      "step": 122
+    },
+    {
+      "epoch": 1.024793388429752,
+      "grad_norm": 0.6001765727996826,
+      "learning_rate": 0.00017416521056479577,
+      "loss": 1.1336,
+      "step": 124
+    },
+    {
+      "epoch": 1.0413223140495869,
+      "grad_norm": 0.35407504439353943,
+      "learning_rate": 0.00017326187292656333,
+      "loss": 1.1833,
+      "step": 126
+    },
+    {
+      "epoch": 1.0578512396694215,
+      "grad_norm": 0.414528489112854,
+      "learning_rate": 0.00017234544239679806,
+      "loss": 1.1301,
+      "step": 128
+    },
+    {
+      "epoch": 1.0743801652892562,
+      "grad_norm": 0.46355852484703064,
+      "learning_rate": 0.00017141608275408006,
+      "loss": 1.213,
+      "step": 130
+    },
+    {
+      "epoch": 1.0909090909090908,
+      "grad_norm": 0.5040593147277832,
+      "learning_rate": 0.00017047396008759754,
+      "loss": 1.132,
+      "step": 132
+    },
+    {
+      "epoch": 1.1074380165289257,
+      "grad_norm": 0.4813704192638397,
+      "learning_rate": 0.00016951924276746425,
+      "loss": 1.0831,
+      "step": 134
+    },
+    {
+      "epoch": 1.1239669421487604,
+      "grad_norm": 0.5174686312675476,
+      "learning_rate": 0.00016855210141462963,
+      "loss": 1.0514,
+      "step": 136
+    },
+    {
+      "epoch": 1.140495867768595,
+      "grad_norm": 0.4712466299533844,
+      "learning_rate": 0.00016757270887038654,
+      "loss": 1.1334,
+      "step": 138
+    },
+    {
+      "epoch": 1.1570247933884297,
+      "grad_norm": 0.5912173390388489,
+      "learning_rate": 0.00016658124016548197,
+      "loss": 1.1011,
+      "step": 140
+    },
+    {
+      "epoch": 1.1735537190082646,
+      "grad_norm": 0.6392802000045776,
+      "learning_rate": 0.00016557787248883696,
+      "loss": 1.1361,
+      "step": 142
+    },
+    {
+      "epoch": 1.1900826446280992,
+      "grad_norm": 0.7376368045806885,
+      "learning_rate": 0.00016456278515588024,
+      "loss": 1.109,
+      "step": 144
+    },
+    {
+      "epoch": 1.2066115702479339,
+      "grad_norm": 0.5020875930786133,
+      "learning_rate": 0.00016353615957650236,
+      "loss": 1.0925,
+      "step": 146
+    },
+    {
+      "epoch": 1.2231404958677685,
+      "grad_norm": 0.8081740736961365,
+      "learning_rate": 0.00016249817922263517,
+      "loss": 1.047,
+      "step": 148
+    },
+    {
+      "epoch": 1.2396694214876034,
+      "grad_norm": 0.6371219754219055,
+      "learning_rate": 0.00016144902959546286,
+      "loss": 1.113,
+      "step": 150
+    },
+    {
+      "epoch": 1.256198347107438,
+      "grad_norm": 0.7588189840316772,
+      "learning_rate": 0.00016038889819227045,
+      "loss": 1.1179,
+      "step": 152
+    },
+    {
+      "epoch": 1.2727272727272727,
+      "grad_norm": 0.6286205053329468,
+      "learning_rate": 0.00015931797447293552,
+      "loss": 1.1209,
+      "step": 154
+    },
+    {
+      "epoch": 1.2892561983471074,
+      "grad_norm": 0.797656238079071,
+      "learning_rate": 0.00015823644982606905,
+      "loss": 1.1698,
+      "step": 156
+    },
+    {
+      "epoch": 1.3057851239669422,
+      "grad_norm": 0.5368632078170776,
+      "learning_rate": 0.00015714451753481168,
+      "loss": 1.1973,
+      "step": 158
+    },
+    {
+      "epoch": 1.322314049586777,
+      "grad_norm": 0.4135212302207947,
+      "learning_rate": 0.00015604237274229147,
+      "loss": 1.1452,
+      "step": 160
+    },
+    {
+      "epoch": 1.3388429752066116,
+      "grad_norm": 0.5289668440818787,
+      "learning_rate": 0.00015493021241674918,
+      "loss": 1.1954,
+      "step": 162
+    },
+    {
+      "epoch": 1.3553719008264462,
+      "grad_norm": 0.4092061221599579,
+      "learning_rate": 0.00015380823531633729,
+      "loss": 1.1226,
+      "step": 164
+    },
+    {
+      "epoch": 1.3719008264462809,
+      "grad_norm": 0.7049645781517029,
+      "learning_rate": 0.00015267664195359917,
+      "loss": 1.0948,
+      "step": 166
+    },
+    {
+      "epoch": 1.3884297520661157,
+      "grad_norm": 0.47164198756217957,
+      "learning_rate": 0.00015153563455963499,
+      "loss": 1.0977,
+      "step": 168
+    },
+    {
+      "epoch": 1.4049586776859504,
+      "grad_norm": 0.7871695160865784,
+      "learning_rate": 0.00015038541704796003,
+      "loss": 1.1674,
+      "step": 170
+    },
+    {
+      "epoch": 1.421487603305785,
+      "grad_norm": 0.5381121635437012,
+      "learning_rate": 0.00014922619497806277,
+      "loss": 1.1415,
+      "step": 172
+    },
+    {
+      "epoch": 1.43801652892562,
+      "grad_norm": 0.39419299364089966,
+      "learning_rate": 0.00014805817551866838,
+      "loss": 1.0747,
+      "step": 174
+    },
+    {
+      "epoch": 1.4545454545454546,
+      "grad_norm": 0.38382914662361145,
+      "learning_rate": 0.00014688156741071514,
+      "loss": 1.1278,
+      "step": 176
+    },
+    {
+      "epoch": 1.4710743801652892,
+      "grad_norm": 0.32674962282180786,
+      "learning_rate": 0.00014569658093004935,
+      "loss": 0.9774,
+      "step": 178
+    },
+    {
+      "epoch": 1.487603305785124,
+      "grad_norm": 0.5443088412284851,
+      "learning_rate": 0.00014450342784984633,
+      "loss": 1.034,
+      "step": 180
+    },
+    {
+      "epoch": 1.5041322314049586,
+      "grad_norm": 0.6682401895523071,
+      "learning_rate": 0.00014330232140276366,
+      "loss": 1.1732,
+      "step": 182
+    },
+    {
+      "epoch": 1.5206611570247934,
+      "grad_norm": 0.5696044564247131,
+      "learning_rate": 0.0001420934762428335,
+      "loss": 1.0384,
+      "step": 184
+    },
+    {
+      "epoch": 1.537190082644628,
+      "grad_norm": 0.6782551407814026,
+      "learning_rate": 0.0001408771084071012,
+      "loss": 1.1107,
+      "step": 186
+    },
+    {
+      "epoch": 1.553719008264463,
+      "grad_norm": 0.8336123824119568,
+      "learning_rate": 0.00013965343527701628,
+      "loss": 1.0737,
+      "step": 188
+    },
+    {
+      "epoch": 1.5702479338842976,
+      "grad_norm": 0.539226233959198,
+      "learning_rate": 0.00013842267553958371,
+      "loss": 1.1665,
+      "step": 190
+    },
+    {
+      "epoch": 1.5867768595041323,
+      "grad_norm": 0.566620409488678,
+      "learning_rate": 0.00013718504914828135,
+      "loss": 1.1333,
+      "step": 192
+    },
+    {
+      "epoch": 1.603305785123967,
+      "grad_norm": 0.4735005795955658,
+      "learning_rate": 0.00013594077728375128,
+      "loss": 1.1709,
+      "step": 194
+    },
+    {
+      "epoch": 1.6198347107438016,
+      "grad_norm": 0.534383237361908,
+      "learning_rate": 0.00013469008231427207,
+      "loss": 1.0783,
+      "step": 196
+    },
+    {
+      "epoch": 1.6363636363636362,
+      "grad_norm": 0.8410363793373108,
+      "learning_rate": 0.0001334331877560182,
+      "loss": 1.0708,
+      "step": 198
+    },
+    {
+      "epoch": 1.6528925619834711,
+      "grad_norm": 0.6392219662666321,
+      "learning_rate": 0.00013217031823311488,
+      "loss": 1.0329,
+      "step": 200
+    },
+    {
+      "epoch": 1.6694214876033058,
+      "grad_norm": 0.5770404934883118,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 1.0404,
+      "step": 202
+    },
+    {
+      "epoch": 1.6859504132231407,
+      "grad_norm": 0.6814575791358948,
+      "learning_rate": 0.00012962755808856342,
+      "loss": 1.0702,
+      "step": 204
+    },
+    {
+      "epoch": 1.7024793388429753,
+      "grad_norm": 0.673312783241272,
+      "learning_rate": 0.0001283481218926818,
+      "loss": 1.0529,
+      "step": 206
+    },
+    {
+      "epoch": 1.71900826446281,
+      "grad_norm": 0.6180073618888855,
+      "learning_rate": 0.0001270636195024719,
+      "loss": 1.0257,
+      "step": 208
+    },
+    {
+      "epoch": 1.7355371900826446,
+      "grad_norm": 0.5565724968910217,
+      "learning_rate": 0.00012577428047595344,
+      "loss": 1.1102,
+      "step": 210
+    },
+    {
+      "epoch": 1.7520661157024793,
+      "grad_norm": 0.5586270689964294,
+      "learning_rate": 0.00012448033523551865,
+      "loss": 1.0277,
+      "step": 212
+    },
+    {
+      "epoch": 1.768595041322314,
+      "grad_norm": 0.542448878288269,
+      "learning_rate": 0.00012318201502675285,
+      "loss": 1.0988,
+      "step": 214
+    },
+    {
+      "epoch": 1.7851239669421488,
+      "grad_norm": 0.513042151927948,
+      "learning_rate": 0.0001218795518771075,
+      "loss": 1.0828,
+      "step": 216
+    },
+    {
+      "epoch": 1.8016528925619835,
+      "grad_norm": 0.7613060474395752,
+      "learning_rate": 0.00012057317855443395,
+      "loss": 1.1962,
+      "step": 218
+    },
+    {
+      "epoch": 1.8181818181818183,
+      "grad_norm": 0.7522129416465759,
+      "learning_rate": 0.00011926312852538455,
+      "loss": 1.1339,
+      "step": 220
+    },
+    {
+      "epoch": 1.834710743801653,
+      "grad_norm": 0.4655594825744629,
+      "learning_rate": 0.00011794963591368893,
+      "loss": 1.0967,
+      "step": 222
+    },
+    {
+      "epoch": 1.8512396694214877,
+      "grad_norm": 0.5036570429801941,
+      "learning_rate": 0.00011663293545831302,
+      "loss": 1.0361,
+      "step": 224
+    },
+    {
+      "epoch": 1.8677685950413223,
+      "grad_norm": 0.43016380071640015,
+      "learning_rate": 0.00011531326247150803,
+      "loss": 1.1281,
+      "step": 226
+    },
+    {
+      "epoch": 1.884297520661157,
+      "grad_norm": 0.5184316635131836,
+      "learning_rate": 0.00011399085279675687,
+      "loss": 1.2083,
+      "step": 228
+    },
+    {
+      "epoch": 1.9008264462809916,
+      "grad_norm": 0.6556355357170105,
+      "learning_rate": 0.0001126659427666257,
+      "loss": 1.0266,
+      "step": 230
+    },
+    {
+      "epoch": 1.9173553719008265,
+      "grad_norm": 0.515681803226471,
+      "learning_rate": 0.00011133876916052821,
+      "loss": 1.0472,
+      "step": 232
+    },
+    {
+      "epoch": 1.9338842975206612,
+      "grad_norm": 0.4592064321041107,
+      "learning_rate": 0.00011000956916240985,
+      "loss": 1.054,
+      "step": 234
+    },
+    {
+      "epoch": 1.950413223140496,
+      "grad_norm": 0.5623230338096619,
+      "learning_rate": 0.00010867858031835975,
+      "loss": 1.1571,
+      "step": 236
+    },
+    {
+      "epoch": 1.9669421487603307,
+      "grad_norm": 0.5241667032241821,
+      "learning_rate": 0.00010734604049415822,
+      "loss": 1.0985,
+      "step": 238
+    },
+    {
+      "epoch": 1.9834710743801653,
+      "grad_norm": 0.54905104637146,
+      "learning_rate": 0.00010601218783276672,
+      "loss": 1.1088,
+      "step": 240
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.8823345303535461,
+      "learning_rate": 0.00010467726071176853,
+      "loss": 1.0991,
+      "step": 242
+    },
+    {
+      "epoch": 2.0165289256198347,
+      "grad_norm": 0.5789780020713806,
+      "learning_rate": 0.00010334149770076747,
+      "loss": 1.1429,
+      "step": 244
+    },
+    {
+      "epoch": 2.0330578512396693,
+      "grad_norm": 0.6136715412139893,
+      "learning_rate": 0.00010200513751875227,
+      "loss": 1.0347,
+      "step": 246
+    },
+    {
+      "epoch": 2.049586776859504,
+      "grad_norm": 0.6462894082069397,
+      "learning_rate": 0.00010066841899143425,
+      "loss": 1.1008,
+      "step": 248
+    },
+    {
+      "epoch": 2.0661157024793386,
+      "grad_norm": 0.7272156476974487,
+      "learning_rate": 9.93315810085658e-05,
+      "loss": 1.1642,
+      "step": 250
+    },
+    {
+      "epoch": 2.0826446280991737,
+      "grad_norm": 0.5664356350898743,
+      "learning_rate": 9.799486248124775e-05,
+      "loss": 1.0799,
+      "step": 252
+    },
+    {
+      "epoch": 2.0991735537190084,
+      "grad_norm": 0.559697687625885,
+      "learning_rate": 9.665850229923258e-05,
+      "loss": 1.0536,
+      "step": 254
+    },
+    {
+      "epoch": 2.115702479338843,
+      "grad_norm": 0.7208287715911865,
+      "learning_rate": 9.532273928823151e-05,
+      "loss": 1.0595,
+      "step": 256
+    },
+    {
+      "epoch": 2.1322314049586777,
+      "grad_norm": 0.6985677480697632,
+      "learning_rate": 9.398781216723331e-05,
+      "loss": 1.0626,
+      "step": 258
+    },
+    {
+      "epoch": 2.1487603305785123,
+      "grad_norm": 0.7583006024360657,
+      "learning_rate": 9.26539595058418e-05,
+      "loss": 0.9919,
+      "step": 260
+    },
+    {
+      "epoch": 2.165289256198347,
+      "grad_norm": 0.6283029317855835,
+      "learning_rate": 9.132141968164026e-05,
+      "loss": 1.1292,
+      "step": 262
+    },
+    {
+      "epoch": 2.1818181818181817,
+      "grad_norm": 1.4162311553955078,
+      "learning_rate": 8.999043083759017e-05,
+      "loss": 1.1834,
+      "step": 264
+    },
+    {
+      "epoch": 2.1983471074380168,
+      "grad_norm": 0.5169870853424072,
+      "learning_rate": 8.866123083947182e-05,
+      "loss": 1.049,
+      "step": 266
+    },
+    {
+      "epoch": 2.2148760330578514,
+      "grad_norm": 0.9136308431625366,
+      "learning_rate": 8.733405723337432e-05,
+      "loss": 1.1336,
+      "step": 268
+    },
+    {
+      "epoch": 2.231404958677686,
+      "grad_norm": 0.6882078647613525,
+      "learning_rate": 8.600914720324316e-05,
+      "loss": 1.0953,
+      "step": 270
+    },
+    {
+      "epoch": 2.2479338842975207,
+      "grad_norm": 0.505447506904602,
+      "learning_rate": 8.4686737528492e-05,
+      "loss": 1.1014,
+      "step": 272
+    },
+    {
+      "epoch": 2.2644628099173554,
+      "grad_norm": 0.40685173869132996,
+      "learning_rate": 8.336706454168701e-05,
+      "loss": 1.0878,
+      "step": 274
+    },
+    {
+      "epoch": 2.28099173553719,
+      "grad_norm": 0.5715451836585999,
+      "learning_rate": 8.20503640863111e-05,
+      "loss": 1.0555,
+      "step": 276
+    },
+    {
+      "epoch": 2.2975206611570247,
+      "grad_norm": 0.5256667733192444,
+      "learning_rate": 8.073687147461547e-05,
+      "loss": 1.0678,
+      "step": 278
+    },
+    {
+      "epoch": 2.3140495867768593,
+      "grad_norm": 0.46319133043289185,
+      "learning_rate": 7.942682144556604e-05,
+      "loss": 1.0699,
+      "step": 280
+    },
+    {
+      "epoch": 2.330578512396694,
+      "grad_norm": 0.6000749468803406,
+      "learning_rate": 7.812044812289249e-05,
+      "loss": 1.1389,
+      "step": 282
+    },
+    {
+      "epoch": 2.347107438016529,
+      "grad_norm": 0.5024062395095825,
+      "learning_rate": 7.681798497324716e-05,
+      "loss": 1.1033,
+      "step": 284
+    },
+    {
+      "epoch": 2.3636363636363638,
+      "grad_norm": 0.6761860251426697,
+      "learning_rate": 7.55196647644814e-05,
+      "loss": 1.0665,
+      "step": 286
+    },
+    {
+      "epoch": 2.3801652892561984,
+      "grad_norm": 0.7175805568695068,
+      "learning_rate": 7.422571952404663e-05,
+      "loss": 1.0511,
+      "step": 288
+    },
+    {
+      "epoch": 2.396694214876033,
+      "grad_norm": 0.6883595585823059,
+      "learning_rate": 7.293638049752812e-05,
+      "loss": 1.0765,
+      "step": 290
+    },
+    {
+      "epoch": 2.4132231404958677,
+      "grad_norm": 0.6382430791854858,
+      "learning_rate": 7.165187810731823e-05,
+      "loss": 1.1036,
+      "step": 292
+    },
+    {
+      "epoch": 2.4297520661157024,
+      "grad_norm": 0.9323483109474182,
+      "learning_rate": 7.037244191143661e-05,
+      "loss": 1.1113,
+      "step": 294
+    },
+    {
+      "epoch": 2.446280991735537,
+      "grad_norm": 0.9768907427787781,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 1.0983,
+      "step": 296
+    },
+    {
+      "epoch": 2.462809917355372,
+      "grad_norm": 0.6783613562583923,
+      "learning_rate": 6.782968176688514e-05,
+      "loss": 1.1141,
+      "step": 298
+    },
+    {
+      "epoch": 2.479338842975207,
+      "grad_norm": 0.753887951374054,
+      "learning_rate": 6.656681224398183e-05,
+      "loss": 1.1234,
+      "step": 300
+    },
+    {
+      "epoch": 2.4958677685950414,
+      "grad_norm": 0.6788628697395325,
+      "learning_rate": 6.530991768572794e-05,
+      "loss": 1.0407,
+      "step": 302
+    },
+    {
+      "epoch": 2.512396694214876,
+      "grad_norm": 0.6727221012115479,
+      "learning_rate": 6.405922271624874e-05,
+      "loss": 1.091,
+      "step": 304
+    },
+    {
+      "epoch": 2.5289256198347108,
+      "grad_norm": 0.7418019771575928,
+      "learning_rate": 6.281495085171869e-05,
+      "loss": 1.0884,
+      "step": 306
+    },
+    {
+      "epoch": 2.5454545454545454,
+      "grad_norm": 0.7063189148902893,
+      "learning_rate": 6.15773244604163e-05,
+      "loss": 1.0218,
+      "step": 308
+    },
+    {
+      "epoch": 2.56198347107438,
+      "grad_norm": 1.0706840753555298,
+      "learning_rate": 6.0346564722983736e-05,
+      "loss": 1.0873,
+      "step": 310
+    },
+    {
+      "epoch": 2.5785123966942147,
+      "grad_norm": 0.683253288269043,
+      "learning_rate": 5.912289159289883e-05,
+      "loss": 1.0346,
+      "step": 312
+    },
+    {
+      "epoch": 2.5950413223140494,
+      "grad_norm": 0.5816308856010437,
+      "learning_rate": 5.790652375716652e-05,
+      "loss": 1.0113,
+      "step": 314
+    },
+    {
+      "epoch": 2.6115702479338845,
+      "grad_norm": 0.7935141324996948,
+      "learning_rate": 5.6697678597236356e-05,
+      "loss": 1.1771,
+      "step": 316
+    },
+    {
+      "epoch": 2.628099173553719,
+      "grad_norm": 0.6827735900878906,
+      "learning_rate": 5.549657215015367e-05,
+      "loss": 1.0899,
+      "step": 318
+    },
+    {
+      "epoch": 2.644628099173554,
+      "grad_norm": 0.5408580899238586,
+      "learning_rate": 5.430341906995065e-05,
+      "loss": 1.1056,
+      "step": 320
+    },
+    {
+      "epoch": 2.6611570247933884,
+      "grad_norm": 0.6996527910232544,
+      "learning_rate": 5.31184325892849e-05,
+      "loss": 1.0494,
+      "step": 322
+    },
+    {
+      "epoch": 2.677685950413223,
+      "grad_norm": 0.6700767874717712,
+      "learning_rate": 5.1941824481331626e-05,
+      "loss": 1.1206,
+      "step": 324
+    },
+    {
+      "epoch": 2.6942148760330578,
+      "grad_norm": 0.7690112590789795,
+      "learning_rate": 5.077380502193725e-05,
+      "loss": 1.1541,
+      "step": 326
+    },
+    {
+      "epoch": 2.7107438016528924,
+      "grad_norm": 0.7921670079231262,
+      "learning_rate": 4.961458295203999e-05,
+      "loss": 1.0684,
+      "step": 328
+    },
+    {
+      "epoch": 2.7272727272727275,
+      "grad_norm": 0.6989784240722656,
+      "learning_rate": 4.8464365440365044e-05,
+      "loss": 1.0097,
+      "step": 330
+    },
+    {
+      "epoch": 2.7438016528925617,
+      "grad_norm": 0.6038585901260376,
+      "learning_rate": 4.7323358046400844e-05,
+      "loss": 1.0751,
+      "step": 332
+    },
+    {
+      "epoch": 2.760330578512397,
+      "grad_norm": 0.8160024881362915,
+      "learning_rate": 4.6191764683662744e-05,
+      "loss": 0.9734,
+      "step": 334
+    },
+    {
+      "epoch": 2.7768595041322315,
+      "grad_norm": 0.7741029858589172,
+      "learning_rate": 4.506978758325081e-05,
+      "loss": 1.1186,
+      "step": 336
+    },
+    {
+      "epoch": 2.793388429752066,
+      "grad_norm": 0.8177542090415955,
+      "learning_rate": 4.395762725770852e-05,
+      "loss": 1.1538,
+      "step": 338
+    },
+    {
+      "epoch": 2.809917355371901,
+      "grad_norm": 0.7617602944374084,
+      "learning_rate": 4.285548246518837e-05,
+      "loss": 1.1162,
+      "step": 340
+    },
+    {
+      "epoch": 2.8264462809917354,
+      "grad_norm": 0.6426255106925964,
+      "learning_rate": 4.176355017393099e-05,
+      "loss": 1.0404,
+      "step": 342
+    },
+    {
+      "epoch": 2.84297520661157,
+      "grad_norm": 0.6394379138946533,
+      "learning_rate": 4.0682025527064486e-05,
+      "loss": 1.1107,
+      "step": 344
+    },
+    {
+      "epoch": 2.8595041322314048,
+      "grad_norm": 0.6632633209228516,
+      "learning_rate": 3.961110180772955e-05,
+      "loss": 1.1085,
+      "step": 346
+    },
+    {
+      "epoch": 2.87603305785124,
+      "grad_norm": 0.5437737703323364,
+      "learning_rate": 3.8550970404537144e-05,
+      "loss": 1.0072,
+      "step": 348
+    },
+    {
+      "epoch": 2.8925619834710745,
+      "grad_norm": 0.8178601264953613,
+      "learning_rate": 3.750182077736486e-05,
+      "loss": 1.0606,
+      "step": 350
+    },
+    {
+      "epoch": 2.909090909090909,
+      "grad_norm": 0.8268756866455078,
+      "learning_rate": 3.646384042349764e-05,
+      "loss": 0.9642,
+      "step": 352
+    },
+    {
+      "epoch": 2.925619834710744,
+      "grad_norm": 1.064460277557373,
+      "learning_rate": 3.543721484411976e-05,
+      "loss": 1.0881,
+      "step": 354
+    },
+    {
+      "epoch": 2.9421487603305785,
+      "grad_norm": 0.7875952124595642,
+      "learning_rate": 3.442212751116305e-05,
+      "loss": 1.0141,
+      "step": 356
+    },
+    {
+      "epoch": 2.958677685950413,
+      "grad_norm": 0.6071433424949646,
+      "learning_rate": 3.3418759834518056e-05,
+      "loss": 1.0692,
+      "step": 358
+    },
+    {
+      "epoch": 2.975206611570248,
+      "grad_norm": 0.6311193704605103,
+      "learning_rate": 3.24272911296135e-05,
+      "loss": 0.9481,
+      "step": 360
+    },
+    {
+      "epoch": 2.991735537190083,
+      "grad_norm": 0.7501534223556519,
+      "learning_rate": 3.1447898585370384e-05,
+      "loss": 1.1183,
+      "step": 362
+    },
+    {
+      "epoch": 3.0082644628099175,
+      "grad_norm": 0.6752927899360657,
+      "learning_rate": 3.0480757232535772e-05,
+      "loss": 1.0628,
+      "step": 364
+    },
+    {
+      "epoch": 3.024793388429752,
+      "grad_norm": 0.9237536787986755,
+      "learning_rate": 2.9526039912402503e-05,
+      "loss": 1.1539,
+      "step": 366
+    },
+    {
+      "epoch": 3.041322314049587,
+      "grad_norm": 0.5888502597808838,
+      "learning_rate": 2.8583917245919945e-05,
+      "loss": 1.0937,
+      "step": 368
+    },
+    {
+      "epoch": 3.0578512396694215,
+      "grad_norm": 0.8892382383346558,
+      "learning_rate": 2.7654557603201957e-05,
+      "loss": 1.0385,
+      "step": 370
+    },
+    {
+      "epoch": 3.074380165289256,
+      "grad_norm": 0.7525384426116943,
+      "learning_rate": 2.673812707343669e-05,
+      "loss": 0.9868,
+      "step": 372
+    },
+    {
+      "epoch": 3.090909090909091,
+      "grad_norm": 0.8219236731529236,
+      "learning_rate": 2.5834789435204243e-05,
+      "loss": 1.0349,
+      "step": 374
+    },
+    {
+      "epoch": 3.1074380165289255,
+      "grad_norm": 1.2317075729370117,
+      "learning_rate": 2.494470612720725e-05,
+      "loss": 1.0493,
+      "step": 376
+    },
+    {
+      "epoch": 3.12396694214876,
+      "grad_norm": 0.9741241931915283,
+      "learning_rate": 2.4068036219419432e-05,
+      "loss": 1.0685,
+      "step": 378
+    },
+    {
+      "epoch": 3.1404958677685952,
+      "grad_norm": 0.910832405090332,
+      "learning_rate": 2.3204936384657872e-05,
+      "loss": 1.0191,
+      "step": 380
+    },
+    {
+      "epoch": 3.15702479338843,
+      "grad_norm": 0.8739452958106995,
+      "learning_rate": 2.235556087058328e-05,
+      "loss": 1.0511,
+      "step": 382
+    },
+    {
+      "epoch": 3.1735537190082646,
+      "grad_norm": 1.0163301229476929,
+      "learning_rate": 2.1520061472133902e-05,
+      "loss": 1.0358,
+      "step": 384
+    },
+    {
+      "epoch": 3.190082644628099,
+      "grad_norm": 0.8788334131240845,
+      "learning_rate": 2.069858750439768e-05,
+      "loss": 1.0087,
+      "step": 386
+    },
+    {
+      "epoch": 3.206611570247934,
+      "grad_norm": 0.8024322390556335,
+      "learning_rate": 1.9891285775927682e-05,
+      "loss": 0.973,
+      "step": 388
+    },
+    {
+      "epoch": 3.2231404958677685,
+      "grad_norm": 1.0479772090911865,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 1.0334,
+      "step": 390
+    },
+    {
+      "epoch": 3.239669421487603,
+      "grad_norm": 0.8988475203514099,
+      "learning_rate": 1.831977358135625e-05,
+      "loss": 1.0007,
+      "step": 392
+    },
+    {
+      "epoch": 3.256198347107438,
+      "grad_norm": 0.9283938407897949,
+      "learning_rate": 1.7555843965823992e-05,
+      "loss": 1.0458,
+      "step": 394
+    },
+    {
+      "epoch": 3.2727272727272725,
+      "grad_norm": 1.1304008960723877,
+      "learning_rate": 1.680664824050432e-05,
+      "loss": 1.0623,
+      "step": 396
+    },
+    {
+      "epoch": 3.2892561983471076,
+      "grad_norm": 0.9807791113853455,
+      "learning_rate": 1.6072320296846898e-05,
+      "loss": 1.0569,
+      "step": 398
+    },
+    {
+      "epoch": 3.3057851239669422,
+      "grad_norm": 1.191261887550354,
+      "learning_rate": 1.5352991369226865e-05,
+      "loss": 0.9944,
+      "step": 400
+    },
+    {
+      "epoch": 3.322314049586777,
+      "grad_norm": 1.0459243059158325,
+      "learning_rate": 1.4648790011491542e-05,
+      "loss": 1.1106,
+      "step": 402
+    },
+    {
+      "epoch": 3.3388429752066116,
+      "grad_norm": 1.2179893255233765,
+      "learning_rate": 1.3959842073986085e-05,
+      "loss": 0.8982,
+      "step": 404
+    },
+    {
+      "epoch": 3.355371900826446,
+      "grad_norm": 1.219767689704895,
+      "learning_rate": 1.3286270681062274e-05,
+      "loss": 1.0193,
+      "step": 406
+    },
+    {
+      "epoch": 3.371900826446281,
+      "grad_norm": 1.2486698627471924,
+      "learning_rate": 1.262819620907465e-05,
+      "loss": 0.9492,
+      "step": 408
+    },
+    {
+      "epoch": 3.3884297520661155,
+      "grad_norm": 1.2574692964553833,
+      "learning_rate": 1.1985736264867509e-05,
+      "loss": 1.0077,
+      "step": 410
+    },
+    {
+      "epoch": 3.4049586776859506,
+      "grad_norm": 1.1906545162200928,
+      "learning_rate": 1.1359005664756994e-05,
+      "loss": 1.014,
+      "step": 412
+    },
+    {
+      "epoch": 3.4214876033057853,
+      "grad_norm": 1.3691320419311523,
+      "learning_rate": 1.0748116414011888e-05,
+      "loss": 1.0101,
+      "step": 414
+    },
+    {
+      "epoch": 3.43801652892562,
+      "grad_norm": 1.3103783130645752,
+      "learning_rate": 1.0153177686836691e-05,
+      "loss": 1.0953,
+      "step": 416
+    },
+    {
+      "epoch": 3.4545454545454546,
+      "grad_norm": 1.1507749557495117,
+      "learning_rate": 9.574295806860767e-06,
+      "loss": 1.0044,
+      "step": 418
+    },
+    {
+      "epoch": 3.4710743801652892,
+      "grad_norm": 1.3561640977859497,
+      "learning_rate": 9.011574228136865e-06,
+      "loss": 1.1707,
+      "step": 420
+    },
+    {
+      "epoch": 3.487603305785124,
+      "grad_norm": 1.31363046169281,
+      "learning_rate": 8.465113516652424e-06,
+      "loss": 1.0806,
+      "step": 422
+    },
+    {
+      "epoch": 3.5041322314049586,
+      "grad_norm": 1.0729997158050537,
+      "learning_rate": 7.935011332357112e-06,
+      "loss": 1.0657,
+      "step": 424
+    },
+    {
+      "epoch": 3.5206611570247937,
+      "grad_norm": 1.6132832765579224,
+      "learning_rate": 7.4213624117096755e-06,
+      "loss": 1.0328,
+      "step": 426
+    },
+    {
+      "epoch": 3.537190082644628,
+      "grad_norm": 0.8563976287841797,
+      "learning_rate": 6.924258550747154e-06,
+      "loss": 0.9862,
+      "step": 428
+    },
+    {
+      "epoch": 3.553719008264463,
+      "grad_norm": 1.1601394414901733,
+      "learning_rate": 6.4437885886798224e-06,
+      "loss": 0.957,
+      "step": 430
+    },
+    {
+      "epoch": 3.5702479338842976,
+      "grad_norm": 1.1800570487976074,
+      "learning_rate": 5.980038392014309e-06,
+      "loss": 1.0435,
+      "step": 432
+    },
+    {
+      "epoch": 3.5867768595041323,
+      "grad_norm": 1.334128737449646,
+      "learning_rate": 5.533090839208133e-06,
+      "loss": 1.0272,
+      "step": 434
+    },
+    {
+      "epoch": 3.603305785123967,
+      "grad_norm": 1.2104339599609375,
+      "learning_rate": 5.103025805858197e-06,
+      "loss": 0.9882,
+      "step": 436
+    },
+    {
+      "epoch": 3.6198347107438016,
+      "grad_norm": 1.1799639463424683,
+      "learning_rate": 4.68992015042592e-06,
+      "loss": 1.0944,
+      "step": 438
+    },
+    {
+      "epoch": 3.6363636363636362,
+      "grad_norm": 1.5897610187530518,
+      "learning_rate": 4.293847700501585e-06,
+      "loss": 1.0863,
+      "step": 440
+    },
+    {
+      "epoch": 3.652892561983471,
+      "grad_norm": 1.3954260349273682,
+      "learning_rate": 3.914879239610392e-06,
+      "loss": 1.0532,
+      "step": 442
+    },
+    {
+      "epoch": 3.669421487603306,
+      "grad_norm": 1.1017087697982788,
+      "learning_rate": 3.5530824945623542e-06,
+      "loss": 1.0719,
+      "step": 444
+    },
+    {
+      "epoch": 3.6859504132231407,
+      "grad_norm": 0.9582527279853821,
+      "learning_rate": 3.2085221233487562e-06,
+      "loss": 1.0178,
+      "step": 446
+    },
+    {
+      "epoch": 3.7024793388429753,
+      "grad_norm": 1.5694618225097656,
+      "learning_rate": 2.8812597035868137e-06,
+      "loss": 1.0657,
+      "step": 448
+    },
+    {
+      "epoch": 3.71900826446281,
+      "grad_norm": 0.8071503639221191,
+      "learning_rate": 2.5713537215149132e-06,
+      "loss": 1.0048,
+      "step": 450
+    },
+    {
+      "epoch": 3.7355371900826446,
+      "grad_norm": 1.3347952365875244,
+      "learning_rate": 2.2788595615403474e-06,
+      "loss": 1.0384,
+      "step": 452
+    },
+    {
+      "epoch": 3.7520661157024793,
+      "grad_norm": 1.4382898807525635,
+      "learning_rate": 2.003829496341325e-06,
+      "loss": 1.0574,
+      "step": 454
+    },
+    {
+      "epoch": 3.768595041322314,
+      "grad_norm": 1.1163910627365112,
+      "learning_rate": 1.7463126775252191e-06,
+      "loss": 1.1162,
+      "step": 456
+    },
+    {
+      "epoch": 3.785123966942149,
+      "grad_norm": 1.3733882904052734,
+      "learning_rate": 1.5063551268444276e-06,
+      "loss": 1.0597,
+      "step": 458
+    },
+    {
+      "epoch": 3.8016528925619832,
+      "grad_norm": 0.9412918090820312,
+      "learning_rate": 1.2839997279717076e-06,
+      "loss": 1.0342,
+      "step": 460
+    },
+    {
+      "epoch": 3.8181818181818183,
+      "grad_norm": 1.3428821563720703,
+      "learning_rate": 1.0792862188362396e-06,
+      "loss": 1.0588,
+      "step": 462
+    },
+    {
+      "epoch": 3.834710743801653,
+      "grad_norm": 1.326529860496521,
+      "learning_rate": 8.922511845219971e-07,
+      "loss": 1.0857,
+      "step": 464
+    },
+    {
+      "epoch": 3.8512396694214877,
+      "grad_norm": 1.1826655864715576,
+      "learning_rate": 7.229280507293657e-07,
+      "loss": 1.0606,
+      "step": 466
+    },
+    {
+      "epoch": 3.8677685950413223,
+      "grad_norm": 1.266386866569519,
+      "learning_rate": 5.713470778016538e-07,
+      "loss": 1.0195,
+      "step": 468
+    },
+    {
+      "epoch": 3.884297520661157,
+      "grad_norm": 1.2093831300735474,
+      "learning_rate": 4.375353553170647e-07,
+      "loss": 1.0039,
+      "step": 470
+    },
+    {
+      "epoch": 3.9008264462809916,
+      "grad_norm": 1.0445263385772705,
+      "learning_rate": 3.2151679724748975e-07,
+      "loss": 1.0612,
+      "step": 472
+    },
+    {
+      "epoch": 3.9173553719008263,
+      "grad_norm": 1.331885814666748,
+      "learning_rate": 2.2331213768468363e-07,
+      "loss": 1.1568,
+      "step": 474
+    },
+    {
+      "epoch": 3.9338842975206614,
+      "grad_norm": 1.254831075668335,
+      "learning_rate": 1.4293892713486134e-07,
+      "loss": 1.0544,
+      "step": 476
+    },
+    {
+      "epoch": 3.950413223140496,
+      "grad_norm": 0.9736830592155457,
+      "learning_rate": 8.041152938216278e-08,
+      "loss": 0.976,
+      "step": 478
+    },
+    {
+      "epoch": 3.9669421487603307,
+      "grad_norm": 1.0081415176391602,
+      "learning_rate": 3.5741118921628346e-08,
+      "loss": 1.0152,
+      "step": 480
+    },
+    {
+      "epoch": 3.9834710743801653,
+      "grad_norm": 1.2260342836380005,
+      "learning_rate": 8.93567896219638e-09,
+      "loss": 1.0639,
+      "step": 482
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 3.486053466796875,
+      "learning_rate": 0.0,
+      "loss": 1.1032,
+      "step": 484
+    }
+  ],
+  "logging_steps": 2,
+  "max_steps": 484,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 9157352821358592.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}