solidity data finetuned

README.md

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

adapter_config.json

@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "/home/ubuntu/Apps/DataInf/models/model",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_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:a3c618c18055bfce72d306d6b635cd0ecbd60120c3067688e0d526ab340b6b02
+size 26235704

checkpoint-100/README.md

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

checkpoint-100/adapter_config.json

@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "/home/ubuntu/Apps/DataInf/models/model",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-100/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3471e7f6f9007da19571b83b2c2ffc8c2b14cebd1f4f0edafaf9d5308fe78d79
+size 26235704

checkpoint-100/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6aabca352b9775a966b16d5684f7f41606975c89d075033dcf2ac50fd4b63e4
+size 52563258

checkpoint-100/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a16561ec857cdb55d8ca0062103fa8db84597e98bbcbc54a602f1c5d7574907a
+size 14244

checkpoint-100/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de4aa167f166f0cccc89350e9848a4fe7936d18a758a5fb69167c22863ba1414
+size 1064

checkpoint-100/special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "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": "</s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-100/tokenizer.model

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

checkpoint-100/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": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% set system_message = false %}{% endif %}{% for message in loop_messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if loop.index0 == 0 and system_message != false %}{% set content = '<<SYS>>\\n' + system_message + '\\n<</SYS>>\\n\\n' + message['content'] %}{% else %}{% set content = message['content'] %}{% endif %}{% if message['role'] == 'user' %}{{ bos_token + '[INST] ' + content.strip() + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ ' '  + content.strip() + ' ' + eos_token }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

checkpoint-100/trainer_state.json

@@ -0,0 +1,733 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.2,
+  "eval_steps": 500,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.032,
+      "grad_norm": 0.3297976851463318,
+      "learning_rate": 0.0002990322580645161,
+      "loss": 1.0389,
+      "step": 1
+    },
+    {
+      "epoch": 0.064,
+      "grad_norm": 0.4069916307926178,
+      "learning_rate": 0.0002980645161290322,
+      "loss": 1.3377,
+      "step": 2
+    },
+    {
+      "epoch": 0.096,
+      "grad_norm": 0.42084500193595886,
+      "learning_rate": 0.00029709677419354836,
+      "loss": 0.9366,
+      "step": 3
+    },
+    {
+      "epoch": 0.128,
+      "grad_norm": 0.4641948938369751,
+      "learning_rate": 0.0002961290322580645,
+      "loss": 1.0086,
+      "step": 4
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.3840750455856323,
+      "learning_rate": 0.00029516129032258065,
+      "loss": 0.8333,
+      "step": 5
+    },
+    {
+      "epoch": 0.192,
+      "grad_norm": 0.4263865053653717,
+      "learning_rate": 0.00029419354838709674,
+      "loss": 0.854,
+      "step": 6
+    },
+    {
+      "epoch": 0.224,
+      "grad_norm": 0.48615148663520813,
+      "learning_rate": 0.0002932258064516129,
+      "loss": 0.9548,
+      "step": 7
+    },
+    {
+      "epoch": 0.256,
+      "grad_norm": 0.44419369101524353,
+      "learning_rate": 0.00029225806451612903,
+      "loss": 0.8482,
+      "step": 8
+    },
+    {
+      "epoch": 0.288,
+      "grad_norm": 0.5317733883857727,
+      "learning_rate": 0.0002912903225806451,
+      "loss": 0.9426,
+      "step": 9
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.47260937094688416,
+      "learning_rate": 0.00029032258064516127,
+      "loss": 0.9816,
+      "step": 10
+    },
+    {
+      "epoch": 0.352,
+      "grad_norm": 0.39063283801078796,
+      "learning_rate": 0.00028935483870967736,
+      "loss": 0.84,
+      "step": 11
+    },
+    {
+      "epoch": 0.384,
+      "grad_norm": 0.39234670996665955,
+      "learning_rate": 0.0002883870967741935,
+      "loss": 0.7476,
+      "step": 12
+    },
+    {
+      "epoch": 0.416,
+      "grad_norm": 0.40661805868148804,
+      "learning_rate": 0.00028741935483870965,
+      "loss": 0.9282,
+      "step": 13
+    },
+    {
+      "epoch": 0.448,
+      "grad_norm": 0.42970865964889526,
+      "learning_rate": 0.0002864516129032258,
+      "loss": 0.7858,
+      "step": 14
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.3780193626880646,
+      "learning_rate": 0.00028548387096774194,
+      "loss": 0.7968,
+      "step": 15
+    },
+    {
+      "epoch": 0.512,
+      "grad_norm": 0.37006014585494995,
+      "learning_rate": 0.00028451612903225803,
+      "loss": 0.6801,
+      "step": 16
+    },
+    {
+      "epoch": 0.544,
+      "grad_norm": 0.3660840392112732,
+      "learning_rate": 0.0002835483870967742,
+      "loss": 0.5914,
+      "step": 17
+    },
+    {
+      "epoch": 0.576,
+      "grad_norm": 0.3270975351333618,
+      "learning_rate": 0.00028258064516129027,
+      "loss": 0.6449,
+      "step": 18
+    },
+    {
+      "epoch": 0.608,
+      "grad_norm": 0.3859024941921234,
+      "learning_rate": 0.0002816129032258064,
+      "loss": 0.8144,
+      "step": 19
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.37092071771621704,
+      "learning_rate": 0.00028064516129032256,
+      "loss": 0.7667,
+      "step": 20
+    },
+    {
+      "epoch": 0.672,
+      "grad_norm": 0.37667015194892883,
+      "learning_rate": 0.0002796774193548387,
+      "loss": 0.7751,
+      "step": 21
+    },
+    {
+      "epoch": 0.704,
+      "grad_norm": 0.3832458555698395,
+      "learning_rate": 0.0002787096774193548,
+      "loss": 0.755,
+      "step": 22
+    },
+    {
+      "epoch": 0.736,
+      "grad_norm": 0.327288419008255,
+      "learning_rate": 0.00027774193548387095,
+      "loss": 0.7178,
+      "step": 23
+    },
+    {
+      "epoch": 0.768,
+      "grad_norm": 0.34552687406539917,
+      "learning_rate": 0.0002767741935483871,
+      "loss": 0.7057,
+      "step": 24
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.3611259460449219,
+      "learning_rate": 0.0002758064516129032,
+      "loss": 0.8159,
+      "step": 25
+    },
+    {
+      "epoch": 0.832,
+      "grad_norm": 0.3345054090023041,
+      "learning_rate": 0.00027483870967741933,
+      "loss": 0.7208,
+      "step": 26
+    },
+    {
+      "epoch": 0.864,
+      "grad_norm": 0.3697254955768585,
+      "learning_rate": 0.0002738709677419355,
+      "loss": 0.8964,
+      "step": 27
+    },
+    {
+      "epoch": 0.896,
+      "grad_norm": 0.3905017375946045,
+      "learning_rate": 0.00027290322580645157,
+      "loss": 0.7794,
+      "step": 28
+    },
+    {
+      "epoch": 0.928,
+      "grad_norm": 0.3715725243091583,
+      "learning_rate": 0.0002719354838709677,
+      "loss": 0.6966,
+      "step": 29
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.3650343120098114,
+      "learning_rate": 0.00027096774193548386,
+      "loss": 0.5761,
+      "step": 30
+    },
+    {
+      "epoch": 0.992,
+      "grad_norm": 0.33932459354400635,
+      "learning_rate": 0.00027,
+      "loss": 0.556,
+      "step": 31
+    },
+    {
+      "epoch": 1.024,
+      "grad_norm": 0.6371742486953735,
+      "learning_rate": 0.0002690322580645161,
+      "loss": 0.847,
+      "step": 32
+    },
+    {
+      "epoch": 1.056,
+      "grad_norm": 0.37499895691871643,
+      "learning_rate": 0.00026806451612903224,
+      "loss": 0.8419,
+      "step": 33
+    },
+    {
+      "epoch": 1.088,
+      "grad_norm": 0.33221954107284546,
+      "learning_rate": 0.0002670967741935484,
+      "loss": 0.6011,
+      "step": 34
+    },
+    {
+      "epoch": 1.12,
+      "grad_norm": 0.344096839427948,
+      "learning_rate": 0.0002661290322580645,
+      "loss": 0.6501,
+      "step": 35
+    },
+    {
+      "epoch": 1.152,
+      "grad_norm": 0.38429391384124756,
+      "learning_rate": 0.0002651612903225806,
+      "loss": 0.8091,
+      "step": 36
+    },
+    {
+      "epoch": 1.184,
+      "grad_norm": 0.38014867901802063,
+      "learning_rate": 0.00026419354838709677,
+      "loss": 0.7668,
+      "step": 37
+    },
+    {
+      "epoch": 1.216,
+      "grad_norm": 0.3352573812007904,
+      "learning_rate": 0.00026322580645161286,
+      "loss": 0.5444,
+      "step": 38
+    },
+    {
+      "epoch": 1.248,
+      "grad_norm": 0.33811062574386597,
+      "learning_rate": 0.000262258064516129,
+      "loss": 0.512,
+      "step": 39
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 0.3998416066169739,
+      "learning_rate": 0.00026129032258064515,
+      "loss": 0.6315,
+      "step": 40
+    },
+    {
+      "epoch": 1.312,
+      "grad_norm": 0.3983341157436371,
+      "learning_rate": 0.0002603225806451613,
+      "loss": 0.5882,
+      "step": 41
+    },
+    {
+      "epoch": 1.3439999999999999,
+      "grad_norm": 0.4585898816585541,
+      "learning_rate": 0.0002593548387096774,
+      "loss": 0.761,
+      "step": 42
+    },
+    {
+      "epoch": 1.376,
+      "grad_norm": 0.4080730080604553,
+      "learning_rate": 0.00025838709677419354,
+      "loss": 0.6716,
+      "step": 43
+    },
+    {
+      "epoch": 1.408,
+      "grad_norm": 0.4068273901939392,
+      "learning_rate": 0.0002574193548387096,
+      "loss": 0.6376,
+      "step": 44
+    },
+    {
+      "epoch": 1.44,
+      "grad_norm": 0.4406949579715729,
+      "learning_rate": 0.00025645161290322577,
+      "loss": 0.4594,
+      "step": 45
+    },
+    {
+      "epoch": 1.472,
+      "grad_norm": 0.34500986337661743,
+      "learning_rate": 0.0002554838709677419,
+      "loss": 0.3672,
+      "step": 46
+    },
+    {
+      "epoch": 1.504,
+      "grad_norm": 0.4760681390762329,
+      "learning_rate": 0.00025451612903225806,
+      "loss": 0.6331,
+      "step": 47
+    },
+    {
+      "epoch": 1.536,
+      "grad_norm": 0.39281558990478516,
+      "learning_rate": 0.0002535483870967742,
+      "loss": 0.5845,
+      "step": 48
+    },
+    {
+      "epoch": 1.568,
+      "grad_norm": 0.4265002906322479,
+      "learning_rate": 0.0002525806451612903,
+      "loss": 0.4461,
+      "step": 49
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 0.40967294573783875,
+      "learning_rate": 0.00025161290322580645,
+      "loss": 0.7011,
+      "step": 50
+    },
+    {
+      "epoch": 1.6320000000000001,
+      "grad_norm": 0.4288088381290436,
+      "learning_rate": 0.00025064516129032254,
+      "loss": 0.6928,
+      "step": 51
+    },
+    {
+      "epoch": 1.6640000000000001,
+      "grad_norm": 0.4356289803981781,
+      "learning_rate": 0.0002496774193548387,
+      "loss": 0.7972,
+      "step": 52
+    },
+    {
+      "epoch": 1.696,
+      "grad_norm": 0.3827487826347351,
+      "learning_rate": 0.0002487096774193548,
+      "loss": 0.2991,
+      "step": 53
+    },
+    {
+      "epoch": 1.728,
+      "grad_norm": 0.40093398094177246,
+      "learning_rate": 0.0002477419354838709,
+      "loss": 0.416,
+      "step": 54
+    },
+    {
+      "epoch": 1.76,
+      "grad_norm": 0.41548973321914673,
+      "learning_rate": 0.00024677419354838707,
+      "loss": 0.5501,
+      "step": 55
+    },
+    {
+      "epoch": 1.792,
+      "grad_norm": 0.4093388617038727,
+      "learning_rate": 0.0002458064516129032,
+      "loss": 0.5557,
+      "step": 56
+    },
+    {
+      "epoch": 1.8239999999999998,
+      "grad_norm": 0.3934040665626526,
+      "learning_rate": 0.00024483870967741936,
+      "loss": 0.602,
+      "step": 57
+    },
+    {
+      "epoch": 1.8559999999999999,
+      "grad_norm": 0.42221033573150635,
+      "learning_rate": 0.00024387096774193545,
+      "loss": 0.6421,
+      "step": 58
+    },
+    {
+      "epoch": 1.888,
+      "grad_norm": 0.4351339340209961,
+      "learning_rate": 0.0002429032258064516,
+      "loss": 0.5615,
+      "step": 59
+    },
+    {
+      "epoch": 1.92,
+      "grad_norm": 0.4319838881492615,
+      "learning_rate": 0.00024193548387096771,
+      "loss": 0.6804,
+      "step": 60
+    },
+    {
+      "epoch": 1.952,
+      "grad_norm": 0.40016525983810425,
+      "learning_rate": 0.00024096774193548386,
+      "loss": 0.5432,
+      "step": 61
+    },
+    {
+      "epoch": 1.984,
+      "grad_norm": 0.3905942440032959,
+      "learning_rate": 0.00023999999999999998,
+      "loss": 0.4187,
+      "step": 62
+    },
+    {
+      "epoch": 2.016,
+      "grad_norm": 0.8056382536888123,
+      "learning_rate": 0.0002390322580645161,
+      "loss": 1.0174,
+      "step": 63
+    },
+    {
+      "epoch": 2.048,
+      "grad_norm": 0.3835236430168152,
+      "learning_rate": 0.00023806451612903224,
+      "loss": 0.5992,
+      "step": 64
+    },
+    {
+      "epoch": 2.08,
+      "grad_norm": 0.41092216968536377,
+      "learning_rate": 0.00023709677419354836,
+      "loss": 0.4746,
+      "step": 65
+    },
+    {
+      "epoch": 2.112,
+      "grad_norm": 0.39536622166633606,
+      "learning_rate": 0.0002361290322580645,
+      "loss": 0.3946,
+      "step": 66
+    },
+    {
+      "epoch": 2.144,
+      "grad_norm": 0.3927665948867798,
+      "learning_rate": 0.0002351612903225806,
+      "loss": 0.5187,
+      "step": 67
+    },
+    {
+      "epoch": 2.176,
+      "grad_norm": 0.39792704582214355,
+      "learning_rate": 0.00023419354838709674,
+      "loss": 0.4568,
+      "step": 68
+    },
+    {
+      "epoch": 2.208,
+      "grad_norm": 0.5023652911186218,
+      "learning_rate": 0.0002332258064516129,
+      "loss": 0.6166,
+      "step": 69
+    },
+    {
+      "epoch": 2.24,
+      "grad_norm": 0.425017774105072,
+      "learning_rate": 0.000232258064516129,
+      "loss": 0.42,
+      "step": 70
+    },
+    {
+      "epoch": 2.2720000000000002,
+      "grad_norm": 0.46458110213279724,
+      "learning_rate": 0.00023129032258064516,
+      "loss": 0.4613,
+      "step": 71
+    },
+    {
+      "epoch": 2.304,
+      "grad_norm": 0.49037960171699524,
+      "learning_rate": 0.00023032258064516125,
+      "loss": 0.5509,
+      "step": 72
+    },
+    {
+      "epoch": 2.336,
+      "grad_norm": 0.5233697891235352,
+      "learning_rate": 0.0002293548387096774,
+      "loss": 0.6396,
+      "step": 73
+    },
+    {
+      "epoch": 2.368,
+      "grad_norm": 0.4720582962036133,
+      "learning_rate": 0.0002283870967741935,
+      "loss": 0.5076,
+      "step": 74
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 0.4900650382041931,
+      "learning_rate": 0.00022741935483870966,
+      "loss": 0.4794,
+      "step": 75
+    },
+    {
+      "epoch": 2.432,
+      "grad_norm": 0.6321704983711243,
+      "learning_rate": 0.0002264516129032258,
+      "loss": 0.6677,
+      "step": 76
+    },
+    {
+      "epoch": 2.464,
+      "grad_norm": 0.5305324792861938,
+      "learning_rate": 0.00022548387096774192,
+      "loss": 0.5102,
+      "step": 77
+    },
+    {
+      "epoch": 2.496,
+      "grad_norm": 0.5799248218536377,
+      "learning_rate": 0.00022451612903225804,
+      "loss": 0.5274,
+      "step": 78
+    },
+    {
+      "epoch": 2.528,
+      "grad_norm": 0.4990101456642151,
+      "learning_rate": 0.00022354838709677416,
+      "loss": 0.5407,
+      "step": 79
+    },
+    {
+      "epoch": 2.56,
+      "grad_norm": 0.4779827296733856,
+      "learning_rate": 0.0002225806451612903,
+      "loss": 0.5166,
+      "step": 80
+    },
+    {
+      "epoch": 2.592,
+      "grad_norm": 0.5140111446380615,
+      "learning_rate": 0.00022161290322580645,
+      "loss": 0.3288,
+      "step": 81
+    },
+    {
+      "epoch": 2.624,
+      "grad_norm": 0.5674853920936584,
+      "learning_rate": 0.00022064516129032257,
+      "loss": 0.666,
+      "step": 82
+    },
+    {
+      "epoch": 2.656,
+      "grad_norm": 0.5277597308158875,
+      "learning_rate": 0.00021967741935483871,
+      "loss": 0.5335,
+      "step": 83
+    },
+    {
+      "epoch": 2.6879999999999997,
+      "grad_norm": 0.6029439568519592,
+      "learning_rate": 0.0002187096774193548,
+      "loss": 0.693,
+      "step": 84
+    },
+    {
+      "epoch": 2.7199999999999998,
+      "grad_norm": 0.5039327144622803,
+      "learning_rate": 0.00021774193548387095,
+      "loss": 0.5728,
+      "step": 85
+    },
+    {
+      "epoch": 2.752,
+      "grad_norm": 0.5564692616462708,
+      "learning_rate": 0.00021677419354838707,
+      "loss": 0.4734,
+      "step": 86
+    },
+    {
+      "epoch": 2.784,
+      "grad_norm": 0.5278319120407104,
+      "learning_rate": 0.00021580645161290322,
+      "loss": 0.5834,
+      "step": 87
+    },
+    {
+      "epoch": 2.816,
+      "grad_norm": 0.5445135831832886,
+      "learning_rate": 0.00021483870967741936,
+      "loss": 0.4642,
+      "step": 88
+    },
+    {
+      "epoch": 2.848,
+      "grad_norm": 0.5394749045372009,
+      "learning_rate": 0.00021387096774193545,
+      "loss": 0.4779,
+      "step": 89
+    },
+    {
+      "epoch": 2.88,
+      "grad_norm": 0.5756134390830994,
+      "learning_rate": 0.0002129032258064516,
+      "loss": 0.5607,
+      "step": 90
+    },
+    {
+      "epoch": 2.912,
+      "grad_norm": 0.48361241817474365,
+      "learning_rate": 0.00021193548387096772,
+      "loss": 0.4278,
+      "step": 91
+    },
+    {
+      "epoch": 2.944,
+      "grad_norm": 0.5017121434211731,
+      "learning_rate": 0.00021096774193548386,
+      "loss": 0.4834,
+      "step": 92
+    },
+    {
+      "epoch": 2.976,
+      "grad_norm": 0.4741989076137543,
+      "learning_rate": 0.00020999999999999998,
+      "loss": 0.468,
+      "step": 93
+    },
+    {
+      "epoch": 3.008,
+      "grad_norm": 1.003368854522705,
+      "learning_rate": 0.0002090322580645161,
+      "loss": 0.8614,
+      "step": 94
+    },
+    {
+      "epoch": 3.04,
+      "grad_norm": 0.4782228469848633,
+      "learning_rate": 0.00020806451612903225,
+      "loss": 0.4111,
+      "step": 95
+    },
+    {
+      "epoch": 3.072,
+      "grad_norm": 0.4558674395084381,
+      "learning_rate": 0.00020709677419354836,
+      "loss": 0.3463,
+      "step": 96
+    },
+    {
+      "epoch": 3.104,
+      "grad_norm": 0.4409371316432953,
+      "learning_rate": 0.0002061290322580645,
+      "loss": 0.2571,
+      "step": 97
+    },
+    {
+      "epoch": 3.136,
+      "grad_norm": 0.5415034890174866,
+      "learning_rate": 0.00020516129032258063,
+      "loss": 0.5707,
+      "step": 98
+    },
+    {
+      "epoch": 3.168,
+      "grad_norm": 0.6157724857330322,
+      "learning_rate": 0.00020419354838709677,
+      "loss": 0.5692,
+      "step": 99
+    },
+    {
+      "epoch": 3.2,
+      "grad_norm": 0.4855688810348511,
+      "learning_rate": 0.00020322580645161287,
+      "loss": 0.3311,
+      "step": 100
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 310,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.3700930822144e+16,
+  "train_batch_size": 3,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-100/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:457c697b05fd5daa3c83df8920300c4940c26fb78ace5b5428b7c95d133a0ef4
+size 5560

checkpoint-200/README.md

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

checkpoint-200/adapter_config.json

@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "/home/ubuntu/Apps/DataInf/models/model",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-200/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76034bd12f617b62f87d1878710f04e43736a4161233cbd240f6ea4c24e35dc7
+size 26235704

checkpoint-200/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8e377a77f5c23ff7f423e5dbb2c0bb98a05cbe4a1ce433ebe86185e505f3d95
+size 52563258

checkpoint-200/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ec44201e5ce901f0bed6a4979735328ac972b7f817413219ecec88ecb8ce9c0
+size 14244

checkpoint-200/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3048d808fac665a3eab1331732df75d683f7b1c8261cab5545365b6834a4e34
+size 1064

checkpoint-200/special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "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": "</s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-200/tokenizer.model

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

checkpoint-200/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": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% set system_message = false %}{% endif %}{% for message in loop_messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if loop.index0 == 0 and system_message != false %}{% set content = '<<SYS>>\\n' + system_message + '\\n<</SYS>>\\n\\n' + message['content'] %}{% else %}{% set content = message['content'] %}{% endif %}{% if message['role'] == 'user' %}{{ bos_token + '[INST] ' + content.strip() + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ ' '  + content.strip() + ' ' + eos_token }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

checkpoint-200/trainer_state.json

@@ -0,0 +1,1433 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 6.4,
+  "eval_steps": 500,
+  "global_step": 200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.032,
+      "grad_norm": 0.3297976851463318,
+      "learning_rate": 0.0002990322580645161,
+      "loss": 1.0389,
+      "step": 1
+    },
+    {
+      "epoch": 0.064,
+      "grad_norm": 0.4069916307926178,
+      "learning_rate": 0.0002980645161290322,
+      "loss": 1.3377,
+      "step": 2
+    },
+    {
+      "epoch": 0.096,
+      "grad_norm": 0.42084500193595886,
+      "learning_rate": 0.00029709677419354836,
+      "loss": 0.9366,
+      "step": 3
+    },
+    {
+      "epoch": 0.128,
+      "grad_norm": 0.4641948938369751,
+      "learning_rate": 0.0002961290322580645,
+      "loss": 1.0086,
+      "step": 4
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.3840750455856323,
+      "learning_rate": 0.00029516129032258065,
+      "loss": 0.8333,
+      "step": 5
+    },
+    {
+      "epoch": 0.192,
+      "grad_norm": 0.4263865053653717,
+      "learning_rate": 0.00029419354838709674,
+      "loss": 0.854,
+      "step": 6
+    },
+    {
+      "epoch": 0.224,
+      "grad_norm": 0.48615148663520813,
+      "learning_rate": 0.0002932258064516129,
+      "loss": 0.9548,
+      "step": 7
+    },
+    {
+      "epoch": 0.256,
+      "grad_norm": 0.44419369101524353,
+      "learning_rate": 0.00029225806451612903,
+      "loss": 0.8482,
+      "step": 8
+    },
+    {
+      "epoch": 0.288,
+      "grad_norm": 0.5317733883857727,
+      "learning_rate": 0.0002912903225806451,
+      "loss": 0.9426,
+      "step": 9
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.47260937094688416,
+      "learning_rate": 0.00029032258064516127,
+      "loss": 0.9816,
+      "step": 10
+    },
+    {
+      "epoch": 0.352,
+      "grad_norm": 0.39063283801078796,
+      "learning_rate": 0.00028935483870967736,
+      "loss": 0.84,
+      "step": 11
+    },
+    {
+      "epoch": 0.384,
+      "grad_norm": 0.39234670996665955,
+      "learning_rate": 0.0002883870967741935,
+      "loss": 0.7476,
+      "step": 12
+    },
+    {
+      "epoch": 0.416,
+      "grad_norm": 0.40661805868148804,
+      "learning_rate": 0.00028741935483870965,
+      "loss": 0.9282,
+      "step": 13
+    },
+    {
+      "epoch": 0.448,
+      "grad_norm": 0.42970865964889526,
+      "learning_rate": 0.0002864516129032258,
+      "loss": 0.7858,
+      "step": 14
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.3780193626880646,
+      "learning_rate": 0.00028548387096774194,
+      "loss": 0.7968,
+      "step": 15
+    },
+    {
+      "epoch": 0.512,
+      "grad_norm": 0.37006014585494995,
+      "learning_rate": 0.00028451612903225803,
+      "loss": 0.6801,
+      "step": 16
+    },
+    {
+      "epoch": 0.544,
+      "grad_norm": 0.3660840392112732,
+      "learning_rate": 0.0002835483870967742,
+      "loss": 0.5914,
+      "step": 17
+    },
+    {
+      "epoch": 0.576,
+      "grad_norm": 0.3270975351333618,
+      "learning_rate": 0.00028258064516129027,
+      "loss": 0.6449,
+      "step": 18
+    },
+    {
+      "epoch": 0.608,
+      "grad_norm": 0.3859024941921234,
+      "learning_rate": 0.0002816129032258064,
+      "loss": 0.8144,
+      "step": 19
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.37092071771621704,
+      "learning_rate": 0.00028064516129032256,
+      "loss": 0.7667,
+      "step": 20
+    },
+    {
+      "epoch": 0.672,
+      "grad_norm": 0.37667015194892883,
+      "learning_rate": 0.0002796774193548387,
+      "loss": 0.7751,
+      "step": 21
+    },
+    {
+      "epoch": 0.704,
+      "grad_norm": 0.3832458555698395,
+      "learning_rate": 0.0002787096774193548,
+      "loss": 0.755,
+      "step": 22
+    },
+    {
+      "epoch": 0.736,
+      "grad_norm": 0.327288419008255,
+      "learning_rate": 0.00027774193548387095,
+      "loss": 0.7178,
+      "step": 23
+    },
+    {
+      "epoch": 0.768,
+      "grad_norm": 0.34552687406539917,
+      "learning_rate": 0.0002767741935483871,
+      "loss": 0.7057,
+      "step": 24
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.3611259460449219,
+      "learning_rate": 0.0002758064516129032,
+      "loss": 0.8159,
+      "step": 25
+    },
+    {
+      "epoch": 0.832,
+      "grad_norm": 0.3345054090023041,
+      "learning_rate": 0.00027483870967741933,
+      "loss": 0.7208,
+      "step": 26
+    },
+    {
+      "epoch": 0.864,
+      "grad_norm": 0.3697254955768585,
+      "learning_rate": 0.0002738709677419355,
+      "loss": 0.8964,
+      "step": 27
+    },
+    {
+      "epoch": 0.896,
+      "grad_norm": 0.3905017375946045,
+      "learning_rate": 0.00027290322580645157,
+      "loss": 0.7794,
+      "step": 28
+    },
+    {
+      "epoch": 0.928,
+      "grad_norm": 0.3715725243091583,
+      "learning_rate": 0.0002719354838709677,
+      "loss": 0.6966,
+      "step": 29
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.3650343120098114,
+      "learning_rate": 0.00027096774193548386,
+      "loss": 0.5761,
+      "step": 30
+    },
+    {
+      "epoch": 0.992,
+      "grad_norm": 0.33932459354400635,
+      "learning_rate": 0.00027,
+      "loss": 0.556,
+      "step": 31
+    },
+    {
+      "epoch": 1.024,
+      "grad_norm": 0.6371742486953735,
+      "learning_rate": 0.0002690322580645161,
+      "loss": 0.847,
+      "step": 32
+    },
+    {
+      "epoch": 1.056,
+      "grad_norm": 0.37499895691871643,
+      "learning_rate": 0.00026806451612903224,
+      "loss": 0.8419,
+      "step": 33
+    },
+    {
+      "epoch": 1.088,
+      "grad_norm": 0.33221954107284546,
+      "learning_rate": 0.0002670967741935484,
+      "loss": 0.6011,
+      "step": 34
+    },
+    {
+      "epoch": 1.12,
+      "grad_norm": 0.344096839427948,
+      "learning_rate": 0.0002661290322580645,
+      "loss": 0.6501,
+      "step": 35
+    },
+    {
+      "epoch": 1.152,
+      "grad_norm": 0.38429391384124756,
+      "learning_rate": 0.0002651612903225806,
+      "loss": 0.8091,
+      "step": 36
+    },
+    {
+      "epoch": 1.184,
+      "grad_norm": 0.38014867901802063,
+      "learning_rate": 0.00026419354838709677,
+      "loss": 0.7668,
+      "step": 37
+    },
+    {
+      "epoch": 1.216,
+      "grad_norm": 0.3352573812007904,
+      "learning_rate": 0.00026322580645161286,
+      "loss": 0.5444,
+      "step": 38
+    },
+    {
+      "epoch": 1.248,
+      "grad_norm": 0.33811062574386597,
+      "learning_rate": 0.000262258064516129,
+      "loss": 0.512,
+      "step": 39
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 0.3998416066169739,
+      "learning_rate": 0.00026129032258064515,
+      "loss": 0.6315,
+      "step": 40
+    },
+    {
+      "epoch": 1.312,
+      "grad_norm": 0.3983341157436371,
+      "learning_rate": 0.0002603225806451613,
+      "loss": 0.5882,
+      "step": 41
+    },
+    {
+      "epoch": 1.3439999999999999,
+      "grad_norm": 0.4585898816585541,
+      "learning_rate": 0.0002593548387096774,
+      "loss": 0.761,
+      "step": 42
+    },
+    {
+      "epoch": 1.376,
+      "grad_norm": 0.4080730080604553,
+      "learning_rate": 0.00025838709677419354,
+      "loss": 0.6716,
+      "step": 43
+    },
+    {
+      "epoch": 1.408,
+      "grad_norm": 0.4068273901939392,
+      "learning_rate": 0.0002574193548387096,
+      "loss": 0.6376,
+      "step": 44
+    },
+    {
+      "epoch": 1.44,
+      "grad_norm": 0.4406949579715729,
+      "learning_rate": 0.00025645161290322577,
+      "loss": 0.4594,
+      "step": 45
+    },
+    {
+      "epoch": 1.472,
+      "grad_norm": 0.34500986337661743,
+      "learning_rate": 0.0002554838709677419,
+      "loss": 0.3672,
+      "step": 46
+    },
+    {
+      "epoch": 1.504,
+      "grad_norm": 0.4760681390762329,
+      "learning_rate": 0.00025451612903225806,
+      "loss": 0.6331,
+      "step": 47
+    },
+    {
+      "epoch": 1.536,
+      "grad_norm": 0.39281558990478516,
+      "learning_rate": 0.0002535483870967742,
+      "loss": 0.5845,
+      "step": 48
+    },
+    {
+      "epoch": 1.568,
+      "grad_norm": 0.4265002906322479,
+      "learning_rate": 0.0002525806451612903,
+      "loss": 0.4461,
+      "step": 49
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 0.40967294573783875,
+      "learning_rate": 0.00025161290322580645,
+      "loss": 0.7011,
+      "step": 50
+    },
+    {
+      "epoch": 1.6320000000000001,
+      "grad_norm": 0.4288088381290436,
+      "learning_rate": 0.00025064516129032254,
+      "loss": 0.6928,
+      "step": 51
+    },
+    {
+      "epoch": 1.6640000000000001,
+      "grad_norm": 0.4356289803981781,
+      "learning_rate": 0.0002496774193548387,
+      "loss": 0.7972,
+      "step": 52
+    },
+    {
+      "epoch": 1.696,
+      "grad_norm": 0.3827487826347351,
+      "learning_rate": 0.0002487096774193548,
+      "loss": 0.2991,
+      "step": 53
+    },
+    {
+      "epoch": 1.728,
+      "grad_norm": 0.40093398094177246,
+      "learning_rate": 0.0002477419354838709,
+      "loss": 0.416,
+      "step": 54
+    },
+    {
+      "epoch": 1.76,
+      "grad_norm": 0.41548973321914673,
+      "learning_rate": 0.00024677419354838707,
+      "loss": 0.5501,
+      "step": 55
+    },
+    {
+      "epoch": 1.792,
+      "grad_norm": 0.4093388617038727,
+      "learning_rate": 0.0002458064516129032,
+      "loss": 0.5557,
+      "step": 56
+    },
+    {
+      "epoch": 1.8239999999999998,
+      "grad_norm": 0.3934040665626526,
+      "learning_rate": 0.00024483870967741936,
+      "loss": 0.602,
+      "step": 57
+    },
+    {
+      "epoch": 1.8559999999999999,
+      "grad_norm": 0.42221033573150635,
+      "learning_rate": 0.00024387096774193545,
+      "loss": 0.6421,
+      "step": 58
+    },
+    {
+      "epoch": 1.888,
+      "grad_norm": 0.4351339340209961,
+      "learning_rate": 0.0002429032258064516,
+      "loss": 0.5615,
+      "step": 59
+    },
+    {
+      "epoch": 1.92,
+      "grad_norm": 0.4319838881492615,
+      "learning_rate": 0.00024193548387096771,
+      "loss": 0.6804,
+      "step": 60
+    },
+    {
+      "epoch": 1.952,
+      "grad_norm": 0.40016525983810425,
+      "learning_rate": 0.00024096774193548386,
+      "loss": 0.5432,
+      "step": 61
+    },
+    {
+      "epoch": 1.984,
+      "grad_norm": 0.3905942440032959,
+      "learning_rate": 0.00023999999999999998,
+      "loss": 0.4187,
+      "step": 62
+    },
+    {
+      "epoch": 2.016,
+      "grad_norm": 0.8056382536888123,
+      "learning_rate": 0.0002390322580645161,
+      "loss": 1.0174,
+      "step": 63
+    },
+    {
+      "epoch": 2.048,
+      "grad_norm": 0.3835236430168152,
+      "learning_rate": 0.00023806451612903224,
+      "loss": 0.5992,
+      "step": 64
+    },
+    {
+      "epoch": 2.08,
+      "grad_norm": 0.41092216968536377,
+      "learning_rate": 0.00023709677419354836,
+      "loss": 0.4746,
+      "step": 65
+    },
+    {
+      "epoch": 2.112,
+      "grad_norm": 0.39536622166633606,
+      "learning_rate": 0.0002361290322580645,
+      "loss": 0.3946,
+      "step": 66
+    },
+    {
+      "epoch": 2.144,
+      "grad_norm": 0.3927665948867798,
+      "learning_rate": 0.0002351612903225806,
+      "loss": 0.5187,
+      "step": 67
+    },
+    {
+      "epoch": 2.176,
+      "grad_norm": 0.39792704582214355,
+      "learning_rate": 0.00023419354838709674,
+      "loss": 0.4568,
+      "step": 68
+    },
+    {
+      "epoch": 2.208,
+      "grad_norm": 0.5023652911186218,
+      "learning_rate": 0.0002332258064516129,
+      "loss": 0.6166,
+      "step": 69
+    },
+    {
+      "epoch": 2.24,
+      "grad_norm": 0.425017774105072,
+      "learning_rate": 0.000232258064516129,
+      "loss": 0.42,
+      "step": 70
+    },
+    {
+      "epoch": 2.2720000000000002,
+      "grad_norm": 0.46458110213279724,
+      "learning_rate": 0.00023129032258064516,
+      "loss": 0.4613,
+      "step": 71
+    },
+    {
+      "epoch": 2.304,
+      "grad_norm": 0.49037960171699524,
+      "learning_rate": 0.00023032258064516125,
+      "loss": 0.5509,
+      "step": 72
+    },
+    {
+      "epoch": 2.336,
+      "grad_norm": 0.5233697891235352,
+      "learning_rate": 0.0002293548387096774,
+      "loss": 0.6396,
+      "step": 73
+    },
+    {
+      "epoch": 2.368,
+      "grad_norm": 0.4720582962036133,
+      "learning_rate": 0.0002283870967741935,
+      "loss": 0.5076,
+      "step": 74
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 0.4900650382041931,
+      "learning_rate": 0.00022741935483870966,
+      "loss": 0.4794,
+      "step": 75
+    },
+    {
+      "epoch": 2.432,
+      "grad_norm": 0.6321704983711243,
+      "learning_rate": 0.0002264516129032258,
+      "loss": 0.6677,
+      "step": 76
+    },
+    {
+      "epoch": 2.464,
+      "grad_norm": 0.5305324792861938,
+      "learning_rate": 0.00022548387096774192,
+      "loss": 0.5102,
+      "step": 77
+    },
+    {
+      "epoch": 2.496,
+      "grad_norm": 0.5799248218536377,
+      "learning_rate": 0.00022451612903225804,
+      "loss": 0.5274,
+      "step": 78
+    },
+    {
+      "epoch": 2.528,
+      "grad_norm": 0.4990101456642151,
+      "learning_rate": 0.00022354838709677416,
+      "loss": 0.5407,
+      "step": 79
+    },
+    {
+      "epoch": 2.56,
+      "grad_norm": 0.4779827296733856,
+      "learning_rate": 0.0002225806451612903,
+      "loss": 0.5166,
+      "step": 80
+    },
+    {
+      "epoch": 2.592,
+      "grad_norm": 0.5140111446380615,
+      "learning_rate": 0.00022161290322580645,
+      "loss": 0.3288,
+      "step": 81
+    },
+    {
+      "epoch": 2.624,
+      "grad_norm": 0.5674853920936584,
+      "learning_rate": 0.00022064516129032257,
+      "loss": 0.666,
+      "step": 82
+    },
+    {
+      "epoch": 2.656,
+      "grad_norm": 0.5277597308158875,
+      "learning_rate": 0.00021967741935483871,
+      "loss": 0.5335,
+      "step": 83
+    },
+    {
+      "epoch": 2.6879999999999997,
+      "grad_norm": 0.6029439568519592,
+      "learning_rate": 0.0002187096774193548,
+      "loss": 0.693,
+      "step": 84
+    },
+    {
+      "epoch": 2.7199999999999998,
+      "grad_norm": 0.5039327144622803,
+      "learning_rate": 0.00021774193548387095,
+      "loss": 0.5728,
+      "step": 85
+    },
+    {
+      "epoch": 2.752,
+      "grad_norm": 0.5564692616462708,
+      "learning_rate": 0.00021677419354838707,
+      "loss": 0.4734,
+      "step": 86
+    },
+    {
+      "epoch": 2.784,
+      "grad_norm": 0.5278319120407104,
+      "learning_rate": 0.00021580645161290322,
+      "loss": 0.5834,
+      "step": 87
+    },
+    {
+      "epoch": 2.816,
+      "grad_norm": 0.5445135831832886,
+      "learning_rate": 0.00021483870967741936,
+      "loss": 0.4642,
+      "step": 88
+    },
+    {
+      "epoch": 2.848,
+      "grad_norm": 0.5394749045372009,
+      "learning_rate": 0.00021387096774193545,
+      "loss": 0.4779,
+      "step": 89
+    },
+    {
+      "epoch": 2.88,
+      "grad_norm": 0.5756134390830994,
+      "learning_rate": 0.0002129032258064516,
+      "loss": 0.5607,
+      "step": 90
+    },
+    {
+      "epoch": 2.912,
+      "grad_norm": 0.48361241817474365,
+      "learning_rate": 0.00021193548387096772,
+      "loss": 0.4278,
+      "step": 91
+    },
+    {
+      "epoch": 2.944,
+      "grad_norm": 0.5017121434211731,
+      "learning_rate": 0.00021096774193548386,
+      "loss": 0.4834,
+      "step": 92
+    },
+    {
+      "epoch": 2.976,
+      "grad_norm": 0.4741989076137543,
+      "learning_rate": 0.00020999999999999998,
+      "loss": 0.468,
+      "step": 93
+    },
+    {
+      "epoch": 3.008,
+      "grad_norm": 1.003368854522705,
+      "learning_rate": 0.0002090322580645161,
+      "loss": 0.8614,
+      "step": 94
+    },
+    {
+      "epoch": 3.04,
+      "grad_norm": 0.4782228469848633,
+      "learning_rate": 0.00020806451612903225,
+      "loss": 0.4111,
+      "step": 95
+    },
+    {
+      "epoch": 3.072,
+      "grad_norm": 0.4558674395084381,
+      "learning_rate": 0.00020709677419354836,
+      "loss": 0.3463,
+      "step": 96
+    },
+    {
+      "epoch": 3.104,
+      "grad_norm": 0.4409371316432953,
+      "learning_rate": 0.0002061290322580645,
+      "loss": 0.2571,
+      "step": 97
+    },
+    {
+      "epoch": 3.136,
+      "grad_norm": 0.5415034890174866,
+      "learning_rate": 0.00020516129032258063,
+      "loss": 0.5707,
+      "step": 98
+    },
+    {
+      "epoch": 3.168,
+      "grad_norm": 0.6157724857330322,
+      "learning_rate": 0.00020419354838709677,
+      "loss": 0.5692,
+      "step": 99
+    },
+    {
+      "epoch": 3.2,
+      "grad_norm": 0.4855688810348511,
+      "learning_rate": 0.00020322580645161287,
+      "loss": 0.3311,
+      "step": 100
+    },
+    {
+      "epoch": 3.232,
+      "grad_norm": 0.569878101348877,
+      "learning_rate": 0.000202258064516129,
+      "loss": 0.4707,
+      "step": 101
+    },
+    {
+      "epoch": 3.2640000000000002,
+      "grad_norm": 0.645232081413269,
+      "learning_rate": 0.00020129032258064516,
+      "loss": 0.5504,
+      "step": 102
+    },
+    {
+      "epoch": 3.296,
+      "grad_norm": 0.5775763392448425,
+      "learning_rate": 0.00020032258064516128,
+      "loss": 0.3651,
+      "step": 103
+    },
+    {
+      "epoch": 3.328,
+      "grad_norm": 0.5808250904083252,
+      "learning_rate": 0.00019935483870967742,
+      "loss": 0.5068,
+      "step": 104
+    },
+    {
+      "epoch": 3.36,
+      "grad_norm": 0.689313530921936,
+      "learning_rate": 0.0001983870967741935,
+      "loss": 0.4936,
+      "step": 105
+    },
+    {
+      "epoch": 3.392,
+      "grad_norm": 0.6571519374847412,
+      "learning_rate": 0.00019741935483870966,
+      "loss": 0.3671,
+      "step": 106
+    },
+    {
+      "epoch": 3.424,
+      "grad_norm": 0.6340517401695251,
+      "learning_rate": 0.00019645161290322578,
+      "loss": 0.4783,
+      "step": 107
+    },
+    {
+      "epoch": 3.456,
+      "grad_norm": 0.7031407952308655,
+      "learning_rate": 0.00019548387096774192,
+      "loss": 0.427,
+      "step": 108
+    },
+    {
+      "epoch": 3.488,
+      "grad_norm": 0.728496789932251,
+      "learning_rate": 0.00019451612903225807,
+      "loss": 0.5497,
+      "step": 109
+    },
+    {
+      "epoch": 3.52,
+      "grad_norm": 0.6106727719306946,
+      "learning_rate": 0.00019354838709677416,
+      "loss": 0.392,
+      "step": 110
+    },
+    {
+      "epoch": 3.552,
+      "grad_norm": 0.5296047329902649,
+      "learning_rate": 0.0001925806451612903,
+      "loss": 0.3412,
+      "step": 111
+    },
+    {
+      "epoch": 3.584,
+      "grad_norm": 0.6282025575637817,
+      "learning_rate": 0.00019161290322580643,
+      "loss": 0.4081,
+      "step": 112
+    },
+    {
+      "epoch": 3.616,
+      "grad_norm": 0.6166461110115051,
+      "learning_rate": 0.00019064516129032257,
+      "loss": 0.4771,
+      "step": 113
+    },
+    {
+      "epoch": 3.648,
+      "grad_norm": 0.5448863506317139,
+      "learning_rate": 0.0001896774193548387,
+      "loss": 0.404,
+      "step": 114
+    },
+    {
+      "epoch": 3.68,
+      "grad_norm": 0.6598389148712158,
+      "learning_rate": 0.0001887096774193548,
+      "loss": 0.3915,
+      "step": 115
+    },
+    {
+      "epoch": 3.7119999999999997,
+      "grad_norm": 0.5567564368247986,
+      "learning_rate": 0.00018774193548387095,
+      "loss": 0.3862,
+      "step": 116
+    },
+    {
+      "epoch": 3.7439999999999998,
+      "grad_norm": 0.6524521708488464,
+      "learning_rate": 0.00018677419354838707,
+      "loss": 0.5315,
+      "step": 117
+    },
+    {
+      "epoch": 3.776,
+      "grad_norm": 0.7040128707885742,
+      "learning_rate": 0.00018580645161290322,
+      "loss": 0.5387,
+      "step": 118
+    },
+    {
+      "epoch": 3.808,
+      "grad_norm": 0.690262496471405,
+      "learning_rate": 0.00018483870967741934,
+      "loss": 0.4877,
+      "step": 119
+    },
+    {
+      "epoch": 3.84,
+      "grad_norm": 0.6928034424781799,
+      "learning_rate": 0.00018387096774193548,
+      "loss": 0.4895,
+      "step": 120
+    },
+    {
+      "epoch": 3.872,
+      "grad_norm": 0.7148469686508179,
+      "learning_rate": 0.00018290322580645157,
+      "loss": 0.4814,
+      "step": 121
+    },
+    {
+      "epoch": 3.904,
+      "grad_norm": 0.6096572875976562,
+      "learning_rate": 0.00018193548387096772,
+      "loss": 0.3403,
+      "step": 122
+    },
+    {
+      "epoch": 3.936,
+      "grad_norm": 0.7132399678230286,
+      "learning_rate": 0.00018096774193548387,
+      "loss": 0.4258,
+      "step": 123
+    },
+    {
+      "epoch": 3.968,
+      "grad_norm": 0.7302684187889099,
+      "learning_rate": 0.00017999999999999998,
+      "loss": 0.7215,
+      "step": 124
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 1.5244004726409912,
+      "learning_rate": 0.00017903225806451613,
+      "loss": 0.8544,
+      "step": 125
+    },
+    {
+      "epoch": 4.032,
+      "grad_norm": 0.6032777428627014,
+      "learning_rate": 0.00017806451612903222,
+      "loss": 0.4183,
+      "step": 126
+    },
+    {
+      "epoch": 4.064,
+      "grad_norm": 0.6349691152572632,
+      "learning_rate": 0.00017709677419354837,
+      "loss": 0.5871,
+      "step": 127
+    },
+    {
+      "epoch": 4.096,
+      "grad_norm": 0.5730060935020447,
+      "learning_rate": 0.00017612903225806449,
+      "loss": 0.3786,
+      "step": 128
+    },
+    {
+      "epoch": 4.128,
+      "grad_norm": 0.6988044381141663,
+      "learning_rate": 0.00017516129032258063,
+      "loss": 0.3216,
+      "step": 129
+    },
+    {
+      "epoch": 4.16,
+      "grad_norm": 0.7379153370857239,
+      "learning_rate": 0.00017419354838709678,
+      "loss": 0.4026,
+      "step": 130
+    },
+    {
+      "epoch": 4.192,
+      "grad_norm": 0.7058238983154297,
+      "learning_rate": 0.00017322580645161287,
+      "loss": 0.4328,
+      "step": 131
+    },
+    {
+      "epoch": 4.224,
+      "grad_norm": 0.80663001537323,
+      "learning_rate": 0.00017225806451612901,
+      "loss": 0.3849,
+      "step": 132
+    },
+    {
+      "epoch": 4.256,
+      "grad_norm": 0.899818480014801,
+      "learning_rate": 0.00017129032258064513,
+      "loss": 0.4191,
+      "step": 133
+    },
+    {
+      "epoch": 4.288,
+      "grad_norm": 0.8538224697113037,
+      "learning_rate": 0.00017032258064516128,
+      "loss": 0.3587,
+      "step": 134
+    },
+    {
+      "epoch": 4.32,
+      "grad_norm": 0.8948169350624084,
+      "learning_rate": 0.00016935483870967742,
+      "loss": 0.3957,
+      "step": 135
+    },
+    {
+      "epoch": 4.352,
+      "grad_norm": 0.7195591926574707,
+      "learning_rate": 0.00016838709677419354,
+      "loss": 0.3361,
+      "step": 136
+    },
+    {
+      "epoch": 4.384,
+      "grad_norm": 0.7769681215286255,
+      "learning_rate": 0.00016741935483870966,
+      "loss": 0.3519,
+      "step": 137
+    },
+    {
+      "epoch": 4.416,
+      "grad_norm": 0.9509867429733276,
+      "learning_rate": 0.00016645161290322578,
+      "loss": 0.4216,
+      "step": 138
+    },
+    {
+      "epoch": 4.448,
+      "grad_norm": 0.7923309206962585,
+      "learning_rate": 0.00016548387096774193,
+      "loss": 0.3999,
+      "step": 139
+    },
+    {
+      "epoch": 4.48,
+      "grad_norm": 0.8961685299873352,
+      "learning_rate": 0.00016451612903225804,
+      "loss": 0.5385,
+      "step": 140
+    },
+    {
+      "epoch": 4.5120000000000005,
+      "grad_norm": 0.7496562004089355,
+      "learning_rate": 0.0001635483870967742,
+      "loss": 0.341,
+      "step": 141
+    },
+    {
+      "epoch": 4.5440000000000005,
+      "grad_norm": 0.8512839674949646,
+      "learning_rate": 0.00016258064516129034,
+      "loss": 0.3847,
+      "step": 142
+    },
+    {
+      "epoch": 4.576,
+      "grad_norm": 0.7487362027168274,
+      "learning_rate": 0.00016161290322580643,
+      "loss": 0.3694,
+      "step": 143
+    },
+    {
+      "epoch": 4.608,
+      "grad_norm": 0.7957774996757507,
+      "learning_rate": 0.00016064516129032257,
+      "loss": 0.3379,
+      "step": 144
+    },
+    {
+      "epoch": 4.64,
+      "grad_norm": 0.7299221754074097,
+      "learning_rate": 0.0001596774193548387,
+      "loss": 0.2989,
+      "step": 145
+    },
+    {
+      "epoch": 4.672,
+      "grad_norm": 0.7909884452819824,
+      "learning_rate": 0.00015870967741935484,
+      "loss": 0.3675,
+      "step": 146
+    },
+    {
+      "epoch": 4.704,
+      "grad_norm": 0.7321597933769226,
+      "learning_rate": 0.00015774193548387093,
+      "loss": 0.3243,
+      "step": 147
+    },
+    {
+      "epoch": 4.736,
+      "grad_norm": 0.7196181416511536,
+      "learning_rate": 0.00015677419354838708,
+      "loss": 0.2709,
+      "step": 148
+    },
+    {
+      "epoch": 4.768,
+      "grad_norm": 0.7918142676353455,
+      "learning_rate": 0.00015580645161290322,
+      "loss": 0.3934,
+      "step": 149
+    },
+    {
+      "epoch": 4.8,
+      "grad_norm": 0.8657622337341309,
+      "learning_rate": 0.00015483870967741934,
+      "loss": 0.3583,
+      "step": 150
+    },
+    {
+      "epoch": 4.832,
+      "grad_norm": 0.8207722306251526,
+      "learning_rate": 0.00015387096774193549,
+      "loss": 0.412,
+      "step": 151
+    },
+    {
+      "epoch": 4.864,
+      "grad_norm": 0.7206109166145325,
+      "learning_rate": 0.00015290322580645158,
+      "loss": 0.3594,
+      "step": 152
+    },
+    {
+      "epoch": 4.896,
+      "grad_norm": 0.8529183864593506,
+      "learning_rate": 0.00015193548387096772,
+      "loss": 0.512,
+      "step": 153
+    },
+    {
+      "epoch": 4.928,
+      "grad_norm": 0.6895930171012878,
+      "learning_rate": 0.00015096774193548384,
+      "loss": 0.333,
+      "step": 154
+    },
+    {
+      "epoch": 4.96,
+      "grad_norm": 0.7422910332679749,
+      "learning_rate": 0.00015,
+      "loss": 0.2872,
+      "step": 155
+    },
+    {
+      "epoch": 4.992,
+      "grad_norm": 0.7366386651992798,
+      "learning_rate": 0.0001490322580645161,
+      "loss": 0.3415,
+      "step": 156
+    },
+    {
+      "epoch": 5.024,
+      "grad_norm": 2.1416280269622803,
+      "learning_rate": 0.00014806451612903225,
+      "loss": 0.9961,
+      "step": 157
+    },
+    {
+      "epoch": 5.056,
+      "grad_norm": 0.7944900393486023,
+      "learning_rate": 0.00014709677419354837,
+      "loss": 0.3372,
+      "step": 158
+    },
+    {
+      "epoch": 5.088,
+      "grad_norm": 0.7071006298065186,
+      "learning_rate": 0.00014612903225806452,
+      "loss": 0.2732,
+      "step": 159
+    },
+    {
+      "epoch": 5.12,
+      "grad_norm": 0.7874396443367004,
+      "learning_rate": 0.00014516129032258063,
+      "loss": 0.2861,
+      "step": 160
+    },
+    {
+      "epoch": 5.152,
+      "grad_norm": 0.8244249224662781,
+      "learning_rate": 0.00014419354838709675,
+      "loss": 0.3428,
+      "step": 161
+    },
+    {
+      "epoch": 5.184,
+      "grad_norm": 0.81637042760849,
+      "learning_rate": 0.0001432258064516129,
+      "loss": 0.3037,
+      "step": 162
+    },
+    {
+      "epoch": 5.216,
+      "grad_norm": 0.9916559457778931,
+      "learning_rate": 0.00014225806451612902,
+      "loss": 0.3337,
+      "step": 163
+    },
+    {
+      "epoch": 5.248,
+      "grad_norm": 0.9077599048614502,
+      "learning_rate": 0.00014129032258064514,
+      "loss": 0.287,
+      "step": 164
+    },
+    {
+      "epoch": 5.28,
+      "grad_norm": 0.9824132919311523,
+      "learning_rate": 0.00014032258064516128,
+      "loss": 0.3852,
+      "step": 165
+    },
+    {
+      "epoch": 5.312,
+      "grad_norm": 1.0016467571258545,
+      "learning_rate": 0.0001393548387096774,
+      "loss": 0.3234,
+      "step": 166
+    },
+    {
+      "epoch": 5.344,
+      "grad_norm": 0.8697543144226074,
+      "learning_rate": 0.00013838709677419355,
+      "loss": 0.2848,
+      "step": 167
+    },
+    {
+      "epoch": 5.376,
+      "grad_norm": 0.8214029669761658,
+      "learning_rate": 0.00013741935483870966,
+      "loss": 0.3377,
+      "step": 168
+    },
+    {
+      "epoch": 5.408,
+      "grad_norm": 0.9105691313743591,
+      "learning_rate": 0.00013645161290322578,
+      "loss": 0.2944,
+      "step": 169
+    },
+    {
+      "epoch": 5.44,
+      "grad_norm": 0.9642040133476257,
+      "learning_rate": 0.00013548387096774193,
+      "loss": 0.3624,
+      "step": 170
+    },
+    {
+      "epoch": 5.4719999999999995,
+      "grad_norm": 0.9218887686729431,
+      "learning_rate": 0.00013451612903225805,
+      "loss": 0.3938,
+      "step": 171
+    },
+    {
+      "epoch": 5.504,
+      "grad_norm": 0.8704710006713867,
+      "learning_rate": 0.0001335483870967742,
+      "loss": 0.3629,
+      "step": 172
+    },
+    {
+      "epoch": 5.536,
+      "grad_norm": 0.8207693099975586,
+      "learning_rate": 0.0001325806451612903,
+      "loss": 0.3169,
+      "step": 173
+    },
+    {
+      "epoch": 5.568,
+      "grad_norm": 0.9315701127052307,
+      "learning_rate": 0.00013161290322580643,
+      "loss": 0.429,
+      "step": 174
+    },
+    {
+      "epoch": 5.6,
+      "grad_norm": 0.860234260559082,
+      "learning_rate": 0.00013064516129032258,
+      "loss": 0.3842,
+      "step": 175
+    },
+    {
+      "epoch": 5.632,
+      "grad_norm": 0.8927604556083679,
+      "learning_rate": 0.0001296774193548387,
+      "loss": 0.3405,
+      "step": 176
+    },
+    {
+      "epoch": 5.664,
+      "grad_norm": 0.8084587454795837,
+      "learning_rate": 0.0001287096774193548,
+      "loss": 0.306,
+      "step": 177
+    },
+    {
+      "epoch": 5.696,
+      "grad_norm": 0.9102941155433655,
+      "learning_rate": 0.00012774193548387096,
+      "loss": 0.3285,
+      "step": 178
+    },
+    {
+      "epoch": 5.728,
+      "grad_norm": 0.763113796710968,
+      "learning_rate": 0.0001267741935483871,
+      "loss": 0.2729,
+      "step": 179
+    },
+    {
+      "epoch": 5.76,
+      "grad_norm": 0.8704251646995544,
+      "learning_rate": 0.00012580645161290322,
+      "loss": 0.3164,
+      "step": 180
+    },
+    {
+      "epoch": 5.792,
+      "grad_norm": 0.9634932279586792,
+      "learning_rate": 0.00012483870967741934,
+      "loss": 0.2939,
+      "step": 181
+    },
+    {
+      "epoch": 5.824,
+      "grad_norm": 1.1567790508270264,
+      "learning_rate": 0.00012387096774193546,
+      "loss": 0.3076,
+      "step": 182
+    },
+    {
+      "epoch": 5.856,
+      "grad_norm": 0.9096764922142029,
+      "learning_rate": 0.0001229032258064516,
+      "loss": 0.3289,
+      "step": 183
+    },
+    {
+      "epoch": 5.888,
+      "grad_norm": 0.9840425848960876,
+      "learning_rate": 0.00012193548387096773,
+      "loss": 0.2772,
+      "step": 184
+    },
+    {
+      "epoch": 5.92,
+      "grad_norm": 0.725844144821167,
+      "learning_rate": 0.00012096774193548386,
+      "loss": 0.2151,
+      "step": 185
+    },
+    {
+      "epoch": 5.952,
+      "grad_norm": 0.8343638181686401,
+      "learning_rate": 0.00011999999999999999,
+      "loss": 0.3825,
+      "step": 186
+    },
+    {
+      "epoch": 5.984,
+      "grad_norm": 0.8040199279785156,
+      "learning_rate": 0.00011903225806451612,
+      "loss": 0.2571,
+      "step": 187
+    },
+    {
+      "epoch": 6.016,
+      "grad_norm": 1.6932090520858765,
+      "learning_rate": 0.00011806451612903225,
+      "loss": 0.5538,
+      "step": 188
+    },
+    {
+      "epoch": 6.048,
+      "grad_norm": 0.744048535823822,
+      "learning_rate": 0.00011709677419354837,
+      "loss": 0.2335,
+      "step": 189
+    },
+    {
+      "epoch": 6.08,
+      "grad_norm": 0.6974924206733704,
+      "learning_rate": 0.0001161290322580645,
+      "loss": 0.2891,
+      "step": 190
+    },
+    {
+      "epoch": 6.112,
+      "grad_norm": 0.7202953696250916,
+      "learning_rate": 0.00011516129032258062,
+      "loss": 0.2017,
+      "step": 191
+    },
+    {
+      "epoch": 6.144,
+      "grad_norm": 0.8437547087669373,
+      "learning_rate": 0.00011419354838709676,
+      "loss": 0.2175,
+      "step": 192
+    },
+    {
+      "epoch": 6.176,
+      "grad_norm": 1.0741796493530273,
+      "learning_rate": 0.0001132258064516129,
+      "loss": 0.3913,
+      "step": 193
+    },
+    {
+      "epoch": 6.208,
+      "grad_norm": 1.031754493713379,
+      "learning_rate": 0.00011225806451612902,
+      "loss": 0.298,
+      "step": 194
+    },
+    {
+      "epoch": 6.24,
+      "grad_norm": 0.9575178027153015,
+      "learning_rate": 0.00011129032258064515,
+      "loss": 0.3201,
+      "step": 195
+    },
+    {
+      "epoch": 6.272,
+      "grad_norm": 0.9503082633018494,
+      "learning_rate": 0.00011032258064516128,
+      "loss": 0.2005,
+      "step": 196
+    },
+    {
+      "epoch": 6.304,
+      "grad_norm": 1.2572892904281616,
+      "learning_rate": 0.0001093548387096774,
+      "loss": 0.3045,
+      "step": 197
+    },
+    {
+      "epoch": 6.336,
+      "grad_norm": 1.5667368173599243,
+      "learning_rate": 0.00010838709677419353,
+      "loss": 0.4053,
+      "step": 198
+    },
+    {
+      "epoch": 6.368,
+      "grad_norm": 0.9439151883125305,
+      "learning_rate": 0.00010741935483870968,
+      "loss": 0.2721,
+      "step": 199
+    },
+    {
+      "epoch": 6.4,
+      "grad_norm": 1.0985567569732666,
+      "learning_rate": 0.0001064516129032258,
+      "loss": 0.2543,
+      "step": 200
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 310,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4.7401861644288e+16,
+  "train_batch_size": 3,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-200/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:457c697b05fd5daa3c83df8920300c4940c26fb78ace5b5428b7c95d133a0ef4
+size 5560

checkpoint-300/README.md

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

checkpoint-300/adapter_config.json

@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "/home/ubuntu/Apps/DataInf/models/model",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-300/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3a386647e475c5ceec94d64bca14946af914e62ba8c1b0ccabaf6e67ee9cc86
+size 26235704

checkpoint-300/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e6e1eb36f19824df0e3da6744f15a8782d02453f8d4fea63614aea6541336c8
+size 52563258

checkpoint-300/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:459e5e31f82079d82419676e4070ee07546d1393dfcf3e2693f2cd031c775968
+size 14244

checkpoint-300/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a2a684bbb13b2471d0a344d410a300b5697fcfde43c8620a62c450f9f491758
+size 1064

checkpoint-300/special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "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": "</s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-300/tokenizer.model

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

checkpoint-300/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": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% set system_message = false %}{% endif %}{% for message in loop_messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if loop.index0 == 0 and system_message != false %}{% set content = '<<SYS>>\\n' + system_message + '\\n<</SYS>>\\n\\n' + message['content'] %}{% else %}{% set content = message['content'] %}{% endif %}{% if message['role'] == 'user' %}{{ bos_token + '[INST] ' + content.strip() + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ ' '  + content.strip() + ' ' + eos_token }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

checkpoint-300/trainer_state.json

@@ -0,0 +1,2133 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 9.6,
+  "eval_steps": 500,
+  "global_step": 300,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.032,
+      "grad_norm": 0.3297976851463318,
+      "learning_rate": 0.0002990322580645161,
+      "loss": 1.0389,
+      "step": 1
+    },
+    {
+      "epoch": 0.064,
+      "grad_norm": 0.4069916307926178,
+      "learning_rate": 0.0002980645161290322,
+      "loss": 1.3377,
+      "step": 2
+    },
+    {
+      "epoch": 0.096,
+      "grad_norm": 0.42084500193595886,
+      "learning_rate": 0.00029709677419354836,
+      "loss": 0.9366,
+      "step": 3
+    },
+    {
+      "epoch": 0.128,
+      "grad_norm": 0.4641948938369751,
+      "learning_rate": 0.0002961290322580645,
+      "loss": 1.0086,
+      "step": 4
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.3840750455856323,
+      "learning_rate": 0.00029516129032258065,
+      "loss": 0.8333,
+      "step": 5
+    },
+    {
+      "epoch": 0.192,
+      "grad_norm": 0.4263865053653717,
+      "learning_rate": 0.00029419354838709674,
+      "loss": 0.854,
+      "step": 6
+    },
+    {
+      "epoch": 0.224,
+      "grad_norm": 0.48615148663520813,
+      "learning_rate": 0.0002932258064516129,
+      "loss": 0.9548,
+      "step": 7
+    },
+    {
+      "epoch": 0.256,
+      "grad_norm": 0.44419369101524353,
+      "learning_rate": 0.00029225806451612903,
+      "loss": 0.8482,
+      "step": 8
+    },
+    {
+      "epoch": 0.288,
+      "grad_norm": 0.5317733883857727,
+      "learning_rate": 0.0002912903225806451,
+      "loss": 0.9426,
+      "step": 9
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.47260937094688416,
+      "learning_rate": 0.00029032258064516127,
+      "loss": 0.9816,
+      "step": 10
+    },
+    {
+      "epoch": 0.352,
+      "grad_norm": 0.39063283801078796,
+      "learning_rate": 0.00028935483870967736,
+      "loss": 0.84,
+      "step": 11
+    },
+    {
+      "epoch": 0.384,
+      "grad_norm": 0.39234670996665955,
+      "learning_rate": 0.0002883870967741935,
+      "loss": 0.7476,
+      "step": 12
+    },
+    {
+      "epoch": 0.416,
+      "grad_norm": 0.40661805868148804,
+      "learning_rate": 0.00028741935483870965,
+      "loss": 0.9282,
+      "step": 13
+    },
+    {
+      "epoch": 0.448,
+      "grad_norm": 0.42970865964889526,
+      "learning_rate": 0.0002864516129032258,
+      "loss": 0.7858,
+      "step": 14
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.3780193626880646,
+      "learning_rate": 0.00028548387096774194,
+      "loss": 0.7968,
+      "step": 15
+    },
+    {
+      "epoch": 0.512,
+      "grad_norm": 0.37006014585494995,
+      "learning_rate": 0.00028451612903225803,
+      "loss": 0.6801,
+      "step": 16
+    },
+    {
+      "epoch": 0.544,
+      "grad_norm": 0.3660840392112732,
+      "learning_rate": 0.0002835483870967742,
+      "loss": 0.5914,
+      "step": 17
+    },
+    {
+      "epoch": 0.576,
+      "grad_norm": 0.3270975351333618,
+      "learning_rate": 0.00028258064516129027,
+      "loss": 0.6449,
+      "step": 18
+    },
+    {
+      "epoch": 0.608,
+      "grad_norm": 0.3859024941921234,
+      "learning_rate": 0.0002816129032258064,
+      "loss": 0.8144,
+      "step": 19
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.37092071771621704,
+      "learning_rate": 0.00028064516129032256,
+      "loss": 0.7667,
+      "step": 20
+    },
+    {
+      "epoch": 0.672,
+      "grad_norm": 0.37667015194892883,
+      "learning_rate": 0.0002796774193548387,
+      "loss": 0.7751,
+      "step": 21
+    },
+    {
+      "epoch": 0.704,
+      "grad_norm": 0.3832458555698395,
+      "learning_rate": 0.0002787096774193548,
+      "loss": 0.755,
+      "step": 22
+    },
+    {
+      "epoch": 0.736,
+      "grad_norm": 0.327288419008255,
+      "learning_rate": 0.00027774193548387095,
+      "loss": 0.7178,
+      "step": 23
+    },
+    {
+      "epoch": 0.768,
+      "grad_norm": 0.34552687406539917,
+      "learning_rate": 0.0002767741935483871,
+      "loss": 0.7057,
+      "step": 24
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.3611259460449219,
+      "learning_rate": 0.0002758064516129032,
+      "loss": 0.8159,
+      "step": 25
+    },
+    {
+      "epoch": 0.832,
+      "grad_norm": 0.3345054090023041,
+      "learning_rate": 0.00027483870967741933,
+      "loss": 0.7208,
+      "step": 26
+    },
+    {
+      "epoch": 0.864,
+      "grad_norm": 0.3697254955768585,
+      "learning_rate": 0.0002738709677419355,
+      "loss": 0.8964,
+      "step": 27
+    },
+    {
+      "epoch": 0.896,
+      "grad_norm": 0.3905017375946045,
+      "learning_rate": 0.00027290322580645157,
+      "loss": 0.7794,
+      "step": 28
+    },
+    {
+      "epoch": 0.928,
+      "grad_norm": 0.3715725243091583,
+      "learning_rate": 0.0002719354838709677,
+      "loss": 0.6966,
+      "step": 29
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.3650343120098114,
+      "learning_rate": 0.00027096774193548386,
+      "loss": 0.5761,
+      "step": 30
+    },
+    {
+      "epoch": 0.992,
+      "grad_norm": 0.33932459354400635,
+      "learning_rate": 0.00027,
+      "loss": 0.556,
+      "step": 31
+    },
+    {
+      "epoch": 1.024,
+      "grad_norm": 0.6371742486953735,
+      "learning_rate": 0.0002690322580645161,
+      "loss": 0.847,
+      "step": 32
+    },
+    {
+      "epoch": 1.056,
+      "grad_norm": 0.37499895691871643,
+      "learning_rate": 0.00026806451612903224,
+      "loss": 0.8419,
+      "step": 33
+    },
+    {
+      "epoch": 1.088,
+      "grad_norm": 0.33221954107284546,
+      "learning_rate": 0.0002670967741935484,
+      "loss": 0.6011,
+      "step": 34
+    },
+    {
+      "epoch": 1.12,
+      "grad_norm": 0.344096839427948,
+      "learning_rate": 0.0002661290322580645,
+      "loss": 0.6501,
+      "step": 35
+    },
+    {
+      "epoch": 1.152,
+      "grad_norm": 0.38429391384124756,
+      "learning_rate": 0.0002651612903225806,
+      "loss": 0.8091,
+      "step": 36
+    },
+    {
+      "epoch": 1.184,
+      "grad_norm": 0.38014867901802063,
+      "learning_rate": 0.00026419354838709677,
+      "loss": 0.7668,
+      "step": 37
+    },
+    {
+      "epoch": 1.216,
+      "grad_norm": 0.3352573812007904,
+      "learning_rate": 0.00026322580645161286,
+      "loss": 0.5444,
+      "step": 38
+    },
+    {
+      "epoch": 1.248,
+      "grad_norm": 0.33811062574386597,
+      "learning_rate": 0.000262258064516129,
+      "loss": 0.512,
+      "step": 39
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 0.3998416066169739,
+      "learning_rate": 0.00026129032258064515,
+      "loss": 0.6315,
+      "step": 40
+    },
+    {
+      "epoch": 1.312,
+      "grad_norm": 0.3983341157436371,
+      "learning_rate": 0.0002603225806451613,
+      "loss": 0.5882,
+      "step": 41
+    },
+    {
+      "epoch": 1.3439999999999999,
+      "grad_norm": 0.4585898816585541,
+      "learning_rate": 0.0002593548387096774,
+      "loss": 0.761,
+      "step": 42
+    },
+    {
+      "epoch": 1.376,
+      "grad_norm": 0.4080730080604553,
+      "learning_rate": 0.00025838709677419354,
+      "loss": 0.6716,
+      "step": 43
+    },
+    {
+      "epoch": 1.408,
+      "grad_norm": 0.4068273901939392,
+      "learning_rate": 0.0002574193548387096,
+      "loss": 0.6376,
+      "step": 44
+    },
+    {
+      "epoch": 1.44,
+      "grad_norm": 0.4406949579715729,
+      "learning_rate": 0.00025645161290322577,
+      "loss": 0.4594,
+      "step": 45
+    },
+    {
+      "epoch": 1.472,
+      "grad_norm": 0.34500986337661743,
+      "learning_rate": 0.0002554838709677419,
+      "loss": 0.3672,
+      "step": 46
+    },
+    {
+      "epoch": 1.504,
+      "grad_norm": 0.4760681390762329,
+      "learning_rate": 0.00025451612903225806,
+      "loss": 0.6331,
+      "step": 47
+    },
+    {
+      "epoch": 1.536,
+      "grad_norm": 0.39281558990478516,
+      "learning_rate": 0.0002535483870967742,
+      "loss": 0.5845,
+      "step": 48
+    },
+    {
+      "epoch": 1.568,
+      "grad_norm": 0.4265002906322479,
+      "learning_rate": 0.0002525806451612903,
+      "loss": 0.4461,
+      "step": 49
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 0.40967294573783875,
+      "learning_rate": 0.00025161290322580645,
+      "loss": 0.7011,
+      "step": 50
+    },
+    {
+      "epoch": 1.6320000000000001,
+      "grad_norm": 0.4288088381290436,
+      "learning_rate": 0.00025064516129032254,
+      "loss": 0.6928,
+      "step": 51
+    },
+    {
+      "epoch": 1.6640000000000001,
+      "grad_norm": 0.4356289803981781,
+      "learning_rate": 0.0002496774193548387,
+      "loss": 0.7972,
+      "step": 52
+    },
+    {
+      "epoch": 1.696,
+      "grad_norm": 0.3827487826347351,
+      "learning_rate": 0.0002487096774193548,
+      "loss": 0.2991,
+      "step": 53
+    },
+    {
+      "epoch": 1.728,
+      "grad_norm": 0.40093398094177246,
+      "learning_rate": 0.0002477419354838709,
+      "loss": 0.416,
+      "step": 54
+    },
+    {
+      "epoch": 1.76,
+      "grad_norm": 0.41548973321914673,
+      "learning_rate": 0.00024677419354838707,
+      "loss": 0.5501,
+      "step": 55
+    },
+    {
+      "epoch": 1.792,
+      "grad_norm": 0.4093388617038727,
+      "learning_rate": 0.0002458064516129032,
+      "loss": 0.5557,
+      "step": 56
+    },
+    {
+      "epoch": 1.8239999999999998,
+      "grad_norm": 0.3934040665626526,
+      "learning_rate": 0.00024483870967741936,
+      "loss": 0.602,
+      "step": 57
+    },
+    {
+      "epoch": 1.8559999999999999,
+      "grad_norm": 0.42221033573150635,
+      "learning_rate": 0.00024387096774193545,
+      "loss": 0.6421,
+      "step": 58
+    },
+    {
+      "epoch": 1.888,
+      "grad_norm": 0.4351339340209961,
+      "learning_rate": 0.0002429032258064516,
+      "loss": 0.5615,
+      "step": 59
+    },
+    {
+      "epoch": 1.92,
+      "grad_norm": 0.4319838881492615,
+      "learning_rate": 0.00024193548387096771,
+      "loss": 0.6804,
+      "step": 60
+    },
+    {
+      "epoch": 1.952,
+      "grad_norm": 0.40016525983810425,
+      "learning_rate": 0.00024096774193548386,
+      "loss": 0.5432,
+      "step": 61
+    },
+    {
+      "epoch": 1.984,
+      "grad_norm": 0.3905942440032959,
+      "learning_rate": 0.00023999999999999998,
+      "loss": 0.4187,
+      "step": 62
+    },
+    {
+      "epoch": 2.016,
+      "grad_norm": 0.8056382536888123,
+      "learning_rate": 0.0002390322580645161,
+      "loss": 1.0174,
+      "step": 63
+    },
+    {
+      "epoch": 2.048,
+      "grad_norm": 0.3835236430168152,
+      "learning_rate": 0.00023806451612903224,
+      "loss": 0.5992,
+      "step": 64
+    },
+    {
+      "epoch": 2.08,
+      "grad_norm": 0.41092216968536377,
+      "learning_rate": 0.00023709677419354836,
+      "loss": 0.4746,
+      "step": 65
+    },
+    {
+      "epoch": 2.112,
+      "grad_norm": 0.39536622166633606,
+      "learning_rate": 0.0002361290322580645,
+      "loss": 0.3946,
+      "step": 66
+    },
+    {
+      "epoch": 2.144,
+      "grad_norm": 0.3927665948867798,
+      "learning_rate": 0.0002351612903225806,
+      "loss": 0.5187,
+      "step": 67
+    },
+    {
+      "epoch": 2.176,
+      "grad_norm": 0.39792704582214355,
+      "learning_rate": 0.00023419354838709674,
+      "loss": 0.4568,
+      "step": 68
+    },
+    {
+      "epoch": 2.208,
+      "grad_norm": 0.5023652911186218,
+      "learning_rate": 0.0002332258064516129,
+      "loss": 0.6166,
+      "step": 69
+    },
+    {
+      "epoch": 2.24,
+      "grad_norm": 0.425017774105072,
+      "learning_rate": 0.000232258064516129,
+      "loss": 0.42,
+      "step": 70
+    },
+    {
+      "epoch": 2.2720000000000002,
+      "grad_norm": 0.46458110213279724,
+      "learning_rate": 0.00023129032258064516,
+      "loss": 0.4613,
+      "step": 71
+    },
+    {
+      "epoch": 2.304,
+      "grad_norm": 0.49037960171699524,
+      "learning_rate": 0.00023032258064516125,
+      "loss": 0.5509,
+      "step": 72
+    },
+    {
+      "epoch": 2.336,
+      "grad_norm": 0.5233697891235352,
+      "learning_rate": 0.0002293548387096774,
+      "loss": 0.6396,
+      "step": 73
+    },
+    {
+      "epoch": 2.368,
+      "grad_norm": 0.4720582962036133,
+      "learning_rate": 0.0002283870967741935,
+      "loss": 0.5076,
+      "step": 74
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 0.4900650382041931,
+      "learning_rate": 0.00022741935483870966,
+      "loss": 0.4794,
+      "step": 75
+    },
+    {
+      "epoch": 2.432,
+      "grad_norm": 0.6321704983711243,
+      "learning_rate": 0.0002264516129032258,
+      "loss": 0.6677,
+      "step": 76
+    },
+    {
+      "epoch": 2.464,
+      "grad_norm": 0.5305324792861938,
+      "learning_rate": 0.00022548387096774192,
+      "loss": 0.5102,
+      "step": 77
+    },
+    {
+      "epoch": 2.496,
+      "grad_norm": 0.5799248218536377,
+      "learning_rate": 0.00022451612903225804,
+      "loss": 0.5274,
+      "step": 78
+    },
+    {
+      "epoch": 2.528,
+      "grad_norm": 0.4990101456642151,
+      "learning_rate": 0.00022354838709677416,
+      "loss": 0.5407,
+      "step": 79
+    },
+    {
+      "epoch": 2.56,
+      "grad_norm": 0.4779827296733856,
+      "learning_rate": 0.0002225806451612903,
+      "loss": 0.5166,
+      "step": 80
+    },
+    {
+      "epoch": 2.592,
+      "grad_norm": 0.5140111446380615,
+      "learning_rate": 0.00022161290322580645,
+      "loss": 0.3288,
+      "step": 81
+    },
+    {
+      "epoch": 2.624,
+      "grad_norm": 0.5674853920936584,
+      "learning_rate": 0.00022064516129032257,
+      "loss": 0.666,
+      "step": 82
+    },
+    {
+      "epoch": 2.656,
+      "grad_norm": 0.5277597308158875,
+      "learning_rate": 0.00021967741935483871,
+      "loss": 0.5335,
+      "step": 83
+    },
+    {
+      "epoch": 2.6879999999999997,
+      "grad_norm": 0.6029439568519592,
+      "learning_rate": 0.0002187096774193548,
+      "loss": 0.693,
+      "step": 84
+    },
+    {
+      "epoch": 2.7199999999999998,
+      "grad_norm": 0.5039327144622803,
+      "learning_rate": 0.00021774193548387095,
+      "loss": 0.5728,
+      "step": 85
+    },
+    {
+      "epoch": 2.752,
+      "grad_norm": 0.5564692616462708,
+      "learning_rate": 0.00021677419354838707,
+      "loss": 0.4734,
+      "step": 86
+    },
+    {
+      "epoch": 2.784,
+      "grad_norm": 0.5278319120407104,
+      "learning_rate": 0.00021580645161290322,
+      "loss": 0.5834,
+      "step": 87
+    },
+    {
+      "epoch": 2.816,
+      "grad_norm": 0.5445135831832886,
+      "learning_rate": 0.00021483870967741936,
+      "loss": 0.4642,
+      "step": 88
+    },
+    {
+      "epoch": 2.848,
+      "grad_norm": 0.5394749045372009,
+      "learning_rate": 0.00021387096774193545,
+      "loss": 0.4779,
+      "step": 89
+    },
+    {
+      "epoch": 2.88,
+      "grad_norm": 0.5756134390830994,
+      "learning_rate": 0.0002129032258064516,
+      "loss": 0.5607,
+      "step": 90
+    },
+    {
+      "epoch": 2.912,
+      "grad_norm": 0.48361241817474365,
+      "learning_rate": 0.00021193548387096772,
+      "loss": 0.4278,
+      "step": 91
+    },
+    {
+      "epoch": 2.944,
+      "grad_norm": 0.5017121434211731,
+      "learning_rate": 0.00021096774193548386,
+      "loss": 0.4834,
+      "step": 92
+    },
+    {
+      "epoch": 2.976,
+      "grad_norm": 0.4741989076137543,
+      "learning_rate": 0.00020999999999999998,
+      "loss": 0.468,
+      "step": 93
+    },
+    {
+      "epoch": 3.008,
+      "grad_norm": 1.003368854522705,
+      "learning_rate": 0.0002090322580645161,
+      "loss": 0.8614,
+      "step": 94
+    },
+    {
+      "epoch": 3.04,
+      "grad_norm": 0.4782228469848633,
+      "learning_rate": 0.00020806451612903225,
+      "loss": 0.4111,
+      "step": 95
+    },
+    {
+      "epoch": 3.072,
+      "grad_norm": 0.4558674395084381,
+      "learning_rate": 0.00020709677419354836,
+      "loss": 0.3463,
+      "step": 96
+    },
+    {
+      "epoch": 3.104,
+      "grad_norm": 0.4409371316432953,
+      "learning_rate": 0.0002061290322580645,
+      "loss": 0.2571,
+      "step": 97
+    },
+    {
+      "epoch": 3.136,
+      "grad_norm": 0.5415034890174866,
+      "learning_rate": 0.00020516129032258063,
+      "loss": 0.5707,
+      "step": 98
+    },
+    {
+      "epoch": 3.168,
+      "grad_norm": 0.6157724857330322,
+      "learning_rate": 0.00020419354838709677,
+      "loss": 0.5692,
+      "step": 99
+    },
+    {
+      "epoch": 3.2,
+      "grad_norm": 0.4855688810348511,
+      "learning_rate": 0.00020322580645161287,
+      "loss": 0.3311,
+      "step": 100
+    },
+    {
+      "epoch": 3.232,
+      "grad_norm": 0.569878101348877,
+      "learning_rate": 0.000202258064516129,
+      "loss": 0.4707,
+      "step": 101
+    },
+    {
+      "epoch": 3.2640000000000002,
+      "grad_norm": 0.645232081413269,
+      "learning_rate": 0.00020129032258064516,
+      "loss": 0.5504,
+      "step": 102
+    },
+    {
+      "epoch": 3.296,
+      "grad_norm": 0.5775763392448425,
+      "learning_rate": 0.00020032258064516128,
+      "loss": 0.3651,
+      "step": 103
+    },
+    {
+      "epoch": 3.328,
+      "grad_norm": 0.5808250904083252,
+      "learning_rate": 0.00019935483870967742,
+      "loss": 0.5068,
+      "step": 104
+    },
+    {
+      "epoch": 3.36,
+      "grad_norm": 0.689313530921936,
+      "learning_rate": 0.0001983870967741935,
+      "loss": 0.4936,
+      "step": 105
+    },
+    {
+      "epoch": 3.392,
+      "grad_norm": 0.6571519374847412,
+      "learning_rate": 0.00019741935483870966,
+      "loss": 0.3671,
+      "step": 106
+    },
+    {
+      "epoch": 3.424,
+      "grad_norm": 0.6340517401695251,
+      "learning_rate": 0.00019645161290322578,
+      "loss": 0.4783,
+      "step": 107
+    },
+    {
+      "epoch": 3.456,
+      "grad_norm": 0.7031407952308655,
+      "learning_rate": 0.00019548387096774192,
+      "loss": 0.427,
+      "step": 108
+    },
+    {
+      "epoch": 3.488,
+      "grad_norm": 0.728496789932251,
+      "learning_rate": 0.00019451612903225807,
+      "loss": 0.5497,
+      "step": 109
+    },
+    {
+      "epoch": 3.52,
+      "grad_norm": 0.6106727719306946,
+      "learning_rate": 0.00019354838709677416,
+      "loss": 0.392,
+      "step": 110
+    },
+    {
+      "epoch": 3.552,
+      "grad_norm": 0.5296047329902649,
+      "learning_rate": 0.0001925806451612903,
+      "loss": 0.3412,
+      "step": 111
+    },
+    {
+      "epoch": 3.584,
+      "grad_norm": 0.6282025575637817,
+      "learning_rate": 0.00019161290322580643,
+      "loss": 0.4081,
+      "step": 112
+    },
+    {
+      "epoch": 3.616,
+      "grad_norm": 0.6166461110115051,
+      "learning_rate": 0.00019064516129032257,
+      "loss": 0.4771,
+      "step": 113
+    },
+    {
+      "epoch": 3.648,
+      "grad_norm": 0.5448863506317139,
+      "learning_rate": 0.0001896774193548387,
+      "loss": 0.404,
+      "step": 114
+    },
+    {
+      "epoch": 3.68,
+      "grad_norm": 0.6598389148712158,
+      "learning_rate": 0.0001887096774193548,
+      "loss": 0.3915,
+      "step": 115
+    },
+    {
+      "epoch": 3.7119999999999997,
+      "grad_norm": 0.5567564368247986,
+      "learning_rate": 0.00018774193548387095,
+      "loss": 0.3862,
+      "step": 116
+    },
+    {
+      "epoch": 3.7439999999999998,
+      "grad_norm": 0.6524521708488464,
+      "learning_rate": 0.00018677419354838707,
+      "loss": 0.5315,
+      "step": 117
+    },
+    {
+      "epoch": 3.776,
+      "grad_norm": 0.7040128707885742,
+      "learning_rate": 0.00018580645161290322,
+      "loss": 0.5387,
+      "step": 118
+    },
+    {
+      "epoch": 3.808,
+      "grad_norm": 0.690262496471405,
+      "learning_rate": 0.00018483870967741934,
+      "loss": 0.4877,
+      "step": 119
+    },
+    {
+      "epoch": 3.84,
+      "grad_norm": 0.6928034424781799,
+      "learning_rate": 0.00018387096774193548,
+      "loss": 0.4895,
+      "step": 120
+    },
+    {
+      "epoch": 3.872,
+      "grad_norm": 0.7148469686508179,
+      "learning_rate": 0.00018290322580645157,
+      "loss": 0.4814,
+      "step": 121
+    },
+    {
+      "epoch": 3.904,
+      "grad_norm": 0.6096572875976562,
+      "learning_rate": 0.00018193548387096772,
+      "loss": 0.3403,
+      "step": 122
+    },
+    {
+      "epoch": 3.936,
+      "grad_norm": 0.7132399678230286,
+      "learning_rate": 0.00018096774193548387,
+      "loss": 0.4258,
+      "step": 123
+    },
+    {
+      "epoch": 3.968,
+      "grad_norm": 0.7302684187889099,
+      "learning_rate": 0.00017999999999999998,
+      "loss": 0.7215,
+      "step": 124
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 1.5244004726409912,
+      "learning_rate": 0.00017903225806451613,
+      "loss": 0.8544,
+      "step": 125
+    },
+    {
+      "epoch": 4.032,
+      "grad_norm": 0.6032777428627014,
+      "learning_rate": 0.00017806451612903222,
+      "loss": 0.4183,
+      "step": 126
+    },
+    {
+      "epoch": 4.064,
+      "grad_norm": 0.6349691152572632,
+      "learning_rate": 0.00017709677419354837,
+      "loss": 0.5871,
+      "step": 127
+    },
+    {
+      "epoch": 4.096,
+      "grad_norm": 0.5730060935020447,
+      "learning_rate": 0.00017612903225806449,
+      "loss": 0.3786,
+      "step": 128
+    },
+    {
+      "epoch": 4.128,
+      "grad_norm": 0.6988044381141663,
+      "learning_rate": 0.00017516129032258063,
+      "loss": 0.3216,
+      "step": 129
+    },
+    {
+      "epoch": 4.16,
+      "grad_norm": 0.7379153370857239,
+      "learning_rate": 0.00017419354838709678,
+      "loss": 0.4026,
+      "step": 130
+    },
+    {
+      "epoch": 4.192,
+      "grad_norm": 0.7058238983154297,
+      "learning_rate": 0.00017322580645161287,
+      "loss": 0.4328,
+      "step": 131
+    },
+    {
+      "epoch": 4.224,
+      "grad_norm": 0.80663001537323,
+      "learning_rate": 0.00017225806451612901,
+      "loss": 0.3849,
+      "step": 132
+    },
+    {
+      "epoch": 4.256,
+      "grad_norm": 0.899818480014801,
+      "learning_rate": 0.00017129032258064513,
+      "loss": 0.4191,
+      "step": 133
+    },
+    {
+      "epoch": 4.288,
+      "grad_norm": 0.8538224697113037,
+      "learning_rate": 0.00017032258064516128,
+      "loss": 0.3587,
+      "step": 134
+    },
+    {
+      "epoch": 4.32,
+      "grad_norm": 0.8948169350624084,
+      "learning_rate": 0.00016935483870967742,
+      "loss": 0.3957,
+      "step": 135
+    },
+    {
+      "epoch": 4.352,
+      "grad_norm": 0.7195591926574707,
+      "learning_rate": 0.00016838709677419354,
+      "loss": 0.3361,
+      "step": 136
+    },
+    {
+      "epoch": 4.384,
+      "grad_norm": 0.7769681215286255,
+      "learning_rate": 0.00016741935483870966,
+      "loss": 0.3519,
+      "step": 137
+    },
+    {
+      "epoch": 4.416,
+      "grad_norm": 0.9509867429733276,
+      "learning_rate": 0.00016645161290322578,
+      "loss": 0.4216,
+      "step": 138
+    },
+    {
+      "epoch": 4.448,
+      "grad_norm": 0.7923309206962585,
+      "learning_rate": 0.00016548387096774193,
+      "loss": 0.3999,
+      "step": 139
+    },
+    {
+      "epoch": 4.48,
+      "grad_norm": 0.8961685299873352,
+      "learning_rate": 0.00016451612903225804,
+      "loss": 0.5385,
+      "step": 140
+    },
+    {
+      "epoch": 4.5120000000000005,
+      "grad_norm": 0.7496562004089355,
+      "learning_rate": 0.0001635483870967742,
+      "loss": 0.341,
+      "step": 141
+    },
+    {
+      "epoch": 4.5440000000000005,
+      "grad_norm": 0.8512839674949646,
+      "learning_rate": 0.00016258064516129034,
+      "loss": 0.3847,
+      "step": 142
+    },
+    {
+      "epoch": 4.576,
+      "grad_norm": 0.7487362027168274,
+      "learning_rate": 0.00016161290322580643,
+      "loss": 0.3694,
+      "step": 143
+    },
+    {
+      "epoch": 4.608,
+      "grad_norm": 0.7957774996757507,
+      "learning_rate": 0.00016064516129032257,
+      "loss": 0.3379,
+      "step": 144
+    },
+    {
+      "epoch": 4.64,
+      "grad_norm": 0.7299221754074097,
+      "learning_rate": 0.0001596774193548387,
+      "loss": 0.2989,
+      "step": 145
+    },
+    {
+      "epoch": 4.672,
+      "grad_norm": 0.7909884452819824,
+      "learning_rate": 0.00015870967741935484,
+      "loss": 0.3675,
+      "step": 146
+    },
+    {
+      "epoch": 4.704,
+      "grad_norm": 0.7321597933769226,
+      "learning_rate": 0.00015774193548387093,
+      "loss": 0.3243,
+      "step": 147
+    },
+    {
+      "epoch": 4.736,
+      "grad_norm": 0.7196181416511536,
+      "learning_rate": 0.00015677419354838708,
+      "loss": 0.2709,
+      "step": 148
+    },
+    {
+      "epoch": 4.768,
+      "grad_norm": 0.7918142676353455,
+      "learning_rate": 0.00015580645161290322,
+      "loss": 0.3934,
+      "step": 149
+    },
+    {
+      "epoch": 4.8,
+      "grad_norm": 0.8657622337341309,
+      "learning_rate": 0.00015483870967741934,
+      "loss": 0.3583,
+      "step": 150
+    },
+    {
+      "epoch": 4.832,
+      "grad_norm": 0.8207722306251526,
+      "learning_rate": 0.00015387096774193549,
+      "loss": 0.412,
+      "step": 151
+    },
+    {
+      "epoch": 4.864,
+      "grad_norm": 0.7206109166145325,
+      "learning_rate": 0.00015290322580645158,
+      "loss": 0.3594,
+      "step": 152
+    },
+    {
+      "epoch": 4.896,
+      "grad_norm": 0.8529183864593506,
+      "learning_rate": 0.00015193548387096772,
+      "loss": 0.512,
+      "step": 153
+    },
+    {
+      "epoch": 4.928,
+      "grad_norm": 0.6895930171012878,
+      "learning_rate": 0.00015096774193548384,
+      "loss": 0.333,
+      "step": 154
+    },
+    {
+      "epoch": 4.96,
+      "grad_norm": 0.7422910332679749,
+      "learning_rate": 0.00015,
+      "loss": 0.2872,
+      "step": 155
+    },
+    {
+      "epoch": 4.992,
+      "grad_norm": 0.7366386651992798,
+      "learning_rate": 0.0001490322580645161,
+      "loss": 0.3415,
+      "step": 156
+    },
+    {
+      "epoch": 5.024,
+      "grad_norm": 2.1416280269622803,
+      "learning_rate": 0.00014806451612903225,
+      "loss": 0.9961,
+      "step": 157
+    },
+    {
+      "epoch": 5.056,
+      "grad_norm": 0.7944900393486023,
+      "learning_rate": 0.00014709677419354837,
+      "loss": 0.3372,
+      "step": 158
+    },
+    {
+      "epoch": 5.088,
+      "grad_norm": 0.7071006298065186,
+      "learning_rate": 0.00014612903225806452,
+      "loss": 0.2732,
+      "step": 159
+    },
+    {
+      "epoch": 5.12,
+      "grad_norm": 0.7874396443367004,
+      "learning_rate": 0.00014516129032258063,
+      "loss": 0.2861,
+      "step": 160
+    },
+    {
+      "epoch": 5.152,
+      "grad_norm": 0.8244249224662781,
+      "learning_rate": 0.00014419354838709675,
+      "loss": 0.3428,
+      "step": 161
+    },
+    {
+      "epoch": 5.184,
+      "grad_norm": 0.81637042760849,
+      "learning_rate": 0.0001432258064516129,
+      "loss": 0.3037,
+      "step": 162
+    },
+    {
+      "epoch": 5.216,
+      "grad_norm": 0.9916559457778931,
+      "learning_rate": 0.00014225806451612902,
+      "loss": 0.3337,
+      "step": 163
+    },
+    {
+      "epoch": 5.248,
+      "grad_norm": 0.9077599048614502,
+      "learning_rate": 0.00014129032258064514,
+      "loss": 0.287,
+      "step": 164
+    },
+    {
+      "epoch": 5.28,
+      "grad_norm": 0.9824132919311523,
+      "learning_rate": 0.00014032258064516128,
+      "loss": 0.3852,
+      "step": 165
+    },
+    {
+      "epoch": 5.312,
+      "grad_norm": 1.0016467571258545,
+      "learning_rate": 0.0001393548387096774,
+      "loss": 0.3234,
+      "step": 166
+    },
+    {
+      "epoch": 5.344,
+      "grad_norm": 0.8697543144226074,
+      "learning_rate": 0.00013838709677419355,
+      "loss": 0.2848,
+      "step": 167
+    },
+    {
+      "epoch": 5.376,
+      "grad_norm": 0.8214029669761658,
+      "learning_rate": 0.00013741935483870966,
+      "loss": 0.3377,
+      "step": 168
+    },
+    {
+      "epoch": 5.408,
+      "grad_norm": 0.9105691313743591,
+      "learning_rate": 0.00013645161290322578,
+      "loss": 0.2944,
+      "step": 169
+    },
+    {
+      "epoch": 5.44,
+      "grad_norm": 0.9642040133476257,
+      "learning_rate": 0.00013548387096774193,
+      "loss": 0.3624,
+      "step": 170
+    },
+    {
+      "epoch": 5.4719999999999995,
+      "grad_norm": 0.9218887686729431,
+      "learning_rate": 0.00013451612903225805,
+      "loss": 0.3938,
+      "step": 171
+    },
+    {
+      "epoch": 5.504,
+      "grad_norm": 0.8704710006713867,
+      "learning_rate": 0.0001335483870967742,
+      "loss": 0.3629,
+      "step": 172
+    },
+    {
+      "epoch": 5.536,
+      "grad_norm": 0.8207693099975586,
+      "learning_rate": 0.0001325806451612903,
+      "loss": 0.3169,
+      "step": 173
+    },
+    {
+      "epoch": 5.568,
+      "grad_norm": 0.9315701127052307,
+      "learning_rate": 0.00013161290322580643,
+      "loss": 0.429,
+      "step": 174
+    },
+    {
+      "epoch": 5.6,
+      "grad_norm": 0.860234260559082,
+      "learning_rate": 0.00013064516129032258,
+      "loss": 0.3842,
+      "step": 175
+    },
+    {
+      "epoch": 5.632,
+      "grad_norm": 0.8927604556083679,
+      "learning_rate": 0.0001296774193548387,
+      "loss": 0.3405,
+      "step": 176
+    },
+    {
+      "epoch": 5.664,
+      "grad_norm": 0.8084587454795837,
+      "learning_rate": 0.0001287096774193548,
+      "loss": 0.306,
+      "step": 177
+    },
+    {
+      "epoch": 5.696,
+      "grad_norm": 0.9102941155433655,
+      "learning_rate": 0.00012774193548387096,
+      "loss": 0.3285,
+      "step": 178
+    },
+    {
+      "epoch": 5.728,
+      "grad_norm": 0.763113796710968,
+      "learning_rate": 0.0001267741935483871,
+      "loss": 0.2729,
+      "step": 179
+    },
+    {
+      "epoch": 5.76,
+      "grad_norm": 0.8704251646995544,
+      "learning_rate": 0.00012580645161290322,
+      "loss": 0.3164,
+      "step": 180
+    },
+    {
+      "epoch": 5.792,
+      "grad_norm": 0.9634932279586792,
+      "learning_rate": 0.00012483870967741934,
+      "loss": 0.2939,
+      "step": 181
+    },
+    {
+      "epoch": 5.824,
+      "grad_norm": 1.1567790508270264,
+      "learning_rate": 0.00012387096774193546,
+      "loss": 0.3076,
+      "step": 182
+    },
+    {
+      "epoch": 5.856,
+      "grad_norm": 0.9096764922142029,
+      "learning_rate": 0.0001229032258064516,
+      "loss": 0.3289,
+      "step": 183
+    },
+    {
+      "epoch": 5.888,
+      "grad_norm": 0.9840425848960876,
+      "learning_rate": 0.00012193548387096773,
+      "loss": 0.2772,
+      "step": 184
+    },
+    {
+      "epoch": 5.92,
+      "grad_norm": 0.725844144821167,
+      "learning_rate": 0.00012096774193548386,
+      "loss": 0.2151,
+      "step": 185
+    },
+    {
+      "epoch": 5.952,
+      "grad_norm": 0.8343638181686401,
+      "learning_rate": 0.00011999999999999999,
+      "loss": 0.3825,
+      "step": 186
+    },
+    {
+      "epoch": 5.984,
+      "grad_norm": 0.8040199279785156,
+      "learning_rate": 0.00011903225806451612,
+      "loss": 0.2571,
+      "step": 187
+    },
+    {
+      "epoch": 6.016,
+      "grad_norm": 1.6932090520858765,
+      "learning_rate": 0.00011806451612903225,
+      "loss": 0.5538,
+      "step": 188
+    },
+    {
+      "epoch": 6.048,
+      "grad_norm": 0.744048535823822,
+      "learning_rate": 0.00011709677419354837,
+      "loss": 0.2335,
+      "step": 189
+    },
+    {
+      "epoch": 6.08,
+      "grad_norm": 0.6974924206733704,
+      "learning_rate": 0.0001161290322580645,
+      "loss": 0.2891,
+      "step": 190
+    },
+    {
+      "epoch": 6.112,
+      "grad_norm": 0.7202953696250916,
+      "learning_rate": 0.00011516129032258062,
+      "loss": 0.2017,
+      "step": 191
+    },
+    {
+      "epoch": 6.144,
+      "grad_norm": 0.8437547087669373,
+      "learning_rate": 0.00011419354838709676,
+      "loss": 0.2175,
+      "step": 192
+    },
+    {
+      "epoch": 6.176,
+      "grad_norm": 1.0741796493530273,
+      "learning_rate": 0.0001132258064516129,
+      "loss": 0.3913,
+      "step": 193
+    },
+    {
+      "epoch": 6.208,
+      "grad_norm": 1.031754493713379,
+      "learning_rate": 0.00011225806451612902,
+      "loss": 0.298,
+      "step": 194
+    },
+    {
+      "epoch": 6.24,
+      "grad_norm": 0.9575178027153015,
+      "learning_rate": 0.00011129032258064515,
+      "loss": 0.3201,
+      "step": 195
+    },
+    {
+      "epoch": 6.272,
+      "grad_norm": 0.9503082633018494,
+      "learning_rate": 0.00011032258064516128,
+      "loss": 0.2005,
+      "step": 196
+    },
+    {
+      "epoch": 6.304,
+      "grad_norm": 1.2572892904281616,
+      "learning_rate": 0.0001093548387096774,
+      "loss": 0.3045,
+      "step": 197
+    },
+    {
+      "epoch": 6.336,
+      "grad_norm": 1.5667368173599243,
+      "learning_rate": 0.00010838709677419353,
+      "loss": 0.4053,
+      "step": 198
+    },
+    {
+      "epoch": 6.368,
+      "grad_norm": 0.9439151883125305,
+      "learning_rate": 0.00010741935483870968,
+      "loss": 0.2721,
+      "step": 199
+    },
+    {
+      "epoch": 6.4,
+      "grad_norm": 1.0985567569732666,
+      "learning_rate": 0.0001064516129032258,
+      "loss": 0.2543,
+      "step": 200
+    },
+    {
+      "epoch": 6.432,
+      "grad_norm": 0.789880633354187,
+      "learning_rate": 0.00010548387096774193,
+      "loss": 0.2148,
+      "step": 201
+    },
+    {
+      "epoch": 6.464,
+      "grad_norm": 0.9937541484832764,
+      "learning_rate": 0.00010451612903225805,
+      "loss": 0.2343,
+      "step": 202
+    },
+    {
+      "epoch": 6.496,
+      "grad_norm": 0.9496509432792664,
+      "learning_rate": 0.00010354838709677418,
+      "loss": 0.2576,
+      "step": 203
+    },
+    {
+      "epoch": 6.5280000000000005,
+      "grad_norm": 0.9214590191841125,
+      "learning_rate": 0.00010258064516129031,
+      "loss": 0.3067,
+      "step": 204
+    },
+    {
+      "epoch": 6.5600000000000005,
+      "grad_norm": 0.8984239101409912,
+      "learning_rate": 0.00010161290322580643,
+      "loss": 0.2471,
+      "step": 205
+    },
+    {
+      "epoch": 6.592,
+      "grad_norm": 0.8055192232131958,
+      "learning_rate": 0.00010064516129032258,
+      "loss": 0.2234,
+      "step": 206
+    },
+    {
+      "epoch": 6.624,
+      "grad_norm": 0.769008219242096,
+      "learning_rate": 9.967741935483871e-05,
+      "loss": 0.1963,
+      "step": 207
+    },
+    {
+      "epoch": 6.656,
+      "grad_norm": 0.7947174310684204,
+      "learning_rate": 9.870967741935483e-05,
+      "loss": 0.2165,
+      "step": 208
+    },
+    {
+      "epoch": 6.688,
+      "grad_norm": 1.0192420482635498,
+      "learning_rate": 9.774193548387096e-05,
+      "loss": 0.2581,
+      "step": 209
+    },
+    {
+      "epoch": 6.72,
+      "grad_norm": 1.0067439079284668,
+      "learning_rate": 9.677419354838708e-05,
+      "loss": 0.2394,
+      "step": 210
+    },
+    {
+      "epoch": 6.752,
+      "grad_norm": 1.0539058446884155,
+      "learning_rate": 9.580645161290321e-05,
+      "loss": 0.2526,
+      "step": 211
+    },
+    {
+      "epoch": 6.784,
+      "grad_norm": 1.130011796951294,
+      "learning_rate": 9.483870967741934e-05,
+      "loss": 0.3339,
+      "step": 212
+    },
+    {
+      "epoch": 6.816,
+      "grad_norm": 0.9603860378265381,
+      "learning_rate": 9.387096774193548e-05,
+      "loss": 0.2808,
+      "step": 213
+    },
+    {
+      "epoch": 6.848,
+      "grad_norm": 1.0667173862457275,
+      "learning_rate": 9.290322580645161e-05,
+      "loss": 0.3025,
+      "step": 214
+    },
+    {
+      "epoch": 6.88,
+      "grad_norm": 0.9093402624130249,
+      "learning_rate": 9.193548387096774e-05,
+      "loss": 0.2698,
+      "step": 215
+    },
+    {
+      "epoch": 6.912,
+      "grad_norm": 0.8621392846107483,
+      "learning_rate": 9.096774193548386e-05,
+      "loss": 0.2259,
+      "step": 216
+    },
+    {
+      "epoch": 6.944,
+      "grad_norm": 1.035175085067749,
+      "learning_rate": 8.999999999999999e-05,
+      "loss": 0.3156,
+      "step": 217
+    },
+    {
+      "epoch": 6.976,
+      "grad_norm": 1.0241689682006836,
+      "learning_rate": 8.903225806451611e-05,
+      "loss": 0.2723,
+      "step": 218
+    },
+    {
+      "epoch": 7.008,
+      "grad_norm": 1.735946536064148,
+      "learning_rate": 8.806451612903224e-05,
+      "loss": 0.411,
+      "step": 219
+    },
+    {
+      "epoch": 7.04,
+      "grad_norm": 0.8678178191184998,
+      "learning_rate": 8.709677419354839e-05,
+      "loss": 0.2415,
+      "step": 220
+    },
+    {
+      "epoch": 7.072,
+      "grad_norm": 0.7134645581245422,
+      "learning_rate": 8.612903225806451e-05,
+      "loss": 0.1509,
+      "step": 221
+    },
+    {
+      "epoch": 7.104,
+      "grad_norm": 0.8543497920036316,
+      "learning_rate": 8.516129032258064e-05,
+      "loss": 0.2459,
+      "step": 222
+    },
+    {
+      "epoch": 7.136,
+      "grad_norm": 0.9644029140472412,
+      "learning_rate": 8.419354838709677e-05,
+      "loss": 0.2828,
+      "step": 223
+    },
+    {
+      "epoch": 7.168,
+      "grad_norm": 0.8568740487098694,
+      "learning_rate": 8.322580645161289e-05,
+      "loss": 0.1936,
+      "step": 224
+    },
+    {
+      "epoch": 7.2,
+      "grad_norm": 1.005867600440979,
+      "learning_rate": 8.225806451612902e-05,
+      "loss": 0.2678,
+      "step": 225
+    },
+    {
+      "epoch": 7.232,
+      "grad_norm": 0.9942033290863037,
+      "learning_rate": 8.129032258064517e-05,
+      "loss": 0.2111,
+      "step": 226
+    },
+    {
+      "epoch": 7.264,
+      "grad_norm": 0.9886007905006409,
+      "learning_rate": 8.032258064516129e-05,
+      "loss": 0.2375,
+      "step": 227
+    },
+    {
+      "epoch": 7.296,
+      "grad_norm": 1.0586844682693481,
+      "learning_rate": 7.935483870967742e-05,
+      "loss": 0.2385,
+      "step": 228
+    },
+    {
+      "epoch": 7.328,
+      "grad_norm": 1.026432991027832,
+      "learning_rate": 7.838709677419354e-05,
+      "loss": 0.2139,
+      "step": 229
+    },
+    {
+      "epoch": 7.36,
+      "grad_norm": 1.0039665699005127,
+      "learning_rate": 7.741935483870967e-05,
+      "loss": 0.2211,
+      "step": 230
+    },
+    {
+      "epoch": 7.392,
+      "grad_norm": 1.1125057935714722,
+      "learning_rate": 7.645161290322579e-05,
+      "loss": 0.2725,
+      "step": 231
+    },
+    {
+      "epoch": 7.424,
+      "grad_norm": 0.9078079462051392,
+      "learning_rate": 7.548387096774192e-05,
+      "loss": 0.1965,
+      "step": 232
+    },
+    {
+      "epoch": 7.456,
+      "grad_norm": 0.8247030377388,
+      "learning_rate": 7.451612903225805e-05,
+      "loss": 0.1502,
+      "step": 233
+    },
+    {
+      "epoch": 7.4879999999999995,
+      "grad_norm": 1.1396474838256836,
+      "learning_rate": 7.354838709677418e-05,
+      "loss": 0.37,
+      "step": 234
+    },
+    {
+      "epoch": 7.52,
+      "grad_norm": 0.753663182258606,
+      "learning_rate": 7.258064516129032e-05,
+      "loss": 0.1627,
+      "step": 235
+    },
+    {
+      "epoch": 7.552,
+      "grad_norm": 0.7927701473236084,
+      "learning_rate": 7.161290322580645e-05,
+      "loss": 0.1684,
+      "step": 236
+    },
+    {
+      "epoch": 7.584,
+      "grad_norm": 0.9258756637573242,
+      "learning_rate": 7.064516129032257e-05,
+      "loss": 0.213,
+      "step": 237
+    },
+    {
+      "epoch": 7.616,
+      "grad_norm": 0.8111560940742493,
+      "learning_rate": 6.96774193548387e-05,
+      "loss": 0.1998,
+      "step": 238
+    },
+    {
+      "epoch": 7.648,
+      "grad_norm": 0.8484370708465576,
+      "learning_rate": 6.870967741935483e-05,
+      "loss": 0.1307,
+      "step": 239
+    },
+    {
+      "epoch": 7.68,
+      "grad_norm": 0.9123087525367737,
+      "learning_rate": 6.774193548387096e-05,
+      "loss": 0.2529,
+      "step": 240
+    },
+    {
+      "epoch": 7.712,
+      "grad_norm": 1.0526336431503296,
+      "learning_rate": 6.67741935483871e-05,
+      "loss": 0.2468,
+      "step": 241
+    },
+    {
+      "epoch": 7.744,
+      "grad_norm": 1.0104210376739502,
+      "learning_rate": 6.580645161290322e-05,
+      "loss": 0.23,
+      "step": 242
+    },
+    {
+      "epoch": 7.776,
+      "grad_norm": 0.8749745488166809,
+      "learning_rate": 6.483870967741935e-05,
+      "loss": 0.1973,
+      "step": 243
+    },
+    {
+      "epoch": 7.808,
+      "grad_norm": 0.9921355247497559,
+      "learning_rate": 6.387096774193548e-05,
+      "loss": 0.2144,
+      "step": 244
+    },
+    {
+      "epoch": 7.84,
+      "grad_norm": 0.8243810534477234,
+      "learning_rate": 6.290322580645161e-05,
+      "loss": 0.1531,
+      "step": 245
+    },
+    {
+      "epoch": 7.872,
+      "grad_norm": 1.0764353275299072,
+      "learning_rate": 6.193548387096773e-05,
+      "loss": 0.2763,
+      "step": 246
+    },
+    {
+      "epoch": 7.904,
+      "grad_norm": 1.1754212379455566,
+      "learning_rate": 6.096774193548386e-05,
+      "loss": 0.2249,
+      "step": 247
+    },
+    {
+      "epoch": 7.936,
+      "grad_norm": 0.8588422536849976,
+      "learning_rate": 5.9999999999999995e-05,
+      "loss": 0.1782,
+      "step": 248
+    },
+    {
+      "epoch": 7.968,
+      "grad_norm": 1.045143961906433,
+      "learning_rate": 5.903225806451613e-05,
+      "loss": 0.2789,
+      "step": 249
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 1.9824038743972778,
+      "learning_rate": 5.806451612903225e-05,
+      "loss": 0.3057,
+      "step": 250
+    },
+    {
+      "epoch": 8.032,
+      "grad_norm": 0.9252362847328186,
+      "learning_rate": 5.709677419354838e-05,
+      "loss": 0.2221,
+      "step": 251
+    },
+    {
+      "epoch": 8.064,
+      "grad_norm": 0.8381021022796631,
+      "learning_rate": 5.612903225806451e-05,
+      "loss": 0.2639,
+      "step": 252
+    },
+    {
+      "epoch": 8.096,
+      "grad_norm": 0.9777012467384338,
+      "learning_rate": 5.516129032258064e-05,
+      "loss": 0.1533,
+      "step": 253
+    },
+    {
+      "epoch": 8.128,
+      "grad_norm": 0.8053516745567322,
+      "learning_rate": 5.419354838709677e-05,
+      "loss": 0.1883,
+      "step": 254
+    },
+    {
+      "epoch": 8.16,
+      "grad_norm": 0.8703336119651794,
+      "learning_rate": 5.32258064516129e-05,
+      "loss": 0.2079,
+      "step": 255
+    },
+    {
+      "epoch": 8.192,
+      "grad_norm": 0.8113718032836914,
+      "learning_rate": 5.2258064516129025e-05,
+      "loss": 0.1609,
+      "step": 256
+    },
+    {
+      "epoch": 8.224,
+      "grad_norm": 1.0667418241500854,
+      "learning_rate": 5.129032258064516e-05,
+      "loss": 0.2544,
+      "step": 257
+    },
+    {
+      "epoch": 8.256,
+      "grad_norm": 0.7853135466575623,
+      "learning_rate": 5.032258064516129e-05,
+      "loss": 0.1391,
+      "step": 258
+    },
+    {
+      "epoch": 8.288,
+      "grad_norm": 0.9970865845680237,
+      "learning_rate": 4.9354838709677415e-05,
+      "loss": 0.2305,
+      "step": 259
+    },
+    {
+      "epoch": 8.32,
+      "grad_norm": 12.063047409057617,
+      "learning_rate": 4.838709677419354e-05,
+      "loss": 0.189,
+      "step": 260
+    },
+    {
+      "epoch": 8.352,
+      "grad_norm": 1.2325772047042847,
+      "learning_rate": 4.741935483870967e-05,
+      "loss": 0.2308,
+      "step": 261
+    },
+    {
+      "epoch": 8.384,
+      "grad_norm": 1.1118851900100708,
+      "learning_rate": 4.6451612903225805e-05,
+      "loss": 0.2009,
+      "step": 262
+    },
+    {
+      "epoch": 8.416,
+      "grad_norm": 1.0783390998840332,
+      "learning_rate": 4.548387096774193e-05,
+      "loss": 0.2276,
+      "step": 263
+    },
+    {
+      "epoch": 8.448,
+      "grad_norm": 1.2127933502197266,
+      "learning_rate": 4.4516129032258055e-05,
+      "loss": 0.2046,
+      "step": 264
+    },
+    {
+      "epoch": 8.48,
+      "grad_norm": 1.1135843992233276,
+      "learning_rate": 4.3548387096774194e-05,
+      "loss": 0.1791,
+      "step": 265
+    },
+    {
+      "epoch": 8.512,
+      "grad_norm": 0.8666661381721497,
+      "learning_rate": 4.258064516129032e-05,
+      "loss": 0.1287,
+      "step": 266
+    },
+    {
+      "epoch": 8.544,
+      "grad_norm": 0.8430101275444031,
+      "learning_rate": 4.1612903225806445e-05,
+      "loss": 0.1475,
+      "step": 267
+    },
+    {
+      "epoch": 8.576,
+      "grad_norm": 0.7744110822677612,
+      "learning_rate": 4.0645161290322584e-05,
+      "loss": 0.1458,
+      "step": 268
+    },
+    {
+      "epoch": 8.608,
+      "grad_norm": 1.4067776203155518,
+      "learning_rate": 3.967741935483871e-05,
+      "loss": 0.2189,
+      "step": 269
+    },
+    {
+      "epoch": 8.64,
+      "grad_norm": 0.8347670435905457,
+      "learning_rate": 3.8709677419354835e-05,
+      "loss": 0.1602,
+      "step": 270
+    },
+    {
+      "epoch": 8.672,
+      "grad_norm": 0.7643276453018188,
+      "learning_rate": 3.774193548387096e-05,
+      "loss": 0.1363,
+      "step": 271
+    },
+    {
+      "epoch": 8.704,
+      "grad_norm": 0.898059606552124,
+      "learning_rate": 3.677419354838709e-05,
+      "loss": 0.156,
+      "step": 272
+    },
+    {
+      "epoch": 8.736,
+      "grad_norm": 0.8416333198547363,
+      "learning_rate": 3.5806451612903225e-05,
+      "loss": 0.1754,
+      "step": 273
+    },
+    {
+      "epoch": 8.768,
+      "grad_norm": 0.8691906929016113,
+      "learning_rate": 3.483870967741935e-05,
+      "loss": 0.1808,
+      "step": 274
+    },
+    {
+      "epoch": 8.8,
+      "grad_norm": 1.062111496925354,
+      "learning_rate": 3.387096774193548e-05,
+      "loss": 0.2559,
+      "step": 275
+    },
+    {
+      "epoch": 8.832,
+      "grad_norm": 0.881698727607727,
+      "learning_rate": 3.290322580645161e-05,
+      "loss": 0.1732,
+      "step": 276
+    },
+    {
+      "epoch": 8.864,
+      "grad_norm": 0.8446074724197388,
+      "learning_rate": 3.193548387096774e-05,
+      "loss": 0.1833,
+      "step": 277
+    },
+    {
+      "epoch": 8.896,
+      "grad_norm": 0.9393475651741028,
+      "learning_rate": 3.0967741935483865e-05,
+      "loss": 0.2165,
+      "step": 278
+    },
+    {
+      "epoch": 8.928,
+      "grad_norm": 0.8838346004486084,
+      "learning_rate": 2.9999999999999997e-05,
+      "loss": 0.146,
+      "step": 279
+    },
+    {
+      "epoch": 8.96,
+      "grad_norm": 0.8380343914031982,
+      "learning_rate": 2.9032258064516126e-05,
+      "loss": 0.1721,
+      "step": 280
+    },
+    {
+      "epoch": 8.992,
+      "grad_norm": 0.8561931252479553,
+      "learning_rate": 2.8064516129032255e-05,
+      "loss": 0.1519,
+      "step": 281
+    },
+    {
+      "epoch": 9.024,
+      "grad_norm": 1.6088253259658813,
+      "learning_rate": 2.7096774193548384e-05,
+      "loss": 0.2658,
+      "step": 282
+    },
+    {
+      "epoch": 9.056,
+      "grad_norm": 0.8154093027114868,
+      "learning_rate": 2.6129032258064513e-05,
+      "loss": 0.1693,
+      "step": 283
+    },
+    {
+      "epoch": 9.088,
+      "grad_norm": 0.7722072005271912,
+      "learning_rate": 2.5161290322580645e-05,
+      "loss": 0.1853,
+      "step": 284
+    },
+    {
+      "epoch": 9.12,
+      "grad_norm": 0.8294870257377625,
+      "learning_rate": 2.419354838709677e-05,
+      "loss": 0.1736,
+      "step": 285
+    },
+    {
+      "epoch": 9.152,
+      "grad_norm": 0.7481442093849182,
+      "learning_rate": 2.3225806451612902e-05,
+      "loss": 0.1544,
+      "step": 286
+    },
+    {
+      "epoch": 9.184,
+      "grad_norm": 0.923413872718811,
+      "learning_rate": 2.2258064516129028e-05,
+      "loss": 0.2162,
+      "step": 287
+    },
+    {
+      "epoch": 9.216,
+      "grad_norm": 0.8326953053474426,
+      "learning_rate": 2.129032258064516e-05,
+      "loss": 0.1926,
+      "step": 288
+    },
+    {
+      "epoch": 9.248,
+      "grad_norm": 0.7642485499382019,
+      "learning_rate": 2.0322580645161292e-05,
+      "loss": 0.1555,
+      "step": 289
+    },
+    {
+      "epoch": 9.28,
+      "grad_norm": 0.7902241945266724,
+      "learning_rate": 1.9354838709677417e-05,
+      "loss": 0.1459,
+      "step": 290
+    },
+    {
+      "epoch": 9.312,
+      "grad_norm": 0.7414844036102295,
+      "learning_rate": 1.8387096774193546e-05,
+      "loss": 0.1425,
+      "step": 291
+    },
+    {
+      "epoch": 9.344,
+      "grad_norm": 0.7870174646377563,
+      "learning_rate": 1.7419354838709675e-05,
+      "loss": 0.1853,
+      "step": 292
+    },
+    {
+      "epoch": 9.376,
+      "grad_norm": 0.9091981649398804,
+      "learning_rate": 1.6451612903225804e-05,
+      "loss": 0.1666,
+      "step": 293
+    },
+    {
+      "epoch": 9.408,
+      "grad_norm": 0.8651584386825562,
+      "learning_rate": 1.5483870967741933e-05,
+      "loss": 0.174,
+      "step": 294
+    },
+    {
+      "epoch": 9.44,
+      "grad_norm": 0.7866891622543335,
+      "learning_rate": 1.4516129032258063e-05,
+      "loss": 0.1478,
+      "step": 295
+    },
+    {
+      "epoch": 9.472,
+      "grad_norm": 0.717932403087616,
+      "learning_rate": 1.3548387096774192e-05,
+      "loss": 0.1425,
+      "step": 296
+    },
+    {
+      "epoch": 9.504,
+      "grad_norm": 1.0217758417129517,
+      "learning_rate": 1.2580645161290322e-05,
+      "loss": 0.1574,
+      "step": 297
+    },
+    {
+      "epoch": 9.536,
+      "grad_norm": 0.8149961829185486,
+      "learning_rate": 1.1612903225806451e-05,
+      "loss": 0.1422,
+      "step": 298
+    },
+    {
+      "epoch": 9.568,
+      "grad_norm": 0.9206218719482422,
+      "learning_rate": 1.064516129032258e-05,
+      "loss": 0.1809,
+      "step": 299
+    },
+    {
+      "epoch": 9.6,
+      "grad_norm": 0.6865082383155823,
+      "learning_rate": 9.677419354838709e-06,
+      "loss": 0.133,
+      "step": 300
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 310,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 7.1102792466432e+16,
+  "train_batch_size": 3,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-300/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:457c697b05fd5daa3c83df8920300c4940c26fb78ace5b5428b7c95d133a0ef4
+size 5560

checkpoint-310/README.md

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

checkpoint-310/adapter_config.json

@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "/home/ubuntu/Apps/DataInf/models/model",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-310/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3c618c18055bfce72d306d6b635cd0ecbd60120c3067688e0d526ab340b6b02
+size 26235704

checkpoint-310/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ef2087b1fbe093489148f4eb3a1c5ef6c381a445db728bd5dffc0f7e1d1f8b9
+size 52563258

checkpoint-310/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9ad5db2e1c1e26a024ec88b44e8e3dd0cd3608c099e37825d10b614778afd4e
+size 14244

checkpoint-310/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e89b1f0ce5285b1ae483386e0af782d4064a7bcec888d6919f207b0b5e5fa62
+size 1064

checkpoint-310/special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "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": "</s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-310/tokenizer.model

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

checkpoint-310/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": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% set system_message = false %}{% endif %}{% for message in loop_messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if loop.index0 == 0 and system_message != false %}{% set content = '<<SYS>>\\n' + system_message + '\\n<</SYS>>\\n\\n' + message['content'] %}{% else %}{% set content = message['content'] %}{% endif %}{% if message['role'] == 'user' %}{{ bos_token + '[INST] ' + content.strip() + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ ' '  + content.strip() + ' ' + eos_token }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

checkpoint-310/trainer_state.json

@@ -0,0 +1,2203 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 9.92,
+  "eval_steps": 500,
+  "global_step": 310,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.032,
+      "grad_norm": 0.3297976851463318,
+      "learning_rate": 0.0002990322580645161,
+      "loss": 1.0389,
+      "step": 1
+    },
+    {
+      "epoch": 0.064,
+      "grad_norm": 0.4069916307926178,
+      "learning_rate": 0.0002980645161290322,
+      "loss": 1.3377,
+      "step": 2
+    },
+    {
+      "epoch": 0.096,
+      "grad_norm": 0.42084500193595886,
+      "learning_rate": 0.00029709677419354836,
+      "loss": 0.9366,
+      "step": 3
+    },
+    {
+      "epoch": 0.128,
+      "grad_norm": 0.4641948938369751,
+      "learning_rate": 0.0002961290322580645,
+      "loss": 1.0086,
+      "step": 4
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.3840750455856323,
+      "learning_rate": 0.00029516129032258065,
+      "loss": 0.8333,
+      "step": 5
+    },
+    {
+      "epoch": 0.192,
+      "grad_norm": 0.4263865053653717,
+      "learning_rate": 0.00029419354838709674,
+      "loss": 0.854,
+      "step": 6
+    },
+    {
+      "epoch": 0.224,
+      "grad_norm": 0.48615148663520813,
+      "learning_rate": 0.0002932258064516129,
+      "loss": 0.9548,
+      "step": 7
+    },
+    {
+      "epoch": 0.256,
+      "grad_norm": 0.44419369101524353,
+      "learning_rate": 0.00029225806451612903,
+      "loss": 0.8482,
+      "step": 8
+    },
+    {
+      "epoch": 0.288,
+      "grad_norm": 0.5317733883857727,
+      "learning_rate": 0.0002912903225806451,
+      "loss": 0.9426,
+      "step": 9
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.47260937094688416,
+      "learning_rate": 0.00029032258064516127,
+      "loss": 0.9816,
+      "step": 10
+    },
+    {
+      "epoch": 0.352,
+      "grad_norm": 0.39063283801078796,
+      "learning_rate": 0.00028935483870967736,
+      "loss": 0.84,
+      "step": 11
+    },
+    {
+      "epoch": 0.384,
+      "grad_norm": 0.39234670996665955,
+      "learning_rate": 0.0002883870967741935,
+      "loss": 0.7476,
+      "step": 12
+    },
+    {
+      "epoch": 0.416,
+      "grad_norm": 0.40661805868148804,
+      "learning_rate": 0.00028741935483870965,
+      "loss": 0.9282,
+      "step": 13
+    },
+    {
+      "epoch": 0.448,
+      "grad_norm": 0.42970865964889526,
+      "learning_rate": 0.0002864516129032258,
+      "loss": 0.7858,
+      "step": 14
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.3780193626880646,
+      "learning_rate": 0.00028548387096774194,
+      "loss": 0.7968,
+      "step": 15
+    },
+    {
+      "epoch": 0.512,
+      "grad_norm": 0.37006014585494995,
+      "learning_rate": 0.00028451612903225803,
+      "loss": 0.6801,
+      "step": 16
+    },
+    {
+      "epoch": 0.544,
+      "grad_norm": 0.3660840392112732,
+      "learning_rate": 0.0002835483870967742,
+      "loss": 0.5914,
+      "step": 17
+    },
+    {
+      "epoch": 0.576,
+      "grad_norm": 0.3270975351333618,
+      "learning_rate": 0.00028258064516129027,
+      "loss": 0.6449,
+      "step": 18
+    },
+    {
+      "epoch": 0.608,
+      "grad_norm": 0.3859024941921234,
+      "learning_rate": 0.0002816129032258064,
+      "loss": 0.8144,
+      "step": 19
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.37092071771621704,
+      "learning_rate": 0.00028064516129032256,
+      "loss": 0.7667,
+      "step": 20
+    },
+    {
+      "epoch": 0.672,
+      "grad_norm": 0.37667015194892883,
+      "learning_rate": 0.0002796774193548387,
+      "loss": 0.7751,
+      "step": 21
+    },
+    {
+      "epoch": 0.704,
+      "grad_norm": 0.3832458555698395,
+      "learning_rate": 0.0002787096774193548,
+      "loss": 0.755,
+      "step": 22
+    },
+    {
+      "epoch": 0.736,
+      "grad_norm": 0.327288419008255,
+      "learning_rate": 0.00027774193548387095,
+      "loss": 0.7178,
+      "step": 23
+    },
+    {
+      "epoch": 0.768,
+      "grad_norm": 0.34552687406539917,
+      "learning_rate": 0.0002767741935483871,
+      "loss": 0.7057,
+      "step": 24
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.3611259460449219,
+      "learning_rate": 0.0002758064516129032,
+      "loss": 0.8159,
+      "step": 25
+    },
+    {
+      "epoch": 0.832,
+      "grad_norm": 0.3345054090023041,
+      "learning_rate": 0.00027483870967741933,
+      "loss": 0.7208,
+      "step": 26
+    },
+    {
+      "epoch": 0.864,
+      "grad_norm": 0.3697254955768585,
+      "learning_rate": 0.0002738709677419355,
+      "loss": 0.8964,
+      "step": 27
+    },
+    {
+      "epoch": 0.896,
+      "grad_norm": 0.3905017375946045,
+      "learning_rate": 0.00027290322580645157,
+      "loss": 0.7794,
+      "step": 28
+    },
+    {
+      "epoch": 0.928,
+      "grad_norm": 0.3715725243091583,
+      "learning_rate": 0.0002719354838709677,
+      "loss": 0.6966,
+      "step": 29
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.3650343120098114,
+      "learning_rate": 0.00027096774193548386,
+      "loss": 0.5761,
+      "step": 30
+    },
+    {
+      "epoch": 0.992,
+      "grad_norm": 0.33932459354400635,
+      "learning_rate": 0.00027,
+      "loss": 0.556,
+      "step": 31
+    },
+    {
+      "epoch": 1.024,
+      "grad_norm": 0.6371742486953735,
+      "learning_rate": 0.0002690322580645161,
+      "loss": 0.847,
+      "step": 32
+    },
+    {
+      "epoch": 1.056,
+      "grad_norm": 0.37499895691871643,
+      "learning_rate": 0.00026806451612903224,
+      "loss": 0.8419,
+      "step": 33
+    },
+    {
+      "epoch": 1.088,
+      "grad_norm": 0.33221954107284546,
+      "learning_rate": 0.0002670967741935484,
+      "loss": 0.6011,
+      "step": 34
+    },
+    {
+      "epoch": 1.12,
+      "grad_norm": 0.344096839427948,
+      "learning_rate": 0.0002661290322580645,
+      "loss": 0.6501,
+      "step": 35
+    },
+    {
+      "epoch": 1.152,
+      "grad_norm": 0.38429391384124756,
+      "learning_rate": 0.0002651612903225806,
+      "loss": 0.8091,
+      "step": 36
+    },
+    {
+      "epoch": 1.184,
+      "grad_norm": 0.38014867901802063,
+      "learning_rate": 0.00026419354838709677,
+      "loss": 0.7668,
+      "step": 37
+    },
+    {
+      "epoch": 1.216,
+      "grad_norm": 0.3352573812007904,
+      "learning_rate": 0.00026322580645161286,
+      "loss": 0.5444,
+      "step": 38
+    },
+    {
+      "epoch": 1.248,
+      "grad_norm": 0.33811062574386597,
+      "learning_rate": 0.000262258064516129,
+      "loss": 0.512,
+      "step": 39
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 0.3998416066169739,
+      "learning_rate": 0.00026129032258064515,
+      "loss": 0.6315,
+      "step": 40
+    },
+    {
+      "epoch": 1.312,
+      "grad_norm": 0.3983341157436371,
+      "learning_rate": 0.0002603225806451613,
+      "loss": 0.5882,
+      "step": 41
+    },
+    {
+      "epoch": 1.3439999999999999,
+      "grad_norm": 0.4585898816585541,
+      "learning_rate": 0.0002593548387096774,
+      "loss": 0.761,
+      "step": 42
+    },
+    {
+      "epoch": 1.376,
+      "grad_norm": 0.4080730080604553,
+      "learning_rate": 0.00025838709677419354,
+      "loss": 0.6716,
+      "step": 43
+    },
+    {
+      "epoch": 1.408,
+      "grad_norm": 0.4068273901939392,
+      "learning_rate": 0.0002574193548387096,
+      "loss": 0.6376,
+      "step": 44
+    },
+    {
+      "epoch": 1.44,
+      "grad_norm": 0.4406949579715729,
+      "learning_rate": 0.00025645161290322577,
+      "loss": 0.4594,
+      "step": 45
+    },
+    {
+      "epoch": 1.472,
+      "grad_norm": 0.34500986337661743,
+      "learning_rate": 0.0002554838709677419,
+      "loss": 0.3672,
+      "step": 46
+    },
+    {
+      "epoch": 1.504,
+      "grad_norm": 0.4760681390762329,
+      "learning_rate": 0.00025451612903225806,
+      "loss": 0.6331,
+      "step": 47
+    },
+    {
+      "epoch": 1.536,
+      "grad_norm": 0.39281558990478516,
+      "learning_rate": 0.0002535483870967742,
+      "loss": 0.5845,
+      "step": 48
+    },
+    {
+      "epoch": 1.568,
+      "grad_norm": 0.4265002906322479,
+      "learning_rate": 0.0002525806451612903,
+      "loss": 0.4461,
+      "step": 49
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 0.40967294573783875,
+      "learning_rate": 0.00025161290322580645,
+      "loss": 0.7011,
+      "step": 50
+    },
+    {
+      "epoch": 1.6320000000000001,
+      "grad_norm": 0.4288088381290436,
+      "learning_rate": 0.00025064516129032254,
+      "loss": 0.6928,
+      "step": 51
+    },
+    {
+      "epoch": 1.6640000000000001,
+      "grad_norm": 0.4356289803981781,
+      "learning_rate": 0.0002496774193548387,
+      "loss": 0.7972,
+      "step": 52
+    },
+    {
+      "epoch": 1.696,
+      "grad_norm": 0.3827487826347351,
+      "learning_rate": 0.0002487096774193548,
+      "loss": 0.2991,
+      "step": 53
+    },
+    {
+      "epoch": 1.728,
+      "grad_norm": 0.40093398094177246,
+      "learning_rate": 0.0002477419354838709,
+      "loss": 0.416,
+      "step": 54
+    },
+    {
+      "epoch": 1.76,
+      "grad_norm": 0.41548973321914673,
+      "learning_rate": 0.00024677419354838707,
+      "loss": 0.5501,
+      "step": 55
+    },
+    {
+      "epoch": 1.792,
+      "grad_norm": 0.4093388617038727,
+      "learning_rate": 0.0002458064516129032,
+      "loss": 0.5557,
+      "step": 56
+    },
+    {
+      "epoch": 1.8239999999999998,
+      "grad_norm": 0.3934040665626526,
+      "learning_rate": 0.00024483870967741936,
+      "loss": 0.602,
+      "step": 57
+    },
+    {
+      "epoch": 1.8559999999999999,
+      "grad_norm": 0.42221033573150635,
+      "learning_rate": 0.00024387096774193545,
+      "loss": 0.6421,
+      "step": 58
+    },
+    {
+      "epoch": 1.888,
+      "grad_norm": 0.4351339340209961,
+      "learning_rate": 0.0002429032258064516,
+      "loss": 0.5615,
+      "step": 59
+    },
+    {
+      "epoch": 1.92,
+      "grad_norm": 0.4319838881492615,
+      "learning_rate": 0.00024193548387096771,
+      "loss": 0.6804,
+      "step": 60
+    },
+    {
+      "epoch": 1.952,
+      "grad_norm": 0.40016525983810425,
+      "learning_rate": 0.00024096774193548386,
+      "loss": 0.5432,
+      "step": 61
+    },
+    {
+      "epoch": 1.984,
+      "grad_norm": 0.3905942440032959,
+      "learning_rate": 0.00023999999999999998,
+      "loss": 0.4187,
+      "step": 62
+    },
+    {
+      "epoch": 2.016,
+      "grad_norm": 0.8056382536888123,
+      "learning_rate": 0.0002390322580645161,
+      "loss": 1.0174,
+      "step": 63
+    },
+    {
+      "epoch": 2.048,
+      "grad_norm": 0.3835236430168152,
+      "learning_rate": 0.00023806451612903224,
+      "loss": 0.5992,
+      "step": 64
+    },
+    {
+      "epoch": 2.08,
+      "grad_norm": 0.41092216968536377,
+      "learning_rate": 0.00023709677419354836,
+      "loss": 0.4746,
+      "step": 65
+    },
+    {
+      "epoch": 2.112,
+      "grad_norm": 0.39536622166633606,
+      "learning_rate": 0.0002361290322580645,
+      "loss": 0.3946,
+      "step": 66
+    },
+    {
+      "epoch": 2.144,
+      "grad_norm": 0.3927665948867798,
+      "learning_rate": 0.0002351612903225806,
+      "loss": 0.5187,
+      "step": 67
+    },
+    {
+      "epoch": 2.176,
+      "grad_norm": 0.39792704582214355,
+      "learning_rate": 0.00023419354838709674,
+      "loss": 0.4568,
+      "step": 68
+    },
+    {
+      "epoch": 2.208,
+      "grad_norm": 0.5023652911186218,
+      "learning_rate": 0.0002332258064516129,
+      "loss": 0.6166,
+      "step": 69
+    },
+    {
+      "epoch": 2.24,
+      "grad_norm": 0.425017774105072,
+      "learning_rate": 0.000232258064516129,
+      "loss": 0.42,
+      "step": 70
+    },
+    {
+      "epoch": 2.2720000000000002,
+      "grad_norm": 0.46458110213279724,
+      "learning_rate": 0.00023129032258064516,
+      "loss": 0.4613,
+      "step": 71
+    },
+    {
+      "epoch": 2.304,
+      "grad_norm": 0.49037960171699524,
+      "learning_rate": 0.00023032258064516125,
+      "loss": 0.5509,
+      "step": 72
+    },
+    {
+      "epoch": 2.336,
+      "grad_norm": 0.5233697891235352,
+      "learning_rate": 0.0002293548387096774,
+      "loss": 0.6396,
+      "step": 73
+    },
+    {
+      "epoch": 2.368,
+      "grad_norm": 0.4720582962036133,
+      "learning_rate": 0.0002283870967741935,
+      "loss": 0.5076,
+      "step": 74
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 0.4900650382041931,
+      "learning_rate": 0.00022741935483870966,
+      "loss": 0.4794,
+      "step": 75
+    },
+    {
+      "epoch": 2.432,
+      "grad_norm": 0.6321704983711243,
+      "learning_rate": 0.0002264516129032258,
+      "loss": 0.6677,
+      "step": 76
+    },
+    {
+      "epoch": 2.464,
+      "grad_norm": 0.5305324792861938,
+      "learning_rate": 0.00022548387096774192,
+      "loss": 0.5102,
+      "step": 77
+    },
+    {
+      "epoch": 2.496,
+      "grad_norm": 0.5799248218536377,
+      "learning_rate": 0.00022451612903225804,
+      "loss": 0.5274,
+      "step": 78
+    },
+    {
+      "epoch": 2.528,
+      "grad_norm": 0.4990101456642151,
+      "learning_rate": 0.00022354838709677416,
+      "loss": 0.5407,
+      "step": 79
+    },
+    {
+      "epoch": 2.56,
+      "grad_norm": 0.4779827296733856,
+      "learning_rate": 0.0002225806451612903,
+      "loss": 0.5166,
+      "step": 80
+    },
+    {
+      "epoch": 2.592,
+      "grad_norm": 0.5140111446380615,
+      "learning_rate": 0.00022161290322580645,
+      "loss": 0.3288,
+      "step": 81
+    },
+    {
+      "epoch": 2.624,
+      "grad_norm": 0.5674853920936584,
+      "learning_rate": 0.00022064516129032257,
+      "loss": 0.666,
+      "step": 82
+    },
+    {
+      "epoch": 2.656,
+      "grad_norm": 0.5277597308158875,
+      "learning_rate": 0.00021967741935483871,
+      "loss": 0.5335,
+      "step": 83
+    },
+    {
+      "epoch": 2.6879999999999997,
+      "grad_norm": 0.6029439568519592,
+      "learning_rate": 0.0002187096774193548,
+      "loss": 0.693,
+      "step": 84
+    },
+    {
+      "epoch": 2.7199999999999998,
+      "grad_norm": 0.5039327144622803,
+      "learning_rate": 0.00021774193548387095,
+      "loss": 0.5728,
+      "step": 85
+    },
+    {
+      "epoch": 2.752,
+      "grad_norm": 0.5564692616462708,
+      "learning_rate": 0.00021677419354838707,
+      "loss": 0.4734,
+      "step": 86
+    },
+    {
+      "epoch": 2.784,
+      "grad_norm": 0.5278319120407104,
+      "learning_rate": 0.00021580645161290322,
+      "loss": 0.5834,
+      "step": 87
+    },
+    {
+      "epoch": 2.816,
+      "grad_norm": 0.5445135831832886,
+      "learning_rate": 0.00021483870967741936,
+      "loss": 0.4642,
+      "step": 88
+    },
+    {
+      "epoch": 2.848,
+      "grad_norm": 0.5394749045372009,
+      "learning_rate": 0.00021387096774193545,
+      "loss": 0.4779,
+      "step": 89
+    },
+    {
+      "epoch": 2.88,
+      "grad_norm": 0.5756134390830994,
+      "learning_rate": 0.0002129032258064516,
+      "loss": 0.5607,
+      "step": 90
+    },
+    {
+      "epoch": 2.912,
+      "grad_norm": 0.48361241817474365,
+      "learning_rate": 0.00021193548387096772,
+      "loss": 0.4278,
+      "step": 91
+    },
+    {
+      "epoch": 2.944,
+      "grad_norm": 0.5017121434211731,
+      "learning_rate": 0.00021096774193548386,
+      "loss": 0.4834,
+      "step": 92
+    },
+    {
+      "epoch": 2.976,
+      "grad_norm": 0.4741989076137543,
+      "learning_rate": 0.00020999999999999998,
+      "loss": 0.468,
+      "step": 93
+    },
+    {
+      "epoch": 3.008,
+      "grad_norm": 1.003368854522705,
+      "learning_rate": 0.0002090322580645161,
+      "loss": 0.8614,
+      "step": 94
+    },
+    {
+      "epoch": 3.04,
+      "grad_norm": 0.4782228469848633,
+      "learning_rate": 0.00020806451612903225,
+      "loss": 0.4111,
+      "step": 95
+    },
+    {
+      "epoch": 3.072,
+      "grad_norm": 0.4558674395084381,
+      "learning_rate": 0.00020709677419354836,
+      "loss": 0.3463,
+      "step": 96
+    },
+    {
+      "epoch": 3.104,
+      "grad_norm": 0.4409371316432953,
+      "learning_rate": 0.0002061290322580645,
+      "loss": 0.2571,
+      "step": 97
+    },
+    {
+      "epoch": 3.136,
+      "grad_norm": 0.5415034890174866,
+      "learning_rate": 0.00020516129032258063,
+      "loss": 0.5707,
+      "step": 98
+    },
+    {
+      "epoch": 3.168,
+      "grad_norm": 0.6157724857330322,
+      "learning_rate": 0.00020419354838709677,
+      "loss": 0.5692,
+      "step": 99
+    },
+    {
+      "epoch": 3.2,
+      "grad_norm": 0.4855688810348511,
+      "learning_rate": 0.00020322580645161287,
+      "loss": 0.3311,
+      "step": 100
+    },
+    {
+      "epoch": 3.232,
+      "grad_norm": 0.569878101348877,
+      "learning_rate": 0.000202258064516129,
+      "loss": 0.4707,
+      "step": 101
+    },
+    {
+      "epoch": 3.2640000000000002,
+      "grad_norm": 0.645232081413269,
+      "learning_rate": 0.00020129032258064516,
+      "loss": 0.5504,
+      "step": 102
+    },
+    {
+      "epoch": 3.296,
+      "grad_norm": 0.5775763392448425,
+      "learning_rate": 0.00020032258064516128,
+      "loss": 0.3651,
+      "step": 103
+    },
+    {
+      "epoch": 3.328,
+      "grad_norm": 0.5808250904083252,
+      "learning_rate": 0.00019935483870967742,
+      "loss": 0.5068,
+      "step": 104
+    },
+    {
+      "epoch": 3.36,
+      "grad_norm": 0.689313530921936,
+      "learning_rate": 0.0001983870967741935,
+      "loss": 0.4936,
+      "step": 105
+    },
+    {
+      "epoch": 3.392,
+      "grad_norm": 0.6571519374847412,
+      "learning_rate": 0.00019741935483870966,
+      "loss": 0.3671,
+      "step": 106
+    },
+    {
+      "epoch": 3.424,
+      "grad_norm": 0.6340517401695251,
+      "learning_rate": 0.00019645161290322578,
+      "loss": 0.4783,
+      "step": 107
+    },
+    {
+      "epoch": 3.456,
+      "grad_norm": 0.7031407952308655,
+      "learning_rate": 0.00019548387096774192,
+      "loss": 0.427,
+      "step": 108
+    },
+    {
+      "epoch": 3.488,
+      "grad_norm": 0.728496789932251,
+      "learning_rate": 0.00019451612903225807,
+      "loss": 0.5497,
+      "step": 109
+    },
+    {
+      "epoch": 3.52,
+      "grad_norm": 0.6106727719306946,
+      "learning_rate": 0.00019354838709677416,
+      "loss": 0.392,
+      "step": 110
+    },
+    {
+      "epoch": 3.552,
+      "grad_norm": 0.5296047329902649,
+      "learning_rate": 0.0001925806451612903,
+      "loss": 0.3412,
+      "step": 111
+    },
+    {
+      "epoch": 3.584,
+      "grad_norm": 0.6282025575637817,
+      "learning_rate": 0.00019161290322580643,
+      "loss": 0.4081,
+      "step": 112
+    },
+    {
+      "epoch": 3.616,
+      "grad_norm": 0.6166461110115051,
+      "learning_rate": 0.00019064516129032257,
+      "loss": 0.4771,
+      "step": 113
+    },
+    {
+      "epoch": 3.648,
+      "grad_norm": 0.5448863506317139,
+      "learning_rate": 0.0001896774193548387,
+      "loss": 0.404,
+      "step": 114
+    },
+    {
+      "epoch": 3.68,
+      "grad_norm": 0.6598389148712158,
+      "learning_rate": 0.0001887096774193548,
+      "loss": 0.3915,
+      "step": 115
+    },
+    {
+      "epoch": 3.7119999999999997,
+      "grad_norm": 0.5567564368247986,
+      "learning_rate": 0.00018774193548387095,
+      "loss": 0.3862,
+      "step": 116
+    },
+    {
+      "epoch": 3.7439999999999998,
+      "grad_norm": 0.6524521708488464,
+      "learning_rate": 0.00018677419354838707,
+      "loss": 0.5315,
+      "step": 117
+    },
+    {
+      "epoch": 3.776,
+      "grad_norm": 0.7040128707885742,
+      "learning_rate": 0.00018580645161290322,
+      "loss": 0.5387,
+      "step": 118
+    },
+    {
+      "epoch": 3.808,
+      "grad_norm": 0.690262496471405,
+      "learning_rate": 0.00018483870967741934,
+      "loss": 0.4877,
+      "step": 119
+    },
+    {
+      "epoch": 3.84,
+      "grad_norm": 0.6928034424781799,
+      "learning_rate": 0.00018387096774193548,
+      "loss": 0.4895,
+      "step": 120
+    },
+    {
+      "epoch": 3.872,
+      "grad_norm": 0.7148469686508179,
+      "learning_rate": 0.00018290322580645157,
+      "loss": 0.4814,
+      "step": 121
+    },
+    {
+      "epoch": 3.904,
+      "grad_norm": 0.6096572875976562,
+      "learning_rate": 0.00018193548387096772,
+      "loss": 0.3403,
+      "step": 122
+    },
+    {
+      "epoch": 3.936,
+      "grad_norm": 0.7132399678230286,
+      "learning_rate": 0.00018096774193548387,
+      "loss": 0.4258,
+      "step": 123
+    },
+    {
+      "epoch": 3.968,
+      "grad_norm": 0.7302684187889099,
+      "learning_rate": 0.00017999999999999998,
+      "loss": 0.7215,
+      "step": 124
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 1.5244004726409912,
+      "learning_rate": 0.00017903225806451613,
+      "loss": 0.8544,
+      "step": 125
+    },
+    {
+      "epoch": 4.032,
+      "grad_norm": 0.6032777428627014,
+      "learning_rate": 0.00017806451612903222,
+      "loss": 0.4183,
+      "step": 126
+    },
+    {
+      "epoch": 4.064,
+      "grad_norm": 0.6349691152572632,
+      "learning_rate": 0.00017709677419354837,
+      "loss": 0.5871,
+      "step": 127
+    },
+    {
+      "epoch": 4.096,
+      "grad_norm": 0.5730060935020447,
+      "learning_rate": 0.00017612903225806449,
+      "loss": 0.3786,
+      "step": 128
+    },
+    {
+      "epoch": 4.128,
+      "grad_norm": 0.6988044381141663,
+      "learning_rate": 0.00017516129032258063,
+      "loss": 0.3216,
+      "step": 129
+    },
+    {
+      "epoch": 4.16,
+      "grad_norm": 0.7379153370857239,
+      "learning_rate": 0.00017419354838709678,
+      "loss": 0.4026,
+      "step": 130
+    },
+    {
+      "epoch": 4.192,
+      "grad_norm": 0.7058238983154297,
+      "learning_rate": 0.00017322580645161287,
+      "loss": 0.4328,
+      "step": 131
+    },
+    {
+      "epoch": 4.224,
+      "grad_norm": 0.80663001537323,
+      "learning_rate": 0.00017225806451612901,
+      "loss": 0.3849,
+      "step": 132
+    },
+    {
+      "epoch": 4.256,
+      "grad_norm": 0.899818480014801,
+      "learning_rate": 0.00017129032258064513,
+      "loss": 0.4191,
+      "step": 133
+    },
+    {
+      "epoch": 4.288,
+      "grad_norm": 0.8538224697113037,
+      "learning_rate": 0.00017032258064516128,
+      "loss": 0.3587,
+      "step": 134
+    },
+    {
+      "epoch": 4.32,
+      "grad_norm": 0.8948169350624084,
+      "learning_rate": 0.00016935483870967742,
+      "loss": 0.3957,
+      "step": 135
+    },
+    {
+      "epoch": 4.352,
+      "grad_norm": 0.7195591926574707,
+      "learning_rate": 0.00016838709677419354,
+      "loss": 0.3361,
+      "step": 136
+    },
+    {
+      "epoch": 4.384,
+      "grad_norm": 0.7769681215286255,
+      "learning_rate": 0.00016741935483870966,
+      "loss": 0.3519,
+      "step": 137
+    },
+    {
+      "epoch": 4.416,
+      "grad_norm": 0.9509867429733276,
+      "learning_rate": 0.00016645161290322578,
+      "loss": 0.4216,
+      "step": 138
+    },
+    {
+      "epoch": 4.448,
+      "grad_norm": 0.7923309206962585,
+      "learning_rate": 0.00016548387096774193,
+      "loss": 0.3999,
+      "step": 139
+    },
+    {
+      "epoch": 4.48,
+      "grad_norm": 0.8961685299873352,
+      "learning_rate": 0.00016451612903225804,
+      "loss": 0.5385,
+      "step": 140
+    },
+    {
+      "epoch": 4.5120000000000005,
+      "grad_norm": 0.7496562004089355,
+      "learning_rate": 0.0001635483870967742,
+      "loss": 0.341,
+      "step": 141
+    },
+    {
+      "epoch": 4.5440000000000005,
+      "grad_norm": 0.8512839674949646,
+      "learning_rate": 0.00016258064516129034,
+      "loss": 0.3847,
+      "step": 142
+    },
+    {
+      "epoch": 4.576,
+      "grad_norm": 0.7487362027168274,
+      "learning_rate": 0.00016161290322580643,
+      "loss": 0.3694,
+      "step": 143
+    },
+    {
+      "epoch": 4.608,
+      "grad_norm": 0.7957774996757507,
+      "learning_rate": 0.00016064516129032257,
+      "loss": 0.3379,
+      "step": 144
+    },
+    {
+      "epoch": 4.64,
+      "grad_norm": 0.7299221754074097,
+      "learning_rate": 0.0001596774193548387,
+      "loss": 0.2989,
+      "step": 145
+    },
+    {
+      "epoch": 4.672,
+      "grad_norm": 0.7909884452819824,
+      "learning_rate": 0.00015870967741935484,
+      "loss": 0.3675,
+      "step": 146
+    },
+    {
+      "epoch": 4.704,
+      "grad_norm": 0.7321597933769226,
+      "learning_rate": 0.00015774193548387093,
+      "loss": 0.3243,
+      "step": 147
+    },
+    {
+      "epoch": 4.736,
+      "grad_norm": 0.7196181416511536,
+      "learning_rate": 0.00015677419354838708,
+      "loss": 0.2709,
+      "step": 148
+    },
+    {
+      "epoch": 4.768,
+      "grad_norm": 0.7918142676353455,
+      "learning_rate": 0.00015580645161290322,
+      "loss": 0.3934,
+      "step": 149
+    },
+    {
+      "epoch": 4.8,
+      "grad_norm": 0.8657622337341309,
+      "learning_rate": 0.00015483870967741934,
+      "loss": 0.3583,
+      "step": 150
+    },
+    {
+      "epoch": 4.832,
+      "grad_norm": 0.8207722306251526,
+      "learning_rate": 0.00015387096774193549,
+      "loss": 0.412,
+      "step": 151
+    },
+    {
+      "epoch": 4.864,
+      "grad_norm": 0.7206109166145325,
+      "learning_rate": 0.00015290322580645158,
+      "loss": 0.3594,
+      "step": 152
+    },
+    {
+      "epoch": 4.896,
+      "grad_norm": 0.8529183864593506,
+      "learning_rate": 0.00015193548387096772,
+      "loss": 0.512,
+      "step": 153
+    },
+    {
+      "epoch": 4.928,
+      "grad_norm": 0.6895930171012878,
+      "learning_rate": 0.00015096774193548384,
+      "loss": 0.333,
+      "step": 154
+    },
+    {
+      "epoch": 4.96,
+      "grad_norm": 0.7422910332679749,
+      "learning_rate": 0.00015,
+      "loss": 0.2872,
+      "step": 155
+    },
+    {
+      "epoch": 4.992,
+      "grad_norm": 0.7366386651992798,
+      "learning_rate": 0.0001490322580645161,
+      "loss": 0.3415,
+      "step": 156
+    },
+    {
+      "epoch": 5.024,
+      "grad_norm": 2.1416280269622803,
+      "learning_rate": 0.00014806451612903225,
+      "loss": 0.9961,
+      "step": 157
+    },
+    {
+      "epoch": 5.056,
+      "grad_norm": 0.7944900393486023,
+      "learning_rate": 0.00014709677419354837,
+      "loss": 0.3372,
+      "step": 158
+    },
+    {
+      "epoch": 5.088,
+      "grad_norm": 0.7071006298065186,
+      "learning_rate": 0.00014612903225806452,
+      "loss": 0.2732,
+      "step": 159
+    },
+    {
+      "epoch": 5.12,
+      "grad_norm": 0.7874396443367004,
+      "learning_rate": 0.00014516129032258063,
+      "loss": 0.2861,
+      "step": 160
+    },
+    {
+      "epoch": 5.152,
+      "grad_norm": 0.8244249224662781,
+      "learning_rate": 0.00014419354838709675,
+      "loss": 0.3428,
+      "step": 161
+    },
+    {
+      "epoch": 5.184,
+      "grad_norm": 0.81637042760849,
+      "learning_rate": 0.0001432258064516129,
+      "loss": 0.3037,
+      "step": 162
+    },
+    {
+      "epoch": 5.216,
+      "grad_norm": 0.9916559457778931,
+      "learning_rate": 0.00014225806451612902,
+      "loss": 0.3337,
+      "step": 163
+    },
+    {
+      "epoch": 5.248,
+      "grad_norm": 0.9077599048614502,
+      "learning_rate": 0.00014129032258064514,
+      "loss": 0.287,
+      "step": 164
+    },
+    {
+      "epoch": 5.28,
+      "grad_norm": 0.9824132919311523,
+      "learning_rate": 0.00014032258064516128,
+      "loss": 0.3852,
+      "step": 165
+    },
+    {
+      "epoch": 5.312,
+      "grad_norm": 1.0016467571258545,
+      "learning_rate": 0.0001393548387096774,
+      "loss": 0.3234,
+      "step": 166
+    },
+    {
+      "epoch": 5.344,
+      "grad_norm": 0.8697543144226074,
+      "learning_rate": 0.00013838709677419355,
+      "loss": 0.2848,
+      "step": 167
+    },
+    {
+      "epoch": 5.376,
+      "grad_norm": 0.8214029669761658,
+      "learning_rate": 0.00013741935483870966,
+      "loss": 0.3377,
+      "step": 168
+    },
+    {
+      "epoch": 5.408,
+      "grad_norm": 0.9105691313743591,
+      "learning_rate": 0.00013645161290322578,
+      "loss": 0.2944,
+      "step": 169
+    },
+    {
+      "epoch": 5.44,
+      "grad_norm": 0.9642040133476257,
+      "learning_rate": 0.00013548387096774193,
+      "loss": 0.3624,
+      "step": 170
+    },
+    {
+      "epoch": 5.4719999999999995,
+      "grad_norm": 0.9218887686729431,
+      "learning_rate": 0.00013451612903225805,
+      "loss": 0.3938,
+      "step": 171
+    },
+    {
+      "epoch": 5.504,
+      "grad_norm": 0.8704710006713867,
+      "learning_rate": 0.0001335483870967742,
+      "loss": 0.3629,
+      "step": 172
+    },
+    {
+      "epoch": 5.536,
+      "grad_norm": 0.8207693099975586,
+      "learning_rate": 0.0001325806451612903,
+      "loss": 0.3169,
+      "step": 173
+    },
+    {
+      "epoch": 5.568,
+      "grad_norm": 0.9315701127052307,
+      "learning_rate": 0.00013161290322580643,
+      "loss": 0.429,
+      "step": 174
+    },
+    {
+      "epoch": 5.6,
+      "grad_norm": 0.860234260559082,
+      "learning_rate": 0.00013064516129032258,
+      "loss": 0.3842,
+      "step": 175
+    },
+    {
+      "epoch": 5.632,
+      "grad_norm": 0.8927604556083679,
+      "learning_rate": 0.0001296774193548387,
+      "loss": 0.3405,
+      "step": 176
+    },
+    {
+      "epoch": 5.664,
+      "grad_norm": 0.8084587454795837,
+      "learning_rate": 0.0001287096774193548,
+      "loss": 0.306,
+      "step": 177
+    },
+    {
+      "epoch": 5.696,
+      "grad_norm": 0.9102941155433655,
+      "learning_rate": 0.00012774193548387096,
+      "loss": 0.3285,
+      "step": 178
+    },
+    {
+      "epoch": 5.728,
+      "grad_norm": 0.763113796710968,
+      "learning_rate": 0.0001267741935483871,
+      "loss": 0.2729,
+      "step": 179
+    },
+    {
+      "epoch": 5.76,
+      "grad_norm": 0.8704251646995544,
+      "learning_rate": 0.00012580645161290322,
+      "loss": 0.3164,
+      "step": 180
+    },
+    {
+      "epoch": 5.792,
+      "grad_norm": 0.9634932279586792,
+      "learning_rate": 0.00012483870967741934,
+      "loss": 0.2939,
+      "step": 181
+    },
+    {
+      "epoch": 5.824,
+      "grad_norm": 1.1567790508270264,
+      "learning_rate": 0.00012387096774193546,
+      "loss": 0.3076,
+      "step": 182
+    },
+    {
+      "epoch": 5.856,
+      "grad_norm": 0.9096764922142029,
+      "learning_rate": 0.0001229032258064516,
+      "loss": 0.3289,
+      "step": 183
+    },
+    {
+      "epoch": 5.888,
+      "grad_norm": 0.9840425848960876,
+      "learning_rate": 0.00012193548387096773,
+      "loss": 0.2772,
+      "step": 184
+    },
+    {
+      "epoch": 5.92,
+      "grad_norm": 0.725844144821167,
+      "learning_rate": 0.00012096774193548386,
+      "loss": 0.2151,
+      "step": 185
+    },
+    {
+      "epoch": 5.952,
+      "grad_norm": 0.8343638181686401,
+      "learning_rate": 0.00011999999999999999,
+      "loss": 0.3825,
+      "step": 186
+    },
+    {
+      "epoch": 5.984,
+      "grad_norm": 0.8040199279785156,
+      "learning_rate": 0.00011903225806451612,
+      "loss": 0.2571,
+      "step": 187
+    },
+    {
+      "epoch": 6.016,
+      "grad_norm": 1.6932090520858765,
+      "learning_rate": 0.00011806451612903225,
+      "loss": 0.5538,
+      "step": 188
+    },
+    {
+      "epoch": 6.048,
+      "grad_norm": 0.744048535823822,
+      "learning_rate": 0.00011709677419354837,
+      "loss": 0.2335,
+      "step": 189
+    },
+    {
+      "epoch": 6.08,
+      "grad_norm": 0.6974924206733704,
+      "learning_rate": 0.0001161290322580645,
+      "loss": 0.2891,
+      "step": 190
+    },
+    {
+      "epoch": 6.112,
+      "grad_norm": 0.7202953696250916,
+      "learning_rate": 0.00011516129032258062,
+      "loss": 0.2017,
+      "step": 191
+    },
+    {
+      "epoch": 6.144,
+      "grad_norm": 0.8437547087669373,
+      "learning_rate": 0.00011419354838709676,
+      "loss": 0.2175,
+      "step": 192
+    },
+    {
+      "epoch": 6.176,
+      "grad_norm": 1.0741796493530273,
+      "learning_rate": 0.0001132258064516129,
+      "loss": 0.3913,
+      "step": 193
+    },
+    {
+      "epoch": 6.208,
+      "grad_norm": 1.031754493713379,
+      "learning_rate": 0.00011225806451612902,
+      "loss": 0.298,
+      "step": 194
+    },
+    {
+      "epoch": 6.24,
+      "grad_norm": 0.9575178027153015,
+      "learning_rate": 0.00011129032258064515,
+      "loss": 0.3201,
+      "step": 195
+    },
+    {
+      "epoch": 6.272,
+      "grad_norm": 0.9503082633018494,
+      "learning_rate": 0.00011032258064516128,
+      "loss": 0.2005,
+      "step": 196
+    },
+    {
+      "epoch": 6.304,
+      "grad_norm": 1.2572892904281616,
+      "learning_rate": 0.0001093548387096774,
+      "loss": 0.3045,
+      "step": 197
+    },
+    {
+      "epoch": 6.336,
+      "grad_norm": 1.5667368173599243,
+      "learning_rate": 0.00010838709677419353,
+      "loss": 0.4053,
+      "step": 198
+    },
+    {
+      "epoch": 6.368,
+      "grad_norm": 0.9439151883125305,
+      "learning_rate": 0.00010741935483870968,
+      "loss": 0.2721,
+      "step": 199
+    },
+    {
+      "epoch": 6.4,
+      "grad_norm": 1.0985567569732666,
+      "learning_rate": 0.0001064516129032258,
+      "loss": 0.2543,
+      "step": 200
+    },
+    {
+      "epoch": 6.432,
+      "grad_norm": 0.789880633354187,
+      "learning_rate": 0.00010548387096774193,
+      "loss": 0.2148,
+      "step": 201
+    },
+    {
+      "epoch": 6.464,
+      "grad_norm": 0.9937541484832764,
+      "learning_rate": 0.00010451612903225805,
+      "loss": 0.2343,
+      "step": 202
+    },
+    {
+      "epoch": 6.496,
+      "grad_norm": 0.9496509432792664,
+      "learning_rate": 0.00010354838709677418,
+      "loss": 0.2576,
+      "step": 203
+    },
+    {
+      "epoch": 6.5280000000000005,
+      "grad_norm": 0.9214590191841125,
+      "learning_rate": 0.00010258064516129031,
+      "loss": 0.3067,
+      "step": 204
+    },
+    {
+      "epoch": 6.5600000000000005,
+      "grad_norm": 0.8984239101409912,
+      "learning_rate": 0.00010161290322580643,
+      "loss": 0.2471,
+      "step": 205
+    },
+    {
+      "epoch": 6.592,
+      "grad_norm": 0.8055192232131958,
+      "learning_rate": 0.00010064516129032258,
+      "loss": 0.2234,
+      "step": 206
+    },
+    {
+      "epoch": 6.624,
+      "grad_norm": 0.769008219242096,
+      "learning_rate": 9.967741935483871e-05,
+      "loss": 0.1963,
+      "step": 207
+    },
+    {
+      "epoch": 6.656,
+      "grad_norm": 0.7947174310684204,
+      "learning_rate": 9.870967741935483e-05,
+      "loss": 0.2165,
+      "step": 208
+    },
+    {
+      "epoch": 6.688,
+      "grad_norm": 1.0192420482635498,
+      "learning_rate": 9.774193548387096e-05,
+      "loss": 0.2581,
+      "step": 209
+    },
+    {
+      "epoch": 6.72,
+      "grad_norm": 1.0067439079284668,
+      "learning_rate": 9.677419354838708e-05,
+      "loss": 0.2394,
+      "step": 210
+    },
+    {
+      "epoch": 6.752,
+      "grad_norm": 1.0539058446884155,
+      "learning_rate": 9.580645161290321e-05,
+      "loss": 0.2526,
+      "step": 211
+    },
+    {
+      "epoch": 6.784,
+      "grad_norm": 1.130011796951294,
+      "learning_rate": 9.483870967741934e-05,
+      "loss": 0.3339,
+      "step": 212
+    },
+    {
+      "epoch": 6.816,
+      "grad_norm": 0.9603860378265381,
+      "learning_rate": 9.387096774193548e-05,
+      "loss": 0.2808,
+      "step": 213
+    },
+    {
+      "epoch": 6.848,
+      "grad_norm": 1.0667173862457275,
+      "learning_rate": 9.290322580645161e-05,
+      "loss": 0.3025,
+      "step": 214
+    },
+    {
+      "epoch": 6.88,
+      "grad_norm": 0.9093402624130249,
+      "learning_rate": 9.193548387096774e-05,
+      "loss": 0.2698,
+      "step": 215
+    },
+    {
+      "epoch": 6.912,
+      "grad_norm": 0.8621392846107483,
+      "learning_rate": 9.096774193548386e-05,
+      "loss": 0.2259,
+      "step": 216
+    },
+    {
+      "epoch": 6.944,
+      "grad_norm": 1.035175085067749,
+      "learning_rate": 8.999999999999999e-05,
+      "loss": 0.3156,
+      "step": 217
+    },
+    {
+      "epoch": 6.976,
+      "grad_norm": 1.0241689682006836,
+      "learning_rate": 8.903225806451611e-05,
+      "loss": 0.2723,
+      "step": 218
+    },
+    {
+      "epoch": 7.008,
+      "grad_norm": 1.735946536064148,
+      "learning_rate": 8.806451612903224e-05,
+      "loss": 0.411,
+      "step": 219
+    },
+    {
+      "epoch": 7.04,
+      "grad_norm": 0.8678178191184998,
+      "learning_rate": 8.709677419354839e-05,
+      "loss": 0.2415,
+      "step": 220
+    },
+    {
+      "epoch": 7.072,
+      "grad_norm": 0.7134645581245422,
+      "learning_rate": 8.612903225806451e-05,
+      "loss": 0.1509,
+      "step": 221
+    },
+    {
+      "epoch": 7.104,
+      "grad_norm": 0.8543497920036316,
+      "learning_rate": 8.516129032258064e-05,
+      "loss": 0.2459,
+      "step": 222
+    },
+    {
+      "epoch": 7.136,
+      "grad_norm": 0.9644029140472412,
+      "learning_rate": 8.419354838709677e-05,
+      "loss": 0.2828,
+      "step": 223
+    },
+    {
+      "epoch": 7.168,
+      "grad_norm": 0.8568740487098694,
+      "learning_rate": 8.322580645161289e-05,
+      "loss": 0.1936,
+      "step": 224
+    },
+    {
+      "epoch": 7.2,
+      "grad_norm": 1.005867600440979,
+      "learning_rate": 8.225806451612902e-05,
+      "loss": 0.2678,
+      "step": 225
+    },
+    {
+      "epoch": 7.232,
+      "grad_norm": 0.9942033290863037,
+      "learning_rate": 8.129032258064517e-05,
+      "loss": 0.2111,
+      "step": 226
+    },
+    {
+      "epoch": 7.264,
+      "grad_norm": 0.9886007905006409,
+      "learning_rate": 8.032258064516129e-05,
+      "loss": 0.2375,
+      "step": 227
+    },
+    {
+      "epoch": 7.296,
+      "grad_norm": 1.0586844682693481,
+      "learning_rate": 7.935483870967742e-05,
+      "loss": 0.2385,
+      "step": 228
+    },
+    {
+      "epoch": 7.328,
+      "grad_norm": 1.026432991027832,
+      "learning_rate": 7.838709677419354e-05,
+      "loss": 0.2139,
+      "step": 229
+    },
+    {
+      "epoch": 7.36,
+      "grad_norm": 1.0039665699005127,
+      "learning_rate": 7.741935483870967e-05,
+      "loss": 0.2211,
+      "step": 230
+    },
+    {
+      "epoch": 7.392,
+      "grad_norm": 1.1125057935714722,
+      "learning_rate": 7.645161290322579e-05,
+      "loss": 0.2725,
+      "step": 231
+    },
+    {
+      "epoch": 7.424,
+      "grad_norm": 0.9078079462051392,
+      "learning_rate": 7.548387096774192e-05,
+      "loss": 0.1965,
+      "step": 232
+    },
+    {
+      "epoch": 7.456,
+      "grad_norm": 0.8247030377388,
+      "learning_rate": 7.451612903225805e-05,
+      "loss": 0.1502,
+      "step": 233
+    },
+    {
+      "epoch": 7.4879999999999995,
+      "grad_norm": 1.1396474838256836,
+      "learning_rate": 7.354838709677418e-05,
+      "loss": 0.37,
+      "step": 234
+    },
+    {
+      "epoch": 7.52,
+      "grad_norm": 0.753663182258606,
+      "learning_rate": 7.258064516129032e-05,
+      "loss": 0.1627,
+      "step": 235
+    },
+    {
+      "epoch": 7.552,
+      "grad_norm": 0.7927701473236084,
+      "learning_rate": 7.161290322580645e-05,
+      "loss": 0.1684,
+      "step": 236
+    },
+    {
+      "epoch": 7.584,
+      "grad_norm": 0.9258756637573242,
+      "learning_rate": 7.064516129032257e-05,
+      "loss": 0.213,
+      "step": 237
+    },
+    {
+      "epoch": 7.616,
+      "grad_norm": 0.8111560940742493,
+      "learning_rate": 6.96774193548387e-05,
+      "loss": 0.1998,
+      "step": 238
+    },
+    {
+      "epoch": 7.648,
+      "grad_norm": 0.8484370708465576,
+      "learning_rate": 6.870967741935483e-05,
+      "loss": 0.1307,
+      "step": 239
+    },
+    {
+      "epoch": 7.68,
+      "grad_norm": 0.9123087525367737,
+      "learning_rate": 6.774193548387096e-05,
+      "loss": 0.2529,
+      "step": 240
+    },
+    {
+      "epoch": 7.712,
+      "grad_norm": 1.0526336431503296,
+      "learning_rate": 6.67741935483871e-05,
+      "loss": 0.2468,
+      "step": 241
+    },
+    {
+      "epoch": 7.744,
+      "grad_norm": 1.0104210376739502,
+      "learning_rate": 6.580645161290322e-05,
+      "loss": 0.23,
+      "step": 242
+    },
+    {
+      "epoch": 7.776,
+      "grad_norm": 0.8749745488166809,
+      "learning_rate": 6.483870967741935e-05,
+      "loss": 0.1973,
+      "step": 243
+    },
+    {
+      "epoch": 7.808,
+      "grad_norm": 0.9921355247497559,
+      "learning_rate": 6.387096774193548e-05,
+      "loss": 0.2144,
+      "step": 244
+    },
+    {
+      "epoch": 7.84,
+      "grad_norm": 0.8243810534477234,
+      "learning_rate": 6.290322580645161e-05,
+      "loss": 0.1531,
+      "step": 245
+    },
+    {
+      "epoch": 7.872,
+      "grad_norm": 1.0764353275299072,
+      "learning_rate": 6.193548387096773e-05,
+      "loss": 0.2763,
+      "step": 246
+    },
+    {
+      "epoch": 7.904,
+      "grad_norm": 1.1754212379455566,
+      "learning_rate": 6.096774193548386e-05,
+      "loss": 0.2249,
+      "step": 247
+    },
+    {
+      "epoch": 7.936,
+      "grad_norm": 0.8588422536849976,
+      "learning_rate": 5.9999999999999995e-05,
+      "loss": 0.1782,
+      "step": 248
+    },
+    {
+      "epoch": 7.968,
+      "grad_norm": 1.045143961906433,
+      "learning_rate": 5.903225806451613e-05,
+      "loss": 0.2789,
+      "step": 249
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 1.9824038743972778,
+      "learning_rate": 5.806451612903225e-05,
+      "loss": 0.3057,
+      "step": 250
+    },
+    {
+      "epoch": 8.032,
+      "grad_norm": 0.9252362847328186,
+      "learning_rate": 5.709677419354838e-05,
+      "loss": 0.2221,
+      "step": 251
+    },
+    {
+      "epoch": 8.064,
+      "grad_norm": 0.8381021022796631,
+      "learning_rate": 5.612903225806451e-05,
+      "loss": 0.2639,
+      "step": 252
+    },
+    {
+      "epoch": 8.096,
+      "grad_norm": 0.9777012467384338,
+      "learning_rate": 5.516129032258064e-05,
+      "loss": 0.1533,
+      "step": 253
+    },
+    {
+      "epoch": 8.128,
+      "grad_norm": 0.8053516745567322,
+      "learning_rate": 5.419354838709677e-05,
+      "loss": 0.1883,
+      "step": 254
+    },
+    {
+      "epoch": 8.16,
+      "grad_norm": 0.8703336119651794,
+      "learning_rate": 5.32258064516129e-05,
+      "loss": 0.2079,
+      "step": 255
+    },
+    {
+      "epoch": 8.192,
+      "grad_norm": 0.8113718032836914,
+      "learning_rate": 5.2258064516129025e-05,
+      "loss": 0.1609,
+      "step": 256
+    },
+    {
+      "epoch": 8.224,
+      "grad_norm": 1.0667418241500854,
+      "learning_rate": 5.129032258064516e-05,
+      "loss": 0.2544,
+      "step": 257
+    },
+    {
+      "epoch": 8.256,
+      "grad_norm": 0.7853135466575623,
+      "learning_rate": 5.032258064516129e-05,
+      "loss": 0.1391,
+      "step": 258
+    },
+    {
+      "epoch": 8.288,
+      "grad_norm": 0.9970865845680237,
+      "learning_rate": 4.9354838709677415e-05,
+      "loss": 0.2305,
+      "step": 259
+    },
+    {
+      "epoch": 8.32,
+      "grad_norm": 12.063047409057617,
+      "learning_rate": 4.838709677419354e-05,
+      "loss": 0.189,
+      "step": 260
+    },
+    {
+      "epoch": 8.352,
+      "grad_norm": 1.2325772047042847,
+      "learning_rate": 4.741935483870967e-05,
+      "loss": 0.2308,
+      "step": 261
+    },
+    {
+      "epoch": 8.384,
+      "grad_norm": 1.1118851900100708,
+      "learning_rate": 4.6451612903225805e-05,
+      "loss": 0.2009,
+      "step": 262
+    },
+    {
+      "epoch": 8.416,
+      "grad_norm": 1.0783390998840332,
+      "learning_rate": 4.548387096774193e-05,
+      "loss": 0.2276,
+      "step": 263
+    },
+    {
+      "epoch": 8.448,
+      "grad_norm": 1.2127933502197266,
+      "learning_rate": 4.4516129032258055e-05,
+      "loss": 0.2046,
+      "step": 264
+    },
+    {
+      "epoch": 8.48,
+      "grad_norm": 1.1135843992233276,
+      "learning_rate": 4.3548387096774194e-05,
+      "loss": 0.1791,
+      "step": 265
+    },
+    {
+      "epoch": 8.512,
+      "grad_norm": 0.8666661381721497,
+      "learning_rate": 4.258064516129032e-05,
+      "loss": 0.1287,
+      "step": 266
+    },
+    {
+      "epoch": 8.544,
+      "grad_norm": 0.8430101275444031,
+      "learning_rate": 4.1612903225806445e-05,
+      "loss": 0.1475,
+      "step": 267
+    },
+    {
+      "epoch": 8.576,
+      "grad_norm": 0.7744110822677612,
+      "learning_rate": 4.0645161290322584e-05,
+      "loss": 0.1458,
+      "step": 268
+    },
+    {
+      "epoch": 8.608,
+      "grad_norm": 1.4067776203155518,
+      "learning_rate": 3.967741935483871e-05,
+      "loss": 0.2189,
+      "step": 269
+    },
+    {
+      "epoch": 8.64,
+      "grad_norm": 0.8347670435905457,
+      "learning_rate": 3.8709677419354835e-05,
+      "loss": 0.1602,
+      "step": 270
+    },
+    {
+      "epoch": 8.672,
+      "grad_norm": 0.7643276453018188,
+      "learning_rate": 3.774193548387096e-05,
+      "loss": 0.1363,
+      "step": 271
+    },
+    {
+      "epoch": 8.704,
+      "grad_norm": 0.898059606552124,
+      "learning_rate": 3.677419354838709e-05,
+      "loss": 0.156,
+      "step": 272
+    },
+    {
+      "epoch": 8.736,
+      "grad_norm": 0.8416333198547363,
+      "learning_rate": 3.5806451612903225e-05,
+      "loss": 0.1754,
+      "step": 273
+    },
+    {
+      "epoch": 8.768,
+      "grad_norm": 0.8691906929016113,
+      "learning_rate": 3.483870967741935e-05,
+      "loss": 0.1808,
+      "step": 274
+    },
+    {
+      "epoch": 8.8,
+      "grad_norm": 1.062111496925354,
+      "learning_rate": 3.387096774193548e-05,
+      "loss": 0.2559,
+      "step": 275
+    },
+    {
+      "epoch": 8.832,
+      "grad_norm": 0.881698727607727,
+      "learning_rate": 3.290322580645161e-05,
+      "loss": 0.1732,
+      "step": 276
+    },
+    {
+      "epoch": 8.864,
+      "grad_norm": 0.8446074724197388,
+      "learning_rate": 3.193548387096774e-05,
+      "loss": 0.1833,
+      "step": 277
+    },
+    {
+      "epoch": 8.896,
+      "grad_norm": 0.9393475651741028,
+      "learning_rate": 3.0967741935483865e-05,
+      "loss": 0.2165,
+      "step": 278
+    },
+    {
+      "epoch": 8.928,
+      "grad_norm": 0.8838346004486084,
+      "learning_rate": 2.9999999999999997e-05,
+      "loss": 0.146,
+      "step": 279
+    },
+    {
+      "epoch": 8.96,
+      "grad_norm": 0.8380343914031982,
+      "learning_rate": 2.9032258064516126e-05,
+      "loss": 0.1721,
+      "step": 280
+    },
+    {
+      "epoch": 8.992,
+      "grad_norm": 0.8561931252479553,
+      "learning_rate": 2.8064516129032255e-05,
+      "loss": 0.1519,
+      "step": 281
+    },
+    {
+      "epoch": 9.024,
+      "grad_norm": 1.6088253259658813,
+      "learning_rate": 2.7096774193548384e-05,
+      "loss": 0.2658,
+      "step": 282
+    },
+    {
+      "epoch": 9.056,
+      "grad_norm": 0.8154093027114868,
+      "learning_rate": 2.6129032258064513e-05,
+      "loss": 0.1693,
+      "step": 283
+    },
+    {
+      "epoch": 9.088,
+      "grad_norm": 0.7722072005271912,
+      "learning_rate": 2.5161290322580645e-05,
+      "loss": 0.1853,
+      "step": 284
+    },
+    {
+      "epoch": 9.12,
+      "grad_norm": 0.8294870257377625,
+      "learning_rate": 2.419354838709677e-05,
+      "loss": 0.1736,
+      "step": 285
+    },
+    {
+      "epoch": 9.152,
+      "grad_norm": 0.7481442093849182,
+      "learning_rate": 2.3225806451612902e-05,
+      "loss": 0.1544,
+      "step": 286
+    },
+    {
+      "epoch": 9.184,
+      "grad_norm": 0.923413872718811,
+      "learning_rate": 2.2258064516129028e-05,
+      "loss": 0.2162,
+      "step": 287
+    },
+    {
+      "epoch": 9.216,
+      "grad_norm": 0.8326953053474426,
+      "learning_rate": 2.129032258064516e-05,
+      "loss": 0.1926,
+      "step": 288
+    },
+    {
+      "epoch": 9.248,
+      "grad_norm": 0.7642485499382019,
+      "learning_rate": 2.0322580645161292e-05,
+      "loss": 0.1555,
+      "step": 289
+    },
+    {
+      "epoch": 9.28,
+      "grad_norm": 0.7902241945266724,
+      "learning_rate": 1.9354838709677417e-05,
+      "loss": 0.1459,
+      "step": 290
+    },
+    {
+      "epoch": 9.312,
+      "grad_norm": 0.7414844036102295,
+      "learning_rate": 1.8387096774193546e-05,
+      "loss": 0.1425,
+      "step": 291
+    },
+    {
+      "epoch": 9.344,
+      "grad_norm": 0.7870174646377563,
+      "learning_rate": 1.7419354838709675e-05,
+      "loss": 0.1853,
+      "step": 292
+    },
+    {
+      "epoch": 9.376,
+      "grad_norm": 0.9091981649398804,
+      "learning_rate": 1.6451612903225804e-05,
+      "loss": 0.1666,
+      "step": 293
+    },
+    {
+      "epoch": 9.408,
+      "grad_norm": 0.8651584386825562,
+      "learning_rate": 1.5483870967741933e-05,
+      "loss": 0.174,
+      "step": 294
+    },
+    {
+      "epoch": 9.44,
+      "grad_norm": 0.7866891622543335,
+      "learning_rate": 1.4516129032258063e-05,
+      "loss": 0.1478,
+      "step": 295
+    },
+    {
+      "epoch": 9.472,
+      "grad_norm": 0.717932403087616,
+      "learning_rate": 1.3548387096774192e-05,
+      "loss": 0.1425,
+      "step": 296
+    },
+    {
+      "epoch": 9.504,
+      "grad_norm": 1.0217758417129517,
+      "learning_rate": 1.2580645161290322e-05,
+      "loss": 0.1574,
+      "step": 297
+    },
+    {
+      "epoch": 9.536,
+      "grad_norm": 0.8149961829185486,
+      "learning_rate": 1.1612903225806451e-05,
+      "loss": 0.1422,
+      "step": 298
+    },
+    {
+      "epoch": 9.568,
+      "grad_norm": 0.9206218719482422,
+      "learning_rate": 1.064516129032258e-05,
+      "loss": 0.1809,
+      "step": 299
+    },
+    {
+      "epoch": 9.6,
+      "grad_norm": 0.6865082383155823,
+      "learning_rate": 9.677419354838709e-06,
+      "loss": 0.133,
+      "step": 300
+    },
+    {
+      "epoch": 9.632,
+      "grad_norm": 0.7960584759712219,
+      "learning_rate": 8.709677419354838e-06,
+      "loss": 0.1289,
+      "step": 301
+    },
+    {
+      "epoch": 9.664,
+      "grad_norm": 1.4710181951522827,
+      "learning_rate": 7.741935483870966e-06,
+      "loss": 0.1844,
+      "step": 302
+    },
+    {
+      "epoch": 9.696,
+      "grad_norm": 0.7321292757987976,
+      "learning_rate": 6.774193548387096e-06,
+      "loss": 0.1356,
+      "step": 303
+    },
+    {
+      "epoch": 9.728,
+      "grad_norm": 0.9279872179031372,
+      "learning_rate": 5.8064516129032256e-06,
+      "loss": 0.1842,
+      "step": 304
+    },
+    {
+      "epoch": 9.76,
+      "grad_norm": 0.790213942527771,
+      "learning_rate": 4.838709677419354e-06,
+      "loss": 0.1341,
+      "step": 305
+    },
+    {
+      "epoch": 9.792,
+      "grad_norm": 0.7292400598526001,
+      "learning_rate": 3.870967741935483e-06,
+      "loss": 0.1287,
+      "step": 306
+    },
+    {
+      "epoch": 9.824,
+      "grad_norm": 0.8236159682273865,
+      "learning_rate": 2.9032258064516128e-06,
+      "loss": 0.1721,
+      "step": 307
+    },
+    {
+      "epoch": 9.856,
+      "grad_norm": 1.0054924488067627,
+      "learning_rate": 1.9354838709677416e-06,
+      "loss": 0.19,
+      "step": 308
+    },
+    {
+      "epoch": 9.888,
+      "grad_norm": 0.8466821312904358,
+      "learning_rate": 9.677419354838708e-07,
+      "loss": 0.1742,
+      "step": 309
+    },
+    {
+      "epoch": 9.92,
+      "grad_norm": 0.7754448652267456,
+      "learning_rate": 0.0,
+      "loss": 0.1368,
+      "step": 310
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 310,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 7.34728855486464e+16,
+  "train_batch_size": 3,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-310/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:457c697b05fd5daa3c83df8920300c4940c26fb78ace5b5428b7c95d133a0ef4
+size 5560

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "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": "</s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

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

tokenizer_config.json

@@ -0,0 +1,44 @@
+{
+  "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": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% set system_message = false %}{% endif %}{% for message in loop_messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if loop.index0 == 0 and system_message != false %}{% set content = '<<SYS>>\\n' + system_message + '\\n<</SYS>>\\n\\n' + message['content'] %}{% else %}{% set content = message['content'] %}{% endif %}{% if message['role'] == 'user' %}{{ bos_token + '[INST] ' + content.strip() + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ ' '  + content.strip() + ' ' + eos_token }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}