Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,14 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+checkpoint-1015/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-1160/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-1296/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-1440/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-145/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-290/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-435/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-580/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-725/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-870/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,202 @@
+---
+base_model: microsoft/Phi-4-mini-instruct
+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 0.15.2

adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "microsoft/Phi-4-mini-instruct",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "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_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "k_proj",
+    "down_proj",
+    "v_proj",
+    "gate_proj",
+    "q_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4cc441c40942232c13b927eed9af87f322fd1200bc9f0d752c896154de091dfc
+size 35668592

added_tokens.json

@@ -0,0 +1,12 @@
+{
+  "<|/tool_call|>": 200026,
+  "<|/tool|>": 200024,
+  "<|assistant|>": 200019,
+  "<|end|>": 200020,
+  "<|system|>": 200022,
+  "<|tag|>": 200028,
+  "<|tool_call|>": 200025,
+  "<|tool_response|>": 200027,
+  "<|tool|>": 200023,
+  "<|user|>": 200021
+}

checkpoint-1015/README.md

@@ -0,0 +1,202 @@
+---
+base_model: microsoft/Phi-4-mini-instruct
+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 0.15.2

checkpoint-1015/adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "microsoft/Phi-4-mini-instruct",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "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_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "k_proj",
+    "q_proj",
+    "down_proj",
+    "o_proj",
+    "gate_proj",
+    "up_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-1015/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9dafe819bf5b39d325d75a8a30bf6ee7f086581c06bb78d8e052610f7031263b
+size 35668592

checkpoint-1015/added_tokens.json

@@ -0,0 +1,12 @@
+{
+  "<|/tool_call|>": 200026,
+  "<|/tool|>": 200024,
+  "<|assistant|>": 200019,
+  "<|end|>": 200020,
+  "<|system|>": 200022,
+  "<|tag|>": 200028,
+  "<|tool_call|>": 200025,
+  "<|tool_response|>": 200027,
+  "<|tool|>": 200023,
+  "<|user|>": 200021
+}

checkpoint-1015/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c9611d917a023fceb7b528ce85df1daf9000a8445f6033ed25b2f15b458706c
+size 18256762

checkpoint-1015/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b8383c5783d7f5d36e86bcd0413175724cfe8d935b75f5718ebce15da2520db
+size 14244

checkpoint-1015/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2b1b8967ebada03e032f79513b5fe237a5a72498509a76353e0945780d48342
+size 1064

checkpoint-1015/special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-1015/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d7f47443257fe193e8dcb1e6912235832f416fd25161c021f77cb63163cd44e
+size 15524193

checkpoint-1015/tokenizer_config.json

@@ -0,0 +1,112 @@
+{
+  "add_bos_token": false,
+  "add_eos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "199999": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200018": {
+      "content": "<|endofprompt|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200019": {
+      "content": "<|assistant|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "200020": {
+      "content": "<|end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "200021": {
+      "content": "<|user|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "200022": {
+      "content": "<|system|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "200023": {
+      "content": "<|tool|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "200024": {
+      "content": "<|/tool|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "200025": {
+      "content": "<|tool_call|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "200026": {
+      "content": "<|/tool_call|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "200027": {
+      "content": "<|tool_response|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "200028": {
+      "content": "<|tag|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "chat_template": "{% for message in messages %}{% if message['role'] == 'system' and 'tools' in message and message['tools'] is not none %}{{ '<|' + message['role'] + '|>' + message['content'] + '<|tool|>' + message['tools'] + '<|/tool|>' + '<|end|>' }}{% else %}{{ '<|' + message['role'] + '|>' + message['content'] + '<|end|>' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>' }}{% else %}{{ eos_token }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

checkpoint-1015/trainer_state.json

@@ -0,0 +1,1455 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 7.0,
+  "eval_steps": 500,
+  "global_step": 1015,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03466204506065858,
+      "grad_norm": 1.530611515045166,
+      "learning_rate": 0.0002,
+      "loss": 3.0151,
+      "step": 5
+    },
+    {
+      "epoch": 0.06932409012131716,
+      "grad_norm": 1.7004058361053467,
+      "learning_rate": 0.0002,
+      "loss": 2.0235,
+      "step": 10
+    },
+    {
+      "epoch": 0.10398613518197573,
+      "grad_norm": 1.933908462524414,
+      "learning_rate": 0.0002,
+      "loss": 1.1225,
+      "step": 15
+    },
+    {
+      "epoch": 0.1386481802426343,
+      "grad_norm": 0.9951248168945312,
+      "learning_rate": 0.0002,
+      "loss": 0.5422,
+      "step": 20
+    },
+    {
+      "epoch": 0.1733102253032929,
+      "grad_norm": 6.152623176574707,
+      "learning_rate": 0.0002,
+      "loss": 1.5639,
+      "step": 25
+    },
+    {
+      "epoch": 0.20797227036395147,
+      "grad_norm": 8.008278846740723,
+      "learning_rate": 0.0002,
+      "loss": 2.6486,
+      "step": 30
+    },
+    {
+      "epoch": 0.24263431542461006,
+      "grad_norm": 4.960943222045898,
+      "learning_rate": 0.0002,
+      "loss": 2.6059,
+      "step": 35
+    },
+    {
+      "epoch": 0.2772963604852686,
+      "grad_norm": 4.607645511627197,
+      "learning_rate": 0.0002,
+      "loss": 1.6898,
+      "step": 40
+    },
+    {
+      "epoch": 0.3119584055459272,
+      "grad_norm": 0.8448249101638794,
+      "learning_rate": 0.0002,
+      "loss": 0.799,
+      "step": 45
+    },
+    {
+      "epoch": 0.3466204506065858,
+      "grad_norm": 0.46238261461257935,
+      "learning_rate": 0.0002,
+      "loss": 0.5374,
+      "step": 50
+    },
+    {
+      "epoch": 0.38128249566724437,
+      "grad_norm": 0.3575257956981659,
+      "learning_rate": 0.0002,
+      "loss": 0.4247,
+      "step": 55
+    },
+    {
+      "epoch": 0.41594454072790293,
+      "grad_norm": 2.5151493549346924,
+      "learning_rate": 0.0002,
+      "loss": 0.7472,
+      "step": 60
+    },
+    {
+      "epoch": 0.4506065857885615,
+      "grad_norm": 17.38052749633789,
+      "learning_rate": 0.0002,
+      "loss": 1.8466,
+      "step": 65
+    },
+    {
+      "epoch": 0.4852686308492201,
+      "grad_norm": 15.523968696594238,
+      "learning_rate": 0.0002,
+      "loss": 2.1105,
+      "step": 70
+    },
+    {
+      "epoch": 0.5199306759098787,
+      "grad_norm": 1.0907574892044067,
+      "learning_rate": 0.0002,
+      "loss": 1.1052,
+      "step": 75
+    },
+    {
+      "epoch": 0.5545927209705372,
+      "grad_norm": 0.5225581526756287,
+      "learning_rate": 0.0002,
+      "loss": 0.5663,
+      "step": 80
+    },
+    {
+      "epoch": 0.5892547660311959,
+      "grad_norm": 0.3306778073310852,
+      "learning_rate": 0.0002,
+      "loss": 0.4648,
+      "step": 85
+    },
+    {
+      "epoch": 0.6239168110918544,
+      "grad_norm": 0.33595138788223267,
+      "learning_rate": 0.0002,
+      "loss": 0.3762,
+      "step": 90
+    },
+    {
+      "epoch": 0.658578856152513,
+      "grad_norm": 1.978458285331726,
+      "learning_rate": 0.0002,
+      "loss": 0.9162,
+      "step": 95
+    },
+    {
+      "epoch": 0.6932409012131716,
+      "grad_norm": 1.1226632595062256,
+      "learning_rate": 0.0002,
+      "loss": 1.5477,
+      "step": 100
+    },
+    {
+      "epoch": 0.7279029462738301,
+      "grad_norm": 22.263992309570312,
+      "learning_rate": 0.0002,
+      "loss": 1.8063,
+      "step": 105
+    },
+    {
+      "epoch": 0.7625649913344887,
+      "grad_norm": 1.3690563440322876,
+      "learning_rate": 0.0002,
+      "loss": 1.3102,
+      "step": 110
+    },
+    {
+      "epoch": 0.7972270363951474,
+      "grad_norm": 0.5651267766952515,
+      "learning_rate": 0.0002,
+      "loss": 0.553,
+      "step": 115
+    },
+    {
+      "epoch": 0.8318890814558059,
+      "grad_norm": 0.3272489011287689,
+      "learning_rate": 0.0002,
+      "loss": 0.4813,
+      "step": 120
+    },
+    {
+      "epoch": 0.8665511265164645,
+      "grad_norm": 0.30475500226020813,
+      "learning_rate": 0.0002,
+      "loss": 0.3746,
+      "step": 125
+    },
+    {
+      "epoch": 0.901213171577123,
+      "grad_norm": 0.2812097370624542,
+      "learning_rate": 0.0002,
+      "loss": 0.284,
+      "step": 130
+    },
+    {
+      "epoch": 0.9358752166377816,
+      "grad_norm": 1.159839391708374,
+      "learning_rate": 0.0002,
+      "loss": 1.5179,
+      "step": 135
+    },
+    {
+      "epoch": 0.9705372616984402,
+      "grad_norm": 4.740174770355225,
+      "learning_rate": 0.0002,
+      "loss": 1.549,
+      "step": 140
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 2.613008499145508,
+      "learning_rate": 0.0002,
+      "loss": 1.3938,
+      "step": 145
+    },
+    {
+      "epoch": 1.0346620450606585,
+      "grad_norm": 0.31811827421188354,
+      "learning_rate": 0.0002,
+      "loss": 0.5353,
+      "step": 150
+    },
+    {
+      "epoch": 1.0693240901213172,
+      "grad_norm": 0.42897579073905945,
+      "learning_rate": 0.0002,
+      "loss": 0.4452,
+      "step": 155
+    },
+    {
+      "epoch": 1.1039861351819757,
+      "grad_norm": 0.28854838013648987,
+      "learning_rate": 0.0002,
+      "loss": 0.3563,
+      "step": 160
+    },
+    {
+      "epoch": 1.1386481802426343,
+      "grad_norm": 0.32319992780685425,
+      "learning_rate": 0.0002,
+      "loss": 0.2697,
+      "step": 165
+    },
+    {
+      "epoch": 1.173310225303293,
+      "grad_norm": 1.0144641399383545,
+      "learning_rate": 0.0002,
+      "loss": 1.3199,
+      "step": 170
+    },
+    {
+      "epoch": 1.2079722703639515,
+      "grad_norm": 2.1387648582458496,
+      "learning_rate": 0.0002,
+      "loss": 1.1948,
+      "step": 175
+    },
+    {
+      "epoch": 1.24263431542461,
+      "grad_norm": 5.240429401397705,
+      "learning_rate": 0.0002,
+      "loss": 1.2138,
+      "step": 180
+    },
+    {
+      "epoch": 1.2772963604852685,
+      "grad_norm": 0.5809195637702942,
+      "learning_rate": 0.0002,
+      "loss": 0.7417,
+      "step": 185
+    },
+    {
+      "epoch": 1.3119584055459272,
+      "grad_norm": 0.3426031768321991,
+      "learning_rate": 0.0002,
+      "loss": 0.4541,
+      "step": 190
+    },
+    {
+      "epoch": 1.3466204506065858,
+      "grad_norm": 0.34089571237564087,
+      "learning_rate": 0.0002,
+      "loss": 0.3709,
+      "step": 195
+    },
+    {
+      "epoch": 1.3812824956672443,
+      "grad_norm": 0.2676282823085785,
+      "learning_rate": 0.0002,
+      "loss": 0.2981,
+      "step": 200
+    },
+    {
+      "epoch": 1.415944540727903,
+      "grad_norm": 1.8662705421447754,
+      "learning_rate": 0.0002,
+      "loss": 0.8353,
+      "step": 205
+    },
+    {
+      "epoch": 1.4506065857885615,
+      "grad_norm": 3.2310688495635986,
+      "learning_rate": 0.0002,
+      "loss": 1.2188,
+      "step": 210
+    },
+    {
+      "epoch": 1.48526863084922,
+      "grad_norm": 2.255415916442871,
+      "learning_rate": 0.0002,
+      "loss": 1.1677,
+      "step": 215
+    },
+    {
+      "epoch": 1.5199306759098787,
+      "grad_norm": 0.5544691681861877,
+      "learning_rate": 0.0002,
+      "loss": 0.799,
+      "step": 220
+    },
+    {
+      "epoch": 1.5545927209705372,
+      "grad_norm": 0.4003375172615051,
+      "learning_rate": 0.0002,
+      "loss": 0.4786,
+      "step": 225
+    },
+    {
+      "epoch": 1.5892547660311958,
+      "grad_norm": 0.3774619698524475,
+      "learning_rate": 0.0002,
+      "loss": 0.4233,
+      "step": 230
+    },
+    {
+      "epoch": 1.6239168110918545,
+      "grad_norm": 0.352490097284317,
+      "learning_rate": 0.0002,
+      "loss": 0.3332,
+      "step": 235
+    },
+    {
+      "epoch": 1.658578856152513,
+      "grad_norm": 0.2637154459953308,
+      "learning_rate": 0.0002,
+      "loss": 0.2438,
+      "step": 240
+    },
+    {
+      "epoch": 1.6932409012131715,
+      "grad_norm": 1.3437107801437378,
+      "learning_rate": 0.0002,
+      "loss": 1.4351,
+      "step": 245
+    },
+    {
+      "epoch": 1.7279029462738302,
+      "grad_norm": 2.647561550140381,
+      "learning_rate": 0.0002,
+      "loss": 1.0698,
+      "step": 250
+    },
+    {
+      "epoch": 1.7625649913344887,
+      "grad_norm": 0.6839751601219177,
+      "learning_rate": 0.0002,
+      "loss": 0.7411,
+      "step": 255
+    },
+    {
+      "epoch": 1.7972270363951472,
+      "grad_norm": 0.4790812134742737,
+      "learning_rate": 0.0002,
+      "loss": 0.5009,
+      "step": 260
+    },
+    {
+      "epoch": 1.831889081455806,
+      "grad_norm": 0.36322328448295593,
+      "learning_rate": 0.0002,
+      "loss": 0.4014,
+      "step": 265
+    },
+    {
+      "epoch": 1.8665511265164645,
+      "grad_norm": 0.31694507598876953,
+      "learning_rate": 0.0002,
+      "loss": 0.3441,
+      "step": 270
+    },
+    {
+      "epoch": 1.901213171577123,
+      "grad_norm": 0.24292677640914917,
+      "learning_rate": 0.0002,
+      "loss": 0.2619,
+      "step": 275
+    },
+    {
+      "epoch": 1.9358752166377817,
+      "grad_norm": 1.133062720298767,
+      "learning_rate": 0.0002,
+      "loss": 1.1564,
+      "step": 280
+    },
+    {
+      "epoch": 1.9705372616984402,
+      "grad_norm": 10.754274368286133,
+      "learning_rate": 0.0002,
+      "loss": 1.436,
+      "step": 285
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.6346553564071655,
+      "learning_rate": 0.0002,
+      "loss": 1.3215,
+      "step": 290
+    },
+    {
+      "epoch": 2.0346620450606587,
+      "grad_norm": 0.7156389355659485,
+      "learning_rate": 0.0002,
+      "loss": 0.551,
+      "step": 295
+    },
+    {
+      "epoch": 2.069324090121317,
+      "grad_norm": 0.3842258155345917,
+      "learning_rate": 0.0002,
+      "loss": 0.3783,
+      "step": 300
+    },
+    {
+      "epoch": 2.1039861351819757,
+      "grad_norm": 0.35967278480529785,
+      "learning_rate": 0.0002,
+      "loss": 0.3124,
+      "step": 305
+    },
+    {
+      "epoch": 2.1386481802426345,
+      "grad_norm": 0.296977162361145,
+      "learning_rate": 0.0002,
+      "loss": 0.2367,
+      "step": 310
+    },
+    {
+      "epoch": 2.1733102253032928,
+      "grad_norm": 1.6834601163864136,
+      "learning_rate": 0.0002,
+      "loss": 0.7685,
+      "step": 315
+    },
+    {
+      "epoch": 2.2079722703639515,
+      "grad_norm": 5.758884906768799,
+      "learning_rate": 0.0002,
+      "loss": 1.0063,
+      "step": 320
+    },
+    {
+      "epoch": 2.2426343154246102,
+      "grad_norm": 15.24948501586914,
+      "learning_rate": 0.0002,
+      "loss": 1.231,
+      "step": 325
+    },
+    {
+      "epoch": 2.2772963604852685,
+      "grad_norm": 0.599730372428894,
+      "learning_rate": 0.0002,
+      "loss": 0.6392,
+      "step": 330
+    },
+    {
+      "epoch": 2.3119584055459272,
+      "grad_norm": 0.5307044982910156,
+      "learning_rate": 0.0002,
+      "loss": 0.3804,
+      "step": 335
+    },
+    {
+      "epoch": 2.346620450606586,
+      "grad_norm": 0.33558061718940735,
+      "learning_rate": 0.0002,
+      "loss": 0.3282,
+      "step": 340
+    },
+    {
+      "epoch": 2.3812824956672443,
+      "grad_norm": 0.2716732919216156,
+      "learning_rate": 0.0002,
+      "loss": 0.2429,
+      "step": 345
+    },
+    {
+      "epoch": 2.415944540727903,
+      "grad_norm": 2.454636812210083,
+      "learning_rate": 0.0002,
+      "loss": 0.5396,
+      "step": 350
+    },
+    {
+      "epoch": 2.4506065857885613,
+      "grad_norm": 13.286089897155762,
+      "learning_rate": 0.0002,
+      "loss": 1.0545,
+      "step": 355
+    },
+    {
+      "epoch": 2.48526863084922,
+      "grad_norm": 12.619502067565918,
+      "learning_rate": 0.0002,
+      "loss": 1.1547,
+      "step": 360
+    },
+    {
+      "epoch": 2.5199306759098787,
+      "grad_norm": 0.6347368359565735,
+      "learning_rate": 0.0002,
+      "loss": 0.7136,
+      "step": 365
+    },
+    {
+      "epoch": 2.554592720970537,
+      "grad_norm": 0.44485101103782654,
+      "learning_rate": 0.0002,
+      "loss": 0.3994,
+      "step": 370
+    },
+    {
+      "epoch": 2.5892547660311958,
+      "grad_norm": 0.36494728922843933,
+      "learning_rate": 0.0002,
+      "loss": 0.3107,
+      "step": 375
+    },
+    {
+      "epoch": 2.6239168110918545,
+      "grad_norm": 0.322171688079834,
+      "learning_rate": 0.0002,
+      "loss": 0.2753,
+      "step": 380
+    },
+    {
+      "epoch": 2.6585788561525128,
+      "grad_norm": 0.9659174084663391,
+      "learning_rate": 0.0002,
+      "loss": 0.2948,
+      "step": 385
+    },
+    {
+      "epoch": 2.6932409012131715,
+      "grad_norm": 0.9371129870414734,
+      "learning_rate": 0.0002,
+      "loss": 1.0286,
+      "step": 390
+    },
+    {
+      "epoch": 2.7279029462738302,
+      "grad_norm": 3.4619617462158203,
+      "learning_rate": 0.0002,
+      "loss": 1.0745,
+      "step": 395
+    },
+    {
+      "epoch": 2.7625649913344885,
+      "grad_norm": 0.6884852051734924,
+      "learning_rate": 0.0002,
+      "loss": 0.7637,
+      "step": 400
+    },
+    {
+      "epoch": 2.7972270363951472,
+      "grad_norm": 0.4440446197986603,
+      "learning_rate": 0.0002,
+      "loss": 0.4331,
+      "step": 405
+    },
+    {
+      "epoch": 2.831889081455806,
+      "grad_norm": 0.37561893463134766,
+      "learning_rate": 0.0002,
+      "loss": 0.3667,
+      "step": 410
+    },
+    {
+      "epoch": 2.8665511265164643,
+      "grad_norm": 0.320077121257782,
+      "learning_rate": 0.0002,
+      "loss": 0.2769,
+      "step": 415
+    },
+    {
+      "epoch": 2.901213171577123,
+      "grad_norm": 1.4914495944976807,
+      "learning_rate": 0.0002,
+      "loss": 0.4493,
+      "step": 420
+    },
+    {
+      "epoch": 2.9358752166377817,
+      "grad_norm": 1.164036750793457,
+      "learning_rate": 0.0002,
+      "loss": 1.1276,
+      "step": 425
+    },
+    {
+      "epoch": 2.97053726169844,
+      "grad_norm": 5.013108253479004,
+      "learning_rate": 0.0002,
+      "loss": 1.0841,
+      "step": 430
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 2.2247564792633057,
+      "learning_rate": 0.0002,
+      "loss": 0.7636,
+      "step": 435
+    },
+    {
+      "epoch": 3.0346620450606587,
+      "grad_norm": 0.3730102479457855,
+      "learning_rate": 0.0002,
+      "loss": 0.4291,
+      "step": 440
+    },
+    {
+      "epoch": 3.069324090121317,
+      "grad_norm": 0.36571791768074036,
+      "learning_rate": 0.0002,
+      "loss": 0.3155,
+      "step": 445
+    },
+    {
+      "epoch": 3.1039861351819757,
+      "grad_norm": 0.34427550435066223,
+      "learning_rate": 0.0002,
+      "loss": 0.2297,
+      "step": 450
+    },
+    {
+      "epoch": 3.1386481802426345,
+      "grad_norm": 0.3725241422653198,
+      "learning_rate": 0.0002,
+      "loss": 0.173,
+      "step": 455
+    },
+    {
+      "epoch": 3.1733102253032928,
+      "grad_norm": 0.9735671877861023,
+      "learning_rate": 0.0002,
+      "loss": 0.8876,
+      "step": 460
+    },
+    {
+      "epoch": 3.2079722703639515,
+      "grad_norm": 3.0348145961761475,
+      "learning_rate": 0.0002,
+      "loss": 0.7825,
+      "step": 465
+    },
+    {
+      "epoch": 3.2426343154246102,
+      "grad_norm": 1.4603136777877808,
+      "learning_rate": 0.0002,
+      "loss": 0.8017,
+      "step": 470
+    },
+    {
+      "epoch": 3.2772963604852685,
+      "grad_norm": 0.6849704384803772,
+      "learning_rate": 0.0002,
+      "loss": 0.6029,
+      "step": 475
+    },
+    {
+      "epoch": 3.3119584055459272,
+      "grad_norm": 0.45950087904930115,
+      "learning_rate": 0.0002,
+      "loss": 0.3388,
+      "step": 480
+    },
+    {
+      "epoch": 3.346620450606586,
+      "grad_norm": 0.3234940469264984,
+      "learning_rate": 0.0002,
+      "loss": 0.2635,
+      "step": 485
+    },
+    {
+      "epoch": 3.3812824956672443,
+      "grad_norm": 0.3088044822216034,
+      "learning_rate": 0.0002,
+      "loss": 0.1867,
+      "step": 490
+    },
+    {
+      "epoch": 3.415944540727903,
+      "grad_norm": 0.36887720227241516,
+      "learning_rate": 0.0002,
+      "loss": 0.1653,
+      "step": 495
+    },
+    {
+      "epoch": 3.4506065857885613,
+      "grad_norm": 1.041858196258545,
+      "learning_rate": 0.0002,
+      "loss": 0.9041,
+      "step": 500
+    },
+    {
+      "epoch": 3.48526863084922,
+      "grad_norm": 1.4774988889694214,
+      "learning_rate": 0.0002,
+      "loss": 0.9789,
+      "step": 505
+    },
+    {
+      "epoch": 3.5199306759098787,
+      "grad_norm": 0.6804758310317993,
+      "learning_rate": 0.0002,
+      "loss": 0.5891,
+      "step": 510
+    },
+    {
+      "epoch": 3.554592720970537,
+      "grad_norm": 0.43344879150390625,
+      "learning_rate": 0.0002,
+      "loss": 0.3632,
+      "step": 515
+    },
+    {
+      "epoch": 3.5892547660311958,
+      "grad_norm": 0.4160469174385071,
+      "learning_rate": 0.0002,
+      "loss": 0.2734,
+      "step": 520
+    },
+    {
+      "epoch": 3.6239168110918545,
+      "grad_norm": 0.35103052854537964,
+      "learning_rate": 0.0002,
+      "loss": 0.2215,
+      "step": 525
+    },
+    {
+      "epoch": 3.6585788561525128,
+      "grad_norm": 1.083409309387207,
+      "learning_rate": 0.0002,
+      "loss": 0.2623,
+      "step": 530
+    },
+    {
+      "epoch": 3.6932409012131715,
+      "grad_norm": 1.2548085451126099,
+      "learning_rate": 0.0002,
+      "loss": 0.9395,
+      "step": 535
+    },
+    {
+      "epoch": 3.7279029462738302,
+      "grad_norm": 2.565399169921875,
+      "learning_rate": 0.0002,
+      "loss": 0.9097,
+      "step": 540
+    },
+    {
+      "epoch": 3.7625649913344885,
+      "grad_norm": 0.6658923625946045,
+      "learning_rate": 0.0002,
+      "loss": 0.739,
+      "step": 545
+    },
+    {
+      "epoch": 3.7972270363951472,
+      "grad_norm": 0.4989807605743408,
+      "learning_rate": 0.0002,
+      "loss": 0.396,
+      "step": 550
+    },
+    {
+      "epoch": 3.831889081455806,
+      "grad_norm": 0.39474496245384216,
+      "learning_rate": 0.0002,
+      "loss": 0.2809,
+      "step": 555
+    },
+    {
+      "epoch": 3.8665511265164643,
+      "grad_norm": 0.38600996136665344,
+      "learning_rate": 0.0002,
+      "loss": 0.2254,
+      "step": 560
+    },
+    {
+      "epoch": 3.901213171577123,
+      "grad_norm": 0.3662823736667633,
+      "learning_rate": 0.0002,
+      "loss": 0.167,
+      "step": 565
+    },
+    {
+      "epoch": 3.9358752166377817,
+      "grad_norm": 1.349672794342041,
+      "learning_rate": 0.0002,
+      "loss": 1.1593,
+      "step": 570
+    },
+    {
+      "epoch": 3.97053726169844,
+      "grad_norm": 2.3923165798187256,
+      "learning_rate": 0.0002,
+      "loss": 0.8778,
+      "step": 575
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.7578555345535278,
+      "learning_rate": 0.0002,
+      "loss": 0.6897,
+      "step": 580
+    },
+    {
+      "epoch": 4.034662045060658,
+      "grad_norm": 0.5052911043167114,
+      "learning_rate": 0.0002,
+      "loss": 0.3913,
+      "step": 585
+    },
+    {
+      "epoch": 4.0693240901213175,
+      "grad_norm": 0.5212499499320984,
+      "learning_rate": 0.0002,
+      "loss": 0.2326,
+      "step": 590
+    },
+    {
+      "epoch": 4.103986135181976,
+      "grad_norm": 0.452105313539505,
+      "learning_rate": 0.0002,
+      "loss": 0.1846,
+      "step": 595
+    },
+    {
+      "epoch": 4.138648180242634,
+      "grad_norm": 0.4193221926689148,
+      "learning_rate": 0.0002,
+      "loss": 0.1359,
+      "step": 600
+    },
+    {
+      "epoch": 4.173310225303293,
+      "grad_norm": 2.3956053256988525,
+      "learning_rate": 0.0002,
+      "loss": 0.3795,
+      "step": 605
+    },
+    {
+      "epoch": 4.2079722703639515,
+      "grad_norm": 1.946535348892212,
+      "learning_rate": 0.0002,
+      "loss": 0.579,
+      "step": 610
+    },
+    {
+      "epoch": 4.24263431542461,
+      "grad_norm": 1.874873161315918,
+      "learning_rate": 0.0002,
+      "loss": 0.7528,
+      "step": 615
+    },
+    {
+      "epoch": 4.277296360485269,
+      "grad_norm": 0.6922146081924438,
+      "learning_rate": 0.0002,
+      "loss": 0.4398,
+      "step": 620
+    },
+    {
+      "epoch": 4.311958405545927,
+      "grad_norm": 0.5228244662284851,
+      "learning_rate": 0.0002,
+      "loss": 0.2615,
+      "step": 625
+    },
+    {
+      "epoch": 4.3466204506065855,
+      "grad_norm": 0.34687915444374084,
+      "learning_rate": 0.0002,
+      "loss": 0.191,
+      "step": 630
+    },
+    {
+      "epoch": 4.381282495667245,
+      "grad_norm": 0.4160069525241852,
+      "learning_rate": 0.0002,
+      "loss": 0.1434,
+      "step": 635
+    },
+    {
+      "epoch": 4.415944540727903,
+      "grad_norm": 1.468666434288025,
+      "learning_rate": 0.0002,
+      "loss": 0.61,
+      "step": 640
+    },
+    {
+      "epoch": 4.450606585788561,
+      "grad_norm": 3.174201488494873,
+      "learning_rate": 0.0002,
+      "loss": 0.5773,
+      "step": 645
+    },
+    {
+      "epoch": 4.4852686308492205,
+      "grad_norm": 1.8258005380630493,
+      "learning_rate": 0.0002,
+      "loss": 0.7495,
+      "step": 650
+    },
+    {
+      "epoch": 4.519930675909879,
+      "grad_norm": 0.8468143343925476,
+      "learning_rate": 0.0002,
+      "loss": 0.5441,
+      "step": 655
+    },
+    {
+      "epoch": 4.554592720970537,
+      "grad_norm": 0.5467656254768372,
+      "learning_rate": 0.0002,
+      "loss": 0.2906,
+      "step": 660
+    },
+    {
+      "epoch": 4.589254766031196,
+      "grad_norm": 0.396992564201355,
+      "learning_rate": 0.0002,
+      "loss": 0.2186,
+      "step": 665
+    },
+    {
+      "epoch": 4.6239168110918545,
+      "grad_norm": 0.31931889057159424,
+      "learning_rate": 0.0002,
+      "loss": 0.1629,
+      "step": 670
+    },
+    {
+      "epoch": 4.658578856152513,
+      "grad_norm": 1.755745530128479,
+      "learning_rate": 0.0002,
+      "loss": 0.2292,
+      "step": 675
+    },
+    {
+      "epoch": 4.693240901213172,
+      "grad_norm": 0.9869062900543213,
+      "learning_rate": 0.0002,
+      "loss": 0.6716,
+      "step": 680
+    },
+    {
+      "epoch": 4.72790294627383,
+      "grad_norm": 1.5987203121185303,
+      "learning_rate": 0.0002,
+      "loss": 0.8182,
+      "step": 685
+    },
+    {
+      "epoch": 4.7625649913344885,
+      "grad_norm": 0.870819091796875,
+      "learning_rate": 0.0002,
+      "loss": 0.5902,
+      "step": 690
+    },
+    {
+      "epoch": 4.797227036395148,
+      "grad_norm": 0.5098839402198792,
+      "learning_rate": 0.0002,
+      "loss": 0.3224,
+      "step": 695
+    },
+    {
+      "epoch": 4.831889081455806,
+      "grad_norm": 0.5435961484909058,
+      "learning_rate": 0.0002,
+      "loss": 0.2182,
+      "step": 700
+    },
+    {
+      "epoch": 4.866551126516464,
+      "grad_norm": 0.33275553584098816,
+      "learning_rate": 0.0002,
+      "loss": 0.1595,
+      "step": 705
+    },
+    {
+      "epoch": 4.9012131715771226,
+      "grad_norm": 1.8109265565872192,
+      "learning_rate": 0.0002,
+      "loss": 0.1985,
+      "step": 710
+    },
+    {
+      "epoch": 4.935875216637782,
+      "grad_norm": 1.149431824684143,
+      "learning_rate": 0.0002,
+      "loss": 0.8148,
+      "step": 715
+    },
+    {
+      "epoch": 4.97053726169844,
+      "grad_norm": 1.4355350732803345,
+      "learning_rate": 0.0002,
+      "loss": 0.6675,
+      "step": 720
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 2.76149845123291,
+      "learning_rate": 0.0002,
+      "loss": 0.5541,
+      "step": 725
+    },
+    {
+      "epoch": 5.034662045060658,
+      "grad_norm": 0.6026546359062195,
+      "learning_rate": 0.0002,
+      "loss": 0.3515,
+      "step": 730
+    },
+    {
+      "epoch": 5.0693240901213175,
+      "grad_norm": 0.37150222063064575,
+      "learning_rate": 0.0002,
+      "loss": 0.1661,
+      "step": 735
+    },
+    {
+      "epoch": 5.103986135181976,
+      "grad_norm": 0.31225013732910156,
+      "learning_rate": 0.0002,
+      "loss": 0.1243,
+      "step": 740
+    },
+    {
+      "epoch": 5.138648180242634,
+      "grad_norm": 0.4382600784301758,
+      "learning_rate": 0.0002,
+      "loss": 0.1004,
+      "step": 745
+    },
+    {
+      "epoch": 5.173310225303293,
+      "grad_norm": 2.0306389331817627,
+      "learning_rate": 0.0002,
+      "loss": 0.3743,
+      "step": 750
+    },
+    {
+      "epoch": 5.2079722703639515,
+      "grad_norm": 1.6935468912124634,
+      "learning_rate": 0.0002,
+      "loss": 0.4202,
+      "step": 755
+    },
+    {
+      "epoch": 5.24263431542461,
+      "grad_norm": 1.4990637302398682,
+      "learning_rate": 0.0002,
+      "loss": 0.5533,
+      "step": 760
+    },
+    {
+      "epoch": 5.277296360485269,
+      "grad_norm": 0.6687419414520264,
+      "learning_rate": 0.0002,
+      "loss": 0.3429,
+      "step": 765
+    },
+    {
+      "epoch": 5.311958405545927,
+      "grad_norm": 0.5400169491767883,
+      "learning_rate": 0.0002,
+      "loss": 0.1759,
+      "step": 770
+    },
+    {
+      "epoch": 5.3466204506065855,
+      "grad_norm": 0.39679139852523804,
+      "learning_rate": 0.0002,
+      "loss": 0.1395,
+      "step": 775
+    },
+    {
+      "epoch": 5.381282495667245,
+      "grad_norm": 0.33043885231018066,
+      "learning_rate": 0.0002,
+      "loss": 0.1004,
+      "step": 780
+    },
+    {
+      "epoch": 5.415944540727903,
+      "grad_norm": 3.1912200450897217,
+      "learning_rate": 0.0002,
+      "loss": 0.305,
+      "step": 785
+    },
+    {
+      "epoch": 5.450606585788561,
+      "grad_norm": 1.2743686437606812,
+      "learning_rate": 0.0002,
+      "loss": 0.4876,
+      "step": 790
+    },
+    {
+      "epoch": 5.4852686308492205,
+      "grad_norm": 2.9798948764801025,
+      "learning_rate": 0.0002,
+      "loss": 0.7476,
+      "step": 795
+    },
+    {
+      "epoch": 5.519930675909879,
+      "grad_norm": 0.7342365384101868,
+      "learning_rate": 0.0002,
+      "loss": 0.463,
+      "step": 800
+    },
+    {
+      "epoch": 5.554592720970537,
+      "grad_norm": 0.5035507678985596,
+      "learning_rate": 0.0002,
+      "loss": 0.2116,
+      "step": 805
+    },
+    {
+      "epoch": 5.589254766031196,
+      "grad_norm": 0.4394471347332001,
+      "learning_rate": 0.0002,
+      "loss": 0.1568,
+      "step": 810
+    },
+    {
+      "epoch": 5.6239168110918545,
+      "grad_norm": 0.383515328168869,
+      "learning_rate": 0.0002,
+      "loss": 0.1035,
+      "step": 815
+    },
+    {
+      "epoch": 5.658578856152513,
+      "grad_norm": 2.142784357070923,
+      "learning_rate": 0.0002,
+      "loss": 0.3458,
+      "step": 820
+    },
+    {
+      "epoch": 5.693240901213172,
+      "grad_norm": 1.2484018802642822,
+      "learning_rate": 0.0002,
+      "loss": 0.3576,
+      "step": 825
+    },
+    {
+      "epoch": 5.72790294627383,
+      "grad_norm": 2.6863198280334473,
+      "learning_rate": 0.0002,
+      "loss": 0.5996,
+      "step": 830
+    },
+    {
+      "epoch": 5.7625649913344885,
+      "grad_norm": 1.098381757736206,
+      "learning_rate": 0.0002,
+      "loss": 0.4993,
+      "step": 835
+    },
+    {
+      "epoch": 5.797227036395148,
+      "grad_norm": 0.5609210133552551,
+      "learning_rate": 0.0002,
+      "loss": 0.2608,
+      "step": 840
+    },
+    {
+      "epoch": 5.831889081455806,
+      "grad_norm": 0.5123816132545471,
+      "learning_rate": 0.0002,
+      "loss": 0.1799,
+      "step": 845
+    },
+    {
+      "epoch": 5.866551126516464,
+      "grad_norm": 0.46399134397506714,
+      "learning_rate": 0.0002,
+      "loss": 0.1254,
+      "step": 850
+    },
+    {
+      "epoch": 5.9012131715771226,
+      "grad_norm": 0.5089249014854431,
+      "learning_rate": 0.0002,
+      "loss": 0.0934,
+      "step": 855
+    },
+    {
+      "epoch": 5.935875216637782,
+      "grad_norm": 1.3031930923461914,
+      "learning_rate": 0.0002,
+      "loss": 0.6664,
+      "step": 860
+    },
+    {
+      "epoch": 5.97053726169844,
+      "grad_norm": 2.294696569442749,
+      "learning_rate": 0.0002,
+      "loss": 0.6034,
+      "step": 865
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 2.738062620162964,
+      "learning_rate": 0.0002,
+      "loss": 0.587,
+      "step": 870
+    },
+    {
+      "epoch": 6.034662045060658,
+      "grad_norm": 0.6086808443069458,
+      "learning_rate": 0.0002,
+      "loss": 0.252,
+      "step": 875
+    },
+    {
+      "epoch": 6.0693240901213175,
+      "grad_norm": 0.4935630261898041,
+      "learning_rate": 0.0002,
+      "loss": 0.1223,
+      "step": 880
+    },
+    {
+      "epoch": 6.103986135181976,
+      "grad_norm": 0.43656599521636963,
+      "learning_rate": 0.0002,
+      "loss": 0.0882,
+      "step": 885
+    },
+    {
+      "epoch": 6.138648180242634,
+      "grad_norm": 0.2987945079803467,
+      "learning_rate": 0.0002,
+      "loss": 0.0629,
+      "step": 890
+    },
+    {
+      "epoch": 6.173310225303293,
+      "grad_norm": 1.7174897193908691,
+      "learning_rate": 0.0002,
+      "loss": 0.4102,
+      "step": 895
+    },
+    {
+      "epoch": 6.2079722703639515,
+      "grad_norm": 2.4946401119232178,
+      "learning_rate": 0.0002,
+      "loss": 0.2899,
+      "step": 900
+    },
+    {
+      "epoch": 6.24263431542461,
+      "grad_norm": 2.8931374549865723,
+      "learning_rate": 0.0002,
+      "loss": 0.4676,
+      "step": 905
+    },
+    {
+      "epoch": 6.277296360485269,
+      "grad_norm": 0.8096083998680115,
+      "learning_rate": 0.0002,
+      "loss": 0.3168,
+      "step": 910
+    },
+    {
+      "epoch": 6.311958405545927,
+      "grad_norm": 0.4966631531715393,
+      "learning_rate": 0.0002,
+      "loss": 0.1399,
+      "step": 915
+    },
+    {
+      "epoch": 6.3466204506065855,
+      "grad_norm": 0.46740466356277466,
+      "learning_rate": 0.0002,
+      "loss": 0.1037,
+      "step": 920
+    },
+    {
+      "epoch": 6.381282495667245,
+      "grad_norm": 0.3550221920013428,
+      "learning_rate": 0.0002,
+      "loss": 0.0682,
+      "step": 925
+    },
+    {
+      "epoch": 6.415944540727903,
+      "grad_norm": 1.7010166645050049,
+      "learning_rate": 0.0002,
+      "loss": 0.401,
+      "step": 930
+    },
+    {
+      "epoch": 6.450606585788561,
+      "grad_norm": 1.4712696075439453,
+      "learning_rate": 0.0002,
+      "loss": 0.2843,
+      "step": 935
+    },
+    {
+      "epoch": 6.4852686308492205,
+      "grad_norm": 1.702062964439392,
+      "learning_rate": 0.0002,
+      "loss": 0.5166,
+      "step": 940
+    },
+    {
+      "epoch": 6.519930675909879,
+      "grad_norm": 0.6730090379714966,
+      "learning_rate": 0.0002,
+      "loss": 0.3467,
+      "step": 945
+    },
+    {
+      "epoch": 6.554592720970537,
+      "grad_norm": 0.6367856860160828,
+      "learning_rate": 0.0002,
+      "loss": 0.1564,
+      "step": 950
+    },
+    {
+      "epoch": 6.589254766031196,
+      "grad_norm": 0.5671469569206238,
+      "learning_rate": 0.0002,
+      "loss": 0.1267,
+      "step": 955
+    },
+    {
+      "epoch": 6.6239168110918545,
+      "grad_norm": 0.29594796895980835,
+      "learning_rate": 0.0002,
+      "loss": 0.0927,
+      "step": 960
+    },
+    {
+      "epoch": 6.658578856152513,
+      "grad_norm": 0.6945505738258362,
+      "learning_rate": 0.0002,
+      "loss": 0.0982,
+      "step": 965
+    },
+    {
+      "epoch": 6.693240901213172,
+      "grad_norm": 1.2007991075515747,
+      "learning_rate": 0.0002,
+      "loss": 0.4829,
+      "step": 970
+    },
+    {
+      "epoch": 6.72790294627383,
+      "grad_norm": 4.258643627166748,
+      "learning_rate": 0.0002,
+      "loss": 0.5014,
+      "step": 975
+    },
+    {
+      "epoch": 6.7625649913344885,
+      "grad_norm": 1.2368519306182861,
+      "learning_rate": 0.0002,
+      "loss": 0.4639,
+      "step": 980
+    },
+    {
+      "epoch": 6.797227036395148,
+      "grad_norm": 0.5854914784431458,
+      "learning_rate": 0.0002,
+      "loss": 0.1885,
+      "step": 985
+    },
+    {
+      "epoch": 6.831889081455806,
+      "grad_norm": 0.433727890253067,
+      "learning_rate": 0.0002,
+      "loss": 0.1182,
+      "step": 990
+    },
+    {
+      "epoch": 6.866551126516464,
+      "grad_norm": 0.37968766689300537,
+      "learning_rate": 0.0002,
+      "loss": 0.0907,
+      "step": 995
+    },
+    {
+      "epoch": 6.9012131715771226,
+      "grad_norm": 0.49255871772766113,
+      "learning_rate": 0.0002,
+      "loss": 0.0748,
+      "step": 1000
+    },
+    {
+      "epoch": 6.935875216637782,
+      "grad_norm": 0.8562117218971252,
+      "learning_rate": 0.0002,
+      "loss": 0.301,
+      "step": 1005
+    },
+    {
+      "epoch": 6.97053726169844,
+      "grad_norm": 2.18452787399292,
+      "learning_rate": 0.0002,
+      "loss": 0.5265,
+      "step": 1010
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 5.248262405395508,
+      "learning_rate": 0.0002,
+      "loss": 0.4677,
+      "step": 1015
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 1440,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.366970120384307e+16,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1015/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:809a1a5c9369a216b8a4d6e1c008ebfd2034bae620a7456bafd493b02b881a58
+size 5624

checkpoint-1160/README.md

@@ -0,0 +1,202 @@
+---
+base_model: microsoft/Phi-4-mini-instruct
+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 0.15.2

checkpoint-1160/adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "microsoft/Phi-4-mini-instruct",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "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_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "k_proj",
+    "q_proj",
+    "down_proj",
+    "o_proj",
+    "gate_proj",
+    "up_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-1160/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:394bc7c676d24ecff6b05cedfa2c4df52c9da9f034d2d0e5f4a4b69dd76f1d0d
+size 35668592

checkpoint-1160/added_tokens.json

@@ -0,0 +1,12 @@
+{
+  "<|/tool_call|>": 200026,
+  "<|/tool|>": 200024,
+  "<|assistant|>": 200019,
+  "<|end|>": 200020,
+  "<|system|>": 200022,
+  "<|tag|>": 200028,
+  "<|tool_call|>": 200025,
+  "<|tool_response|>": 200027,
+  "<|tool|>": 200023,
+  "<|user|>": 200021
+}

checkpoint-1160/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f397552e938c99a451111c00c20c30925abd9cf56bce32a4de25063d8b2bb2a
+size 18256762

checkpoint-1160/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:049aa61b6fdbbca66e0b99d3a611f23d30e85c99c5762395ef88e735640d7730
+size 14244

checkpoint-1160/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79763ab31b6efc519aa37c2bf6d03bfe87dd23be12eaf579ec750bf1c06975fc
+size 1064

checkpoint-1160/special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-1160/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d7f47443257fe193e8dcb1e6912235832f416fd25161c021f77cb63163cd44e
+size 15524193

checkpoint-1160/tokenizer_config.json

@@ -0,0 +1,112 @@
+{
+  "add_bos_token": false,
+  "add_eos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "199999": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200018": {
+      "content": "<|endofprompt|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200019": {
+      "content": "<|assistant|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "200020": {
+      "content": "<|end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "200021": {
+      "content": "<|user|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "200022": {
+      "content": "<|system|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "200023": {
+      "content": "<|tool|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "200024": {
+      "content": "<|/tool|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "200025": {
+      "content": "<|tool_call|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "200026": {
+      "content": "<|/tool_call|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "200027": {
+      "content": "<|tool_response|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "200028": {
+      "content": "<|tag|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "chat_template": "{% for message in messages %}{% if message['role'] == 'system' and 'tools' in message and message['tools'] is not none %}{{ '<|' + message['role'] + '|>' + message['content'] + '<|tool|>' + message['tools'] + '<|/tool|>' + '<|end|>' }}{% else %}{{ '<|' + message['role'] + '|>' + message['content'] + '<|end|>' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>' }}{% else %}{{ eos_token }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

checkpoint-1160/trainer_state.json

@@ -0,0 +1,1658 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 8.0,
+  "eval_steps": 500,
+  "global_step": 1160,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03466204506065858,
+      "grad_norm": 1.530611515045166,
+      "learning_rate": 0.0002,
+      "loss": 3.0151,
+      "step": 5
+    },
+    {
+      "epoch": 0.06932409012131716,
+      "grad_norm": 1.7004058361053467,
+      "learning_rate": 0.0002,
+      "loss": 2.0235,
+      "step": 10
+    },
+    {
+      "epoch": 0.10398613518197573,
+      "grad_norm": 1.933908462524414,
+      "learning_rate": 0.0002,
+      "loss": 1.1225,
+      "step": 15
+    },
+    {
+      "epoch": 0.1386481802426343,
+      "grad_norm": 0.9951248168945312,
+      "learning_rate": 0.0002,
+      "loss": 0.5422,
+      "step": 20
+    },
+    {
+      "epoch": 0.1733102253032929,
+      "grad_norm": 6.152623176574707,
+      "learning_rate": 0.0002,
+      "loss": 1.5639,
+      "step": 25
+    },
+    {
+      "epoch": 0.20797227036395147,
+      "grad_norm": 8.008278846740723,
+      "learning_rate": 0.0002,
+      "loss": 2.6486,
+      "step": 30
+    },
+    {
+      "epoch": 0.24263431542461006,
+      "grad_norm": 4.960943222045898,
+      "learning_rate": 0.0002,
+      "loss": 2.6059,
+      "step": 35
+    },
+    {
+      "epoch": 0.2772963604852686,
+      "grad_norm": 4.607645511627197,
+      "learning_rate": 0.0002,
+      "loss": 1.6898,
+      "step": 40
+    },
+    {
+      "epoch": 0.3119584055459272,
+      "grad_norm": 0.8448249101638794,
+      "learning_rate": 0.0002,
+      "loss": 0.799,
+      "step": 45
+    },
+    {
+      "epoch": 0.3466204506065858,
+      "grad_norm": 0.46238261461257935,
+      "learning_rate": 0.0002,
+      "loss": 0.5374,
+      "step": 50
+    },
+    {
+      "epoch": 0.38128249566724437,
+      "grad_norm": 0.3575257956981659,
+      "learning_rate": 0.0002,
+      "loss": 0.4247,
+      "step": 55
+    },
+    {
+      "epoch": 0.41594454072790293,
+      "grad_norm": 2.5151493549346924,
+      "learning_rate": 0.0002,
+      "loss": 0.7472,
+      "step": 60
+    },
+    {
+      "epoch": 0.4506065857885615,
+      "grad_norm": 17.38052749633789,
+      "learning_rate": 0.0002,
+      "loss": 1.8466,
+      "step": 65
+    },
+    {
+      "epoch": 0.4852686308492201,
+      "grad_norm": 15.523968696594238,
+      "learning_rate": 0.0002,
+      "loss": 2.1105,
+      "step": 70
+    },
+    {
+      "epoch": 0.5199306759098787,
+      "grad_norm": 1.0907574892044067,
+      "learning_rate": 0.0002,
+      "loss": 1.1052,
+      "step": 75
+    },
+    {
+      "epoch": 0.5545927209705372,
+      "grad_norm": 0.5225581526756287,
+      "learning_rate": 0.0002,
+      "loss": 0.5663,
+      "step": 80
+    },
+    {
+      "epoch": 0.5892547660311959,
+      "grad_norm": 0.3306778073310852,
+      "learning_rate": 0.0002,
+      "loss": 0.4648,
+      "step": 85
+    },
+    {
+      "epoch": 0.6239168110918544,
+      "grad_norm": 0.33595138788223267,
+      "learning_rate": 0.0002,
+      "loss": 0.3762,
+      "step": 90
+    },
+    {
+      "epoch": 0.658578856152513,
+      "grad_norm": 1.978458285331726,
+      "learning_rate": 0.0002,
+      "loss": 0.9162,
+      "step": 95
+    },
+    {
+      "epoch": 0.6932409012131716,
+      "grad_norm": 1.1226632595062256,
+      "learning_rate": 0.0002,
+      "loss": 1.5477,
+      "step": 100
+    },
+    {
+      "epoch": 0.7279029462738301,
+      "grad_norm": 22.263992309570312,
+      "learning_rate": 0.0002,
+      "loss": 1.8063,
+      "step": 105
+    },
+    {
+      "epoch": 0.7625649913344887,
+      "grad_norm": 1.3690563440322876,
+      "learning_rate": 0.0002,
+      "loss": 1.3102,
+      "step": 110
+    },
+    {
+      "epoch": 0.7972270363951474,
+      "grad_norm": 0.5651267766952515,
+      "learning_rate": 0.0002,
+      "loss": 0.553,
+      "step": 115
+    },
+    {
+      "epoch": 0.8318890814558059,
+      "grad_norm": 0.3272489011287689,
+      "learning_rate": 0.0002,
+      "loss": 0.4813,
+      "step": 120
+    },
+    {
+      "epoch": 0.8665511265164645,
+      "grad_norm": 0.30475500226020813,
+      "learning_rate": 0.0002,
+      "loss": 0.3746,
+      "step": 125
+    },
+    {
+      "epoch": 0.901213171577123,
+      "grad_norm": 0.2812097370624542,
+      "learning_rate": 0.0002,
+      "loss": 0.284,
+      "step": 130
+    },
+    {
+      "epoch": 0.9358752166377816,
+      "grad_norm": 1.159839391708374,
+      "learning_rate": 0.0002,
+      "loss": 1.5179,
+      "step": 135
+    },
+    {
+      "epoch": 0.9705372616984402,
+      "grad_norm": 4.740174770355225,
+      "learning_rate": 0.0002,
+      "loss": 1.549,
+      "step": 140
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 2.613008499145508,
+      "learning_rate": 0.0002,
+      "loss": 1.3938,
+      "step": 145
+    },
+    {
+      "epoch": 1.0346620450606585,
+      "grad_norm": 0.31811827421188354,
+      "learning_rate": 0.0002,
+      "loss": 0.5353,
+      "step": 150
+    },
+    {
+      "epoch": 1.0693240901213172,
+      "grad_norm": 0.42897579073905945,
+      "learning_rate": 0.0002,
+      "loss": 0.4452,
+      "step": 155
+    },
+    {
+      "epoch": 1.1039861351819757,
+      "grad_norm": 0.28854838013648987,
+      "learning_rate": 0.0002,
+      "loss": 0.3563,
+      "step": 160
+    },
+    {
+      "epoch": 1.1386481802426343,
+      "grad_norm": 0.32319992780685425,
+      "learning_rate": 0.0002,
+      "loss": 0.2697,
+      "step": 165
+    },
+    {
+      "epoch": 1.173310225303293,
+      "grad_norm": 1.0144641399383545,
+      "learning_rate": 0.0002,
+      "loss": 1.3199,
+      "step": 170
+    },
+    {
+      "epoch": 1.2079722703639515,
+      "grad_norm": 2.1387648582458496,
+      "learning_rate": 0.0002,
+      "loss": 1.1948,
+      "step": 175
+    },
+    {
+      "epoch": 1.24263431542461,
+      "grad_norm": 5.240429401397705,
+      "learning_rate": 0.0002,
+      "loss": 1.2138,
+      "step": 180
+    },
+    {
+      "epoch": 1.2772963604852685,
+      "grad_norm": 0.5809195637702942,
+      "learning_rate": 0.0002,
+      "loss": 0.7417,
+      "step": 185
+    },
+    {
+      "epoch": 1.3119584055459272,
+      "grad_norm": 0.3426031768321991,
+      "learning_rate": 0.0002,
+      "loss": 0.4541,
+      "step": 190
+    },
+    {
+      "epoch": 1.3466204506065858,
+      "grad_norm": 0.34089571237564087,
+      "learning_rate": 0.0002,
+      "loss": 0.3709,
+      "step": 195
+    },
+    {
+      "epoch": 1.3812824956672443,
+      "grad_norm": 0.2676282823085785,
+      "learning_rate": 0.0002,
+      "loss": 0.2981,
+      "step": 200
+    },
+    {
+      "epoch": 1.415944540727903,
+      "grad_norm": 1.8662705421447754,
+      "learning_rate": 0.0002,
+      "loss": 0.8353,
+      "step": 205
+    },
+    {
+      "epoch": 1.4506065857885615,
+      "grad_norm": 3.2310688495635986,
+      "learning_rate": 0.0002,
+      "loss": 1.2188,
+      "step": 210
+    },
+    {
+      "epoch": 1.48526863084922,
+      "grad_norm": 2.255415916442871,
+      "learning_rate": 0.0002,
+      "loss": 1.1677,
+      "step": 215
+    },
+    {
+      "epoch": 1.5199306759098787,
+      "grad_norm": 0.5544691681861877,
+      "learning_rate": 0.0002,
+      "loss": 0.799,
+      "step": 220
+    },
+    {
+      "epoch": 1.5545927209705372,
+      "grad_norm": 0.4003375172615051,
+      "learning_rate": 0.0002,
+      "loss": 0.4786,
+      "step": 225
+    },
+    {
+      "epoch": 1.5892547660311958,
+      "grad_norm": 0.3774619698524475,
+      "learning_rate": 0.0002,
+      "loss": 0.4233,
+      "step": 230
+    },
+    {
+      "epoch": 1.6239168110918545,
+      "grad_norm": 0.352490097284317,
+      "learning_rate": 0.0002,
+      "loss": 0.3332,
+      "step": 235
+    },
+    {
+      "epoch": 1.658578856152513,
+      "grad_norm": 0.2637154459953308,
+      "learning_rate": 0.0002,
+      "loss": 0.2438,
+      "step": 240
+    },
+    {
+      "epoch": 1.6932409012131715,
+      "grad_norm": 1.3437107801437378,
+      "learning_rate": 0.0002,
+      "loss": 1.4351,
+      "step": 245
+    },
+    {
+      "epoch": 1.7279029462738302,
+      "grad_norm": 2.647561550140381,
+      "learning_rate": 0.0002,
+      "loss": 1.0698,
+      "step": 250
+    },
+    {
+      "epoch": 1.7625649913344887,
+      "grad_norm": 0.6839751601219177,
+      "learning_rate": 0.0002,
+      "loss": 0.7411,
+      "step": 255
+    },
+    {
+      "epoch": 1.7972270363951472,
+      "grad_norm": 0.4790812134742737,
+      "learning_rate": 0.0002,
+      "loss": 0.5009,
+      "step": 260
+    },
+    {
+      "epoch": 1.831889081455806,
+      "grad_norm": 0.36322328448295593,
+      "learning_rate": 0.0002,
+      "loss": 0.4014,
+      "step": 265
+    },
+    {
+      "epoch": 1.8665511265164645,
+      "grad_norm": 0.31694507598876953,
+      "learning_rate": 0.0002,
+      "loss": 0.3441,
+      "step": 270
+    },
+    {
+      "epoch": 1.901213171577123,
+      "grad_norm": 0.24292677640914917,
+      "learning_rate": 0.0002,
+      "loss": 0.2619,
+      "step": 275
+    },
+    {
+      "epoch": 1.9358752166377817,
+      "grad_norm": 1.133062720298767,
+      "learning_rate": 0.0002,
+      "loss": 1.1564,
+      "step": 280
+    },
+    {
+      "epoch": 1.9705372616984402,
+      "grad_norm": 10.754274368286133,
+      "learning_rate": 0.0002,
+      "loss": 1.436,
+      "step": 285
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.6346553564071655,
+      "learning_rate": 0.0002,
+      "loss": 1.3215,
+      "step": 290
+    },
+    {
+      "epoch": 2.0346620450606587,
+      "grad_norm": 0.7156389355659485,
+      "learning_rate": 0.0002,
+      "loss": 0.551,
+      "step": 295
+    },
+    {
+      "epoch": 2.069324090121317,
+      "grad_norm": 0.3842258155345917,
+      "learning_rate": 0.0002,
+      "loss": 0.3783,
+      "step": 300
+    },
+    {
+      "epoch": 2.1039861351819757,
+      "grad_norm": 0.35967278480529785,
+      "learning_rate": 0.0002,
+      "loss": 0.3124,
+      "step": 305
+    },
+    {
+      "epoch": 2.1386481802426345,
+      "grad_norm": 0.296977162361145,
+      "learning_rate": 0.0002,
+      "loss": 0.2367,
+      "step": 310
+    },
+    {
+      "epoch": 2.1733102253032928,
+      "grad_norm": 1.6834601163864136,
+      "learning_rate": 0.0002,
+      "loss": 0.7685,
+      "step": 315
+    },
+    {
+      "epoch": 2.2079722703639515,
+      "grad_norm": 5.758884906768799,
+      "learning_rate": 0.0002,
+      "loss": 1.0063,
+      "step": 320
+    },
+    {
+      "epoch": 2.2426343154246102,
+      "grad_norm": 15.24948501586914,
+      "learning_rate": 0.0002,
+      "loss": 1.231,
+      "step": 325
+    },
+    {
+      "epoch": 2.2772963604852685,
+      "grad_norm": 0.599730372428894,
+      "learning_rate": 0.0002,
+      "loss": 0.6392,
+      "step": 330
+    },
+    {
+      "epoch": 2.3119584055459272,
+      "grad_norm": 0.5307044982910156,
+      "learning_rate": 0.0002,
+      "loss": 0.3804,
+      "step": 335
+    },
+    {
+      "epoch": 2.346620450606586,
+      "grad_norm": 0.33558061718940735,
+      "learning_rate": 0.0002,
+      "loss": 0.3282,
+      "step": 340
+    },
+    {
+      "epoch": 2.3812824956672443,
+      "grad_norm": 0.2716732919216156,
+      "learning_rate": 0.0002,
+      "loss": 0.2429,
+      "step": 345
+    },
+    {
+      "epoch": 2.415944540727903,
+      "grad_norm": 2.454636812210083,
+      "learning_rate": 0.0002,
+      "loss": 0.5396,
+      "step": 350
+    },
+    {
+      "epoch": 2.4506065857885613,
+      "grad_norm": 13.286089897155762,
+      "learning_rate": 0.0002,
+      "loss": 1.0545,
+      "step": 355
+    },
+    {
+      "epoch": 2.48526863084922,
+      "grad_norm": 12.619502067565918,
+      "learning_rate": 0.0002,
+      "loss": 1.1547,
+      "step": 360
+    },
+    {
+      "epoch": 2.5199306759098787,
+      "grad_norm": 0.6347368359565735,
+      "learning_rate": 0.0002,
+      "loss": 0.7136,
+      "step": 365
+    },
+    {
+      "epoch": 2.554592720970537,
+      "grad_norm": 0.44485101103782654,
+      "learning_rate": 0.0002,
+      "loss": 0.3994,
+      "step": 370
+    },
+    {
+      "epoch": 2.5892547660311958,
+      "grad_norm": 0.36494728922843933,
+      "learning_rate": 0.0002,
+      "loss": 0.3107,
+      "step": 375
+    },
+    {
+      "epoch": 2.6239168110918545,
+      "grad_norm": 0.322171688079834,
+      "learning_rate": 0.0002,
+      "loss": 0.2753,
+      "step": 380
+    },
+    {
+      "epoch": 2.6585788561525128,
+      "grad_norm": 0.9659174084663391,
+      "learning_rate": 0.0002,
+      "loss": 0.2948,
+      "step": 385
+    },
+    {
+      "epoch": 2.6932409012131715,
+      "grad_norm": 0.9371129870414734,
+      "learning_rate": 0.0002,
+      "loss": 1.0286,
+      "step": 390
+    },
+    {
+      "epoch": 2.7279029462738302,
+      "grad_norm": 3.4619617462158203,
+      "learning_rate": 0.0002,
+      "loss": 1.0745,
+      "step": 395
+    },
+    {
+      "epoch": 2.7625649913344885,
+      "grad_norm": 0.6884852051734924,
+      "learning_rate": 0.0002,
+      "loss": 0.7637,
+      "step": 400
+    },
+    {
+      "epoch": 2.7972270363951472,
+      "grad_norm": 0.4440446197986603,
+      "learning_rate": 0.0002,
+      "loss": 0.4331,
+      "step": 405
+    },
+    {
+      "epoch": 2.831889081455806,
+      "grad_norm": 0.37561893463134766,
+      "learning_rate": 0.0002,
+      "loss": 0.3667,
+      "step": 410
+    },
+    {
+      "epoch": 2.8665511265164643,
+      "grad_norm": 0.320077121257782,
+      "learning_rate": 0.0002,
+      "loss": 0.2769,
+      "step": 415
+    },
+    {
+      "epoch": 2.901213171577123,
+      "grad_norm": 1.4914495944976807,
+      "learning_rate": 0.0002,
+      "loss": 0.4493,
+      "step": 420
+    },
+    {
+      "epoch": 2.9358752166377817,
+      "grad_norm": 1.164036750793457,
+      "learning_rate": 0.0002,
+      "loss": 1.1276,
+      "step": 425
+    },
+    {
+      "epoch": 2.97053726169844,
+      "grad_norm": 5.013108253479004,
+      "learning_rate": 0.0002,
+      "loss": 1.0841,
+      "step": 430
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 2.2247564792633057,
+      "learning_rate": 0.0002,
+      "loss": 0.7636,
+      "step": 435
+    },
+    {
+      "epoch": 3.0346620450606587,
+      "grad_norm": 0.3730102479457855,
+      "learning_rate": 0.0002,
+      "loss": 0.4291,
+      "step": 440
+    },
+    {
+      "epoch": 3.069324090121317,
+      "grad_norm": 0.36571791768074036,
+      "learning_rate": 0.0002,
+      "loss": 0.3155,
+      "step": 445
+    },
+    {
+      "epoch": 3.1039861351819757,
+      "grad_norm": 0.34427550435066223,
+      "learning_rate": 0.0002,
+      "loss": 0.2297,
+      "step": 450
+    },
+    {
+      "epoch": 3.1386481802426345,
+      "grad_norm": 0.3725241422653198,
+      "learning_rate": 0.0002,
+      "loss": 0.173,
+      "step": 455
+    },
+    {
+      "epoch": 3.1733102253032928,
+      "grad_norm": 0.9735671877861023,
+      "learning_rate": 0.0002,
+      "loss": 0.8876,
+      "step": 460
+    },
+    {
+      "epoch": 3.2079722703639515,
+      "grad_norm": 3.0348145961761475,
+      "learning_rate": 0.0002,
+      "loss": 0.7825,
+      "step": 465
+    },
+    {
+      "epoch": 3.2426343154246102,
+      "grad_norm": 1.4603136777877808,
+      "learning_rate": 0.0002,
+      "loss": 0.8017,
+      "step": 470
+    },
+    {
+      "epoch": 3.2772963604852685,
+      "grad_norm": 0.6849704384803772,
+      "learning_rate": 0.0002,
+      "loss": 0.6029,
+      "step": 475
+    },
+    {
+      "epoch": 3.3119584055459272,
+      "grad_norm": 0.45950087904930115,
+      "learning_rate": 0.0002,
+      "loss": 0.3388,
+      "step": 480
+    },
+    {
+      "epoch": 3.346620450606586,
+      "grad_norm": 0.3234940469264984,
+      "learning_rate": 0.0002,
+      "loss": 0.2635,
+      "step": 485
+    },
+    {
+      "epoch": 3.3812824956672443,
+      "grad_norm": 0.3088044822216034,
+      "learning_rate": 0.0002,
+      "loss": 0.1867,
+      "step": 490
+    },
+    {
+      "epoch": 3.415944540727903,
+      "grad_norm": 0.36887720227241516,
+      "learning_rate": 0.0002,
+      "loss": 0.1653,
+      "step": 495
+    },
+    {
+      "epoch": 3.4506065857885613,
+      "grad_norm": 1.041858196258545,
+      "learning_rate": 0.0002,
+      "loss": 0.9041,
+      "step": 500
+    },
+    {
+      "epoch": 3.48526863084922,
+      "grad_norm": 1.4774988889694214,
+      "learning_rate": 0.0002,
+      "loss": 0.9789,
+      "step": 505
+    },
+    {
+      "epoch": 3.5199306759098787,
+      "grad_norm": 0.6804758310317993,
+      "learning_rate": 0.0002,
+      "loss": 0.5891,
+      "step": 510
+    },
+    {
+      "epoch": 3.554592720970537,
+      "grad_norm": 0.43344879150390625,
+      "learning_rate": 0.0002,
+      "loss": 0.3632,
+      "step": 515
+    },
+    {
+      "epoch": 3.5892547660311958,
+      "grad_norm": 0.4160469174385071,
+      "learning_rate": 0.0002,
+      "loss": 0.2734,
+      "step": 520
+    },
+    {
+      "epoch": 3.6239168110918545,
+      "grad_norm": 0.35103052854537964,
+      "learning_rate": 0.0002,
+      "loss": 0.2215,
+      "step": 525
+    },
+    {
+      "epoch": 3.6585788561525128,
+      "grad_norm": 1.083409309387207,
+      "learning_rate": 0.0002,
+      "loss": 0.2623,
+      "step": 530
+    },
+    {
+      "epoch": 3.6932409012131715,
+      "grad_norm": 1.2548085451126099,
+      "learning_rate": 0.0002,
+      "loss": 0.9395,
+      "step": 535
+    },
+    {
+      "epoch": 3.7279029462738302,
+      "grad_norm": 2.565399169921875,
+      "learning_rate": 0.0002,
+      "loss": 0.9097,
+      "step": 540
+    },
+    {
+      "epoch": 3.7625649913344885,
+      "grad_norm": 0.6658923625946045,
+      "learning_rate": 0.0002,
+      "loss": 0.739,
+      "step": 545
+    },
+    {
+      "epoch": 3.7972270363951472,
+      "grad_norm": 0.4989807605743408,
+      "learning_rate": 0.0002,
+      "loss": 0.396,
+      "step": 550
+    },
+    {
+      "epoch": 3.831889081455806,
+      "grad_norm": 0.39474496245384216,
+      "learning_rate": 0.0002,
+      "loss": 0.2809,
+      "step": 555
+    },
+    {
+      "epoch": 3.8665511265164643,
+      "grad_norm": 0.38600996136665344,
+      "learning_rate": 0.0002,
+      "loss": 0.2254,
+      "step": 560
+    },
+    {
+      "epoch": 3.901213171577123,
+      "grad_norm": 0.3662823736667633,
+      "learning_rate": 0.0002,
+      "loss": 0.167,
+      "step": 565
+    },
+    {
+      "epoch": 3.9358752166377817,
+      "grad_norm": 1.349672794342041,
+      "learning_rate": 0.0002,
+      "loss": 1.1593,
+      "step": 570
+    },
+    {
+      "epoch": 3.97053726169844,
+      "grad_norm": 2.3923165798187256,
+      "learning_rate": 0.0002,
+      "loss": 0.8778,
+      "step": 575
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.7578555345535278,
+      "learning_rate": 0.0002,
+      "loss": 0.6897,
+      "step": 580
+    },
+    {
+      "epoch": 4.034662045060658,
+      "grad_norm": 0.5052911043167114,
+      "learning_rate": 0.0002,
+      "loss": 0.3913,
+      "step": 585
+    },
+    {
+      "epoch": 4.0693240901213175,
+      "grad_norm": 0.5212499499320984,
+      "learning_rate": 0.0002,
+      "loss": 0.2326,
+      "step": 590
+    },
+    {
+      "epoch": 4.103986135181976,
+      "grad_norm": 0.452105313539505,
+      "learning_rate": 0.0002,
+      "loss": 0.1846,
+      "step": 595
+    },
+    {
+      "epoch": 4.138648180242634,
+      "grad_norm": 0.4193221926689148,
+      "learning_rate": 0.0002,
+      "loss": 0.1359,
+      "step": 600
+    },
+    {
+      "epoch": 4.173310225303293,
+      "grad_norm": 2.3956053256988525,
+      "learning_rate": 0.0002,
+      "loss": 0.3795,
+      "step": 605
+    },
+    {
+      "epoch": 4.2079722703639515,
+      "grad_norm": 1.946535348892212,
+      "learning_rate": 0.0002,
+      "loss": 0.579,
+      "step": 610
+    },
+    {
+      "epoch": 4.24263431542461,
+      "grad_norm": 1.874873161315918,
+      "learning_rate": 0.0002,
+      "loss": 0.7528,
+      "step": 615
+    },
+    {
+      "epoch": 4.277296360485269,
+      "grad_norm": 0.6922146081924438,
+      "learning_rate": 0.0002,
+      "loss": 0.4398,
+      "step": 620
+    },
+    {
+      "epoch": 4.311958405545927,
+      "grad_norm": 0.5228244662284851,
+      "learning_rate": 0.0002,
+      "loss": 0.2615,
+      "step": 625
+    },
+    {
+      "epoch": 4.3466204506065855,
+      "grad_norm": 0.34687915444374084,
+      "learning_rate": 0.0002,
+      "loss": 0.191,
+      "step": 630
+    },
+    {
+      "epoch": 4.381282495667245,
+      "grad_norm": 0.4160069525241852,
+      "learning_rate": 0.0002,
+      "loss": 0.1434,
+      "step": 635
+    },
+    {
+      "epoch": 4.415944540727903,
+      "grad_norm": 1.468666434288025,
+      "learning_rate": 0.0002,
+      "loss": 0.61,
+      "step": 640
+    },
+    {
+      "epoch": 4.450606585788561,
+      "grad_norm": 3.174201488494873,
+      "learning_rate": 0.0002,
+      "loss": 0.5773,
+      "step": 645
+    },
+    {
+      "epoch": 4.4852686308492205,
+      "grad_norm": 1.8258005380630493,
+      "learning_rate": 0.0002,
+      "loss": 0.7495,
+      "step": 650
+    },
+    {
+      "epoch": 4.519930675909879,
+      "grad_norm": 0.8468143343925476,
+      "learning_rate": 0.0002,
+      "loss": 0.5441,
+      "step": 655
+    },
+    {
+      "epoch": 4.554592720970537,
+      "grad_norm": 0.5467656254768372,
+      "learning_rate": 0.0002,
+      "loss": 0.2906,
+      "step": 660
+    },
+    {
+      "epoch": 4.589254766031196,
+      "grad_norm": 0.396992564201355,
+      "learning_rate": 0.0002,
+      "loss": 0.2186,
+      "step": 665
+    },
+    {
+      "epoch": 4.6239168110918545,
+      "grad_norm": 0.31931889057159424,
+      "learning_rate": 0.0002,
+      "loss": 0.1629,
+      "step": 670
+    },
+    {
+      "epoch": 4.658578856152513,
+      "grad_norm": 1.755745530128479,
+      "learning_rate": 0.0002,
+      "loss": 0.2292,
+      "step": 675
+    },
+    {
+      "epoch": 4.693240901213172,
+      "grad_norm": 0.9869062900543213,
+      "learning_rate": 0.0002,
+      "loss": 0.6716,
+      "step": 680
+    },
+    {
+      "epoch": 4.72790294627383,
+      "grad_norm": 1.5987203121185303,
+      "learning_rate": 0.0002,
+      "loss": 0.8182,
+      "step": 685
+    },
+    {
+      "epoch": 4.7625649913344885,
+      "grad_norm": 0.870819091796875,
+      "learning_rate": 0.0002,
+      "loss": 0.5902,
+      "step": 690
+    },
+    {
+      "epoch": 4.797227036395148,
+      "grad_norm": 0.5098839402198792,
+      "learning_rate": 0.0002,
+      "loss": 0.3224,
+      "step": 695
+    },
+    {
+      "epoch": 4.831889081455806,
+      "grad_norm": 0.5435961484909058,
+      "learning_rate": 0.0002,
+      "loss": 0.2182,
+      "step": 700
+    },
+    {
+      "epoch": 4.866551126516464,
+      "grad_norm": 0.33275553584098816,
+      "learning_rate": 0.0002,
+      "loss": 0.1595,
+      "step": 705
+    },
+    {
+      "epoch": 4.9012131715771226,
+      "grad_norm": 1.8109265565872192,
+      "learning_rate": 0.0002,
+      "loss": 0.1985,
+      "step": 710
+    },
+    {
+      "epoch": 4.935875216637782,
+      "grad_norm": 1.149431824684143,
+      "learning_rate": 0.0002,
+      "loss": 0.8148,
+      "step": 715
+    },
+    {
+      "epoch": 4.97053726169844,
+      "grad_norm": 1.4355350732803345,
+      "learning_rate": 0.0002,
+      "loss": 0.6675,
+      "step": 720
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 2.76149845123291,
+      "learning_rate": 0.0002,
+      "loss": 0.5541,
+      "step": 725
+    },
+    {
+      "epoch": 5.034662045060658,
+      "grad_norm": 0.6026546359062195,
+      "learning_rate": 0.0002,
+      "loss": 0.3515,
+      "step": 730
+    },
+    {
+      "epoch": 5.0693240901213175,
+      "grad_norm": 0.37150222063064575,
+      "learning_rate": 0.0002,
+      "loss": 0.1661,
+      "step": 735
+    },
+    {
+      "epoch": 5.103986135181976,
+      "grad_norm": 0.31225013732910156,
+      "learning_rate": 0.0002,
+      "loss": 0.1243,
+      "step": 740
+    },
+    {
+      "epoch": 5.138648180242634,
+      "grad_norm": 0.4382600784301758,
+      "learning_rate": 0.0002,
+      "loss": 0.1004,
+      "step": 745
+    },
+    {
+      "epoch": 5.173310225303293,
+      "grad_norm": 2.0306389331817627,
+      "learning_rate": 0.0002,
+      "loss": 0.3743,
+      "step": 750
+    },
+    {
+      "epoch": 5.2079722703639515,
+      "grad_norm": 1.6935468912124634,
+      "learning_rate": 0.0002,
+      "loss": 0.4202,
+      "step": 755
+    },
+    {
+      "epoch": 5.24263431542461,
+      "grad_norm": 1.4990637302398682,
+      "learning_rate": 0.0002,
+      "loss": 0.5533,
+      "step": 760
+    },
+    {
+      "epoch": 5.277296360485269,
+      "grad_norm": 0.6687419414520264,
+      "learning_rate": 0.0002,
+      "loss": 0.3429,
+      "step": 765
+    },
+    {
+      "epoch": 5.311958405545927,
+      "grad_norm": 0.5400169491767883,
+      "learning_rate": 0.0002,
+      "loss": 0.1759,
+      "step": 770
+    },
+    {
+      "epoch": 5.3466204506065855,
+      "grad_norm": 0.39679139852523804,
+      "learning_rate": 0.0002,
+      "loss": 0.1395,
+      "step": 775
+    },
+    {
+      "epoch": 5.381282495667245,
+      "grad_norm": 0.33043885231018066,
+      "learning_rate": 0.0002,
+      "loss": 0.1004,
+      "step": 780
+    },
+    {
+      "epoch": 5.415944540727903,
+      "grad_norm": 3.1912200450897217,
+      "learning_rate": 0.0002,
+      "loss": 0.305,
+      "step": 785
+    },
+    {
+      "epoch": 5.450606585788561,
+      "grad_norm": 1.2743686437606812,
+      "learning_rate": 0.0002,
+      "loss": 0.4876,
+      "step": 790
+    },
+    {
+      "epoch": 5.4852686308492205,
+      "grad_norm": 2.9798948764801025,
+      "learning_rate": 0.0002,
+      "loss": 0.7476,
+      "step": 795
+    },
+    {
+      "epoch": 5.519930675909879,
+      "grad_norm": 0.7342365384101868,
+      "learning_rate": 0.0002,
+      "loss": 0.463,
+      "step": 800
+    },
+    {
+      "epoch": 5.554592720970537,
+      "grad_norm": 0.5035507678985596,
+      "learning_rate": 0.0002,
+      "loss": 0.2116,
+      "step": 805
+    },
+    {
+      "epoch": 5.589254766031196,
+      "grad_norm": 0.4394471347332001,
+      "learning_rate": 0.0002,
+      "loss": 0.1568,
+      "step": 810
+    },
+    {
+      "epoch": 5.6239168110918545,
+      "grad_norm": 0.383515328168869,
+      "learning_rate": 0.0002,
+      "loss": 0.1035,
+      "step": 815
+    },
+    {
+      "epoch": 5.658578856152513,
+      "grad_norm": 2.142784357070923,
+      "learning_rate": 0.0002,
+      "loss": 0.3458,
+      "step": 820
+    },
+    {
+      "epoch": 5.693240901213172,
+      "grad_norm": 1.2484018802642822,
+      "learning_rate": 0.0002,
+      "loss": 0.3576,
+      "step": 825
+    },
+    {
+      "epoch": 5.72790294627383,
+      "grad_norm": 2.6863198280334473,
+      "learning_rate": 0.0002,
+      "loss": 0.5996,
+      "step": 830
+    },
+    {
+      "epoch": 5.7625649913344885,
+      "grad_norm": 1.098381757736206,
+      "learning_rate": 0.0002,
+      "loss": 0.4993,
+      "step": 835
+    },
+    {
+      "epoch": 5.797227036395148,
+      "grad_norm": 0.5609210133552551,
+      "learning_rate": 0.0002,
+      "loss": 0.2608,
+      "step": 840
+    },
+    {
+      "epoch": 5.831889081455806,
+      "grad_norm": 0.5123816132545471,
+      "learning_rate": 0.0002,
+      "loss": 0.1799,
+      "step": 845
+    },
+    {
+      "epoch": 5.866551126516464,
+      "grad_norm": 0.46399134397506714,
+      "learning_rate": 0.0002,
+      "loss": 0.1254,
+      "step": 850
+    },
+    {
+      "epoch": 5.9012131715771226,
+      "grad_norm": 0.5089249014854431,
+      "learning_rate": 0.0002,
+      "loss": 0.0934,
+      "step": 855
+    },
+    {
+      "epoch": 5.935875216637782,
+      "grad_norm": 1.3031930923461914,
+      "learning_rate": 0.0002,
+      "loss": 0.6664,
+      "step": 860
+    },
+    {
+      "epoch": 5.97053726169844,
+      "grad_norm": 2.294696569442749,
+      "learning_rate": 0.0002,
+      "loss": 0.6034,
+      "step": 865
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 2.738062620162964,
+      "learning_rate": 0.0002,
+      "loss": 0.587,
+      "step": 870
+    },
+    {
+      "epoch": 6.034662045060658,
+      "grad_norm": 0.6086808443069458,
+      "learning_rate": 0.0002,
+      "loss": 0.252,
+      "step": 875
+    },
+    {
+      "epoch": 6.0693240901213175,
+      "grad_norm": 0.4935630261898041,
+      "learning_rate": 0.0002,
+      "loss": 0.1223,
+      "step": 880
+    },
+    {
+      "epoch": 6.103986135181976,
+      "grad_norm": 0.43656599521636963,
+      "learning_rate": 0.0002,
+      "loss": 0.0882,
+      "step": 885
+    },
+    {
+      "epoch": 6.138648180242634,
+      "grad_norm": 0.2987945079803467,
+      "learning_rate": 0.0002,
+      "loss": 0.0629,
+      "step": 890
+    },
+    {
+      "epoch": 6.173310225303293,
+      "grad_norm": 1.7174897193908691,
+      "learning_rate": 0.0002,
+      "loss": 0.4102,
+      "step": 895
+    },
+    {
+      "epoch": 6.2079722703639515,
+      "grad_norm": 2.4946401119232178,
+      "learning_rate": 0.0002,
+      "loss": 0.2899,
+      "step": 900
+    },
+    {
+      "epoch": 6.24263431542461,
+      "grad_norm": 2.8931374549865723,
+      "learning_rate": 0.0002,
+      "loss": 0.4676,
+      "step": 905
+    },
+    {
+      "epoch": 6.277296360485269,
+      "grad_norm": 0.8096083998680115,
+      "learning_rate": 0.0002,
+      "loss": 0.3168,
+      "step": 910
+    },
+    {
+      "epoch": 6.311958405545927,
+      "grad_norm": 0.4966631531715393,
+      "learning_rate": 0.0002,
+      "loss": 0.1399,
+      "step": 915
+    },
+    {
+      "epoch": 6.3466204506065855,
+      "grad_norm": 0.46740466356277466,
+      "learning_rate": 0.0002,
+      "loss": 0.1037,
+      "step": 920
+    },
+    {
+      "epoch": 6.381282495667245,
+      "grad_norm": 0.3550221920013428,
+      "learning_rate": 0.0002,
+      "loss": 0.0682,
+      "step": 925
+    },
+    {
+      "epoch": 6.415944540727903,
+      "grad_norm": 1.7010166645050049,
+      "learning_rate": 0.0002,
+      "loss": 0.401,
+      "step": 930
+    },
+    {
+      "epoch": 6.450606585788561,
+      "grad_norm": 1.4712696075439453,
+      "learning_rate": 0.0002,
+      "loss": 0.2843,
+      "step": 935
+    },
+    {
+      "epoch": 6.4852686308492205,
+      "grad_norm": 1.702062964439392,
+      "learning_rate": 0.0002,
+      "loss": 0.5166,
+      "step": 940
+    },
+    {
+      "epoch": 6.519930675909879,
+      "grad_norm": 0.6730090379714966,
+      "learning_rate": 0.0002,
+      "loss": 0.3467,
+      "step": 945
+    },
+    {
+      "epoch": 6.554592720970537,
+      "grad_norm": 0.6367856860160828,
+      "learning_rate": 0.0002,
+      "loss": 0.1564,
+      "step": 950
+    },
+    {
+      "epoch": 6.589254766031196,
+      "grad_norm": 0.5671469569206238,
+      "learning_rate": 0.0002,
+      "loss": 0.1267,
+      "step": 955
+    },
+    {
+      "epoch": 6.6239168110918545,
+      "grad_norm": 0.29594796895980835,
+      "learning_rate": 0.0002,
+      "loss": 0.0927,
+      "step": 960
+    },
+    {
+      "epoch": 6.658578856152513,
+      "grad_norm": 0.6945505738258362,
+      "learning_rate": 0.0002,
+      "loss": 0.0982,
+      "step": 965
+    },
+    {
+      "epoch": 6.693240901213172,
+      "grad_norm": 1.2007991075515747,
+      "learning_rate": 0.0002,
+      "loss": 0.4829,
+      "step": 970
+    },
+    {
+      "epoch": 6.72790294627383,
+      "grad_norm": 4.258643627166748,
+      "learning_rate": 0.0002,
+      "loss": 0.5014,
+      "step": 975
+    },
+    {
+      "epoch": 6.7625649913344885,
+      "grad_norm": 1.2368519306182861,
+      "learning_rate": 0.0002,
+      "loss": 0.4639,
+      "step": 980
+    },
+    {
+      "epoch": 6.797227036395148,
+      "grad_norm": 0.5854914784431458,
+      "learning_rate": 0.0002,
+      "loss": 0.1885,
+      "step": 985
+    },
+    {
+      "epoch": 6.831889081455806,
+      "grad_norm": 0.433727890253067,
+      "learning_rate": 0.0002,
+      "loss": 0.1182,
+      "step": 990
+    },
+    {
+      "epoch": 6.866551126516464,
+      "grad_norm": 0.37968766689300537,
+      "learning_rate": 0.0002,
+      "loss": 0.0907,
+      "step": 995
+    },
+    {
+      "epoch": 6.9012131715771226,
+      "grad_norm": 0.49255871772766113,
+      "learning_rate": 0.0002,
+      "loss": 0.0748,
+      "step": 1000
+    },
+    {
+      "epoch": 6.935875216637782,
+      "grad_norm": 0.8562117218971252,
+      "learning_rate": 0.0002,
+      "loss": 0.301,
+      "step": 1005
+    },
+    {
+      "epoch": 6.97053726169844,
+      "grad_norm": 2.18452787399292,
+      "learning_rate": 0.0002,
+      "loss": 0.5265,
+      "step": 1010
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 5.248262405395508,
+      "learning_rate": 0.0002,
+      "loss": 0.4677,
+      "step": 1015
+    },
+    {
+      "epoch": 7.034662045060658,
+      "grad_norm": 0.6046018600463867,
+      "learning_rate": 0.0002,
+      "loss": 0.1937,
+      "step": 1020
+    },
+    {
+      "epoch": 7.0693240901213175,
+      "grad_norm": 0.4035234749317169,
+      "learning_rate": 0.0002,
+      "loss": 0.0889,
+      "step": 1025
+    },
+    {
+      "epoch": 7.103986135181976,
+      "grad_norm": 0.41130027174949646,
+      "learning_rate": 0.0002,
+      "loss": 0.0768,
+      "step": 1030
+    },
+    {
+      "epoch": 7.138648180242634,
+      "grad_norm": 0.43616095185279846,
+      "learning_rate": 0.0002,
+      "loss": 0.062,
+      "step": 1035
+    },
+    {
+      "epoch": 7.173310225303293,
+      "grad_norm": 1.4820456504821777,
+      "learning_rate": 0.0002,
+      "loss": 0.2592,
+      "step": 1040
+    },
+    {
+      "epoch": 7.2079722703639515,
+      "grad_norm": 2.2512240409851074,
+      "learning_rate": 0.0002,
+      "loss": 0.2771,
+      "step": 1045
+    },
+    {
+      "epoch": 7.24263431542461,
+      "grad_norm": 1.473806619644165,
+      "learning_rate": 0.0002,
+      "loss": 0.3877,
+      "step": 1050
+    },
+    {
+      "epoch": 7.277296360485269,
+      "grad_norm": 0.7703912258148193,
+      "learning_rate": 0.0002,
+      "loss": 0.2664,
+      "step": 1055
+    },
+    {
+      "epoch": 7.311958405545927,
+      "grad_norm": 0.5043675303459167,
+      "learning_rate": 0.0002,
+      "loss": 0.1109,
+      "step": 1060
+    },
+    {
+      "epoch": 7.3466204506065855,
+      "grad_norm": 0.43726152181625366,
+      "learning_rate": 0.0002,
+      "loss": 0.0839,
+      "step": 1065
+    },
+    {
+      "epoch": 7.381282495667245,
+      "grad_norm": 0.4088805615901947,
+      "learning_rate": 0.0002,
+      "loss": 0.0627,
+      "step": 1070
+    },
+    {
+      "epoch": 7.415944540727903,
+      "grad_norm": 2.5372557640075684,
+      "learning_rate": 0.0002,
+      "loss": 0.1959,
+      "step": 1075
+    },
+    {
+      "epoch": 7.450606585788561,
+      "grad_norm": 2.1121976375579834,
+      "learning_rate": 0.0002,
+      "loss": 0.3118,
+      "step": 1080
+    },
+    {
+      "epoch": 7.4852686308492205,
+      "grad_norm": 2.125603199005127,
+      "learning_rate": 0.0002,
+      "loss": 0.565,
+      "step": 1085
+    },
+    {
+      "epoch": 7.519930675909879,
+      "grad_norm": 0.8563218116760254,
+      "learning_rate": 0.0002,
+      "loss": 0.4099,
+      "step": 1090
+    },
+    {
+      "epoch": 7.554592720970537,
+      "grad_norm": 0.4825403392314911,
+      "learning_rate": 0.0002,
+      "loss": 0.1419,
+      "step": 1095
+    },
+    {
+      "epoch": 7.589254766031196,
+      "grad_norm": 0.4735303521156311,
+      "learning_rate": 0.0002,
+      "loss": 0.09,
+      "step": 1100
+    },
+    {
+      "epoch": 7.6239168110918545,
+      "grad_norm": 0.24926654994487762,
+      "learning_rate": 0.0002,
+      "loss": 0.0699,
+      "step": 1105
+    },
+    {
+      "epoch": 7.658578856152513,
+      "grad_norm": 0.2843971252441406,
+      "learning_rate": 0.0002,
+      "loss": 0.0602,
+      "step": 1110
+    },
+    {
+      "epoch": 7.693240901213172,
+      "grad_norm": 0.9436930418014526,
+      "learning_rate": 0.0002,
+      "loss": 0.3591,
+      "step": 1115
+    },
+    {
+      "epoch": 7.72790294627383,
+      "grad_norm": 1.8918225765228271,
+      "learning_rate": 0.0002,
+      "loss": 0.4049,
+      "step": 1120
+    },
+    {
+      "epoch": 7.7625649913344885,
+      "grad_norm": 1.1229664087295532,
+      "learning_rate": 0.0002,
+      "loss": 0.4094,
+      "step": 1125
+    },
+    {
+      "epoch": 7.797227036395148,
+      "grad_norm": 0.6665800213813782,
+      "learning_rate": 0.0002,
+      "loss": 0.1265,
+      "step": 1130
+    },
+    {
+      "epoch": 7.831889081455806,
+      "grad_norm": 0.38160014152526855,
+      "learning_rate": 0.0002,
+      "loss": 0.0895,
+      "step": 1135
+    },
+    {
+      "epoch": 7.866551126516464,
+      "grad_norm": 0.5825662612915039,
+      "learning_rate": 0.0002,
+      "loss": 0.0637,
+      "step": 1140
+    },
+    {
+      "epoch": 7.9012131715771226,
+      "grad_norm": 2.218074321746826,
+      "learning_rate": 0.0002,
+      "loss": 0.22,
+      "step": 1145
+    },
+    {
+      "epoch": 7.935875216637782,
+      "grad_norm": 1.0831362009048462,
+      "learning_rate": 0.0002,
+      "loss": 0.3117,
+      "step": 1150
+    },
+    {
+      "epoch": 7.97053726169844,
+      "grad_norm": 1.6957491636276245,
+      "learning_rate": 0.0002,
+      "loss": 0.3566,
+      "step": 1155
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 6.261979103088379,
+      "learning_rate": 0.0002,
+      "loss": 0.4143,
+      "step": 1160
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 1440,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.705287300557005e+16,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1160/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:809a1a5c9369a216b8a4d6e1c008ebfd2034bae620a7456bafd493b02b881a58
+size 5624

checkpoint-1296/README.md

@@ -0,0 +1,202 @@
+---
+base_model: microsoft/Phi-4-mini-instruct
+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 0.15.2

checkpoint-1296/adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "microsoft/Phi-4-mini-instruct",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "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_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "k_proj",
+    "down_proj",
+    "v_proj",
+    "gate_proj",
+    "q_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-1296/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cce141f122b838f99ad3388d6423141fed7e541da19924acd35d22b943f6a3a8
+size 35668592

checkpoint-1296/added_tokens.json

@@ -0,0 +1,12 @@
+{
+  "<|/tool_call|>": 200026,
+  "<|/tool|>": 200024,
+  "<|assistant|>": 200019,
+  "<|end|>": 200020,
+  "<|system|>": 200022,
+  "<|tag|>": 200028,
+  "<|tool_call|>": 200025,
+  "<|tool_response|>": 200027,
+  "<|tool|>": 200023,
+  "<|user|>": 200021
+}

checkpoint-1296/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2fe732b7d8fd4b3625dd06412d2d8b308d3976b90d7e58b49e1d8a7bd16bb5b9
+size 18586618

checkpoint-1296/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2aead8a90f9f2693e3481ad74bca9b9235f64a374a51400d02ce063512f502c2
+size 14244

checkpoint-1296/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:718c89d47513626d81f89576e0c3ab350e1560231539c499bab2294e1070c3f1
+size 1064

checkpoint-1296/special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-1296/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d7f47443257fe193e8dcb1e6912235832f416fd25161c021f77cb63163cd44e
+size 15524193

checkpoint-1296/tokenizer_config.json

@@ -0,0 +1,112 @@
+{
+  "add_bos_token": false,
+  "add_eos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "199999": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200018": {
+      "content": "<|endofprompt|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200019": {
+      "content": "<|assistant|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "200020": {
+      "content": "<|end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "200021": {
+      "content": "<|user|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "200022": {
+      "content": "<|system|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "200023": {
+      "content": "<|tool|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "200024": {
+      "content": "<|/tool|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "200025": {
+      "content": "<|tool_call|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "200026": {
+      "content": "<|/tool_call|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "200027": {
+      "content": "<|tool_response|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "200028": {
+      "content": "<|tag|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "chat_template": "{% for message in messages %}{% if message['role'] == 'system' and 'tools' in message and message['tools'] is not none %}{{ '<|' + message['role'] + '|>' + message['content'] + '<|tool|>' + message['tools'] + '<|/tool|>' + '<|end|>' }}{% else %}{{ '<|' + message['role'] + '|>' + message['content'] + '<|end|>' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>' }}{% else %}{{ eos_token }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

checkpoint-1296/trainer_state.json

@@ -0,0 +1,1847 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 8.998266897746968,
+  "eval_steps": 500,
+  "global_step": 1296,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03466204506065858,
+      "grad_norm": 1.530611515045166,
+      "learning_rate": 0.0002,
+      "loss": 3.0151,
+      "step": 5
+    },
+    {
+      "epoch": 0.06932409012131716,
+      "grad_norm": 1.7004058361053467,
+      "learning_rate": 0.0002,
+      "loss": 2.0235,
+      "step": 10
+    },
+    {
+      "epoch": 0.10398613518197573,
+      "grad_norm": 1.933908462524414,
+      "learning_rate": 0.0002,
+      "loss": 1.1225,
+      "step": 15
+    },
+    {
+      "epoch": 0.1386481802426343,
+      "grad_norm": 0.9951248168945312,
+      "learning_rate": 0.0002,
+      "loss": 0.5422,
+      "step": 20
+    },
+    {
+      "epoch": 0.1733102253032929,
+      "grad_norm": 6.152623176574707,
+      "learning_rate": 0.0002,
+      "loss": 1.5639,
+      "step": 25
+    },
+    {
+      "epoch": 0.20797227036395147,
+      "grad_norm": 8.008278846740723,
+      "learning_rate": 0.0002,
+      "loss": 2.6486,
+      "step": 30
+    },
+    {
+      "epoch": 0.24263431542461006,
+      "grad_norm": 4.960943222045898,
+      "learning_rate": 0.0002,
+      "loss": 2.6059,
+      "step": 35
+    },
+    {
+      "epoch": 0.2772963604852686,
+      "grad_norm": 4.607645511627197,
+      "learning_rate": 0.0002,
+      "loss": 1.6898,
+      "step": 40
+    },
+    {
+      "epoch": 0.3119584055459272,
+      "grad_norm": 0.8448249101638794,
+      "learning_rate": 0.0002,
+      "loss": 0.799,
+      "step": 45
+    },
+    {
+      "epoch": 0.3466204506065858,
+      "grad_norm": 0.46238261461257935,
+      "learning_rate": 0.0002,
+      "loss": 0.5374,
+      "step": 50
+    },
+    {
+      "epoch": 0.38128249566724437,
+      "grad_norm": 0.3575257956981659,
+      "learning_rate": 0.0002,
+      "loss": 0.4247,
+      "step": 55
+    },
+    {
+      "epoch": 0.41594454072790293,
+      "grad_norm": 2.5151493549346924,
+      "learning_rate": 0.0002,
+      "loss": 0.7472,
+      "step": 60
+    },
+    {
+      "epoch": 0.4506065857885615,
+      "grad_norm": 17.38052749633789,
+      "learning_rate": 0.0002,
+      "loss": 1.8466,
+      "step": 65
+    },
+    {
+      "epoch": 0.4852686308492201,
+      "grad_norm": 15.523968696594238,
+      "learning_rate": 0.0002,
+      "loss": 2.1105,
+      "step": 70
+    },
+    {
+      "epoch": 0.5199306759098787,
+      "grad_norm": 1.0907574892044067,
+      "learning_rate": 0.0002,
+      "loss": 1.1052,
+      "step": 75
+    },
+    {
+      "epoch": 0.5545927209705372,
+      "grad_norm": 0.5225581526756287,
+      "learning_rate": 0.0002,
+      "loss": 0.5663,
+      "step": 80
+    },
+    {
+      "epoch": 0.5892547660311959,
+      "grad_norm": 0.3306778073310852,
+      "learning_rate": 0.0002,
+      "loss": 0.4648,
+      "step": 85
+    },
+    {
+      "epoch": 0.6239168110918544,
+      "grad_norm": 0.33595138788223267,
+      "learning_rate": 0.0002,
+      "loss": 0.3762,
+      "step": 90
+    },
+    {
+      "epoch": 0.658578856152513,
+      "grad_norm": 1.978458285331726,
+      "learning_rate": 0.0002,
+      "loss": 0.9162,
+      "step": 95
+    },
+    {
+      "epoch": 0.6932409012131716,
+      "grad_norm": 1.1226632595062256,
+      "learning_rate": 0.0002,
+      "loss": 1.5477,
+      "step": 100
+    },
+    {
+      "epoch": 0.7279029462738301,
+      "grad_norm": 22.263992309570312,
+      "learning_rate": 0.0002,
+      "loss": 1.8063,
+      "step": 105
+    },
+    {
+      "epoch": 0.7625649913344887,
+      "grad_norm": 1.3690563440322876,
+      "learning_rate": 0.0002,
+      "loss": 1.3102,
+      "step": 110
+    },
+    {
+      "epoch": 0.7972270363951474,
+      "grad_norm": 0.5651267766952515,
+      "learning_rate": 0.0002,
+      "loss": 0.553,
+      "step": 115
+    },
+    {
+      "epoch": 0.8318890814558059,
+      "grad_norm": 0.3272489011287689,
+      "learning_rate": 0.0002,
+      "loss": 0.4813,
+      "step": 120
+    },
+    {
+      "epoch": 0.8665511265164645,
+      "grad_norm": 0.30475500226020813,
+      "learning_rate": 0.0002,
+      "loss": 0.3746,
+      "step": 125
+    },
+    {
+      "epoch": 0.901213171577123,
+      "grad_norm": 0.2812097370624542,
+      "learning_rate": 0.0002,
+      "loss": 0.284,
+      "step": 130
+    },
+    {
+      "epoch": 0.9358752166377816,
+      "grad_norm": 1.159839391708374,
+      "learning_rate": 0.0002,
+      "loss": 1.5179,
+      "step": 135
+    },
+    {
+      "epoch": 0.9705372616984402,
+      "grad_norm": 4.740174770355225,
+      "learning_rate": 0.0002,
+      "loss": 1.549,
+      "step": 140
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 2.613008499145508,
+      "learning_rate": 0.0002,
+      "loss": 1.3938,
+      "step": 145
+    },
+    {
+      "epoch": 1.0346620450606585,
+      "grad_norm": 0.31811827421188354,
+      "learning_rate": 0.0002,
+      "loss": 0.5353,
+      "step": 150
+    },
+    {
+      "epoch": 1.0693240901213172,
+      "grad_norm": 0.42897579073905945,
+      "learning_rate": 0.0002,
+      "loss": 0.4452,
+      "step": 155
+    },
+    {
+      "epoch": 1.1039861351819757,
+      "grad_norm": 0.28854838013648987,
+      "learning_rate": 0.0002,
+      "loss": 0.3563,
+      "step": 160
+    },
+    {
+      "epoch": 1.1386481802426343,
+      "grad_norm": 0.32319992780685425,
+      "learning_rate": 0.0002,
+      "loss": 0.2697,
+      "step": 165
+    },
+    {
+      "epoch": 1.173310225303293,
+      "grad_norm": 1.0144641399383545,
+      "learning_rate": 0.0002,
+      "loss": 1.3199,
+      "step": 170
+    },
+    {
+      "epoch": 1.2079722703639515,
+      "grad_norm": 2.1387648582458496,
+      "learning_rate": 0.0002,
+      "loss": 1.1948,
+      "step": 175
+    },
+    {
+      "epoch": 1.24263431542461,
+      "grad_norm": 5.240429401397705,
+      "learning_rate": 0.0002,
+      "loss": 1.2138,
+      "step": 180
+    },
+    {
+      "epoch": 1.2772963604852685,
+      "grad_norm": 0.5809195637702942,
+      "learning_rate": 0.0002,
+      "loss": 0.7417,
+      "step": 185
+    },
+    {
+      "epoch": 1.3119584055459272,
+      "grad_norm": 0.3426031768321991,
+      "learning_rate": 0.0002,
+      "loss": 0.4541,
+      "step": 190
+    },
+    {
+      "epoch": 1.3466204506065858,
+      "grad_norm": 0.34089571237564087,
+      "learning_rate": 0.0002,
+      "loss": 0.3709,
+      "step": 195
+    },
+    {
+      "epoch": 1.3812824956672443,
+      "grad_norm": 0.2676282823085785,
+      "learning_rate": 0.0002,
+      "loss": 0.2981,
+      "step": 200
+    },
+    {
+      "epoch": 1.415944540727903,
+      "grad_norm": 1.8662705421447754,
+      "learning_rate": 0.0002,
+      "loss": 0.8353,
+      "step": 205
+    },
+    {
+      "epoch": 1.4506065857885615,
+      "grad_norm": 3.2310688495635986,
+      "learning_rate": 0.0002,
+      "loss": 1.2188,
+      "step": 210
+    },
+    {
+      "epoch": 1.48526863084922,
+      "grad_norm": 2.255415916442871,
+      "learning_rate": 0.0002,
+      "loss": 1.1677,
+      "step": 215
+    },
+    {
+      "epoch": 1.5199306759098787,
+      "grad_norm": 0.5544691681861877,
+      "learning_rate": 0.0002,
+      "loss": 0.799,
+      "step": 220
+    },
+    {
+      "epoch": 1.5545927209705372,
+      "grad_norm": 0.4003375172615051,
+      "learning_rate": 0.0002,
+      "loss": 0.4786,
+      "step": 225
+    },
+    {
+      "epoch": 1.5892547660311958,
+      "grad_norm": 0.3774619698524475,
+      "learning_rate": 0.0002,
+      "loss": 0.4233,
+      "step": 230
+    },
+    {
+      "epoch": 1.6239168110918545,
+      "grad_norm": 0.352490097284317,
+      "learning_rate": 0.0002,
+      "loss": 0.3332,
+      "step": 235
+    },
+    {
+      "epoch": 1.658578856152513,
+      "grad_norm": 0.2637154459953308,
+      "learning_rate": 0.0002,
+      "loss": 0.2438,
+      "step": 240
+    },
+    {
+      "epoch": 1.6932409012131715,
+      "grad_norm": 1.3437107801437378,
+      "learning_rate": 0.0002,
+      "loss": 1.4351,
+      "step": 245
+    },
+    {
+      "epoch": 1.7279029462738302,
+      "grad_norm": 2.647561550140381,
+      "learning_rate": 0.0002,
+      "loss": 1.0698,
+      "step": 250
+    },
+    {
+      "epoch": 1.7625649913344887,
+      "grad_norm": 0.6839751601219177,
+      "learning_rate": 0.0002,
+      "loss": 0.7411,
+      "step": 255
+    },
+    {
+      "epoch": 1.7972270363951472,
+      "grad_norm": 0.4790812134742737,
+      "learning_rate": 0.0002,
+      "loss": 0.5009,
+      "step": 260
+    },
+    {
+      "epoch": 1.831889081455806,
+      "grad_norm": 0.36322328448295593,
+      "learning_rate": 0.0002,
+      "loss": 0.4014,
+      "step": 265
+    },
+    {
+      "epoch": 1.8665511265164645,
+      "grad_norm": 0.31694507598876953,
+      "learning_rate": 0.0002,
+      "loss": 0.3441,
+      "step": 270
+    },
+    {
+      "epoch": 1.901213171577123,
+      "grad_norm": 0.24292677640914917,
+      "learning_rate": 0.0002,
+      "loss": 0.2619,
+      "step": 275
+    },
+    {
+      "epoch": 1.9358752166377817,
+      "grad_norm": 1.133062720298767,
+      "learning_rate": 0.0002,
+      "loss": 1.1564,
+      "step": 280
+    },
+    {
+      "epoch": 1.9705372616984402,
+      "grad_norm": 10.754274368286133,
+      "learning_rate": 0.0002,
+      "loss": 1.436,
+      "step": 285
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.6346553564071655,
+      "learning_rate": 0.0002,
+      "loss": 1.3215,
+      "step": 290
+    },
+    {
+      "epoch": 2.0346620450606587,
+      "grad_norm": 0.7156389355659485,
+      "learning_rate": 0.0002,
+      "loss": 0.551,
+      "step": 295
+    },
+    {
+      "epoch": 2.069324090121317,
+      "grad_norm": 0.3842258155345917,
+      "learning_rate": 0.0002,
+      "loss": 0.3783,
+      "step": 300
+    },
+    {
+      "epoch": 2.1039861351819757,
+      "grad_norm": 0.35967278480529785,
+      "learning_rate": 0.0002,
+      "loss": 0.3124,
+      "step": 305
+    },
+    {
+      "epoch": 2.1386481802426345,
+      "grad_norm": 0.296977162361145,
+      "learning_rate": 0.0002,
+      "loss": 0.2367,
+      "step": 310
+    },
+    {
+      "epoch": 2.1733102253032928,
+      "grad_norm": 1.6834601163864136,
+      "learning_rate": 0.0002,
+      "loss": 0.7685,
+      "step": 315
+    },
+    {
+      "epoch": 2.2079722703639515,
+      "grad_norm": 5.758884906768799,
+      "learning_rate": 0.0002,
+      "loss": 1.0063,
+      "step": 320
+    },
+    {
+      "epoch": 2.2426343154246102,
+      "grad_norm": 15.24948501586914,
+      "learning_rate": 0.0002,
+      "loss": 1.231,
+      "step": 325
+    },
+    {
+      "epoch": 2.2772963604852685,
+      "grad_norm": 0.599730372428894,
+      "learning_rate": 0.0002,
+      "loss": 0.6392,
+      "step": 330
+    },
+    {
+      "epoch": 2.3119584055459272,
+      "grad_norm": 0.5307044982910156,
+      "learning_rate": 0.0002,
+      "loss": 0.3804,
+      "step": 335
+    },
+    {
+      "epoch": 2.346620450606586,
+      "grad_norm": 0.33558061718940735,
+      "learning_rate": 0.0002,
+      "loss": 0.3282,
+      "step": 340
+    },
+    {
+      "epoch": 2.3812824956672443,
+      "grad_norm": 0.2716732919216156,
+      "learning_rate": 0.0002,
+      "loss": 0.2429,
+      "step": 345
+    },
+    {
+      "epoch": 2.415944540727903,
+      "grad_norm": 2.454636812210083,
+      "learning_rate": 0.0002,
+      "loss": 0.5396,
+      "step": 350
+    },
+    {
+      "epoch": 2.4506065857885613,
+      "grad_norm": 13.286089897155762,
+      "learning_rate": 0.0002,
+      "loss": 1.0545,
+      "step": 355
+    },
+    {
+      "epoch": 2.48526863084922,
+      "grad_norm": 12.619502067565918,
+      "learning_rate": 0.0002,
+      "loss": 1.1547,
+      "step": 360
+    },
+    {
+      "epoch": 2.5199306759098787,
+      "grad_norm": 0.6347368359565735,
+      "learning_rate": 0.0002,
+      "loss": 0.7136,
+      "step": 365
+    },
+    {
+      "epoch": 2.554592720970537,
+      "grad_norm": 0.44485101103782654,
+      "learning_rate": 0.0002,
+      "loss": 0.3994,
+      "step": 370
+    },
+    {
+      "epoch": 2.5892547660311958,
+      "grad_norm": 0.36494728922843933,
+      "learning_rate": 0.0002,
+      "loss": 0.3107,
+      "step": 375
+    },
+    {
+      "epoch": 2.6239168110918545,
+      "grad_norm": 0.322171688079834,
+      "learning_rate": 0.0002,
+      "loss": 0.2753,
+      "step": 380
+    },
+    {
+      "epoch": 2.6585788561525128,
+      "grad_norm": 0.9659174084663391,
+      "learning_rate": 0.0002,
+      "loss": 0.2948,
+      "step": 385
+    },
+    {
+      "epoch": 2.6932409012131715,
+      "grad_norm": 0.9371129870414734,
+      "learning_rate": 0.0002,
+      "loss": 1.0286,
+      "step": 390
+    },
+    {
+      "epoch": 2.7279029462738302,
+      "grad_norm": 3.4619617462158203,
+      "learning_rate": 0.0002,
+      "loss": 1.0745,
+      "step": 395
+    },
+    {
+      "epoch": 2.7625649913344885,
+      "grad_norm": 0.6884852051734924,
+      "learning_rate": 0.0002,
+      "loss": 0.7637,
+      "step": 400
+    },
+    {
+      "epoch": 2.7972270363951472,
+      "grad_norm": 0.4440446197986603,
+      "learning_rate": 0.0002,
+      "loss": 0.4331,
+      "step": 405
+    },
+    {
+      "epoch": 2.831889081455806,
+      "grad_norm": 0.37561893463134766,
+      "learning_rate": 0.0002,
+      "loss": 0.3667,
+      "step": 410
+    },
+    {
+      "epoch": 2.8665511265164643,
+      "grad_norm": 0.320077121257782,
+      "learning_rate": 0.0002,
+      "loss": 0.2769,
+      "step": 415
+    },
+    {
+      "epoch": 2.901213171577123,
+      "grad_norm": 1.4914495944976807,
+      "learning_rate": 0.0002,
+      "loss": 0.4493,
+      "step": 420
+    },
+    {
+      "epoch": 2.9358752166377817,
+      "grad_norm": 1.164036750793457,
+      "learning_rate": 0.0002,
+      "loss": 1.1276,
+      "step": 425
+    },
+    {
+      "epoch": 2.97053726169844,
+      "grad_norm": 5.013108253479004,
+      "learning_rate": 0.0002,
+      "loss": 1.0841,
+      "step": 430
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 2.2247564792633057,
+      "learning_rate": 0.0002,
+      "loss": 0.7636,
+      "step": 435
+    },
+    {
+      "epoch": 3.0346620450606587,
+      "grad_norm": 0.3730102479457855,
+      "learning_rate": 0.0002,
+      "loss": 0.4291,
+      "step": 440
+    },
+    {
+      "epoch": 3.069324090121317,
+      "grad_norm": 0.36571791768074036,
+      "learning_rate": 0.0002,
+      "loss": 0.3155,
+      "step": 445
+    },
+    {
+      "epoch": 3.1039861351819757,
+      "grad_norm": 0.34427550435066223,
+      "learning_rate": 0.0002,
+      "loss": 0.2297,
+      "step": 450
+    },
+    {
+      "epoch": 3.1386481802426345,
+      "grad_norm": 0.3725241422653198,
+      "learning_rate": 0.0002,
+      "loss": 0.173,
+      "step": 455
+    },
+    {
+      "epoch": 3.1733102253032928,
+      "grad_norm": 0.9735671877861023,
+      "learning_rate": 0.0002,
+      "loss": 0.8876,
+      "step": 460
+    },
+    {
+      "epoch": 3.2079722703639515,
+      "grad_norm": 3.0348145961761475,
+      "learning_rate": 0.0002,
+      "loss": 0.7825,
+      "step": 465
+    },
+    {
+      "epoch": 3.2426343154246102,
+      "grad_norm": 1.4603136777877808,
+      "learning_rate": 0.0002,
+      "loss": 0.8017,
+      "step": 470
+    },
+    {
+      "epoch": 3.2772963604852685,
+      "grad_norm": 0.6849704384803772,
+      "learning_rate": 0.0002,
+      "loss": 0.6029,
+      "step": 475
+    },
+    {
+      "epoch": 3.3119584055459272,
+      "grad_norm": 0.45950087904930115,
+      "learning_rate": 0.0002,
+      "loss": 0.3388,
+      "step": 480
+    },
+    {
+      "epoch": 3.346620450606586,
+      "grad_norm": 0.3234940469264984,
+      "learning_rate": 0.0002,
+      "loss": 0.2635,
+      "step": 485
+    },
+    {
+      "epoch": 3.3812824956672443,
+      "grad_norm": 0.3088044822216034,
+      "learning_rate": 0.0002,
+      "loss": 0.1867,
+      "step": 490
+    },
+    {
+      "epoch": 3.415944540727903,
+      "grad_norm": 0.36887720227241516,
+      "learning_rate": 0.0002,
+      "loss": 0.1653,
+      "step": 495
+    },
+    {
+      "epoch": 3.4506065857885613,
+      "grad_norm": 1.041858196258545,
+      "learning_rate": 0.0002,
+      "loss": 0.9041,
+      "step": 500
+    },
+    {
+      "epoch": 3.48526863084922,
+      "grad_norm": 1.4774988889694214,
+      "learning_rate": 0.0002,
+      "loss": 0.9789,
+      "step": 505
+    },
+    {
+      "epoch": 3.5199306759098787,
+      "grad_norm": 0.6804758310317993,
+      "learning_rate": 0.0002,
+      "loss": 0.5891,
+      "step": 510
+    },
+    {
+      "epoch": 3.554592720970537,
+      "grad_norm": 0.43344879150390625,
+      "learning_rate": 0.0002,
+      "loss": 0.3632,
+      "step": 515
+    },
+    {
+      "epoch": 3.5892547660311958,
+      "grad_norm": 0.4160469174385071,
+      "learning_rate": 0.0002,
+      "loss": 0.2734,
+      "step": 520
+    },
+    {
+      "epoch": 3.6239168110918545,
+      "grad_norm": 0.35103052854537964,
+      "learning_rate": 0.0002,
+      "loss": 0.2215,
+      "step": 525
+    },
+    {
+      "epoch": 3.6585788561525128,
+      "grad_norm": 1.083409309387207,
+      "learning_rate": 0.0002,
+      "loss": 0.2623,
+      "step": 530
+    },
+    {
+      "epoch": 3.6932409012131715,
+      "grad_norm": 1.2548085451126099,
+      "learning_rate": 0.0002,
+      "loss": 0.9395,
+      "step": 535
+    },
+    {
+      "epoch": 3.7279029462738302,
+      "grad_norm": 2.565399169921875,
+      "learning_rate": 0.0002,
+      "loss": 0.9097,
+      "step": 540
+    },
+    {
+      "epoch": 3.7625649913344885,
+      "grad_norm": 0.6658923625946045,
+      "learning_rate": 0.0002,
+      "loss": 0.739,
+      "step": 545
+    },
+    {
+      "epoch": 3.7972270363951472,
+      "grad_norm": 0.4989807605743408,
+      "learning_rate": 0.0002,
+      "loss": 0.396,
+      "step": 550
+    },
+    {
+      "epoch": 3.831889081455806,
+      "grad_norm": 0.39474496245384216,
+      "learning_rate": 0.0002,
+      "loss": 0.2809,
+      "step": 555
+    },
+    {
+      "epoch": 3.8665511265164643,
+      "grad_norm": 0.38600996136665344,
+      "learning_rate": 0.0002,
+      "loss": 0.2254,
+      "step": 560
+    },
+    {
+      "epoch": 3.901213171577123,
+      "grad_norm": 0.3662823736667633,
+      "learning_rate": 0.0002,
+      "loss": 0.167,
+      "step": 565
+    },
+    {
+      "epoch": 3.9358752166377817,
+      "grad_norm": 1.349672794342041,
+      "learning_rate": 0.0002,
+      "loss": 1.1593,
+      "step": 570
+    },
+    {
+      "epoch": 3.97053726169844,
+      "grad_norm": 2.3923165798187256,
+      "learning_rate": 0.0002,
+      "loss": 0.8778,
+      "step": 575
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.7578555345535278,
+      "learning_rate": 0.0002,
+      "loss": 0.6897,
+      "step": 580
+    },
+    {
+      "epoch": 4.034662045060658,
+      "grad_norm": 0.5052911043167114,
+      "learning_rate": 0.0002,
+      "loss": 0.3913,
+      "step": 585
+    },
+    {
+      "epoch": 4.0693240901213175,
+      "grad_norm": 0.5212499499320984,
+      "learning_rate": 0.0002,
+      "loss": 0.2326,
+      "step": 590
+    },
+    {
+      "epoch": 4.103986135181976,
+      "grad_norm": 0.452105313539505,
+      "learning_rate": 0.0002,
+      "loss": 0.1846,
+      "step": 595
+    },
+    {
+      "epoch": 4.138648180242634,
+      "grad_norm": 0.4193221926689148,
+      "learning_rate": 0.0002,
+      "loss": 0.1359,
+      "step": 600
+    },
+    {
+      "epoch": 4.173310225303293,
+      "grad_norm": 2.3956053256988525,
+      "learning_rate": 0.0002,
+      "loss": 0.3795,
+      "step": 605
+    },
+    {
+      "epoch": 4.2079722703639515,
+      "grad_norm": 1.946535348892212,
+      "learning_rate": 0.0002,
+      "loss": 0.579,
+      "step": 610
+    },
+    {
+      "epoch": 4.24263431542461,
+      "grad_norm": 1.874873161315918,
+      "learning_rate": 0.0002,
+      "loss": 0.7528,
+      "step": 615
+    },
+    {
+      "epoch": 4.277296360485269,
+      "grad_norm": 0.6922146081924438,
+      "learning_rate": 0.0002,
+      "loss": 0.4398,
+      "step": 620
+    },
+    {
+      "epoch": 4.311958405545927,
+      "grad_norm": 0.5228244662284851,
+      "learning_rate": 0.0002,
+      "loss": 0.2615,
+      "step": 625
+    },
+    {
+      "epoch": 4.3466204506065855,
+      "grad_norm": 0.34687915444374084,
+      "learning_rate": 0.0002,
+      "loss": 0.191,
+      "step": 630
+    },
+    {
+      "epoch": 4.381282495667245,
+      "grad_norm": 0.4160069525241852,
+      "learning_rate": 0.0002,
+      "loss": 0.1434,
+      "step": 635
+    },
+    {
+      "epoch": 4.415944540727903,
+      "grad_norm": 1.468666434288025,
+      "learning_rate": 0.0002,
+      "loss": 0.61,
+      "step": 640
+    },
+    {
+      "epoch": 4.450606585788561,
+      "grad_norm": 3.174201488494873,
+      "learning_rate": 0.0002,
+      "loss": 0.5773,
+      "step": 645
+    },
+    {
+      "epoch": 4.4852686308492205,
+      "grad_norm": 1.8258005380630493,
+      "learning_rate": 0.0002,
+      "loss": 0.7495,
+      "step": 650
+    },
+    {
+      "epoch": 4.519930675909879,
+      "grad_norm": 0.8468143343925476,
+      "learning_rate": 0.0002,
+      "loss": 0.5441,
+      "step": 655
+    },
+    {
+      "epoch": 4.554592720970537,
+      "grad_norm": 0.5467656254768372,
+      "learning_rate": 0.0002,
+      "loss": 0.2906,
+      "step": 660
+    },
+    {
+      "epoch": 4.589254766031196,
+      "grad_norm": 0.396992564201355,
+      "learning_rate": 0.0002,
+      "loss": 0.2186,
+      "step": 665
+    },
+    {
+      "epoch": 4.6239168110918545,
+      "grad_norm": 0.31931889057159424,
+      "learning_rate": 0.0002,
+      "loss": 0.1629,
+      "step": 670
+    },
+    {
+      "epoch": 4.658578856152513,
+      "grad_norm": 1.755745530128479,
+      "learning_rate": 0.0002,
+      "loss": 0.2292,
+      "step": 675
+    },
+    {
+      "epoch": 4.693240901213172,
+      "grad_norm": 0.9869062900543213,
+      "learning_rate": 0.0002,
+      "loss": 0.6716,
+      "step": 680
+    },
+    {
+      "epoch": 4.72790294627383,
+      "grad_norm": 1.5987203121185303,
+      "learning_rate": 0.0002,
+      "loss": 0.8182,
+      "step": 685
+    },
+    {
+      "epoch": 4.7625649913344885,
+      "grad_norm": 0.870819091796875,
+      "learning_rate": 0.0002,
+      "loss": 0.5902,
+      "step": 690
+    },
+    {
+      "epoch": 4.797227036395148,
+      "grad_norm": 0.5098839402198792,
+      "learning_rate": 0.0002,
+      "loss": 0.3224,
+      "step": 695
+    },
+    {
+      "epoch": 4.831889081455806,
+      "grad_norm": 0.5435961484909058,
+      "learning_rate": 0.0002,
+      "loss": 0.2182,
+      "step": 700
+    },
+    {
+      "epoch": 4.866551126516464,
+      "grad_norm": 0.33275553584098816,
+      "learning_rate": 0.0002,
+      "loss": 0.1595,
+      "step": 705
+    },
+    {
+      "epoch": 4.9012131715771226,
+      "grad_norm": 1.8109265565872192,
+      "learning_rate": 0.0002,
+      "loss": 0.1985,
+      "step": 710
+    },
+    {
+      "epoch": 4.935875216637782,
+      "grad_norm": 1.149431824684143,
+      "learning_rate": 0.0002,
+      "loss": 0.8148,
+      "step": 715
+    },
+    {
+      "epoch": 4.97053726169844,
+      "grad_norm": 1.4355350732803345,
+      "learning_rate": 0.0002,
+      "loss": 0.6675,
+      "step": 720
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 2.76149845123291,
+      "learning_rate": 0.0002,
+      "loss": 0.5541,
+      "step": 725
+    },
+    {
+      "epoch": 5.034662045060658,
+      "grad_norm": 0.6026546359062195,
+      "learning_rate": 0.0002,
+      "loss": 0.3515,
+      "step": 730
+    },
+    {
+      "epoch": 5.0693240901213175,
+      "grad_norm": 0.37150222063064575,
+      "learning_rate": 0.0002,
+      "loss": 0.1661,
+      "step": 735
+    },
+    {
+      "epoch": 5.103986135181976,
+      "grad_norm": 0.31225013732910156,
+      "learning_rate": 0.0002,
+      "loss": 0.1243,
+      "step": 740
+    },
+    {
+      "epoch": 5.138648180242634,
+      "grad_norm": 0.4382600784301758,
+      "learning_rate": 0.0002,
+      "loss": 0.1004,
+      "step": 745
+    },
+    {
+      "epoch": 5.173310225303293,
+      "grad_norm": 2.0306389331817627,
+      "learning_rate": 0.0002,
+      "loss": 0.3743,
+      "step": 750
+    },
+    {
+      "epoch": 5.2079722703639515,
+      "grad_norm": 1.6935468912124634,
+      "learning_rate": 0.0002,
+      "loss": 0.4202,
+      "step": 755
+    },
+    {
+      "epoch": 5.24263431542461,
+      "grad_norm": 1.4990637302398682,
+      "learning_rate": 0.0002,
+      "loss": 0.5533,
+      "step": 760
+    },
+    {
+      "epoch": 5.277296360485269,
+      "grad_norm": 0.6687419414520264,
+      "learning_rate": 0.0002,
+      "loss": 0.3429,
+      "step": 765
+    },
+    {
+      "epoch": 5.311958405545927,
+      "grad_norm": 0.5400169491767883,
+      "learning_rate": 0.0002,
+      "loss": 0.1759,
+      "step": 770
+    },
+    {
+      "epoch": 5.3466204506065855,
+      "grad_norm": 0.39679139852523804,
+      "learning_rate": 0.0002,
+      "loss": 0.1395,
+      "step": 775
+    },
+    {
+      "epoch": 5.381282495667245,
+      "grad_norm": 0.33043885231018066,
+      "learning_rate": 0.0002,
+      "loss": 0.1004,
+      "step": 780
+    },
+    {
+      "epoch": 5.415944540727903,
+      "grad_norm": 3.1912200450897217,
+      "learning_rate": 0.0002,
+      "loss": 0.305,
+      "step": 785
+    },
+    {
+      "epoch": 5.450606585788561,
+      "grad_norm": 1.2743686437606812,
+      "learning_rate": 0.0002,
+      "loss": 0.4876,
+      "step": 790
+    },
+    {
+      "epoch": 5.4852686308492205,
+      "grad_norm": 2.9798948764801025,
+      "learning_rate": 0.0002,
+      "loss": 0.7476,
+      "step": 795
+    },
+    {
+      "epoch": 5.519930675909879,
+      "grad_norm": 0.7342365384101868,
+      "learning_rate": 0.0002,
+      "loss": 0.463,
+      "step": 800
+    },
+    {
+      "epoch": 5.554592720970537,
+      "grad_norm": 0.5035507678985596,
+      "learning_rate": 0.0002,
+      "loss": 0.2116,
+      "step": 805
+    },
+    {
+      "epoch": 5.589254766031196,
+      "grad_norm": 0.4394471347332001,
+      "learning_rate": 0.0002,
+      "loss": 0.1568,
+      "step": 810
+    },
+    {
+      "epoch": 5.6239168110918545,
+      "grad_norm": 0.383515328168869,
+      "learning_rate": 0.0002,
+      "loss": 0.1035,
+      "step": 815
+    },
+    {
+      "epoch": 5.658578856152513,
+      "grad_norm": 2.142784357070923,
+      "learning_rate": 0.0002,
+      "loss": 0.3458,
+      "step": 820
+    },
+    {
+      "epoch": 5.693240901213172,
+      "grad_norm": 1.2484018802642822,
+      "learning_rate": 0.0002,
+      "loss": 0.3576,
+      "step": 825
+    },
+    {
+      "epoch": 5.72790294627383,
+      "grad_norm": 2.6863198280334473,
+      "learning_rate": 0.0002,
+      "loss": 0.5996,
+      "step": 830
+    },
+    {
+      "epoch": 5.7625649913344885,
+      "grad_norm": 1.098381757736206,
+      "learning_rate": 0.0002,
+      "loss": 0.4993,
+      "step": 835
+    },
+    {
+      "epoch": 5.797227036395148,
+      "grad_norm": 0.5609210133552551,
+      "learning_rate": 0.0002,
+      "loss": 0.2608,
+      "step": 840
+    },
+    {
+      "epoch": 5.831889081455806,
+      "grad_norm": 0.5123816132545471,
+      "learning_rate": 0.0002,
+      "loss": 0.1799,
+      "step": 845
+    },
+    {
+      "epoch": 5.866551126516464,
+      "grad_norm": 0.46399134397506714,
+      "learning_rate": 0.0002,
+      "loss": 0.1254,
+      "step": 850
+    },
+    {
+      "epoch": 5.9012131715771226,
+      "grad_norm": 0.5089249014854431,
+      "learning_rate": 0.0002,
+      "loss": 0.0934,
+      "step": 855
+    },
+    {
+      "epoch": 5.935875216637782,
+      "grad_norm": 1.3031930923461914,
+      "learning_rate": 0.0002,
+      "loss": 0.6664,
+      "step": 860
+    },
+    {
+      "epoch": 5.97053726169844,
+      "grad_norm": 2.294696569442749,
+      "learning_rate": 0.0002,
+      "loss": 0.6034,
+      "step": 865
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 2.738062620162964,
+      "learning_rate": 0.0002,
+      "loss": 0.587,
+      "step": 870
+    },
+    {
+      "epoch": 6.034662045060658,
+      "grad_norm": 0.6086808443069458,
+      "learning_rate": 0.0002,
+      "loss": 0.252,
+      "step": 875
+    },
+    {
+      "epoch": 6.0693240901213175,
+      "grad_norm": 0.4935630261898041,
+      "learning_rate": 0.0002,
+      "loss": 0.1223,
+      "step": 880
+    },
+    {
+      "epoch": 6.103986135181976,
+      "grad_norm": 0.43656599521636963,
+      "learning_rate": 0.0002,
+      "loss": 0.0882,
+      "step": 885
+    },
+    {
+      "epoch": 6.138648180242634,
+      "grad_norm": 0.2987945079803467,
+      "learning_rate": 0.0002,
+      "loss": 0.0629,
+      "step": 890
+    },
+    {
+      "epoch": 6.173310225303293,
+      "grad_norm": 1.7174897193908691,
+      "learning_rate": 0.0002,
+      "loss": 0.4102,
+      "step": 895
+    },
+    {
+      "epoch": 6.2079722703639515,
+      "grad_norm": 2.4946401119232178,
+      "learning_rate": 0.0002,
+      "loss": 0.2899,
+      "step": 900
+    },
+    {
+      "epoch": 6.24263431542461,
+      "grad_norm": 2.8931374549865723,
+      "learning_rate": 0.0002,
+      "loss": 0.4676,
+      "step": 905
+    },
+    {
+      "epoch": 6.277296360485269,
+      "grad_norm": 0.8096083998680115,
+      "learning_rate": 0.0002,
+      "loss": 0.3168,
+      "step": 910
+    },
+    {
+      "epoch": 6.311958405545927,
+      "grad_norm": 0.4966631531715393,
+      "learning_rate": 0.0002,
+      "loss": 0.1399,
+      "step": 915
+    },
+    {
+      "epoch": 6.3466204506065855,
+      "grad_norm": 0.46740466356277466,
+      "learning_rate": 0.0002,
+      "loss": 0.1037,
+      "step": 920
+    },
+    {
+      "epoch": 6.381282495667245,
+      "grad_norm": 0.3550221920013428,
+      "learning_rate": 0.0002,
+      "loss": 0.0682,
+      "step": 925
+    },
+    {
+      "epoch": 6.415944540727903,
+      "grad_norm": 1.7010166645050049,
+      "learning_rate": 0.0002,
+      "loss": 0.401,
+      "step": 930
+    },
+    {
+      "epoch": 6.450606585788561,
+      "grad_norm": 1.4712696075439453,
+      "learning_rate": 0.0002,
+      "loss": 0.2843,
+      "step": 935
+    },
+    {
+      "epoch": 6.4852686308492205,
+      "grad_norm": 1.702062964439392,
+      "learning_rate": 0.0002,
+      "loss": 0.5166,
+      "step": 940
+    },
+    {
+      "epoch": 6.519930675909879,
+      "grad_norm": 0.6730090379714966,
+      "learning_rate": 0.0002,
+      "loss": 0.3467,
+      "step": 945
+    },
+    {
+      "epoch": 6.554592720970537,
+      "grad_norm": 0.6367856860160828,
+      "learning_rate": 0.0002,
+      "loss": 0.1564,
+      "step": 950
+    },
+    {
+      "epoch": 6.589254766031196,
+      "grad_norm": 0.5671469569206238,
+      "learning_rate": 0.0002,
+      "loss": 0.1267,
+      "step": 955
+    },
+    {
+      "epoch": 6.6239168110918545,
+      "grad_norm": 0.29594796895980835,
+      "learning_rate": 0.0002,
+      "loss": 0.0927,
+      "step": 960
+    },
+    {
+      "epoch": 6.658578856152513,
+      "grad_norm": 0.6945505738258362,
+      "learning_rate": 0.0002,
+      "loss": 0.0982,
+      "step": 965
+    },
+    {
+      "epoch": 6.693240901213172,
+      "grad_norm": 1.2007991075515747,
+      "learning_rate": 0.0002,
+      "loss": 0.4829,
+      "step": 970
+    },
+    {
+      "epoch": 6.72790294627383,
+      "grad_norm": 4.258643627166748,
+      "learning_rate": 0.0002,
+      "loss": 0.5014,
+      "step": 975
+    },
+    {
+      "epoch": 6.7625649913344885,
+      "grad_norm": 1.2368519306182861,
+      "learning_rate": 0.0002,
+      "loss": 0.4639,
+      "step": 980
+    },
+    {
+      "epoch": 6.797227036395148,
+      "grad_norm": 0.5854914784431458,
+      "learning_rate": 0.0002,
+      "loss": 0.1885,
+      "step": 985
+    },
+    {
+      "epoch": 6.831889081455806,
+      "grad_norm": 0.433727890253067,
+      "learning_rate": 0.0002,
+      "loss": 0.1182,
+      "step": 990
+    },
+    {
+      "epoch": 6.866551126516464,
+      "grad_norm": 0.37968766689300537,
+      "learning_rate": 0.0002,
+      "loss": 0.0907,
+      "step": 995
+    },
+    {
+      "epoch": 6.9012131715771226,
+      "grad_norm": 0.49255871772766113,
+      "learning_rate": 0.0002,
+      "loss": 0.0748,
+      "step": 1000
+    },
+    {
+      "epoch": 6.935875216637782,
+      "grad_norm": 0.8562117218971252,
+      "learning_rate": 0.0002,
+      "loss": 0.301,
+      "step": 1005
+    },
+    {
+      "epoch": 6.97053726169844,
+      "grad_norm": 2.18452787399292,
+      "learning_rate": 0.0002,
+      "loss": 0.5265,
+      "step": 1010
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 5.248262405395508,
+      "learning_rate": 0.0002,
+      "loss": 0.4677,
+      "step": 1015
+    },
+    {
+      "epoch": 7.034662045060658,
+      "grad_norm": 0.6046018600463867,
+      "learning_rate": 0.0002,
+      "loss": 0.1937,
+      "step": 1020
+    },
+    {
+      "epoch": 7.0693240901213175,
+      "grad_norm": 0.4035234749317169,
+      "learning_rate": 0.0002,
+      "loss": 0.0889,
+      "step": 1025
+    },
+    {
+      "epoch": 7.103986135181976,
+      "grad_norm": 0.41130027174949646,
+      "learning_rate": 0.0002,
+      "loss": 0.0768,
+      "step": 1030
+    },
+    {
+      "epoch": 7.138648180242634,
+      "grad_norm": 0.43616095185279846,
+      "learning_rate": 0.0002,
+      "loss": 0.062,
+      "step": 1035
+    },
+    {
+      "epoch": 7.173310225303293,
+      "grad_norm": 1.4820456504821777,
+      "learning_rate": 0.0002,
+      "loss": 0.2592,
+      "step": 1040
+    },
+    {
+      "epoch": 7.2079722703639515,
+      "grad_norm": 2.2512240409851074,
+      "learning_rate": 0.0002,
+      "loss": 0.2771,
+      "step": 1045
+    },
+    {
+      "epoch": 7.24263431542461,
+      "grad_norm": 1.473806619644165,
+      "learning_rate": 0.0002,
+      "loss": 0.3877,
+      "step": 1050
+    },
+    {
+      "epoch": 7.277296360485269,
+      "grad_norm": 0.7703912258148193,
+      "learning_rate": 0.0002,
+      "loss": 0.2664,
+      "step": 1055
+    },
+    {
+      "epoch": 7.311958405545927,
+      "grad_norm": 0.5043675303459167,
+      "learning_rate": 0.0002,
+      "loss": 0.1109,
+      "step": 1060
+    },
+    {
+      "epoch": 7.3466204506065855,
+      "grad_norm": 0.43726152181625366,
+      "learning_rate": 0.0002,
+      "loss": 0.0839,
+      "step": 1065
+    },
+    {
+      "epoch": 7.381282495667245,
+      "grad_norm": 0.4088805615901947,
+      "learning_rate": 0.0002,
+      "loss": 0.0627,
+      "step": 1070
+    },
+    {
+      "epoch": 7.415944540727903,
+      "grad_norm": 2.5372557640075684,
+      "learning_rate": 0.0002,
+      "loss": 0.1959,
+      "step": 1075
+    },
+    {
+      "epoch": 7.450606585788561,
+      "grad_norm": 2.1121976375579834,
+      "learning_rate": 0.0002,
+      "loss": 0.3118,
+      "step": 1080
+    },
+    {
+      "epoch": 7.4852686308492205,
+      "grad_norm": 2.125603199005127,
+      "learning_rate": 0.0002,
+      "loss": 0.565,
+      "step": 1085
+    },
+    {
+      "epoch": 7.519930675909879,
+      "grad_norm": 0.8563218116760254,
+      "learning_rate": 0.0002,
+      "loss": 0.4099,
+      "step": 1090
+    },
+    {
+      "epoch": 7.554592720970537,
+      "grad_norm": 0.4825403392314911,
+      "learning_rate": 0.0002,
+      "loss": 0.1419,
+      "step": 1095
+    },
+    {
+      "epoch": 7.589254766031196,
+      "grad_norm": 0.4735303521156311,
+      "learning_rate": 0.0002,
+      "loss": 0.09,
+      "step": 1100
+    },
+    {
+      "epoch": 7.6239168110918545,
+      "grad_norm": 0.24926654994487762,
+      "learning_rate": 0.0002,
+      "loss": 0.0699,
+      "step": 1105
+    },
+    {
+      "epoch": 7.658578856152513,
+      "grad_norm": 0.2843971252441406,
+      "learning_rate": 0.0002,
+      "loss": 0.0602,
+      "step": 1110
+    },
+    {
+      "epoch": 7.693240901213172,
+      "grad_norm": 0.9436930418014526,
+      "learning_rate": 0.0002,
+      "loss": 0.3591,
+      "step": 1115
+    },
+    {
+      "epoch": 7.72790294627383,
+      "grad_norm": 1.8918225765228271,
+      "learning_rate": 0.0002,
+      "loss": 0.4049,
+      "step": 1120
+    },
+    {
+      "epoch": 7.7625649913344885,
+      "grad_norm": 1.1229664087295532,
+      "learning_rate": 0.0002,
+      "loss": 0.4094,
+      "step": 1125
+    },
+    {
+      "epoch": 7.797227036395148,
+      "grad_norm": 0.6665800213813782,
+      "learning_rate": 0.0002,
+      "loss": 0.1265,
+      "step": 1130
+    },
+    {
+      "epoch": 7.831889081455806,
+      "grad_norm": 0.38160014152526855,
+      "learning_rate": 0.0002,
+      "loss": 0.0895,
+      "step": 1135
+    },
+    {
+      "epoch": 7.866551126516464,
+      "grad_norm": 0.5825662612915039,
+      "learning_rate": 0.0002,
+      "loss": 0.0637,
+      "step": 1140
+    },
+    {
+      "epoch": 7.9012131715771226,
+      "grad_norm": 2.218074321746826,
+      "learning_rate": 0.0002,
+      "loss": 0.22,
+      "step": 1145
+    },
+    {
+      "epoch": 7.935875216637782,
+      "grad_norm": 1.0831362009048462,
+      "learning_rate": 0.0002,
+      "loss": 0.3117,
+      "step": 1150
+    },
+    {
+      "epoch": 7.97053726169844,
+      "grad_norm": 1.6957491636276245,
+      "learning_rate": 0.0002,
+      "loss": 0.3566,
+      "step": 1155
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 6.261979103088379,
+      "learning_rate": 0.0002,
+      "loss": 0.4143,
+      "step": 1160
+    },
+    {
+      "epoch": 8.090121317157712,
+      "grad_norm": 0.3784933388233185,
+      "learning_rate": 0.0002,
+      "loss": 0.0921,
+      "step": 1165
+    },
+    {
+      "epoch": 8.124783362218372,
+      "grad_norm": 0.5006704330444336,
+      "learning_rate": 0.0002,
+      "loss": 0.0649,
+      "step": 1170
+    },
+    {
+      "epoch": 8.15944540727903,
+      "grad_norm": 1.7417300939559937,
+      "learning_rate": 0.0002,
+      "loss": 0.1036,
+      "step": 1175
+    },
+    {
+      "epoch": 8.194107452339688,
+      "grad_norm": 0.5341992974281311,
+      "learning_rate": 0.0002,
+      "loss": 0.2169,
+      "step": 1180
+    },
+    {
+      "epoch": 8.228769497400346,
+      "grad_norm": 1.425203800201416,
+      "learning_rate": 0.0002,
+      "loss": 0.3661,
+      "step": 1185
+    },
+    {
+      "epoch": 8.263431542461005,
+      "grad_norm": 0.8877242803573608,
+      "learning_rate": 0.0002,
+      "loss": 0.3186,
+      "step": 1190
+    },
+    {
+      "epoch": 8.298093587521663,
+      "grad_norm": 0.5418034195899963,
+      "learning_rate": 0.0002,
+      "loss": 0.1068,
+      "step": 1195
+    },
+    {
+      "epoch": 8.332755632582323,
+      "grad_norm": 0.44961827993392944,
+      "learning_rate": 0.0002,
+      "loss": 0.0702,
+      "step": 1200
+    },
+    {
+      "epoch": 8.367417677642981,
+      "grad_norm": 0.38408568501472473,
+      "learning_rate": 0.0002,
+      "loss": 0.0578,
+      "step": 1205
+    },
+    {
+      "epoch": 8.40207972270364,
+      "grad_norm": 0.28024882078170776,
+      "learning_rate": 0.0002,
+      "loss": 0.0554,
+      "step": 1210
+    },
+    {
+      "epoch": 8.436741767764298,
+      "grad_norm": 1.7511780261993408,
+      "learning_rate": 0.0002,
+      "loss": 0.266,
+      "step": 1215
+    },
+    {
+      "epoch": 8.471403812824956,
+      "grad_norm": 2.1751325130462646,
+      "learning_rate": 0.0002,
+      "loss": 0.361,
+      "step": 1220
+    },
+    {
+      "epoch": 8.506065857885615,
+      "grad_norm": 1.0328117609024048,
+      "learning_rate": 0.0002,
+      "loss": 0.3873,
+      "step": 1225
+    },
+    {
+      "epoch": 8.540727902946275,
+      "grad_norm": 0.4595634937286377,
+      "learning_rate": 0.0002,
+      "loss": 0.1175,
+      "step": 1230
+    },
+    {
+      "epoch": 8.575389948006933,
+      "grad_norm": 0.36790379881858826,
+      "learning_rate": 0.0002,
+      "loss": 0.0759,
+      "step": 1235
+    },
+    {
+      "epoch": 8.610051993067591,
+      "grad_norm": 0.3406282663345337,
+      "learning_rate": 0.0002,
+      "loss": 0.0655,
+      "step": 1240
+    },
+    {
+      "epoch": 8.64471403812825,
+      "grad_norm": 0.312312513589859,
+      "learning_rate": 0.0002,
+      "loss": 0.0564,
+      "step": 1245
+    },
+    {
+      "epoch": 8.679376083188908,
+      "grad_norm": 0.9704126119613647,
+      "learning_rate": 0.0002,
+      "loss": 0.2244,
+      "step": 1250
+    },
+    {
+      "epoch": 8.714038128249566,
+      "grad_norm": 2.1745662689208984,
+      "learning_rate": 0.0002,
+      "loss": 0.269,
+      "step": 1255
+    },
+    {
+      "epoch": 8.748700173310226,
+      "grad_norm": 2.6419990062713623,
+      "learning_rate": 0.0002,
+      "loss": 0.4,
+      "step": 1260
+    },
+    {
+      "epoch": 8.783362218370884,
+      "grad_norm": 0.6658149361610413,
+      "learning_rate": 0.0002,
+      "loss": 0.1695,
+      "step": 1265
+    },
+    {
+      "epoch": 8.818024263431543,
+      "grad_norm": 0.420835942029953,
+      "learning_rate": 0.0002,
+      "loss": 0.087,
+      "step": 1270
+    },
+    {
+      "epoch": 8.852686308492201,
+      "grad_norm": 0.40058913826942444,
+      "learning_rate": 0.0002,
+      "loss": 0.0663,
+      "step": 1275
+    },
+    {
+      "epoch": 8.88734835355286,
+      "grad_norm": 0.3358669579029083,
+      "learning_rate": 0.0002,
+      "loss": 0.0572,
+      "step": 1280
+    },
+    {
+      "epoch": 8.922010398613518,
+      "grad_norm": 2.614215850830078,
+      "learning_rate": 0.0002,
+      "loss": 0.306,
+      "step": 1285
+    },
+    {
+      "epoch": 8.956672443674178,
+      "grad_norm": 2.6841623783111572,
+      "learning_rate": 0.0002,
+      "loss": 0.2573,
+      "step": 1290
+    },
+    {
+      "epoch": 8.991334488734836,
+      "grad_norm": 8.573723793029785,
+      "learning_rate": 0.0002,
+      "loss": 0.4228,
+      "step": 1295
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 1440,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3.0145023652552704e+16,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1296/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2877d9d0c39629ade070fa861730d5845f15b3b234922c043c4a491dd528a21c
+size 5624

checkpoint-1440/README.md

@@ -0,0 +1,202 @@
+---
+base_model: microsoft/Phi-4-mini-instruct
+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 0.15.2

checkpoint-1440/adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "microsoft/Phi-4-mini-instruct",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "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_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "k_proj",
+    "down_proj",
+    "v_proj",
+    "gate_proj",
+    "q_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-1440/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4cc441c40942232c13b927eed9af87f322fd1200bc9f0d752c896154de091dfc
+size 35668592