Upload folder using huggingface_hub

lora_model/adapter_config.json

@@ -15,7 +15,7 @@
   "loftq_config": {},
   "lora_alpha": 16,
   "lora_bias": false,
-  "lora_dropout": 0,
+  "lora_dropout": 0.05,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
@@ -25,13 +25,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
-    "k_proj",
+    "down_proj",
     "o_proj",
-    "gate_proj",
     "up_proj",
+    "q_proj",
+    "k_proj",
     "v_proj",
-    "down_proj"
+    "gate_proj"
   ],
   "task_type": "CAUSAL_LM",
   "trainable_token_indices": null,

lora_model/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:56bddf678ba845612458f34c6ca85ce2a6f8397b743474b982faaf6158e3a65a
+oid sha256:090722b72662baa380df4b248e961887a300e28f0b670bf9da9f694b6a49591f
 size 262219392

outputs/README.md

@@ -4,9 +4,9 @@ library_name: transformers
 model_name: outputs
 tags:
 - generated_from_trainer
-- trl
-- sft
 - unsloth
+- sft
+- trl
 licence: license
 ---
 

outputs/checkpoint-234/README.md

@@ -0,0 +1,210 @@
+---
+base_model: unsloth/phi-4-unsloth-bnb-4bit
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:unsloth/phi-4-unsloth-bnb-4bit
+- lora
+- sft
+- transformers
+- trl
+- unsloth
+---
+
+# 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 0.16.0

outputs/checkpoint-234/adapter_config.json

@@ -0,0 +1,41 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "unsloth/phi-4-unsloth-bnb-4bit",
+  "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": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "o_proj",
+    "up_proj",
+    "q_proj",
+    "k_proj",
+    "v_proj",
+    "gate_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

outputs/checkpoint-234/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:090722b72662baa380df4b248e961887a300e28f0b670bf9da9f694b6a49591f
+size 262219392

outputs/checkpoint-234/chat_template.jinja

@@ -0,0 +1 @@
+{% for message in messages %}{% if (message['role'] == 'system') %}{{'<|im_start|>system<|im_sep|>' + message['content'] + '<|im_end|>'}}{% elif (message['role'] == 'user') %}{{'<|im_start|>user<|im_sep|>' + message['content'] + '<|im_end|>'}}{% elif (message['role'] == 'assistant') %}{{'<|im_start|>assistant<|im_sep|>' + message['content'] + '<|im_end|>'}}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant<|im_sep|>' }}{% endif %}

outputs/checkpoint-234/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1bb74bb20e05bdd4bdc4bc430861fe195ccd025114218f489ae23e95cac2892d
+size 133777940

outputs/checkpoint-234/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52d65d45896c35326a39d3517462d70c6fce1e0d3f9dd11c09e645d193d17ecb
+size 14244

outputs/checkpoint-234/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0ede7b1423721cae7c5a3bccce2b3f83abcf842665a4c5b368aefc719a462de
+size 1064

outputs/checkpoint-234/special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": true,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": true,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|dummy_87|>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": true,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "�",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

outputs/checkpoint-234/tokenizer_config.json

@@ -0,0 +1,790 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "5809": {
+      "content": "�",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100256": {
+      "content": "<|dummy_0|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100257": {
+      "content": "<|endoftext|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100258": {
+      "content": "<|fim_prefix|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100259": {
+      "content": "<|fim_middle|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100260": {
+      "content": "<|fim_suffix|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100261": {
+      "content": "<|dummy_1|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100262": {
+      "content": "<|dummy_2|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100263": {
+      "content": "<|dummy_3|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100264": {
+      "content": "<|im_start|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100265": {
+      "content": "<|im_end|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100266": {
+      "content": "<|im_sep|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100267": {
+      "content": "<|dummy_4|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100268": {
+      "content": "<|dummy_5|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100269": {
+      "content": "<|dummy_6|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100270": {
+      "content": "<|dummy_7|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100271": {
+      "content": "<|dummy_8|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100272": {
+      "content": "<|dummy_9|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100273": {
+      "content": "<|dummy_10|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100274": {
+      "content": "<|dummy_11|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100275": {
+      "content": "<|dummy_12|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100276": {
+      "content": "<|endofprompt|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100277": {
+      "content": "<|dummy_13|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100278": {
+      "content": "<|dummy_14|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100279": {
+      "content": "<|dummy_15|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100280": {
+      "content": "<|dummy_16|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100281": {
+      "content": "<|dummy_17|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100282": {
+      "content": "<|dummy_18|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100283": {
+      "content": "<|dummy_19|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100284": {
+      "content": "<|dummy_20|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100285": {
+      "content": "<|dummy_21|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100286": {
+      "content": "<|dummy_22|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100287": {
+      "content": "<|dummy_23|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100288": {
+      "content": "<|dummy_24|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100289": {
+      "content": "<|dummy_25|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100290": {
+      "content": "<|dummy_26|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100291": {
+      "content": "<|dummy_27|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100292": {
+      "content": "<|dummy_28|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100293": {
+      "content": "<|dummy_29|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100294": {
+      "content": "<|dummy_30|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100295": {
+      "content": "<|dummy_31|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100296": {
+      "content": "<|dummy_32|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100297": {
+      "content": "<|dummy_33|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100298": {
+      "content": "<|dummy_34|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100299": {
+      "content": "<|dummy_35|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100300": {
+      "content": "<|dummy_36|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100301": {
+      "content": "<|dummy_37|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100302": {
+      "content": "<|dummy_38|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100303": {
+      "content": "<|dummy_39|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100304": {
+      "content": "<|dummy_40|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100305": {
+      "content": "<|dummy_41|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100306": {
+      "content": "<|dummy_42|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100307": {
+      "content": "<|dummy_43|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100308": {
+      "content": "<|dummy_44|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100309": {
+      "content": "<|dummy_45|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100310": {
+      "content": "<|dummy_46|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100311": {
+      "content": "<|dummy_47|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100312": {
+      "content": "<|dummy_48|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100313": {
+      "content": "<|dummy_49|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100314": {
+      "content": "<|dummy_50|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100315": {
+      "content": "<|dummy_51|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100316": {
+      "content": "<|dummy_52|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100317": {
+      "content": "<|dummy_53|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100318": {
+      "content": "<|dummy_54|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100319": {
+      "content": "<|dummy_55|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100320": {
+      "content": "<|dummy_56|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100321": {
+      "content": "<|dummy_57|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100322": {
+      "content": "<|dummy_58|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100323": {
+      "content": "<|dummy_59|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100324": {
+      "content": "<|dummy_60|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100325": {
+      "content": "<|dummy_61|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100326": {
+      "content": "<|dummy_62|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100327": {
+      "content": "<|dummy_63|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100328": {
+      "content": "<|dummy_64|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100329": {
+      "content": "<|dummy_65|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100330": {
+      "content": "<|dummy_66|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100331": {
+      "content": "<|dummy_67|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100332": {
+      "content": "<|dummy_68|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100333": {
+      "content": "<|dummy_69|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100334": {
+      "content": "<|dummy_70|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100335": {
+      "content": "<|dummy_71|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100336": {
+      "content": "<|dummy_72|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100337": {
+      "content": "<|dummy_73|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100338": {
+      "content": "<|dummy_74|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100339": {
+      "content": "<|dummy_75|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100340": {
+      "content": "<|dummy_76|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100341": {
+      "content": "<|dummy_77|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100342": {
+      "content": "<|dummy_78|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100343": {
+      "content": "<|dummy_79|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100344": {
+      "content": "<|dummy_80|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100345": {
+      "content": "<|dummy_81|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100346": {
+      "content": "<|dummy_82|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100347": {
+      "content": "<|dummy_83|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100348": {
+      "content": "<|dummy_84|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100349": {
+      "content": "<|dummy_85|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100350": {
+      "content": "<|dummy_86|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100351": {
+      "content": "<|dummy_87|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "extra_special_tokens": {},
+  "model_max_length": 16384,
+  "pad_token": "<|dummy_87|>",
+  "padding_side": "right",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "�"
+}

outputs/checkpoint-234/trainer_state.json

@@ -0,0 +1,1672 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 234,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.012903225806451613,
+      "grad_norm": 2.793485164642334,
+      "learning_rate": 0.0,
+      "loss": 0.7187,
+      "step": 1
+    },
+    {
+      "epoch": 0.025806451612903226,
+      "grad_norm": 4.024425983428955,
+      "learning_rate": 6.666666666666667e-05,
+      "loss": 1.5016,
+      "step": 2
+    },
+    {
+      "epoch": 0.03870967741935484,
+      "grad_norm": 2.2235827445983887,
+      "learning_rate": 0.00013333333333333334,
+      "loss": 0.8721,
+      "step": 3
+    },
+    {
+      "epoch": 0.05161290322580645,
+      "grad_norm": 1.6403107643127441,
+      "learning_rate": 0.0002,
+      "loss": 0.7268,
+      "step": 4
+    },
+    {
+      "epoch": 0.06451612903225806,
+      "grad_norm": 1.0975494384765625,
+      "learning_rate": 0.00019913419913419916,
+      "loss": 0.8342,
+      "step": 5
+    },
+    {
+      "epoch": 0.07741935483870968,
+      "grad_norm": 0.6378797292709351,
+      "learning_rate": 0.00019826839826839827,
+      "loss": 0.7296,
+      "step": 6
+    },
+    {
+      "epoch": 0.09032258064516129,
+      "grad_norm": 0.6447148323059082,
+      "learning_rate": 0.00019740259740259742,
+      "loss": 0.4854,
+      "step": 7
+    },
+    {
+      "epoch": 0.1032258064516129,
+      "grad_norm": 0.7005094885826111,
+      "learning_rate": 0.00019653679653679654,
+      "loss": 0.5046,
+      "step": 8
+    },
+    {
+      "epoch": 0.11612903225806452,
+      "grad_norm": 0.5454447269439697,
+      "learning_rate": 0.00019567099567099566,
+      "loss": 0.6874,
+      "step": 9
+    },
+    {
+      "epoch": 0.12903225806451613,
+      "grad_norm": 0.4927928149700165,
+      "learning_rate": 0.0001948051948051948,
+      "loss": 0.6352,
+      "step": 10
+    },
+    {
+      "epoch": 0.14193548387096774,
+      "grad_norm": 0.4271396994590759,
+      "learning_rate": 0.00019393939393939395,
+      "loss": 0.4966,
+      "step": 11
+    },
+    {
+      "epoch": 0.15483870967741936,
+      "grad_norm": 0.5025472044944763,
+      "learning_rate": 0.00019307359307359307,
+      "loss": 0.6799,
+      "step": 12
+    },
+    {
+      "epoch": 0.16774193548387098,
+      "grad_norm": 0.44721734523773193,
+      "learning_rate": 0.00019220779220779222,
+      "loss": 0.5222,
+      "step": 13
+    },
+    {
+      "epoch": 0.18064516129032257,
+      "grad_norm": 0.6115127205848694,
+      "learning_rate": 0.00019134199134199136,
+      "loss": 0.5898,
+      "step": 14
+    },
+    {
+      "epoch": 0.1935483870967742,
+      "grad_norm": 0.5611880421638489,
+      "learning_rate": 0.00019047619047619048,
+      "loss": 0.5321,
+      "step": 15
+    },
+    {
+      "epoch": 0.2064516129032258,
+      "grad_norm": 0.5329087972640991,
+      "learning_rate": 0.00018961038961038963,
+      "loss": 0.4671,
+      "step": 16
+    },
+    {
+      "epoch": 0.21935483870967742,
+      "grad_norm": 0.5033156871795654,
+      "learning_rate": 0.00018874458874458875,
+      "loss": 0.3578,
+      "step": 17
+    },
+    {
+      "epoch": 0.23225806451612904,
+      "grad_norm": 0.5309613943099976,
+      "learning_rate": 0.0001878787878787879,
+      "loss": 0.4625,
+      "step": 18
+    },
+    {
+      "epoch": 0.24516129032258063,
+      "grad_norm": 0.48208287358283997,
+      "learning_rate": 0.000187012987012987,
+      "loss": 0.3629,
+      "step": 19
+    },
+    {
+      "epoch": 0.25806451612903225,
+      "grad_norm": 0.8097040057182312,
+      "learning_rate": 0.00018614718614718616,
+      "loss": 0.7498,
+      "step": 20
+    },
+    {
+      "epoch": 0.2709677419354839,
+      "grad_norm": 0.7283074259757996,
+      "learning_rate": 0.0001852813852813853,
+      "loss": 0.6304,
+      "step": 21
+    },
+    {
+      "epoch": 0.2838709677419355,
+      "grad_norm": 0.6570721864700317,
+      "learning_rate": 0.00018441558441558442,
+      "loss": 0.5135,
+      "step": 22
+    },
+    {
+      "epoch": 0.2967741935483871,
+      "grad_norm": 0.5550969839096069,
+      "learning_rate": 0.00018354978354978357,
+      "loss": 0.494,
+      "step": 23
+    },
+    {
+      "epoch": 0.3096774193548387,
+      "grad_norm": 0.5073785781860352,
+      "learning_rate": 0.00018268398268398272,
+      "loss": 0.4362,
+      "step": 24
+    },
+    {
+      "epoch": 0.3225806451612903,
+      "grad_norm": 0.5898240208625793,
+      "learning_rate": 0.00018181818181818183,
+      "loss": 0.5772,
+      "step": 25
+    },
+    {
+      "epoch": 0.33548387096774196,
+      "grad_norm": 0.6110000610351562,
+      "learning_rate": 0.00018095238095238095,
+      "loss": 0.4122,
+      "step": 26
+    },
+    {
+      "epoch": 0.34838709677419355,
+      "grad_norm": 0.45508354902267456,
+      "learning_rate": 0.0001800865800865801,
+      "loss": 0.4488,
+      "step": 27
+    },
+    {
+      "epoch": 0.36129032258064514,
+      "grad_norm": 0.5008929967880249,
+      "learning_rate": 0.00017922077922077922,
+      "loss": 0.2138,
+      "step": 28
+    },
+    {
+      "epoch": 0.3741935483870968,
+      "grad_norm": 0.4376208484172821,
+      "learning_rate": 0.00017835497835497836,
+      "loss": 0.3489,
+      "step": 29
+    },
+    {
+      "epoch": 0.3870967741935484,
+      "grad_norm": 0.49918413162231445,
+      "learning_rate": 0.0001774891774891775,
+      "loss": 0.2516,
+      "step": 30
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.8587069511413574,
+      "learning_rate": 0.00017662337662337663,
+      "loss": 0.5475,
+      "step": 31
+    },
+    {
+      "epoch": 0.4129032258064516,
+      "grad_norm": 0.5014280676841736,
+      "learning_rate": 0.00017575757575757578,
+      "loss": 0.414,
+      "step": 32
+    },
+    {
+      "epoch": 0.4258064516129032,
+      "grad_norm": 0.5355783700942993,
+      "learning_rate": 0.0001748917748917749,
+      "loss": 0.3855,
+      "step": 33
+    },
+    {
+      "epoch": 0.43870967741935485,
+      "grad_norm": 0.6740708351135254,
+      "learning_rate": 0.00017402597402597401,
+      "loss": 0.5328,
+      "step": 34
+    },
+    {
+      "epoch": 0.45161290322580644,
+      "grad_norm": 0.7475488781929016,
+      "learning_rate": 0.00017316017316017316,
+      "loss": 0.4002,
+      "step": 35
+    },
+    {
+      "epoch": 0.4645161290322581,
+      "grad_norm": 0.7730025053024292,
+      "learning_rate": 0.0001722943722943723,
+      "loss": 0.4861,
+      "step": 36
+    },
+    {
+      "epoch": 0.4774193548387097,
+      "grad_norm": 0.6816443204879761,
+      "learning_rate": 0.00017142857142857143,
+      "loss": 0.5896,
+      "step": 37
+    },
+    {
+      "epoch": 0.49032258064516127,
+      "grad_norm": 0.546295166015625,
+      "learning_rate": 0.00017056277056277057,
+      "loss": 0.5281,
+      "step": 38
+    },
+    {
+      "epoch": 0.5032258064516129,
+      "grad_norm": 0.5791237950325012,
+      "learning_rate": 0.00016969696969696972,
+      "loss": 0.2921,
+      "step": 39
+    },
+    {
+      "epoch": 0.5161290322580645,
+      "grad_norm": 0.6966618299484253,
+      "learning_rate": 0.00016883116883116884,
+      "loss": 0.5568,
+      "step": 40
+    },
+    {
+      "epoch": 0.5290322580645161,
+      "grad_norm": 0.4658902585506439,
+      "learning_rate": 0.00016796536796536798,
+      "loss": 0.2625,
+      "step": 41
+    },
+    {
+      "epoch": 0.5419354838709678,
+      "grad_norm": 1.02367103099823,
+      "learning_rate": 0.0001670995670995671,
+      "loss": 0.5627,
+      "step": 42
+    },
+    {
+      "epoch": 0.5548387096774193,
+      "grad_norm": 0.6116736531257629,
+      "learning_rate": 0.00016623376623376625,
+      "loss": 0.4865,
+      "step": 43
+    },
+    {
+      "epoch": 0.567741935483871,
+      "grad_norm": 0.6404047608375549,
+      "learning_rate": 0.00016536796536796537,
+      "loss": 0.3376,
+      "step": 44
+    },
+    {
+      "epoch": 0.5806451612903226,
+      "grad_norm": 0.4990862011909485,
+      "learning_rate": 0.0001645021645021645,
+      "loss": 0.3086,
+      "step": 45
+    },
+    {
+      "epoch": 0.5935483870967742,
+      "grad_norm": 0.4322117865085602,
+      "learning_rate": 0.00016363636363636366,
+      "loss": 0.1709,
+      "step": 46
+    },
+    {
+      "epoch": 0.6064516129032258,
+      "grad_norm": 0.52425616979599,
+      "learning_rate": 0.00016277056277056278,
+      "loss": 0.2935,
+      "step": 47
+    },
+    {
+      "epoch": 0.6193548387096774,
+      "grad_norm": 0.658065140247345,
+      "learning_rate": 0.00016190476190476192,
+      "loss": 0.1955,
+      "step": 48
+    },
+    {
+      "epoch": 0.632258064516129,
+      "grad_norm": 0.9186128377914429,
+      "learning_rate": 0.00016103896103896104,
+      "loss": 0.5349,
+      "step": 49
+    },
+    {
+      "epoch": 0.6451612903225806,
+      "grad_norm": 0.6453927159309387,
+      "learning_rate": 0.00016017316017316016,
+      "loss": 0.322,
+      "step": 50
+    },
+    {
+      "epoch": 0.6580645161290323,
+      "grad_norm": 0.6589412689208984,
+      "learning_rate": 0.0001593073593073593,
+      "loss": 0.2992,
+      "step": 51
+    },
+    {
+      "epoch": 0.6709677419354839,
+      "grad_norm": 0.6165477633476257,
+      "learning_rate": 0.00015844155844155845,
+      "loss": 0.3571,
+      "step": 52
+    },
+    {
+      "epoch": 0.6838709677419355,
+      "grad_norm": 0.4464414715766907,
+      "learning_rate": 0.00015757575757575757,
+      "loss": 0.2457,
+      "step": 53
+    },
+    {
+      "epoch": 0.6967741935483871,
+      "grad_norm": 0.518046498298645,
+      "learning_rate": 0.00015670995670995672,
+      "loss": 0.2647,
+      "step": 54
+    },
+    {
+      "epoch": 0.7096774193548387,
+      "grad_norm": 0.8638506531715393,
+      "learning_rate": 0.00015584415584415587,
+      "loss": 0.3846,
+      "step": 55
+    },
+    {
+      "epoch": 0.7225806451612903,
+      "grad_norm": 0.5871357917785645,
+      "learning_rate": 0.00015497835497835498,
+      "loss": 0.2507,
+      "step": 56
+    },
+    {
+      "epoch": 0.7354838709677419,
+      "grad_norm": 0.623793363571167,
+      "learning_rate": 0.00015411255411255413,
+      "loss": 0.3449,
+      "step": 57
+    },
+    {
+      "epoch": 0.7483870967741936,
+      "grad_norm": 0.4925064444541931,
+      "learning_rate": 0.00015324675324675325,
+      "loss": 0.2015,
+      "step": 58
+    },
+    {
+      "epoch": 0.7612903225806451,
+      "grad_norm": 0.5898606777191162,
+      "learning_rate": 0.00015238095238095237,
+      "loss": 0.1438,
+      "step": 59
+    },
+    {
+      "epoch": 0.7741935483870968,
+      "grad_norm": 0.742535412311554,
+      "learning_rate": 0.00015151515151515152,
+      "loss": 0.3838,
+      "step": 60
+    },
+    {
+      "epoch": 0.7870967741935484,
+      "grad_norm": 0.6661336421966553,
+      "learning_rate": 0.00015064935064935066,
+      "loss": 0.1771,
+      "step": 61
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.8693909645080566,
+      "learning_rate": 0.00014978354978354978,
+      "loss": 0.3226,
+      "step": 62
+    },
+    {
+      "epoch": 0.8129032258064516,
+      "grad_norm": 0.7258728742599487,
+      "learning_rate": 0.00014891774891774893,
+      "loss": 0.3407,
+      "step": 63
+    },
+    {
+      "epoch": 0.8258064516129032,
+      "grad_norm": 0.4309225082397461,
+      "learning_rate": 0.00014805194805194807,
+      "loss": 0.1695,
+      "step": 64
+    },
+    {
+      "epoch": 0.8387096774193549,
+      "grad_norm": 0.6421737670898438,
+      "learning_rate": 0.0001471861471861472,
+      "loss": 0.3036,
+      "step": 65
+    },
+    {
+      "epoch": 0.8516129032258064,
+      "grad_norm": 0.47266942262649536,
+      "learning_rate": 0.00014632034632034634,
+      "loss": 0.1524,
+      "step": 66
+    },
+    {
+      "epoch": 0.864516129032258,
+      "grad_norm": 0.5186790227890015,
+      "learning_rate": 0.00014545454545454546,
+      "loss": 0.2081,
+      "step": 67
+    },
+    {
+      "epoch": 0.8774193548387097,
+      "grad_norm": 0.9141486287117004,
+      "learning_rate": 0.00014458874458874458,
+      "loss": 0.4174,
+      "step": 68
+    },
+    {
+      "epoch": 0.8903225806451613,
+      "grad_norm": 0.6384373903274536,
+      "learning_rate": 0.00014372294372294372,
+      "loss": 0.2237,
+      "step": 69
+    },
+    {
+      "epoch": 0.9032258064516129,
+      "grad_norm": 0.5125257968902588,
+      "learning_rate": 0.00014285714285714287,
+      "loss": 0.2249,
+      "step": 70
+    },
+    {
+      "epoch": 0.9161290322580645,
+      "grad_norm": 0.5451396107673645,
+      "learning_rate": 0.00014199134199134201,
+      "loss": 0.2341,
+      "step": 71
+    },
+    {
+      "epoch": 0.9290322580645162,
+      "grad_norm": 0.644568145275116,
+      "learning_rate": 0.00014112554112554113,
+      "loss": 0.2977,
+      "step": 72
+    },
+    {
+      "epoch": 0.9419354838709677,
+      "grad_norm": 0.7048823833465576,
+      "learning_rate": 0.00014025974025974028,
+      "loss": 0.3164,
+      "step": 73
+    },
+    {
+      "epoch": 0.9548387096774194,
+      "grad_norm": 0.6860247254371643,
+      "learning_rate": 0.0001393939393939394,
+      "loss": 0.2071,
+      "step": 74
+    },
+    {
+      "epoch": 0.967741935483871,
+      "grad_norm": 0.6741384267807007,
+      "learning_rate": 0.00013852813852813852,
+      "loss": 0.2399,
+      "step": 75
+    },
+    {
+      "epoch": 0.9806451612903225,
+      "grad_norm": 0.6632363796234131,
+      "learning_rate": 0.00013766233766233766,
+      "loss": 0.2165,
+      "step": 76
+    },
+    {
+      "epoch": 0.9935483870967742,
+      "grad_norm": 0.8669230937957764,
+      "learning_rate": 0.0001367965367965368,
+      "loss": 0.3115,
+      "step": 77
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.979816198348999,
+      "learning_rate": 0.00013593073593073593,
+      "loss": 0.2582,
+      "step": 78
+    },
+    {
+      "epoch": 1.0129032258064516,
+      "grad_norm": 0.5123947858810425,
+      "learning_rate": 0.00013506493506493507,
+      "loss": 0.1861,
+      "step": 79
+    },
+    {
+      "epoch": 1.0258064516129033,
+      "grad_norm": 0.5714449286460876,
+      "learning_rate": 0.00013419913419913422,
+      "loss": 0.1552,
+      "step": 80
+    },
+    {
+      "epoch": 1.038709677419355,
+      "grad_norm": 0.7106695771217346,
+      "learning_rate": 0.00013333333333333334,
+      "loss": 0.1569,
+      "step": 81
+    },
+    {
+      "epoch": 1.0516129032258064,
+      "grad_norm": 0.6655531525611877,
+      "learning_rate": 0.00013246753246753249,
+      "loss": 0.171,
+      "step": 82
+    },
+    {
+      "epoch": 1.064516129032258,
+      "grad_norm": 0.6956263184547424,
+      "learning_rate": 0.0001316017316017316,
+      "loss": 0.1865,
+      "step": 83
+    },
+    {
+      "epoch": 1.0774193548387097,
+      "grad_norm": 0.43610459566116333,
+      "learning_rate": 0.00013073593073593072,
+      "loss": 0.0821,
+      "step": 84
+    },
+    {
+      "epoch": 1.0903225806451613,
+      "grad_norm": 0.5302578806877136,
+      "learning_rate": 0.00012987012987012987,
+      "loss": 0.1022,
+      "step": 85
+    },
+    {
+      "epoch": 1.103225806451613,
+      "grad_norm": 0.6859675049781799,
+      "learning_rate": 0.00012900432900432902,
+      "loss": 0.2019,
+      "step": 86
+    },
+    {
+      "epoch": 1.1161290322580646,
+      "grad_norm": 0.8297210335731506,
+      "learning_rate": 0.00012813852813852814,
+      "loss": 0.2055,
+      "step": 87
+    },
+    {
+      "epoch": 1.129032258064516,
+      "grad_norm": 0.41531994938850403,
+      "learning_rate": 0.00012727272727272728,
+      "loss": 0.1127,
+      "step": 88
+    },
+    {
+      "epoch": 1.1419354838709677,
+      "grad_norm": 0.5810811519622803,
+      "learning_rate": 0.00012640692640692643,
+      "loss": 0.1254,
+      "step": 89
+    },
+    {
+      "epoch": 1.1548387096774193,
+      "grad_norm": 0.5267877578735352,
+      "learning_rate": 0.00012554112554112555,
+      "loss": 0.1512,
+      "step": 90
+    },
+    {
+      "epoch": 1.167741935483871,
+      "grad_norm": 0.6002141237258911,
+      "learning_rate": 0.00012467532467532467,
+      "loss": 0.1361,
+      "step": 91
+    },
+    {
+      "epoch": 1.1806451612903226,
+      "grad_norm": 0.6372831463813782,
+      "learning_rate": 0.0001238095238095238,
+      "loss": 0.179,
+      "step": 92
+    },
+    {
+      "epoch": 1.1935483870967742,
+      "grad_norm": 0.4526427090167999,
+      "learning_rate": 0.00012294372294372293,
+      "loss": 0.1321,
+      "step": 93
+    },
+    {
+      "epoch": 1.206451612903226,
+      "grad_norm": 0.43479424715042114,
+      "learning_rate": 0.00012207792207792208,
+      "loss": 0.0682,
+      "step": 94
+    },
+    {
+      "epoch": 1.2193548387096773,
+      "grad_norm": 0.5935952067375183,
+      "learning_rate": 0.00012121212121212122,
+      "loss": 0.1947,
+      "step": 95
+    },
+    {
+      "epoch": 1.232258064516129,
+      "grad_norm": 0.4366312325000763,
+      "learning_rate": 0.00012034632034632037,
+      "loss": 0.0702,
+      "step": 96
+    },
+    {
+      "epoch": 1.2451612903225806,
+      "grad_norm": 0.40079551935195923,
+      "learning_rate": 0.00011948051948051949,
+      "loss": 0.0944,
+      "step": 97
+    },
+    {
+      "epoch": 1.2580645161290323,
+      "grad_norm": 0.4562125504016876,
+      "learning_rate": 0.00011861471861471862,
+      "loss": 0.1036,
+      "step": 98
+    },
+    {
+      "epoch": 1.270967741935484,
+      "grad_norm": 0.7254213094711304,
+      "learning_rate": 0.00011774891774891777,
+      "loss": 0.1459,
+      "step": 99
+    },
+    {
+      "epoch": 1.2838709677419355,
+      "grad_norm": 0.5328529477119446,
+      "learning_rate": 0.00011688311688311689,
+      "loss": 0.0784,
+      "step": 100
+    },
+    {
+      "epoch": 1.2967741935483872,
+      "grad_norm": 0.46808844804763794,
+      "learning_rate": 0.00011601731601731602,
+      "loss": 0.1028,
+      "step": 101
+    },
+    {
+      "epoch": 1.3096774193548386,
+      "grad_norm": 0.5326903462409973,
+      "learning_rate": 0.00011515151515151516,
+      "loss": 0.1486,
+      "step": 102
+    },
+    {
+      "epoch": 1.3225806451612903,
+      "grad_norm": 0.6174523234367371,
+      "learning_rate": 0.00011428571428571428,
+      "loss": 0.1267,
+      "step": 103
+    },
+    {
+      "epoch": 1.335483870967742,
+      "grad_norm": 0.9775211215019226,
+      "learning_rate": 0.00011341991341991343,
+      "loss": 0.0859,
+      "step": 104
+    },
+    {
+      "epoch": 1.3483870967741935,
+      "grad_norm": 0.4287857711315155,
+      "learning_rate": 0.00011255411255411256,
+      "loss": 0.0774,
+      "step": 105
+    },
+    {
+      "epoch": 1.3612903225806452,
+      "grad_norm": 0.4066872000694275,
+      "learning_rate": 0.00011168831168831168,
+      "loss": 0.0803,
+      "step": 106
+    },
+    {
+      "epoch": 1.3741935483870968,
+      "grad_norm": 0.47322240471839905,
+      "learning_rate": 0.00011082251082251083,
+      "loss": 0.1089,
+      "step": 107
+    },
+    {
+      "epoch": 1.3870967741935485,
+      "grad_norm": 0.7848142981529236,
+      "learning_rate": 0.00010995670995670997,
+      "loss": 0.1632,
+      "step": 108
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 0.4280541241168976,
+      "learning_rate": 0.00010909090909090909,
+      "loss": 0.0811,
+      "step": 109
+    },
+    {
+      "epoch": 1.4129032258064516,
+      "grad_norm": 0.6968611478805542,
+      "learning_rate": 0.00010822510822510823,
+      "loss": 0.1355,
+      "step": 110
+    },
+    {
+      "epoch": 1.4258064516129032,
+      "grad_norm": 0.5956393480300903,
+      "learning_rate": 0.00010735930735930737,
+      "loss": 0.1291,
+      "step": 111
+    },
+    {
+      "epoch": 1.4387096774193548,
+      "grad_norm": 0.47604626417160034,
+      "learning_rate": 0.00010649350649350649,
+      "loss": 0.1,
+      "step": 112
+    },
+    {
+      "epoch": 1.4516129032258065,
+      "grad_norm": 0.4992416203022003,
+      "learning_rate": 0.00010562770562770564,
+      "loss": 0.0785,
+      "step": 113
+    },
+    {
+      "epoch": 1.4645161290322581,
+      "grad_norm": 0.40504857897758484,
+      "learning_rate": 0.00010476190476190477,
+      "loss": 0.0713,
+      "step": 114
+    },
+    {
+      "epoch": 1.4774193548387098,
+      "grad_norm": 0.3858068883419037,
+      "learning_rate": 0.00010389610389610389,
+      "loss": 0.0541,
+      "step": 115
+    },
+    {
+      "epoch": 1.4903225806451612,
+      "grad_norm": 0.4108275771141052,
+      "learning_rate": 0.00010303030303030303,
+      "loss": 0.0452,
+      "step": 116
+    },
+    {
+      "epoch": 1.5032258064516129,
+      "grad_norm": 0.36258989572525024,
+      "learning_rate": 0.00010216450216450218,
+      "loss": 0.0686,
+      "step": 117
+    },
+    {
+      "epoch": 1.5161290322580645,
+      "grad_norm": 0.3928491175174713,
+      "learning_rate": 0.0001012987012987013,
+      "loss": 0.0898,
+      "step": 118
+    },
+    {
+      "epoch": 1.5290322580645161,
+      "grad_norm": 0.5681027770042419,
+      "learning_rate": 0.00010043290043290043,
+      "loss": 0.1086,
+      "step": 119
+    },
+    {
+      "epoch": 1.5419354838709678,
+      "grad_norm": 0.4988275468349457,
+      "learning_rate": 9.956709956709958e-05,
+      "loss": 0.0883,
+      "step": 120
+    },
+    {
+      "epoch": 1.5548387096774192,
+      "grad_norm": 0.4192441999912262,
+      "learning_rate": 9.870129870129871e-05,
+      "loss": 0.0605,
+      "step": 121
+    },
+    {
+      "epoch": 1.567741935483871,
+      "grad_norm": 0.6245271563529968,
+      "learning_rate": 9.783549783549783e-05,
+      "loss": 0.0819,
+      "step": 122
+    },
+    {
+      "epoch": 1.5806451612903225,
+      "grad_norm": 0.4546557366847992,
+      "learning_rate": 9.696969696969698e-05,
+      "loss": 0.0558,
+      "step": 123
+    },
+    {
+      "epoch": 1.5935483870967742,
+      "grad_norm": 0.40151137113571167,
+      "learning_rate": 9.610389610389611e-05,
+      "loss": 0.0572,
+      "step": 124
+    },
+    {
+      "epoch": 1.6064516129032258,
+      "grad_norm": 0.6247302889823914,
+      "learning_rate": 9.523809523809524e-05,
+      "loss": 0.1137,
+      "step": 125
+    },
+    {
+      "epoch": 1.6193548387096774,
+      "grad_norm": 0.5640382170677185,
+      "learning_rate": 9.437229437229437e-05,
+      "loss": 0.1135,
+      "step": 126
+    },
+    {
+      "epoch": 1.632258064516129,
+      "grad_norm": 0.4762142300605774,
+      "learning_rate": 9.35064935064935e-05,
+      "loss": 0.0741,
+      "step": 127
+    },
+    {
+      "epoch": 1.6451612903225805,
+      "grad_norm": 0.49186083674430847,
+      "learning_rate": 9.264069264069265e-05,
+      "loss": 0.0765,
+      "step": 128
+    },
+    {
+      "epoch": 1.6580645161290324,
+      "grad_norm": 0.34283480048179626,
+      "learning_rate": 9.177489177489178e-05,
+      "loss": 0.0599,
+      "step": 129
+    },
+    {
+      "epoch": 1.6709677419354838,
+      "grad_norm": 0.5842408537864685,
+      "learning_rate": 9.090909090909092e-05,
+      "loss": 0.0802,
+      "step": 130
+    },
+    {
+      "epoch": 1.6838709677419355,
+      "grad_norm": 0.2652600109577179,
+      "learning_rate": 9.004329004329005e-05,
+      "loss": 0.0355,
+      "step": 131
+    },
+    {
+      "epoch": 1.696774193548387,
+      "grad_norm": 0.7124427556991577,
+      "learning_rate": 8.917748917748918e-05,
+      "loss": 0.1123,
+      "step": 132
+    },
+    {
+      "epoch": 1.7096774193548387,
+      "grad_norm": 0.344987154006958,
+      "learning_rate": 8.831168831168831e-05,
+      "loss": 0.0386,
+      "step": 133
+    },
+    {
+      "epoch": 1.7225806451612904,
+      "grad_norm": 0.3747287392616272,
+      "learning_rate": 8.744588744588745e-05,
+      "loss": 0.0559,
+      "step": 134
+    },
+    {
+      "epoch": 1.7354838709677418,
+      "grad_norm": 0.6383305191993713,
+      "learning_rate": 8.658008658008658e-05,
+      "loss": 0.0763,
+      "step": 135
+    },
+    {
+      "epoch": 1.7483870967741937,
+      "grad_norm": 0.3109307885169983,
+      "learning_rate": 8.571428571428571e-05,
+      "loss": 0.0392,
+      "step": 136
+    },
+    {
+      "epoch": 1.761290322580645,
+      "grad_norm": 0.5307775139808655,
+      "learning_rate": 8.484848484848486e-05,
+      "loss": 0.0437,
+      "step": 137
+    },
+    {
+      "epoch": 1.7741935483870968,
+      "grad_norm": 0.4100543260574341,
+      "learning_rate": 8.398268398268399e-05,
+      "loss": 0.0702,
+      "step": 138
+    },
+    {
+      "epoch": 1.7870967741935484,
+      "grad_norm": 0.21597693860530853,
+      "learning_rate": 8.311688311688312e-05,
+      "loss": 0.0211,
+      "step": 139
+    },
+    {
+      "epoch": 1.8,
+      "grad_norm": 0.32146573066711426,
+      "learning_rate": 8.225108225108226e-05,
+      "loss": 0.0386,
+      "step": 140
+    },
+    {
+      "epoch": 1.8129032258064517,
+      "grad_norm": 0.3650757968425751,
+      "learning_rate": 8.138528138528139e-05,
+      "loss": 0.0354,
+      "step": 141
+    },
+    {
+      "epoch": 1.8258064516129031,
+      "grad_norm": 0.2730308473110199,
+      "learning_rate": 8.051948051948052e-05,
+      "loss": 0.0255,
+      "step": 142
+    },
+    {
+      "epoch": 1.838709677419355,
+      "grad_norm": 0.35907551646232605,
+      "learning_rate": 7.965367965367965e-05,
+      "loss": 0.0425,
+      "step": 143
+    },
+    {
+      "epoch": 1.8516129032258064,
+      "grad_norm": 0.3438459038734436,
+      "learning_rate": 7.878787878787879e-05,
+      "loss": 0.0413,
+      "step": 144
+    },
+    {
+      "epoch": 1.864516129032258,
+      "grad_norm": 0.30859899520874023,
+      "learning_rate": 7.792207792207793e-05,
+      "loss": 0.0526,
+      "step": 145
+    },
+    {
+      "epoch": 1.8774193548387097,
+      "grad_norm": 0.572073221206665,
+      "learning_rate": 7.705627705627707e-05,
+      "loss": 0.0805,
+      "step": 146
+    },
+    {
+      "epoch": 1.8903225806451613,
+      "grad_norm": 0.29864397644996643,
+      "learning_rate": 7.619047619047618e-05,
+      "loss": 0.0505,
+      "step": 147
+    },
+    {
+      "epoch": 1.903225806451613,
+      "grad_norm": 0.48550477623939514,
+      "learning_rate": 7.532467532467533e-05,
+      "loss": 0.0634,
+      "step": 148
+    },
+    {
+      "epoch": 1.9161290322580644,
+      "grad_norm": 0.5192674994468689,
+      "learning_rate": 7.445887445887446e-05,
+      "loss": 0.059,
+      "step": 149
+    },
+    {
+      "epoch": 1.9290322580645163,
+      "grad_norm": 0.38177090883255005,
+      "learning_rate": 7.35930735930736e-05,
+      "loss": 0.0508,
+      "step": 150
+    },
+    {
+      "epoch": 1.9419354838709677,
+      "grad_norm": 0.2791922092437744,
+      "learning_rate": 7.272727272727273e-05,
+      "loss": 0.0232,
+      "step": 151
+    },
+    {
+      "epoch": 1.9548387096774194,
+      "grad_norm": 0.5312056541442871,
+      "learning_rate": 7.186147186147186e-05,
+      "loss": 0.0522,
+      "step": 152
+    },
+    {
+      "epoch": 1.967741935483871,
+      "grad_norm": 0.35744139552116394,
+      "learning_rate": 7.099567099567101e-05,
+      "loss": 0.043,
+      "step": 153
+    },
+    {
+      "epoch": 1.9806451612903224,
+      "grad_norm": 0.4663527309894562,
+      "learning_rate": 7.012987012987014e-05,
+      "loss": 0.0429,
+      "step": 154
+    },
+    {
+      "epoch": 1.9935483870967743,
+      "grad_norm": 0.40046221017837524,
+      "learning_rate": 6.926406926406926e-05,
+      "loss": 0.0403,
+      "step": 155
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.5130640864372253,
+      "learning_rate": 6.83982683982684e-05,
+      "loss": 0.0324,
+      "step": 156
+    },
+    {
+      "epoch": 2.0129032258064514,
+      "grad_norm": 0.23333851993083954,
+      "learning_rate": 6.753246753246754e-05,
+      "loss": 0.0219,
+      "step": 157
+    },
+    {
+      "epoch": 2.0258064516129033,
+      "grad_norm": 0.2739700973033905,
+      "learning_rate": 6.666666666666667e-05,
+      "loss": 0.0221,
+      "step": 158
+    },
+    {
+      "epoch": 2.0387096774193547,
+      "grad_norm": 0.22633981704711914,
+      "learning_rate": 6.58008658008658e-05,
+      "loss": 0.0185,
+      "step": 159
+    },
+    {
+      "epoch": 2.0516129032258066,
+      "grad_norm": 0.21664434671401978,
+      "learning_rate": 6.493506493506494e-05,
+      "loss": 0.0162,
+      "step": 160
+    },
+    {
+      "epoch": 2.064516129032258,
+      "grad_norm": 0.2563764452934265,
+      "learning_rate": 6.406926406926407e-05,
+      "loss": 0.0176,
+      "step": 161
+    },
+    {
+      "epoch": 2.07741935483871,
+      "grad_norm": 0.3219418227672577,
+      "learning_rate": 6.320346320346321e-05,
+      "loss": 0.0162,
+      "step": 162
+    },
+    {
+      "epoch": 2.0903225806451613,
+      "grad_norm": 0.21077695488929749,
+      "learning_rate": 6.233766233766233e-05,
+      "loss": 0.0196,
+      "step": 163
+    },
+    {
+      "epoch": 2.1032258064516127,
+      "grad_norm": 0.28284111618995667,
+      "learning_rate": 6.147186147186147e-05,
+      "loss": 0.0253,
+      "step": 164
+    },
+    {
+      "epoch": 2.1161290322580646,
+      "grad_norm": 0.2859232723712921,
+      "learning_rate": 6.060606060606061e-05,
+      "loss": 0.0179,
+      "step": 165
+    },
+    {
+      "epoch": 2.129032258064516,
+      "grad_norm": 0.3736005425453186,
+      "learning_rate": 5.9740259740259744e-05,
+      "loss": 0.0294,
+      "step": 166
+    },
+    {
+      "epoch": 2.141935483870968,
+      "grad_norm": 0.3151097297668457,
+      "learning_rate": 5.887445887445888e-05,
+      "loss": 0.0193,
+      "step": 167
+    },
+    {
+      "epoch": 2.1548387096774193,
+      "grad_norm": 0.22999654710292816,
+      "learning_rate": 5.800865800865801e-05,
+      "loss": 0.0209,
+      "step": 168
+    },
+    {
+      "epoch": 2.167741935483871,
+      "grad_norm": 0.4394060969352722,
+      "learning_rate": 5.714285714285714e-05,
+      "loss": 0.0376,
+      "step": 169
+    },
+    {
+      "epoch": 2.1806451612903226,
+      "grad_norm": 0.3017919659614563,
+      "learning_rate": 5.627705627705628e-05,
+      "loss": 0.0338,
+      "step": 170
+    },
+    {
+      "epoch": 2.193548387096774,
+      "grad_norm": 0.27291226387023926,
+      "learning_rate": 5.5411255411255414e-05,
+      "loss": 0.0188,
+      "step": 171
+    },
+    {
+      "epoch": 2.206451612903226,
+      "grad_norm": 0.21319767832756042,
+      "learning_rate": 5.4545454545454546e-05,
+      "loss": 0.0177,
+      "step": 172
+    },
+    {
+      "epoch": 2.2193548387096773,
+      "grad_norm": 0.3137580156326294,
+      "learning_rate": 5.3679653679653686e-05,
+      "loss": 0.0228,
+      "step": 173
+    },
+    {
+      "epoch": 2.232258064516129,
+      "grad_norm": 0.2079544961452484,
+      "learning_rate": 5.281385281385282e-05,
+      "loss": 0.0194,
+      "step": 174
+    },
+    {
+      "epoch": 2.2451612903225806,
+      "grad_norm": 0.24419479072093964,
+      "learning_rate": 5.1948051948051944e-05,
+      "loss": 0.0285,
+      "step": 175
+    },
+    {
+      "epoch": 2.258064516129032,
+      "grad_norm": 0.24746587872505188,
+      "learning_rate": 5.108225108225109e-05,
+      "loss": 0.0195,
+      "step": 176
+    },
+    {
+      "epoch": 2.270967741935484,
+      "grad_norm": 0.18721561133861542,
+      "learning_rate": 5.0216450216450216e-05,
+      "loss": 0.0245,
+      "step": 177
+    },
+    {
+      "epoch": 2.2838709677419353,
+      "grad_norm": 0.21970334649085999,
+      "learning_rate": 4.9350649350649355e-05,
+      "loss": 0.0243,
+      "step": 178
+    },
+    {
+      "epoch": 2.296774193548387,
+      "grad_norm": 0.16727742552757263,
+      "learning_rate": 4.848484848484849e-05,
+      "loss": 0.0172,
+      "step": 179
+    },
+    {
+      "epoch": 2.3096774193548386,
+      "grad_norm": 0.19507913291454315,
+      "learning_rate": 4.761904761904762e-05,
+      "loss": 0.0254,
+      "step": 180
+    },
+    {
+      "epoch": 2.3225806451612905,
+      "grad_norm": 0.13436348736286163,
+      "learning_rate": 4.675324675324675e-05,
+      "loss": 0.011,
+      "step": 181
+    },
+    {
+      "epoch": 2.335483870967742,
+      "grad_norm": 0.19645601511001587,
+      "learning_rate": 4.588744588744589e-05,
+      "loss": 0.0168,
+      "step": 182
+    },
+    {
+      "epoch": 2.3483870967741938,
+      "grad_norm": 0.22561688721179962,
+      "learning_rate": 4.5021645021645025e-05,
+      "loss": 0.0156,
+      "step": 183
+    },
+    {
+      "epoch": 2.361290322580645,
+      "grad_norm": 0.25399160385131836,
+      "learning_rate": 4.415584415584416e-05,
+      "loss": 0.0313,
+      "step": 184
+    },
+    {
+      "epoch": 2.3741935483870966,
+      "grad_norm": 0.21687330305576324,
+      "learning_rate": 4.329004329004329e-05,
+      "loss": 0.0136,
+      "step": 185
+    },
+    {
+      "epoch": 2.3870967741935485,
+      "grad_norm": 0.19569694995880127,
+      "learning_rate": 4.242424242424243e-05,
+      "loss": 0.0172,
+      "step": 186
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 0.22807073593139648,
+      "learning_rate": 4.155844155844156e-05,
+      "loss": 0.0231,
+      "step": 187
+    },
+    {
+      "epoch": 2.412903225806452,
+      "grad_norm": 0.36123302578926086,
+      "learning_rate": 4.0692640692640695e-05,
+      "loss": 0.0285,
+      "step": 188
+    },
+    {
+      "epoch": 2.425806451612903,
+      "grad_norm": 0.22407294809818268,
+      "learning_rate": 3.982683982683983e-05,
+      "loss": 0.0201,
+      "step": 189
+    },
+    {
+      "epoch": 2.4387096774193546,
+      "grad_norm": 0.14869819581508636,
+      "learning_rate": 3.8961038961038966e-05,
+      "loss": 0.0128,
+      "step": 190
+    },
+    {
+      "epoch": 2.4516129032258065,
+      "grad_norm": 0.21592901647090912,
+      "learning_rate": 3.809523809523809e-05,
+      "loss": 0.0187,
+      "step": 191
+    },
+    {
+      "epoch": 2.464516129032258,
+      "grad_norm": 0.4154917895793915,
+      "learning_rate": 3.722943722943723e-05,
+      "loss": 0.0253,
+      "step": 192
+    },
+    {
+      "epoch": 2.47741935483871,
+      "grad_norm": 0.1732252538204193,
+      "learning_rate": 3.6363636363636364e-05,
+      "loss": 0.0125,
+      "step": 193
+    },
+    {
+      "epoch": 2.490322580645161,
+      "grad_norm": 0.22216366231441498,
+      "learning_rate": 3.5497835497835503e-05,
+      "loss": 0.0152,
+      "step": 194
+    },
+    {
+      "epoch": 2.5032258064516126,
+      "grad_norm": 0.2107250988483429,
+      "learning_rate": 3.463203463203463e-05,
+      "loss": 0.0149,
+      "step": 195
+    },
+    {
+      "epoch": 2.5161290322580645,
+      "grad_norm": 0.12403655797243118,
+      "learning_rate": 3.376623376623377e-05,
+      "loss": 0.0114,
+      "step": 196
+    },
+    {
+      "epoch": 2.5290322580645164,
+      "grad_norm": 0.16927888989448547,
+      "learning_rate": 3.29004329004329e-05,
+      "loss": 0.0129,
+      "step": 197
+    },
+    {
+      "epoch": 2.541935483870968,
+      "grad_norm": 0.24353042244911194,
+      "learning_rate": 3.2034632034632034e-05,
+      "loss": 0.0152,
+      "step": 198
+    },
+    {
+      "epoch": 2.554838709677419,
+      "grad_norm": 0.12740740180015564,
+      "learning_rate": 3.1168831168831166e-05,
+      "loss": 0.0139,
+      "step": 199
+    },
+    {
+      "epoch": 2.567741935483871,
+      "grad_norm": 0.3001946210861206,
+      "learning_rate": 3.0303030303030306e-05,
+      "loss": 0.026,
+      "step": 200
+    },
+    {
+      "epoch": 2.5806451612903225,
+      "grad_norm": 0.25068429112434387,
+      "learning_rate": 2.943722943722944e-05,
+      "loss": 0.0197,
+      "step": 201
+    },
+    {
+      "epoch": 2.5935483870967744,
+      "grad_norm": 0.19569292664527893,
+      "learning_rate": 2.857142857142857e-05,
+      "loss": 0.0128,
+      "step": 202
+    },
+    {
+      "epoch": 2.606451612903226,
+      "grad_norm": 0.25671446323394775,
+      "learning_rate": 2.7705627705627707e-05,
+      "loss": 0.0228,
+      "step": 203
+    },
+    {
+      "epoch": 2.6193548387096772,
+      "grad_norm": 0.11213606595993042,
+      "learning_rate": 2.6839826839826843e-05,
+      "loss": 0.01,
+      "step": 204
+    },
+    {
+      "epoch": 2.632258064516129,
+      "grad_norm": 0.07896478474140167,
+      "learning_rate": 2.5974025974025972e-05,
+      "loss": 0.0076,
+      "step": 205
+    },
+    {
+      "epoch": 2.6451612903225805,
+      "grad_norm": 0.23440855741500854,
+      "learning_rate": 2.5108225108225108e-05,
+      "loss": 0.0163,
+      "step": 206
+    },
+    {
+      "epoch": 2.6580645161290324,
+      "grad_norm": 0.1345127820968628,
+      "learning_rate": 2.4242424242424244e-05,
+      "loss": 0.0108,
+      "step": 207
+    },
+    {
+      "epoch": 2.670967741935484,
+      "grad_norm": 0.21752691268920898,
+      "learning_rate": 2.3376623376623376e-05,
+      "loss": 0.0175,
+      "step": 208
+    },
+    {
+      "epoch": 2.6838709677419352,
+      "grad_norm": 0.10310844331979752,
+      "learning_rate": 2.2510822510822512e-05,
+      "loss": 0.008,
+      "step": 209
+    },
+    {
+      "epoch": 2.696774193548387,
+      "grad_norm": 0.14364340901374817,
+      "learning_rate": 2.1645021645021645e-05,
+      "loss": 0.0123,
+      "step": 210
+    },
+    {
+      "epoch": 2.709677419354839,
+      "grad_norm": 0.12540531158447266,
+      "learning_rate": 2.077922077922078e-05,
+      "loss": 0.0086,
+      "step": 211
+    },
+    {
+      "epoch": 2.7225806451612904,
+      "grad_norm": 0.19787082076072693,
+      "learning_rate": 1.9913419913419914e-05,
+      "loss": 0.0141,
+      "step": 212
+    },
+    {
+      "epoch": 2.735483870967742,
+      "grad_norm": 0.19301635026931763,
+      "learning_rate": 1.9047619047619046e-05,
+      "loss": 0.0135,
+      "step": 213
+    },
+    {
+      "epoch": 2.7483870967741937,
+      "grad_norm": 0.19226261973381042,
+      "learning_rate": 1.8181818181818182e-05,
+      "loss": 0.0134,
+      "step": 214
+    },
+    {
+      "epoch": 2.761290322580645,
+      "grad_norm": 0.12996652722358704,
+      "learning_rate": 1.7316017316017315e-05,
+      "loss": 0.0122,
+      "step": 215
+    },
+    {
+      "epoch": 2.774193548387097,
+      "grad_norm": 0.1624728888273239,
+      "learning_rate": 1.645021645021645e-05,
+      "loss": 0.0139,
+      "step": 216
+    },
+    {
+      "epoch": 2.7870967741935484,
+      "grad_norm": 0.09435854852199554,
+      "learning_rate": 1.5584415584415583e-05,
+      "loss": 0.0097,
+      "step": 217
+    },
+    {
+      "epoch": 2.8,
+      "grad_norm": 0.1358294039964676,
+      "learning_rate": 1.471861471861472e-05,
+      "loss": 0.0123,
+      "step": 218
+    },
+    {
+      "epoch": 2.8129032258064517,
+      "grad_norm": 0.12223871797323227,
+      "learning_rate": 1.3852813852813853e-05,
+      "loss": 0.0122,
+      "step": 219
+    },
+    {
+      "epoch": 2.825806451612903,
+      "grad_norm": 0.16250500082969666,
+      "learning_rate": 1.2987012987012986e-05,
+      "loss": 0.0127,
+      "step": 220
+    },
+    {
+      "epoch": 2.838709677419355,
+      "grad_norm": 0.23408320546150208,
+      "learning_rate": 1.2121212121212122e-05,
+      "loss": 0.0127,
+      "step": 221
+    },
+    {
+      "epoch": 2.8516129032258064,
+      "grad_norm": 0.23933890461921692,
+      "learning_rate": 1.1255411255411256e-05,
+      "loss": 0.0146,
+      "step": 222
+    },
+    {
+      "epoch": 2.864516129032258,
+      "grad_norm": 0.13585495948791504,
+      "learning_rate": 1.038961038961039e-05,
+      "loss": 0.0122,
+      "step": 223
+    },
+    {
+      "epoch": 2.8774193548387097,
+      "grad_norm": 0.16187234222888947,
+      "learning_rate": 9.523809523809523e-06,
+      "loss": 0.0101,
+      "step": 224
+    },
+    {
+      "epoch": 2.8903225806451616,
+      "grad_norm": 0.20218585431575775,
+      "learning_rate": 8.658008658008657e-06,
+      "loss": 0.0124,
+      "step": 225
+    },
+    {
+      "epoch": 2.903225806451613,
+      "grad_norm": 0.12428252398967743,
+      "learning_rate": 7.792207792207792e-06,
+      "loss": 0.0104,
+      "step": 226
+    },
+    {
+      "epoch": 2.9161290322580644,
+      "grad_norm": 0.14734520018100739,
+      "learning_rate": 6.926406926406927e-06,
+      "loss": 0.0126,
+      "step": 227
+    },
+    {
+      "epoch": 2.9290322580645163,
+      "grad_norm": 0.11576768010854721,
+      "learning_rate": 6.060606060606061e-06,
+      "loss": 0.0125,
+      "step": 228
+    },
+    {
+      "epoch": 2.9419354838709677,
+      "grad_norm": 0.13777028024196625,
+      "learning_rate": 5.194805194805195e-06,
+      "loss": 0.0126,
+      "step": 229
+    },
+    {
+      "epoch": 2.9548387096774196,
+      "grad_norm": 0.12558940052986145,
+      "learning_rate": 4.329004329004329e-06,
+      "loss": 0.0099,
+      "step": 230
+    },
+    {
+      "epoch": 2.967741935483871,
+      "grad_norm": 0.1385784149169922,
+      "learning_rate": 3.4632034632034634e-06,
+      "loss": 0.0106,
+      "step": 231
+    },
+    {
+      "epoch": 2.9806451612903224,
+      "grad_norm": 0.15794174373149872,
+      "learning_rate": 2.5974025974025976e-06,
+      "loss": 0.0125,
+      "step": 232
+    },
+    {
+      "epoch": 2.9935483870967743,
+      "grad_norm": 0.21669098734855652,
+      "learning_rate": 1.7316017316017317e-06,
+      "loss": 0.0161,
+      "step": 233
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.19324541091918945,
+      "learning_rate": 8.658008658008658e-07,
+      "loss": 0.0111,
+      "step": 234
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 234,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.0353463173494784e+17,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

outputs/checkpoint-234/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a383eae8a7749f88723b7d26011b143d7dd0d6f6ac555ebe3e35308554b71457
+size 5688

outputs/checkpoint-87/README.md

@@ -0,0 +1,210 @@
+---
+base_model: unsloth/phi-4-unsloth-bnb-4bit
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:unsloth/phi-4-unsloth-bnb-4bit
+- lora
+- sft
+- transformers
+- trl
+- unsloth
+---
+
+# 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 0.16.0

outputs/checkpoint-87/adapter_config.json

@@ -0,0 +1,41 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "unsloth/phi-4-unsloth-bnb-4bit",
+  "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": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "o_proj",
+    "up_proj",
+    "q_proj",
+    "k_proj",
+    "v_proj",
+    "gate_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

outputs/checkpoint-87/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a4fcd6a217815aff0cea0990c6ec63f6a1ced14d8550c564cf934dae3ca3e6a
+size 262219392

outputs/checkpoint-87/chat_template.jinja

@@ -0,0 +1 @@
+{% for message in messages %}{% if (message['role'] == 'system') %}{{'<|im_start|>system<|im_sep|>' + message['content'] + '<|im_end|>'}}{% elif (message['role'] == 'user') %}{{'<|im_start|>user<|im_sep|>' + message['content'] + '<|im_end|>'}}{% elif (message['role'] == 'assistant') %}{{'<|im_start|>assistant<|im_sep|>' + message['content'] + '<|im_end|>'}}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant<|im_sep|>' }}{% endif %}

outputs/checkpoint-87/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1e02bd147e5345475abd814ec684bff13c49cb8d37b66300c98ed9e27b1ee9d
+size 133778516

outputs/checkpoint-87/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c00c4365d25c9e7a26248ebf654c98af9ac52614e63c8c21d5b0905fc80a36a0
+size 14244

outputs/checkpoint-87/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9eff6e9c5edd767e33c412f800829af557353034949807d6edf978428ca96a5
+size 1064

outputs/checkpoint-87/special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": true,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": true,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|dummy_87|>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": true,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "�",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

outputs/checkpoint-87/tokenizer_config.json

@@ -0,0 +1,790 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "5809": {
+      "content": "�",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100256": {
+      "content": "<|dummy_0|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100257": {
+      "content": "<|endoftext|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100258": {
+      "content": "<|fim_prefix|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100259": {
+      "content": "<|fim_middle|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100260": {
+      "content": "<|fim_suffix|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100261": {
+      "content": "<|dummy_1|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100262": {
+      "content": "<|dummy_2|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100263": {
+      "content": "<|dummy_3|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100264": {
+      "content": "<|im_start|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100265": {
+      "content": "<|im_end|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100266": {
+      "content": "<|im_sep|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100267": {
+      "content": "<|dummy_4|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100268": {
+      "content": "<|dummy_5|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100269": {
+      "content": "<|dummy_6|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100270": {
+      "content": "<|dummy_7|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100271": {
+      "content": "<|dummy_8|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100272": {
+      "content": "<|dummy_9|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100273": {
+      "content": "<|dummy_10|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100274": {
+      "content": "<|dummy_11|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100275": {
+      "content": "<|dummy_12|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100276": {
+      "content": "<|endofprompt|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100277": {
+      "content": "<|dummy_13|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100278": {
+      "content": "<|dummy_14|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100279": {
+      "content": "<|dummy_15|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100280": {
+      "content": "<|dummy_16|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100281": {
+      "content": "<|dummy_17|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100282": {
+      "content": "<|dummy_18|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100283": {
+      "content": "<|dummy_19|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100284": {
+      "content": "<|dummy_20|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100285": {
+      "content": "<|dummy_21|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100286": {
+      "content": "<|dummy_22|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100287": {
+      "content": "<|dummy_23|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100288": {
+      "content": "<|dummy_24|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100289": {
+      "content": "<|dummy_25|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100290": {
+      "content": "<|dummy_26|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100291": {
+      "content": "<|dummy_27|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100292": {
+      "content": "<|dummy_28|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100293": {
+      "content": "<|dummy_29|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100294": {
+      "content": "<|dummy_30|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100295": {
+      "content": "<|dummy_31|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100296": {
+      "content": "<|dummy_32|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100297": {
+      "content": "<|dummy_33|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100298": {
+      "content": "<|dummy_34|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100299": {
+      "content": "<|dummy_35|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100300": {
+      "content": "<|dummy_36|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100301": {
+      "content": "<|dummy_37|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100302": {
+      "content": "<|dummy_38|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100303": {
+      "content": "<|dummy_39|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100304": {
+      "content": "<|dummy_40|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100305": {
+      "content": "<|dummy_41|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100306": {
+      "content": "<|dummy_42|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100307": {
+      "content": "<|dummy_43|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100308": {
+      "content": "<|dummy_44|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100309": {
+      "content": "<|dummy_45|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100310": {
+      "content": "<|dummy_46|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100311": {
+      "content": "<|dummy_47|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100312": {
+      "content": "<|dummy_48|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100313": {
+      "content": "<|dummy_49|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100314": {
+      "content": "<|dummy_50|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100315": {
+      "content": "<|dummy_51|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100316": {
+      "content": "<|dummy_52|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100317": {
+      "content": "<|dummy_53|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100318": {
+      "content": "<|dummy_54|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100319": {
+      "content": "<|dummy_55|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100320": {
+      "content": "<|dummy_56|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100321": {
+      "content": "<|dummy_57|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100322": {
+      "content": "<|dummy_58|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100323": {
+      "content": "<|dummy_59|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100324": {
+      "content": "<|dummy_60|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100325": {
+      "content": "<|dummy_61|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100326": {
+      "content": "<|dummy_62|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100327": {
+      "content": "<|dummy_63|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100328": {
+      "content": "<|dummy_64|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100329": {
+      "content": "<|dummy_65|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100330": {
+      "content": "<|dummy_66|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100331": {
+      "content": "<|dummy_67|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100332": {
+      "content": "<|dummy_68|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100333": {
+      "content": "<|dummy_69|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100334": {
+      "content": "<|dummy_70|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100335": {
+      "content": "<|dummy_71|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100336": {
+      "content": "<|dummy_72|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100337": {
+      "content": "<|dummy_73|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100338": {
+      "content": "<|dummy_74|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100339": {
+      "content": "<|dummy_75|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100340": {
+      "content": "<|dummy_76|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100341": {
+      "content": "<|dummy_77|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100342": {
+      "content": "<|dummy_78|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100343": {
+      "content": "<|dummy_79|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100344": {
+      "content": "<|dummy_80|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100345": {
+      "content": "<|dummy_81|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100346": {
+      "content": "<|dummy_82|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100347": {
+      "content": "<|dummy_83|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100348": {
+      "content": "<|dummy_84|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100349": {
+      "content": "<|dummy_85|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100350": {
+      "content": "<|dummy_86|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100351": {
+      "content": "<|dummy_87|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "extra_special_tokens": {},
+  "model_max_length": 16384,
+  "pad_token": "<|dummy_87|>",
+  "padding_side": "right",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "�"
+}

outputs/checkpoint-87/trainer_state.json

@@ -0,0 +1,643 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 87,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03508771929824561,
+      "grad_norm": 0.043367721140384674,
+      "learning_rate": 0.0,
+      "loss": 0.0033,
+      "step": 1
+    },
+    {
+      "epoch": 0.07017543859649122,
+      "grad_norm": 0.06946025043725967,
+      "learning_rate": 6.666666666666667e-05,
+      "loss": 0.0037,
+      "step": 2
+    },
+    {
+      "epoch": 0.10526315789473684,
+      "grad_norm": 0.044264402240514755,
+      "learning_rate": 0.00013333333333333334,
+      "loss": 0.0032,
+      "step": 3
+    },
+    {
+      "epoch": 0.14035087719298245,
+      "grad_norm": 0.03978864848613739,
+      "learning_rate": 0.0002,
+      "loss": 0.0038,
+      "step": 4
+    },
+    {
+      "epoch": 0.17543859649122806,
+      "grad_norm": 0.03119363822042942,
+      "learning_rate": 0.00019761904761904763,
+      "loss": 0.0036,
+      "step": 5
+    },
+    {
+      "epoch": 0.21052631578947367,
+      "grad_norm": 0.0629071518778801,
+      "learning_rate": 0.00019523809523809525,
+      "loss": 0.0035,
+      "step": 6
+    },
+    {
+      "epoch": 0.24561403508771928,
+      "grad_norm": 0.13739793002605438,
+      "learning_rate": 0.00019285714285714286,
+      "loss": 0.007,
+      "step": 7
+    },
+    {
+      "epoch": 0.2807017543859649,
+      "grad_norm": 0.073564812541008,
+      "learning_rate": 0.00019047619047619048,
+      "loss": 0.0038,
+      "step": 8
+    },
+    {
+      "epoch": 0.3157894736842105,
+      "grad_norm": 0.09854966402053833,
+      "learning_rate": 0.0001880952380952381,
+      "loss": 0.004,
+      "step": 9
+    },
+    {
+      "epoch": 0.3508771929824561,
+      "grad_norm": 0.07107563316822052,
+      "learning_rate": 0.00018571428571428572,
+      "loss": 0.0038,
+      "step": 10
+    },
+    {
+      "epoch": 0.38596491228070173,
+      "grad_norm": 0.062161125242710114,
+      "learning_rate": 0.00018333333333333334,
+      "loss": 0.0027,
+      "step": 11
+    },
+    {
+      "epoch": 0.42105263157894735,
+      "grad_norm": 0.07297360152006149,
+      "learning_rate": 0.00018095238095238095,
+      "loss": 0.0037,
+      "step": 12
+    },
+    {
+      "epoch": 0.45614035087719296,
+      "grad_norm": 0.09481006115674973,
+      "learning_rate": 0.0001785714285714286,
+      "loss": 0.0082,
+      "step": 13
+    },
+    {
+      "epoch": 0.49122807017543857,
+      "grad_norm": 0.15246650576591492,
+      "learning_rate": 0.0001761904761904762,
+      "loss": 0.0089,
+      "step": 14
+    },
+    {
+      "epoch": 0.5263157894736842,
+      "grad_norm": 0.09137029945850372,
+      "learning_rate": 0.00017380952380952383,
+      "loss": 0.0041,
+      "step": 15
+    },
+    {
+      "epoch": 0.5614035087719298,
+      "grad_norm": 0.12798666954040527,
+      "learning_rate": 0.00017142857142857143,
+      "loss": 0.0026,
+      "step": 16
+    },
+    {
+      "epoch": 0.5964912280701754,
+      "grad_norm": 0.1691877394914627,
+      "learning_rate": 0.00016904761904761904,
+      "loss": 0.0131,
+      "step": 17
+    },
+    {
+      "epoch": 0.631578947368421,
+      "grad_norm": 0.11234349757432938,
+      "learning_rate": 0.0001666666666666667,
+      "loss": 0.0085,
+      "step": 18
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 0.04114694893360138,
+      "learning_rate": 0.00016428571428571428,
+      "loss": 0.0029,
+      "step": 19
+    },
+    {
+      "epoch": 0.7017543859649122,
+      "grad_norm": 0.08836357295513153,
+      "learning_rate": 0.00016190476190476192,
+      "loss": 0.0041,
+      "step": 20
+    },
+    {
+      "epoch": 0.7368421052631579,
+      "grad_norm": 0.10266884416341782,
+      "learning_rate": 0.00015952380952380954,
+      "loss": 0.0057,
+      "step": 21
+    },
+    {
+      "epoch": 0.7719298245614035,
+      "grad_norm": 0.08742401748895645,
+      "learning_rate": 0.00015714285714285716,
+      "loss": 0.0061,
+      "step": 22
+    },
+    {
+      "epoch": 0.8070175438596491,
+      "grad_norm": 0.06542518734931946,
+      "learning_rate": 0.00015476190476190478,
+      "loss": 0.0059,
+      "step": 23
+    },
+    {
+      "epoch": 0.8421052631578947,
+      "grad_norm": 0.0995144322514534,
+      "learning_rate": 0.00015238095238095237,
+      "loss": 0.0041,
+      "step": 24
+    },
+    {
+      "epoch": 0.8771929824561403,
+      "grad_norm": 0.1686088740825653,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 0.0058,
+      "step": 25
+    },
+    {
+      "epoch": 0.9122807017543859,
+      "grad_norm": 0.11190295219421387,
+      "learning_rate": 0.00014761904761904763,
+      "loss": 0.0069,
+      "step": 26
+    },
+    {
+      "epoch": 0.9473684210526315,
+      "grad_norm": 0.13313594460487366,
+      "learning_rate": 0.00014523809523809525,
+      "loss": 0.0085,
+      "step": 27
+    },
+    {
+      "epoch": 0.9824561403508771,
+      "grad_norm": 0.0898401066660881,
+      "learning_rate": 0.00014285714285714287,
+      "loss": 0.0042,
+      "step": 28
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.050766751170158386,
+      "learning_rate": 0.00014047619047619049,
+      "loss": 0.0015,
+      "step": 29
+    },
+    {
+      "epoch": 1.0350877192982457,
+      "grad_norm": 0.06956154853105545,
+      "learning_rate": 0.0001380952380952381,
+      "loss": 0.0051,
+      "step": 30
+    },
+    {
+      "epoch": 1.0701754385964912,
+      "grad_norm": 0.06322275847196579,
+      "learning_rate": 0.00013571428571428572,
+      "loss": 0.0061,
+      "step": 31
+    },
+    {
+      "epoch": 1.1052631578947367,
+      "grad_norm": 0.03425135090947151,
+      "learning_rate": 0.00013333333333333334,
+      "loss": 0.0028,
+      "step": 32
+    },
+    {
+      "epoch": 1.1403508771929824,
+      "grad_norm": 0.09477324038743973,
+      "learning_rate": 0.00013095238095238096,
+      "loss": 0.0039,
+      "step": 33
+    },
+    {
+      "epoch": 1.1754385964912282,
+      "grad_norm": 0.049563754349946976,
+      "learning_rate": 0.00012857142857142858,
+      "loss": 0.0038,
+      "step": 34
+    },
+    {
+      "epoch": 1.2105263157894737,
+      "grad_norm": 0.05497609078884125,
+      "learning_rate": 0.0001261904761904762,
+      "loss": 0.0046,
+      "step": 35
+    },
+    {
+      "epoch": 1.2456140350877192,
+      "grad_norm": 0.12121907621622086,
+      "learning_rate": 0.0001238095238095238,
+      "loss": 0.0071,
+      "step": 36
+    },
+    {
+      "epoch": 1.280701754385965,
+      "grad_norm": 0.026673054322600365,
+      "learning_rate": 0.00012142857142857143,
+      "loss": 0.0017,
+      "step": 37
+    },
+    {
+      "epoch": 1.3157894736842106,
+      "grad_norm": 0.09272781759500504,
+      "learning_rate": 0.00011904761904761905,
+      "loss": 0.0067,
+      "step": 38
+    },
+    {
+      "epoch": 1.3508771929824561,
+      "grad_norm": 0.04980189725756645,
+      "learning_rate": 0.00011666666666666668,
+      "loss": 0.0037,
+      "step": 39
+    },
+    {
+      "epoch": 1.3859649122807016,
+      "grad_norm": 0.0377652607858181,
+      "learning_rate": 0.00011428571428571428,
+      "loss": 0.0025,
+      "step": 40
+    },
+    {
+      "epoch": 1.4210526315789473,
+      "grad_norm": 0.04286219924688339,
+      "learning_rate": 0.00011190476190476191,
+      "loss": 0.0028,
+      "step": 41
+    },
+    {
+      "epoch": 1.456140350877193,
+      "grad_norm": 0.04524603486061096,
+      "learning_rate": 0.00010952380952380953,
+      "loss": 0.0018,
+      "step": 42
+    },
+    {
+      "epoch": 1.4912280701754386,
+      "grad_norm": 0.15857696533203125,
+      "learning_rate": 0.00010714285714285715,
+      "loss": 0.0192,
+      "step": 43
+    },
+    {
+      "epoch": 1.526315789473684,
+      "grad_norm": 0.045452795922756195,
+      "learning_rate": 0.00010476190476190477,
+      "loss": 0.002,
+      "step": 44
+    },
+    {
+      "epoch": 1.5614035087719298,
+      "grad_norm": 0.06400217860937119,
+      "learning_rate": 0.00010238095238095237,
+      "loss": 0.0032,
+      "step": 45
+    },
+    {
+      "epoch": 1.5964912280701755,
+      "grad_norm": 0.024957947432994843,
+      "learning_rate": 0.0001,
+      "loss": 0.002,
+      "step": 46
+    },
+    {
+      "epoch": 1.631578947368421,
+      "grad_norm": 0.04150143265724182,
+      "learning_rate": 9.761904761904762e-05,
+      "loss": 0.0028,
+      "step": 47
+    },
+    {
+      "epoch": 1.6666666666666665,
+      "grad_norm": 0.0963282361626625,
+      "learning_rate": 9.523809523809524e-05,
+      "loss": 0.0053,
+      "step": 48
+    },
+    {
+      "epoch": 1.7017543859649122,
+      "grad_norm": 0.08165717869997025,
+      "learning_rate": 9.285714285714286e-05,
+      "loss": 0.0051,
+      "step": 49
+    },
+    {
+      "epoch": 1.736842105263158,
+      "grad_norm": 0.07597285509109497,
+      "learning_rate": 9.047619047619048e-05,
+      "loss": 0.0034,
+      "step": 50
+    },
+    {
+      "epoch": 1.7719298245614035,
+      "grad_norm": 0.08033040165901184,
+      "learning_rate": 8.80952380952381e-05,
+      "loss": 0.0056,
+      "step": 51
+    },
+    {
+      "epoch": 1.807017543859649,
+      "grad_norm": 0.04683045297861099,
+      "learning_rate": 8.571428571428571e-05,
+      "loss": 0.003,
+      "step": 52
+    },
+    {
+      "epoch": 1.8421052631578947,
+      "grad_norm": 0.07887265831232071,
+      "learning_rate": 8.333333333333334e-05,
+      "loss": 0.0035,
+      "step": 53
+    },
+    {
+      "epoch": 1.8771929824561404,
+      "grad_norm": 0.1161859855055809,
+      "learning_rate": 8.095238095238096e-05,
+      "loss": 0.005,
+      "step": 54
+    },
+    {
+      "epoch": 1.912280701754386,
+      "grad_norm": 0.05016123130917549,
+      "learning_rate": 7.857142857142858e-05,
+      "loss": 0.0027,
+      "step": 55
+    },
+    {
+      "epoch": 1.9473684210526314,
+      "grad_norm": 0.11343929171562195,
+      "learning_rate": 7.619047619047618e-05,
+      "loss": 0.0037,
+      "step": 56
+    },
+    {
+      "epoch": 1.9824561403508771,
+      "grad_norm": 0.03468641638755798,
+      "learning_rate": 7.380952380952382e-05,
+      "loss": 0.002,
+      "step": 57
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.028209766373038292,
+      "learning_rate": 7.142857142857143e-05,
+      "loss": 0.0009,
+      "step": 58
+    },
+    {
+      "epoch": 2.0350877192982457,
+      "grad_norm": 0.02228238247334957,
+      "learning_rate": 6.904761904761905e-05,
+      "loss": 0.0023,
+      "step": 59
+    },
+    {
+      "epoch": 2.0701754385964914,
+      "grad_norm": 0.05176170915365219,
+      "learning_rate": 6.666666666666667e-05,
+      "loss": 0.0022,
+      "step": 60
+    },
+    {
+      "epoch": 2.1052631578947367,
+      "grad_norm": 0.08067404478788376,
+      "learning_rate": 6.428571428571429e-05,
+      "loss": 0.0035,
+      "step": 61
+    },
+    {
+      "epoch": 2.1403508771929824,
+      "grad_norm": 0.024810029193758965,
+      "learning_rate": 6.19047619047619e-05,
+      "loss": 0.0016,
+      "step": 62
+    },
+    {
+      "epoch": 2.175438596491228,
+      "grad_norm": 0.08523717522621155,
+      "learning_rate": 5.9523809523809524e-05,
+      "loss": 0.0036,
+      "step": 63
+    },
+    {
+      "epoch": 2.2105263157894735,
+      "grad_norm": 0.08478069305419922,
+      "learning_rate": 5.714285714285714e-05,
+      "loss": 0.0032,
+      "step": 64
+    },
+    {
+      "epoch": 2.245614035087719,
+      "grad_norm": 0.019477397203445435,
+      "learning_rate": 5.4761904761904766e-05,
+      "loss": 0.0024,
+      "step": 65
+    },
+    {
+      "epoch": 2.280701754385965,
+      "grad_norm": 0.0420527420938015,
+      "learning_rate": 5.2380952380952384e-05,
+      "loss": 0.0027,
+      "step": 66
+    },
+    {
+      "epoch": 2.3157894736842106,
+      "grad_norm": 0.05265393853187561,
+      "learning_rate": 5e-05,
+      "loss": 0.0025,
+      "step": 67
+    },
+    {
+      "epoch": 2.3508771929824563,
+      "grad_norm": 0.08029446750879288,
+      "learning_rate": 4.761904761904762e-05,
+      "loss": 0.0028,
+      "step": 68
+    },
+    {
+      "epoch": 2.3859649122807016,
+      "grad_norm": 0.06714743375778198,
+      "learning_rate": 4.523809523809524e-05,
+      "loss": 0.0026,
+      "step": 69
+    },
+    {
+      "epoch": 2.4210526315789473,
+      "grad_norm": 0.07133755087852478,
+      "learning_rate": 4.2857142857142856e-05,
+      "loss": 0.0048,
+      "step": 70
+    },
+    {
+      "epoch": 2.456140350877193,
+      "grad_norm": 0.015778280794620514,
+      "learning_rate": 4.047619047619048e-05,
+      "loss": 0.0013,
+      "step": 71
+    },
+    {
+      "epoch": 2.4912280701754383,
+      "grad_norm": 0.03038935363292694,
+      "learning_rate": 3.809523809523809e-05,
+      "loss": 0.0026,
+      "step": 72
+    },
+    {
+      "epoch": 2.526315789473684,
+      "grad_norm": 0.07423048466444016,
+      "learning_rate": 3.571428571428572e-05,
+      "loss": 0.0051,
+      "step": 73
+    },
+    {
+      "epoch": 2.56140350877193,
+      "grad_norm": 0.06572224199771881,
+      "learning_rate": 3.3333333333333335e-05,
+      "loss": 0.0016,
+      "step": 74
+    },
+    {
+      "epoch": 2.5964912280701755,
+      "grad_norm": 0.09695594757795334,
+      "learning_rate": 3.095238095238095e-05,
+      "loss": 0.0012,
+      "step": 75
+    },
+    {
+      "epoch": 2.6315789473684212,
+      "grad_norm": 0.011839903891086578,
+      "learning_rate": 2.857142857142857e-05,
+      "loss": 0.001,
+      "step": 76
+    },
+    {
+      "epoch": 2.6666666666666665,
+      "grad_norm": 0.015379734337329865,
+      "learning_rate": 2.6190476190476192e-05,
+      "loss": 0.0019,
+      "step": 77
+    },
+    {
+      "epoch": 2.7017543859649122,
+      "grad_norm": 0.025853777304291725,
+      "learning_rate": 2.380952380952381e-05,
+      "loss": 0.0009,
+      "step": 78
+    },
+    {
+      "epoch": 2.736842105263158,
+      "grad_norm": 0.06937374174594879,
+      "learning_rate": 2.1428571428571428e-05,
+      "loss": 0.0017,
+      "step": 79
+    },
+    {
+      "epoch": 2.7719298245614032,
+      "grad_norm": 0.023749876767396927,
+      "learning_rate": 1.9047619047619046e-05,
+      "loss": 0.0014,
+      "step": 80
+    },
+    {
+      "epoch": 2.807017543859649,
+      "grad_norm": 0.01632499136030674,
+      "learning_rate": 1.6666666666666667e-05,
+      "loss": 0.0018,
+      "step": 81
+    },
+    {
+      "epoch": 2.8421052631578947,
+      "grad_norm": 0.019440138712525368,
+      "learning_rate": 1.4285714285714285e-05,
+      "loss": 0.0016,
+      "step": 82
+    },
+    {
+      "epoch": 2.8771929824561404,
+      "grad_norm": 0.04011471942067146,
+      "learning_rate": 1.1904761904761905e-05,
+      "loss": 0.0029,
+      "step": 83
+    },
+    {
+      "epoch": 2.912280701754386,
+      "grad_norm": 0.02127029560506344,
+      "learning_rate": 9.523809523809523e-06,
+      "loss": 0.0016,
+      "step": 84
+    },
+    {
+      "epoch": 2.9473684210526314,
+      "grad_norm": 0.013040756806731224,
+      "learning_rate": 7.142857142857143e-06,
+      "loss": 0.0019,
+      "step": 85
+    },
+    {
+      "epoch": 2.982456140350877,
+      "grad_norm": 0.01978246122598648,
+      "learning_rate": 4.7619047619047615e-06,
+      "loss": 0.0013,
+      "step": 86
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.015681693330407143,
+      "learning_rate": 2.3809523809523808e-06,
+      "loss": 0.0005,
+      "step": 87
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 87,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.738355493837824e+16,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

outputs/checkpoint-87/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f0ccf889cbd530606222de25955500111140231327241d36e46bd2014c7e7ea
+size 5688

unsloth_compiled_cache/__pycache__/UnslothDPOTrainer.cpython-311.pyc

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:908e85fce08f1df14d743b81521cf3d9e8f238f61ec19fcf6b1a83c0a0d59e8c
+oid sha256:516f74f609708808fda3c2feba2baceee4114016040c7803ad428f64096f0158
 size 120027

unsloth_compiled_cache/__pycache__/UnslothGRPOTrainer.cpython-311.pyc

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37f03ddd4b2c46371b49b471617fcadb7fa3e286338c02bc0934ee29d37c37e2
+oid sha256:d43407db88b5d97a4ea9503e75337e958ebb1ad3aeb5ce0616c6a4ecae63dabd
 size 130267