Upload folder using huggingface_hub

checkpoint-150/README.md

@@ -0,0 +1,202 @@
+---
+base_model: unsloth/qwen2.5-3b-bnb-4bit
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.14.0

checkpoint-150/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "unsloth/qwen2.5-3b-bnb-4bit",
+  "bias": "none",
+  "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": 8,
+  "lora_bias": false,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "o_proj",
+    "v_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-150/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d677ee422d7d952d82e155501d8cedf29701adb2bc408cddedcd4a2effc7a9b
+size 59021064

checkpoint-150/added_tokens.json

@@ -0,0 +1,25 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|PAD_TOKEN|>": 151665,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

checkpoint-150/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44a7c8de71650802e9962c5585657526f55438d992b89e4f9c1d9b9076e1490e
+size 30290452

checkpoint-150/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8abf2c3a2d675d09f86f31a4bbaac529a18147ee9c2568ece2b0294dff92a441
+size 14244

checkpoint-150/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f35320c42144c7251b9b46e1825ad1d96489c18d4a0a4f57d23b19abb29d8223
+size 1064

checkpoint-150/special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|PAD_TOKEN|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-150/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eaa46ac5142907d0036d00b99940ae991dbf7e4dc1026d70b5d786d2f672592e
+size 11422353

checkpoint-150/tokenizer_config.json

@@ -0,0 +1,216 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<|PAD_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 32768,
+  "pad_token": "<|PAD_TOKEN|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-150/trainer_state.json

@@ -0,0 +1,1083 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.2631939684715556,
+  "eval_steps": 500,
+  "global_step": 150,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02193283070596299,
+      "grad_norm": 0.4870755076408386,
+      "learning_rate": 8.695652173913044e-07,
+      "loss": 2.9525,
+      "step": 1
+    },
+    {
+      "epoch": 0.04386566141192598,
+      "grad_norm": 0.35328975319862366,
+      "learning_rate": 1.7391304347826088e-06,
+      "loss": 2.8102,
+      "step": 2
+    },
+    {
+      "epoch": 0.06579849211788896,
+      "grad_norm": 0.4670841097831726,
+      "learning_rate": 2.6086956521739132e-06,
+      "loss": 2.8848,
+      "step": 3
+    },
+    {
+      "epoch": 0.08773132282385196,
+      "grad_norm": 0.6589818000793457,
+      "learning_rate": 3.4782608695652175e-06,
+      "loss": 3.0569,
+      "step": 4
+    },
+    {
+      "epoch": 0.10966415352981494,
+      "grad_norm": 0.47537556290626526,
+      "learning_rate": 4.347826086956522e-06,
+      "loss": 2.8093,
+      "step": 5
+    },
+    {
+      "epoch": 0.13159698423577793,
+      "grad_norm": 0.6465238928794861,
+      "learning_rate": 5.2173913043478265e-06,
+      "loss": 3.06,
+      "step": 6
+    },
+    {
+      "epoch": 0.15352981494174092,
+      "grad_norm": 0.4992265999317169,
+      "learning_rate": 6.086956521739132e-06,
+      "loss": 2.98,
+      "step": 7
+    },
+    {
+      "epoch": 0.17546264564770392,
+      "grad_norm": 0.5841557383537292,
+      "learning_rate": 6.956521739130435e-06,
+      "loss": 2.9831,
+      "step": 8
+    },
+    {
+      "epoch": 0.1973954763536669,
+      "grad_norm": 0.41789695620536804,
+      "learning_rate": 7.82608695652174e-06,
+      "loss": 2.8239,
+      "step": 9
+    },
+    {
+      "epoch": 0.21932830705962988,
+      "grad_norm": 0.43609240651130676,
+      "learning_rate": 8.695652173913044e-06,
+      "loss": 2.8341,
+      "step": 10
+    },
+    {
+      "epoch": 0.24126113776559288,
+      "grad_norm": 0.3185977041721344,
+      "learning_rate": 9.565217391304349e-06,
+      "loss": 2.7383,
+      "step": 11
+    },
+    {
+      "epoch": 0.26319396847155585,
+      "grad_norm": 0.43681928515434265,
+      "learning_rate": 1.0434782608695653e-05,
+      "loss": 2.9235,
+      "step": 12
+    },
+    {
+      "epoch": 0.2851267991775189,
+      "grad_norm": 0.3825719952583313,
+      "learning_rate": 1.1304347826086957e-05,
+      "loss": 2.6964,
+      "step": 13
+    },
+    {
+      "epoch": 0.30705962988348184,
+      "grad_norm": 0.5028628706932068,
+      "learning_rate": 1.2173913043478263e-05,
+      "loss": 2.8067,
+      "step": 14
+    },
+    {
+      "epoch": 0.3289924605894448,
+      "grad_norm": 0.5002133846282959,
+      "learning_rate": 1.3043478260869566e-05,
+      "loss": 2.8252,
+      "step": 15
+    },
+    {
+      "epoch": 0.35092529129540784,
+      "grad_norm": 0.3002101182937622,
+      "learning_rate": 1.391304347826087e-05,
+      "loss": 2.7313,
+      "step": 16
+    },
+    {
+      "epoch": 0.3728581220013708,
+      "grad_norm": 0.4624859392642975,
+      "learning_rate": 1.4782608695652174e-05,
+      "loss": 2.7972,
+      "step": 17
+    },
+    {
+      "epoch": 0.3947909527073338,
+      "grad_norm": 0.57045578956604,
+      "learning_rate": 1.565217391304348e-05,
+      "loss": 3.0034,
+      "step": 18
+    },
+    {
+      "epoch": 0.4167237834132968,
+      "grad_norm": 0.4259621500968933,
+      "learning_rate": 1.6521739130434785e-05,
+      "loss": 2.8309,
+      "step": 19
+    },
+    {
+      "epoch": 0.43865661411925977,
+      "grad_norm": 0.46009618043899536,
+      "learning_rate": 1.739130434782609e-05,
+      "loss": 2.8408,
+      "step": 20
+    },
+    {
+      "epoch": 0.46058944482522274,
+      "grad_norm": 0.5475765466690063,
+      "learning_rate": 1.8260869565217393e-05,
+      "loss": 2.8943,
+      "step": 21
+    },
+    {
+      "epoch": 0.48252227553118576,
+      "grad_norm": 0.7618455290794373,
+      "learning_rate": 1.9130434782608697e-05,
+      "loss": 2.9959,
+      "step": 22
+    },
+    {
+      "epoch": 0.5044551062371487,
+      "grad_norm": 0.6684309840202332,
+      "learning_rate": 2e-05,
+      "loss": 2.9095,
+      "step": 23
+    },
+    {
+      "epoch": 0.5263879369431117,
+      "grad_norm": 0.545538604259491,
+      "learning_rate": 1.9999729347501484e-05,
+      "loss": 2.8353,
+      "step": 24
+    },
+    {
+      "epoch": 0.5483207676490747,
+      "grad_norm": 0.6128362417221069,
+      "learning_rate": 1.9998917404656488e-05,
+      "loss": 2.8127,
+      "step": 25
+    },
+    {
+      "epoch": 0.5702535983550377,
+      "grad_norm": 0.7084450125694275,
+      "learning_rate": 1.9997564215415886e-05,
+      "loss": 2.9335,
+      "step": 26
+    },
+    {
+      "epoch": 0.5921864290610007,
+      "grad_norm": 0.5246658325195312,
+      "learning_rate": 1.9995669853028485e-05,
+      "loss": 2.8186,
+      "step": 27
+    },
+    {
+      "epoch": 0.6141192597669637,
+      "grad_norm": 0.7249352335929871,
+      "learning_rate": 1.9993234420037072e-05,
+      "loss": 2.8336,
+      "step": 28
+    },
+    {
+      "epoch": 0.6360520904729267,
+      "grad_norm": 0.5946571826934814,
+      "learning_rate": 1.999025804827285e-05,
+      "loss": 2.8233,
+      "step": 29
+    },
+    {
+      "epoch": 0.6579849211788896,
+      "grad_norm": 0.42332401871681213,
+      "learning_rate": 1.9986740898848306e-05,
+      "loss": 2.7259,
+      "step": 30
+    },
+    {
+      "epoch": 0.6799177518848526,
+      "grad_norm": 0.9102485775947571,
+      "learning_rate": 1.99826831621485e-05,
+      "loss": 2.9075,
+      "step": 31
+    },
+    {
+      "epoch": 0.7018505825908157,
+      "grad_norm": 0.6430304646492004,
+      "learning_rate": 1.997808505782075e-05,
+      "loss": 2.9084,
+      "step": 32
+    },
+    {
+      "epoch": 0.7237834132967786,
+      "grad_norm": 0.5709037780761719,
+      "learning_rate": 1.9972946834762732e-05,
+      "loss": 2.8107,
+      "step": 33
+    },
+    {
+      "epoch": 0.7457162440027416,
+      "grad_norm": 0.49835285544395447,
+      "learning_rate": 1.9967268771109037e-05,
+      "loss": 2.7338,
+      "step": 34
+    },
+    {
+      "epoch": 0.7676490747087046,
+      "grad_norm": 0.5714299082756042,
+      "learning_rate": 1.996105117421608e-05,
+      "loss": 2.7816,
+      "step": 35
+    },
+    {
+      "epoch": 0.7895819054146676,
+      "grad_norm": 0.48475122451782227,
+      "learning_rate": 1.9954294380645497e-05,
+      "loss": 2.7685,
+      "step": 36
+    },
+    {
+      "epoch": 0.8115147361206305,
+      "grad_norm": 0.5309097766876221,
+      "learning_rate": 1.9946998756145894e-05,
+      "loss": 2.7778,
+      "step": 37
+    },
+    {
+      "epoch": 0.8334475668265936,
+      "grad_norm": 0.45952990651130676,
+      "learning_rate": 1.9939164695633067e-05,
+      "loss": 2.7954,
+      "step": 38
+    },
+    {
+      "epoch": 0.8553803975325566,
+      "grad_norm": 0.48351016640663147,
+      "learning_rate": 1.9930792623168638e-05,
+      "loss": 2.6792,
+      "step": 39
+    },
+    {
+      "epoch": 0.8773132282385195,
+      "grad_norm": 0.4013523459434509,
+      "learning_rate": 1.992188299193706e-05,
+      "loss": 2.7983,
+      "step": 40
+    },
+    {
+      "epoch": 0.8992460589444825,
+      "grad_norm": 0.318466454744339,
+      "learning_rate": 1.9912436284221134e-05,
+      "loss": 2.5984,
+      "step": 41
+    },
+    {
+      "epoch": 0.9211788896504455,
+      "grad_norm": 0.3661440908908844,
+      "learning_rate": 1.9902453011375865e-05,
+      "loss": 2.8038,
+      "step": 42
+    },
+    {
+      "epoch": 0.9431117203564084,
+      "grad_norm": 0.4626653790473938,
+      "learning_rate": 1.98919337138008e-05,
+      "loss": 2.7242,
+      "step": 43
+    },
+    {
+      "epoch": 0.9650445510623715,
+      "grad_norm": 0.30195215344429016,
+      "learning_rate": 1.9880878960910772e-05,
+      "loss": 2.6637,
+      "step": 44
+    },
+    {
+      "epoch": 0.9869773817683345,
+      "grad_norm": 0.40314823389053345,
+      "learning_rate": 1.9869289351105087e-05,
+      "loss": 2.7072,
+      "step": 45
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.4138323962688446,
+      "learning_rate": 1.9857165511735105e-05,
+      "loss": 2.6019,
+      "step": 46
+    },
+    {
+      "epoch": 1.021932830705963,
+      "grad_norm": 0.29498204588890076,
+      "learning_rate": 1.9844508099070313e-05,
+      "loss": 2.5943,
+      "step": 47
+    },
+    {
+      "epoch": 1.043865661411926,
+      "grad_norm": 0.29517868161201477,
+      "learning_rate": 1.9831317798262787e-05,
+      "loss": 2.6963,
+      "step": 48
+    },
+    {
+      "epoch": 1.065798492117889,
+      "grad_norm": 0.29591700434684753,
+      "learning_rate": 1.98175953233101e-05,
+      "loss": 2.7676,
+      "step": 49
+    },
+    {
+      "epoch": 1.0877313228238519,
+      "grad_norm": 0.2561758756637573,
+      "learning_rate": 1.980334141701667e-05,
+      "loss": 2.629,
+      "step": 50
+    },
+    {
+      "epoch": 1.1096641535298148,
+      "grad_norm": 0.2604333460330963,
+      "learning_rate": 1.978855685095358e-05,
+      "loss": 2.7115,
+      "step": 51
+    },
+    {
+      "epoch": 1.1315969842357778,
+      "grad_norm": 0.4252321422100067,
+      "learning_rate": 1.977324242541677e-05,
+      "loss": 2.6442,
+      "step": 52
+    },
+    {
+      "epoch": 1.153529814941741,
+      "grad_norm": 0.23818732798099518,
+      "learning_rate": 1.9757398969383752e-05,
+      "loss": 2.7172,
+      "step": 53
+    },
+    {
+      "epoch": 1.175462645647704,
+      "grad_norm": 0.16449472308158875,
+      "learning_rate": 1.974102734046872e-05,
+      "loss": 2.6405,
+      "step": 54
+    },
+    {
+      "epoch": 1.197395476353667,
+      "grad_norm": 0.25156456232070923,
+      "learning_rate": 1.9724128424876117e-05,
+      "loss": 2.6376,
+      "step": 55
+    },
+    {
+      "epoch": 1.21932830705963,
+      "grad_norm": 0.1786828637123108,
+      "learning_rate": 1.9706703137352695e-05,
+      "loss": 2.5754,
+      "step": 56
+    },
+    {
+      "epoch": 1.2412611377655929,
+      "grad_norm": 0.21457381546497345,
+      "learning_rate": 1.968875242113798e-05,
+      "loss": 2.6309,
+      "step": 57
+    },
+    {
+      "epoch": 1.2631939684715559,
+      "grad_norm": 0.16352739930152893,
+      "learning_rate": 1.9670277247913205e-05,
+      "loss": 2.5966,
+      "step": 58
+    },
+    {
+      "epoch": 1.2851267991775188,
+      "grad_norm": 0.19751280546188354,
+      "learning_rate": 1.965127861774873e-05,
+      "loss": 2.7516,
+      "step": 59
+    },
+    {
+      "epoch": 1.3070596298834818,
+      "grad_norm": 0.14813798666000366,
+      "learning_rate": 1.96317575590499e-05,
+      "loss": 2.6464,
+      "step": 60
+    },
+    {
+      "epoch": 1.3289924605894448,
+      "grad_norm": 0.15344278514385223,
+      "learning_rate": 1.9611715128501378e-05,
+      "loss": 2.7081,
+      "step": 61
+    },
+    {
+      "epoch": 1.350925291295408,
+      "grad_norm": 0.1399158239364624,
+      "learning_rate": 1.9591152411009942e-05,
+      "loss": 2.6382,
+      "step": 62
+    },
+    {
+      "epoch": 1.3728581220013707,
+      "grad_norm": 0.1705392748117447,
+      "learning_rate": 1.9570070519645767e-05,
+      "loss": 2.6442,
+      "step": 63
+    },
+    {
+      "epoch": 1.3947909527073339,
+      "grad_norm": 0.16903157532215118,
+      "learning_rate": 1.9548470595582166e-05,
+      "loss": 2.5898,
+      "step": 64
+    },
+    {
+      "epoch": 1.4167237834132969,
+      "grad_norm": 0.13648824393749237,
+      "learning_rate": 1.9526353808033827e-05,
+      "loss": 2.5725,
+      "step": 65
+    },
+    {
+      "epoch": 1.4386566141192598,
+      "grad_norm": 0.129099041223526,
+      "learning_rate": 1.9503721354193507e-05,
+      "loss": 2.6863,
+      "step": 66
+    },
+    {
+      "epoch": 1.4605894448252228,
+      "grad_norm": 0.12659573554992676,
+      "learning_rate": 1.948057445916724e-05,
+      "loss": 2.6224,
+      "step": 67
+    },
+    {
+      "epoch": 1.4825222755311858,
+      "grad_norm": 0.1909603327512741,
+      "learning_rate": 1.9456914375908026e-05,
+      "loss": 2.6401,
+      "step": 68
+    },
+    {
+      "epoch": 1.5044551062371487,
+      "grad_norm": 0.25878530740737915,
+      "learning_rate": 1.9432742385147988e-05,
+      "loss": 2.6704,
+      "step": 69
+    },
+    {
+      "epoch": 1.5263879369431117,
+      "grad_norm": 0.13662640750408173,
+      "learning_rate": 1.9408059795329073e-05,
+      "loss": 2.6154,
+      "step": 70
+    },
+    {
+      "epoch": 1.5483207676490747,
+      "grad_norm": 0.13560184836387634,
+      "learning_rate": 1.9382867942532195e-05,
+      "loss": 2.6227,
+      "step": 71
+    },
+    {
+      "epoch": 1.5702535983550376,
+      "grad_norm": 0.1390749216079712,
+      "learning_rate": 1.9357168190404937e-05,
+      "loss": 2.6884,
+      "step": 72
+    },
+    {
+      "epoch": 1.5921864290610008,
+      "grad_norm": 0.12690310180187225,
+      "learning_rate": 1.9330961930087724e-05,
+      "loss": 2.674,
+      "step": 73
+    },
+    {
+      "epoch": 1.6141192597669636,
+      "grad_norm": 0.09753144532442093,
+      "learning_rate": 1.9304250580138524e-05,
+      "loss": 2.6209,
+      "step": 74
+    },
+    {
+      "epoch": 1.6360520904729268,
+      "grad_norm": 0.12032578140497208,
+      "learning_rate": 1.9277035586456056e-05,
+      "loss": 2.6915,
+      "step": 75
+    },
+    {
+      "epoch": 1.6579849211788895,
+      "grad_norm": 0.16928426921367645,
+      "learning_rate": 1.9249318422201524e-05,
+      "loss": 2.6132,
+      "step": 76
+    },
+    {
+      "epoch": 1.6799177518848527,
+      "grad_norm": 0.09693765640258789,
+      "learning_rate": 1.9221100587718884e-05,
+      "loss": 2.6633,
+      "step": 77
+    },
+    {
+      "epoch": 1.7018505825908157,
+      "grad_norm": 0.16512952744960785,
+      "learning_rate": 1.919238361045362e-05,
+      "loss": 2.6585,
+      "step": 78
+    },
+    {
+      "epoch": 1.7237834132967786,
+      "grad_norm": 0.14026080071926117,
+      "learning_rate": 1.916316904487005e-05,
+      "loss": 2.7693,
+      "step": 79
+    },
+    {
+      "epoch": 1.7457162440027416,
+      "grad_norm": 0.14885276556015015,
+      "learning_rate": 1.9133458472367216e-05,
+      "loss": 2.7144,
+      "step": 80
+    },
+    {
+      "epoch": 1.7676490747087046,
+      "grad_norm": 0.11436336487531662,
+      "learning_rate": 1.9103253501193256e-05,
+      "loss": 2.5687,
+      "step": 81
+    },
+    {
+      "epoch": 1.7895819054146676,
+      "grad_norm": 0.24450720846652985,
+      "learning_rate": 1.9072555766358346e-05,
+      "loss": 2.5209,
+      "step": 82
+    },
+    {
+      "epoch": 1.8115147361206305,
+      "grad_norm": 0.19669459760189056,
+      "learning_rate": 1.904136692954622e-05,
+      "loss": 2.5729,
+      "step": 83
+    },
+    {
+      "epoch": 1.8334475668265937,
+      "grad_norm": 0.1368049532175064,
+      "learning_rate": 1.900968867902419e-05,
+      "loss": 2.6268,
+      "step": 84
+    },
+    {
+      "epoch": 1.8553803975325565,
+      "grad_norm": 0.1277005970478058,
+      "learning_rate": 1.89775227295518e-05,
+      "loss": 2.6601,
+      "step": 85
+    },
+    {
+      "epoch": 1.8773132282385196,
+      "grad_norm": 0.09511096775531769,
+      "learning_rate": 1.8944870822287957e-05,
+      "loss": 2.5918,
+      "step": 86
+    },
+    {
+      "epoch": 1.8992460589444824,
+      "grad_norm": 0.06676003336906433,
+      "learning_rate": 1.891173472469672e-05,
+      "loss": 2.5671,
+      "step": 87
+    },
+    {
+      "epoch": 1.9211788896504456,
+      "grad_norm": 0.13803276419639587,
+      "learning_rate": 1.8878116230451615e-05,
+      "loss": 2.6257,
+      "step": 88
+    },
+    {
+      "epoch": 1.9431117203564083,
+      "grad_norm": 0.10050716996192932,
+      "learning_rate": 1.884401715933853e-05,
+      "loss": 2.6772,
+      "step": 89
+    },
+    {
+      "epoch": 1.9650445510623715,
+      "grad_norm": 0.1283024400472641,
+      "learning_rate": 1.8809439357157226e-05,
+      "loss": 2.6121,
+      "step": 90
+    },
+    {
+      "epoch": 1.9869773817683345,
+      "grad_norm": 0.13763798773288727,
+      "learning_rate": 1.8774384695621407e-05,
+      "loss": 2.568,
+      "step": 91
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.22271642088890076,
+      "learning_rate": 1.8738855072257428e-05,
+      "loss": 2.5865,
+      "step": 92
+    },
+    {
+      "epoch": 2.021932830705963,
+      "grad_norm": 0.11131051927804947,
+      "learning_rate": 1.8702852410301556e-05,
+      "loss": 2.5144,
+      "step": 93
+    },
+    {
+      "epoch": 2.043865661411926,
+      "grad_norm": 0.11161550134420395,
+      "learning_rate": 1.8666378658595863e-05,
+      "loss": 2.5182,
+      "step": 94
+    },
+    {
+      "epoch": 2.065798492117889,
+      "grad_norm": 0.08552844822406769,
+      "learning_rate": 1.8629435791482765e-05,
+      "loss": 2.6402,
+      "step": 95
+    },
+    {
+      "epoch": 2.087731322823852,
+      "grad_norm": 0.11428907513618469,
+      "learning_rate": 1.8592025808698116e-05,
+      "loss": 2.6265,
+      "step": 96
+    },
+    {
+      "epoch": 2.109664153529815,
+      "grad_norm": 0.09980299323797226,
+      "learning_rate": 1.8554150735262975e-05,
+      "loss": 2.623,
+      "step": 97
+    },
+    {
+      "epoch": 2.131596984235778,
+      "grad_norm": 0.08849837630987167,
+      "learning_rate": 1.8515812621373998e-05,
+      "loss": 2.627,
+      "step": 98
+    },
+    {
+      "epoch": 2.153529814941741,
+      "grad_norm": 0.09756634384393692,
+      "learning_rate": 1.8477013542292446e-05,
+      "loss": 2.6233,
+      "step": 99
+    },
+    {
+      "epoch": 2.1754626456477038,
+      "grad_norm": 0.07598986476659775,
+      "learning_rate": 1.8437755598231857e-05,
+      "loss": 2.6633,
+      "step": 100
+    },
+    {
+      "epoch": 2.197395476353667,
+      "grad_norm": 0.18077166378498077,
+      "learning_rate": 1.8398040914244363e-05,
+      "loss": 2.6253,
+      "step": 101
+    },
+    {
+      "epoch": 2.2193283070596297,
+      "grad_norm": 0.14006111025810242,
+      "learning_rate": 1.8357871640105648e-05,
+      "loss": 2.6086,
+      "step": 102
+    },
+    {
+      "epoch": 2.241261137765593,
+      "grad_norm": 0.08927474915981293,
+      "learning_rate": 1.8317249950198598e-05,
+      "loss": 2.4877,
+      "step": 103
+    },
+    {
+      "epoch": 2.2631939684715556,
+      "grad_norm": 0.08106345683336258,
+      "learning_rate": 1.8276178043395588e-05,
+      "loss": 2.6523,
+      "step": 104
+    },
+    {
+      "epoch": 2.285126799177519,
+      "grad_norm": 0.09083954989910126,
+      "learning_rate": 1.8234658142939454e-05,
+      "loss": 2.6456,
+      "step": 105
+    },
+    {
+      "epoch": 2.307059629883482,
+      "grad_norm": 0.07053636014461517,
+      "learning_rate": 1.8192692496323158e-05,
+      "loss": 2.6306,
+      "step": 106
+    },
+    {
+      "epoch": 2.3289924605894448,
+      "grad_norm": 0.06668028235435486,
+      "learning_rate": 1.8150283375168112e-05,
+      "loss": 2.5175,
+      "step": 107
+    },
+    {
+      "epoch": 2.350925291295408,
+      "grad_norm": 0.13295046985149384,
+      "learning_rate": 1.8107433075101254e-05,
+      "loss": 2.473,
+      "step": 108
+    },
+    {
+      "epoch": 2.3728581220013707,
+      "grad_norm": 0.09093775600194931,
+      "learning_rate": 1.8064143915630723e-05,
+      "loss": 2.547,
+      "step": 109
+    },
+    {
+      "epoch": 2.394790952707334,
+      "grad_norm": 0.18302415311336517,
+      "learning_rate": 1.8020418240020362e-05,
+      "loss": 2.5652,
+      "step": 110
+    },
+    {
+      "epoch": 2.4167237834132966,
+      "grad_norm": 0.07250549644231796,
+      "learning_rate": 1.7976258415162836e-05,
+      "loss": 2.5828,
+      "step": 111
+    },
+    {
+      "epoch": 2.43865661411926,
+      "grad_norm": 0.3828829526901245,
+      "learning_rate": 1.7931666831451536e-05,
+      "loss": 2.5063,
+      "step": 112
+    },
+    {
+      "epoch": 2.4605894448252226,
+      "grad_norm": 0.5052575469017029,
+      "learning_rate": 1.7886645902651166e-05,
+      "loss": 2.6184,
+      "step": 113
+    },
+    {
+      "epoch": 2.4825222755311858,
+      "grad_norm": 0.07245208323001862,
+      "learning_rate": 1.7841198065767107e-05,
+      "loss": 2.5883,
+      "step": 114
+    },
+    {
+      "epoch": 2.504455106237149,
+      "grad_norm": 0.05822201445698738,
+      "learning_rate": 1.779532578091347e-05,
+      "loss": 2.6,
+      "step": 115
+    },
+    {
+      "epoch": 2.5263879369431117,
+      "grad_norm": 0.08909498155117035,
+      "learning_rate": 1.7749031531179962e-05,
+      "loss": 2.549,
+      "step": 116
+    },
+    {
+      "epoch": 2.5483207676490744,
+      "grad_norm": 0.07801003754138947,
+      "learning_rate": 1.7702317822497457e-05,
+      "loss": 2.5591,
+      "step": 117
+    },
+    {
+      "epoch": 2.5702535983550376,
+      "grad_norm": 0.2434745877981186,
+      "learning_rate": 1.7655187183502344e-05,
+      "loss": 2.6557,
+      "step": 118
+    },
+    {
+      "epoch": 2.592186429061001,
+      "grad_norm": 0.06782998889684677,
+      "learning_rate": 1.7607642165399665e-05,
+      "loss": 2.5268,
+      "step": 119
+    },
+    {
+      "epoch": 2.6141192597669636,
+      "grad_norm": 0.0920061469078064,
+      "learning_rate": 1.755968534182501e-05,
+      "loss": 2.5052,
+      "step": 120
+    },
+    {
+      "epoch": 2.6360520904729268,
+      "grad_norm": 0.0655408501625061,
+      "learning_rate": 1.7511319308705198e-05,
+      "loss": 2.5784,
+      "step": 121
+    },
+    {
+      "epoch": 2.6579849211788895,
+      "grad_norm": 0.13081596791744232,
+      "learning_rate": 1.746254668411778e-05,
+      "loss": 2.5305,
+      "step": 122
+    },
+    {
+      "epoch": 2.6799177518848527,
+      "grad_norm": 0.3778601884841919,
+      "learning_rate": 1.7413370108149288e-05,
+      "loss": 2.5846,
+      "step": 123
+    },
+    {
+      "epoch": 2.701850582590816,
+      "grad_norm": 0.07771953195333481,
+      "learning_rate": 1.7363792242752354e-05,
+      "loss": 2.563,
+      "step": 124
+    },
+    {
+      "epoch": 2.7237834132967786,
+      "grad_norm": 0.06316570937633514,
+      "learning_rate": 1.731381577160161e-05,
+      "loss": 2.5705,
+      "step": 125
+    },
+    {
+      "epoch": 2.7457162440027414,
+      "grad_norm": 0.10998786240816116,
+      "learning_rate": 1.726344339994841e-05,
+      "loss": 2.6364,
+      "step": 126
+    },
+    {
+      "epoch": 2.7676490747087046,
+      "grad_norm": 0.08724892884492874,
+      "learning_rate": 1.7212677854474402e-05,
+      "loss": 2.4682,
+      "step": 127
+    },
+    {
+      "epoch": 2.7895819054146678,
+      "grad_norm": 0.10323834419250488,
+      "learning_rate": 1.7161521883143936e-05,
+      "loss": 2.6225,
+      "step": 128
+    },
+    {
+      "epoch": 2.8115147361206305,
+      "grad_norm": 0.07787463814020157,
+      "learning_rate": 1.7109978255055295e-05,
+      "loss": 2.5786,
+      "step": 129
+    },
+    {
+      "epoch": 2.8334475668265937,
+      "grad_norm": 0.07260199636220932,
+      "learning_rate": 1.705804976029083e-05,
+      "loss": 2.678,
+      "step": 130
+    },
+    {
+      "epoch": 2.8553803975325565,
+      "grad_norm": 0.07246023416519165,
+      "learning_rate": 1.7005739209765906e-05,
+      "loss": 2.4259,
+      "step": 131
+    },
+    {
+      "epoch": 2.8773132282385196,
+      "grad_norm": 0.09231323003768921,
+      "learning_rate": 1.6953049435076768e-05,
+      "loss": 2.6071,
+      "step": 132
+    },
+    {
+      "epoch": 2.8992460589444824,
+      "grad_norm": 0.08409086614847183,
+      "learning_rate": 1.6899983288347248e-05,
+      "loss": 2.4503,
+      "step": 133
+    },
+    {
+      "epoch": 2.9211788896504456,
+      "grad_norm": 0.10303400456905365,
+      "learning_rate": 1.6846543642074382e-05,
+      "loss": 2.5125,
+      "step": 134
+    },
+    {
+      "epoch": 2.9431117203564083,
+      "grad_norm": 0.053891055285930634,
+      "learning_rate": 1.679273338897293e-05,
+      "loss": 2.6059,
+      "step": 135
+    },
+    {
+      "epoch": 2.9650445510623715,
+      "grad_norm": 0.08152981102466583,
+      "learning_rate": 1.6738555441818785e-05,
+      "loss": 2.62,
+      "step": 136
+    },
+    {
+      "epoch": 2.9869773817683347,
+      "grad_norm": 0.06032385304570198,
+      "learning_rate": 1.668401273329129e-05,
+      "loss": 2.534,
+      "step": 137
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.08430641144514084,
+      "learning_rate": 1.6629108215814523e-05,
+      "loss": 2.5903,
+      "step": 138
+    },
+    {
+      "epoch": 3.021932830705963,
+      "grad_norm": 0.0818452313542366,
+      "learning_rate": 1.6573844861397444e-05,
+      "loss": 2.7053,
+      "step": 139
+    },
+    {
+      "epoch": 3.043865661411926,
+      "grad_norm": 0.11237948387861252,
+      "learning_rate": 1.6518225661473045e-05,
+      "loss": 2.4826,
+      "step": 140
+    },
+    {
+      "epoch": 3.065798492117889,
+      "grad_norm": 0.0827915221452713,
+      "learning_rate": 1.6462253626736413e-05,
+      "loss": 2.5895,
+      "step": 141
+    },
+    {
+      "epoch": 3.087731322823852,
+      "grad_norm": 0.11660678684711456,
+      "learning_rate": 1.6405931786981753e-05,
+      "loss": 2.5654,
+      "step": 142
+    },
+    {
+      "epoch": 3.109664153529815,
+      "grad_norm": 0.09041120111942291,
+      "learning_rate": 1.63492631909384e-05,
+      "loss": 2.5197,
+      "step": 143
+    },
+    {
+      "epoch": 3.131596984235778,
+      "grad_norm": 0.06614544242620468,
+      "learning_rate": 1.629225090610577e-05,
+      "loss": 2.5294,
+      "step": 144
+    },
+    {
+      "epoch": 3.153529814941741,
+      "grad_norm": 0.04271303862333298,
+      "learning_rate": 1.6234898018587336e-05,
+      "loss": 2.5046,
+      "step": 145
+    },
+    {
+      "epoch": 3.1754626456477038,
+      "grad_norm": 0.08055449277162552,
+      "learning_rate": 1.6177207632923558e-05,
+      "loss": 2.5966,
+      "step": 146
+    },
+    {
+      "epoch": 3.197395476353667,
+      "grad_norm": 0.06253743171691895,
+      "learning_rate": 1.6119182871923834e-05,
+      "loss": 2.5158,
+      "step": 147
+    },
+    {
+      "epoch": 3.2193283070596297,
+      "grad_norm": 0.08224272727966309,
+      "learning_rate": 1.606082687649748e-05,
+      "loss": 2.6654,
+      "step": 148
+    },
+    {
+      "epoch": 3.241261137765593,
+      "grad_norm": 0.09529576450586319,
+      "learning_rate": 1.6002142805483686e-05,
+      "loss": 2.5656,
+      "step": 149
+    },
+    {
+      "epoch": 3.2631939684715556,
+      "grad_norm": 0.04647281765937805,
+      "learning_rate": 1.5943133835480536e-05,
+      "loss": 2.5524,
+      "step": 150
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 450,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 50,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3.2639143951466496e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-150/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d943a4e54196cfafe2ccbd67fea9be9b81170f52fff3eddc00ac7d1672f3b07b
+size 5560

checkpoint-200/README.md

@@ -0,0 +1,202 @@
+---
+base_model: unsloth/qwen2.5-3b-bnb-4bit
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.14.0

checkpoint-200/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "unsloth/qwen2.5-3b-bnb-4bit",
+  "bias": "none",
+  "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": 8,
+  "lora_bias": false,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "o_proj",
+    "v_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-200/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b098f5be97368564400daa33e61e01649d6898d5f945ead65c7699fe89f22c2
+size 59021064

checkpoint-200/added_tokens.json

@@ -0,0 +1,25 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|PAD_TOKEN|>": 151665,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

checkpoint-200/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e21724620d938204f90c9851c1ae3b89f43daf4cec5db4c95ee7cd30653c2b4c
+size 30290452

checkpoint-200/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f619428f22a65bad4c67283dd32446722a932445baa6cbcfa5dc672cec70838
+size 14244

checkpoint-200/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:861460d28a40118010decbc24a8a35b7c62b696146d598c3f8218a79b43aff1e
+size 1064

checkpoint-200/special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|PAD_TOKEN|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-200/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eaa46ac5142907d0036d00b99940ae991dbf7e4dc1026d70b5d786d2f672592e
+size 11422353

checkpoint-200/tokenizer_config.json

@@ -0,0 +1,216 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<|PAD_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 32768,
+  "pad_token": "<|PAD_TOKEN|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-200/trainer_state.json

@@ -0,0 +1,1433 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.3509252912954075,
+  "eval_steps": 500,
+  "global_step": 200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02193283070596299,
+      "grad_norm": 0.4870755076408386,
+      "learning_rate": 8.695652173913044e-07,
+      "loss": 2.9525,
+      "step": 1
+    },
+    {
+      "epoch": 0.04386566141192598,
+      "grad_norm": 0.35328975319862366,
+      "learning_rate": 1.7391304347826088e-06,
+      "loss": 2.8102,
+      "step": 2
+    },
+    {
+      "epoch": 0.06579849211788896,
+      "grad_norm": 0.4670841097831726,
+      "learning_rate": 2.6086956521739132e-06,
+      "loss": 2.8848,
+      "step": 3
+    },
+    {
+      "epoch": 0.08773132282385196,
+      "grad_norm": 0.6589818000793457,
+      "learning_rate": 3.4782608695652175e-06,
+      "loss": 3.0569,
+      "step": 4
+    },
+    {
+      "epoch": 0.10966415352981494,
+      "grad_norm": 0.47537556290626526,
+      "learning_rate": 4.347826086956522e-06,
+      "loss": 2.8093,
+      "step": 5
+    },
+    {
+      "epoch": 0.13159698423577793,
+      "grad_norm": 0.6465238928794861,
+      "learning_rate": 5.2173913043478265e-06,
+      "loss": 3.06,
+      "step": 6
+    },
+    {
+      "epoch": 0.15352981494174092,
+      "grad_norm": 0.4992265999317169,
+      "learning_rate": 6.086956521739132e-06,
+      "loss": 2.98,
+      "step": 7
+    },
+    {
+      "epoch": 0.17546264564770392,
+      "grad_norm": 0.5841557383537292,
+      "learning_rate": 6.956521739130435e-06,
+      "loss": 2.9831,
+      "step": 8
+    },
+    {
+      "epoch": 0.1973954763536669,
+      "grad_norm": 0.41789695620536804,
+      "learning_rate": 7.82608695652174e-06,
+      "loss": 2.8239,
+      "step": 9
+    },
+    {
+      "epoch": 0.21932830705962988,
+      "grad_norm": 0.43609240651130676,
+      "learning_rate": 8.695652173913044e-06,
+      "loss": 2.8341,
+      "step": 10
+    },
+    {
+      "epoch": 0.24126113776559288,
+      "grad_norm": 0.3185977041721344,
+      "learning_rate": 9.565217391304349e-06,
+      "loss": 2.7383,
+      "step": 11
+    },
+    {
+      "epoch": 0.26319396847155585,
+      "grad_norm": 0.43681928515434265,
+      "learning_rate": 1.0434782608695653e-05,
+      "loss": 2.9235,
+      "step": 12
+    },
+    {
+      "epoch": 0.2851267991775189,
+      "grad_norm": 0.3825719952583313,
+      "learning_rate": 1.1304347826086957e-05,
+      "loss": 2.6964,
+      "step": 13
+    },
+    {
+      "epoch": 0.30705962988348184,
+      "grad_norm": 0.5028628706932068,
+      "learning_rate": 1.2173913043478263e-05,
+      "loss": 2.8067,
+      "step": 14
+    },
+    {
+      "epoch": 0.3289924605894448,
+      "grad_norm": 0.5002133846282959,
+      "learning_rate": 1.3043478260869566e-05,
+      "loss": 2.8252,
+      "step": 15
+    },
+    {
+      "epoch": 0.35092529129540784,
+      "grad_norm": 0.3002101182937622,
+      "learning_rate": 1.391304347826087e-05,
+      "loss": 2.7313,
+      "step": 16
+    },
+    {
+      "epoch": 0.3728581220013708,
+      "grad_norm": 0.4624859392642975,
+      "learning_rate": 1.4782608695652174e-05,
+      "loss": 2.7972,
+      "step": 17
+    },
+    {
+      "epoch": 0.3947909527073338,
+      "grad_norm": 0.57045578956604,
+      "learning_rate": 1.565217391304348e-05,
+      "loss": 3.0034,
+      "step": 18
+    },
+    {
+      "epoch": 0.4167237834132968,
+      "grad_norm": 0.4259621500968933,
+      "learning_rate": 1.6521739130434785e-05,
+      "loss": 2.8309,
+      "step": 19
+    },
+    {
+      "epoch": 0.43865661411925977,
+      "grad_norm": 0.46009618043899536,
+      "learning_rate": 1.739130434782609e-05,
+      "loss": 2.8408,
+      "step": 20
+    },
+    {
+      "epoch": 0.46058944482522274,
+      "grad_norm": 0.5475765466690063,
+      "learning_rate": 1.8260869565217393e-05,
+      "loss": 2.8943,
+      "step": 21
+    },
+    {
+      "epoch": 0.48252227553118576,
+      "grad_norm": 0.7618455290794373,
+      "learning_rate": 1.9130434782608697e-05,
+      "loss": 2.9959,
+      "step": 22
+    },
+    {
+      "epoch": 0.5044551062371487,
+      "grad_norm": 0.6684309840202332,
+      "learning_rate": 2e-05,
+      "loss": 2.9095,
+      "step": 23
+    },
+    {
+      "epoch": 0.5263879369431117,
+      "grad_norm": 0.545538604259491,
+      "learning_rate": 1.9999729347501484e-05,
+      "loss": 2.8353,
+      "step": 24
+    },
+    {
+      "epoch": 0.5483207676490747,
+      "grad_norm": 0.6128362417221069,
+      "learning_rate": 1.9998917404656488e-05,
+      "loss": 2.8127,
+      "step": 25
+    },
+    {
+      "epoch": 0.5702535983550377,
+      "grad_norm": 0.7084450125694275,
+      "learning_rate": 1.9997564215415886e-05,
+      "loss": 2.9335,
+      "step": 26
+    },
+    {
+      "epoch": 0.5921864290610007,
+      "grad_norm": 0.5246658325195312,
+      "learning_rate": 1.9995669853028485e-05,
+      "loss": 2.8186,
+      "step": 27
+    },
+    {
+      "epoch": 0.6141192597669637,
+      "grad_norm": 0.7249352335929871,
+      "learning_rate": 1.9993234420037072e-05,
+      "loss": 2.8336,
+      "step": 28
+    },
+    {
+      "epoch": 0.6360520904729267,
+      "grad_norm": 0.5946571826934814,
+      "learning_rate": 1.999025804827285e-05,
+      "loss": 2.8233,
+      "step": 29
+    },
+    {
+      "epoch": 0.6579849211788896,
+      "grad_norm": 0.42332401871681213,
+      "learning_rate": 1.9986740898848306e-05,
+      "loss": 2.7259,
+      "step": 30
+    },
+    {
+      "epoch": 0.6799177518848526,
+      "grad_norm": 0.9102485775947571,
+      "learning_rate": 1.99826831621485e-05,
+      "loss": 2.9075,
+      "step": 31
+    },
+    {
+      "epoch": 0.7018505825908157,
+      "grad_norm": 0.6430304646492004,
+      "learning_rate": 1.997808505782075e-05,
+      "loss": 2.9084,
+      "step": 32
+    },
+    {
+      "epoch": 0.7237834132967786,
+      "grad_norm": 0.5709037780761719,
+      "learning_rate": 1.9972946834762732e-05,
+      "loss": 2.8107,
+      "step": 33
+    },
+    {
+      "epoch": 0.7457162440027416,
+      "grad_norm": 0.49835285544395447,
+      "learning_rate": 1.9967268771109037e-05,
+      "loss": 2.7338,
+      "step": 34
+    },
+    {
+      "epoch": 0.7676490747087046,
+      "grad_norm": 0.5714299082756042,
+      "learning_rate": 1.996105117421608e-05,
+      "loss": 2.7816,
+      "step": 35
+    },
+    {
+      "epoch": 0.7895819054146676,
+      "grad_norm": 0.48475122451782227,
+      "learning_rate": 1.9954294380645497e-05,
+      "loss": 2.7685,
+      "step": 36
+    },
+    {
+      "epoch": 0.8115147361206305,
+      "grad_norm": 0.5309097766876221,
+      "learning_rate": 1.9946998756145894e-05,
+      "loss": 2.7778,
+      "step": 37
+    },
+    {
+      "epoch": 0.8334475668265936,
+      "grad_norm": 0.45952990651130676,
+      "learning_rate": 1.9939164695633067e-05,
+      "loss": 2.7954,
+      "step": 38
+    },
+    {
+      "epoch": 0.8553803975325566,
+      "grad_norm": 0.48351016640663147,
+      "learning_rate": 1.9930792623168638e-05,
+      "loss": 2.6792,
+      "step": 39
+    },
+    {
+      "epoch": 0.8773132282385195,
+      "grad_norm": 0.4013523459434509,
+      "learning_rate": 1.992188299193706e-05,
+      "loss": 2.7983,
+      "step": 40
+    },
+    {
+      "epoch": 0.8992460589444825,
+      "grad_norm": 0.318466454744339,
+      "learning_rate": 1.9912436284221134e-05,
+      "loss": 2.5984,
+      "step": 41
+    },
+    {
+      "epoch": 0.9211788896504455,
+      "grad_norm": 0.3661440908908844,
+      "learning_rate": 1.9902453011375865e-05,
+      "loss": 2.8038,
+      "step": 42
+    },
+    {
+      "epoch": 0.9431117203564084,
+      "grad_norm": 0.4626653790473938,
+      "learning_rate": 1.98919337138008e-05,
+      "loss": 2.7242,
+      "step": 43
+    },
+    {
+      "epoch": 0.9650445510623715,
+      "grad_norm": 0.30195215344429016,
+      "learning_rate": 1.9880878960910772e-05,
+      "loss": 2.6637,
+      "step": 44
+    },
+    {
+      "epoch": 0.9869773817683345,
+      "grad_norm": 0.40314823389053345,
+      "learning_rate": 1.9869289351105087e-05,
+      "loss": 2.7072,
+      "step": 45
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.4138323962688446,
+      "learning_rate": 1.9857165511735105e-05,
+      "loss": 2.6019,
+      "step": 46
+    },
+    {
+      "epoch": 1.021932830705963,
+      "grad_norm": 0.29498204588890076,
+      "learning_rate": 1.9844508099070313e-05,
+      "loss": 2.5943,
+      "step": 47
+    },
+    {
+      "epoch": 1.043865661411926,
+      "grad_norm": 0.29517868161201477,
+      "learning_rate": 1.9831317798262787e-05,
+      "loss": 2.6963,
+      "step": 48
+    },
+    {
+      "epoch": 1.065798492117889,
+      "grad_norm": 0.29591700434684753,
+      "learning_rate": 1.98175953233101e-05,
+      "loss": 2.7676,
+      "step": 49
+    },
+    {
+      "epoch": 1.0877313228238519,
+      "grad_norm": 0.2561758756637573,
+      "learning_rate": 1.980334141701667e-05,
+      "loss": 2.629,
+      "step": 50
+    },
+    {
+      "epoch": 1.1096641535298148,
+      "grad_norm": 0.2604333460330963,
+      "learning_rate": 1.978855685095358e-05,
+      "loss": 2.7115,
+      "step": 51
+    },
+    {
+      "epoch": 1.1315969842357778,
+      "grad_norm": 0.4252321422100067,
+      "learning_rate": 1.977324242541677e-05,
+      "loss": 2.6442,
+      "step": 52
+    },
+    {
+      "epoch": 1.153529814941741,
+      "grad_norm": 0.23818732798099518,
+      "learning_rate": 1.9757398969383752e-05,
+      "loss": 2.7172,
+      "step": 53
+    },
+    {
+      "epoch": 1.175462645647704,
+      "grad_norm": 0.16449472308158875,
+      "learning_rate": 1.974102734046872e-05,
+      "loss": 2.6405,
+      "step": 54
+    },
+    {
+      "epoch": 1.197395476353667,
+      "grad_norm": 0.25156456232070923,
+      "learning_rate": 1.9724128424876117e-05,
+      "loss": 2.6376,
+      "step": 55
+    },
+    {
+      "epoch": 1.21932830705963,
+      "grad_norm": 0.1786828637123108,
+      "learning_rate": 1.9706703137352695e-05,
+      "loss": 2.5754,
+      "step": 56
+    },
+    {
+      "epoch": 1.2412611377655929,
+      "grad_norm": 0.21457381546497345,
+      "learning_rate": 1.968875242113798e-05,
+      "loss": 2.6309,
+      "step": 57
+    },
+    {
+      "epoch": 1.2631939684715559,
+      "grad_norm": 0.16352739930152893,
+      "learning_rate": 1.9670277247913205e-05,
+      "loss": 2.5966,
+      "step": 58
+    },
+    {
+      "epoch": 1.2851267991775188,
+      "grad_norm": 0.19751280546188354,
+      "learning_rate": 1.965127861774873e-05,
+      "loss": 2.7516,
+      "step": 59
+    },
+    {
+      "epoch": 1.3070596298834818,
+      "grad_norm": 0.14813798666000366,
+      "learning_rate": 1.96317575590499e-05,
+      "loss": 2.6464,
+      "step": 60
+    },
+    {
+      "epoch": 1.3289924605894448,
+      "grad_norm": 0.15344278514385223,
+      "learning_rate": 1.9611715128501378e-05,
+      "loss": 2.7081,
+      "step": 61
+    },
+    {
+      "epoch": 1.350925291295408,
+      "grad_norm": 0.1399158239364624,
+      "learning_rate": 1.9591152411009942e-05,
+      "loss": 2.6382,
+      "step": 62
+    },
+    {
+      "epoch": 1.3728581220013707,
+      "grad_norm": 0.1705392748117447,
+      "learning_rate": 1.9570070519645767e-05,
+      "loss": 2.6442,
+      "step": 63
+    },
+    {
+      "epoch": 1.3947909527073339,
+      "grad_norm": 0.16903157532215118,
+      "learning_rate": 1.9548470595582166e-05,
+      "loss": 2.5898,
+      "step": 64
+    },
+    {
+      "epoch": 1.4167237834132969,
+      "grad_norm": 0.13648824393749237,
+      "learning_rate": 1.9526353808033827e-05,
+      "loss": 2.5725,
+      "step": 65
+    },
+    {
+      "epoch": 1.4386566141192598,
+      "grad_norm": 0.129099041223526,
+      "learning_rate": 1.9503721354193507e-05,
+      "loss": 2.6863,
+      "step": 66
+    },
+    {
+      "epoch": 1.4605894448252228,
+      "grad_norm": 0.12659573554992676,
+      "learning_rate": 1.948057445916724e-05,
+      "loss": 2.6224,
+      "step": 67
+    },
+    {
+      "epoch": 1.4825222755311858,
+      "grad_norm": 0.1909603327512741,
+      "learning_rate": 1.9456914375908026e-05,
+      "loss": 2.6401,
+      "step": 68
+    },
+    {
+      "epoch": 1.5044551062371487,
+      "grad_norm": 0.25878530740737915,
+      "learning_rate": 1.9432742385147988e-05,
+      "loss": 2.6704,
+      "step": 69
+    },
+    {
+      "epoch": 1.5263879369431117,
+      "grad_norm": 0.13662640750408173,
+      "learning_rate": 1.9408059795329073e-05,
+      "loss": 2.6154,
+      "step": 70
+    },
+    {
+      "epoch": 1.5483207676490747,
+      "grad_norm": 0.13560184836387634,
+      "learning_rate": 1.9382867942532195e-05,
+      "loss": 2.6227,
+      "step": 71
+    },
+    {
+      "epoch": 1.5702535983550376,
+      "grad_norm": 0.1390749216079712,
+      "learning_rate": 1.9357168190404937e-05,
+      "loss": 2.6884,
+      "step": 72
+    },
+    {
+      "epoch": 1.5921864290610008,
+      "grad_norm": 0.12690310180187225,
+      "learning_rate": 1.9330961930087724e-05,
+      "loss": 2.674,
+      "step": 73
+    },
+    {
+      "epoch": 1.6141192597669636,
+      "grad_norm": 0.09753144532442093,
+      "learning_rate": 1.9304250580138524e-05,
+      "loss": 2.6209,
+      "step": 74
+    },
+    {
+      "epoch": 1.6360520904729268,
+      "grad_norm": 0.12032578140497208,
+      "learning_rate": 1.9277035586456056e-05,
+      "loss": 2.6915,
+      "step": 75
+    },
+    {
+      "epoch": 1.6579849211788895,
+      "grad_norm": 0.16928426921367645,
+      "learning_rate": 1.9249318422201524e-05,
+      "loss": 2.6132,
+      "step": 76
+    },
+    {
+      "epoch": 1.6799177518848527,
+      "grad_norm": 0.09693765640258789,
+      "learning_rate": 1.9221100587718884e-05,
+      "loss": 2.6633,
+      "step": 77
+    },
+    {
+      "epoch": 1.7018505825908157,
+      "grad_norm": 0.16512952744960785,
+      "learning_rate": 1.919238361045362e-05,
+      "loss": 2.6585,
+      "step": 78
+    },
+    {
+      "epoch": 1.7237834132967786,
+      "grad_norm": 0.14026080071926117,
+      "learning_rate": 1.916316904487005e-05,
+      "loss": 2.7693,
+      "step": 79
+    },
+    {
+      "epoch": 1.7457162440027416,
+      "grad_norm": 0.14885276556015015,
+      "learning_rate": 1.9133458472367216e-05,
+      "loss": 2.7144,
+      "step": 80
+    },
+    {
+      "epoch": 1.7676490747087046,
+      "grad_norm": 0.11436336487531662,
+      "learning_rate": 1.9103253501193256e-05,
+      "loss": 2.5687,
+      "step": 81
+    },
+    {
+      "epoch": 1.7895819054146676,
+      "grad_norm": 0.24450720846652985,
+      "learning_rate": 1.9072555766358346e-05,
+      "loss": 2.5209,
+      "step": 82
+    },
+    {
+      "epoch": 1.8115147361206305,
+      "grad_norm": 0.19669459760189056,
+      "learning_rate": 1.904136692954622e-05,
+      "loss": 2.5729,
+      "step": 83
+    },
+    {
+      "epoch": 1.8334475668265937,
+      "grad_norm": 0.1368049532175064,
+      "learning_rate": 1.900968867902419e-05,
+      "loss": 2.6268,
+      "step": 84
+    },
+    {
+      "epoch": 1.8553803975325565,
+      "grad_norm": 0.1277005970478058,
+      "learning_rate": 1.89775227295518e-05,
+      "loss": 2.6601,
+      "step": 85
+    },
+    {
+      "epoch": 1.8773132282385196,
+      "grad_norm": 0.09511096775531769,
+      "learning_rate": 1.8944870822287957e-05,
+      "loss": 2.5918,
+      "step": 86
+    },
+    {
+      "epoch": 1.8992460589444824,
+      "grad_norm": 0.06676003336906433,
+      "learning_rate": 1.891173472469672e-05,
+      "loss": 2.5671,
+      "step": 87
+    },
+    {
+      "epoch": 1.9211788896504456,
+      "grad_norm": 0.13803276419639587,
+      "learning_rate": 1.8878116230451615e-05,
+      "loss": 2.6257,
+      "step": 88
+    },
+    {
+      "epoch": 1.9431117203564083,
+      "grad_norm": 0.10050716996192932,
+      "learning_rate": 1.884401715933853e-05,
+      "loss": 2.6772,
+      "step": 89
+    },
+    {
+      "epoch": 1.9650445510623715,
+      "grad_norm": 0.1283024400472641,
+      "learning_rate": 1.8809439357157226e-05,
+      "loss": 2.6121,
+      "step": 90
+    },
+    {
+      "epoch": 1.9869773817683345,
+      "grad_norm": 0.13763798773288727,
+      "learning_rate": 1.8774384695621407e-05,
+      "loss": 2.568,
+      "step": 91
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.22271642088890076,
+      "learning_rate": 1.8738855072257428e-05,
+      "loss": 2.5865,
+      "step": 92
+    },
+    {
+      "epoch": 2.021932830705963,
+      "grad_norm": 0.11131051927804947,
+      "learning_rate": 1.8702852410301556e-05,
+      "loss": 2.5144,
+      "step": 93
+    },
+    {
+      "epoch": 2.043865661411926,
+      "grad_norm": 0.11161550134420395,
+      "learning_rate": 1.8666378658595863e-05,
+      "loss": 2.5182,
+      "step": 94
+    },
+    {
+      "epoch": 2.065798492117889,
+      "grad_norm": 0.08552844822406769,
+      "learning_rate": 1.8629435791482765e-05,
+      "loss": 2.6402,
+      "step": 95
+    },
+    {
+      "epoch": 2.087731322823852,
+      "grad_norm": 0.11428907513618469,
+      "learning_rate": 1.8592025808698116e-05,
+      "loss": 2.6265,
+      "step": 96
+    },
+    {
+      "epoch": 2.109664153529815,
+      "grad_norm": 0.09980299323797226,
+      "learning_rate": 1.8554150735262975e-05,
+      "loss": 2.623,
+      "step": 97
+    },
+    {
+      "epoch": 2.131596984235778,
+      "grad_norm": 0.08849837630987167,
+      "learning_rate": 1.8515812621373998e-05,
+      "loss": 2.627,
+      "step": 98
+    },
+    {
+      "epoch": 2.153529814941741,
+      "grad_norm": 0.09756634384393692,
+      "learning_rate": 1.8477013542292446e-05,
+      "loss": 2.6233,
+      "step": 99
+    },
+    {
+      "epoch": 2.1754626456477038,
+      "grad_norm": 0.07598986476659775,
+      "learning_rate": 1.8437755598231857e-05,
+      "loss": 2.6633,
+      "step": 100
+    },
+    {
+      "epoch": 2.197395476353667,
+      "grad_norm": 0.18077166378498077,
+      "learning_rate": 1.8398040914244363e-05,
+      "loss": 2.6253,
+      "step": 101
+    },
+    {
+      "epoch": 2.2193283070596297,
+      "grad_norm": 0.14006111025810242,
+      "learning_rate": 1.8357871640105648e-05,
+      "loss": 2.6086,
+      "step": 102
+    },
+    {
+      "epoch": 2.241261137765593,
+      "grad_norm": 0.08927474915981293,
+      "learning_rate": 1.8317249950198598e-05,
+      "loss": 2.4877,
+      "step": 103
+    },
+    {
+      "epoch": 2.2631939684715556,
+      "grad_norm": 0.08106345683336258,
+      "learning_rate": 1.8276178043395588e-05,
+      "loss": 2.6523,
+      "step": 104
+    },
+    {
+      "epoch": 2.285126799177519,
+      "grad_norm": 0.09083954989910126,
+      "learning_rate": 1.8234658142939454e-05,
+      "loss": 2.6456,
+      "step": 105
+    },
+    {
+      "epoch": 2.307059629883482,
+      "grad_norm": 0.07053636014461517,
+      "learning_rate": 1.8192692496323158e-05,
+      "loss": 2.6306,
+      "step": 106
+    },
+    {
+      "epoch": 2.3289924605894448,
+      "grad_norm": 0.06668028235435486,
+      "learning_rate": 1.8150283375168112e-05,
+      "loss": 2.5175,
+      "step": 107
+    },
+    {
+      "epoch": 2.350925291295408,
+      "grad_norm": 0.13295046985149384,
+      "learning_rate": 1.8107433075101254e-05,
+      "loss": 2.473,
+      "step": 108
+    },
+    {
+      "epoch": 2.3728581220013707,
+      "grad_norm": 0.09093775600194931,
+      "learning_rate": 1.8064143915630723e-05,
+      "loss": 2.547,
+      "step": 109
+    },
+    {
+      "epoch": 2.394790952707334,
+      "grad_norm": 0.18302415311336517,
+      "learning_rate": 1.8020418240020362e-05,
+      "loss": 2.5652,
+      "step": 110
+    },
+    {
+      "epoch": 2.4167237834132966,
+      "grad_norm": 0.07250549644231796,
+      "learning_rate": 1.7976258415162836e-05,
+      "loss": 2.5828,
+      "step": 111
+    },
+    {
+      "epoch": 2.43865661411926,
+      "grad_norm": 0.3828829526901245,
+      "learning_rate": 1.7931666831451536e-05,
+      "loss": 2.5063,
+      "step": 112
+    },
+    {
+      "epoch": 2.4605894448252226,
+      "grad_norm": 0.5052575469017029,
+      "learning_rate": 1.7886645902651166e-05,
+      "loss": 2.6184,
+      "step": 113
+    },
+    {
+      "epoch": 2.4825222755311858,
+      "grad_norm": 0.07245208323001862,
+      "learning_rate": 1.7841198065767107e-05,
+      "loss": 2.5883,
+      "step": 114
+    },
+    {
+      "epoch": 2.504455106237149,
+      "grad_norm": 0.05822201445698738,
+      "learning_rate": 1.779532578091347e-05,
+      "loss": 2.6,
+      "step": 115
+    },
+    {
+      "epoch": 2.5263879369431117,
+      "grad_norm": 0.08909498155117035,
+      "learning_rate": 1.7749031531179962e-05,
+      "loss": 2.549,
+      "step": 116
+    },
+    {
+      "epoch": 2.5483207676490744,
+      "grad_norm": 0.07801003754138947,
+      "learning_rate": 1.7702317822497457e-05,
+      "loss": 2.5591,
+      "step": 117
+    },
+    {
+      "epoch": 2.5702535983550376,
+      "grad_norm": 0.2434745877981186,
+      "learning_rate": 1.7655187183502344e-05,
+      "loss": 2.6557,
+      "step": 118
+    },
+    {
+      "epoch": 2.592186429061001,
+      "grad_norm": 0.06782998889684677,
+      "learning_rate": 1.7607642165399665e-05,
+      "loss": 2.5268,
+      "step": 119
+    },
+    {
+      "epoch": 2.6141192597669636,
+      "grad_norm": 0.0920061469078064,
+      "learning_rate": 1.755968534182501e-05,
+      "loss": 2.5052,
+      "step": 120
+    },
+    {
+      "epoch": 2.6360520904729268,
+      "grad_norm": 0.0655408501625061,
+      "learning_rate": 1.7511319308705198e-05,
+      "loss": 2.5784,
+      "step": 121
+    },
+    {
+      "epoch": 2.6579849211788895,
+      "grad_norm": 0.13081596791744232,
+      "learning_rate": 1.746254668411778e-05,
+      "loss": 2.5305,
+      "step": 122
+    },
+    {
+      "epoch": 2.6799177518848527,
+      "grad_norm": 0.3778601884841919,
+      "learning_rate": 1.7413370108149288e-05,
+      "loss": 2.5846,
+      "step": 123
+    },
+    {
+      "epoch": 2.701850582590816,
+      "grad_norm": 0.07771953195333481,
+      "learning_rate": 1.7363792242752354e-05,
+      "loss": 2.563,
+      "step": 124
+    },
+    {
+      "epoch": 2.7237834132967786,
+      "grad_norm": 0.06316570937633514,
+      "learning_rate": 1.731381577160161e-05,
+      "loss": 2.5705,
+      "step": 125
+    },
+    {
+      "epoch": 2.7457162440027414,
+      "grad_norm": 0.10998786240816116,
+      "learning_rate": 1.726344339994841e-05,
+      "loss": 2.6364,
+      "step": 126
+    },
+    {
+      "epoch": 2.7676490747087046,
+      "grad_norm": 0.08724892884492874,
+      "learning_rate": 1.7212677854474402e-05,
+      "loss": 2.4682,
+      "step": 127
+    },
+    {
+      "epoch": 2.7895819054146678,
+      "grad_norm": 0.10323834419250488,
+      "learning_rate": 1.7161521883143936e-05,
+      "loss": 2.6225,
+      "step": 128
+    },
+    {
+      "epoch": 2.8115147361206305,
+      "grad_norm": 0.07787463814020157,
+      "learning_rate": 1.7109978255055295e-05,
+      "loss": 2.5786,
+      "step": 129
+    },
+    {
+      "epoch": 2.8334475668265937,
+      "grad_norm": 0.07260199636220932,
+      "learning_rate": 1.705804976029083e-05,
+      "loss": 2.678,
+      "step": 130
+    },
+    {
+      "epoch": 2.8553803975325565,
+      "grad_norm": 0.07246023416519165,
+      "learning_rate": 1.7005739209765906e-05,
+      "loss": 2.4259,
+      "step": 131
+    },
+    {
+      "epoch": 2.8773132282385196,
+      "grad_norm": 0.09231323003768921,
+      "learning_rate": 1.6953049435076768e-05,
+      "loss": 2.6071,
+      "step": 132
+    },
+    {
+      "epoch": 2.8992460589444824,
+      "grad_norm": 0.08409086614847183,
+      "learning_rate": 1.6899983288347248e-05,
+      "loss": 2.4503,
+      "step": 133
+    },
+    {
+      "epoch": 2.9211788896504456,
+      "grad_norm": 0.10303400456905365,
+      "learning_rate": 1.6846543642074382e-05,
+      "loss": 2.5125,
+      "step": 134
+    },
+    {
+      "epoch": 2.9431117203564083,
+      "grad_norm": 0.053891055285930634,
+      "learning_rate": 1.679273338897293e-05,
+      "loss": 2.6059,
+      "step": 135
+    },
+    {
+      "epoch": 2.9650445510623715,
+      "grad_norm": 0.08152981102466583,
+      "learning_rate": 1.6738555441818785e-05,
+      "loss": 2.62,
+      "step": 136
+    },
+    {
+      "epoch": 2.9869773817683347,
+      "grad_norm": 0.06032385304570198,
+      "learning_rate": 1.668401273329129e-05,
+      "loss": 2.534,
+      "step": 137
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.08430641144514084,
+      "learning_rate": 1.6629108215814523e-05,
+      "loss": 2.5903,
+      "step": 138
+    },
+    {
+      "epoch": 3.021932830705963,
+      "grad_norm": 0.0818452313542366,
+      "learning_rate": 1.6573844861397444e-05,
+      "loss": 2.7053,
+      "step": 139
+    },
+    {
+      "epoch": 3.043865661411926,
+      "grad_norm": 0.11237948387861252,
+      "learning_rate": 1.6518225661473045e-05,
+      "loss": 2.4826,
+      "step": 140
+    },
+    {
+      "epoch": 3.065798492117889,
+      "grad_norm": 0.0827915221452713,
+      "learning_rate": 1.6462253626736413e-05,
+      "loss": 2.5895,
+      "step": 141
+    },
+    {
+      "epoch": 3.087731322823852,
+      "grad_norm": 0.11660678684711456,
+      "learning_rate": 1.6405931786981753e-05,
+      "loss": 2.5654,
+      "step": 142
+    },
+    {
+      "epoch": 3.109664153529815,
+      "grad_norm": 0.09041120111942291,
+      "learning_rate": 1.63492631909384e-05,
+      "loss": 2.5197,
+      "step": 143
+    },
+    {
+      "epoch": 3.131596984235778,
+      "grad_norm": 0.06614544242620468,
+      "learning_rate": 1.629225090610577e-05,
+      "loss": 2.5294,
+      "step": 144
+    },
+    {
+      "epoch": 3.153529814941741,
+      "grad_norm": 0.04271303862333298,
+      "learning_rate": 1.6234898018587336e-05,
+      "loss": 2.5046,
+      "step": 145
+    },
+    {
+      "epoch": 3.1754626456477038,
+      "grad_norm": 0.08055449277162552,
+      "learning_rate": 1.6177207632923558e-05,
+      "loss": 2.5966,
+      "step": 146
+    },
+    {
+      "epoch": 3.197395476353667,
+      "grad_norm": 0.06253743171691895,
+      "learning_rate": 1.6119182871923834e-05,
+      "loss": 2.5158,
+      "step": 147
+    },
+    {
+      "epoch": 3.2193283070596297,
+      "grad_norm": 0.08224272727966309,
+      "learning_rate": 1.606082687649748e-05,
+      "loss": 2.6654,
+      "step": 148
+    },
+    {
+      "epoch": 3.241261137765593,
+      "grad_norm": 0.09529576450586319,
+      "learning_rate": 1.6002142805483686e-05,
+      "loss": 2.5656,
+      "step": 149
+    },
+    {
+      "epoch": 3.2631939684715556,
+      "grad_norm": 0.04647281765937805,
+      "learning_rate": 1.5943133835480536e-05,
+      "loss": 2.5524,
+      "step": 150
+    },
+    {
+      "epoch": 3.285126799177519,
+      "grad_norm": 0.07187870889902115,
+      "learning_rate": 1.588380316067307e-05,
+      "loss": 2.5522,
+      "step": 151
+    },
+    {
+      "epoch": 3.307059629883482,
+      "grad_norm": 0.06179989129304886,
+      "learning_rate": 1.582415399266036e-05,
+      "loss": 2.6259,
+      "step": 152
+    },
+    {
+      "epoch": 3.3289924605894448,
+      "grad_norm": 0.0755513459444046,
+      "learning_rate": 1.5764189560281677e-05,
+      "loss": 2.5568,
+      "step": 153
+    },
+    {
+      "epoch": 3.350925291295408,
+      "grad_norm": 0.08130097389221191,
+      "learning_rate": 1.5703913109441715e-05,
+      "loss": 2.6148,
+      "step": 154
+    },
+    {
+      "epoch": 3.3728581220013707,
+      "grad_norm": 0.07435321062803268,
+      "learning_rate": 1.564332790293487e-05,
+      "loss": 2.5511,
+      "step": 155
+    },
+    {
+      "epoch": 3.394790952707334,
+      "grad_norm": 0.05641249567270279,
+      "learning_rate": 1.5582437220268648e-05,
+      "loss": 2.4647,
+      "step": 156
+    },
+    {
+      "epoch": 3.4167237834132966,
+      "grad_norm": 0.05596217140555382,
+      "learning_rate": 1.5521244357486132e-05,
+      "loss": 2.5502,
+      "step": 157
+    },
+    {
+      "epoch": 3.43865661411926,
+      "grad_norm": 0.06887087225914001,
+      "learning_rate": 1.5459752626987563e-05,
+      "loss": 2.4662,
+      "step": 158
+    },
+    {
+      "epoch": 3.4605894448252226,
+      "grad_norm": 0.06323248893022537,
+      "learning_rate": 1.5397965357351035e-05,
+      "loss": 2.5123,
+      "step": 159
+    },
+    {
+      "epoch": 3.4825222755311858,
+      "grad_norm": 0.09084805101156235,
+      "learning_rate": 1.5335885893152335e-05,
+      "loss": 2.4644,
+      "step": 160
+    },
+    {
+      "epoch": 3.504455106237149,
+      "grad_norm": 0.07094909995794296,
+      "learning_rate": 1.5273517594783878e-05,
+      "loss": 2.493,
+      "step": 161
+    },
+    {
+      "epoch": 3.5263879369431117,
+      "grad_norm": 0.04841725155711174,
+      "learning_rate": 1.521086383827282e-05,
+      "loss": 2.4868,
+      "step": 162
+    },
+    {
+      "epoch": 3.5483207676490744,
+      "grad_norm": 0.062218405306339264,
+      "learning_rate": 1.5147928015098309e-05,
+      "loss": 2.4924,
+      "step": 163
+    },
+    {
+      "epoch": 3.5702535983550376,
+      "grad_norm": 0.06784085184335709,
+      "learning_rate": 1.5084713532007906e-05,
+      "loss": 2.5649,
+      "step": 164
+    },
+    {
+      "epoch": 3.592186429061001,
+      "grad_norm": 0.07132422924041748,
+      "learning_rate": 1.5021223810833165e-05,
+      "loss": 2.5442,
+      "step": 165
+    },
+    {
+      "epoch": 3.6141192597669636,
+      "grad_norm": 0.05512155964970589,
+      "learning_rate": 1.4957462288304421e-05,
+      "loss": 2.4669,
+      "step": 166
+    },
+    {
+      "epoch": 3.6360520904729268,
+      "grad_norm": 0.060434065759181976,
+      "learning_rate": 1.489343241586475e-05,
+      "loss": 2.549,
+      "step": 167
+    },
+    {
+      "epoch": 3.6579849211788895,
+      "grad_norm": 0.05476135015487671,
+      "learning_rate": 1.4829137659483144e-05,
+      "loss": 2.5643,
+      "step": 168
+    },
+    {
+      "epoch": 3.6799177518848527,
+      "grad_norm": 0.06881222128868103,
+      "learning_rate": 1.4764581499466895e-05,
+      "loss": 2.3814,
+      "step": 169
+    },
+    {
+      "epoch": 3.701850582590816,
+      "grad_norm": 0.08369456231594086,
+      "learning_rate": 1.4699767430273202e-05,
+      "loss": 2.5987,
+      "step": 170
+    },
+    {
+      "epoch": 3.7237834132967786,
+      "grad_norm": 0.05814111605286598,
+      "learning_rate": 1.4634698960320018e-05,
+      "loss": 2.5668,
+      "step": 171
+    },
+    {
+      "epoch": 3.7457162440027414,
+      "grad_norm": 0.05372776836156845,
+      "learning_rate": 1.4569379611796137e-05,
+      "loss": 2.5888,
+      "step": 172
+    },
+    {
+      "epoch": 3.7676490747087046,
+      "grad_norm": 0.060161709785461426,
+      "learning_rate": 1.4503812920470535e-05,
+      "loss": 2.5052,
+      "step": 173
+    },
+    {
+      "epoch": 3.7895819054146678,
+      "grad_norm": 0.06631386280059814,
+      "learning_rate": 1.443800243550098e-05,
+      "loss": 2.4963,
+      "step": 174
+    },
+    {
+      "epoch": 3.8115147361206305,
+      "grad_norm": 0.06452737748622894,
+      "learning_rate": 1.4371951719241906e-05,
+      "loss": 2.4251,
+      "step": 175
+    },
+    {
+      "epoch": 3.8334475668265937,
+      "grad_norm": 0.09428981691598892,
+      "learning_rate": 1.4305664347051586e-05,
+      "loss": 2.5676,
+      "step": 176
+    },
+    {
+      "epoch": 3.8553803975325565,
+      "grad_norm": 0.050980083644390106,
+      "learning_rate": 1.423914390709861e-05,
+      "loss": 2.5683,
+      "step": 177
+    },
+    {
+      "epoch": 3.8773132282385196,
+      "grad_norm": 0.05442551150918007,
+      "learning_rate": 1.4172394000167625e-05,
+      "loss": 2.5449,
+      "step": 178
+    },
+    {
+      "epoch": 3.8992460589444824,
+      "grad_norm": 0.04739952087402344,
+      "learning_rate": 1.4105418239464452e-05,
+      "loss": 2.5018,
+      "step": 179
+    },
+    {
+      "epoch": 3.9211788896504456,
+      "grad_norm": 0.06977739185094833,
+      "learning_rate": 1.4038220250420487e-05,
+      "loss": 2.5065,
+      "step": 180
+    },
+    {
+      "epoch": 3.9431117203564083,
+      "grad_norm": 0.09621317684650421,
+      "learning_rate": 1.3970803670496453e-05,
+      "loss": 2.5293,
+      "step": 181
+    },
+    {
+      "epoch": 3.9650445510623715,
+      "grad_norm": 0.07425831258296967,
+      "learning_rate": 1.390317214898551e-05,
+      "loss": 2.5197,
+      "step": 182
+    },
+    {
+      "epoch": 3.9869773817683347,
+      "grad_norm": 0.05756077170372009,
+      "learning_rate": 1.3835329346815716e-05,
+      "loss": 2.4661,
+      "step": 183
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.07039082795381546,
+      "learning_rate": 1.3767278936351853e-05,
+      "loss": 2.7058,
+      "step": 184
+    },
+    {
+      "epoch": 4.021932830705963,
+      "grad_norm": 0.06809078902006149,
+      "learning_rate": 1.3699024601196641e-05,
+      "loss": 2.5684,
+      "step": 185
+    },
+    {
+      "epoch": 4.043865661411926,
+      "grad_norm": 0.044164013117551804,
+      "learning_rate": 1.3630570035991352e-05,
+      "loss": 2.4878,
+      "step": 186
+    },
+    {
+      "epoch": 4.065798492117889,
+      "grad_norm": 0.07478977739810944,
+      "learning_rate": 1.3561918946215807e-05,
+      "loss": 2.5928,
+      "step": 187
+    },
+    {
+      "epoch": 4.087731322823852,
+      "grad_norm": 0.053608592599630356,
+      "learning_rate": 1.34930750479878e-05,
+      "loss": 2.5654,
+      "step": 188
+    },
+    {
+      "epoch": 4.109664153529815,
+      "grad_norm": 0.049672599881887436,
+      "learning_rate": 1.3424042067861944e-05,
+      "loss": 2.4353,
+      "step": 189
+    },
+    {
+      "epoch": 4.131596984235778,
+      "grad_norm": 0.07206689566373825,
+      "learning_rate": 1.335482374262795e-05,
+      "loss": 2.5453,
+      "step": 190
+    },
+    {
+      "epoch": 4.153529814941741,
+      "grad_norm": 0.059480294585227966,
+      "learning_rate": 1.3285423819108349e-05,
+      "loss": 2.5138,
+      "step": 191
+    },
+    {
+      "epoch": 4.175462645647704,
+      "grad_norm": 0.05027122050523758,
+      "learning_rate": 1.3215846053955683e-05,
+      "loss": 2.441,
+      "step": 192
+    },
+    {
+      "epoch": 4.197395476353667,
+      "grad_norm": 0.04946836456656456,
+      "learning_rate": 1.3146094213449148e-05,
+      "loss": 2.5398,
+      "step": 193
+    },
+    {
+      "epoch": 4.21932830705963,
+      "grad_norm": 0.073307566344738,
+      "learning_rate": 1.3076172073290726e-05,
+      "loss": 2.5996,
+      "step": 194
+    },
+    {
+      "epoch": 4.241261137765592,
+      "grad_norm": 0.04758650064468384,
+      "learning_rate": 1.3006083418400799e-05,
+      "loss": 2.5598,
+      "step": 195
+    },
+    {
+      "epoch": 4.263193968471556,
+      "grad_norm": 0.0642954632639885,
+      "learning_rate": 1.2935832042713288e-05,
+      "loss": 2.53,
+      "step": 196
+    },
+    {
+      "epoch": 4.285126799177519,
+      "grad_norm": 0.06495189666748047,
+      "learning_rate": 1.2865421748970257e-05,
+      "loss": 2.6442,
+      "step": 197
+    },
+    {
+      "epoch": 4.307059629883482,
+      "grad_norm": 0.05023903772234917,
+      "learning_rate": 1.2794856348516095e-05,
+      "loss": 2.5318,
+      "step": 198
+    },
+    {
+      "epoch": 4.328992460589445,
+      "grad_norm": 0.04791835695505142,
+      "learning_rate": 1.2724139661091188e-05,
+      "loss": 2.5011,
+      "step": 199
+    },
+    {
+      "epoch": 4.3509252912954075,
+      "grad_norm": 0.0522720031440258,
+      "learning_rate": 1.2653275514625165e-05,
+      "loss": 2.5169,
+      "step": 200
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 450,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 50,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4.351885860195533e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-200/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d943a4e54196cfafe2ccbd67fea9be9b81170f52fff3eddc00ac7d1672f3b07b
+size 5560

checkpoint-250/README.md

@@ -0,0 +1,202 @@
+---
+base_model: unsloth/qwen2.5-3b-bnb-4bit
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.14.0

checkpoint-250/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "unsloth/qwen2.5-3b-bnb-4bit",
+  "bias": "none",
+  "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": 8,
+  "lora_bias": false,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "o_proj",
+    "q_proj",
+    "k_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-250/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94598c2ddb228fb1d2135fdc101c0644ee5193e51cf3fc49b155e994beca8e53
+size 59021064

checkpoint-250/added_tokens.json

@@ -0,0 +1,25 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|PAD_TOKEN|>": 151665,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

checkpoint-250/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5df104e80c8055d3a1fa2c68c7ff931fbe389d525fecef8afa9ede1635cec888
+size 31038930

checkpoint-250/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9898dd1ae633d917d6ed924334c68d7550ccbf863cc831784300f8e3fde895b1
+size 14244

checkpoint-250/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:298d2d8308a6c46320f4c8b7be147f2e6dab604695d0ab82228eb07ddc0e26a7
+size 1064

checkpoint-250/special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|PAD_TOKEN|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-250/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eaa46ac5142907d0036d00b99940ae991dbf7e4dc1026d70b5d786d2f672592e
+size 11422353

checkpoint-250/tokenizer_config.json

@@ -0,0 +1,222 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<|PAD_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "max_length": 4096,
+  "model_max_length": 32768,
+  "pad_to_multiple_of": null,
+  "pad_token": "<|PAD_TOKEN|>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "stride": 0,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": null
+}

checkpoint-250/trainer_state.json

@@ -0,0 +1,1783 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 5.5483207676490744,
+  "eval_steps": 500,
+  "global_step": 250,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02193283070596299,
+      "grad_norm": 0.4870755076408386,
+      "learning_rate": 8.695652173913044e-07,
+      "loss": 2.9525,
+      "step": 1
+    },
+    {
+      "epoch": 0.04386566141192598,
+      "grad_norm": 0.35328975319862366,
+      "learning_rate": 1.7391304347826088e-06,
+      "loss": 2.8102,
+      "step": 2
+    },
+    {
+      "epoch": 0.06579849211788896,
+      "grad_norm": 0.4670841097831726,
+      "learning_rate": 2.6086956521739132e-06,
+      "loss": 2.8848,
+      "step": 3
+    },
+    {
+      "epoch": 0.08773132282385196,
+      "grad_norm": 0.6589818000793457,
+      "learning_rate": 3.4782608695652175e-06,
+      "loss": 3.0569,
+      "step": 4
+    },
+    {
+      "epoch": 0.10966415352981494,
+      "grad_norm": 0.47537556290626526,
+      "learning_rate": 4.347826086956522e-06,
+      "loss": 2.8093,
+      "step": 5
+    },
+    {
+      "epoch": 0.13159698423577793,
+      "grad_norm": 0.6465238928794861,
+      "learning_rate": 5.2173913043478265e-06,
+      "loss": 3.06,
+      "step": 6
+    },
+    {
+      "epoch": 0.15352981494174092,
+      "grad_norm": 0.4992265999317169,
+      "learning_rate": 6.086956521739132e-06,
+      "loss": 2.98,
+      "step": 7
+    },
+    {
+      "epoch": 0.17546264564770392,
+      "grad_norm": 0.5841557383537292,
+      "learning_rate": 6.956521739130435e-06,
+      "loss": 2.9831,
+      "step": 8
+    },
+    {
+      "epoch": 0.1973954763536669,
+      "grad_norm": 0.41789695620536804,
+      "learning_rate": 7.82608695652174e-06,
+      "loss": 2.8239,
+      "step": 9
+    },
+    {
+      "epoch": 0.21932830705962988,
+      "grad_norm": 0.43609240651130676,
+      "learning_rate": 8.695652173913044e-06,
+      "loss": 2.8341,
+      "step": 10
+    },
+    {
+      "epoch": 0.24126113776559288,
+      "grad_norm": 0.3185977041721344,
+      "learning_rate": 9.565217391304349e-06,
+      "loss": 2.7383,
+      "step": 11
+    },
+    {
+      "epoch": 0.26319396847155585,
+      "grad_norm": 0.43681928515434265,
+      "learning_rate": 1.0434782608695653e-05,
+      "loss": 2.9235,
+      "step": 12
+    },
+    {
+      "epoch": 0.2851267991775189,
+      "grad_norm": 0.3825719952583313,
+      "learning_rate": 1.1304347826086957e-05,
+      "loss": 2.6964,
+      "step": 13
+    },
+    {
+      "epoch": 0.30705962988348184,
+      "grad_norm": 0.5028628706932068,
+      "learning_rate": 1.2173913043478263e-05,
+      "loss": 2.8067,
+      "step": 14
+    },
+    {
+      "epoch": 0.3289924605894448,
+      "grad_norm": 0.5002133846282959,
+      "learning_rate": 1.3043478260869566e-05,
+      "loss": 2.8252,
+      "step": 15
+    },
+    {
+      "epoch": 0.35092529129540784,
+      "grad_norm": 0.3002101182937622,
+      "learning_rate": 1.391304347826087e-05,
+      "loss": 2.7313,
+      "step": 16
+    },
+    {
+      "epoch": 0.3728581220013708,
+      "grad_norm": 0.4624859392642975,
+      "learning_rate": 1.4782608695652174e-05,
+      "loss": 2.7972,
+      "step": 17
+    },
+    {
+      "epoch": 0.3947909527073338,
+      "grad_norm": 0.57045578956604,
+      "learning_rate": 1.565217391304348e-05,
+      "loss": 3.0034,
+      "step": 18
+    },
+    {
+      "epoch": 0.4167237834132968,
+      "grad_norm": 0.4259621500968933,
+      "learning_rate": 1.6521739130434785e-05,
+      "loss": 2.8309,
+      "step": 19
+    },
+    {
+      "epoch": 0.43865661411925977,
+      "grad_norm": 0.46009618043899536,
+      "learning_rate": 1.739130434782609e-05,
+      "loss": 2.8408,
+      "step": 20
+    },
+    {
+      "epoch": 0.46058944482522274,
+      "grad_norm": 0.5475765466690063,
+      "learning_rate": 1.8260869565217393e-05,
+      "loss": 2.8943,
+      "step": 21
+    },
+    {
+      "epoch": 0.48252227553118576,
+      "grad_norm": 0.7618455290794373,
+      "learning_rate": 1.9130434782608697e-05,
+      "loss": 2.9959,
+      "step": 22
+    },
+    {
+      "epoch": 0.5044551062371487,
+      "grad_norm": 0.6684309840202332,
+      "learning_rate": 2e-05,
+      "loss": 2.9095,
+      "step": 23
+    },
+    {
+      "epoch": 0.5263879369431117,
+      "grad_norm": 0.545538604259491,
+      "learning_rate": 1.9999729347501484e-05,
+      "loss": 2.8353,
+      "step": 24
+    },
+    {
+      "epoch": 0.5483207676490747,
+      "grad_norm": 0.6128362417221069,
+      "learning_rate": 1.9998917404656488e-05,
+      "loss": 2.8127,
+      "step": 25
+    },
+    {
+      "epoch": 0.5702535983550377,
+      "grad_norm": 0.7084450125694275,
+      "learning_rate": 1.9997564215415886e-05,
+      "loss": 2.9335,
+      "step": 26
+    },
+    {
+      "epoch": 0.5921864290610007,
+      "grad_norm": 0.5246658325195312,
+      "learning_rate": 1.9995669853028485e-05,
+      "loss": 2.8186,
+      "step": 27
+    },
+    {
+      "epoch": 0.6141192597669637,
+      "grad_norm": 0.7249352335929871,
+      "learning_rate": 1.9993234420037072e-05,
+      "loss": 2.8336,
+      "step": 28
+    },
+    {
+      "epoch": 0.6360520904729267,
+      "grad_norm": 0.5946571826934814,
+      "learning_rate": 1.999025804827285e-05,
+      "loss": 2.8233,
+      "step": 29
+    },
+    {
+      "epoch": 0.6579849211788896,
+      "grad_norm": 0.42332401871681213,
+      "learning_rate": 1.9986740898848306e-05,
+      "loss": 2.7259,
+      "step": 30
+    },
+    {
+      "epoch": 0.6799177518848526,
+      "grad_norm": 0.9102485775947571,
+      "learning_rate": 1.99826831621485e-05,
+      "loss": 2.9075,
+      "step": 31
+    },
+    {
+      "epoch": 0.7018505825908157,
+      "grad_norm": 0.6430304646492004,
+      "learning_rate": 1.997808505782075e-05,
+      "loss": 2.9084,
+      "step": 32
+    },
+    {
+      "epoch": 0.7237834132967786,
+      "grad_norm": 0.5709037780761719,
+      "learning_rate": 1.9972946834762732e-05,
+      "loss": 2.8107,
+      "step": 33
+    },
+    {
+      "epoch": 0.7457162440027416,
+      "grad_norm": 0.49835285544395447,
+      "learning_rate": 1.9967268771109037e-05,
+      "loss": 2.7338,
+      "step": 34
+    },
+    {
+      "epoch": 0.7676490747087046,
+      "grad_norm": 0.5714299082756042,
+      "learning_rate": 1.996105117421608e-05,
+      "loss": 2.7816,
+      "step": 35
+    },
+    {
+      "epoch": 0.7895819054146676,
+      "grad_norm": 0.48475122451782227,
+      "learning_rate": 1.9954294380645497e-05,
+      "loss": 2.7685,
+      "step": 36
+    },
+    {
+      "epoch": 0.8115147361206305,
+      "grad_norm": 0.5309097766876221,
+      "learning_rate": 1.9946998756145894e-05,
+      "loss": 2.7778,
+      "step": 37
+    },
+    {
+      "epoch": 0.8334475668265936,
+      "grad_norm": 0.45952990651130676,
+      "learning_rate": 1.9939164695633067e-05,
+      "loss": 2.7954,
+      "step": 38
+    },
+    {
+      "epoch": 0.8553803975325566,
+      "grad_norm": 0.48351016640663147,
+      "learning_rate": 1.9930792623168638e-05,
+      "loss": 2.6792,
+      "step": 39
+    },
+    {
+      "epoch": 0.8773132282385195,
+      "grad_norm": 0.4013523459434509,
+      "learning_rate": 1.992188299193706e-05,
+      "loss": 2.7983,
+      "step": 40
+    },
+    {
+      "epoch": 0.8992460589444825,
+      "grad_norm": 0.318466454744339,
+      "learning_rate": 1.9912436284221134e-05,
+      "loss": 2.5984,
+      "step": 41
+    },
+    {
+      "epoch": 0.9211788896504455,
+      "grad_norm": 0.3661440908908844,
+      "learning_rate": 1.9902453011375865e-05,
+      "loss": 2.8038,
+      "step": 42
+    },
+    {
+      "epoch": 0.9431117203564084,
+      "grad_norm": 0.4626653790473938,
+      "learning_rate": 1.98919337138008e-05,
+      "loss": 2.7242,
+      "step": 43
+    },
+    {
+      "epoch": 0.9650445510623715,
+      "grad_norm": 0.30195215344429016,
+      "learning_rate": 1.9880878960910772e-05,
+      "loss": 2.6637,
+      "step": 44
+    },
+    {
+      "epoch": 0.9869773817683345,
+      "grad_norm": 0.40314823389053345,
+      "learning_rate": 1.9869289351105087e-05,
+      "loss": 2.7072,
+      "step": 45
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.4138323962688446,
+      "learning_rate": 1.9857165511735105e-05,
+      "loss": 2.6019,
+      "step": 46
+    },
+    {
+      "epoch": 1.021932830705963,
+      "grad_norm": 0.29498204588890076,
+      "learning_rate": 1.9844508099070313e-05,
+      "loss": 2.5943,
+      "step": 47
+    },
+    {
+      "epoch": 1.043865661411926,
+      "grad_norm": 0.29517868161201477,
+      "learning_rate": 1.9831317798262787e-05,
+      "loss": 2.6963,
+      "step": 48
+    },
+    {
+      "epoch": 1.065798492117889,
+      "grad_norm": 0.29591700434684753,
+      "learning_rate": 1.98175953233101e-05,
+      "loss": 2.7676,
+      "step": 49
+    },
+    {
+      "epoch": 1.0877313228238519,
+      "grad_norm": 0.2561758756637573,
+      "learning_rate": 1.980334141701667e-05,
+      "loss": 2.629,
+      "step": 50
+    },
+    {
+      "epoch": 1.1096641535298148,
+      "grad_norm": 0.2604333460330963,
+      "learning_rate": 1.978855685095358e-05,
+      "loss": 2.7115,
+      "step": 51
+    },
+    {
+      "epoch": 1.1315969842357778,
+      "grad_norm": 0.4252321422100067,
+      "learning_rate": 1.977324242541677e-05,
+      "loss": 2.6442,
+      "step": 52
+    },
+    {
+      "epoch": 1.153529814941741,
+      "grad_norm": 0.23818732798099518,
+      "learning_rate": 1.9757398969383752e-05,
+      "loss": 2.7172,
+      "step": 53
+    },
+    {
+      "epoch": 1.175462645647704,
+      "grad_norm": 0.16449472308158875,
+      "learning_rate": 1.974102734046872e-05,
+      "loss": 2.6405,
+      "step": 54
+    },
+    {
+      "epoch": 1.197395476353667,
+      "grad_norm": 0.25156456232070923,
+      "learning_rate": 1.9724128424876117e-05,
+      "loss": 2.6376,
+      "step": 55
+    },
+    {
+      "epoch": 1.21932830705963,
+      "grad_norm": 0.1786828637123108,
+      "learning_rate": 1.9706703137352695e-05,
+      "loss": 2.5754,
+      "step": 56
+    },
+    {
+      "epoch": 1.2412611377655929,
+      "grad_norm": 0.21457381546497345,
+      "learning_rate": 1.968875242113798e-05,
+      "loss": 2.6309,
+      "step": 57
+    },
+    {
+      "epoch": 1.2631939684715559,
+      "grad_norm": 0.16352739930152893,
+      "learning_rate": 1.9670277247913205e-05,
+      "loss": 2.5966,
+      "step": 58
+    },
+    {
+      "epoch": 1.2851267991775188,
+      "grad_norm": 0.19751280546188354,
+      "learning_rate": 1.965127861774873e-05,
+      "loss": 2.7516,
+      "step": 59
+    },
+    {
+      "epoch": 1.3070596298834818,
+      "grad_norm": 0.14813798666000366,
+      "learning_rate": 1.96317575590499e-05,
+      "loss": 2.6464,
+      "step": 60
+    },
+    {
+      "epoch": 1.3289924605894448,
+      "grad_norm": 0.15344278514385223,
+      "learning_rate": 1.9611715128501378e-05,
+      "loss": 2.7081,
+      "step": 61
+    },
+    {
+      "epoch": 1.350925291295408,
+      "grad_norm": 0.1399158239364624,
+      "learning_rate": 1.9591152411009942e-05,
+      "loss": 2.6382,
+      "step": 62
+    },
+    {
+      "epoch": 1.3728581220013707,
+      "grad_norm": 0.1705392748117447,
+      "learning_rate": 1.9570070519645767e-05,
+      "loss": 2.6442,
+      "step": 63
+    },
+    {
+      "epoch": 1.3947909527073339,
+      "grad_norm": 0.16903157532215118,
+      "learning_rate": 1.9548470595582166e-05,
+      "loss": 2.5898,
+      "step": 64
+    },
+    {
+      "epoch": 1.4167237834132969,
+      "grad_norm": 0.13648824393749237,
+      "learning_rate": 1.9526353808033827e-05,
+      "loss": 2.5725,
+      "step": 65
+    },
+    {
+      "epoch": 1.4386566141192598,
+      "grad_norm": 0.129099041223526,
+      "learning_rate": 1.9503721354193507e-05,
+      "loss": 2.6863,
+      "step": 66
+    },
+    {
+      "epoch": 1.4605894448252228,
+      "grad_norm": 0.12659573554992676,
+      "learning_rate": 1.948057445916724e-05,
+      "loss": 2.6224,
+      "step": 67
+    },
+    {
+      "epoch": 1.4825222755311858,
+      "grad_norm": 0.1909603327512741,
+      "learning_rate": 1.9456914375908026e-05,
+      "loss": 2.6401,
+      "step": 68
+    },
+    {
+      "epoch": 1.5044551062371487,
+      "grad_norm": 0.25878530740737915,
+      "learning_rate": 1.9432742385147988e-05,
+      "loss": 2.6704,
+      "step": 69
+    },
+    {
+      "epoch": 1.5263879369431117,
+      "grad_norm": 0.13662640750408173,
+      "learning_rate": 1.9408059795329073e-05,
+      "loss": 2.6154,
+      "step": 70
+    },
+    {
+      "epoch": 1.5483207676490747,
+      "grad_norm": 0.13560184836387634,
+      "learning_rate": 1.9382867942532195e-05,
+      "loss": 2.6227,
+      "step": 71
+    },
+    {
+      "epoch": 1.5702535983550376,
+      "grad_norm": 0.1390749216079712,
+      "learning_rate": 1.9357168190404937e-05,
+      "loss": 2.6884,
+      "step": 72
+    },
+    {
+      "epoch": 1.5921864290610008,
+      "grad_norm": 0.12690310180187225,
+      "learning_rate": 1.9330961930087724e-05,
+      "loss": 2.674,
+      "step": 73
+    },
+    {
+      "epoch": 1.6141192597669636,
+      "grad_norm": 0.09753144532442093,
+      "learning_rate": 1.9304250580138524e-05,
+      "loss": 2.6209,
+      "step": 74
+    },
+    {
+      "epoch": 1.6360520904729268,
+      "grad_norm": 0.12032578140497208,
+      "learning_rate": 1.9277035586456056e-05,
+      "loss": 2.6915,
+      "step": 75
+    },
+    {
+      "epoch": 1.6579849211788895,
+      "grad_norm": 0.16928426921367645,
+      "learning_rate": 1.9249318422201524e-05,
+      "loss": 2.6132,
+      "step": 76
+    },
+    {
+      "epoch": 1.6799177518848527,
+      "grad_norm": 0.09693765640258789,
+      "learning_rate": 1.9221100587718884e-05,
+      "loss": 2.6633,
+      "step": 77
+    },
+    {
+      "epoch": 1.7018505825908157,
+      "grad_norm": 0.16512952744960785,
+      "learning_rate": 1.919238361045362e-05,
+      "loss": 2.6585,
+      "step": 78
+    },
+    {
+      "epoch": 1.7237834132967786,
+      "grad_norm": 0.14026080071926117,
+      "learning_rate": 1.916316904487005e-05,
+      "loss": 2.7693,
+      "step": 79
+    },
+    {
+      "epoch": 1.7457162440027416,
+      "grad_norm": 0.14885276556015015,
+      "learning_rate": 1.9133458472367216e-05,
+      "loss": 2.7144,
+      "step": 80
+    },
+    {
+      "epoch": 1.7676490747087046,
+      "grad_norm": 0.11436336487531662,
+      "learning_rate": 1.9103253501193256e-05,
+      "loss": 2.5687,
+      "step": 81
+    },
+    {
+      "epoch": 1.7895819054146676,
+      "grad_norm": 0.24450720846652985,
+      "learning_rate": 1.9072555766358346e-05,
+      "loss": 2.5209,
+      "step": 82
+    },
+    {
+      "epoch": 1.8115147361206305,
+      "grad_norm": 0.19669459760189056,
+      "learning_rate": 1.904136692954622e-05,
+      "loss": 2.5729,
+      "step": 83
+    },
+    {
+      "epoch": 1.8334475668265937,
+      "grad_norm": 0.1368049532175064,
+      "learning_rate": 1.900968867902419e-05,
+      "loss": 2.6268,
+      "step": 84
+    },
+    {
+      "epoch": 1.8553803975325565,
+      "grad_norm": 0.1277005970478058,
+      "learning_rate": 1.89775227295518e-05,
+      "loss": 2.6601,
+      "step": 85
+    },
+    {
+      "epoch": 1.8773132282385196,
+      "grad_norm": 0.09511096775531769,
+      "learning_rate": 1.8944870822287957e-05,
+      "loss": 2.5918,
+      "step": 86
+    },
+    {
+      "epoch": 1.8992460589444824,
+      "grad_norm": 0.06676003336906433,
+      "learning_rate": 1.891173472469672e-05,
+      "loss": 2.5671,
+      "step": 87
+    },
+    {
+      "epoch": 1.9211788896504456,
+      "grad_norm": 0.13803276419639587,
+      "learning_rate": 1.8878116230451615e-05,
+      "loss": 2.6257,
+      "step": 88
+    },
+    {
+      "epoch": 1.9431117203564083,
+      "grad_norm": 0.10050716996192932,
+      "learning_rate": 1.884401715933853e-05,
+      "loss": 2.6772,
+      "step": 89
+    },
+    {
+      "epoch": 1.9650445510623715,
+      "grad_norm": 0.1283024400472641,
+      "learning_rate": 1.8809439357157226e-05,
+      "loss": 2.6121,
+      "step": 90
+    },
+    {
+      "epoch": 1.9869773817683345,
+      "grad_norm": 0.13763798773288727,
+      "learning_rate": 1.8774384695621407e-05,
+      "loss": 2.568,
+      "step": 91
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.22271642088890076,
+      "learning_rate": 1.8738855072257428e-05,
+      "loss": 2.5865,
+      "step": 92
+    },
+    {
+      "epoch": 2.021932830705963,
+      "grad_norm": 0.11131051927804947,
+      "learning_rate": 1.8702852410301556e-05,
+      "loss": 2.5144,
+      "step": 93
+    },
+    {
+      "epoch": 2.043865661411926,
+      "grad_norm": 0.11161550134420395,
+      "learning_rate": 1.8666378658595863e-05,
+      "loss": 2.5182,
+      "step": 94
+    },
+    {
+      "epoch": 2.065798492117889,
+      "grad_norm": 0.08552844822406769,
+      "learning_rate": 1.8629435791482765e-05,
+      "loss": 2.6402,
+      "step": 95
+    },
+    {
+      "epoch": 2.087731322823852,
+      "grad_norm": 0.11428907513618469,
+      "learning_rate": 1.8592025808698116e-05,
+      "loss": 2.6265,
+      "step": 96
+    },
+    {
+      "epoch": 2.109664153529815,
+      "grad_norm": 0.09980299323797226,
+      "learning_rate": 1.8554150735262975e-05,
+      "loss": 2.623,
+      "step": 97
+    },
+    {
+      "epoch": 2.131596984235778,
+      "grad_norm": 0.08849837630987167,
+      "learning_rate": 1.8515812621373998e-05,
+      "loss": 2.627,
+      "step": 98
+    },
+    {
+      "epoch": 2.153529814941741,
+      "grad_norm": 0.09756634384393692,
+      "learning_rate": 1.8477013542292446e-05,
+      "loss": 2.6233,
+      "step": 99
+    },
+    {
+      "epoch": 2.1754626456477038,
+      "grad_norm": 0.07598986476659775,
+      "learning_rate": 1.8437755598231857e-05,
+      "loss": 2.6633,
+      "step": 100
+    },
+    {
+      "epoch": 2.197395476353667,
+      "grad_norm": 0.18077166378498077,
+      "learning_rate": 1.8398040914244363e-05,
+      "loss": 2.6253,
+      "step": 101
+    },
+    {
+      "epoch": 2.2193283070596297,
+      "grad_norm": 0.14006111025810242,
+      "learning_rate": 1.8357871640105648e-05,
+      "loss": 2.6086,
+      "step": 102
+    },
+    {
+      "epoch": 2.241261137765593,
+      "grad_norm": 0.08927474915981293,
+      "learning_rate": 1.8317249950198598e-05,
+      "loss": 2.4877,
+      "step": 103
+    },
+    {
+      "epoch": 2.2631939684715556,
+      "grad_norm": 0.08106345683336258,
+      "learning_rate": 1.8276178043395588e-05,
+      "loss": 2.6523,
+      "step": 104
+    },
+    {
+      "epoch": 2.285126799177519,
+      "grad_norm": 0.09083954989910126,
+      "learning_rate": 1.8234658142939454e-05,
+      "loss": 2.6456,
+      "step": 105
+    },
+    {
+      "epoch": 2.307059629883482,
+      "grad_norm": 0.07053636014461517,
+      "learning_rate": 1.8192692496323158e-05,
+      "loss": 2.6306,
+      "step": 106
+    },
+    {
+      "epoch": 2.3289924605894448,
+      "grad_norm": 0.06668028235435486,
+      "learning_rate": 1.8150283375168112e-05,
+      "loss": 2.5175,
+      "step": 107
+    },
+    {
+      "epoch": 2.350925291295408,
+      "grad_norm": 0.13295046985149384,
+      "learning_rate": 1.8107433075101254e-05,
+      "loss": 2.473,
+      "step": 108
+    },
+    {
+      "epoch": 2.3728581220013707,
+      "grad_norm": 0.09093775600194931,
+      "learning_rate": 1.8064143915630723e-05,
+      "loss": 2.547,
+      "step": 109
+    },
+    {
+      "epoch": 2.394790952707334,
+      "grad_norm": 0.18302415311336517,
+      "learning_rate": 1.8020418240020362e-05,
+      "loss": 2.5652,
+      "step": 110
+    },
+    {
+      "epoch": 2.4167237834132966,
+      "grad_norm": 0.07250549644231796,
+      "learning_rate": 1.7976258415162836e-05,
+      "loss": 2.5828,
+      "step": 111
+    },
+    {
+      "epoch": 2.43865661411926,
+      "grad_norm": 0.3828829526901245,
+      "learning_rate": 1.7931666831451536e-05,
+      "loss": 2.5063,
+      "step": 112
+    },
+    {
+      "epoch": 2.4605894448252226,
+      "grad_norm": 0.5052575469017029,
+      "learning_rate": 1.7886645902651166e-05,
+      "loss": 2.6184,
+      "step": 113
+    },
+    {
+      "epoch": 2.4825222755311858,
+      "grad_norm": 0.07245208323001862,
+      "learning_rate": 1.7841198065767107e-05,
+      "loss": 2.5883,
+      "step": 114
+    },
+    {
+      "epoch": 2.504455106237149,
+      "grad_norm": 0.05822201445698738,
+      "learning_rate": 1.779532578091347e-05,
+      "loss": 2.6,
+      "step": 115
+    },
+    {
+      "epoch": 2.5263879369431117,
+      "grad_norm": 0.08909498155117035,
+      "learning_rate": 1.7749031531179962e-05,
+      "loss": 2.549,
+      "step": 116
+    },
+    {
+      "epoch": 2.5483207676490744,
+      "grad_norm": 0.07801003754138947,
+      "learning_rate": 1.7702317822497457e-05,
+      "loss": 2.5591,
+      "step": 117
+    },
+    {
+      "epoch": 2.5702535983550376,
+      "grad_norm": 0.2434745877981186,
+      "learning_rate": 1.7655187183502344e-05,
+      "loss": 2.6557,
+      "step": 118
+    },
+    {
+      "epoch": 2.592186429061001,
+      "grad_norm": 0.06782998889684677,
+      "learning_rate": 1.7607642165399665e-05,
+      "loss": 2.5268,
+      "step": 119
+    },
+    {
+      "epoch": 2.6141192597669636,
+      "grad_norm": 0.0920061469078064,
+      "learning_rate": 1.755968534182501e-05,
+      "loss": 2.5052,
+      "step": 120
+    },
+    {
+      "epoch": 2.6360520904729268,
+      "grad_norm": 0.0655408501625061,
+      "learning_rate": 1.7511319308705198e-05,
+      "loss": 2.5784,
+      "step": 121
+    },
+    {
+      "epoch": 2.6579849211788895,
+      "grad_norm": 0.13081596791744232,
+      "learning_rate": 1.746254668411778e-05,
+      "loss": 2.5305,
+      "step": 122
+    },
+    {
+      "epoch": 2.6799177518848527,
+      "grad_norm": 0.3778601884841919,
+      "learning_rate": 1.7413370108149288e-05,
+      "loss": 2.5846,
+      "step": 123
+    },
+    {
+      "epoch": 2.701850582590816,
+      "grad_norm": 0.07771953195333481,
+      "learning_rate": 1.7363792242752354e-05,
+      "loss": 2.563,
+      "step": 124
+    },
+    {
+      "epoch": 2.7237834132967786,
+      "grad_norm": 0.06316570937633514,
+      "learning_rate": 1.731381577160161e-05,
+      "loss": 2.5705,
+      "step": 125
+    },
+    {
+      "epoch": 2.7457162440027414,
+      "grad_norm": 0.10998786240816116,
+      "learning_rate": 1.726344339994841e-05,
+      "loss": 2.6364,
+      "step": 126
+    },
+    {
+      "epoch": 2.7676490747087046,
+      "grad_norm": 0.08724892884492874,
+      "learning_rate": 1.7212677854474402e-05,
+      "loss": 2.4682,
+      "step": 127
+    },
+    {
+      "epoch": 2.7895819054146678,
+      "grad_norm": 0.10323834419250488,
+      "learning_rate": 1.7161521883143936e-05,
+      "loss": 2.6225,
+      "step": 128
+    },
+    {
+      "epoch": 2.8115147361206305,
+      "grad_norm": 0.07787463814020157,
+      "learning_rate": 1.7109978255055295e-05,
+      "loss": 2.5786,
+      "step": 129
+    },
+    {
+      "epoch": 2.8334475668265937,
+      "grad_norm": 0.07260199636220932,
+      "learning_rate": 1.705804976029083e-05,
+      "loss": 2.678,
+      "step": 130
+    },
+    {
+      "epoch": 2.8553803975325565,
+      "grad_norm": 0.07246023416519165,
+      "learning_rate": 1.7005739209765906e-05,
+      "loss": 2.4259,
+      "step": 131
+    },
+    {
+      "epoch": 2.8773132282385196,
+      "grad_norm": 0.09231323003768921,
+      "learning_rate": 1.6953049435076768e-05,
+      "loss": 2.6071,
+      "step": 132
+    },
+    {
+      "epoch": 2.8992460589444824,
+      "grad_norm": 0.08409086614847183,
+      "learning_rate": 1.6899983288347248e-05,
+      "loss": 2.4503,
+      "step": 133
+    },
+    {
+      "epoch": 2.9211788896504456,
+      "grad_norm": 0.10303400456905365,
+      "learning_rate": 1.6846543642074382e-05,
+      "loss": 2.5125,
+      "step": 134
+    },
+    {
+      "epoch": 2.9431117203564083,
+      "grad_norm": 0.053891055285930634,
+      "learning_rate": 1.679273338897293e-05,
+      "loss": 2.6059,
+      "step": 135
+    },
+    {
+      "epoch": 2.9650445510623715,
+      "grad_norm": 0.08152981102466583,
+      "learning_rate": 1.6738555441818785e-05,
+      "loss": 2.62,
+      "step": 136
+    },
+    {
+      "epoch": 2.9869773817683347,
+      "grad_norm": 0.06032385304570198,
+      "learning_rate": 1.668401273329129e-05,
+      "loss": 2.534,
+      "step": 137
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.08430641144514084,
+      "learning_rate": 1.6629108215814523e-05,
+      "loss": 2.5903,
+      "step": 138
+    },
+    {
+      "epoch": 3.021932830705963,
+      "grad_norm": 0.0818452313542366,
+      "learning_rate": 1.6573844861397444e-05,
+      "loss": 2.7053,
+      "step": 139
+    },
+    {
+      "epoch": 3.043865661411926,
+      "grad_norm": 0.11237948387861252,
+      "learning_rate": 1.6518225661473045e-05,
+      "loss": 2.4826,
+      "step": 140
+    },
+    {
+      "epoch": 3.065798492117889,
+      "grad_norm": 0.0827915221452713,
+      "learning_rate": 1.6462253626736413e-05,
+      "loss": 2.5895,
+      "step": 141
+    },
+    {
+      "epoch": 3.087731322823852,
+      "grad_norm": 0.11660678684711456,
+      "learning_rate": 1.6405931786981753e-05,
+      "loss": 2.5654,
+      "step": 142
+    },
+    {
+      "epoch": 3.109664153529815,
+      "grad_norm": 0.09041120111942291,
+      "learning_rate": 1.63492631909384e-05,
+      "loss": 2.5197,
+      "step": 143
+    },
+    {
+      "epoch": 3.131596984235778,
+      "grad_norm": 0.06614544242620468,
+      "learning_rate": 1.629225090610577e-05,
+      "loss": 2.5294,
+      "step": 144
+    },
+    {
+      "epoch": 3.153529814941741,
+      "grad_norm": 0.04271303862333298,
+      "learning_rate": 1.6234898018587336e-05,
+      "loss": 2.5046,
+      "step": 145
+    },
+    {
+      "epoch": 3.1754626456477038,
+      "grad_norm": 0.08055449277162552,
+      "learning_rate": 1.6177207632923558e-05,
+      "loss": 2.5966,
+      "step": 146
+    },
+    {
+      "epoch": 3.197395476353667,
+      "grad_norm": 0.06253743171691895,
+      "learning_rate": 1.6119182871923834e-05,
+      "loss": 2.5158,
+      "step": 147
+    },
+    {
+      "epoch": 3.2193283070596297,
+      "grad_norm": 0.08224272727966309,
+      "learning_rate": 1.606082687649748e-05,
+      "loss": 2.6654,
+      "step": 148
+    },
+    {
+      "epoch": 3.241261137765593,
+      "grad_norm": 0.09529576450586319,
+      "learning_rate": 1.6002142805483686e-05,
+      "loss": 2.5656,
+      "step": 149
+    },
+    {
+      "epoch": 3.2631939684715556,
+      "grad_norm": 0.04647281765937805,
+      "learning_rate": 1.5943133835480536e-05,
+      "loss": 2.5524,
+      "step": 150
+    },
+    {
+      "epoch": 3.285126799177519,
+      "grad_norm": 0.07187870889902115,
+      "learning_rate": 1.588380316067307e-05,
+      "loss": 2.5522,
+      "step": 151
+    },
+    {
+      "epoch": 3.307059629883482,
+      "grad_norm": 0.06179989129304886,
+      "learning_rate": 1.582415399266036e-05,
+      "loss": 2.6259,
+      "step": 152
+    },
+    {
+      "epoch": 3.3289924605894448,
+      "grad_norm": 0.0755513459444046,
+      "learning_rate": 1.5764189560281677e-05,
+      "loss": 2.5568,
+      "step": 153
+    },
+    {
+      "epoch": 3.350925291295408,
+      "grad_norm": 0.08130097389221191,
+      "learning_rate": 1.5703913109441715e-05,
+      "loss": 2.6148,
+      "step": 154
+    },
+    {
+      "epoch": 3.3728581220013707,
+      "grad_norm": 0.07435321062803268,
+      "learning_rate": 1.564332790293487e-05,
+      "loss": 2.5511,
+      "step": 155
+    },
+    {
+      "epoch": 3.394790952707334,
+      "grad_norm": 0.05641249567270279,
+      "learning_rate": 1.5582437220268648e-05,
+      "loss": 2.4647,
+      "step": 156
+    },
+    {
+      "epoch": 3.4167237834132966,
+      "grad_norm": 0.05596217140555382,
+      "learning_rate": 1.5521244357486132e-05,
+      "loss": 2.5502,
+      "step": 157
+    },
+    {
+      "epoch": 3.43865661411926,
+      "grad_norm": 0.06887087225914001,
+      "learning_rate": 1.5459752626987563e-05,
+      "loss": 2.4662,
+      "step": 158
+    },
+    {
+      "epoch": 3.4605894448252226,
+      "grad_norm": 0.06323248893022537,
+      "learning_rate": 1.5397965357351035e-05,
+      "loss": 2.5123,
+      "step": 159
+    },
+    {
+      "epoch": 3.4825222755311858,
+      "grad_norm": 0.09084805101156235,
+      "learning_rate": 1.5335885893152335e-05,
+      "loss": 2.4644,
+      "step": 160
+    },
+    {
+      "epoch": 3.504455106237149,
+      "grad_norm": 0.07094909995794296,
+      "learning_rate": 1.5273517594783878e-05,
+      "loss": 2.493,
+      "step": 161
+    },
+    {
+      "epoch": 3.5263879369431117,
+      "grad_norm": 0.04841725155711174,
+      "learning_rate": 1.521086383827282e-05,
+      "loss": 2.4868,
+      "step": 162
+    },
+    {
+      "epoch": 3.5483207676490744,
+      "grad_norm": 0.062218405306339264,
+      "learning_rate": 1.5147928015098309e-05,
+      "loss": 2.4924,
+      "step": 163
+    },
+    {
+      "epoch": 3.5702535983550376,
+      "grad_norm": 0.06784085184335709,
+      "learning_rate": 1.5084713532007906e-05,
+      "loss": 2.5649,
+      "step": 164
+    },
+    {
+      "epoch": 3.592186429061001,
+      "grad_norm": 0.07132422924041748,
+      "learning_rate": 1.5021223810833165e-05,
+      "loss": 2.5442,
+      "step": 165
+    },
+    {
+      "epoch": 3.6141192597669636,
+      "grad_norm": 0.05512155964970589,
+      "learning_rate": 1.4957462288304421e-05,
+      "loss": 2.4669,
+      "step": 166
+    },
+    {
+      "epoch": 3.6360520904729268,
+      "grad_norm": 0.060434065759181976,
+      "learning_rate": 1.489343241586475e-05,
+      "loss": 2.549,
+      "step": 167
+    },
+    {
+      "epoch": 3.6579849211788895,
+      "grad_norm": 0.05476135015487671,
+      "learning_rate": 1.4829137659483144e-05,
+      "loss": 2.5643,
+      "step": 168
+    },
+    {
+      "epoch": 3.6799177518848527,
+      "grad_norm": 0.06881222128868103,
+      "learning_rate": 1.4764581499466895e-05,
+      "loss": 2.3814,
+      "step": 169
+    },
+    {
+      "epoch": 3.701850582590816,
+      "grad_norm": 0.08369456231594086,
+      "learning_rate": 1.4699767430273202e-05,
+      "loss": 2.5987,
+      "step": 170
+    },
+    {
+      "epoch": 3.7237834132967786,
+      "grad_norm": 0.05814111605286598,
+      "learning_rate": 1.4634698960320018e-05,
+      "loss": 2.5668,
+      "step": 171
+    },
+    {
+      "epoch": 3.7457162440027414,
+      "grad_norm": 0.05372776836156845,
+      "learning_rate": 1.4569379611796137e-05,
+      "loss": 2.5888,
+      "step": 172
+    },
+    {
+      "epoch": 3.7676490747087046,
+      "grad_norm": 0.060161709785461426,
+      "learning_rate": 1.4503812920470535e-05,
+      "loss": 2.5052,
+      "step": 173
+    },
+    {
+      "epoch": 3.7895819054146678,
+      "grad_norm": 0.06631386280059814,
+      "learning_rate": 1.443800243550098e-05,
+      "loss": 2.4963,
+      "step": 174
+    },
+    {
+      "epoch": 3.8115147361206305,
+      "grad_norm": 0.06452737748622894,
+      "learning_rate": 1.4371951719241906e-05,
+      "loss": 2.4251,
+      "step": 175
+    },
+    {
+      "epoch": 3.8334475668265937,
+      "grad_norm": 0.09428981691598892,
+      "learning_rate": 1.4305664347051586e-05,
+      "loss": 2.5676,
+      "step": 176
+    },
+    {
+      "epoch": 3.8553803975325565,
+      "grad_norm": 0.050980083644390106,
+      "learning_rate": 1.423914390709861e-05,
+      "loss": 2.5683,
+      "step": 177
+    },
+    {
+      "epoch": 3.8773132282385196,
+      "grad_norm": 0.05442551150918007,
+      "learning_rate": 1.4172394000167625e-05,
+      "loss": 2.5449,
+      "step": 178
+    },
+    {
+      "epoch": 3.8992460589444824,
+      "grad_norm": 0.04739952087402344,
+      "learning_rate": 1.4105418239464452e-05,
+      "loss": 2.5018,
+      "step": 179
+    },
+    {
+      "epoch": 3.9211788896504456,
+      "grad_norm": 0.06977739185094833,
+      "learning_rate": 1.4038220250420487e-05,
+      "loss": 2.5065,
+      "step": 180
+    },
+    {
+      "epoch": 3.9431117203564083,
+      "grad_norm": 0.09621317684650421,
+      "learning_rate": 1.3970803670496453e-05,
+      "loss": 2.5293,
+      "step": 181
+    },
+    {
+      "epoch": 3.9650445510623715,
+      "grad_norm": 0.07425831258296967,
+      "learning_rate": 1.390317214898551e-05,
+      "loss": 2.5197,
+      "step": 182
+    },
+    {
+      "epoch": 3.9869773817683347,
+      "grad_norm": 0.05756077170372009,
+      "learning_rate": 1.3835329346815716e-05,
+      "loss": 2.4661,
+      "step": 183
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.07039082795381546,
+      "learning_rate": 1.3767278936351853e-05,
+      "loss": 2.7058,
+      "step": 184
+    },
+    {
+      "epoch": 4.021932830705963,
+      "grad_norm": 0.06809078902006149,
+      "learning_rate": 1.3699024601196641e-05,
+      "loss": 2.5684,
+      "step": 185
+    },
+    {
+      "epoch": 4.043865661411926,
+      "grad_norm": 0.044164013117551804,
+      "learning_rate": 1.3630570035991352e-05,
+      "loss": 2.4878,
+      "step": 186
+    },
+    {
+      "epoch": 4.065798492117889,
+      "grad_norm": 0.07478977739810944,
+      "learning_rate": 1.3561918946215807e-05,
+      "loss": 2.5928,
+      "step": 187
+    },
+    {
+      "epoch": 4.087731322823852,
+      "grad_norm": 0.053608592599630356,
+      "learning_rate": 1.34930750479878e-05,
+      "loss": 2.5654,
+      "step": 188
+    },
+    {
+      "epoch": 4.109664153529815,
+      "grad_norm": 0.049672599881887436,
+      "learning_rate": 1.3424042067861944e-05,
+      "loss": 2.4353,
+      "step": 189
+    },
+    {
+      "epoch": 4.131596984235778,
+      "grad_norm": 0.07206689566373825,
+      "learning_rate": 1.335482374262795e-05,
+      "loss": 2.5453,
+      "step": 190
+    },
+    {
+      "epoch": 4.153529814941741,
+      "grad_norm": 0.059480294585227966,
+      "learning_rate": 1.3285423819108349e-05,
+      "loss": 2.5138,
+      "step": 191
+    },
+    {
+      "epoch": 4.175462645647704,
+      "grad_norm": 0.05027122050523758,
+      "learning_rate": 1.3215846053955683e-05,
+      "loss": 2.441,
+      "step": 192
+    },
+    {
+      "epoch": 4.197395476353667,
+      "grad_norm": 0.04946836456656456,
+      "learning_rate": 1.3146094213449148e-05,
+      "loss": 2.5398,
+      "step": 193
+    },
+    {
+      "epoch": 4.21932830705963,
+      "grad_norm": 0.073307566344738,
+      "learning_rate": 1.3076172073290726e-05,
+      "loss": 2.5996,
+      "step": 194
+    },
+    {
+      "epoch": 4.241261137765592,
+      "grad_norm": 0.04758650064468384,
+      "learning_rate": 1.3006083418400799e-05,
+      "loss": 2.5598,
+      "step": 195
+    },
+    {
+      "epoch": 4.263193968471556,
+      "grad_norm": 0.0642954632639885,
+      "learning_rate": 1.2935832042713288e-05,
+      "loss": 2.53,
+      "step": 196
+    },
+    {
+      "epoch": 4.285126799177519,
+      "grad_norm": 0.06495189666748047,
+      "learning_rate": 1.2865421748970257e-05,
+      "loss": 2.6442,
+      "step": 197
+    },
+    {
+      "epoch": 4.307059629883482,
+      "grad_norm": 0.05023903772234917,
+      "learning_rate": 1.2794856348516095e-05,
+      "loss": 2.5318,
+      "step": 198
+    },
+    {
+      "epoch": 4.328992460589445,
+      "grad_norm": 0.04791835695505142,
+      "learning_rate": 1.2724139661091188e-05,
+      "loss": 2.5011,
+      "step": 199
+    },
+    {
+      "epoch": 4.3509252912954075,
+      "grad_norm": 0.0522720031440258,
+      "learning_rate": 1.2653275514625165e-05,
+      "loss": 2.5169,
+      "step": 200
+    },
+    {
+      "epoch": 4.460589444825223,
+      "grad_norm": 0.029327793046832085,
+      "learning_rate": 1.1066666666666669e-05,
+      "loss": 2.5083,
+      "step": 201
+    },
+    {
+      "epoch": 4.482522275531186,
+      "grad_norm": 0.03090927191078663,
+      "learning_rate": 1.1022222222222224e-05,
+      "loss": 2.4109,
+      "step": 202
+    },
+    {
+      "epoch": 4.504455106237149,
+      "grad_norm": 0.02843533828854561,
+      "learning_rate": 1.0977777777777779e-05,
+      "loss": 2.4774,
+      "step": 203
+    },
+    {
+      "epoch": 4.526387936943111,
+      "grad_norm": 0.02873154915869236,
+      "learning_rate": 1.0933333333333334e-05,
+      "loss": 2.446,
+      "step": 204
+    },
+    {
+      "epoch": 4.5483207676490744,
+      "grad_norm": 0.028993114829063416,
+      "learning_rate": 1.088888888888889e-05,
+      "loss": 2.4648,
+      "step": 205
+    },
+    {
+      "epoch": 4.570253598355038,
+      "grad_norm": 0.030261656269431114,
+      "learning_rate": 1.0844444444444446e-05,
+      "loss": 2.4367,
+      "step": 206
+    },
+    {
+      "epoch": 4.592186429061001,
+      "grad_norm": 0.02922758273780346,
+      "learning_rate": 1.0800000000000002e-05,
+      "loss": 2.4355,
+      "step": 207
+    },
+    {
+      "epoch": 4.614119259766964,
+      "grad_norm": 0.02983424812555313,
+      "learning_rate": 1.0755555555555557e-05,
+      "loss": 2.3387,
+      "step": 208
+    },
+    {
+      "epoch": 4.636052090472926,
+      "grad_norm": 0.029514959082007408,
+      "learning_rate": 1.0711111111111112e-05,
+      "loss": 2.4137,
+      "step": 209
+    },
+    {
+      "epoch": 4.6579849211788895,
+      "grad_norm": 0.02933017536997795,
+      "learning_rate": 1.0666666666666667e-05,
+      "loss": 2.3596,
+      "step": 210
+    },
+    {
+      "epoch": 4.679917751884853,
+      "grad_norm": 0.031085500493645668,
+      "learning_rate": 1.0622222222222223e-05,
+      "loss": 2.4262,
+      "step": 211
+    },
+    {
+      "epoch": 4.701850582590816,
+      "grad_norm": 0.029262671247124672,
+      "learning_rate": 1.0577777777777778e-05,
+      "loss": 2.3534,
+      "step": 212
+    },
+    {
+      "epoch": 4.723783413296779,
+      "grad_norm": 0.029088234528899193,
+      "learning_rate": 1.0533333333333333e-05,
+      "loss": 2.516,
+      "step": 213
+    },
+    {
+      "epoch": 4.745716244002741,
+      "grad_norm": 0.02934742532670498,
+      "learning_rate": 1.048888888888889e-05,
+      "loss": 2.3666,
+      "step": 214
+    },
+    {
+      "epoch": 4.767649074708705,
+      "grad_norm": 0.029668718576431274,
+      "learning_rate": 1.0444444444444445e-05,
+      "loss": 2.4138,
+      "step": 215
+    },
+    {
+      "epoch": 4.789581905414668,
+      "grad_norm": 0.028572525829076767,
+      "learning_rate": 1.04e-05,
+      "loss": 2.4271,
+      "step": 216
+    },
+    {
+      "epoch": 4.81151473612063,
+      "grad_norm": 0.030027270317077637,
+      "learning_rate": 1.0355555555555557e-05,
+      "loss": 2.5324,
+      "step": 217
+    },
+    {
+      "epoch": 4.833447566826593,
+      "grad_norm": 0.02753366157412529,
+      "learning_rate": 1.0311111111111113e-05,
+      "loss": 2.4258,
+      "step": 218
+    },
+    {
+      "epoch": 4.8553803975325565,
+      "grad_norm": 0.029277922585606575,
+      "learning_rate": 1.0266666666666668e-05,
+      "loss": 2.4316,
+      "step": 219
+    },
+    {
+      "epoch": 4.87731322823852,
+      "grad_norm": 0.028264250606298447,
+      "learning_rate": 1.0222222222222223e-05,
+      "loss": 2.4487,
+      "step": 220
+    },
+    {
+      "epoch": 4.899246058944483,
+      "grad_norm": 0.028467316180467606,
+      "learning_rate": 1.0177777777777778e-05,
+      "loss": 2.4881,
+      "step": 221
+    },
+    {
+      "epoch": 4.921178889650445,
+      "grad_norm": 0.028634829446673393,
+      "learning_rate": 1.0133333333333335e-05,
+      "loss": 2.5201,
+      "step": 222
+    },
+    {
+      "epoch": 4.943111720356408,
+      "grad_norm": 0.028971495106816292,
+      "learning_rate": 1.008888888888889e-05,
+      "loss": 2.4427,
+      "step": 223
+    },
+    {
+      "epoch": 4.9650445510623715,
+      "grad_norm": 0.030583087354898453,
+      "learning_rate": 1.0044444444444446e-05,
+      "loss": 2.3183,
+      "step": 224
+    },
+    {
+      "epoch": 4.986977381768335,
+      "grad_norm": 0.028553923591971397,
+      "learning_rate": 1e-05,
+      "loss": 2.3613,
+      "step": 225
+    },
+    {
+      "epoch": 5.021932830705963,
+      "grad_norm": 0.053584929555654526,
+      "learning_rate": 9.955555555555556e-06,
+      "loss": 4.878,
+      "step": 226
+    },
+    {
+      "epoch": 5.043865661411926,
+      "grad_norm": 0.027103936299681664,
+      "learning_rate": 9.911111111111113e-06,
+      "loss": 2.4959,
+      "step": 227
+    },
+    {
+      "epoch": 5.065798492117889,
+      "grad_norm": 0.0283459834754467,
+      "learning_rate": 9.866666666666668e-06,
+      "loss": 2.4955,
+      "step": 228
+    },
+    {
+      "epoch": 5.087731322823852,
+      "grad_norm": 0.028463320806622505,
+      "learning_rate": 9.822222222222223e-06,
+      "loss": 2.387,
+      "step": 229
+    },
+    {
+      "epoch": 5.109664153529815,
+      "grad_norm": 0.028587784618139267,
+      "learning_rate": 9.777777777777779e-06,
+      "loss": 2.5115,
+      "step": 230
+    },
+    {
+      "epoch": 5.131596984235778,
+      "grad_norm": 0.0302690751850605,
+      "learning_rate": 9.733333333333334e-06,
+      "loss": 2.4082,
+      "step": 231
+    },
+    {
+      "epoch": 5.153529814941741,
+      "grad_norm": 0.027068497613072395,
+      "learning_rate": 9.688888888888889e-06,
+      "loss": 2.5213,
+      "step": 232
+    },
+    {
+      "epoch": 5.175462645647704,
+      "grad_norm": 0.028512222692370415,
+      "learning_rate": 9.644444444444444e-06,
+      "loss": 2.4945,
+      "step": 233
+    },
+    {
+      "epoch": 5.197395476353667,
+      "grad_norm": 0.029183950275182724,
+      "learning_rate": 9.600000000000001e-06,
+      "loss": 2.4854,
+      "step": 234
+    },
+    {
+      "epoch": 5.21932830705963,
+      "grad_norm": 0.028871431946754456,
+      "learning_rate": 9.555555555555556e-06,
+      "loss": 2.4324,
+      "step": 235
+    },
+    {
+      "epoch": 5.241261137765592,
+      "grad_norm": 0.02765199914574623,
+      "learning_rate": 9.511111111111112e-06,
+      "loss": 2.454,
+      "step": 236
+    },
+    {
+      "epoch": 5.263193968471556,
+      "grad_norm": 0.02877068519592285,
+      "learning_rate": 9.466666666666667e-06,
+      "loss": 2.3276,
+      "step": 237
+    },
+    {
+      "epoch": 5.285126799177519,
+      "grad_norm": 0.027244411408901215,
+      "learning_rate": 9.422222222222222e-06,
+      "loss": 2.4658,
+      "step": 238
+    },
+    {
+      "epoch": 5.307059629883482,
+      "grad_norm": 0.028541099280118942,
+      "learning_rate": 9.377777777777779e-06,
+      "loss": 2.4584,
+      "step": 239
+    },
+    {
+      "epoch": 5.328992460589445,
+      "grad_norm": 0.028118062764406204,
+      "learning_rate": 9.333333333333334e-06,
+      "loss": 2.484,
+      "step": 240
+    },
+    {
+      "epoch": 5.3509252912954075,
+      "grad_norm": 0.027342138811945915,
+      "learning_rate": 9.28888888888889e-06,
+      "loss": 2.3875,
+      "step": 241
+    },
+    {
+      "epoch": 5.372858122001371,
+      "grad_norm": 0.02763846516609192,
+      "learning_rate": 9.244444444444445e-06,
+      "loss": 2.4074,
+      "step": 242
+    },
+    {
+      "epoch": 5.394790952707334,
+      "grad_norm": 0.027283240109682083,
+      "learning_rate": 9.200000000000002e-06,
+      "loss": 2.4734,
+      "step": 243
+    },
+    {
+      "epoch": 5.416723783413297,
+      "grad_norm": 0.027629459276795387,
+      "learning_rate": 9.155555555555557e-06,
+      "loss": 2.3984,
+      "step": 244
+    },
+    {
+      "epoch": 5.438656614119259,
+      "grad_norm": 0.026949698105454445,
+      "learning_rate": 9.111111111111112e-06,
+      "loss": 2.4766,
+      "step": 245
+    },
+    {
+      "epoch": 5.460589444825223,
+      "grad_norm": 0.02796311490237713,
+      "learning_rate": 9.066666666666667e-06,
+      "loss": 2.4041,
+      "step": 246
+    },
+    {
+      "epoch": 5.482522275531186,
+      "grad_norm": 0.02679138071835041,
+      "learning_rate": 9.022222222222223e-06,
+      "loss": 2.4235,
+      "step": 247
+    },
+    {
+      "epoch": 5.504455106237149,
+      "grad_norm": 0.026427317410707474,
+      "learning_rate": 8.977777777777778e-06,
+      "loss": 2.4135,
+      "step": 248
+    },
+    {
+      "epoch": 5.526387936943111,
+      "grad_norm": 0.027638597413897514,
+      "learning_rate": 8.933333333333333e-06,
+      "loss": 2.4062,
+      "step": 249
+    },
+    {
+      "epoch": 5.5483207676490744,
+      "grad_norm": 0.02851198799908161,
+      "learning_rate": 8.888888888888888e-06,
+      "loss": 2.3332,
+      "step": 250
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 450,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 50,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 5.461794998137651e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-250/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:add45799a67f153bafa276db61374a176531e06e777cc6ded0d3da54dc515062
+size 5688

checkpoint-300/README.md

@@ -0,0 +1,202 @@
+---
+base_model: unsloth/qwen2.5-3b-bnb-4bit
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.14.0

checkpoint-300/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "unsloth/qwen2.5-3b-bnb-4bit",
+  "bias": "none",
+  "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": 8,
+  "lora_bias": false,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "o_proj",
+    "q_proj",
+    "k_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-300/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07467a4f6928a25ad5d7a28f7d46d29621b3ff12186884fab011411ef350035f
+size 59021064

checkpoint-300/added_tokens.json

@@ -0,0 +1,25 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|PAD_TOKEN|>": 151665,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

checkpoint-300/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:649d366874685aa63fb16d72f1561bfbfb730fa56c61ebc9af25399c3caa4bce
+size 31039186

checkpoint-300/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ab483104aa9e57229c1f6a249723f9b17044996dac0cca5bbb886666df7215e
+size 14244

checkpoint-300/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fee19ee4f942d5562c99a834fbd18afe8c3c56b682a8faff6df172cc35572134
+size 1064