Checkpoint backup 2237

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,202 @@
+---
+base_model: unsloth/Qwen3-8B-unsloth-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 0.15.2

adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "unsloth/Qwen3-8B-unsloth-bnb-4bit",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "down_proj",
+    "up_proj",
+    "o_proj",
+    "v_proj",
+    "q_proj",
+    "k_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc7d58eeaecb76c281283b1dbfb155b387e34375f463c3cb57e71d0cfc0b6c04
+size 349243752

added_tokens.json

@@ -0,0 +1,28 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 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
+}

chat_template.jinja

@@ -0,0 +1,6 @@
+{% for message in messages %}{% if message['role'] == 'user' %}<|im_start|>user
+{{ message['content'] }}<|im_end|>
+{% elif message['role'] == 'assistant' %}<|im_start|>assistant
+{{ message['content'] }}<|im_end|>
+{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant
+{% endif %}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a328f3d6ef3bc7b5320ffd651122eca6df818ca23056556aacdbf921d2970742
+size 177908997

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b0fddee376f3c5d553c1ae7bddca8f93e8e2732b91728bbdf07960418a191e2
+size 14645

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c39bb2a5d4848eeb28b11a77e322996e28ca2866b96c5d8f5046cd48a71808b
+size 1465

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": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|vision_pad|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae1a036a9837df9caeebb840d09d80e8feef0f6d2bae982970d1ad34f5946aff
+size 11422753

tokenizer_config.json

@@ -0,0 +1,240 @@
+{
+  "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": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "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": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 40960,
+  "pad_token": "<|vision_pad|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_state.json

@@ -0,0 +1,422 @@
+{
+  "best_global_step": 1313,
+  "best_metric": 0.512985110282898,
+  "best_model_checkpoint": "outputs_v3/checkpoint-1313",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 1313,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0007618322064565279,
+      "grad_norm": 1.4868226051330566,
+      "learning_rate": 0.0,
+      "loss": 2.9396,
+      "step": 1
+    },
+    {
+      "epoch": 0.019045805161413198,
+      "grad_norm": 1.2571601867675781,
+      "learning_rate": 1.008403361344538e-05,
+      "loss": 2.7963,
+      "step": 25
+    },
+    {
+      "epoch": 0.038091610322826396,
+      "grad_norm": 0.6987431645393372,
+      "learning_rate": 2.058823529411765e-05,
+      "loss": 2.1442,
+      "step": 50
+    },
+    {
+      "epoch": 0.0571374154842396,
+      "grad_norm": 0.3330633044242859,
+      "learning_rate": 3.1092436974789916e-05,
+      "loss": 1.1326,
+      "step": 75
+    },
+    {
+      "epoch": 0.07618322064565279,
+      "grad_norm": 0.23947548866271973,
+      "learning_rate": 4.159663865546219e-05,
+      "loss": 0.7952,
+      "step": 100
+    },
+    {
+      "epoch": 0.09522902580706599,
+      "grad_norm": 0.3273511528968811,
+      "learning_rate": 4.9999788640180545e-05,
+      "loss": 0.6819,
+      "step": 125
+    },
+    {
+      "epoch": 0.1142748309684792,
+      "grad_norm": 0.1918083131313324,
+      "learning_rate": 4.999239142174581e-05,
+      "loss": 0.6792,
+      "step": 150
+    },
+    {
+      "epoch": 0.1333206361298924,
+      "grad_norm": 0.22439052164554596,
+      "learning_rate": 4.9974429785904524e-05,
+      "loss": 0.6258,
+      "step": 175
+    },
+    {
+      "epoch": 0.15236644129130558,
+      "grad_norm": 0.24658527970314026,
+      "learning_rate": 4.994591132513616e-05,
+      "loss": 0.6512,
+      "step": 200
+    },
+    {
+      "epoch": 0.1714122464527188,
+      "grad_norm": 0.24695466458797455,
+      "learning_rate": 4.990684809434646e-05,
+      "loss": 0.6244,
+      "step": 225
+    },
+    {
+      "epoch": 0.19045805161413198,
+      "grad_norm": 0.26622363924980164,
+      "learning_rate": 4.985725660577184e-05,
+      "loss": 0.5796,
+      "step": 250
+    },
+    {
+      "epoch": 0.2095038567755452,
+      "grad_norm": 0.2716868817806244,
+      "learning_rate": 4.979715782199951e-05,
+      "loss": 0.6268,
+      "step": 275
+    },
+    {
+      "epoch": 0.2285496619369584,
+      "grad_norm": 0.2595020830631256,
+      "learning_rate": 4.972657714710653e-05,
+      "loss": 0.5945,
+      "step": 300
+    },
+    {
+      "epoch": 0.24759546709837157,
+      "grad_norm": 0.26612213253974915,
+      "learning_rate": 4.9645544415921344e-05,
+      "loss": 0.5592,
+      "step": 325
+    },
+    {
+      "epoch": 0.2666412722597848,
+      "grad_norm": 0.24327930808067322,
+      "learning_rate": 4.955409388141243e-05,
+      "loss": 0.631,
+      "step": 350
+    },
+    {
+      "epoch": 0.285687077421198,
+      "grad_norm": 0.2701154947280884,
+      "learning_rate": 4.9452264200209426e-05,
+      "loss": 0.569,
+      "step": 375
+    },
+    {
+      "epoch": 0.30473288258261116,
+      "grad_norm": 0.2970716953277588,
+      "learning_rate": 4.9340098416262714e-05,
+      "loss": 0.5791,
+      "step": 400
+    },
+    {
+      "epoch": 0.32377868774402435,
+      "grad_norm": 0.26807665824890137,
+      "learning_rate": 4.921764394264855e-05,
+      "loss": 0.5411,
+      "step": 425
+    },
+    {
+      "epoch": 0.3428244929054376,
+      "grad_norm": 0.2829282283782959,
+      "learning_rate": 4.908495254152731e-05,
+      "loss": 0.5746,
+      "step": 450
+    },
+    {
+      "epoch": 0.3618702980668508,
+      "grad_norm": 0.3086259961128235,
+      "learning_rate": 4.8942080302263306e-05,
+      "loss": 0.5579,
+      "step": 475
+    },
+    {
+      "epoch": 0.38091610322826397,
+      "grad_norm": 0.2836249768733978,
+      "learning_rate": 4.878908761771554e-05,
+      "loss": 0.5702,
+      "step": 500
+    },
+    {
+      "epoch": 0.39996190838967716,
+      "grad_norm": 0.31077441573143005,
+      "learning_rate": 4.862603915870933e-05,
+      "loss": 0.542,
+      "step": 525
+    },
+    {
+      "epoch": 0.4190077135510904,
+      "grad_norm": 0.25948625802993774,
+      "learning_rate": 4.845300384669958e-05,
+      "loss": 0.5407,
+      "step": 550
+    },
+    {
+      "epoch": 0.4380535187125036,
+      "grad_norm": 0.26232826709747314,
+      "learning_rate": 4.827005482463733e-05,
+      "loss": 0.5419,
+      "step": 575
+    },
+    {
+      "epoch": 0.4570993238739168,
+      "grad_norm": 0.31146982312202454,
+      "learning_rate": 4.807726942605184e-05,
+      "loss": 0.5637,
+      "step": 600
+    },
+    {
+      "epoch": 0.47614512903532996,
+      "grad_norm": 0.2727930247783661,
+      "learning_rate": 4.7874729142361285e-05,
+      "loss": 0.5695,
+      "step": 625
+    },
+    {
+      "epoch": 0.49519093419674315,
+      "grad_norm": 0.2699703872203827,
+      "learning_rate": 4.76625195884259e-05,
+      "loss": 0.5232,
+      "step": 650
+    },
+    {
+      "epoch": 0.5142367393581564,
+      "grad_norm": 0.29125288128852844,
+      "learning_rate": 4.7440730466358116e-05,
+      "loss": 0.5954,
+      "step": 675
+    },
+    {
+      "epoch": 0.5332825445195696,
+      "grad_norm": 0.2931804060935974,
+      "learning_rate": 4.720945552760503e-05,
+      "loss": 0.5733,
+      "step": 700
+    },
+    {
+      "epoch": 0.5523283496809828,
+      "grad_norm": 0.298470139503479,
+      "learning_rate": 4.69687925333191e-05,
+      "loss": 0.5817,
+      "step": 725
+    },
+    {
+      "epoch": 0.571374154842396,
+      "grad_norm": 0.2937164306640625,
+      "learning_rate": 4.6718843213034067e-05,
+      "loss": 0.5482,
+      "step": 750
+    },
+    {
+      "epoch": 0.5904199600038091,
+      "grad_norm": 0.31254154443740845,
+      "learning_rate": 4.645971322166327e-05,
+      "loss": 0.5594,
+      "step": 775
+    },
+    {
+      "epoch": 0.6094657651652223,
+      "grad_norm": 0.2997235953807831,
+      "learning_rate": 4.619151209483878e-05,
+      "loss": 0.5867,
+      "step": 800
+    },
+    {
+      "epoch": 0.6285115703266355,
+      "grad_norm": 0.3079950213432312,
+      "learning_rate": 4.591435320261011e-05,
+      "loss": 0.5839,
+      "step": 825
+    },
+    {
+      "epoch": 0.6475573754880487,
+      "grad_norm": 0.2768675982952118,
+      "learning_rate": 4.5628353701522055e-05,
+      "loss": 0.5709,
+      "step": 850
+    },
+    {
+      "epoch": 0.666603180649462,
+      "grad_norm": 0.2898074686527252,
+      "learning_rate": 4.533363448509204e-05,
+      "loss": 0.5604,
+      "step": 875
+    },
+    {
+      "epoch": 0.6856489858108752,
+      "grad_norm": 0.3034629225730896,
+      "learning_rate": 4.503032013270774e-05,
+      "loss": 0.527,
+      "step": 900
+    },
+    {
+      "epoch": 0.7046947909722884,
+      "grad_norm": 0.3099200129508972,
+      "learning_rate": 4.471853885696673e-05,
+      "loss": 0.5484,
+      "step": 925
+    },
+    {
+      "epoch": 0.7237405961337016,
+      "grad_norm": 0.27591314911842346,
+      "learning_rate": 4.4398422449480356e-05,
+      "loss": 0.539,
+      "step": 950
+    },
+    {
+      "epoch": 0.7427864012951148,
+      "grad_norm": 0.297590434551239,
+      "learning_rate": 4.407010622516469e-05,
+      "loss": 0.5427,
+      "step": 975
+    },
+    {
+      "epoch": 0.7618322064565279,
+      "grad_norm": 0.2939580976963043,
+      "learning_rate": 4.373372896504215e-05,
+      "loss": 0.5544,
+      "step": 1000
+    },
+    {
+      "epoch": 0.7808780116179411,
+      "grad_norm": 0.3100650906562805,
+      "learning_rate": 4.338943285757812e-05,
+      "loss": 0.5418,
+      "step": 1025
+    },
+    {
+      "epoch": 0.7999238167793543,
+      "grad_norm": 0.31046804785728455,
+      "learning_rate": 4.303736343857704e-05,
+      "loss": 0.5492,
+      "step": 1050
+    },
+    {
+      "epoch": 0.8189696219407675,
+      "grad_norm": 0.31424999237060547,
+      "learning_rate": 4.267766952966369e-05,
+      "loss": 0.5501,
+      "step": 1075
+    },
+    {
+      "epoch": 0.8380154271021808,
+      "grad_norm": 0.3023451268672943,
+      "learning_rate": 4.2310503175375484e-05,
+      "loss": 0.5701,
+      "step": 1100
+    },
+    {
+      "epoch": 0.857061232263594,
+      "grad_norm": 0.2925208806991577,
+      "learning_rate": 4.1936019578892394e-05,
+      "loss": 0.5296,
+      "step": 1125
+    },
+    {
+      "epoch": 0.8761070374250072,
+      "grad_norm": 0.2963685691356659,
+      "learning_rate": 4.1554377036431816e-05,
+      "loss": 0.5826,
+      "step": 1150
+    },
+    {
+      "epoch": 0.8951528425864204,
+      "grad_norm": 0.30757901072502136,
+      "learning_rate": 4.116573687033583e-05,
+      "loss": 0.5844,
+      "step": 1175
+    },
+    {
+      "epoch": 0.9141986477478335,
+      "grad_norm": 0.3231395184993744,
+      "learning_rate": 4.0770263360879435e-05,
+      "loss": 0.5727,
+      "step": 1200
+    },
+    {
+      "epoch": 0.9332444529092467,
+      "grad_norm": 0.29189741611480713,
+      "learning_rate": 4.0368123676828385e-05,
+      "loss": 0.5553,
+      "step": 1225
+    },
+    {
+      "epoch": 0.9522902580706599,
+      "grad_norm": 0.3302098512649536,
+      "learning_rate": 3.995948780477605e-05,
+      "loss": 0.5463,
+      "step": 1250
+    },
+    {
+      "epoch": 0.9713360632320731,
+      "grad_norm": 0.340754896402359,
+      "learning_rate": 3.954452847728919e-05,
+      "loss": 0.5442,
+      "step": 1275
+    },
+    {
+      "epoch": 0.9903818683934863,
+      "grad_norm": 0.302099347114563,
+      "learning_rate": 3.912342109989296e-05,
+      "loss": 0.5517,
+      "step": 1300
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.512985110282898,
+      "eval_runtime": 190.5141,
+      "eval_samples_per_second": 19.458,
+      "eval_steps_per_second": 4.866,
+      "step": 1313
+    }
+  ],
+  "logging_steps": 25,
+  "max_steps": 3939,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 2,
+        "early_stopping_threshold": 0.001
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 0
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.450179662830715e+17,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a75ffe960bb7c8e891c0badf4b0056801eb6431277c701860933e86bf88c9d5e
+size 5969