Upload task output 7673621a-3beb-4b7e-9253-68dd30966ad5

.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/Qwen2-0.5B
+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 0.15.1

adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "unsloth/Qwen2-0.5B",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": "gaussian",
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 1280,
+  "lora_bias": false,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 128,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "k_proj",
+    "v_proj",
+    "gate_proj",
+    "up_proj",
+    "down_proj",
+    "q_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:faf965173ee04206facc9b2d95b0224e762a2c2adc47951b7e4b42f48b744f2c
+size 281587880

added_tokens.json

@@ -0,0 +1,6 @@
+{
+  "<|PAD_TOKEN|>": 151646,
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644
+}

loss.txt

@@ -0,0 +1 @@
+300,0.05141889303922653

special_tokens_map.json

@@ -0,0 +1,20 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "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
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9479047c22047670077878de944c696032b1a81049beeb6e99fbda7fb93e395a
+size 11418456

tokenizer_config.json

@@ -0,0 +1,53 @@
+{
+  "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": "<|PAD_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 32768,
+  "pad_token": "<|PAD_TOKEN|>",
+  "padding_side": "left",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_state.json

@@ -0,0 +1,500 @@
+{
+  "best_global_step": 300,
+  "best_metric": 0.05141889303922653,
+  "best_model_checkpoint": "/workspace/scripts/soutputs/7673621a-3beb-4b7e-9253-68dd30966ad5_0/checkpoint-300",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 300,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.1,
+      "grad_norm": 6.584600925445557,
+      "learning_rate": 2.7907215657142855e-05,
+      "loss": 0.3762,
+      "step": 10
+    },
+    {
+      "epoch": 0.1,
+      "eval_loss": 0.28799575567245483,
+      "eval_runtime": 1.0684,
+      "eval_samples_per_second": 15.912,
+      "eval_steps_per_second": 15.912,
+      "step": 10
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 4.3658952713012695,
+      "learning_rate": 5.891523305396825e-05,
+      "loss": 0.1712,
+      "step": 20
+    },
+    {
+      "epoch": 0.2,
+      "eval_loss": 0.13228200376033783,
+      "eval_runtime": 1.0569,
+      "eval_samples_per_second": 16.084,
+      "eval_steps_per_second": 16.084,
+      "step": 20
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 3.1832616329193115,
+      "learning_rate": 8.992325045079366e-05,
+      "loss": 0.1465,
+      "step": 30
+    },
+    {
+      "epoch": 0.3,
+      "eval_loss": 0.1652909815311432,
+      "eval_runtime": 1.0578,
+      "eval_samples_per_second": 16.072,
+      "eval_steps_per_second": 16.072,
+      "step": 30
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.6943491101264954,
+      "learning_rate": 0.00010847621103058175,
+      "loss": 0.1381,
+      "step": 40
+    },
+    {
+      "epoch": 0.4,
+      "eval_loss": 0.1189466342329979,
+      "eval_runtime": 1.0651,
+      "eval_samples_per_second": 15.96,
+      "eval_steps_per_second": 15.96,
+      "step": 40
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 2.4766085147857666,
+      "learning_rate": 0.0001078942380533427,
+      "loss": 0.1187,
+      "step": 50
+    },
+    {
+      "epoch": 0.5,
+      "eval_loss": 0.11941006779670715,
+      "eval_runtime": 1.0598,
+      "eval_samples_per_second": 16.04,
+      "eval_steps_per_second": 16.04,
+      "step": 50
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.44038501381874084,
+      "learning_rate": 0.00010667367672602237,
+      "loss": 0.1139,
+      "step": 60
+    },
+    {
+      "epoch": 0.6,
+      "eval_loss": 0.11109943687915802,
+      "eval_runtime": 1.0569,
+      "eval_samples_per_second": 16.085,
+      "eval_steps_per_second": 16.085,
+      "step": 60
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 0.22996506094932556,
+      "learning_rate": 0.00010483166105415293,
+      "loss": 0.1113,
+      "step": 70
+    },
+    {
+      "epoch": 0.7,
+      "eval_loss": 0.11180288344621658,
+      "eval_runtime": 1.0567,
+      "eval_samples_per_second": 16.087,
+      "eval_steps_per_second": 16.087,
+      "step": 70
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.6509195566177368,
+      "learning_rate": 0.00010239404890001927,
+      "loss": 0.1104,
+      "step": 80
+    },
+    {
+      "epoch": 0.8,
+      "eval_loss": 0.10831819474697113,
+      "eval_runtime": 1.0589,
+      "eval_samples_per_second": 16.054,
+      "eval_steps_per_second": 16.054,
+      "step": 80
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 0.8517053723335266,
+      "learning_rate": 9.939505899495366e-05,
+      "loss": 0.1081,
+      "step": 90
+    },
+    {
+      "epoch": 0.9,
+      "eval_loss": 0.10679890215396881,
+      "eval_runtime": 1.0581,
+      "eval_samples_per_second": 16.066,
+      "eval_steps_per_second": 16.066,
+      "step": 90
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.0003941059112549,
+      "learning_rate": 9.587679058335631e-05,
+      "loss": 0.1102,
+      "step": 100
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.1071733757853508,
+      "eval_runtime": 1.0572,
+      "eval_samples_per_second": 16.08,
+      "eval_steps_per_second": 16.08,
+      "step": 100
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.1071733757853508,
+      "eval_runtime": 1.0451,
+      "eval_samples_per_second": 16.266,
+      "eval_steps_per_second": 16.266,
+      "step": 100
+    },
+    {
+      "epoch": 1.1,
+      "grad_norm": 0.46666786074638367,
+      "learning_rate": 9.188863244158655e-05,
+      "loss": 0.1056,
+      "step": 110
+    },
+    {
+      "epoch": 1.1,
+      "eval_loss": 0.10584582388401031,
+      "eval_runtime": 1.0571,
+      "eval_samples_per_second": 16.081,
+      "eval_steps_per_second": 16.081,
+      "step": 110
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 0.23497658967971802,
+      "learning_rate": 8.74865695678044e-05,
+      "loss": 0.1028,
+      "step": 120
+    },
+    {
+      "epoch": 1.2,
+      "eval_loss": 0.10479530692100525,
+      "eval_runtime": 1.0571,
+      "eval_samples_per_second": 16.082,
+      "eval_steps_per_second": 16.082,
+      "step": 120
+    },
+    {
+      "epoch": 1.3,
+      "grad_norm": 0.4804553687572479,
+      "learning_rate": 8.273239727531691e-05,
+      "loss": 0.1014,
+      "step": 130
+    },
+    {
+      "epoch": 1.3,
+      "eval_loss": 0.10915076732635498,
+      "eval_runtime": 1.0574,
+      "eval_samples_per_second": 16.077,
+      "eval_steps_per_second": 16.077,
+      "step": 130
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 0.6005699038505554,
+      "learning_rate": 7.769285372183642e-05,
+      "loss": 0.0992,
+      "step": 140
+    },
+    {
+      "epoch": 1.4,
+      "eval_loss": 0.10174299776554108,
+      "eval_runtime": 1.0574,
+      "eval_samples_per_second": 16.077,
+      "eval_steps_per_second": 16.077,
+      "step": 140
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 0.3633825182914734,
+      "learning_rate": 7.243868305203808e-05,
+      "loss": 0.0917,
+      "step": 150
+    },
+    {
+      "epoch": 1.5,
+      "eval_loss": 0.09136371314525604,
+      "eval_runtime": 1.0595,
+      "eval_samples_per_second": 16.045,
+      "eval_steps_per_second": 16.045,
+      "step": 150
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 0.37585020065307617,
+      "learning_rate": 6.704364230484171e-05,
+      "loss": 0.0885,
+      "step": 160
+    },
+    {
+      "epoch": 1.6,
+      "eval_loss": 0.09008041769266129,
+      "eval_runtime": 1.0596,
+      "eval_samples_per_second": 16.044,
+      "eval_steps_per_second": 16.044,
+      "step": 160
+    },
+    {
+      "epoch": 1.7,
+      "grad_norm": 0.5123192071914673,
+      "learning_rate": 6.158346602626281e-05,
+      "loss": 0.0833,
+      "step": 170
+    },
+    {
+      "epoch": 1.7,
+      "eval_loss": 0.08343079686164856,
+      "eval_runtime": 1.058,
+      "eval_samples_per_second": 16.067,
+      "eval_steps_per_second": 16.067,
+      "step": 170
+    },
+    {
+      "epoch": 1.8,
+      "grad_norm": 0.3181597888469696,
+      "learning_rate": 5.6134803122398577e-05,
+      "loss": 0.0816,
+      "step": 180
+    },
+    {
+      "epoch": 1.8,
+      "eval_loss": 0.08084844052791595,
+      "eval_runtime": 1.0571,
+      "eval_samples_per_second": 16.081,
+      "eval_steps_per_second": 16.081,
+      "step": 180
+    },
+    {
+      "epoch": 1.9,
+      "grad_norm": 0.500211775302887,
+      "learning_rate": 5.07741408768029e-05,
+      "loss": 0.0787,
+      "step": 190
+    },
+    {
+      "epoch": 1.9,
+      "eval_loss": 0.07607461512088776,
+      "eval_runtime": 1.0567,
+      "eval_samples_per_second": 16.088,
+      "eval_steps_per_second": 16.088,
+      "step": 190
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.4431775212287903,
+      "learning_rate": 4.557673123668739e-05,
+      "loss": 0.0745,
+      "step": 200
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.0782596543431282,
+      "eval_runtime": 1.058,
+      "eval_samples_per_second": 16.068,
+      "eval_steps_per_second": 16.068,
+      "step": 200
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.0782596543431282,
+      "eval_runtime": 1.0466,
+      "eval_samples_per_second": 16.243,
+      "eval_steps_per_second": 16.243,
+      "step": 200
+    },
+    {
+      "epoch": 2.1,
+      "grad_norm": 0.4298710823059082,
+      "learning_rate": 4.0615534440536785e-05,
+      "loss": 0.0695,
+      "step": 210
+    },
+    {
+      "epoch": 2.1,
+      "eval_loss": 0.07331126183271408,
+      "eval_runtime": 1.0586,
+      "eval_samples_per_second": 16.06,
+      "eval_steps_per_second": 16.06,
+      "step": 210
+    },
+    {
+      "epoch": 2.2,
+      "grad_norm": 0.5784715414047241,
+      "learning_rate": 3.59601948162916e-05,
+      "loss": 0.0677,
+      "step": 220
+    },
+    {
+      "epoch": 2.2,
+      "eval_loss": 0.07047608494758606,
+      "eval_runtime": 1.0565,
+      "eval_samples_per_second": 16.09,
+      "eval_steps_per_second": 16.09,
+      "step": 220
+    },
+    {
+      "epoch": 2.3,
+      "grad_norm": 0.5269572734832764,
+      "learning_rate": 3.1676063127645905e-05,
+      "loss": 0.0636,
+      "step": 230
+    },
+    {
+      "epoch": 2.3,
+      "eval_loss": 0.06599157303571701,
+      "eval_runtime": 1.0589,
+      "eval_samples_per_second": 16.055,
+      "eval_steps_per_second": 16.055,
+      "step": 230
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 0.6816230416297913,
+      "learning_rate": 2.7823279192575794e-05,
+      "loss": 0.0619,
+      "step": 240
+    },
+    {
+      "epoch": 2.4,
+      "eval_loss": 0.06297663599252701,
+      "eval_runtime": 1.0584,
+      "eval_samples_per_second": 16.061,
+      "eval_steps_per_second": 16.061,
+      "step": 240
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 0.6032505631446838,
+      "learning_rate": 2.4455927652123132e-05,
+      "loss": 0.057,
+      "step": 250
+    },
+    {
+      "epoch": 2.5,
+      "eval_loss": 0.06109685078263283,
+      "eval_runtime": 1.0609,
+      "eval_samples_per_second": 16.024,
+      "eval_steps_per_second": 16.024,
+      "step": 250
+    },
+    {
+      "epoch": 2.6,
+      "grad_norm": 0.4768277406692505,
+      "learning_rate": 2.1621278740590256e-05,
+      "loss": 0.0553,
+      "step": 260
+    },
+    {
+      "epoch": 2.6,
+      "eval_loss": 0.05680255964398384,
+      "eval_runtime": 1.0587,
+      "eval_samples_per_second": 16.057,
+      "eval_steps_per_second": 16.057,
+      "step": 260
+    },
+    {
+      "epoch": 2.7,
+      "grad_norm": 0.514683187007904,
+      "learning_rate": 1.9359124715068038e-05,
+      "loss": 0.0529,
+      "step": 270
+    },
+    {
+      "epoch": 2.7,
+      "eval_loss": 0.0532442182302475,
+      "eval_runtime": 1.0589,
+      "eval_samples_per_second": 16.055,
+      "eval_steps_per_second": 16.055,
+      "step": 270
+    },
+    {
+      "epoch": 2.8,
+      "grad_norm": 0.49393996596336365,
+      "learning_rate": 1.7701221259372036e-05,
+      "loss": 0.051,
+      "step": 280
+    },
+    {
+      "epoch": 2.8,
+      "eval_loss": 0.05284074693918228,
+      "eval_runtime": 1.0586,
+      "eval_samples_per_second": 16.059,
+      "eval_steps_per_second": 16.059,
+      "step": 280
+    },
+    {
+      "epoch": 2.9,
+      "grad_norm": 0.4914567768573761,
+      "learning_rate": 1.6670841703851018e-05,
+      "loss": 0.0512,
+      "step": 290
+    },
+    {
+      "epoch": 2.9,
+      "eval_loss": 0.05378786474466324,
+      "eval_runtime": 1.0571,
+      "eval_samples_per_second": 16.082,
+      "eval_steps_per_second": 16.082,
+      "step": 290
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.45328783988952637,
+      "learning_rate": 1.628245031884467e-05,
+      "loss": 0.0507,
+      "step": 300
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.05141889303922653,
+      "eval_runtime": 1.0576,
+      "eval_samples_per_second": 16.073,
+      "eval_steps_per_second": 16.073,
+      "step": 300
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 300,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.010448199581696e+17,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7bb21190ad7ef19565bbde0a666ead0e17a8ecc55048cda7d102ccfe433c7c1e
+size 5688