Training in progress, step 50, checkpoint

last-checkpoint/README.md

@@ -0,0 +1,202 @@
+---
+base_model: unsloth/SmolLM2-1.7B-Instruct
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.13.2

last-checkpoint/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "unsloth/SmolLM2-1.7B-Instruct",
+  "bias": "none",
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 128,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "gate_proj",
+    "down_proj",
+    "k_proj",
+    "o_proj",
+    "v_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

last-checkpoint/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4256d7260da585cb38362625d5c6c6e714abf4c45c670df626b52ddd7d74b7d
+size 289452128

last-checkpoint/added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<|PAD_TOKEN|>": 49152
+}

last-checkpoint/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8cdfe117c660bcfd09b6659bcb97f09c2056cd54396e7bf0eac94e04133ba46
+size 147359892

last-checkpoint/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1983f721b360ca749bb29929a8141bbaf32429407675fa911781f839e1292ce6
+size 14244

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14c7988274ea42082ca98c4badf72b98ef1698024d0fb100dd463f8f4922415a
+size 1064

last-checkpoint/special_tokens_map.json

@@ -0,0 +1,34 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": {
+    "content": "<|im_start|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|PAD_TOKEN|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "�",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

last-checkpoint/tokenizer_config.json

@@ -0,0 +1,171 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<repo_name>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<reponame>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "<file_sep>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "<filename>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "7": {
+      "content": "<gh_stars>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "8": {
+      "content": "<issue_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "9": {
+      "content": "<issue_comment>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "10": {
+      "content": "<issue_closed>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "11": {
+      "content": "<jupyter_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "12": {
+      "content": "<jupyter_text>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "13": {
+      "content": "<jupyter_code>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "14": {
+      "content": "<jupyter_output>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "15": {
+      "content": "<jupyter_script>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "16": {
+      "content": "<empty_output>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "24211": {
+      "content": "�",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49152": {
+      "content": "<|PAD_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": "<|im_start|>",
+  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "model_max_length": 2048,
+  "pad_token": "<|PAD_TOKEN|>",
+  "padding_side": "left",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "�",
+  "vocab_size": 49152
+}

last-checkpoint/trainer_state.json

@@ -0,0 +1,408 @@
+{
+  "best_metric": 1.5464621782302856,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.037091988130563795,
+  "eval_steps": 50,
+  "global_step": 50,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.000741839762611276,
+      "grad_norm": 0.34722599387168884,
+      "learning_rate": 1.0017e-05,
+      "loss": 1.6873,
+      "step": 1
+    },
+    {
+      "epoch": 0.000741839762611276,
+      "eval_loss": 1.8154631853103638,
+      "eval_runtime": 24.6231,
+      "eval_samples_per_second": 23.068,
+      "eval_steps_per_second": 5.767,
+      "step": 1
+    },
+    {
+      "epoch": 0.001483679525222552,
+      "grad_norm": 0.3773996829986572,
+      "learning_rate": 2.0034e-05,
+      "loss": 1.6132,
+      "step": 2
+    },
+    {
+      "epoch": 0.002225519287833828,
+      "grad_norm": 0.3886512517929077,
+      "learning_rate": 3.0050999999999997e-05,
+      "loss": 1.7477,
+      "step": 3
+    },
+    {
+      "epoch": 0.002967359050445104,
+      "grad_norm": 0.3726235628128052,
+      "learning_rate": 4.0068e-05,
+      "loss": 1.6803,
+      "step": 4
+    },
+    {
+      "epoch": 0.00370919881305638,
+      "grad_norm": 0.41099005937576294,
+      "learning_rate": 5.0085e-05,
+      "loss": 1.7182,
+      "step": 5
+    },
+    {
+      "epoch": 0.004451038575667656,
+      "grad_norm": 0.41989028453826904,
+      "learning_rate": 6.0101999999999995e-05,
+      "loss": 1.7672,
+      "step": 6
+    },
+    {
+      "epoch": 0.0051928783382789315,
+      "grad_norm": 0.4218914806842804,
+      "learning_rate": 7.0119e-05,
+      "loss": 1.6714,
+      "step": 7
+    },
+    {
+      "epoch": 0.005934718100890208,
+      "grad_norm": 0.40673041343688965,
+      "learning_rate": 8.0136e-05,
+      "loss": 1.7538,
+      "step": 8
+    },
+    {
+      "epoch": 0.0066765578635014835,
+      "grad_norm": 0.40596580505371094,
+      "learning_rate": 9.0153e-05,
+      "loss": 1.6588,
+      "step": 9
+    },
+    {
+      "epoch": 0.00741839762611276,
+      "grad_norm": 0.3768528997898102,
+      "learning_rate": 0.00010017,
+      "loss": 1.6586,
+      "step": 10
+    },
+    {
+      "epoch": 0.008160237388724036,
+      "grad_norm": 0.37419360876083374,
+      "learning_rate": 9.964278947368421e-05,
+      "loss": 1.594,
+      "step": 11
+    },
+    {
+      "epoch": 0.008902077151335312,
+      "grad_norm": 0.3967873156070709,
+      "learning_rate": 9.911557894736841e-05,
+      "loss": 1.6244,
+      "step": 12
+    },
+    {
+      "epoch": 0.009643916913946587,
+      "grad_norm": 0.42619067430496216,
+      "learning_rate": 9.858836842105263e-05,
+      "loss": 1.5205,
+      "step": 13
+    },
+    {
+      "epoch": 0.010385756676557863,
+      "grad_norm": 0.42936253547668457,
+      "learning_rate": 9.806115789473684e-05,
+      "loss": 1.5066,
+      "step": 14
+    },
+    {
+      "epoch": 0.01112759643916914,
+      "grad_norm": 0.42404335737228394,
+      "learning_rate": 9.753394736842106e-05,
+      "loss": 1.6706,
+      "step": 15
+    },
+    {
+      "epoch": 0.011869436201780416,
+      "grad_norm": 0.4178953468799591,
+      "learning_rate": 9.700673684210526e-05,
+      "loss": 1.6554,
+      "step": 16
+    },
+    {
+      "epoch": 0.012611275964391691,
+      "grad_norm": 0.42441174387931824,
+      "learning_rate": 9.647952631578948e-05,
+      "loss": 1.6094,
+      "step": 17
+    },
+    {
+      "epoch": 0.013353115727002967,
+      "grad_norm": 0.4085826277732849,
+      "learning_rate": 9.595231578947368e-05,
+      "loss": 1.8246,
+      "step": 18
+    },
+    {
+      "epoch": 0.014094955489614243,
+      "grad_norm": 0.4366580843925476,
+      "learning_rate": 9.542510526315789e-05,
+      "loss": 1.7384,
+      "step": 19
+    },
+    {
+      "epoch": 0.01483679525222552,
+      "grad_norm": 0.4653952419757843,
+      "learning_rate": 9.48978947368421e-05,
+      "loss": 1.8026,
+      "step": 20
+    },
+    {
+      "epoch": 0.015578635014836795,
+      "grad_norm": 0.41364946961402893,
+      "learning_rate": 9.437068421052632e-05,
+      "loss": 1.4229,
+      "step": 21
+    },
+    {
+      "epoch": 0.016320474777448073,
+      "grad_norm": 0.4450036883354187,
+      "learning_rate": 9.384347368421052e-05,
+      "loss": 1.5319,
+      "step": 22
+    },
+    {
+      "epoch": 0.017062314540059347,
+      "grad_norm": 0.4304330348968506,
+      "learning_rate": 9.331626315789474e-05,
+      "loss": 1.5087,
+      "step": 23
+    },
+    {
+      "epoch": 0.017804154302670624,
+      "grad_norm": 0.4402780830860138,
+      "learning_rate": 9.278905263157894e-05,
+      "loss": 1.527,
+      "step": 24
+    },
+    {
+      "epoch": 0.018545994065281898,
+      "grad_norm": 0.5134778618812561,
+      "learning_rate": 9.226184210526316e-05,
+      "loss": 1.7225,
+      "step": 25
+    },
+    {
+      "epoch": 0.019287833827893175,
+      "grad_norm": 0.44076353311538696,
+      "learning_rate": 9.173463157894736e-05,
+      "loss": 1.448,
+      "step": 26
+    },
+    {
+      "epoch": 0.020029673590504452,
+      "grad_norm": 0.48980656266212463,
+      "learning_rate": 9.120742105263159e-05,
+      "loss": 1.6529,
+      "step": 27
+    },
+    {
+      "epoch": 0.020771513353115726,
+      "grad_norm": 0.46377643942832947,
+      "learning_rate": 9.068021052631579e-05,
+      "loss": 1.4986,
+      "step": 28
+    },
+    {
+      "epoch": 0.021513353115727003,
+      "grad_norm": 0.472007155418396,
+      "learning_rate": 9.0153e-05,
+      "loss": 1.7628,
+      "step": 29
+    },
+    {
+      "epoch": 0.02225519287833828,
+      "grad_norm": 0.45802855491638184,
+      "learning_rate": 8.96257894736842e-05,
+      "loss": 1.6237,
+      "step": 30
+    },
+    {
+      "epoch": 0.022997032640949554,
+      "grad_norm": 0.46878162026405334,
+      "learning_rate": 8.909857894736842e-05,
+      "loss": 1.6249,
+      "step": 31
+    },
+    {
+      "epoch": 0.02373887240356083,
+      "grad_norm": 0.47090795636177063,
+      "learning_rate": 8.857136842105263e-05,
+      "loss": 1.5893,
+      "step": 32
+    },
+    {
+      "epoch": 0.024480712166172106,
+      "grad_norm": 0.5051029920578003,
+      "learning_rate": 8.804415789473684e-05,
+      "loss": 1.5688,
+      "step": 33
+    },
+    {
+      "epoch": 0.025222551928783383,
+      "grad_norm": 0.4550938606262207,
+      "learning_rate": 8.751694736842105e-05,
+      "loss": 1.4056,
+      "step": 34
+    },
+    {
+      "epoch": 0.02596439169139466,
+      "grad_norm": 0.540347158908844,
+      "learning_rate": 8.698973684210527e-05,
+      "loss": 1.658,
+      "step": 35
+    },
+    {
+      "epoch": 0.026706231454005934,
+      "grad_norm": 0.4885530173778534,
+      "learning_rate": 8.646252631578948e-05,
+      "loss": 1.4331,
+      "step": 36
+    },
+    {
+      "epoch": 0.02744807121661721,
+      "grad_norm": 0.49800577759742737,
+      "learning_rate": 8.593531578947368e-05,
+      "loss": 1.3833,
+      "step": 37
+    },
+    {
+      "epoch": 0.028189910979228485,
+      "grad_norm": 0.5188278555870056,
+      "learning_rate": 8.54081052631579e-05,
+      "loss": 1.5612,
+      "step": 38
+    },
+    {
+      "epoch": 0.028931750741839762,
+      "grad_norm": 0.5572861433029175,
+      "learning_rate": 8.48808947368421e-05,
+      "loss": 1.6761,
+      "step": 39
+    },
+    {
+      "epoch": 0.02967359050445104,
+      "grad_norm": 0.5264113545417786,
+      "learning_rate": 8.435368421052631e-05,
+      "loss": 1.3864,
+      "step": 40
+    },
+    {
+      "epoch": 0.030415430267062313,
+      "grad_norm": 0.5517453551292419,
+      "learning_rate": 8.382647368421053e-05,
+      "loss": 1.5269,
+      "step": 41
+    },
+    {
+      "epoch": 0.03115727002967359,
+      "grad_norm": 0.5187894105911255,
+      "learning_rate": 8.329926315789474e-05,
+      "loss": 1.4188,
+      "step": 42
+    },
+    {
+      "epoch": 0.031899109792284865,
+      "grad_norm": 0.5830979943275452,
+      "learning_rate": 8.277205263157894e-05,
+      "loss": 1.7822,
+      "step": 43
+    },
+    {
+      "epoch": 0.032640949554896145,
+      "grad_norm": 0.5921754837036133,
+      "learning_rate": 8.224484210526316e-05,
+      "loss": 1.5062,
+      "step": 44
+    },
+    {
+      "epoch": 0.03338278931750742,
+      "grad_norm": 0.5693333148956299,
+      "learning_rate": 8.171763157894736e-05,
+      "loss": 1.5407,
+      "step": 45
+    },
+    {
+      "epoch": 0.03412462908011869,
+      "grad_norm": 0.6015297770500183,
+      "learning_rate": 8.119042105263158e-05,
+      "loss": 1.5718,
+      "step": 46
+    },
+    {
+      "epoch": 0.034866468842729974,
+      "grad_norm": 0.6420146226882935,
+      "learning_rate": 8.066321052631578e-05,
+      "loss": 1.6665,
+      "step": 47
+    },
+    {
+      "epoch": 0.03560830860534125,
+      "grad_norm": 0.6055085062980652,
+      "learning_rate": 8.0136e-05,
+      "loss": 1.5059,
+      "step": 48
+    },
+    {
+      "epoch": 0.03635014836795252,
+      "grad_norm": 0.7061499953269958,
+      "learning_rate": 7.960878947368421e-05,
+      "loss": 1.8428,
+      "step": 49
+    },
+    {
+      "epoch": 0.037091988130563795,
+      "grad_norm": 0.7242527604103088,
+      "learning_rate": 7.908157894736842e-05,
+      "loss": 1.5827,
+      "step": 50
+    },
+    {
+      "epoch": 0.037091988130563795,
+      "eval_loss": 1.5464621782302856,
+      "eval_runtime": 24.5932,
+      "eval_samples_per_second": 23.096,
+      "eval_steps_per_second": 5.774,
+      "step": 50
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 200,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 50,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 5,
+        "early_stopping_threshold": 0.0
+      },
+      "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": 4136300131123200.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

last-checkpoint/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07201d85f1f94c8598a27f5499e04641cb8ed4168a1939f549b06ebd90b019b1
+size 6840