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",
+    "o_proj",
+    "v_proj",
+    "k_proj",
+    "gate_proj",
+    "down_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 sha256:47d0f70225c53f9658a975ca4926b69e9d7c8dbeb051fbc5c5ae5c44e2dc141c
+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:ce0710113b9803b3bbaa9cb3dc082acfb3e42e0cb56495d75616cf4123c14ef2
+size 147359892

last-checkpoint/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04eeb213be82c8d7e78418cd6a261124ae37b3e0527f4017e3d5378d4bf92842
+size 14244

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d359eb5d29e75fb2bbe5b7026981da69b95b8ad1fea469302d13cde104f7e8a
+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": 0.9435171484947205,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.07510326699211416,
+  "eval_steps": 50,
+  "global_step": 50,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0015020653398422831,
+      "grad_norm": 0.48013806343078613,
+      "learning_rate": 1e-05,
+      "loss": 1.1844,
+      "step": 1
+    },
+    {
+      "epoch": 0.0015020653398422831,
+      "eval_loss": 1.4352283477783203,
+      "eval_runtime": 33.3798,
+      "eval_samples_per_second": 33.613,
+      "eval_steps_per_second": 8.418,
+      "step": 1
+    },
+    {
+      "epoch": 0.0030041306796845663,
+      "grad_norm": 0.42095404863357544,
+      "learning_rate": 2e-05,
+      "loss": 1.2759,
+      "step": 2
+    },
+    {
+      "epoch": 0.004506196019526849,
+      "grad_norm": 0.40659624338150024,
+      "learning_rate": 3e-05,
+      "loss": 1.3025,
+      "step": 3
+    },
+    {
+      "epoch": 0.0060082613593691325,
+      "grad_norm": 0.41802921891212463,
+      "learning_rate": 4e-05,
+      "loss": 1.3053,
+      "step": 4
+    },
+    {
+      "epoch": 0.007510326699211416,
+      "grad_norm": 0.4731360673904419,
+      "learning_rate": 5e-05,
+      "loss": 1.305,
+      "step": 5
+    },
+    {
+      "epoch": 0.009012392039053699,
+      "grad_norm": 0.4001414179801941,
+      "learning_rate": 6e-05,
+      "loss": 1.301,
+      "step": 6
+    },
+    {
+      "epoch": 0.010514457378895982,
+      "grad_norm": 0.3494016230106354,
+      "learning_rate": 7e-05,
+      "loss": 1.2796,
+      "step": 7
+    },
+    {
+      "epoch": 0.012016522718738265,
+      "grad_norm": 0.25853636860847473,
+      "learning_rate": 8e-05,
+      "loss": 1.2454,
+      "step": 8
+    },
+    {
+      "epoch": 0.013518588058580548,
+      "grad_norm": 0.36195915937423706,
+      "learning_rate": 9e-05,
+      "loss": 1.2594,
+      "step": 9
+    },
+    {
+      "epoch": 0.015020653398422831,
+      "grad_norm": 0.41546186804771423,
+      "learning_rate": 0.0001,
+      "loss": 1.2273,
+      "step": 10
+    },
+    {
+      "epoch": 0.016522718738265114,
+      "grad_norm": 0.38150355219841003,
+      "learning_rate": 9.999316524962345e-05,
+      "loss": 1.1949,
+      "step": 11
+    },
+    {
+      "epoch": 0.018024784078107398,
+      "grad_norm": 0.3044074773788452,
+      "learning_rate": 9.997266286704631e-05,
+      "loss": 1.1619,
+      "step": 12
+    },
+    {
+      "epoch": 0.01952684941794968,
+      "grad_norm": 0.23984934389591217,
+      "learning_rate": 9.993849845741524e-05,
+      "loss": 1.1339,
+      "step": 13
+    },
+    {
+      "epoch": 0.021028914757791964,
+      "grad_norm": 0.24785546958446503,
+      "learning_rate": 9.989068136093873e-05,
+      "loss": 1.0967,
+      "step": 14
+    },
+    {
+      "epoch": 0.022530980097634247,
+      "grad_norm": 0.25208961963653564,
+      "learning_rate": 9.98292246503335e-05,
+      "loss": 1.074,
+      "step": 15
+    },
+    {
+      "epoch": 0.02403304543747653,
+      "grad_norm": 0.26858824491500854,
+      "learning_rate": 9.975414512725057e-05,
+      "loss": 1.0323,
+      "step": 16
+    },
+    {
+      "epoch": 0.025535110777318813,
+      "grad_norm": 0.2699333131313324,
+      "learning_rate": 9.966546331768191e-05,
+      "loss": 1.0193,
+      "step": 17
+    },
+    {
+      "epoch": 0.027037176117161096,
+      "grad_norm": 0.29868969321250916,
+      "learning_rate": 9.956320346634876e-05,
+      "loss": 0.9937,
+      "step": 18
+    },
+    {
+      "epoch": 0.02853924145700338,
+      "grad_norm": 0.2335326373577118,
+      "learning_rate": 9.944739353007344e-05,
+      "loss": 0.9666,
+      "step": 19
+    },
+    {
+      "epoch": 0.030041306796845663,
+      "grad_norm": 0.25925031304359436,
+      "learning_rate": 9.931806517013612e-05,
+      "loss": 0.9465,
+      "step": 20
+    },
+    {
+      "epoch": 0.031543372136687946,
+      "grad_norm": 0.3260612189769745,
+      "learning_rate": 9.917525374361912e-05,
+      "loss": 0.9378,
+      "step": 21
+    },
+    {
+      "epoch": 0.03304543747653023,
+      "grad_norm": 0.2550596594810486,
+      "learning_rate": 9.901899829374047e-05,
+      "loss": 0.9038,
+      "step": 22
+    },
+    {
+      "epoch": 0.03454750281637251,
+      "grad_norm": 0.28878340125083923,
+      "learning_rate": 9.884934153917997e-05,
+      "loss": 0.8962,
+      "step": 23
+    },
+    {
+      "epoch": 0.036049568156214795,
+      "grad_norm": 0.27984026074409485,
+      "learning_rate": 9.86663298624003e-05,
+      "loss": 0.8538,
+      "step": 24
+    },
+    {
+      "epoch": 0.03755163349605708,
+      "grad_norm": 0.2650708556175232,
+      "learning_rate": 9.847001329696653e-05,
+      "loss": 0.8394,
+      "step": 25
+    },
+    {
+      "epoch": 0.03905369883589936,
+      "grad_norm": 0.24351182579994202,
+      "learning_rate": 9.826044551386744e-05,
+      "loss": 0.8104,
+      "step": 26
+    },
+    {
+      "epoch": 0.040555764175741645,
+      "grad_norm": 0.3326224088668823,
+      "learning_rate": 9.803768380684242e-05,
+      "loss": 0.794,
+      "step": 27
+    },
+    {
+      "epoch": 0.04205782951558393,
+      "grad_norm": 0.298579603433609,
+      "learning_rate": 9.780178907671789e-05,
+      "loss": 0.7783,
+      "step": 28
+    },
+    {
+      "epoch": 0.04355989485542621,
+      "grad_norm": 0.2561696469783783,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 0.7657,
+      "step": 29
+    },
+    {
+      "epoch": 0.045061960195268494,
+      "grad_norm": 0.2900291383266449,
+      "learning_rate": 9.729086208503174e-05,
+      "loss": 0.7382,
+      "step": 30
+    },
+    {
+      "epoch": 0.04656402553511078,
+      "grad_norm": 0.2575244605541229,
+      "learning_rate": 9.701596950580806e-05,
+      "loss": 0.723,
+      "step": 31
+    },
+    {
+      "epoch": 0.04806609087495306,
+      "grad_norm": 0.34842997789382935,
+      "learning_rate": 9.672822322997305e-05,
+      "loss": 0.7148,
+      "step": 32
+    },
+    {
+      "epoch": 0.04956815621479534,
+      "grad_norm": 0.2418001890182495,
+      "learning_rate": 9.642770192448536e-05,
+      "loss": 0.6728,
+      "step": 33
+    },
+    {
+      "epoch": 0.051070221554637626,
+      "grad_norm": 0.37016379833221436,
+      "learning_rate": 9.611448774886924e-05,
+      "loss": 0.6626,
+      "step": 34
+    },
+    {
+      "epoch": 0.05257228689447991,
+      "grad_norm": 0.3161463439464569,
+      "learning_rate": 9.578866633275288e-05,
+      "loss": 0.6567,
+      "step": 35
+    },
+    {
+      "epoch": 0.05407435223432219,
+      "grad_norm": 0.4346078038215637,
+      "learning_rate": 9.545032675245813e-05,
+      "loss": 0.6694,
+      "step": 36
+    },
+    {
+      "epoch": 0.055576417574164476,
+      "grad_norm": 0.435017853975296,
+      "learning_rate": 9.509956150664796e-05,
+      "loss": 0.6299,
+      "step": 37
+    },
+    {
+      "epoch": 0.05707848291400676,
+      "grad_norm": 0.3490477204322815,
+      "learning_rate": 9.473646649103818e-05,
+      "loss": 0.6261,
+      "step": 38
+    },
+    {
+      "epoch": 0.05858054825384904,
+      "grad_norm": 0.5194304585456848,
+      "learning_rate": 9.43611409721806e-05,
+      "loss": 0.5896,
+      "step": 39
+    },
+    {
+      "epoch": 0.060082613593691325,
+      "grad_norm": 0.2708154618740082,
+      "learning_rate": 9.397368756032445e-05,
+      "loss": 0.6089,
+      "step": 40
+    },
+    {
+      "epoch": 0.06158467893353361,
+      "grad_norm": 0.4544765055179596,
+      "learning_rate": 9.357421218136386e-05,
+      "loss": 0.5747,
+      "step": 41
+    },
+    {
+      "epoch": 0.06308674427337589,
+      "grad_norm": 0.3197058439254761,
+      "learning_rate": 9.316282404787871e-05,
+      "loss": 0.5633,
+      "step": 42
+    },
+    {
+      "epoch": 0.06458880961321818,
+      "grad_norm": 0.49233025312423706,
+      "learning_rate": 9.273963562927695e-05,
+      "loss": 0.5625,
+      "step": 43
+    },
+    {
+      "epoch": 0.06609087495306046,
+      "grad_norm": 0.31287699937820435,
+      "learning_rate": 9.230476262104677e-05,
+      "loss": 0.5604,
+      "step": 44
+    },
+    {
+      "epoch": 0.06759294029290275,
+      "grad_norm": 0.4544554054737091,
+      "learning_rate": 9.185832391312644e-05,
+      "loss": 0.5784,
+      "step": 45
+    },
+    {
+      "epoch": 0.06909500563274502,
+      "grad_norm": 0.4347470998764038,
+      "learning_rate": 9.140044155740101e-05,
+      "loss": 0.5394,
+      "step": 46
+    },
+    {
+      "epoch": 0.07059707097258731,
+      "grad_norm": 0.4225442707538605,
+      "learning_rate": 9.093124073433463e-05,
+      "loss": 0.55,
+      "step": 47
+    },
+    {
+      "epoch": 0.07209913631242959,
+      "grad_norm": 0.4641411602497101,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 0.5168,
+      "step": 48
+    },
+    {
+      "epoch": 0.07360120165227188,
+      "grad_norm": 0.5490090847015381,
+      "learning_rate": 8.995939984474624e-05,
+      "loss": 0.545,
+      "step": 49
+    },
+    {
+      "epoch": 0.07510326699211416,
+      "grad_norm": 0.5186936855316162,
+      "learning_rate": 8.945702546981969e-05,
+      "loss": 0.4797,
+      "step": 50
+    },
+    {
+      "epoch": 0.07510326699211416,
+      "eval_loss": 0.9435171484947205,
+      "eval_runtime": 33.2926,
+      "eval_samples_per_second": 33.701,
+      "eval_steps_per_second": 8.44,
+      "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": 1.6627926527115264e+16,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

last-checkpoint/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c3ea326e631ef3b4c75f2780b618455f013526aae75ccfbbcbf41b55a6c131f
+size 6840