Training in progress, step 50, checkpoint

last-checkpoint/README.md

@@ -0,0 +1,202 @@
+---
+base_model: unsloth/SmolLM2-135M
+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/SmolLM2-135M",
+  "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": 32,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "o_proj",
+    "down_proj",
+    "up_proj",
+    "v_proj",
+    "gate_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 sha256:9063db456df82ef7b034a44b128b7b65ac821a1352a1dd757dfba2826368b8b7
+size 19593064

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:bc7151a659f73b08e69c2541c786c9bf3ed59f19d113c5da63c943bda68f74f4
+size 39428606

last-checkpoint/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27cbf8427518d7b8072db3cf1c9eb707b8dd6aa4ed125a08b8a76ec0c86b034c
+size 14244

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a07b109def4971c920d90baf18ed40bd4d7e546cc0be64c2624f45e72194da30
+size 1064

last-checkpoint/special_tokens_map.json

@@ -0,0 +1,43 @@
+{
+  "additional_special_tokens": [
+    "<|endoftext|>",
+    "<|im_start|>",
+    "<|im_end|>",
+    "<repo_name>",
+    "<reponame>",
+    "<file_sep>",
+    "<filename>",
+    "<gh_stars>",
+    "<issue_start>",
+    "<issue_comment>",
+    "<issue_closed>",
+    "<jupyter_start>",
+    "<jupyter_text>",
+    "<jupyter_code>",
+    "<jupyter_output>",
+    "<jupyter_script>",
+    "<empty_output>"
+  ],
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "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
+  },
+  "unk_token": "�"
+}

last-checkpoint/tokenizer_config.json

@@ -0,0 +1,186 @@
+{
+  "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": [
+    "<|endoftext|>",
+    "<|im_start|>",
+    "<|im_end|>",
+    "<repo_name>",
+    "<reponame>",
+    "<file_sep>",
+    "<filename>",
+    "<gh_stars>",
+    "<issue_start>",
+    "<issue_comment>",
+    "<issue_closed>",
+    "<jupyter_start>",
+    "<jupyter_text>",
+    "<jupyter_code>",
+    "<jupyter_output>",
+    "<jupyter_script>",
+    "<empty_output>"
+  ],
+  "bos_token": "<|endoftext|>",
+  "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": "<|endoftext|>",
+  "model_max_length": 8192,
+  "pad_token": "<|PAD_TOKEN|>",
+  "padding_side": "left",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "�",
+  "vocab_size": 49152
+}

last-checkpoint/trainer_state.json

@@ -0,0 +1,416 @@
+{
+  "best_metric": NaN,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.6793478260869565,
+  "eval_steps": 25,
+  "global_step": 50,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01358695652173913,
+      "grad_norm": NaN,
+      "learning_rate": 7.142857142857143e-06,
+      "loss": 0.0,
+      "step": 1
+    },
+    {
+      "epoch": 0.01358695652173913,
+      "eval_loss": NaN,
+      "eval_runtime": 2.0311,
+      "eval_samples_per_second": 24.618,
+      "eval_steps_per_second": 4.431,
+      "step": 1
+    },
+    {
+      "epoch": 0.02717391304347826,
+      "grad_norm": NaN,
+      "learning_rate": 1.4285714285714285e-05,
+      "loss": 0.0,
+      "step": 2
+    },
+    {
+      "epoch": 0.04076086956521739,
+      "grad_norm": NaN,
+      "learning_rate": 2.1428571428571428e-05,
+      "loss": 0.0,
+      "step": 3
+    },
+    {
+      "epoch": 0.05434782608695652,
+      "grad_norm": NaN,
+      "learning_rate": 2.857142857142857e-05,
+      "loss": 0.0,
+      "step": 4
+    },
+    {
+      "epoch": 0.06793478260869565,
+      "grad_norm": NaN,
+      "learning_rate": 3.571428571428572e-05,
+      "loss": 0.0,
+      "step": 5
+    },
+    {
+      "epoch": 0.08152173913043478,
+      "grad_norm": NaN,
+      "learning_rate": 4.2857142857142856e-05,
+      "loss": 0.0,
+      "step": 6
+    },
+    {
+      "epoch": 0.09510869565217392,
+      "grad_norm": NaN,
+      "learning_rate": 5e-05,
+      "loss": 0.0,
+      "step": 7
+    },
+    {
+      "epoch": 0.10869565217391304,
+      "grad_norm": NaN,
+      "learning_rate": 5.714285714285714e-05,
+      "loss": 0.0,
+      "step": 8
+    },
+    {
+      "epoch": 0.12228260869565218,
+      "grad_norm": NaN,
+      "learning_rate": 6.428571428571429e-05,
+      "loss": 0.0,
+      "step": 9
+    },
+    {
+      "epoch": 0.1358695652173913,
+      "grad_norm": NaN,
+      "learning_rate": 7.142857142857143e-05,
+      "loss": 0.0,
+      "step": 10
+    },
+    {
+      "epoch": 0.14945652173913043,
+      "grad_norm": NaN,
+      "learning_rate": 7.857142857142858e-05,
+      "loss": 0.0,
+      "step": 11
+    },
+    {
+      "epoch": 0.16304347826086957,
+      "grad_norm": NaN,
+      "learning_rate": 8.571428571428571e-05,
+      "loss": 0.0,
+      "step": 12
+    },
+    {
+      "epoch": 0.1766304347826087,
+      "grad_norm": NaN,
+      "learning_rate": 9.285714285714286e-05,
+      "loss": 0.0,
+      "step": 13
+    },
+    {
+      "epoch": 0.19021739130434784,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001,
+      "loss": 0.0,
+      "step": 14
+    },
+    {
+      "epoch": 0.20380434782608695,
+      "grad_norm": NaN,
+      "learning_rate": 9.999716755396153e-05,
+      "loss": 0.0,
+      "step": 15
+    },
+    {
+      "epoch": 0.21739130434782608,
+      "grad_norm": NaN,
+      "learning_rate": 9.99886705724128e-05,
+      "loss": 0.0,
+      "step": 16
+    },
+    {
+      "epoch": 0.23097826086956522,
+      "grad_norm": NaN,
+      "learning_rate": 9.997451012500901e-05,
+      "loss": 0.0,
+      "step": 17
+    },
+    {
+      "epoch": 0.24456521739130435,
+      "grad_norm": NaN,
+      "learning_rate": 9.995468799435917e-05,
+      "loss": 0.0,
+      "step": 18
+    },
+    {
+      "epoch": 0.25815217391304346,
+      "grad_norm": NaN,
+      "learning_rate": 9.992920667580176e-05,
+      "loss": 0.0,
+      "step": 19
+    },
+    {
+      "epoch": 0.2717391304347826,
+      "grad_norm": NaN,
+      "learning_rate": 9.989806937709054e-05,
+      "loss": 0.0,
+      "step": 20
+    },
+    {
+      "epoch": 0.28532608695652173,
+      "grad_norm": NaN,
+      "learning_rate": 9.986128001799077e-05,
+      "loss": 0.0,
+      "step": 21
+    },
+    {
+      "epoch": 0.29891304347826086,
+      "grad_norm": NaN,
+      "learning_rate": 9.981884322978576e-05,
+      "loss": 0.0,
+      "step": 22
+    },
+    {
+      "epoch": 0.3125,
+      "grad_norm": NaN,
+      "learning_rate": 9.977076435469385e-05,
+      "loss": 0.0,
+      "step": 23
+    },
+    {
+      "epoch": 0.32608695652173914,
+      "grad_norm": NaN,
+      "learning_rate": 9.971704944519594e-05,
+      "loss": 0.0,
+      "step": 24
+    },
+    {
+      "epoch": 0.33967391304347827,
+      "grad_norm": NaN,
+      "learning_rate": 9.96577052632734e-05,
+      "loss": 0.0,
+      "step": 25
+    },
+    {
+      "epoch": 0.33967391304347827,
+      "eval_loss": NaN,
+      "eval_runtime": 1.3689,
+      "eval_samples_per_second": 36.527,
+      "eval_steps_per_second": 6.575,
+      "step": 25
+    },
+    {
+      "epoch": 0.3532608695652174,
+      "grad_norm": NaN,
+      "learning_rate": 9.959273927955706e-05,
+      "loss": 0.0,
+      "step": 26
+    },
+    {
+      "epoch": 0.36684782608695654,
+      "grad_norm": NaN,
+      "learning_rate": 9.952215967238665e-05,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 0.3804347826086957,
+      "grad_norm": NaN,
+      "learning_rate": 9.94459753267812e-05,
+      "loss": 0.0,
+      "step": 28
+    },
+    {
+      "epoch": 0.39402173913043476,
+      "grad_norm": NaN,
+      "learning_rate": 9.936419583332062e-05,
+      "loss": 0.0,
+      "step": 29
+    },
+    {
+      "epoch": 0.4076086956521739,
+      "grad_norm": NaN,
+      "learning_rate": 9.927683148693833e-05,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.421195652173913,
+      "grad_norm": NaN,
+      "learning_rate": 9.918389328562534e-05,
+      "loss": 0.0,
+      "step": 31
+    },
+    {
+      "epoch": 0.43478260869565216,
+      "grad_norm": NaN,
+      "learning_rate": 9.90853929290456e-05,
+      "loss": 0.0,
+      "step": 32
+    },
+    {
+      "epoch": 0.4483695652173913,
+      "grad_norm": NaN,
+      "learning_rate": 9.898134281706337e-05,
+      "loss": 0.0,
+      "step": 33
+    },
+    {
+      "epoch": 0.46195652173913043,
+      "grad_norm": NaN,
+      "learning_rate": 9.887175604818206e-05,
+      "loss": 0.0,
+      "step": 34
+    },
+    {
+      "epoch": 0.47554347826086957,
+      "grad_norm": NaN,
+      "learning_rate": 9.875664641789545e-05,
+      "loss": 0.0,
+      "step": 35
+    },
+    {
+      "epoch": 0.4891304347826087,
+      "grad_norm": NaN,
+      "learning_rate": 9.86360284169509e-05,
+      "loss": 0.0,
+      "step": 36
+    },
+    {
+      "epoch": 0.5027173913043478,
+      "grad_norm": NaN,
+      "learning_rate": 9.85099172295253e-05,
+      "loss": 0.0,
+      "step": 37
+    },
+    {
+      "epoch": 0.5163043478260869,
+      "grad_norm": NaN,
+      "learning_rate": 9.83783287313134e-05,
+      "loss": 0.0,
+      "step": 38
+    },
+    {
+      "epoch": 0.529891304347826,
+      "grad_norm": NaN,
+      "learning_rate": 9.82412794875295e-05,
+      "loss": 0.0,
+      "step": 39
+    },
+    {
+      "epoch": 0.5434782608695652,
+      "grad_norm": NaN,
+      "learning_rate": 9.809878675082187e-05,
+      "loss": 0.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.5570652173913043,
+      "grad_norm": NaN,
+      "learning_rate": 9.795086845910114e-05,
+      "loss": 0.0,
+      "step": 41
+    },
+    {
+      "epoch": 0.5706521739130435,
+      "grad_norm": NaN,
+      "learning_rate": 9.779754323328192e-05,
+      "loss": 0.0,
+      "step": 42
+    },
+    {
+      "epoch": 0.5842391304347826,
+      "grad_norm": NaN,
+      "learning_rate": 9.76388303749388e-05,
+      "loss": 0.0,
+      "step": 43
+    },
+    {
+      "epoch": 0.5978260869565217,
+      "grad_norm": NaN,
+      "learning_rate": 9.747474986387654e-05,
+      "loss": 0.0,
+      "step": 44
+    },
+    {
+      "epoch": 0.6114130434782609,
+      "grad_norm": NaN,
+      "learning_rate": 9.730532235561486e-05,
+      "loss": 0.0,
+      "step": 45
+    },
+    {
+      "epoch": 0.625,
+      "grad_norm": NaN,
+      "learning_rate": 9.713056917878818e-05,
+      "loss": 0.0,
+      "step": 46
+    },
+    {
+      "epoch": 0.6385869565217391,
+      "grad_norm": NaN,
+      "learning_rate": 9.695051233246065e-05,
+      "loss": 0.0,
+      "step": 47
+    },
+    {
+      "epoch": 0.6521739130434783,
+      "grad_norm": NaN,
+      "learning_rate": 9.676517448335676e-05,
+      "loss": 0.0,
+      "step": 48
+    },
+    {
+      "epoch": 0.6657608695652174,
+      "grad_norm": NaN,
+      "learning_rate": 9.657457896300791e-05,
+      "loss": 0.0,
+      "step": 49
+    },
+    {
+      "epoch": 0.6793478260869565,
+      "grad_norm": NaN,
+      "learning_rate": 9.637874976481529e-05,
+      "loss": 0.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.6793478260869565,
+      "eval_loss": NaN,
+      "eval_runtime": 1.3639,
+      "eval_samples_per_second": 36.661,
+      "eval_steps_per_second": 6.599,
+      "step": 50
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 294,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 50,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 1,
+        "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": 2080334001733632.0,
+  "train_batch_size": 6,
+  "trial_name": null,
+  "trial_params": null
+}

last-checkpoint/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:82a0949aa2354f61ead11c9932d3ffa6c335eff2e5864bd59baef7267199a743
+size 6840