End of training

README.md

@@ -0,0 +1,152 @@
+---
+library_name: peft
+license: other
+base_model: facebook/opt-125m
+tags:
+- axolotl
+- generated_from_trainer
+model-index:
+- name: fd18c646-50f9-43a7-bc2f-b5987f2b2f56
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+[<img src="https://raw.githubusercontent.com/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl)
+<details><summary>See axolotl config</summary>
+
+axolotl version: `0.4.1`
+```yaml
+adapter: lora
+base_model: facebook/opt-125m
+bf16: true
+chat_template: llama3
+datasets:
+- data_files:
+  - 13cdc72de92bf83a_train_data.json
+  ds_type: json
+  format: custom
+  path: /workspace/input_data/13cdc72de92bf83a_train_data.json
+  type:
+    field_instruction: problem
+    field_output: solution
+    format: '{instruction}'
+    no_input_format: '{instruction}'
+    system_format: '{system}'
+    system_prompt: ''
+debug: null
+deepspeed: null
+early_stopping_patience: 2
+eval_max_new_tokens: 128
+eval_steps: 5
+eval_table_size: null
+flash_attention: false
+fp16: false
+fsdp: null
+fsdp_config: null
+gradient_accumulation_steps: 4
+gradient_checkpointing: false
+group_by_length: false
+hub_model_id: null
+hub_repo: null
+hub_strategy: checkpoint
+hub_token: null
+learning_rate: 0.0002
+load_in_4bit: false
+load_in_8bit: true
+local_rank: null
+logging_steps: 1
+lora_alpha: 16
+lora_dropout: 0.05
+lora_fan_in_fan_out: null
+lora_model_dir: null
+lora_r: 8
+lora_target_linear: true
+lr_scheduler: cosine
+max_steps: 25
+micro_batch_size: 2
+mlflow_experiment_name: /tmp/13cdc72de92bf83a_train_data.json
+model_type: AutoModelForCausalLM
+num_epochs: 1
+optimizer: adamw_bnb_8bit
+output_dir: miner_id_24
+pad_to_sequence_len: true
+resume_from_checkpoint: null
+s2_attention: null
+sample_packing: false
+save_steps: 10
+sequence_len: 512
+strict: false
+tf32: false
+tokenizer_type: AutoTokenizer
+train_on_inputs: false
+trust_remote_code: true
+val_set_size: 0.05
+wandb_entity: null
+wandb_mode: online
+wandb_name: fe7a2471-cad2-4b25-b149-efff9f858e97
+wandb_project: Gradients-On-Demand
+wandb_run: your_name
+wandb_runid: fe7a2471-cad2-4b25-b149-efff9f858e97
+warmup_steps: 10
+weight_decay: 0.0
+xformers_attention: null
+
+```
+
+</details><br>
+
+# fd18c646-50f9-43a7-bc2f-b5987f2b2f56
+
+This model is a fine-tuned version of [facebook/opt-125m](https://huggingface.co/facebook/opt-125m) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.9231
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 0.0002
+- train_batch_size: 2
+- eval_batch_size: 2
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 8
+- optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 10
+- training_steps: 25
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 8.3185        | 0.0009 | 1    | 2.0675          |
+| 8.2323        | 0.0043 | 5    | 2.0522          |
+| 8.0955        | 0.0086 | 10   | 2.0068          |
+| 9.532         | 0.0129 | 15   | 1.9589          |
+| 7.6952        | 0.0172 | 20   | 1.9288          |
+| 8.0331        | 0.0215 | 25   | 1.9231          |
+
+
+### Framework versions
+
+- PEFT 0.13.2
+- Transformers 4.46.0
+- Pytorch 2.5.0+cu124
+- Datasets 3.0.1
+- Tokenizers 0.20.1

adapter_config.json

@@ -0,0 +1,33 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "facebook/opt-125m",
+  "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": 16,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "fc2",
+    "v_proj",
+    "fc1",
+    "k_proj",
+    "out_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9f2da1dd08365fdf2943ee1d0bc4cf21db7ee74672a5ef3fb44f47639a66290
+size 5360906

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9bc26ab10f353db835982b86fa0af6bea177343c28f8cbee88da52240273276c
+size 5327744

config.json

@@ -0,0 +1,47 @@
+{
+  "_attn_implementation_autoset": true,
+  "_name_or_path": "facebook/opt-125m",
+  "_remove_final_layer_norm": false,
+  "activation_dropout": 0.0,
+  "activation_function": "relu",
+  "architectures": [
+    "OPTForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 2,
+  "do_layer_norm_before": true,
+  "dropout": 0.1,
+  "enable_bias": true,
+  "eos_token_id": 2,
+  "ffn_dim": 3072,
+  "hidden_size": 768,
+  "init_std": 0.02,
+  "layer_norm_elementwise_affine": true,
+  "layerdrop": 0.0,
+  "max_position_embeddings": 2048,
+  "model_type": "opt",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "prefix": "</s>",
+  "quantization_config": {
+    "_load_in_4bit": false,
+    "_load_in_8bit": true,
+    "bnb_4bit_compute_dtype": "float32",
+    "bnb_4bit_quant_storage": "uint8",
+    "bnb_4bit_quant_type": "fp4",
+    "bnb_4bit_use_double_quant": false,
+    "llm_int8_enable_fp32_cpu_offload": false,
+    "llm_int8_has_fp16_weight": false,
+    "llm_int8_skip_modules": null,
+    "llm_int8_threshold": 6.0,
+    "load_in_4bit": false,
+    "load_in_8bit": true,
+    "quant_method": "bitsandbytes"
+  },
+  "torch_dtype": "float16",
+  "transformers_version": "4.46.0",
+  "use_cache": false,
+  "vocab_size": 50272,
+  "word_embed_proj_dim": 768
+}

last-checkpoint/README.md

@@ -0,0 +1,202 @@
+---
+base_model: facebook/opt-125m
+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 +1,33 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "facebook/opt-125m",
+  "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": 16,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "fc2",
+    "v_proj",
+    "fc1",
+    "k_proj",
+    "out_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 sha256:9bc26ab10f353db835982b86fa0af6bea177343c28f8cbee88da52240273276c
+size 5327744

last-checkpoint/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5024460d99174b9c1a6e6a2b3808a93643a0856199c5c0aae81ac32a5c6d3e0
+size 2857722

last-checkpoint/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48528364bd0a7d080ac65fa20a58eebe3d2caddfabdade0c815327aab9aaef45
+size 14244

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4521b8db9cc205e54aa606d85e707c024abd2d8ad4a20bec4b2cff365dc59cdf
+size 1064

last-checkpoint/special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

last-checkpoint/tokenizer_config.json

@@ -0,0 +1,31 @@
+{
+  "add_bos_token": true,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "</s>",
+  "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": "</s>",
+  "errors": "replace",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "</s>"
+}

last-checkpoint/trainer_state.json

@@ -0,0 +1,265 @@
+{
+  "best_metric": 1.923120141029358,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.021482277121374866,
+  "eval_steps": 5,
+  "global_step": 25,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0008592910848549946,
+      "grad_norm": 3.3073325157165527,
+      "learning_rate": 2e-05,
+      "loss": 8.3185,
+      "step": 1
+    },
+    {
+      "epoch": 0.0008592910848549946,
+      "eval_loss": 2.0675454139709473,
+      "eval_runtime": 20.2053,
+      "eval_samples_per_second": 24.251,
+      "eval_steps_per_second": 12.126,
+      "step": 1
+    },
+    {
+      "epoch": 0.0017185821697099893,
+      "grad_norm": 3.7460267543792725,
+      "learning_rate": 4e-05,
+      "loss": 9.2787,
+      "step": 2
+    },
+    {
+      "epoch": 0.0025778732545649837,
+      "grad_norm": 3.0592331886291504,
+      "learning_rate": 6e-05,
+      "loss": 8.1589,
+      "step": 3
+    },
+    {
+      "epoch": 0.0034371643394199786,
+      "grad_norm": 3.309882640838623,
+      "learning_rate": 8e-05,
+      "loss": 9.1155,
+      "step": 4
+    },
+    {
+      "epoch": 0.004296455424274973,
+      "grad_norm": 2.840452194213867,
+      "learning_rate": 0.0001,
+      "loss": 8.2323,
+      "step": 5
+    },
+    {
+      "epoch": 0.004296455424274973,
+      "eval_loss": 2.052173614501953,
+      "eval_runtime": 19.0719,
+      "eval_samples_per_second": 25.692,
+      "eval_steps_per_second": 12.846,
+      "step": 5
+    },
+    {
+      "epoch": 0.0051557465091299675,
+      "grad_norm": 2.7349984645843506,
+      "learning_rate": 0.00012,
+      "loss": 8.8164,
+      "step": 6
+    },
+    {
+      "epoch": 0.006015037593984963,
+      "grad_norm": 3.8210105895996094,
+      "learning_rate": 0.00014,
+      "loss": 9.0191,
+      "step": 7
+    },
+    {
+      "epoch": 0.006874328678839957,
+      "grad_norm": 3.515184164047241,
+      "learning_rate": 0.00016,
+      "loss": 8.2134,
+      "step": 8
+    },
+    {
+      "epoch": 0.007733619763694952,
+      "grad_norm": 2.7120907306671143,
+      "learning_rate": 0.00018,
+      "loss": 8.0587,
+      "step": 9
+    },
+    {
+      "epoch": 0.008592910848549946,
+      "grad_norm": 3.9589414596557617,
+      "learning_rate": 0.0002,
+      "loss": 8.0955,
+      "step": 10
+    },
+    {
+      "epoch": 0.008592910848549946,
+      "eval_loss": 2.0068485736846924,
+      "eval_runtime": 18.8486,
+      "eval_samples_per_second": 25.997,
+      "eval_steps_per_second": 12.998,
+      "step": 10
+    },
+    {
+      "epoch": 0.00945220193340494,
+      "grad_norm": 3.420163631439209,
+      "learning_rate": 0.00019781476007338058,
+      "loss": 8.4802,
+      "step": 11
+    },
+    {
+      "epoch": 0.010311493018259935,
+      "grad_norm": 3.446446657180786,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 8.0042,
+      "step": 12
+    },
+    {
+      "epoch": 0.01117078410311493,
+      "grad_norm": 3.0574252605438232,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 8.1575,
+      "step": 13
+    },
+    {
+      "epoch": 0.012030075187969926,
+      "grad_norm": 3.0679614543914795,
+      "learning_rate": 0.00016691306063588583,
+      "loss": 7.8128,
+      "step": 14
+    },
+    {
+      "epoch": 0.01288936627282492,
+      "grad_norm": 3.8208773136138916,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 9.532,
+      "step": 15
+    },
+    {
+      "epoch": 0.01288936627282492,
+      "eval_loss": 1.958902359008789,
+      "eval_runtime": 19.3706,
+      "eval_samples_per_second": 25.296,
+      "eval_steps_per_second": 12.648,
+      "step": 15
+    },
+    {
+      "epoch": 0.013748657357679914,
+      "grad_norm": 3.206510543823242,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 7.9036,
+      "step": 16
+    },
+    {
+      "epoch": 0.014607948442534909,
+      "grad_norm": 3.5856943130493164,
+      "learning_rate": 0.00011045284632676536,
+      "loss": 8.6164,
+      "step": 17
+    },
+    {
+      "epoch": 0.015467239527389903,
+      "grad_norm": 3.43984055519104,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 7.6898,
+      "step": 18
+    },
+    {
+      "epoch": 0.0163265306122449,
+      "grad_norm": 3.85607647895813,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 7.55,
+      "step": 19
+    },
+    {
+      "epoch": 0.017185821697099892,
+      "grad_norm": 3.1455907821655273,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 7.6952,
+      "step": 20
+    },
+    {
+      "epoch": 0.017185821697099892,
+      "eval_loss": 1.928753137588501,
+      "eval_runtime": 19.174,
+      "eval_samples_per_second": 25.555,
+      "eval_steps_per_second": 12.778,
+      "step": 20
+    },
+    {
+      "epoch": 0.01804511278195489,
+      "grad_norm": 3.3137094974517822,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 7.6498,
+      "step": 21
+    },
+    {
+      "epoch": 0.01890440386680988,
+      "grad_norm": 3.6163105964660645,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 7.9769,
+      "step": 22
+    },
+    {
+      "epoch": 0.019763694951664877,
+      "grad_norm": 3.250875949859619,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 7.7797,
+      "step": 23
+    },
+    {
+      "epoch": 0.02062298603651987,
+      "grad_norm": 3.4587433338165283,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 8.4249,
+      "step": 24
+    },
+    {
+      "epoch": 0.021482277121374866,
+      "grad_norm": 3.9059975147247314,
+      "learning_rate": 0.0,
+      "loss": 8.0331,
+      "step": 25
+    },
+    {
+      "epoch": 0.021482277121374866,
+      "eval_loss": 1.923120141029358,
+      "eval_runtime": 19.308,
+      "eval_samples_per_second": 25.378,
+      "eval_steps_per_second": 12.689,
+      "step": 25
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 25,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 10,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 2,
+        "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": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 85979522138112.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

last-checkpoint/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d378a371d0114188b3cc9dcb923fabc93b7f3b4cd074ab7bd5f6614f5835e78
+size 6712

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,31 @@
+{
+  "add_bos_token": true,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "</s>",
+  "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": "</s>",
+  "errors": "replace",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "</s>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d378a371d0114188b3cc9dcb923fabc93b7f3b4cd074ab7bd5f6614f5835e78
+size 6712