End of training

README.md

@@ -0,0 +1,158 @@
+---
+library_name: peft
+license: mit
+base_model: EleutherAI/gpt-neo-125m
+tags:
+- axolotl
+- generated_from_trainer
+model-index:
+- name: 800c0a0f-6f19-4ff1-8d1c-22976973d989
+  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: EleutherAI/gpt-neo-125m
+bf16: auto
+chat_template: llama3
+dataset_prepared_path: null
+datasets:
+- data_files:
+  - 882781a320e204e0_train_data.json
+  ds_type: json
+  format: custom
+  path: /workspace/input_data/882781a320e204e0_train_data.json
+  type:
+    field_instruction: prompt_type
+    field_output: input
+    format: '{instruction}'
+    no_input_format: '{instruction}'
+    system_format: '{system}'
+    system_prompt: ''
+debug: null
+deepspeed: null
+device: cuda
+early_stopping_patience: 1
+eval_max_new_tokens: 128
+eval_steps: 5
+eval_table_size: null
+evals_per_epoch: null
+flash_attention: false
+fp16: null
+gradient_accumulation_steps: 4
+gradient_checkpointing: true
+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: false
+local_rank: null
+logging_steps: 3
+lora_alpha: 32
+lora_dropout: 0.05
+lora_fan_in_fan_out: null
+lora_model_dir: null
+lora_r: 16
+lora_target_linear: true
+lr_scheduler: cosine
+max_memory:
+  0: 78GiB
+max_steps: 30
+micro_batch_size: 2
+mlflow_experiment_name: /tmp/882781a320e204e0_train_data.json
+model_type: AutoModelForCausalLM
+num_epochs: 1
+optimizer: adamw_torch
+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: 1024
+special_tokens:
+  pad_token: <|endoftext|>
+strict: false
+tf32: false
+tokenizer_type: AutoTokenizer
+train_on_inputs: true
+trust_remote_code: true
+val_set_size: 0.05
+wandb_entity: null
+wandb_mode: online
+wandb_name: 93fed7b9-eabe-4412-9294-859693833e4a
+wandb_project: Gradients-On-Demand
+wandb_run: your_name
+wandb_runid: 93fed7b9-eabe-4412-9294-859693833e4a
+warmup_steps: 5
+weight_decay: 0.01
+xformers_attention: true
+
+```
+
+</details><br>
+
+# 800c0a0f-6f19-4ff1-8d1c-22976973d989
+
+This model is a fine-tuned version of [EleutherAI/gpt-neo-125m](https://huggingface.co/EleutherAI/gpt-neo-125m) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 2.4069
+
+## 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_TORCH 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: 5
+- training_steps: 30
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| No log        | 0.0002 | 1    | 2.5993          |
+| 9.9456        | 0.0009 | 5    | 2.5781          |
+| 10.5193       | 0.0018 | 10   | 2.4776          |
+| 9.4294        | 0.0026 | 15   | 2.4330          |
+| 9.1762        | 0.0035 | 20   | 2.4167          |
+| 8.8708        | 0.0044 | 25   | 2.4079          |
+| 10.183        | 0.0053 | 30   | 2.4069          |
+
+
+### 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": "EleutherAI/gpt-neo-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": 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": [
+    "out_proj",
+    "c_proj",
+    "c_fc",
+    "v_proj",
+    "q_proj",
+    "k_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:e289492747a772d16ed149bf776487ca8f45cc31c731d68ccf8673e3ce4f3092
+size 10669066

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ccc5cff09f82ef7a06dacb2a72a0ce993224408a23f0d43a9ad0b59c85db87d
+size 10636096

config.json

@@ -0,0 +1,55 @@
+{
+  "_attn_implementation_autoset": true,
+  "_name_or_path": "EleutherAI/gpt-neo-125m",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPTNeoForCausalLM"
+  ],
+  "attention_dropout": 0,
+  "attention_layers": [
+    "global",
+    "local",
+    "global",
+    "local",
+    "global",
+    "local",
+    "global",
+    "local",
+    "global",
+    "local",
+    "global",
+    "local"
+  ],
+  "attention_types": [
+    [
+      [
+        "global",
+        "local"
+      ],
+      6
+    ]
+  ],
+  "bos_token_id": 50256,
+  "classifier_dropout": 0.1,
+  "embed_dropout": 0,
+  "eos_token_id": 50256,
+  "gradient_checkpointing": false,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": null,
+  "layer_norm_epsilon": 1e-05,
+  "max_position_embeddings": 2048,
+  "model_type": "gpt_neo",
+  "num_heads": 12,
+  "num_layers": 12,
+  "resid_dropout": 0,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "transformers_version": "4.46.0",
+  "use_cache": false,
+  "vocab_size": 50257,
+  "window_size": 256
+}

last-checkpoint/README.md

@@ -0,0 +1,202 @@
+---
+base_model: EleutherAI/gpt-neo-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": "EleutherAI/gpt-neo-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": 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": [
+    "out_proj",
+    "c_proj",
+    "c_fc",
+    "v_proj",
+    "q_proj",
+    "k_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 sha256:7ccc5cff09f82ef7a06dacb2a72a0ce993224408a23f0d43a9ad0b59c85db87d
+size 10636096

last-checkpoint/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d9dd7f8bf5ff5658130f3f7dcc3f3ce87ffa0bc3ac2534f073d32f25a2f4d74
+size 21354682

last-checkpoint/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8691329f440bf4f5ee2475d4e8590532ce29184583b8bedd7cbb7e69b495e52
+size 14244

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
+size 1064

last-checkpoint/special_tokens_map.json

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

last-checkpoint/tokenizer_config.json

@@ -0,0 +1,23 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "50256": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "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": true,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "model_max_length": 2048,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

last-checkpoint/trainer_state.json

@@ -0,0 +1,168 @@
+{
+  "best_metric": 2.406879425048828,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.0052514113167913875,
+  "eval_steps": 5,
+  "global_step": 30,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.00017504704389304627,
+      "eval_loss": 2.599263906478882,
+      "eval_runtime": 29.6592,
+      "eval_samples_per_second": 81.122,
+      "eval_steps_per_second": 40.561,
+      "step": 1
+    },
+    {
+      "epoch": 0.0005251411316791387,
+      "grad_norm": 1.3951877355575562,
+      "learning_rate": 0.00012,
+      "loss": 9.9456,
+      "step": 3
+    },
+    {
+      "epoch": 0.0008752352194652313,
+      "eval_loss": 2.5780935287475586,
+      "eval_runtime": 29.8289,
+      "eval_samples_per_second": 80.66,
+      "eval_steps_per_second": 40.33,
+      "step": 5
+    },
+    {
+      "epoch": 0.0010502822633582775,
+      "grad_norm": 1.2411249876022339,
+      "learning_rate": 0.0001992114701314478,
+      "loss": 11.1858,
+      "step": 6
+    },
+    {
+      "epoch": 0.0015754233950374162,
+      "grad_norm": 0.9938393831253052,
+      "learning_rate": 0.00018763066800438636,
+      "loss": 10.5193,
+      "step": 9
+    },
+    {
+      "epoch": 0.0017504704389304626,
+      "eval_loss": 2.4776437282562256,
+      "eval_runtime": 29.9977,
+      "eval_samples_per_second": 80.206,
+      "eval_steps_per_second": 40.103,
+      "step": 10
+    },
+    {
+      "epoch": 0.002100564526716555,
+      "grad_norm": 0.5660353899002075,
+      "learning_rate": 0.000163742398974869,
+      "loss": 9.1216,
+      "step": 12
+    },
+    {
+      "epoch": 0.0026257056583956937,
+      "grad_norm": 0.7864254713058472,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 9.4294,
+      "step": 15
+    },
+    {
+      "epoch": 0.0026257056583956937,
+      "eval_loss": 2.4329674243927,
+      "eval_runtime": 29.8474,
+      "eval_samples_per_second": 80.61,
+      "eval_steps_per_second": 40.305,
+      "step": 15
+    },
+    {
+      "epoch": 0.0031508467900748325,
+      "grad_norm": 0.8525682687759399,
+      "learning_rate": 9.372094804706867e-05,
+      "loss": 9.1762,
+      "step": 18
+    },
+    {
+      "epoch": 0.003500940877860925,
+      "eval_loss": 2.4166924953460693,
+      "eval_runtime": 29.7208,
+      "eval_samples_per_second": 80.953,
+      "eval_steps_per_second": 40.477,
+      "step": 20
+    },
+    {
+      "epoch": 0.0036759879217539712,
+      "grad_norm": 1.8014469146728516,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 11.2091,
+      "step": 21
+    },
+    {
+      "epoch": 0.00420112905343311,
+      "grad_norm": 0.7783241271972656,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 8.8708,
+      "step": 24
+    },
+    {
+      "epoch": 0.0043761760973261565,
+      "eval_loss": 2.4078986644744873,
+      "eval_runtime": 29.6893,
+      "eval_samples_per_second": 81.039,
+      "eval_steps_per_second": 40.52,
+      "step": 25
+    },
+    {
+      "epoch": 0.004726270185112249,
+      "grad_norm": 1.095931887626648,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 10.1005,
+      "step": 27
+    },
+    {
+      "epoch": 0.0052514113167913875,
+      "grad_norm": 0.9916987419128418,
+      "learning_rate": 0.0,
+      "loss": 10.183,
+      "step": 30
+    },
+    {
+      "epoch": 0.0052514113167913875,
+      "eval_loss": 2.406879425048828,
+      "eval_runtime": 29.5806,
+      "eval_samples_per_second": 81.337,
+      "eval_steps_per_second": 40.669,
+      "step": 30
+    }
+  ],
+  "logging_steps": 3,
+  "max_steps": 30,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 10,
+  "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": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 149764618321920.0,
+  "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 sha256:45c650f28f8d507e56d809ba2953d24c90b2f8ec7b071df35599e5bffe36d264
+size 6776

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1,23 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "50256": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "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": true,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "model_max_length": 2048,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45c650f28f8d507e56d809ba2953d24c90b2f8ec7b071df35599e5bffe36d264
+size 6776