Duplicate from sn56/befb98dc-b818-46e6-856d-db5bcc75d6df

Co-authored-by: Roy Joy <[email protected]>

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,192 @@
+---
+library_name: peft
+license: mit
+base_model: fxmarty/really-tiny-falcon-testing
+tags:
+- axolotl
+- generated_from_trainer
+model-index:
+- name: befb98dc-b818-46e6-856d-db5bcc75d6df
+  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: fxmarty/really-tiny-falcon-testing
+bf16: auto
+chat_template: llama3
+cosine_min_lr_ratio: 0.1
+data_processes: 4
+dataset_prepared_path: null
+datasets:
+- data_files:
+  - 7aa1c9ae1d62b619_train_data.json
+  ds_type: json
+  format: custom
+  path: /workspace/input_data/7aa1c9ae1d62b619_train_data.json
+  type:
+    field_input: new-context
+    field_instruction: new-instruction
+    field_output: new-response
+    format: '{instruction} {input}'
+    no_input_format: '{instruction}'
+    system_format: '{system}'
+    system_prompt: ''
+debug: null
+deepspeed: null
+device_map:
+  lm_head: 3
+  model.embed_tokens: 0
+  model.layers.0: 0
+  model.layers.1: 0
+  model.layers.10: 3
+  model.layers.11: 3
+  model.layers.2: 0
+  model.layers.3: 1
+  model.layers.4: 1
+  model.layers.5: 1
+  model.layers.6: 2
+  model.layers.7: 2
+  model.layers.8: 2
+  model.layers.9: 3
+  model.norm: 3
+do_eval: true
+early_stopping_patience: 1
+eval_batch_size: 1
+eval_sample_packing: false
+eval_steps: 25
+evaluation_strategy: steps
+flash_attention: false
+fp16: null
+fsdp: null
+fsdp_config: null
+gradient_accumulation_steps: 32
+gradient_checkpointing: true
+group_by_length: true
+hub_model_id: sn56/befb98dc-b818-46e6-856d-db5bcc75d6df
+hub_strategy: checkpoint
+hub_token: null
+learning_rate: 0.0001
+load_in_4bit: false
+load_in_8bit: false
+local_rank: null
+logging_steps: 1
+lora_alpha: 64
+lora_dropout: 0.05
+lora_fan_in_fan_out: null
+lora_model_dir: null
+lora_r: 32
+lora_target_linear: true
+lora_target_modules:
+- q_proj
+- v_proj
+lr_scheduler: cosine
+max_grad_norm: 0.3
+max_memory:
+  0: 60GB
+  1: 70GB
+  2: 70GB
+  3: 70GB
+  cpu: 96GB
+max_steps: 75
+micro_batch_size: 1
+mixed_precision: bf16
+mlflow_experiment_name: /tmp/7aa1c9ae1d62b619_train_data.json
+model_type: AutoModelForCausalLM
+num_epochs: 3
+optim_args:
+  adam_beta1: 0.9
+  adam_beta2: 0.95
+  adam_epsilon: 1e-5
+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: 25
+save_strategy: steps
+sequence_len: 2048
+strict: false
+tf32: false
+tokenizer_type: AutoTokenizer
+torch_compile: false
+torch_dtype: bfloat16
+train_on_inputs: false
+trust_remote_code: true
+use_cache: false
+val_set_size: 50
+wandb_entity: null
+wandb_mode: online
+wandb_name: befb98dc-b818-46e6-856d-db5bcc75d6df
+wandb_project: Public_TuningSN
+wandb_runid: befb98dc-b818-46e6-856d-db5bcc75d6df
+warmup_ratio: 0.05
+weight_decay: 0.01
+xformers_attention: null
+
+```
+
+</details><br>
+
+# befb98dc-b818-46e6-856d-db5bcc75d6df
+
+This model is a fine-tuned version of [fxmarty/really-tiny-falcon-testing](https://huggingface.co/fxmarty/really-tiny-falcon-testing) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 10.9498
+
+## 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: 0.0001
+- train_batch_size: 1
+- eval_batch_size: 1
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 4
+- gradient_accumulation_steps: 32
+- total_train_batch_size: 128
+- total_eval_batch_size: 4
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=adam_beta1=0.9,adam_beta2=0.95,adam_epsilon=1e-5
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 3
+- training_steps: 75
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 355.0044      | 0.0086 | 1    | 11.0968         |
+| 350.7261      | 0.2152 | 25   | 11.0101         |
+| 348.3621      | 0.4305 | 50   | 10.9658         |
+| 347.5739      | 0.6457 | 75   | 10.9498         |
+
+
+### 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": "fxmarty/really-tiny-falcon-testing",
+  "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": 64,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "dense_h_to_4h",
+    "dense",
+    "dense_4h_to_h",
+    "query_key_value",
+    "v_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 sha256:86460e6ae88ae67482bc5337e3f89e1128b342e4046f477928f81cf793b493ba
+size 129182

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0a51e343aae5bc85c782069c8afef89f6f15c933f681b4b496412bc7e95bee8
+size 125048

config.json

@@ -0,0 +1,40 @@
+{
+  "_attn_implementation_autoset": true,
+  "_name_or_path": "fxmarty/really-tiny-falcon-testing",
+  "alibi": false,
+  "apply_residual_connection_post_layernorm": false,
+  "architectures": [
+    "FalconForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "auto_map": {
+    "AutoConfig": "tiiuae/falcon-7b--configuration_falcon.FalconConfig",
+    "AutoModel": "tiiuae/falcon-7b--modeling_falcon.FalconModel",
+    "AutoModelForCausalLM": "tiiuae/falcon-7b--modeling_falcon.FalconForCausalLM",
+    "AutoModelForQuestionAnswering": "tiiuae/falcon-7b--modeling_falcon.FalconForQuestionAnswering",
+    "AutoModelForSequenceClassification": "tiiuae/falcon-7b--modeling_falcon.FalconForSequenceClassification",
+    "AutoModelForTokenClassification": "tiiuae/falcon-7b--modeling_falcon.FalconForTokenClassification"
+  },
+  "bias": false,
+  "bos_token_id": null,
+  "eos_token_id": 11,
+  "hidden_dropout": 0.0,
+  "hidden_size": 32,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "max_position_embeddings": 2048,
+  "model_type": "falcon",
+  "multi_query": true,
+  "new_decoder_architecture": false,
+  "nm_kv_hears": 2,
+  "num_attention_heads": 2,
+  "num_hidden_layers": 2,
+  "num_kv_heads": 71,
+  "parallel_attn": true,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "torch_dtype": "float32",
+  "transformers_version": "4.46.0",
+  "use_cache": false,
+  "vocab_size": 65024
+}

last-checkpoint/README.md

@@ -0,0 +1,202 @@
+---
+base_model: fxmarty/really-tiny-falcon-testing
+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": "fxmarty/really-tiny-falcon-testing",
+  "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": 64,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "dense_h_to_4h",
+    "dense",
+    "dense_4h_to_h",
+    "query_key_value",
+    "v_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:a0a51e343aae5bc85c782069c8afef89f6f15c933f681b4b496412bc7e95bee8
+size 125048

last-checkpoint/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59c88789b4f96fd53ad25a947dd56458ea8414f9edb5fbb10e7ac37e36ce0515
+size 259694

last-checkpoint/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f657e7d1c61ed5692689f7b706707b55743aad5546a4e25f8c3dbcf01c6f082
+size 15024

last-checkpoint/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ccc1fd59ab9c3f59b904557db0de0f3597b621d456666c6c13e1acb72fa37119
+size 15024

last-checkpoint/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc036b80f4bca61503d0b4f42fec9620a493f3c406076f5fe39ff41891111e4d
+size 15024

last-checkpoint/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8225bb832a5e579602acfcac6e13ed41c379eb598b030b6563129391e5d6ad5d
+size 15024

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b823f3900a3c8aa20bff7ce05b4e552f6bc019793f00b0bb20027204b5c704a
+size 1064

last-checkpoint/special_tokens_map.json

@@ -0,0 +1,29 @@
+{
+  "additional_special_tokens": [
+    ">>TITLE<<",
+    ">>ABSTRACT<<",
+    ">>INTRODUCTION<<",
+    ">>SUMMARY<<",
+    ">>COMMENT<<",
+    ">>ANSWER<<",
+    ">>QUESTION<<",
+    ">>DOMAIN<<",
+    ">>PREFIX<<",
+    ">>SUFFIX<<",
+    ">>MIDDLE<<"
+  ],
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

last-checkpoint/tokenizer_config.json

@@ -0,0 +1,124 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": ">>TITLE<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": ">>ABSTRACT<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": ">>INTRODUCTION<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": ">>SUMMARY<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": ">>COMMENT<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": ">>ANSWER<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": ">>QUESTION<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "7": {
+      "content": ">>DOMAIN<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "8": {
+      "content": ">>PREFIX<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "9": {
+      "content": ">>SUFFIX<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "10": {
+      "content": ">>MIDDLE<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "11": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    ">>TITLE<<",
+    ">>ABSTRACT<<",
+    ">>INTRODUCTION<<",
+    ">>SUMMARY<<",
+    ">>COMMENT<<",
+    ">>ANSWER<<",
+    ">>QUESTION<<",
+    ">>DOMAIN<<",
+    ">>PREFIX<<",
+    ">>SUFFIX<<",
+    ">>MIDDLE<<"
+  ],
+  "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|>",
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 2048,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}

last-checkpoint/trainer_state.json

@@ -0,0 +1,599 @@
+{
+  "best_metric": 10.949830055236816,
+  "best_model_checkpoint": "miner_id_24/checkpoint-75",
+  "epoch": 0.645682001614205,
+  "eval_steps": 25,
+  "global_step": 75,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.008609093354856066,
+      "grad_norm": 10.867487907409668,
+      "learning_rate": 3.3333333333333335e-05,
+      "loss": 355.0044,
+      "step": 1
+    },
+    {
+      "epoch": 0.008609093354856066,
+      "eval_loss": 11.096755027770996,
+      "eval_runtime": 0.6034,
+      "eval_samples_per_second": 82.868,
+      "eval_steps_per_second": 21.546,
+      "step": 1
+    },
+    {
+      "epoch": 0.017218186709712133,
+      "grad_norm": 11.303132057189941,
+      "learning_rate": 6.666666666666667e-05,
+      "loss": 354.975,
+      "step": 2
+    },
+    {
+      "epoch": 0.0258272800645682,
+      "grad_norm": 13.843127250671387,
+      "learning_rate": 0.0001,
+      "loss": 355.0412,
+      "step": 3
+    },
+    {
+      "epoch": 0.034436373419424265,
+      "grad_norm": 11.937524795532227,
+      "learning_rate": 9.99571699711836e-05,
+      "loss": 354.924,
+      "step": 4
+    },
+    {
+      "epoch": 0.04304546677428033,
+      "grad_norm": 12.751911163330078,
+      "learning_rate": 9.982876141412856e-05,
+      "loss": 354.8232,
+      "step": 5
+    },
+    {
+      "epoch": 0.0516545601291364,
+      "grad_norm": 12.354517936706543,
+      "learning_rate": 9.961501876182148e-05,
+      "loss": 354.8041,
+      "step": 6
+    },
+    {
+      "epoch": 0.060263653483992465,
+      "grad_norm": 13.037909507751465,
+      "learning_rate": 9.931634888554937e-05,
+      "loss": 354.611,
+      "step": 7
+    },
+    {
+      "epoch": 0.06887274683884853,
+      "grad_norm": 13.028841972351074,
+      "learning_rate": 9.893332032039701e-05,
+      "loss": 354.4688,
+      "step": 8
+    },
+    {
+      "epoch": 0.0774818401937046,
+      "grad_norm": 14.73702335357666,
+      "learning_rate": 9.846666218300807e-05,
+      "loss": 354.3231,
+      "step": 9
+    },
+    {
+      "epoch": 0.08609093354856066,
+      "grad_norm": 17.07733917236328,
+      "learning_rate": 9.791726278367022e-05,
+      "loss": 354.056,
+      "step": 10
+    },
+    {
+      "epoch": 0.09470002690341674,
+      "grad_norm": 21.84981918334961,
+      "learning_rate": 9.728616793536588e-05,
+      "loss": 353.632,
+      "step": 11
+    },
+    {
+      "epoch": 0.1033091202582728,
+      "grad_norm": 25.133949279785156,
+      "learning_rate": 9.657457896300791e-05,
+      "loss": 353.3881,
+      "step": 12
+    },
+    {
+      "epoch": 0.11191821361312887,
+      "grad_norm": 18.78001594543457,
+      "learning_rate": 9.578385041664925e-05,
+      "loss": 353.659,
+      "step": 13
+    },
+    {
+      "epoch": 0.12052730696798493,
+      "grad_norm": 10.563817024230957,
+      "learning_rate": 9.491548749301997e-05,
+      "loss": 353.9691,
+      "step": 14
+    },
+    {
+      "epoch": 0.129136400322841,
+      "grad_norm": 11.821118354797363,
+      "learning_rate": 9.397114317029975e-05,
+      "loss": 353.8424,
+      "step": 15
+    },
+    {
+      "epoch": 0.13774549367769706,
+      "grad_norm": 11.502336502075195,
+      "learning_rate": 9.295261506157986e-05,
+      "loss": 353.7357,
+      "step": 16
+    },
+    {
+      "epoch": 0.14635458703255314,
+      "grad_norm": 10.819986343383789,
+      "learning_rate": 9.186184199300464e-05,
+      "loss": 353.6895,
+      "step": 17
+    },
+    {
+      "epoch": 0.1549636803874092,
+      "grad_norm": 11.171977996826172,
+      "learning_rate": 9.070090031310558e-05,
+      "loss": 353.5294,
+      "step": 18
+    },
+    {
+      "epoch": 0.16357277374226525,
+      "grad_norm": 11.021985054016113,
+      "learning_rate": 8.947199994035401e-05,
+      "loss": 353.4442,
+      "step": 19
+    },
+    {
+      "epoch": 0.17218186709712133,
+      "grad_norm": 11.427451133728027,
+      "learning_rate": 8.817748015645558e-05,
+      "loss": 353.2932,
+      "step": 20
+    },
+    {
+      "epoch": 0.1807909604519774,
+      "grad_norm": 12.078248977661133,
+      "learning_rate": 8.681980515339464e-05,
+      "loss": 353.0774,
+      "step": 21
+    },
+    {
+      "epoch": 0.18940005380683347,
+      "grad_norm": 13.572750091552734,
+      "learning_rate": 8.540155934270471e-05,
+      "loss": 352.7897,
+      "step": 22
+    },
+    {
+      "epoch": 0.19800914716168955,
+      "grad_norm": 16.139827728271484,
+      "learning_rate": 8.392544243589427e-05,
+      "loss": 352.1232,
+      "step": 23
+    },
+    {
+      "epoch": 0.2066182405165456,
+      "grad_norm": 19.074623107910156,
+      "learning_rate": 8.239426430539243e-05,
+      "loss": 351.4342,
+      "step": 24
+    },
+    {
+      "epoch": 0.21522733387140167,
+      "grad_norm": 22.747406005859375,
+      "learning_rate": 8.081093963579707e-05,
+      "loss": 350.7261,
+      "step": 25
+    },
+    {
+      "epoch": 0.21522733387140167,
+      "eval_loss": 11.010053634643555,
+      "eval_runtime": 0.0769,
+      "eval_samples_per_second": 650.534,
+      "eval_steps_per_second": 169.139,
+      "step": 25
+    },
+    {
+      "epoch": 0.22383642722625774,
+      "grad_norm": 8.548608779907227,
+      "learning_rate": 7.917848237560709e-05,
+      "loss": 353.2629,
+      "step": 26
+    },
+    {
+      "epoch": 0.2324455205811138,
+      "grad_norm": 9.44759750366211,
+      "learning_rate": 7.75e-05,
+      "loss": 352.9843,
+      "step": 27
+    },
+    {
+      "epoch": 0.24105461393596986,
+      "grad_norm": 10.709016799926758,
+      "learning_rate": 7.577868759557654e-05,
+      "loss": 352.6682,
+      "step": 28
+    },
+    {
+      "epoch": 0.24966370729082593,
+      "grad_norm": 9.533336639404297,
+      "learning_rate": 7.401782177833148e-05,
+      "loss": 352.8022,
+      "step": 29
+    },
+    {
+      "epoch": 0.258272800645682,
+      "grad_norm": 9.468610763549805,
+      "learning_rate": 7.222075445642904e-05,
+      "loss": 352.7345,
+      "step": 30
+    },
+    {
+      "epoch": 0.2668818940005381,
+      "grad_norm": 9.217055320739746,
+      "learning_rate": 7.03909064496551e-05,
+      "loss": 352.7065,
+      "step": 31
+    },
+    {
+      "epoch": 0.2754909873553941,
+      "grad_norm": 9.265793800354004,
+      "learning_rate": 6.853176097769229e-05,
+      "loss": 352.6331,
+      "step": 32
+    },
+    {
+      "epoch": 0.2841000807102502,
+      "grad_norm": 9.615739822387695,
+      "learning_rate": 6.664685702961344e-05,
+      "loss": 352.4907,
+      "step": 33
+    },
+    {
+      "epoch": 0.29270917406510627,
+      "grad_norm": 10.331357955932617,
+      "learning_rate": 6.473978262721463e-05,
+      "loss": 352.2647,
+      "step": 34
+    },
+    {
+      "epoch": 0.3013182674199623,
+      "grad_norm": 12.123662948608398,
+      "learning_rate": 6.281416799501188e-05,
+      "loss": 351.5476,
+      "step": 35
+    },
+    {
+      "epoch": 0.3099273607748184,
+      "grad_norm": 14.970151901245117,
+      "learning_rate": 6.087367864990233e-05,
+      "loss": 350.6174,
+      "step": 36
+    },
+    {
+      "epoch": 0.31853645412967446,
+      "grad_norm": 18.231613159179688,
+      "learning_rate": 5.8922008423644624e-05,
+      "loss": 349.7336,
+      "step": 37
+    },
+    {
+      "epoch": 0.3271455474845305,
+      "grad_norm": 14.60504150390625,
+      "learning_rate": 5.696287243144013e-05,
+      "loss": 350.7061,
+      "step": 38
+    },
+    {
+      "epoch": 0.3357546408393866,
+      "grad_norm": 9.001364707946777,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 352.3064,
+      "step": 39
+    },
+    {
+      "epoch": 0.34436373419424265,
+      "grad_norm": 9.125486373901367,
+      "learning_rate": 5.303712756855988e-05,
+      "loss": 352.185,
+      "step": 40
+    },
+    {
+      "epoch": 0.35297282754909876,
+      "grad_norm": 8.79714584350586,
+      "learning_rate": 5.107799157635538e-05,
+      "loss": 352.1189,
+      "step": 41
+    },
+    {
+      "epoch": 0.3615819209039548,
+      "grad_norm": 8.923425674438477,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 352.1105,
+      "step": 42
+    },
+    {
+      "epoch": 0.37019101425881085,
+      "grad_norm": 8.289681434631348,
+      "learning_rate": 4.718583200498814e-05,
+      "loss": 352.2823,
+      "step": 43
+    },
+    {
+      "epoch": 0.37880010761366695,
+      "grad_norm": 8.199746131896973,
+      "learning_rate": 4.526021737278538e-05,
+      "loss": 352.2198,
+      "step": 44
+    },
+    {
+      "epoch": 0.387409200968523,
+      "grad_norm": 8.637060165405273,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 352.026,
+      "step": 45
+    },
+    {
+      "epoch": 0.3960182943233791,
+      "grad_norm": 9.83723258972168,
+      "learning_rate": 4.146823902230772e-05,
+      "loss": 351.563,
+      "step": 46
+    },
+    {
+      "epoch": 0.40462738767823514,
+      "grad_norm": 10.942987442016602,
+      "learning_rate": 3.960909355034491e-05,
+      "loss": 351.0425,
+      "step": 47
+    },
+    {
+      "epoch": 0.4132364810330912,
+      "grad_norm": 13.6652193069458,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 350.1031,
+      "step": 48
+    },
+    {
+      "epoch": 0.4218455743879473,
+      "grad_norm": 16.773061752319336,
+      "learning_rate": 3.598217822166854e-05,
+      "loss": 349.162,
+      "step": 49
+    },
+    {
+      "epoch": 0.43045466774280333,
+      "grad_norm": 20.8967227935791,
+      "learning_rate": 3.422131240442349e-05,
+      "loss": 348.3621,
+      "step": 50
+    },
+    {
+      "epoch": 0.43045466774280333,
+      "eval_loss": 10.965777397155762,
+      "eval_runtime": 0.0782,
+      "eval_samples_per_second": 639.534,
+      "eval_steps_per_second": 166.279,
+      "step": 50
+    },
+    {
+      "epoch": 0.4390637610976594,
+      "grad_norm": 7.474067687988281,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 352.3553,
+      "step": 51
+    },
+    {
+      "epoch": 0.4476728544525155,
+      "grad_norm": 8.300982475280762,
+      "learning_rate": 3.082151762439293e-05,
+      "loss": 351.9735,
+      "step": 52
+    },
+    {
+      "epoch": 0.4562819478073715,
+      "grad_norm": 8.844514846801758,
+      "learning_rate": 2.9189060364202943e-05,
+      "loss": 351.6582,
+      "step": 53
+    },
+    {
+      "epoch": 0.4648910411622276,
+      "grad_norm": 8.853071212768555,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 351.5546,
+      "step": 54
+    },
+    {
+      "epoch": 0.47350013451708367,
+      "grad_norm": 8.490742683410645,
+      "learning_rate": 2.6074557564105727e-05,
+      "loss": 351.6604,
+      "step": 55
+    },
+    {
+      "epoch": 0.4821092278719397,
+      "grad_norm": 7.409176349639893,
+      "learning_rate": 2.459844065729529e-05,
+      "loss": 352.1426,
+      "step": 56
+    },
+    {
+      "epoch": 0.4907183212267958,
+      "grad_norm": 7.821872234344482,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 351.8066,
+      "step": 57
+    },
+    {
+      "epoch": 0.49932741458165186,
+      "grad_norm": 8.349543571472168,
+      "learning_rate": 2.1822519843544424e-05,
+      "loss": 351.5433,
+      "step": 58
+    },
+    {
+      "epoch": 0.5079365079365079,
+      "grad_norm": 9.260781288146973,
+      "learning_rate": 2.0528000059645997e-05,
+      "loss": 351.208,
+      "step": 59
+    },
+    {
+      "epoch": 0.516545601291364,
+      "grad_norm": 10.735580444335938,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 350.6387,
+      "step": 60
+    },
+    {
+      "epoch": 0.5251546946462201,
+      "grad_norm": 13.846049308776855,
+      "learning_rate": 1.8138158006995364e-05,
+      "loss": 349.4801,
+      "step": 61
+    },
+    {
+      "epoch": 0.5337637880010762,
+      "grad_norm": 17.65458869934082,
+      "learning_rate": 1.7047384938420154e-05,
+      "loss": 348.2975,
+      "step": 62
+    },
+    {
+      "epoch": 0.5423728813559322,
+      "grad_norm": 13.394047737121582,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 349.9447,
+      "step": 63
+    },
+    {
+      "epoch": 0.5509819747107882,
+      "grad_norm": 7.800135612487793,
+      "learning_rate": 1.5084512506980026e-05,
+      "loss": 351.9247,
+      "step": 64
+    },
+    {
+      "epoch": 0.5595910680656443,
+      "grad_norm": 8.641666412353516,
+      "learning_rate": 1.4216149583350754e-05,
+      "loss": 351.5002,
+      "step": 65
+    },
+    {
+      "epoch": 0.5682001614205004,
+      "grad_norm": 8.432456970214844,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 351.3875,
+      "step": 66
+    },
+    {
+      "epoch": 0.5768092547753565,
+      "grad_norm": 9.028701782226562,
+      "learning_rate": 1.2713832064634126e-05,
+      "loss": 351.1097,
+      "step": 67
+    },
+    {
+      "epoch": 0.5854183481302125,
+      "grad_norm": 8.943015098571777,
+      "learning_rate": 1.2082737216329794e-05,
+      "loss": 351.1015,
+      "step": 68
+    },
+    {
+      "epoch": 0.5940274414850686,
+      "grad_norm": 7.793323516845703,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 351.5153,
+      "step": 69
+    },
+    {
+      "epoch": 0.6026365348399246,
+      "grad_norm": 8.137232780456543,
+      "learning_rate": 1.1066679679603e-05,
+      "loss": 351.4627,
+      "step": 70
+    },
+    {
+      "epoch": 0.6112456281947808,
+      "grad_norm": 8.868036270141602,
+      "learning_rate": 1.0683651114450641e-05,
+      "loss": 351.1549,
+      "step": 71
+    },
+    {
+      "epoch": 0.6198547215496368,
+      "grad_norm": 10.001080513000488,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 350.6647,
+      "step": 72
+    },
+    {
+      "epoch": 0.6284638149044929,
+      "grad_norm": 12.413795471191406,
+      "learning_rate": 1.017123858587145e-05,
+      "loss": 349.7495,
+      "step": 73
+    },
+    {
+      "epoch": 0.6370729082593489,
+      "grad_norm": 16.752674102783203,
+      "learning_rate": 1.00428300288164e-05,
+      "loss": 348.3455,
+      "step": 74
+    },
+    {
+      "epoch": 0.645682001614205,
+      "grad_norm": 20.989471435546875,
+      "learning_rate": 1e-05,
+      "loss": 347.5739,
+      "step": 75
+    },
+    {
+      "epoch": 0.645682001614205,
+      "eval_loss": 10.949830055236816,
+      "eval_runtime": 0.0779,
+      "eval_samples_per_second": 641.476,
+      "eval_steps_per_second": 166.784,
+      "step": 75
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 75,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 25,
+  "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": 6323739033600.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

last-checkpoint/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:458fb79226d29dc9e8fb6bef2fd3e23a2ec5d8598abfe12fd24e5af775278a06
+size 6840

special_tokens_map.json

@@ -0,0 +1,29 @@
+{
+  "additional_special_tokens": [
+    ">>TITLE<<",
+    ">>ABSTRACT<<",
+    ">>INTRODUCTION<<",
+    ">>SUMMARY<<",
+    ">>COMMENT<<",
+    ">>ANSWER<<",
+    ">>QUESTION<<",
+    ">>DOMAIN<<",
+    ">>PREFIX<<",
+    ">>SUFFIX<<",
+    ">>MIDDLE<<"
+  ],
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,124 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": ">>TITLE<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": ">>ABSTRACT<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": ">>INTRODUCTION<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": ">>SUMMARY<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": ">>COMMENT<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": ">>ANSWER<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": ">>QUESTION<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "7": {
+      "content": ">>DOMAIN<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "8": {
+      "content": ">>PREFIX<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "9": {
+      "content": ">>SUFFIX<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "10": {
+      "content": ">>MIDDLE<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "11": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    ">>TITLE<<",
+    ">>ABSTRACT<<",
+    ">>INTRODUCTION<<",
+    ">>SUMMARY<<",
+    ">>COMMENT<<",
+    ">>ANSWER<<",
+    ">>QUESTION<<",
+    ">>DOMAIN<<",
+    ">>PREFIX<<",
+    ">>SUFFIX<<",
+    ">>MIDDLE<<"
+  ],
+  "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|>",
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 2048,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:458fb79226d29dc9e8fb6bef2fd3e23a2ec5d8598abfe12fd24e5af775278a06
+size 6840