End of training

README.md

@@ -0,0 +1,167 @@
+---
+library_name: peft
+base_model: katuni4ka/tiny-random-falcon-40b
+tags:
+- axolotl
+- generated_from_trainer
+model-index:
+- name: 246c1af2-6d59-49c1-af3c-679189ac4ada
+  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
+accelerate_config:
+  dynamo_backend: inductor
+  mixed_precision: bf16
+  num_machines: 1
+  num_processes: auto
+  use_cpu: false
+adapter: lora
+base_model: katuni4ka/tiny-random-falcon-40b
+bf16: auto
+chat_template: llama3
+dataset_prepared_path: null
+datasets:
+- data_files:
+  - 1ad82bd34b989afb_train_data.json
+  ds_type: json
+  format: custom
+  path: /workspace/input_data/1ad82bd34b989afb_train_data.json
+  type:
+    field_input: context
+    field_instruction: statement
+    field_output: justification
+    format: '{instruction} {input}'
+    no_input_format: '{instruction}'
+    system_format: '{system}'
+    system_prompt: ''
+debug: null
+deepspeed: null
+device_map: auto
+early_stopping_patience: null
+eval_max_new_tokens: 128
+eval_table_size: null
+evals_per_epoch: 4
+flash_attention: false
+fp16: null
+fsdp: null
+fsdp_config: null
+gradient_accumulation_steps: 16
+gradient_checkpointing: true
+group_by_length: false
+hub_model_id: null
+hub_repo: null
+hub_strategy: checkpoint
+hub_token: null
+learning_rate: 0.0001
+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
+lora_target_modules:
+- q_proj
+- v_proj
+lr_scheduler: cosine
+max_memory:
+  0: 70GiB
+max_steps: 50
+micro_batch_size: 2
+mlflow_experiment_name: /tmp/1ad82bd34b989afb_train_data.json
+model_type: AutoModelForCausalLM
+num_epochs: 1
+optimizer: adamw_bnb_8bit
+output_dir: miner_id_24
+pad_to_sequence_len: true
+quantization_config:
+  llm_int8_enable_fp32_cpu_offload: true
+  load_in_8bit: true
+resume_from_checkpoint: null
+s2_attention: null
+sample_packing: false
+saves_per_epoch: 4
+sequence_len: 512
+special_tokens:
+  pad_token: <|endoftext|>
+strict: false
+tf32: false
+tokenizer_type: AutoTokenizer
+torch_compile: true
+train_on_inputs: false
+trust_remote_code: true
+val_set_size: 0.05
+wandb_entity: null
+wandb_mode: online
+wandb_name: 246c1af2-6d59-49c1-af3c-679189ac4ada
+wandb_project: Gradients-On-Demand
+wandb_run: your_name
+wandb_runid: 246c1af2-6d59-49c1-af3c-679189ac4ada
+warmup_steps: 10
+weight_decay: 0.0
+xformers_attention: null
+
+```
+
+</details><br>
+
+# 246c1af2-6d59-49c1-af3c-679189ac4ada
+
+This model is a fine-tuned version of [katuni4ka/tiny-random-falcon-40b](https://huggingface.co/katuni4ka/tiny-random-falcon-40b) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 11.0813
+
+## 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: 2
+- eval_batch_size: 2
+- seed: 42
+- gradient_accumulation_steps: 16
+- total_train_batch_size: 32
+- 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: 50
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 178.0         | 0.0015 | 1    | 11.1198         |
+| 177.8125      | 0.0192 | 13   | 11.1134         |
+| 177.5625      | 0.0383 | 26   | 11.0940         |
+| 177.4375      | 0.0575 | 39   | 11.0813         |
+
+
+### 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": "katuni4ka/tiny-random-falcon-40b",
+  "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": [
+    "dense_h_to_4h",
+    "q_proj",
+    "dense_4h_to_h",
+    "query_key_value",
+    "dense",
+    "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 sha256:97c9a223d9b641c634271a2acabdbf8c137ac4d9dc035ba47e1c463e4ef957d5
+size 129182

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54bad2ebdce62033c5cc03d5819af0f695964488fc49bafa0463c1f98b69934b
+size 125040

config.json

@@ -0,0 +1,34 @@
+{
+  "_attn_implementation_autoset": true,
+  "_name_or_path": "katuni4ka/tiny-random-falcon-40b",
+  "activation": "gelu",
+  "alibi": false,
+  "apply_residual_connection_post_layernorm": false,
+  "architectures": [
+    "FalconForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bias": false,
+  "bos_token_id": null,
+  "eos_token_id": 11,
+  "ffn_hidden_size": 512,
+  "hidden_dropout": 0.0,
+  "hidden_size": 128,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "max_position_embeddings": 2048,
+  "model_type": "falcon",
+  "multi_query": true,
+  "new_decoder_architecture": true,
+  "num_attention_heads": 16,
+  "num_hidden_layers": 2,
+  "num_kv_heads": 8,
+  "num_ln_in_parallel_attn": 2,
+  "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: katuni4ka/tiny-random-falcon-40b
+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": "katuni4ka/tiny-random-falcon-40b",
+  "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": [
+    "dense_h_to_4h",
+    "q_proj",
+    "dense_4h_to_h",
+    "query_key_value",
+    "dense",
+    "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 sha256:54bad2ebdce62033c5cc03d5819af0f695964488fc49bafa0463c1f98b69934b
+size 125040

last-checkpoint/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00cba44cafb5427c68d520b538784bedcd772f1627691f363c3bec2399597abc
+size 162868

last-checkpoint/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2edc13c60910e9acd555e90579b2ee1807926bb393c7c79b1e24163c3f5bfc9f
+size 14244

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
+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": false,
+  "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 +1,415 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.07367160880375725,
+  "eval_steps": 13,
+  "global_step": 50,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0014734321760751451,
+      "grad_norm": 2.526303768157959,
+      "learning_rate": 1e-05,
+      "loss": 178.0,
+      "step": 1
+    },
+    {
+      "epoch": 0.0014734321760751451,
+      "eval_loss": 11.119754791259766,
+      "eval_runtime": 16.9469,
+      "eval_samples_per_second": 67.505,
+      "eval_steps_per_second": 33.752,
+      "step": 1
+    },
+    {
+      "epoch": 0.0029468643521502903,
+      "grad_norm": 2.3691565990448,
+      "learning_rate": 2e-05,
+      "loss": 177.875,
+      "step": 2
+    },
+    {
+      "epoch": 0.004420296528225435,
+      "grad_norm": 2.2422916889190674,
+      "learning_rate": 3e-05,
+      "loss": 178.0,
+      "step": 3
+    },
+    {
+      "epoch": 0.0058937287043005805,
+      "grad_norm": 2.2829580307006836,
+      "learning_rate": 4e-05,
+      "loss": 177.9375,
+      "step": 4
+    },
+    {
+      "epoch": 0.007367160880375725,
+      "grad_norm": 2.3341360092163086,
+      "learning_rate": 5e-05,
+      "loss": 178.0,
+      "step": 5
+    },
+    {
+      "epoch": 0.00884059305645087,
+      "grad_norm": 2.2904160022735596,
+      "learning_rate": 6e-05,
+      "loss": 177.875,
+      "step": 6
+    },
+    {
+      "epoch": 0.010314025232526015,
+      "grad_norm": 2.4523940086364746,
+      "learning_rate": 7e-05,
+      "loss": 177.9375,
+      "step": 7
+    },
+    {
+      "epoch": 0.011787457408601161,
+      "grad_norm": 2.219071388244629,
+      "learning_rate": 8e-05,
+      "loss": 178.0,
+      "step": 8
+    },
+    {
+      "epoch": 0.013260889584676305,
+      "grad_norm": 2.4279353618621826,
+      "learning_rate": 9e-05,
+      "loss": 177.9375,
+      "step": 9
+    },
+    {
+      "epoch": 0.01473432176075145,
+      "grad_norm": 2.4859466552734375,
+      "learning_rate": 0.0001,
+      "loss": 177.9375,
+      "step": 10
+    },
+    {
+      "epoch": 0.016207753936826594,
+      "grad_norm": 2.4604239463806152,
+      "learning_rate": 9.98458666866564e-05,
+      "loss": 177.875,
+      "step": 11
+    },
+    {
+      "epoch": 0.01768118611290174,
+      "grad_norm": 2.6057918071746826,
+      "learning_rate": 9.938441702975689e-05,
+      "loss": 177.8125,
+      "step": 12
+    },
+    {
+      "epoch": 0.019154618288976886,
+      "grad_norm": 2.450312376022339,
+      "learning_rate": 9.861849601988383e-05,
+      "loss": 177.8125,
+      "step": 13
+    },
+    {
+      "epoch": 0.019154618288976886,
+      "eval_loss": 11.113417625427246,
+      "eval_runtime": 1.4419,
+      "eval_samples_per_second": 793.402,
+      "eval_steps_per_second": 396.701,
+      "step": 13
+    },
+    {
+      "epoch": 0.02062805046505203,
+      "grad_norm": 2.529689311981201,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 177.875,
+      "step": 14
+    },
+    {
+      "epoch": 0.022101482641127174,
+      "grad_norm": 2.641403913497925,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 177.8125,
+      "step": 15
+    },
+    {
+      "epoch": 0.023574914817202322,
+      "grad_norm": 2.6765689849853516,
+      "learning_rate": 9.45503262094184e-05,
+      "loss": 177.875,
+      "step": 16
+    },
+    {
+      "epoch": 0.025048346993277466,
+      "grad_norm": 2.610333204269409,
+      "learning_rate": 9.263200821770461e-05,
+      "loss": 177.8125,
+      "step": 17
+    },
+    {
+      "epoch": 0.02652177916935261,
+      "grad_norm": 2.503725290298462,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 177.6875,
+      "step": 18
+    },
+    {
+      "epoch": 0.027995211345427755,
+      "grad_norm": 2.6443910598754883,
+      "learning_rate": 8.802029828000156e-05,
+      "loss": 177.75,
+      "step": 19
+    },
+    {
+      "epoch": 0.0294686435215029,
+      "grad_norm": 2.664630651473999,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 177.6875,
+      "step": 20
+    },
+    {
+      "epoch": 0.030942075697578047,
+      "grad_norm": 2.6151347160339355,
+      "learning_rate": 8.247240241650918e-05,
+      "loss": 177.625,
+      "step": 21
+    },
+    {
+      "epoch": 0.03241550787365319,
+      "grad_norm": 2.9669296741485596,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 177.5625,
+      "step": 22
+    },
+    {
+      "epoch": 0.03388894004972834,
+      "grad_norm": 3.140516996383667,
+      "learning_rate": 7.612492823579745e-05,
+      "loss": 177.4375,
+      "step": 23
+    },
+    {
+      "epoch": 0.03536237222580348,
+      "grad_norm": 2.9213013648986816,
+      "learning_rate": 7.269952498697734e-05,
+      "loss": 177.5625,
+      "step": 24
+    },
+    {
+      "epoch": 0.03683580440187863,
+      "grad_norm": 2.808756113052368,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 177.4375,
+      "step": 25
+    },
+    {
+      "epoch": 0.03830923657795377,
+      "grad_norm": 2.989635944366455,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 177.5625,
+      "step": 26
+    },
+    {
+      "epoch": 0.03830923657795377,
+      "eval_loss": 11.093968391418457,
+      "eval_runtime": 1.4116,
+      "eval_samples_per_second": 810.449,
+      "eval_steps_per_second": 405.224,
+      "step": 26
+    },
+    {
+      "epoch": 0.039782668754028916,
+      "grad_norm": 3.0922422409057617,
+      "learning_rate": 6.167226819279528e-05,
+      "loss": 177.5625,
+      "step": 27
+    },
+    {
+      "epoch": 0.04125610093010406,
+      "grad_norm": 2.9242608547210693,
+      "learning_rate": 5.782172325201155e-05,
+      "loss": 177.5,
+      "step": 28
+    },
+    {
+      "epoch": 0.042729533106179204,
+      "grad_norm": 3.0539040565490723,
+      "learning_rate": 5.392295478639225e-05,
+      "loss": 177.5,
+      "step": 29
+    },
+    {
+      "epoch": 0.04420296528225435,
+      "grad_norm": 2.946568489074707,
+      "learning_rate": 5e-05,
+      "loss": 177.5,
+      "step": 30
+    },
+    {
+      "epoch": 0.04567639745832949,
+      "grad_norm": 2.963487148284912,
+      "learning_rate": 4.607704521360776e-05,
+      "loss": 177.625,
+      "step": 31
+    },
+    {
+      "epoch": 0.047149829634404644,
+      "grad_norm": 2.9389593601226807,
+      "learning_rate": 4.2178276747988446e-05,
+      "loss": 177.3125,
+      "step": 32
+    },
+    {
+      "epoch": 0.04862326181047979,
+      "grad_norm": 3.1627955436706543,
+      "learning_rate": 3.832773180720475e-05,
+      "loss": 177.5,
+      "step": 33
+    },
+    {
+      "epoch": 0.05009669398655493,
+      "grad_norm": 3.1742196083068848,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 177.375,
+      "step": 34
+    },
+    {
+      "epoch": 0.05157012616263008,
+      "grad_norm": 3.0531041622161865,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 177.3125,
+      "step": 35
+    },
+    {
+      "epoch": 0.05304355833870522,
+      "grad_norm": 3.1435036659240723,
+      "learning_rate": 2.7300475013022663e-05,
+      "loss": 177.25,
+      "step": 36
+    },
+    {
+      "epoch": 0.054516990514780365,
+      "grad_norm": 3.3767170906066895,
+      "learning_rate": 2.3875071764202563e-05,
+      "loss": 177.375,
+      "step": 37
+    },
+    {
+      "epoch": 0.05599042269085551,
+      "grad_norm": 3.366469383239746,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 177.1875,
+      "step": 38
+    },
+    {
+      "epoch": 0.057463854866930654,
+      "grad_norm": 3.1645619869232178,
+      "learning_rate": 1.7527597583490822e-05,
+      "loss": 177.4375,
+      "step": 39
+    },
+    {
+      "epoch": 0.057463854866930654,
+      "eval_loss": 11.081294059753418,
+      "eval_runtime": 1.407,
+      "eval_samples_per_second": 813.067,
+      "eval_steps_per_second": 406.533,
+      "step": 39
+    },
+    {
+      "epoch": 0.0589372870430058,
+      "grad_norm": 3.380972385406494,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 177.375,
+      "step": 40
+    },
+    {
+      "epoch": 0.06041071921908095,
+      "grad_norm": 3.349307060241699,
+      "learning_rate": 1.1979701719998453e-05,
+      "loss": 177.25,
+      "step": 41
+    },
+    {
+      "epoch": 0.061884151395156094,
+      "grad_norm": 3.404517412185669,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 177.125,
+      "step": 42
+    },
+    {
+      "epoch": 0.06335758357123124,
+      "grad_norm": 3.3322713375091553,
+      "learning_rate": 7.367991782295391e-06,
+      "loss": 177.5,
+      "step": 43
+    },
+    {
+      "epoch": 0.06483101574730638,
+      "grad_norm": 3.0686938762664795,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 177.25,
+      "step": 44
+    },
+    {
+      "epoch": 0.06630444792338153,
+      "grad_norm": 3.107104778289795,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 177.4375,
+      "step": 45
+    },
+    {
+      "epoch": 0.06777788009945668,
+      "grad_norm": 3.2900314331054688,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 177.3125,
+      "step": 46
+    },
+    {
+      "epoch": 0.06925131227553182,
+      "grad_norm": 3.3762176036834717,
+      "learning_rate": 1.3815039801161721e-06,
+      "loss": 177.375,
+      "step": 47
+    },
+    {
+      "epoch": 0.07072474445160697,
+      "grad_norm": 3.4525339603424072,
+      "learning_rate": 6.15582970243117e-07,
+      "loss": 177.25,
+      "step": 48
+    },
+    {
+      "epoch": 0.0721981766276821,
+      "grad_norm": 3.322770595550537,
+      "learning_rate": 1.5413331334360182e-07,
+      "loss": 177.4375,
+      "step": 49
+    },
+    {
+      "epoch": 0.07367160880375725,
+      "grad_norm": 3.364713430404663,
+      "learning_rate": 0.0,
+      "loss": 177.125,
+      "step": 50
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 50,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 13,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1928960409600.0,
+  "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:b7d969e7001942d487f4f54344cdcf82aebaf3ef75c470d7e50d4d7833dab957
+size 6776

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": false,
+  "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:b7d969e7001942d487f4f54344cdcf82aebaf3ef75c470d7e50d4d7833dab957
+size 6776