End of training

README.md

@@ -0,0 +1,167 @@
+---
+library_name: peft
+base_model: samoline/abcd8351-bb0a-4b86-9251-81ff047d7475
+tags:
+- axolotl
+- generated_from_trainer
+model-index:
+- name: a407c9d1-9dba-449c-937f-934464814b5f
+  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: samoline/abcd8351-bb0a-4b86-9251-81ff047d7475
+bf16: auto
+chat_template: llama3
+dataset_prepared_path: null
+datasets:
+- data_files:
+  - train_c4393383-ef1d-4e9c-b95c-18b4f735570d.json
+  ds_type: json
+  format: custom
+  path: /workspace/input_data/train_c4393383-ef1d-4e9c-b95c-18b4f735570d.json
+  type:
+    field_input: input
+    field_instruction: instruction
+    field_output: output
+    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/train_c4393383-ef1d-4e9c-b95c-18b4f735570d.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: a407c9d1-9dba-449c-937f-934464814b5f
+wandb_project: Gradients-On-Demand
+wandb_run: your_name
+wandb_runid: a407c9d1-9dba-449c-937f-934464814b5f
+warmup_steps: 10
+weight_decay: 0.0
+xformers_attention: null
+
+```
+
+</details><br>
+
+# a407c9d1-9dba-449c-937f-934464814b5f
+
+This model is a fine-tuned version of [samoline/abcd8351-bb0a-4b86-9251-81ff047d7475](https://huggingface.co/samoline/abcd8351-bb0a-4b86-9251-81ff047d7475) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.2246
+
+## 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 |
+|:-------------:|:------:|:----:|:---------------:|
+| 1.4242        | 0.0008 | 1    | 1.6579          |
+| 1.4496        | 0.0106 | 13   | 1.3727          |
+| 1.3879        | 0.0212 | 26   | 1.2557          |
+| 1.3243        | 0.0317 | 39   | 1.2246          |
+
+
+### 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 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "samoline/abcd8351-bb0a-4b86-9251-81ff047d7475",
+  "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": [
+    "gate_proj",
+    "up_proj",
+    "k_proj",
+    "q_proj",
+    "o_proj",
+    "down_proj",
+    "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 sha256:65de2cd0a8a6c52298cc6949e39dccfaf6b0f196fa512571fc605129e18f49f4
+size 51521322

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:181e7fe0d0449f96b2db5af587197bd7a41a98a8f4502537fe55dd836cfbd98e
+size 51431872

added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "<|endofprompt|>": 100276,
+  "<|im_end|>": 100265,
+  "<|im_start|>": 100264
+}

config.json

@@ -0,0 +1,37 @@
+{
+  "_attn_implementation_autoset": true,
+  "_name_or_path": "samoline/abcd8351-bb0a-4b86-9251-81ff047d7475",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 100257,
+  "eos_token_id": 100257,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 3072,
+  "initializer_range": 0.02,
+  "intermediate_size": 9216,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 24,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 32.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": true,
+  "torch_dtype": "float16",
+  "transformers_version": "4.46.0",
+  "use_cache": false,
+  "vocab_size": 100263
+}

last-checkpoint/README.md

@@ -0,0 +1,202 @@
+---
+base_model: samoline/abcd8351-bb0a-4b86-9251-81ff047d7475
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.13.2

last-checkpoint/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "samoline/abcd8351-bb0a-4b86-9251-81ff047d7475",
+  "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": [
+    "gate_proj",
+    "up_proj",
+    "k_proj",
+    "q_proj",
+    "o_proj",
+    "down_proj",
+    "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 sha256:181e7fe0d0449f96b2db5af587197bd7a41a98a8f4502537fe55dd836cfbd98e
+size 51431872

last-checkpoint/added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "<|endofprompt|>": 100276,
+  "<|im_end|>": 100265,
+  "<|im_start|>": 100264
+}

last-checkpoint/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df2e5cfb41cd22d600c53e66e1f89517c7768e6826fb8dd37eade8c93bb0ea99
+size 26550260

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

last-checkpoint/tokenizer_config.json

@@ -0,0 +1,70 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "100257": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100258": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100259": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100260": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100264": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100265": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100276": {
+      "content": "<|endofprompt|>",
+      "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": false,
+  "eos_token": "<|endoftext|>",
+  "extra_special_tokens": {},
+  "model_max_length": 8192,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

last-checkpoint/trainer_state.json

@@ -0,0 +1,415 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.04067314047485891,
+  "eval_steps": 13,
+  "global_step": 50,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0008134628094971783,
+      "grad_norm": 0.9108312726020813,
+      "learning_rate": 1e-05,
+      "loss": 1.4242,
+      "step": 1
+    },
+    {
+      "epoch": 0.0008134628094971783,
+      "eval_loss": 1.6578611135482788,
+      "eval_runtime": 195.6942,
+      "eval_samples_per_second": 10.583,
+      "eval_steps_per_second": 5.294,
+      "step": 1
+    },
+    {
+      "epoch": 0.0016269256189943566,
+      "grad_norm": 0.8185848593711853,
+      "learning_rate": 2e-05,
+      "loss": 1.4684,
+      "step": 2
+    },
+    {
+      "epoch": 0.0024403884284915347,
+      "grad_norm": 0.8753907680511475,
+      "learning_rate": 3e-05,
+      "loss": 1.4355,
+      "step": 3
+    },
+    {
+      "epoch": 0.0032538512379887133,
+      "grad_norm": 0.8084831237792969,
+      "learning_rate": 4e-05,
+      "loss": 1.4623,
+      "step": 4
+    },
+    {
+      "epoch": 0.004067314047485892,
+      "grad_norm": 0.776229202747345,
+      "learning_rate": 5e-05,
+      "loss": 1.4744,
+      "step": 5
+    },
+    {
+      "epoch": 0.0048807768569830694,
+      "grad_norm": 0.7320299744606018,
+      "learning_rate": 6e-05,
+      "loss": 1.5194,
+      "step": 6
+    },
+    {
+      "epoch": 0.005694239666480248,
+      "grad_norm": 0.8332337141036987,
+      "learning_rate": 7e-05,
+      "loss": 1.4006,
+      "step": 7
+    },
+    {
+      "epoch": 0.0065077024759774265,
+      "grad_norm": 0.9180299639701843,
+      "learning_rate": 8e-05,
+      "loss": 1.4191,
+      "step": 8
+    },
+    {
+      "epoch": 0.007321165285474605,
+      "grad_norm": 0.8599632382392883,
+      "learning_rate": 9e-05,
+      "loss": 1.3284,
+      "step": 9
+    },
+    {
+      "epoch": 0.008134628094971784,
+      "grad_norm": 1.0169434547424316,
+      "learning_rate": 0.0001,
+      "loss": 1.3026,
+      "step": 10
+    },
+    {
+      "epoch": 0.008948090904468962,
+      "grad_norm": 1.1758923530578613,
+      "learning_rate": 9.98458666866564e-05,
+      "loss": 1.3743,
+      "step": 11
+    },
+    {
+      "epoch": 0.009761553713966139,
+      "grad_norm": 1.301285982131958,
+      "learning_rate": 9.938441702975689e-05,
+      "loss": 1.3781,
+      "step": 12
+    },
+    {
+      "epoch": 0.010575016523463317,
+      "grad_norm": 1.1804258823394775,
+      "learning_rate": 9.861849601988383e-05,
+      "loss": 1.4496,
+      "step": 13
+    },
+    {
+      "epoch": 0.010575016523463317,
+      "eval_loss": 1.3726698160171509,
+      "eval_runtime": 36.4237,
+      "eval_samples_per_second": 56.859,
+      "eval_steps_per_second": 28.443,
+      "step": 13
+    },
+    {
+      "epoch": 0.011388479332960496,
+      "grad_norm": 1.139792799949646,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 1.2662,
+      "step": 14
+    },
+    {
+      "epoch": 0.012201942142457674,
+      "grad_norm": 1.2657827138900757,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 1.2368,
+      "step": 15
+    },
+    {
+      "epoch": 0.013015404951954853,
+      "grad_norm": 0.998916745185852,
+      "learning_rate": 9.45503262094184e-05,
+      "loss": 1.1436,
+      "step": 16
+    },
+    {
+      "epoch": 0.013828867761452032,
+      "grad_norm": 1.0009139776229858,
+      "learning_rate": 9.263200821770461e-05,
+      "loss": 1.239,
+      "step": 17
+    },
+    {
+      "epoch": 0.01464233057094921,
+      "grad_norm": 1.1696265935897827,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 1.2521,
+      "step": 18
+    },
+    {
+      "epoch": 0.015455793380446387,
+      "grad_norm": 0.9146084189414978,
+      "learning_rate": 8.802029828000156e-05,
+      "loss": 1.1897,
+      "step": 19
+    },
+    {
+      "epoch": 0.016269256189943567,
+      "grad_norm": 0.9100729823112488,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 1.084,
+      "step": 20
+    },
+    {
+      "epoch": 0.017082718999440746,
+      "grad_norm": 0.8398633599281311,
+      "learning_rate": 8.247240241650918e-05,
+      "loss": 1.2046,
+      "step": 21
+    },
+    {
+      "epoch": 0.017896181808937924,
+      "grad_norm": 0.8264802694320679,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 1.2017,
+      "step": 22
+    },
+    {
+      "epoch": 0.0187096446184351,
+      "grad_norm": 0.8314357399940491,
+      "learning_rate": 7.612492823579745e-05,
+      "loss": 1.2994,
+      "step": 23
+    },
+    {
+      "epoch": 0.019523107427932278,
+      "grad_norm": 0.9849143028259277,
+      "learning_rate": 7.269952498697734e-05,
+      "loss": 1.363,
+      "step": 24
+    },
+    {
+      "epoch": 0.020336570237429456,
+      "grad_norm": 1.168421983718872,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 1.2528,
+      "step": 25
+    },
+    {
+      "epoch": 0.021150033046926635,
+      "grad_norm": 1.078614354133606,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 1.3879,
+      "step": 26
+    },
+    {
+      "epoch": 0.021150033046926635,
+      "eval_loss": 1.2557233572006226,
+      "eval_runtime": 36.435,
+      "eval_samples_per_second": 56.841,
+      "eval_steps_per_second": 28.434,
+      "step": 26
+    },
+    {
+      "epoch": 0.021963495856423813,
+      "grad_norm": 0.7654521465301514,
+      "learning_rate": 6.167226819279528e-05,
+      "loss": 1.1113,
+      "step": 27
+    },
+    {
+      "epoch": 0.022776958665920992,
+      "grad_norm": 0.7602103352546692,
+      "learning_rate": 5.782172325201155e-05,
+      "loss": 1.2211,
+      "step": 28
+    },
+    {
+      "epoch": 0.02359042147541817,
+      "grad_norm": 0.8696973323822021,
+      "learning_rate": 5.392295478639225e-05,
+      "loss": 1.1937,
+      "step": 29
+    },
+    {
+      "epoch": 0.02440388428491535,
+      "grad_norm": 0.6972202062606812,
+      "learning_rate": 5e-05,
+      "loss": 1.1481,
+      "step": 30
+    },
+    {
+      "epoch": 0.025217347094412527,
+      "grad_norm": 0.8415080308914185,
+      "learning_rate": 4.607704521360776e-05,
+      "loss": 1.3055,
+      "step": 31
+    },
+    {
+      "epoch": 0.026030809903909706,
+      "grad_norm": 0.6529223322868347,
+      "learning_rate": 4.2178276747988446e-05,
+      "loss": 1.2149,
+      "step": 32
+    },
+    {
+      "epoch": 0.026844272713406885,
+      "grad_norm": 0.8038480281829834,
+      "learning_rate": 3.832773180720475e-05,
+      "loss": 1.1512,
+      "step": 33
+    },
+    {
+      "epoch": 0.027657735522904063,
+      "grad_norm": 0.7951949238777161,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 1.2931,
+      "step": 34
+    },
+    {
+      "epoch": 0.02847119833240124,
+      "grad_norm": 0.6698573231697083,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 1.1721,
+      "step": 35
+    },
+    {
+      "epoch": 0.02928466114189842,
+      "grad_norm": 0.7140055298805237,
+      "learning_rate": 2.7300475013022663e-05,
+      "loss": 1.1752,
+      "step": 36
+    },
+    {
+      "epoch": 0.0300981239513956,
+      "grad_norm": 0.6723005175590515,
+      "learning_rate": 2.3875071764202563e-05,
+      "loss": 1.2337,
+      "step": 37
+    },
+    {
+      "epoch": 0.030911586760892774,
+      "grad_norm": 0.6740083694458008,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 1.2048,
+      "step": 38
+    },
+    {
+      "epoch": 0.031725049570389956,
+      "grad_norm": 0.7262203097343445,
+      "learning_rate": 1.7527597583490822e-05,
+      "loss": 1.3243,
+      "step": 39
+    },
+    {
+      "epoch": 0.031725049570389956,
+      "eval_loss": 1.2246425151824951,
+      "eval_runtime": 36.4241,
+      "eval_samples_per_second": 56.858,
+      "eval_steps_per_second": 28.443,
+      "step": 39
+    },
+    {
+      "epoch": 0.032538512379887134,
+      "grad_norm": 0.7718028426170349,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.2117,
+      "step": 40
+    },
+    {
+      "epoch": 0.03335197518938431,
+      "grad_norm": 0.7411465048789978,
+      "learning_rate": 1.1979701719998453e-05,
+      "loss": 1.1954,
+      "step": 41
+    },
+    {
+      "epoch": 0.03416543799888149,
+      "grad_norm": 0.7557942867279053,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 1.1628,
+      "step": 42
+    },
+    {
+      "epoch": 0.03497890080837867,
+      "grad_norm": 0.9376694560050964,
+      "learning_rate": 7.367991782295391e-06,
+      "loss": 1.2205,
+      "step": 43
+    },
+    {
+      "epoch": 0.03579236361787585,
+      "grad_norm": 0.7513824105262756,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 1.2009,
+      "step": 44
+    },
+    {
+      "epoch": 0.03660582642737303,
+      "grad_norm": 0.7382362484931946,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.2458,
+      "step": 45
+    },
+    {
+      "epoch": 0.0374192892368702,
+      "grad_norm": 0.7333554625511169,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 1.1459,
+      "step": 46
+    },
+    {
+      "epoch": 0.03823275204636738,
+      "grad_norm": 0.6778184175491333,
+      "learning_rate": 1.3815039801161721e-06,
+      "loss": 1.1253,
+      "step": 47
+    },
+    {
+      "epoch": 0.039046214855864556,
+      "grad_norm": 0.7480204105377197,
+      "learning_rate": 6.15582970243117e-07,
+      "loss": 1.2115,
+      "step": 48
+    },
+    {
+      "epoch": 0.039859677665361734,
+      "grad_norm": 0.7647523283958435,
+      "learning_rate": 1.5413331334360182e-07,
+      "loss": 1.2324,
+      "step": 49
+    },
+    {
+      "epoch": 0.04067314047485891,
+      "grad_norm": 0.8021819591522217,
+      "learning_rate": 0.0,
+      "loss": 1.2514,
+      "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": 1.53307661205504e+16,
+  "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 sha256:0bfa4c9ef60788d923e8521efbb3e8c084e4f7dd882a7f2930bdaaf7a827143c
+size 6776

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1,70 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "100257": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100258": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100259": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100260": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100264": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100265": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100276": {
+      "content": "<|endofprompt|>",
+      "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": false,
+  "eos_token": "<|endoftext|>",
+  "extra_special_tokens": {},
+  "model_max_length": 8192,
+  "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 sha256:0bfa4c9ef60788d923e8521efbb3e8c084e4f7dd882a7f2930bdaaf7a827143c
+size 6776