End of training

README.md

@@ -0,0 +1,168 @@
+---
+library_name: peft
+base_model: NousResearch/CodeLlama-7b-hf
+tags:
+- axolotl
+- generated_from_trainer
+model-index:
+- name: 1aa80b92-52ba-44a0-a76e-1996e838379f
+  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: NousResearch/CodeLlama-7b-hf
+bf16: auto
+chat_template: llama3
+dataset_prepared_path: null
+datasets:
+- data_files:
+  - 40971d92d753c8f8_train_data.json
+  ds_type: json
+  format: custom
+  path: /workspace/input_data/40971d92d753c8f8_train_data.json
+  type:
+    field_input: ''
+    field_instruction: text
+    field_output: phonemes
+    format: '{instruction}'
+    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: 100
+micro_batch_size: 2
+mlflow_experiment_name: /tmp/40971d92d753c8f8_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: </s>
+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: 1aa80b92-52ba-44a0-a76e-1996e838379f
+wandb_project: Gradients-On-Demand
+wandb_run: your_name
+wandb_runid: 1aa80b92-52ba-44a0-a76e-1996e838379f
+warmup_steps: 10
+weight_decay: 0.0
+xformers_attention: null
+
+```
+
+</details><br>
+
+# 1aa80b92-52ba-44a0-a76e-1996e838379f
+
+This model is a fine-tuned version of [NousResearch/CodeLlama-7b-hf](https://huggingface.co/NousResearch/CodeLlama-7b-hf) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.4357
+
+## 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: 100
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 46.3785       | 0.0000 | 1    | 3.1592          |
+| 20.1506       | 0.0012 | 25   | 1.1930          |
+| 9.8757        | 0.0024 | 50   | 0.5902          |
+| 7.3535        | 0.0036 | 75   | 0.4550          |
+| 7.457         | 0.0048 | 100  | 0.4357          |
+
+
+### 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": "NousResearch/CodeLlama-7b-hf",
+  "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": [
+    "o_proj",
+    "v_proj",
+    "k_proj",
+    "up_proj",
+    "gate_proj",
+    "down_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5090d3ffb943f693fb9811a29b2f5b121499c16a55dfd3f59fe5970a993d8f5
+size 80115210

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:274380708c9c95e73a4357fd1763b1fda96cf255109eb16f26180885c103c95b
+size 80013120

config.json

@@ -0,0 +1,33 @@
+{
+  "_attn_implementation_autoset": true,
+  "_name_or_path": "NousResearch/CodeLlama-7b-hf",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "auto_map": {
+    "AutoConfig": "NousResearch/CodeLlama-7b-hf--configuration_llama.LlamaConfig",
+    "AutoModel": "NousResearch/CodeLlama-7b-hf--modeling_llama.LlamaModel",
+    "AutoModelForCausalLM": "NousResearch/CodeLlama-7b-hf--modeling_llama.LlamaForCausalLM",
+    "AutoModelForSequenceClassification": "NousResearch/CodeLlama-7b-hf--modeling_llama.LlamaForSequenceClassification"
+  },
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 16384,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.46.0",
+  "use_cache": false,
+  "vocab_size": 32016
+}

last-checkpoint/README.md

@@ -0,0 +1,202 @@
+---
+base_model: NousResearch/CodeLlama-7b-hf
+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": "NousResearch/CodeLlama-7b-hf",
+  "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": [
+    "o_proj",
+    "v_proj",
+    "k_proj",
+    "up_proj",
+    "gate_proj",
+    "down_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

last-checkpoint/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:274380708c9c95e73a4357fd1763b1fda96cf255109eb16f26180885c103c95b
+size 80013120

last-checkpoint/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca9626c6485b27c10737a3aa5faaa1af9bfb6868768120b7c2f9809f228fed59
+size 41119636

last-checkpoint/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4c6893fc4a9ed236abb30b22cb769913941a10e57b959801e5127eb964077c8
+size 14244

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49d60a69e2379be2053e816cbaff31e6c931b5922dd86c71c9eaf473299cbf62
+size 1064

last-checkpoint/special_tokens_map.json

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

last-checkpoint/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45ccb9c8b6b561889acea59191d66986d314e7cbd6a78abc6e49b139ca91c1e6
+size 500058

last-checkpoint/tokenizer_config.json

@@ -0,0 +1,42 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

last-checkpoint/trainer_state.json

@@ -0,0 +1,773 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.004810771316978715,
+  "eval_steps": 25,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 4.8107713169787154e-05,
+      "grad_norm": 28.79413414001465,
+      "learning_rate": 1e-05,
+      "loss": 46.3785,
+      "step": 1
+    },
+    {
+      "epoch": 4.8107713169787154e-05,
+      "eval_loss": 3.159205675125122,
+      "eval_runtime": 1020.1376,
+      "eval_samples_per_second": 34.319,
+      "eval_steps_per_second": 17.159,
+      "step": 1
+    },
+    {
+      "epoch": 9.621542633957431e-05,
+      "grad_norm": 24.000699996948242,
+      "learning_rate": 2e-05,
+      "loss": 54.7236,
+      "step": 2
+    },
+    {
+      "epoch": 0.00014432313950936147,
+      "grad_norm": 20.53596305847168,
+      "learning_rate": 3e-05,
+      "loss": 50.8974,
+      "step": 3
+    },
+    {
+      "epoch": 0.00019243085267914861,
+      "grad_norm": 20.681873321533203,
+      "learning_rate": 4e-05,
+      "loss": 47.2597,
+      "step": 4
+    },
+    {
+      "epoch": 0.00024053856584893576,
+      "grad_norm": 23.725183486938477,
+      "learning_rate": 5e-05,
+      "loss": 48.6015,
+      "step": 5
+    },
+    {
+      "epoch": 0.00028864627901872294,
+      "grad_norm": 24.895259857177734,
+      "learning_rate": 6e-05,
+      "loss": 49.2229,
+      "step": 6
+    },
+    {
+      "epoch": 0.0003367539921885101,
+      "grad_norm": 31.08332633972168,
+      "learning_rate": 7e-05,
+      "loss": 49.7453,
+      "step": 7
+    },
+    {
+      "epoch": 0.00038486170535829723,
+      "grad_norm": 28.04768180847168,
+      "learning_rate": 8e-05,
+      "loss": 45.4243,
+      "step": 8
+    },
+    {
+      "epoch": 0.0004329694185280844,
+      "grad_norm": 34.26695251464844,
+      "learning_rate": 9e-05,
+      "loss": 45.0237,
+      "step": 9
+    },
+    {
+      "epoch": 0.0004810771316978715,
+      "grad_norm": 28.066192626953125,
+      "learning_rate": 0.0001,
+      "loss": 40.1862,
+      "step": 10
+    },
+    {
+      "epoch": 0.0005291848448676587,
+      "grad_norm": 36.87377166748047,
+      "learning_rate": 9.99695413509548e-05,
+      "loss": 42.7223,
+      "step": 11
+    },
+    {
+      "epoch": 0.0005772925580374459,
+      "grad_norm": 51.84431457519531,
+      "learning_rate": 9.987820251299122e-05,
+      "loss": 41.4564,
+      "step": 12
+    },
+    {
+      "epoch": 0.000625400271207233,
+      "grad_norm": 37.15995788574219,
+      "learning_rate": 9.972609476841367e-05,
+      "loss": 36.3818,
+      "step": 13
+    },
+    {
+      "epoch": 0.0006735079843770202,
+      "grad_norm": 32.011775970458984,
+      "learning_rate": 9.951340343707852e-05,
+      "loss": 37.9136,
+      "step": 14
+    },
+    {
+      "epoch": 0.0007216156975468073,
+      "grad_norm": 36.100765228271484,
+      "learning_rate": 9.924038765061042e-05,
+      "loss": 34.0668,
+      "step": 15
+    },
+    {
+      "epoch": 0.0007697234107165945,
+      "grad_norm": 31.221710205078125,
+      "learning_rate": 9.890738003669029e-05,
+      "loss": 32.4345,
+      "step": 16
+    },
+    {
+      "epoch": 0.0008178311238863816,
+      "grad_norm": 38.979557037353516,
+      "learning_rate": 9.851478631379982e-05,
+      "loss": 32.5324,
+      "step": 17
+    },
+    {
+      "epoch": 0.0008659388370561688,
+      "grad_norm": 29.161985397338867,
+      "learning_rate": 9.806308479691595e-05,
+      "loss": 28.3464,
+      "step": 18
+    },
+    {
+      "epoch": 0.0009140465502259559,
+      "grad_norm": 34.893436431884766,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 28.3675,
+      "step": 19
+    },
+    {
+      "epoch": 0.000962154263395743,
+      "grad_norm": 25.342071533203125,
+      "learning_rate": 9.698463103929542e-05,
+      "loss": 25.7898,
+      "step": 20
+    },
+    {
+      "epoch": 0.0010102619765655302,
+      "grad_norm": 29.598787307739258,
+      "learning_rate": 9.635919272833938e-05,
+      "loss": 27.7703,
+      "step": 21
+    },
+    {
+      "epoch": 0.0010583696897353174,
+      "grad_norm": 27.906885147094727,
+      "learning_rate": 9.567727288213005e-05,
+      "loss": 23.4641,
+      "step": 22
+    },
+    {
+      "epoch": 0.0011064774029051045,
+      "grad_norm": 36.29619216918945,
+      "learning_rate": 9.493970231495835e-05,
+      "loss": 26.2492,
+      "step": 23
+    },
+    {
+      "epoch": 0.0011545851160748917,
+      "grad_norm": 37.084129333496094,
+      "learning_rate": 9.414737964294636e-05,
+      "loss": 24.152,
+      "step": 24
+    },
+    {
+      "epoch": 0.0012026928292446788,
+      "grad_norm": 27.066692352294922,
+      "learning_rate": 9.330127018922194e-05,
+      "loss": 20.1506,
+      "step": 25
+    },
+    {
+      "epoch": 0.0012026928292446788,
+      "eval_loss": 1.1929811239242554,
+      "eval_runtime": 960.029,
+      "eval_samples_per_second": 36.468,
+      "eval_steps_per_second": 18.234,
+      "step": 25
+    },
+    {
+      "epoch": 0.001250800542414466,
+      "grad_norm": 27.218626022338867,
+      "learning_rate": 9.24024048078213e-05,
+      "loss": 20.0776,
+      "step": 26
+    },
+    {
+      "epoch": 0.001298908255584253,
+      "grad_norm": 25.43698501586914,
+      "learning_rate": 9.145187862775209e-05,
+      "loss": 18.0897,
+      "step": 27
+    },
+    {
+      "epoch": 0.0013470159687540403,
+      "grad_norm": 26.085866928100586,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 17.6861,
+      "step": 28
+    },
+    {
+      "epoch": 0.0013951236819238274,
+      "grad_norm": 28.28208351135254,
+      "learning_rate": 8.940053768033609e-05,
+      "loss": 17.7331,
+      "step": 29
+    },
+    {
+      "epoch": 0.0014432313950936146,
+      "grad_norm": 20.444143295288086,
+      "learning_rate": 8.83022221559489e-05,
+      "loss": 15.5734,
+      "step": 30
+    },
+    {
+      "epoch": 0.0014913391082634017,
+      "grad_norm": 23.68974494934082,
+      "learning_rate": 8.715724127386972e-05,
+      "loss": 15.233,
+      "step": 31
+    },
+    {
+      "epoch": 0.001539446821433189,
+      "grad_norm": 27.690643310546875,
+      "learning_rate": 8.596699001693255e-05,
+      "loss": 14.4445,
+      "step": 32
+    },
+    {
+      "epoch": 0.001587554534602976,
+      "grad_norm": 24.823087692260742,
+      "learning_rate": 8.473291852294987e-05,
+      "loss": 13.5306,
+      "step": 33
+    },
+    {
+      "epoch": 0.0016356622477727632,
+      "grad_norm": 20.906787872314453,
+      "learning_rate": 8.345653031794292e-05,
+      "loss": 12.5153,
+      "step": 34
+    },
+    {
+      "epoch": 0.0016837699609425505,
+      "grad_norm": 23.420969009399414,
+      "learning_rate": 8.213938048432697e-05,
+      "loss": 13.0124,
+      "step": 35
+    },
+    {
+      "epoch": 0.0017318776741123375,
+      "grad_norm": 18.17311668395996,
+      "learning_rate": 8.07830737662829e-05,
+      "loss": 13.3438,
+      "step": 36
+    },
+    {
+      "epoch": 0.0017799853872821248,
+      "grad_norm": 22.257150650024414,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 13.308,
+      "step": 37
+    },
+    {
+      "epoch": 0.0018280931004519118,
+      "grad_norm": 29.457996368408203,
+      "learning_rate": 7.795964517353735e-05,
+      "loss": 13.6901,
+      "step": 38
+    },
+    {
+      "epoch": 0.001876200813621699,
+      "grad_norm": 21.267175674438477,
+      "learning_rate": 7.649596321166024e-05,
+      "loss": 13.0333,
+      "step": 39
+    },
+    {
+      "epoch": 0.001924308526791486,
+      "grad_norm": 21.757160186767578,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 12.0777,
+      "step": 40
+    },
+    {
+      "epoch": 0.0019724162399612733,
+      "grad_norm": 14.248445510864258,
+      "learning_rate": 7.347357813929454e-05,
+      "loss": 10.7264,
+      "step": 41
+    },
+    {
+      "epoch": 0.0020205239531310604,
+      "grad_norm": 18.01346206665039,
+      "learning_rate": 7.191855733945387e-05,
+      "loss": 11.4455,
+      "step": 42
+    },
+    {
+      "epoch": 0.0020686316663008474,
+      "grad_norm": 16.95344352722168,
+      "learning_rate": 7.033683215379002e-05,
+      "loss": 10.1439,
+      "step": 43
+    },
+    {
+      "epoch": 0.002116739379470635,
+      "grad_norm": 19.399534225463867,
+      "learning_rate": 6.873032967079561e-05,
+      "loss": 10.2624,
+      "step": 44
+    },
+    {
+      "epoch": 0.002164847092640422,
+      "grad_norm": 14.035258293151855,
+      "learning_rate": 6.710100716628344e-05,
+      "loss": 10.0812,
+      "step": 45
+    },
+    {
+      "epoch": 0.002212954805810209,
+      "grad_norm": 21.936786651611328,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 10.9526,
+      "step": 46
+    },
+    {
+      "epoch": 0.002261062518979996,
+      "grad_norm": 37.380340576171875,
+      "learning_rate": 6.378186779084995e-05,
+      "loss": 11.2345,
+      "step": 47
+    },
+    {
+      "epoch": 0.0023091702321497835,
+      "grad_norm": 17.827646255493164,
+      "learning_rate": 6.209609477998338e-05,
+      "loss": 9.6337,
+      "step": 48
+    },
+    {
+      "epoch": 0.0023572779453195705,
+      "grad_norm": 18.466480255126953,
+      "learning_rate": 6.0395584540887963e-05,
+      "loss": 8.5151,
+      "step": 49
+    },
+    {
+      "epoch": 0.0024053856584893576,
+      "grad_norm": 26.748825073242188,
+      "learning_rate": 5.868240888334653e-05,
+      "loss": 9.8757,
+      "step": 50
+    },
+    {
+      "epoch": 0.0024053856584893576,
+      "eval_loss": 0.5901936292648315,
+      "eval_runtime": 749.3104,
+      "eval_samples_per_second": 46.723,
+      "eval_steps_per_second": 23.361,
+      "step": 50
+    },
+    {
+      "epoch": 0.002453493371659145,
+      "grad_norm": 17.362829208374023,
+      "learning_rate": 5.695865504800327e-05,
+      "loss": 9.4627,
+      "step": 51
+    },
+    {
+      "epoch": 0.002501601084828932,
+      "grad_norm": 15.710803031921387,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 7.1618,
+      "step": 52
+    },
+    {
+      "epoch": 0.002549708797998719,
+      "grad_norm": 24.15390968322754,
+      "learning_rate": 5.348782368720626e-05,
+      "loss": 9.0488,
+      "step": 53
+    },
+    {
+      "epoch": 0.002597816511168506,
+      "grad_norm": 16.362722396850586,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 8.9919,
+      "step": 54
+    },
+    {
+      "epoch": 0.0026459242243382936,
+      "grad_norm": 19.021665573120117,
+      "learning_rate": 5e-05,
+      "loss": 9.1912,
+      "step": 55
+    },
+    {
+      "epoch": 0.0026940319375080807,
+      "grad_norm": 17.228673934936523,
+      "learning_rate": 4.825502516487497e-05,
+      "loss": 8.5915,
+      "step": 56
+    },
+    {
+      "epoch": 0.0027421396506778677,
+      "grad_norm": 16.646337509155273,
+      "learning_rate": 4.6512176312793736e-05,
+      "loss": 8.0812,
+      "step": 57
+    },
+    {
+      "epoch": 0.0027902473638476547,
+      "grad_norm": 21.439090728759766,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 9.7901,
+      "step": 58
+    },
+    {
+      "epoch": 0.002838355077017442,
+      "grad_norm": 14.49473762512207,
+      "learning_rate": 4.3041344951996746e-05,
+      "loss": 7.1048,
+      "step": 59
+    },
+    {
+      "epoch": 0.0028864627901872292,
+      "grad_norm": 21.155902862548828,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 10.7377,
+      "step": 60
+    },
+    {
+      "epoch": 0.0029345705033570163,
+      "grad_norm": 25.964038848876953,
+      "learning_rate": 3.960441545911204e-05,
+      "loss": 10.4005,
+      "step": 61
+    },
+    {
+      "epoch": 0.0029826782165268033,
+      "grad_norm": 17.16797637939453,
+      "learning_rate": 3.790390522001662e-05,
+      "loss": 7.4939,
+      "step": 62
+    },
+    {
+      "epoch": 0.003030785929696591,
+      "grad_norm": 18.470211029052734,
+      "learning_rate": 3.6218132209150045e-05,
+      "loss": 7.8696,
+      "step": 63
+    },
+    {
+      "epoch": 0.003078893642866378,
+      "grad_norm": 22.93252182006836,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 8.0851,
+      "step": 64
+    },
+    {
+      "epoch": 0.003127001356036165,
+      "grad_norm": 17.68440818786621,
+      "learning_rate": 3.289899283371657e-05,
+      "loss": 7.3134,
+      "step": 65
+    },
+    {
+      "epoch": 0.003175109069205952,
+      "grad_norm": 21.785123825073242,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 8.7969,
+      "step": 66
+    },
+    {
+      "epoch": 0.0032232167823757394,
+      "grad_norm": 15.482522010803223,
+      "learning_rate": 2.9663167846209998e-05,
+      "loss": 6.0866,
+      "step": 67
+    },
+    {
+      "epoch": 0.0032713244955455264,
+      "grad_norm": 16.00934600830078,
+      "learning_rate": 2.8081442660546125e-05,
+      "loss": 7.6092,
+      "step": 68
+    },
+    {
+      "epoch": 0.0033194322087153135,
+      "grad_norm": 19.86813735961914,
+      "learning_rate": 2.6526421860705473e-05,
+      "loss": 7.5374,
+      "step": 69
+    },
+    {
+      "epoch": 0.003367539921885101,
+      "grad_norm": 19.0589542388916,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 7.9793,
+      "step": 70
+    },
+    {
+      "epoch": 0.003415647635054888,
+      "grad_norm": 16.755290985107422,
+      "learning_rate": 2.350403678833976e-05,
+      "loss": 6.9908,
+      "step": 71
+    },
+    {
+      "epoch": 0.003463755348224675,
+      "grad_norm": 33.61604309082031,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 6.9951,
+      "step": 72
+    },
+    {
+      "epoch": 0.003511863061394462,
+      "grad_norm": 16.12103271484375,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 7.0701,
+      "step": 73
+    },
+    {
+      "epoch": 0.0035599707745642495,
+      "grad_norm": 15.112361907958984,
+      "learning_rate": 1.9216926233717085e-05,
+      "loss": 7.0203,
+      "step": 74
+    },
+    {
+      "epoch": 0.0036080784877340366,
+      "grad_norm": 27.100276947021484,
+      "learning_rate": 1.7860619515673033e-05,
+      "loss": 7.3535,
+      "step": 75
+    },
+    {
+      "epoch": 0.0036080784877340366,
+      "eval_loss": 0.4549826979637146,
+      "eval_runtime": 1059.2638,
+      "eval_samples_per_second": 33.051,
+      "eval_steps_per_second": 16.526,
+      "step": 75
+    },
+    {
+      "epoch": 0.0036561862009038236,
+      "grad_norm": 17.09381675720215,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 7.9682,
+      "step": 76
+    },
+    {
+      "epoch": 0.0037042939140736106,
+      "grad_norm": 41.06929397583008,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 6.666,
+      "step": 77
+    },
+    {
+      "epoch": 0.003752401627243398,
+      "grad_norm": 18.997638702392578,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 8.8896,
+      "step": 78
+    },
+    {
+      "epoch": 0.003800509340413185,
+      "grad_norm": 17.806833267211914,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 5.5866,
+      "step": 79
+    },
+    {
+      "epoch": 0.003848617053582972,
+      "grad_norm": 16.152570724487305,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 6.114,
+      "step": 80
+    },
+    {
+      "epoch": 0.0038967247667527592,
+      "grad_norm": 20.27669334411621,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 8.8004,
+      "step": 81
+    },
+    {
+      "epoch": 0.003944832479922547,
+      "grad_norm": 23.097076416015625,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 7.4391,
+      "step": 82
+    },
+    {
+      "epoch": 0.003992940193092334,
+      "grad_norm": 31.06700897216797,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 9.0983,
+      "step": 83
+    },
+    {
+      "epoch": 0.004041047906262121,
+      "grad_norm": 22.504980087280273,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 8.9527,
+      "step": 84
+    },
+    {
+      "epoch": 0.004089155619431908,
+      "grad_norm": 19.458494186401367,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 6.1833,
+      "step": 85
+    },
+    {
+      "epoch": 0.004137263332601695,
+      "grad_norm": 17.132970809936523,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 6.1848,
+      "step": 86
+    },
+    {
+      "epoch": 0.004185371045771482,
+      "grad_norm": 19.203487396240234,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 7.0421,
+      "step": 87
+    },
+    {
+      "epoch": 0.00423347875894127,
+      "grad_norm": 19.03404426574707,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 7.3711,
+      "step": 88
+    },
+    {
+      "epoch": 0.004281586472111056,
+      "grad_norm": 17.356229782104492,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 7.0651,
+      "step": 89
+    },
+    {
+      "epoch": 0.004329694185280844,
+      "grad_norm": 17.76946258544922,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 6.8242,
+      "step": 90
+    },
+    {
+      "epoch": 0.004377801898450631,
+      "grad_norm": 22.919456481933594,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 6.8237,
+      "step": 91
+    },
+    {
+      "epoch": 0.004425909611620418,
+      "grad_norm": 18.166902542114258,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 6.936,
+      "step": 92
+    },
+    {
+      "epoch": 0.004474017324790205,
+      "grad_norm": 17.692848205566406,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 7.2349,
+      "step": 93
+    },
+    {
+      "epoch": 0.004522125037959992,
+      "grad_norm": 18.518360137939453,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 6.0009,
+      "step": 94
+    },
+    {
+      "epoch": 0.0045702327511297795,
+      "grad_norm": 18.700481414794922,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 8.2517,
+      "step": 95
+    },
+    {
+      "epoch": 0.004618340464299567,
+      "grad_norm": 16.704484939575195,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 6.4917,
+      "step": 96
+    },
+    {
+      "epoch": 0.004666448177469354,
+      "grad_norm": 21.030405044555664,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 6.2497,
+      "step": 97
+    },
+    {
+      "epoch": 0.004714555890639141,
+      "grad_norm": 20.96607780456543,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 6.0075,
+      "step": 98
+    },
+    {
+      "epoch": 0.0047626636038089285,
+      "grad_norm": 22.39644432067871,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 6.1534,
+      "step": 99
+    },
+    {
+      "epoch": 0.004810771316978715,
+      "grad_norm": 18.28731918334961,
+      "learning_rate": 0.0,
+      "loss": 7.457,
+      "step": 100
+    },
+    {
+      "epoch": 0.004810771316978715,
+      "eval_loss": 0.43572717905044556,
+      "eval_runtime": 827.9428,
+      "eval_samples_per_second": 42.286,
+      "eval_steps_per_second": 21.143,
+      "step": 100
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 100,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 25,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 6.51499696816128e+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:c2f68998c0d8cd582b5bbcb8b2667b1c6e1cd4c77646b021444750b0fb07898c
+size 6776

special_tokens_map.json

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

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45ccb9c8b6b561889acea59191d66986d314e7cbd6a78abc6e49b139ca91c1e6
+size 500058

tokenizer_config.json

@@ -0,0 +1,42 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2f68998c0d8cd582b5bbcb8b2667b1c6e1cd4c77646b021444750b0fb07898c
+size 6776