End of training

README.md

@@ -0,0 +1,168 @@
+---
+library_name: peft
+license: apache-2.0
+base_model: echarlaix/tiny-random-mistral
+tags:
+- axolotl
+- generated_from_trainer
+model-index:
+- name: 818864ef-8094-4357-9a8e-fe11c35169de
+  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: echarlaix/tiny-random-mistral
+bf16: auto
+chat_template: llama3
+dataset_prepared_path: null
+datasets:
+- data_files:
+  - 7e930cf543f535d6_train_data.json
+  ds_type: json
+  format: custom
+  path: /workspace/input_data/7e930cf543f535d6_train_data.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: 100
+micro_batch_size: 2
+mlflow_experiment_name: /tmp/7e930cf543f535d6_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: 818864ef-8094-4357-9a8e-fe11c35169de
+wandb_project: Gradients-On-Demand
+wandb_run: your_name
+wandb_runid: 818864ef-8094-4357-9a8e-fe11c35169de
+warmup_steps: 10
+weight_decay: 0.0
+xformers_attention: null
+
+```
+
+</details><br>
+
+# 818864ef-8094-4357-9a8e-fe11c35169de
+
+This model is a fine-tuned version of [echarlaix/tiny-random-mistral](https://huggingface.co/echarlaix/tiny-random-mistral) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: nan
+
+## 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: 93
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 11974.167     | 0.0108 | 1    | nan             |
+| 0.0           | 0.2598 | 24   | nan             |
+| 0.0           | 0.5196 | 48   | nan             |
+| 0.0           | 0.7794 | 72   | nan             |
+
+
+### 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": "echarlaix/tiny-random-mistral",
+  "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": [
+    "down_proj",
+    "o_proj",
+    "gate_proj",
+    "v_proj",
+    "up_proj",
+    "q_proj",
+    "k_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25ba1705ceacb905125d051c93c499f170f2d6efbb8755f63288d05cfb41fa3f
+size 37506

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6a6dbfd0b99b517ae2cd69391b268041323be1f99c8ecc52acf9ecd0ff00e29
+size 31064

config.json

@@ -0,0 +1,33 @@
+{
+  "_attn_implementation_autoset": true,
+  "_name_or_path": "echarlaix/tiny-random-mistral",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 8,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 32,
+  "initializer_range": 0.02,
+  "intermediate_size": 37,
+  "is_decoder": true,
+  "max_position_embeddings": 512,
+  "model_type": "mistral",
+  "num_attention_heads": 4,
+  "num_hidden_layers": 2,
+  "num_key_value_heads": 2,
+  "pad_token_id": 0,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 10000.0,
+  "sliding_window": 4096,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.46.0",
+  "type_vocab_size": 16,
+  "use_cache": false,
+  "vocab_size": 32000
+}

last-checkpoint/README.md

@@ -0,0 +1,202 @@
+---
+base_model: echarlaix/tiny-random-mistral
+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": "echarlaix/tiny-random-mistral",
+  "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": [
+    "down_proj",
+    "o_proj",
+    "gate_proj",
+    "v_proj",
+    "up_proj",
+    "q_proj",
+    "k_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

last-checkpoint/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6a6dbfd0b99b517ae2cd69391b268041323be1f99c8ecc52acf9ecd0ff00e29
+size 31064

last-checkpoint/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:025cb83ae7004cde045c6592ec39ee56d5f5c559b2e01ab2378c4372e4d107ca
+size 71654

last-checkpoint/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d55ef7e39ffed254f36f6faafb6597d5bd8ba2346f104d20c3b8cca9fcde4d05
+size 14244

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6fd302dab6dad7411e029f26a1eed4b8af7dfa13be419c5f8a4344ac60a0c3b
+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:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

last-checkpoint/tokenizer_config.json

@@ -0,0 +1,44 @@
+{
+  "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
+    }
+  },
+  "additional_special_tokens": [],
+  "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": 512,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}

last-checkpoint/trainer_state.json

@@ -0,0 +1,716 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.006765899864682,
+  "eval_steps": 24,
+  "global_step": 93,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.010825439783491205,
+      "grad_norm": NaN,
+      "learning_rate": 1e-05,
+      "loss": 11974.167,
+      "step": 1
+    },
+    {
+      "epoch": 0.010825439783491205,
+      "eval_loss": NaN,
+      "eval_runtime": 14.1198,
+      "eval_samples_per_second": 11.048,
+      "eval_steps_per_second": 5.524,
+      "step": 1
+    },
+    {
+      "epoch": 0.02165087956698241,
+      "grad_norm": NaN,
+      "learning_rate": 2e-05,
+      "loss": 0.0,
+      "step": 2
+    },
+    {
+      "epoch": 0.03247631935047361,
+      "grad_norm": NaN,
+      "learning_rate": 3e-05,
+      "loss": 0.0,
+      "step": 3
+    },
+    {
+      "epoch": 0.04330175913396482,
+      "grad_norm": NaN,
+      "learning_rate": 4e-05,
+      "loss": 0.0,
+      "step": 4
+    },
+    {
+      "epoch": 0.05412719891745602,
+      "grad_norm": NaN,
+      "learning_rate": 5e-05,
+      "loss": 0.0,
+      "step": 5
+    },
+    {
+      "epoch": 0.06495263870094722,
+      "grad_norm": NaN,
+      "learning_rate": 6e-05,
+      "loss": 0.0,
+      "step": 6
+    },
+    {
+      "epoch": 0.07577807848443843,
+      "grad_norm": NaN,
+      "learning_rate": 7e-05,
+      "loss": 0.0,
+      "step": 7
+    },
+    {
+      "epoch": 0.08660351826792964,
+      "grad_norm": NaN,
+      "learning_rate": 8e-05,
+      "loss": 0.0,
+      "step": 8
+    },
+    {
+      "epoch": 0.09742895805142084,
+      "grad_norm": NaN,
+      "learning_rate": 9e-05,
+      "loss": 0.0,
+      "step": 9
+    },
+    {
+      "epoch": 0.10825439783491204,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001,
+      "loss": 0.0,
+      "step": 10
+    },
+    {
+      "epoch": 0.11907983761840325,
+      "grad_norm": NaN,
+      "learning_rate": 9.996418774081658e-05,
+      "loss": 0.0,
+      "step": 11
+    },
+    {
+      "epoch": 0.12990527740189445,
+      "grad_norm": NaN,
+      "learning_rate": 9.985680226398261e-05,
+      "loss": 0.0,
+      "step": 12
+    },
+    {
+      "epoch": 0.14073071718538566,
+      "grad_norm": NaN,
+      "learning_rate": 9.967799739815925e-05,
+      "loss": 0.0,
+      "step": 13
+    },
+    {
+      "epoch": 0.15155615696887687,
+      "grad_norm": NaN,
+      "learning_rate": 9.942802927959443e-05,
+      "loss": 0.0,
+      "step": 14
+    },
+    {
+      "epoch": 0.16238159675236807,
+      "grad_norm": NaN,
+      "learning_rate": 9.910725598521013e-05,
+      "loss": 0.0,
+      "step": 15
+    },
+    {
+      "epoch": 0.17320703653585928,
+      "grad_norm": NaN,
+      "learning_rate": 9.871613701966067e-05,
+      "loss": 0.0,
+      "step": 16
+    },
+    {
+      "epoch": 0.18403247631935046,
+      "grad_norm": NaN,
+      "learning_rate": 9.825523265709666e-05,
+      "loss": 0.0,
+      "step": 17
+    },
+    {
+      "epoch": 0.19485791610284167,
+      "grad_norm": NaN,
+      "learning_rate": 9.772520313857775e-05,
+      "loss": 0.0,
+      "step": 18
+    },
+    {
+      "epoch": 0.20568335588633288,
+      "grad_norm": NaN,
+      "learning_rate": 9.712680772628364e-05,
+      "loss": 0.0,
+      "step": 19
+    },
+    {
+      "epoch": 0.2165087956698241,
+      "grad_norm": NaN,
+      "learning_rate": 9.646090361587827e-05,
+      "loss": 0.0,
+      "step": 20
+    },
+    {
+      "epoch": 0.2273342354533153,
+      "grad_norm": NaN,
+      "learning_rate": 9.572844470858537e-05,
+      "loss": 0.0,
+      "step": 21
+    },
+    {
+      "epoch": 0.2381596752368065,
+      "grad_norm": NaN,
+      "learning_rate": 9.493048024473412e-05,
+      "loss": 0.0,
+      "step": 22
+    },
+    {
+      "epoch": 0.2489851150202977,
+      "grad_norm": NaN,
+      "learning_rate": 9.406815330073244e-05,
+      "loss": 0.0,
+      "step": 23
+    },
+    {
+      "epoch": 0.2598105548037889,
+      "grad_norm": NaN,
+      "learning_rate": 9.314269915162114e-05,
+      "loss": 0.0,
+      "step": 24
+    },
+    {
+      "epoch": 0.2598105548037889,
+      "eval_loss": NaN,
+      "eval_runtime": 0.679,
+      "eval_samples_per_second": 229.759,
+      "eval_steps_per_second": 114.879,
+      "step": 24
+    },
+    {
+      "epoch": 0.2706359945872801,
+      "grad_norm": NaN,
+      "learning_rate": 9.215544350155422e-05,
+      "loss": 0.0,
+      "step": 25
+    },
+    {
+      "epoch": 0.2814614343707713,
+      "grad_norm": NaN,
+      "learning_rate": 9.110780058474052e-05,
+      "loss": 0.0,
+      "step": 26
+    },
+    {
+      "epoch": 0.2922868741542625,
+      "grad_norm": NaN,
+      "learning_rate": 9.000127113956674e-05,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 0.30311231393775373,
+      "grad_norm": NaN,
+      "learning_rate": 8.883744025880428e-05,
+      "loss": 0.0,
+      "step": 28
+    },
+    {
+      "epoch": 0.31393775372124494,
+      "grad_norm": NaN,
+      "learning_rate": 8.761797511897906e-05,
+      "loss": 0.0,
+      "step": 29
+    },
+    {
+      "epoch": 0.32476319350473615,
+      "grad_norm": NaN,
+      "learning_rate": 8.634462259215719e-05,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.33558863328822736,
+      "grad_norm": NaN,
+      "learning_rate": 8.501920674356754e-05,
+      "loss": 0.0,
+      "step": 31
+    },
+    {
+      "epoch": 0.34641407307171856,
+      "grad_norm": NaN,
+      "learning_rate": 8.364362621864595e-05,
+      "loss": 0.0,
+      "step": 32
+    },
+    {
+      "epoch": 0.3572395128552097,
+      "grad_norm": NaN,
+      "learning_rate": 8.221985152324385e-05,
+      "loss": 0.0,
+      "step": 33
+    },
+    {
+      "epoch": 0.3680649526387009,
+      "grad_norm": NaN,
+      "learning_rate": 8.074992220089769e-05,
+      "loss": 0.0,
+      "step": 34
+    },
+    {
+      "epoch": 0.37889039242219213,
+      "grad_norm": NaN,
+      "learning_rate": 7.923594391120236e-05,
+      "loss": 0.0,
+      "step": 35
+    },
+    {
+      "epoch": 0.38971583220568334,
+      "grad_norm": NaN,
+      "learning_rate": 7.768008541347423e-05,
+      "loss": 0.0,
+      "step": 36
+    },
+    {
+      "epoch": 0.40054127198917455,
+      "grad_norm": NaN,
+      "learning_rate": 7.608457546002424e-05,
+      "loss": 0.0,
+      "step": 37
+    },
+    {
+      "epoch": 0.41136671177266576,
+      "grad_norm": NaN,
+      "learning_rate": 7.445169960349167e-05,
+      "loss": 0.0,
+      "step": 38
+    },
+    {
+      "epoch": 0.42219215155615697,
+      "grad_norm": NaN,
+      "learning_rate": 7.278379692281208e-05,
+      "loss": 0.0,
+      "step": 39
+    },
+    {
+      "epoch": 0.4330175913396482,
+      "grad_norm": NaN,
+      "learning_rate": 7.10832566725092e-05,
+      "loss": 0.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.4438430311231394,
+      "grad_norm": NaN,
+      "learning_rate": 6.935251486011087e-05,
+      "loss": 0.0,
+      "step": 41
+    },
+    {
+      "epoch": 0.4546684709066306,
+      "grad_norm": NaN,
+      "learning_rate": 6.759405075659166e-05,
+      "loss": 0.0,
+      "step": 42
+    },
+    {
+      "epoch": 0.4654939106901218,
+      "grad_norm": NaN,
+      "learning_rate": 6.58103833448412e-05,
+      "loss": 0.0,
+      "step": 43
+    },
+    {
+      "epoch": 0.476319350473613,
+      "grad_norm": NaN,
+      "learning_rate": 6.400406771124536e-05,
+      "loss": 0.0,
+      "step": 44
+    },
+    {
+      "epoch": 0.4871447902571042,
+      "grad_norm": NaN,
+      "learning_rate": 6.21776913855496e-05,
+      "loss": 0.0,
+      "step": 45
+    },
+    {
+      "epoch": 0.4979702300405954,
+      "grad_norm": NaN,
+      "learning_rate": 6.0333870634247645e-05,
+      "loss": 0.0,
+      "step": 46
+    },
+    {
+      "epoch": 0.5087956698240866,
+      "grad_norm": NaN,
+      "learning_rate": 5.847524671280484e-05,
+      "loss": 0.0,
+      "step": 47
+    },
+    {
+      "epoch": 0.5196211096075778,
+      "grad_norm": NaN,
+      "learning_rate": 5.660448208208513e-05,
+      "loss": 0.0,
+      "step": 48
+    },
+    {
+      "epoch": 0.5196211096075778,
+      "eval_loss": NaN,
+      "eval_runtime": 0.7027,
+      "eval_samples_per_second": 222.007,
+      "eval_steps_per_second": 111.003,
+      "step": 48
+    },
+    {
+      "epoch": 0.530446549391069,
+      "grad_norm": NaN,
+      "learning_rate": 5.472425659440157e-05,
+      "loss": 0.0,
+      "step": 49
+    },
+    {
+      "epoch": 0.5412719891745602,
+      "grad_norm": NaN,
+      "learning_rate": 5.2837263654653715e-05,
+      "loss": 0.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.5520974289580515,
+      "grad_norm": NaN,
+      "learning_rate": 5.094620636205095e-05,
+      "loss": 0.0,
+      "step": 51
+    },
+    {
+      "epoch": 0.5629228687415426,
+      "grad_norm": NaN,
+      "learning_rate": 4.9053793637949067e-05,
+      "loss": 0.0,
+      "step": 52
+    },
+    {
+      "epoch": 0.5737483085250338,
+      "grad_norm": NaN,
+      "learning_rate": 4.7162736345346303e-05,
+      "loss": 0.0,
+      "step": 53
+    },
+    {
+      "epoch": 0.584573748308525,
+      "grad_norm": NaN,
+      "learning_rate": 4.527574340559844e-05,
+      "loss": 0.0,
+      "step": 54
+    },
+    {
+      "epoch": 0.5953991880920162,
+      "grad_norm": NaN,
+      "learning_rate": 4.3395517917914895e-05,
+      "loss": 0.0,
+      "step": 55
+    },
+    {
+      "epoch": 0.6062246278755075,
+      "grad_norm": NaN,
+      "learning_rate": 4.1524753287195165e-05,
+      "loss": 0.0,
+      "step": 56
+    },
+    {
+      "epoch": 0.6170500676589986,
+      "grad_norm": NaN,
+      "learning_rate": 3.966612936575235e-05,
+      "loss": 0.0,
+      "step": 57
+    },
+    {
+      "epoch": 0.6278755074424899,
+      "grad_norm": NaN,
+      "learning_rate": 3.7822308614450406e-05,
+      "loss": 0.0,
+      "step": 58
+    },
+    {
+      "epoch": 0.638700947225981,
+      "grad_norm": NaN,
+      "learning_rate": 3.599593228875465e-05,
+      "loss": 0.0,
+      "step": 59
+    },
+    {
+      "epoch": 0.6495263870094723,
+      "grad_norm": NaN,
+      "learning_rate": 3.41896166551588e-05,
+      "loss": 0.0,
+      "step": 60
+    },
+    {
+      "epoch": 0.6603518267929634,
+      "grad_norm": NaN,
+      "learning_rate": 3.240594924340835e-05,
+      "loss": 0.0,
+      "step": 61
+    },
+    {
+      "epoch": 0.6711772665764547,
+      "grad_norm": NaN,
+      "learning_rate": 3.0647485139889145e-05,
+      "loss": 0.0,
+      "step": 62
+    },
+    {
+      "epoch": 0.6820027063599459,
+      "grad_norm": NaN,
+      "learning_rate": 2.8916743327490803e-05,
+      "loss": 0.0,
+      "step": 63
+    },
+    {
+      "epoch": 0.6928281461434371,
+      "grad_norm": NaN,
+      "learning_rate": 2.721620307718793e-05,
+      "loss": 0.0,
+      "step": 64
+    },
+    {
+      "epoch": 0.7036535859269283,
+      "grad_norm": NaN,
+      "learning_rate": 2.554830039650834e-05,
+      "loss": 0.0,
+      "step": 65
+    },
+    {
+      "epoch": 0.7144790257104194,
+      "grad_norm": NaN,
+      "learning_rate": 2.391542453997578e-05,
+      "loss": 0.0,
+      "step": 66
+    },
+    {
+      "epoch": 0.7253044654939107,
+      "grad_norm": NaN,
+      "learning_rate": 2.2319914586525777e-05,
+      "loss": 0.0,
+      "step": 67
+    },
+    {
+      "epoch": 0.7361299052774019,
+      "grad_norm": NaN,
+      "learning_rate": 2.0764056088797645e-05,
+      "loss": 0.0,
+      "step": 68
+    },
+    {
+      "epoch": 0.7469553450608931,
+      "grad_norm": NaN,
+      "learning_rate": 1.9250077799102322e-05,
+      "loss": 0.0,
+      "step": 69
+    },
+    {
+      "epoch": 0.7577807848443843,
+      "grad_norm": NaN,
+      "learning_rate": 1.7780148476756147e-05,
+      "loss": 0.0,
+      "step": 70
+    },
+    {
+      "epoch": 0.7686062246278755,
+      "grad_norm": NaN,
+      "learning_rate": 1.6356373781354058e-05,
+      "loss": 0.0,
+      "step": 71
+    },
+    {
+      "epoch": 0.7794316644113667,
+      "grad_norm": NaN,
+      "learning_rate": 1.4980793256432474e-05,
+      "loss": 0.0,
+      "step": 72
+    },
+    {
+      "epoch": 0.7794316644113667,
+      "eval_loss": NaN,
+      "eval_runtime": 0.6819,
+      "eval_samples_per_second": 228.779,
+      "eval_steps_per_second": 114.39,
+      "step": 72
+    },
+    {
+      "epoch": 0.790257104194858,
+      "grad_norm": NaN,
+      "learning_rate": 1.3655377407842812e-05,
+      "loss": 0.0,
+      "step": 73
+    },
+    {
+      "epoch": 0.8010825439783491,
+      "grad_norm": NaN,
+      "learning_rate": 1.2382024881020937e-05,
+      "loss": 0.0,
+      "step": 74
+    },
+    {
+      "epoch": 0.8119079837618404,
+      "grad_norm": NaN,
+      "learning_rate": 1.1162559741195733e-05,
+      "loss": 0.0,
+      "step": 75
+    },
+    {
+      "epoch": 0.8227334235453315,
+      "grad_norm": NaN,
+      "learning_rate": 9.998728860433276e-06,
+      "loss": 0.0,
+      "step": 76
+    },
+    {
+      "epoch": 0.8335588633288228,
+      "grad_norm": NaN,
+      "learning_rate": 8.8921994152595e-06,
+      "loss": 0.0,
+      "step": 77
+    },
+    {
+      "epoch": 0.8443843031123139,
+      "grad_norm": NaN,
+      "learning_rate": 7.844556498445788e-06,
+      "loss": 0.0,
+      "step": 78
+    },
+    {
+      "epoch": 0.8552097428958051,
+      "grad_norm": NaN,
+      "learning_rate": 6.857300848378856e-06,
+      "loss": 0.0,
+      "step": 79
+    },
+    {
+      "epoch": 0.8660351826792964,
+      "grad_norm": NaN,
+      "learning_rate": 5.931846699267557e-06,
+      "loss": 0.0,
+      "step": 80
+    },
+    {
+      "epoch": 0.8768606224627875,
+      "grad_norm": NaN,
+      "learning_rate": 5.0695197552659e-06,
+      "loss": 0.0,
+      "step": 81
+    },
+    {
+      "epoch": 0.8876860622462788,
+      "grad_norm": NaN,
+      "learning_rate": 4.271555291414636e-06,
+      "loss": 0.0,
+      "step": 82
+    },
+    {
+      "epoch": 0.8985115020297699,
+      "grad_norm": NaN,
+      "learning_rate": 3.539096384121743e-06,
+      "loss": 0.0,
+      "step": 83
+    },
+    {
+      "epoch": 0.9093369418132612,
+      "grad_norm": NaN,
+      "learning_rate": 2.8731922737163685e-06,
+      "loss": 0.0,
+      "step": 84
+    },
+    {
+      "epoch": 0.9201623815967523,
+      "grad_norm": NaN,
+      "learning_rate": 2.274796861422246e-06,
+      "loss": 0.0,
+      "step": 85
+    },
+    {
+      "epoch": 0.9309878213802436,
+      "grad_norm": NaN,
+      "learning_rate": 1.7447673429033362e-06,
+      "loss": 0.0,
+      "step": 86
+    },
+    {
+      "epoch": 0.9418132611637348,
+      "grad_norm": NaN,
+      "learning_rate": 1.2838629803393342e-06,
+      "loss": 0.0,
+      "step": 87
+    },
+    {
+      "epoch": 0.952638700947226,
+      "grad_norm": NaN,
+      "learning_rate": 8.927440147898702e-07,
+      "loss": 0.0,
+      "step": 88
+    },
+    {
+      "epoch": 0.9634641407307172,
+      "grad_norm": NaN,
+      "learning_rate": 5.719707204055735e-07,
+      "loss": 0.0,
+      "step": 89
+    },
+    {
+      "epoch": 0.9742895805142084,
+      "grad_norm": NaN,
+      "learning_rate": 3.2200260184075406e-07,
+      "loss": 0.0,
+      "step": 90
+    },
+    {
+      "epoch": 0.9851150202976996,
+      "grad_norm": NaN,
+      "learning_rate": 1.431977360173975e-07,
+      "loss": 0.0,
+      "step": 91
+    },
+    {
+      "epoch": 0.9959404600811907,
+      "grad_norm": NaN,
+      "learning_rate": 3.581225918342646e-08,
+      "loss": 0.0,
+      "step": 92
+    },
+    {
+      "epoch": 1.006765899864682,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 0.0,
+      "step": 93
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 93,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 24,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 13425906401280.0,
+  "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 sha256:8ccfffad861961f21fb18ee924e1ee63a7d7fa9645e4d98d4830155136777638
+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:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

tokenizer_config.json

@@ -0,0 +1,44 @@
+{
+  "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
+    }
+  },
+  "additional_special_tokens": [],
+  "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": 512,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ccfffad861961f21fb18ee924e1ee63a7d7fa9645e4d98d4830155136777638
+size 6776