End of training

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,163 @@
+---
+library_name: peft
+license: mit
+base_model: fxmarty/tiny-dummy-qwen2
+tags:
+- axolotl
+- generated_from_trainer
+model-index:
+- name: f0260cb8-a421-4aa0-b9a6-4983766fe03f
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+[<img src="https://raw.githubusercontent.com/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl)
+<details><summary>See axolotl config</summary>
+
+axolotl version: `0.4.1`
+```yaml
+adapter: lora
+base_model: fxmarty/tiny-dummy-qwen2
+bf16: true
+chat_template: llama3
+data_processes: 16
+dataset_prepared_path: null
+datasets:
+- data_files:
+  - 0dede6371eb018a8_train_data.json
+  ds_type: json
+  format: custom
+  path: /workspace/input_data/0dede6371eb018a8_train_data.json
+  type:
+    field_instruction: label_name
+    field_output: text
+    format: '{instruction}'
+    no_input_format: '{instruction}'
+    system_format: '{system}'
+    system_prompt: ''
+debug: null
+deepspeed: null
+device_map: auto
+do_eval: true
+early_stopping_patience: 5
+eval_batch_size: 8
+eval_max_new_tokens: 128
+eval_steps: 25
+eval_table_size: null
+evals_per_epoch: null
+flash_attention: true
+fp16: false
+fsdp: null
+fsdp_config: null
+gradient_accumulation_steps: 4
+gradient_checkpointing: true
+group_by_length: true
+hub_model_id: null
+hub_repo: null
+hub_strategy: checkpoint
+hub_token: null
+learning_rate: 0.0001
+load_in_4bit: false
+load_in_8bit: false
+local_rank: null
+logging_steps: 1
+lora_alpha: 128
+lora_dropout: 0.05
+lora_fan_in_fan_out: null
+lora_model_dir: null
+lora_r: 64
+lora_target_linear: true
+lr_scheduler: cosine
+max_grad_norm: 1.0
+max_memory:
+  0: 75GB
+max_steps: 50
+micro_batch_size: 8
+mlflow_experiment_name: /tmp/0dede6371eb018a8_train_data.json
+model_type: AutoModelForCausalLM
+num_epochs: 1
+optim_args:
+  adam_beta1: 0.9
+  adam_beta2: 0.95
+  adam_epsilon: 1e-5
+optimizer: adamw_bnb_8bit
+output_dir: miner_id_24
+pad_to_sequence_len: true
+resume_from_checkpoint: null
+s2_attention: null
+sample_packing: false
+save_steps: 25
+saves_per_epoch: null
+sequence_len: 512
+strict: false
+tf32: true
+tokenizer_type: AutoTokenizer
+train_on_inputs: false
+trust_remote_code: true
+val_set_size: 0.05
+wandb_entity: null
+wandb_mode: online
+wandb_name: 04808d17-ba6e-4c71-9301-c50f7f6725a3
+wandb_project: Gradients-On-Demand
+wandb_run: your_name
+wandb_runid: 04808d17-ba6e-4c71-9301-c50f7f6725a3
+warmup_steps: 5
+weight_decay: 0.0
+xformers_attention: null
+
+```
+
+</details><br>
+
+# f0260cb8-a421-4aa0-b9a6-4983766fe03f
+
+This model is a fine-tuned version of [fxmarty/tiny-dummy-qwen2](https://huggingface.co/fxmarty/tiny-dummy-qwen2) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 11.9283
+
+## 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: 8
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 32
+- optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=adam_beta1=0.9,adam_beta2=0.95,adam_epsilon=1e-5
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 5
+- training_steps: 50
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 11.9297       | 0.0012 | 1    | 11.9331         |
+| 11.9292       | 0.0296 | 25   | 11.9303         |
+| 11.9258       | 0.0592 | 50   | 11.9283         |
+
+
+### 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": "fxmarty/tiny-dummy-qwen2",
+  "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": 128,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "k_proj",
+    "up_proj",
+    "o_proj",
+    "q_proj",
+    "v_proj",
+    "down_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 sha256:9ad7dd755115e5ffd9fa2ebc6e849f7339c3a5da55785b35741244985cd3b182
+size 100226

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe0950d78b6b65ae6acf32b2c6ba275dae979e57c907a8fc722d07f5cb21dc3a
+size 93608

added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644
+}

config.json

@@ -0,0 +1,29 @@
+{
+  "_attn_implementation_autoset": true,
+  "_name_or_path": "fxmarty/tiny-dummy-qwen2",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 8,
+  "initializer_range": 0.02,
+  "intermediate_size": 32,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 21,
+  "model_type": "qwen2",
+  "num_attention_heads": 4,
+  "num_hidden_layers": 2,
+  "num_key_value_heads": 2,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.46.0",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

last-checkpoint/README.md

@@ -0,0 +1,202 @@
+---
+base_model: fxmarty/tiny-dummy-qwen2
+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": "fxmarty/tiny-dummy-qwen2",
+  "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": 128,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "k_proj",
+    "up_proj",
+    "o_proj",
+    "q_proj",
+    "v_proj",
+    "down_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:fe0950d78b6b65ae6acf32b2c6ba275dae979e57c907a8fc722d07f5cb21dc3a
+size 93608

last-checkpoint/added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644
+}

last-checkpoint/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7af3f802ca709c054c835eb572b2ce7d410d5f3373d78a44d7171af185267b50
+size 197158

last-checkpoint/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2304f462d773142c08745241cad03aa79f80eef241d004cab762acb8dddb2d64
+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 +1,20 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

last-checkpoint/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bcfe42da0a4497e8b2b172c1f9f4ec423a46dc12907f4349c55025f670422ba9
+size 11418266

last-checkpoint/tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": null,
+  "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|>",
+  "errors": "replace",
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

last-checkpoint/trainer_state.json

@@ -0,0 +1,416 @@
+{
+  "best_metric": 11.928251266479492,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.059224163458691144,
+  "eval_steps": 25,
+  "global_step": 50,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0011844832691738228,
+      "grad_norm": 0.04947250336408615,
+      "learning_rate": 2e-05,
+      "loss": 11.9297,
+      "step": 1
+    },
+    {
+      "epoch": 0.0011844832691738228,
+      "eval_loss": 11.933135986328125,
+      "eval_runtime": 3.8968,
+      "eval_samples_per_second": 364.919,
+      "eval_steps_per_second": 45.679,
+      "step": 1
+    },
+    {
+      "epoch": 0.0023689665383476457,
+      "grad_norm": 0.027419790625572205,
+      "learning_rate": 4e-05,
+      "loss": 11.9325,
+      "step": 2
+    },
+    {
+      "epoch": 0.0035534498075214687,
+      "grad_norm": 0.02337762713432312,
+      "learning_rate": 6e-05,
+      "loss": 11.9355,
+      "step": 3
+    },
+    {
+      "epoch": 0.004737933076695291,
+      "grad_norm": 0.03190230950713158,
+      "learning_rate": 8e-05,
+      "loss": 11.9317,
+      "step": 4
+    },
+    {
+      "epoch": 0.005922416345869114,
+      "grad_norm": 0.03439483046531677,
+      "learning_rate": 0.0001,
+      "loss": 11.9334,
+      "step": 5
+    },
+    {
+      "epoch": 0.0071068996150429374,
+      "grad_norm": 0.027597956359386444,
+      "learning_rate": 9.987820251299122e-05,
+      "loss": 11.9309,
+      "step": 6
+    },
+    {
+      "epoch": 0.00829138288421676,
+      "grad_norm": 0.03297834470868111,
+      "learning_rate": 9.951340343707852e-05,
+      "loss": 11.932,
+      "step": 7
+    },
+    {
+      "epoch": 0.009475866153390583,
+      "grad_norm": 0.0381988063454628,
+      "learning_rate": 9.890738003669029e-05,
+      "loss": 11.9351,
+      "step": 8
+    },
+    {
+      "epoch": 0.010660349422564407,
+      "grad_norm": 0.039473991841077805,
+      "learning_rate": 9.806308479691595e-05,
+      "loss": 11.9316,
+      "step": 9
+    },
+    {
+      "epoch": 0.011844832691738229,
+      "grad_norm": 0.029513362795114517,
+      "learning_rate": 9.698463103929542e-05,
+      "loss": 11.9322,
+      "step": 10
+    },
+    {
+      "epoch": 0.013029315960912053,
+      "grad_norm": 0.030284477397799492,
+      "learning_rate": 9.567727288213005e-05,
+      "loss": 11.9342,
+      "step": 11
+    },
+    {
+      "epoch": 0.014213799230085875,
+      "grad_norm": 0.03255433961749077,
+      "learning_rate": 9.414737964294636e-05,
+      "loss": 11.9338,
+      "step": 12
+    },
+    {
+      "epoch": 0.015398282499259699,
+      "grad_norm": 0.035852886736392975,
+      "learning_rate": 9.24024048078213e-05,
+      "loss": 11.9316,
+      "step": 13
+    },
+    {
+      "epoch": 0.01658276576843352,
+      "grad_norm": 0.039442382752895355,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 11.9345,
+      "step": 14
+    },
+    {
+      "epoch": 0.017767249037607343,
+      "grad_norm": 0.03384656086564064,
+      "learning_rate": 8.83022221559489e-05,
+      "loss": 11.9351,
+      "step": 15
+    },
+    {
+      "epoch": 0.018951732306781165,
+      "grad_norm": 0.03966505080461502,
+      "learning_rate": 8.596699001693255e-05,
+      "loss": 11.9318,
+      "step": 16
+    },
+    {
+      "epoch": 0.02013621557595499,
+      "grad_norm": 0.04789691045880318,
+      "learning_rate": 8.345653031794292e-05,
+      "loss": 11.9333,
+      "step": 17
+    },
+    {
+      "epoch": 0.021320698845128813,
+      "grad_norm": 0.03581372648477554,
+      "learning_rate": 8.07830737662829e-05,
+      "loss": 11.9312,
+      "step": 18
+    },
+    {
+      "epoch": 0.022505182114302635,
+      "grad_norm": 0.06038711592555046,
+      "learning_rate": 7.795964517353735e-05,
+      "loss": 11.9338,
+      "step": 19
+    },
+    {
+      "epoch": 0.023689665383476458,
+      "grad_norm": 0.04483047127723694,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 11.9306,
+      "step": 20
+    },
+    {
+      "epoch": 0.02487414865265028,
+      "grad_norm": 0.05461433157324791,
+      "learning_rate": 7.191855733945387e-05,
+      "loss": 11.9301,
+      "step": 21
+    },
+    {
+      "epoch": 0.026058631921824105,
+      "grad_norm": 0.05950816720724106,
+      "learning_rate": 6.873032967079561e-05,
+      "loss": 11.9309,
+      "step": 22
+    },
+    {
+      "epoch": 0.027243115190997928,
+      "grad_norm": 0.05849950388073921,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 11.9306,
+      "step": 23
+    },
+    {
+      "epoch": 0.02842759846017175,
+      "grad_norm": 0.050035472959280014,
+      "learning_rate": 6.209609477998338e-05,
+      "loss": 11.9304,
+      "step": 24
+    },
+    {
+      "epoch": 0.029612081729345572,
+      "grad_norm": 0.07346203923225403,
+      "learning_rate": 5.868240888334653e-05,
+      "loss": 11.9292,
+      "step": 25
+    },
+    {
+      "epoch": 0.029612081729345572,
+      "eval_loss": 11.930323600769043,
+      "eval_runtime": 3.8975,
+      "eval_samples_per_second": 364.852,
+      "eval_steps_per_second": 45.671,
+      "step": 25
+    },
+    {
+      "epoch": 0.030796564998519398,
+      "grad_norm": 0.10136387497186661,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 11.9295,
+      "step": 26
+    },
+    {
+      "epoch": 0.03198104826769322,
+      "grad_norm": 0.09428074955940247,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 11.9297,
+      "step": 27
+    },
+    {
+      "epoch": 0.03316553153686704,
+      "grad_norm": 0.06541600078344345,
+      "learning_rate": 4.825502516487497e-05,
+      "loss": 11.9307,
+      "step": 28
+    },
+    {
+      "epoch": 0.034350014806040864,
+      "grad_norm": 0.08133825659751892,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 11.931,
+      "step": 29
+    },
+    {
+      "epoch": 0.035534498075214686,
+      "grad_norm": 0.07791212946176529,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 11.9292,
+      "step": 30
+    },
+    {
+      "epoch": 0.03671898134438851,
+      "grad_norm": 0.09555291384458542,
+      "learning_rate": 3.790390522001662e-05,
+      "loss": 11.9288,
+      "step": 31
+    },
+    {
+      "epoch": 0.03790346461356233,
+      "grad_norm": 0.0607481487095356,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 11.9313,
+      "step": 32
+    },
+    {
+      "epoch": 0.03908794788273615,
+      "grad_norm": 0.12006837129592896,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 11.9262,
+      "step": 33
+    },
+    {
+      "epoch": 0.04027243115190998,
+      "grad_norm": 0.10482200980186462,
+      "learning_rate": 2.8081442660546125e-05,
+      "loss": 11.9294,
+      "step": 34
+    },
+    {
+      "epoch": 0.041456914421083804,
+      "grad_norm": 0.10226080566644669,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 11.9287,
+      "step": 35
+    },
+    {
+      "epoch": 0.042641397690257626,
+      "grad_norm": 0.08812256902456284,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 11.9278,
+      "step": 36
+    },
+    {
+      "epoch": 0.04382588095943145,
+      "grad_norm": 0.11083268374204636,
+      "learning_rate": 1.9216926233717085e-05,
+      "loss": 11.9319,
+      "step": 37
+    },
+    {
+      "epoch": 0.04501036422860527,
+      "grad_norm": 0.10659115761518478,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 11.9289,
+      "step": 38
+    },
+    {
+      "epoch": 0.04619484749777909,
+      "grad_norm": 0.11986081302165985,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 11.9278,
+      "step": 39
+    },
+    {
+      "epoch": 0.047379330766952915,
+      "grad_norm": 0.09401536732912064,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 11.9303,
+      "step": 40
+    },
+    {
+      "epoch": 0.04856381403612674,
+      "grad_norm": 0.08666479587554932,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 11.929,
+      "step": 41
+    },
+    {
+      "epoch": 0.04974829730530056,
+      "grad_norm": 0.13678693771362305,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 11.9265,
+      "step": 42
+    },
+    {
+      "epoch": 0.05093278057447439,
+      "grad_norm": 0.11096008121967316,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 11.9285,
+      "step": 43
+    },
+    {
+      "epoch": 0.05211726384364821,
+      "grad_norm": 0.11912527680397034,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 11.9243,
+      "step": 44
+    },
+    {
+      "epoch": 0.05330174711282203,
+      "grad_norm": 0.15638715028762817,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 11.9243,
+      "step": 45
+    },
+    {
+      "epoch": 0.054486230381995855,
+      "grad_norm": 0.12490303069353104,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 11.9285,
+      "step": 46
+    },
+    {
+      "epoch": 0.05567071365116968,
+      "grad_norm": 0.1347106397151947,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 11.9302,
+      "step": 47
+    },
+    {
+      "epoch": 0.0568551969203435,
+      "grad_norm": 0.13335788249969482,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 11.9256,
+      "step": 48
+    },
+    {
+      "epoch": 0.05803968018951732,
+      "grad_norm": 0.14592963457107544,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 11.9242,
+      "step": 49
+    },
+    {
+      "epoch": 0.059224163458691144,
+      "grad_norm": 0.14100728929042816,
+      "learning_rate": 0.0,
+      "loss": 11.9258,
+      "step": 50
+    },
+    {
+      "epoch": 0.059224163458691144,
+      "eval_loss": 11.928251266479492,
+      "eval_runtime": 3.8981,
+      "eval_samples_per_second": 364.795,
+      "eval_steps_per_second": 45.664,
+      "step": 50
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 50,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 25,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 5,
+        "early_stopping_threshold": 0.0
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 0
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 120520704000.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

last-checkpoint/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0cc98201c6118a7470b25d3719881888a4aac5ac5a62ac51216a052208b67322
+size 6840

special_tokens_map.json

@@ -0,0 +1,20 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bcfe42da0a4497e8b2b172c1f9f4ec423a46dc12907f4349c55025f670422ba9
+size 11418266

tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": null,
+  "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|>",
+  "errors": "replace",
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0cc98201c6118a7470b25d3719881888a4aac5ac5a62ac51216a052208b67322
+size 6840