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 +1,165 @@
+---
+library_name: peft
+base_model: peft-internal-testing/tiny-dummy-qwen2
+tags:
+- axolotl
+- generated_from_trainer
+model-index:
+- name: a9e7a6db-0def-40a4-a8a4-0bf2c657692a
+  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: peft-internal-testing/tiny-dummy-qwen2
+bf16: auto
+chat_template: llama3
+dataset_prepared_path: null
+datasets:
+- data_files:
+  - c5efe3191618858d_train_data.json
+  ds_type: json
+  format: custom
+  path: /workspace/input_data/c5efe3191618858d_train_data.json
+  type:
+    field_instruction: question
+    field_output: answer
+    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/c5efe3191618858d_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
+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: a9e7a6db-0def-40a4-a8a4-0bf2c657692a
+wandb_project: Gradients-On-Demand
+wandb_run: your_name
+wandb_runid: a9e7a6db-0def-40a4-a8a4-0bf2c657692a
+warmup_steps: 10
+weight_decay: 0.0
+xformers_attention: null
+
+```
+
+</details><br>
+
+# a9e7a6db-0def-40a4-a8a4-0bf2c657692a
+
+This model is a fine-tuned version of [peft-internal-testing/tiny-dummy-qwen2](https://huggingface.co/peft-internal-testing/tiny-dummy-qwen2) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 11.9285
+
+## 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: 56
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 11.9287       | 0.0179 | 1    | 11.9288         |
+| 11.9286       | 0.2503 | 14   | 11.9287         |
+| 11.9304       | 0.5006 | 28   | 11.9286         |
+| 11.9279       | 0.7508 | 42   | 11.9285         |
+| 13.9592       | 1.0034 | 56   | 11.9285         |
+
+
+### 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": "peft-internal-testing/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": 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": [
+    "v_proj",
+    "down_proj",
+    "k_proj",
+    "q_proj",
+    "gate_proj",
+    "o_proj",
+    "up_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 sha256:8a5a6287d8823fe0879ab294b3da41caa5a430114dba79e42f0253a5f6dba7af
+size 21378

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e019a9f57ecb8b85aec8bb6eee672a122e591e36bd2565bc6c4c332b190d0fc5
+size 14696

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": "peft-internal-testing/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: peft-internal-testing/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": "peft-internal-testing/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": 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": [
+    "v_proj",
+    "down_proj",
+    "k_proj",
+    "q_proj",
+    "gate_proj",
+    "o_proj",
+    "up_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:e019a9f57ecb8b85aec8bb6eee672a122e591e36bd2565bc6c4c332b190d0fc5
+size 14696

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:bdac6c649202ef2291ed5061c16538bc0530983fc22e3831ec5e6375e3ece8d5
+size 39398

last-checkpoint/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3f3d68d08c427bfcb26826cb256501e784dd1de9309d24ccf5d718c10dd6b5c
+size 14244

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e41d236d9989ea458dc3f7994dccaa194aab3668a60eebd5db6cd4583a97af79
+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 +1,465 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0033519553072625,
+  "eval_steps": 14,
+  "global_step": 56,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.017877094972067038,
+      "grad_norm": 0.008051837794482708,
+      "learning_rate": 1e-05,
+      "loss": 11.9287,
+      "step": 1
+    },
+    {
+      "epoch": 0.017877094972067038,
+      "eval_loss": 11.928812026977539,
+      "eval_runtime": 17.7636,
+      "eval_samples_per_second": 5.348,
+      "eval_steps_per_second": 2.702,
+      "step": 1
+    },
+    {
+      "epoch": 0.035754189944134075,
+      "grad_norm": 0.008926309645175934,
+      "learning_rate": 2e-05,
+      "loss": 11.9296,
+      "step": 2
+    },
+    {
+      "epoch": 0.053631284916201116,
+      "grad_norm": 0.00831968616694212,
+      "learning_rate": 3e-05,
+      "loss": 11.9287,
+      "step": 3
+    },
+    {
+      "epoch": 0.07150837988826815,
+      "grad_norm": 0.007635825779289007,
+      "learning_rate": 4e-05,
+      "loss": 11.9297,
+      "step": 4
+    },
+    {
+      "epoch": 0.0893854748603352,
+      "grad_norm": 0.006136827636510134,
+      "learning_rate": 5e-05,
+      "loss": 11.9308,
+      "step": 5
+    },
+    {
+      "epoch": 0.10726256983240223,
+      "grad_norm": 0.008952487260103226,
+      "learning_rate": 6e-05,
+      "loss": 11.9298,
+      "step": 6
+    },
+    {
+      "epoch": 0.12513966480446928,
+      "grad_norm": 0.008229999803006649,
+      "learning_rate": 7e-05,
+      "loss": 11.9316,
+      "step": 7
+    },
+    {
+      "epoch": 0.1430167597765363,
+      "grad_norm": 0.008337481878697872,
+      "learning_rate": 8e-05,
+      "loss": 11.9323,
+      "step": 8
+    },
+    {
+      "epoch": 0.16089385474860335,
+      "grad_norm": 0.0077857039868831635,
+      "learning_rate": 9e-05,
+      "loss": 11.9287,
+      "step": 9
+    },
+    {
+      "epoch": 0.1787709497206704,
+      "grad_norm": 0.007779798936098814,
+      "learning_rate": 0.0001,
+      "loss": 11.9293,
+      "step": 10
+    },
+    {
+      "epoch": 0.19664804469273742,
+      "grad_norm": 0.010903590358793736,
+      "learning_rate": 9.988343845952697e-05,
+      "loss": 11.9297,
+      "step": 11
+    },
+    {
+      "epoch": 0.21452513966480447,
+      "grad_norm": 0.008899732492864132,
+      "learning_rate": 9.953429730181653e-05,
+      "loss": 11.929,
+      "step": 12
+    },
+    {
+      "epoch": 0.2324022346368715,
+      "grad_norm": 0.008686481043696404,
+      "learning_rate": 9.895420438411616e-05,
+      "loss": 11.9327,
+      "step": 13
+    },
+    {
+      "epoch": 0.25027932960893856,
+      "grad_norm": 0.008174674585461617,
+      "learning_rate": 9.814586436738998e-05,
+      "loss": 11.9286,
+      "step": 14
+    },
+    {
+      "epoch": 0.25027932960893856,
+      "eval_loss": 11.928715705871582,
+      "eval_runtime": 0.3873,
+      "eval_samples_per_second": 245.313,
+      "eval_steps_per_second": 123.947,
+      "step": 14
+    },
+    {
+      "epoch": 0.2681564245810056,
+      "grad_norm": 0.008636604063212872,
+      "learning_rate": 9.711304610594104e-05,
+      "loss": 11.9307,
+      "step": 15
+    },
+    {
+      "epoch": 0.2860335195530726,
+      "grad_norm": 0.009689634665846825,
+      "learning_rate": 9.586056507527266e-05,
+      "loss": 11.9291,
+      "step": 16
+    },
+    {
+      "epoch": 0.3039106145251397,
+      "grad_norm": 0.007181845605373383,
+      "learning_rate": 9.439426092011875e-05,
+      "loss": 11.9316,
+      "step": 17
+    },
+    {
+      "epoch": 0.3217877094972067,
+      "grad_norm": 0.00760689377784729,
+      "learning_rate": 9.272097022732443e-05,
+      "loss": 11.9297,
+      "step": 18
+    },
+    {
+      "epoch": 0.3396648044692737,
+      "grad_norm": 0.007029213942587376,
+      "learning_rate": 9.08484946505221e-05,
+      "loss": 11.9308,
+      "step": 19
+    },
+    {
+      "epoch": 0.3575418994413408,
+      "grad_norm": 0.009038039483129978,
+      "learning_rate": 8.8785564535221e-05,
+      "loss": 11.931,
+      "step": 20
+    },
+    {
+      "epoch": 0.3754189944134078,
+      "grad_norm": 0.0075072660110890865,
+      "learning_rate": 8.654179821390621e-05,
+      "loss": 11.9313,
+      "step": 21
+    },
+    {
+      "epoch": 0.39329608938547483,
+      "grad_norm": 0.00974891148507595,
+      "learning_rate": 8.412765716093272e-05,
+      "loss": 11.9313,
+      "step": 22
+    },
+    {
+      "epoch": 0.4111731843575419,
+      "grad_norm": 0.0073928870260715485,
+      "learning_rate": 8.155439721630264e-05,
+      "loss": 11.9301,
+      "step": 23
+    },
+    {
+      "epoch": 0.42905027932960893,
+      "grad_norm": 0.009019100107252598,
+      "learning_rate": 7.883401610574336e-05,
+      "loss": 11.9291,
+      "step": 24
+    },
+    {
+      "epoch": 0.44692737430167595,
+      "grad_norm": 0.007918241433799267,
+      "learning_rate": 7.597919750177168e-05,
+      "loss": 11.9313,
+      "step": 25
+    },
+    {
+      "epoch": 0.464804469273743,
+      "grad_norm": 0.009383410215377808,
+      "learning_rate": 7.300325188655761e-05,
+      "loss": 11.9298,
+      "step": 26
+    },
+    {
+      "epoch": 0.48268156424581005,
+      "grad_norm": 0.008459771983325481,
+      "learning_rate": 6.992005449231208e-05,
+      "loss": 11.9309,
+      "step": 27
+    },
+    {
+      "epoch": 0.5005586592178771,
+      "grad_norm": 0.008441867306828499,
+      "learning_rate": 6.674398060854931e-05,
+      "loss": 11.9304,
+      "step": 28
+    },
+    {
+      "epoch": 0.5005586592178771,
+      "eval_loss": 11.928580284118652,
+      "eval_runtime": 0.3886,
+      "eval_samples_per_second": 244.488,
+      "eval_steps_per_second": 123.531,
+      "step": 28
+    },
+    {
+      "epoch": 0.5184357541899441,
+      "grad_norm": 0.010095364414155483,
+      "learning_rate": 6.348983855785121e-05,
+      "loss": 11.9277,
+      "step": 29
+    },
+    {
+      "epoch": 0.5363128491620112,
+      "grad_norm": 0.007604570593684912,
+      "learning_rate": 6.01728006526317e-05,
+      "loss": 11.9298,
+      "step": 30
+    },
+    {
+      "epoch": 0.5541899441340782,
+      "grad_norm": 0.0103254783898592,
+      "learning_rate": 5.680833245481234e-05,
+      "loss": 11.9283,
+      "step": 31
+    },
+    {
+      "epoch": 0.5720670391061452,
+      "grad_norm": 0.00810755044221878,
+      "learning_rate": 5.341212066823355e-05,
+      "loss": 11.931,
+      "step": 32
+    },
+    {
+      "epoch": 0.5899441340782123,
+      "grad_norm": 0.007562727201730013,
+      "learning_rate": 5e-05,
+      "loss": 11.9287,
+      "step": 33
+    },
+    {
+      "epoch": 0.6078212290502794,
+      "grad_norm": 0.008853144943714142,
+      "learning_rate": 4.658787933176646e-05,
+      "loss": 11.9304,
+      "step": 34
+    },
+    {
+      "epoch": 0.6256983240223464,
+      "grad_norm": 0.009539203718304634,
+      "learning_rate": 4.319166754518768e-05,
+      "loss": 11.93,
+      "step": 35
+    },
+    {
+      "epoch": 0.6435754189944134,
+      "grad_norm": 0.009173383004963398,
+      "learning_rate": 3.982719934736832e-05,
+      "loss": 11.9296,
+      "step": 36
+    },
+    {
+      "epoch": 0.6614525139664804,
+      "grad_norm": 0.008169720880687237,
+      "learning_rate": 3.651016144214878e-05,
+      "loss": 11.9302,
+      "step": 37
+    },
+    {
+      "epoch": 0.6793296089385474,
+      "grad_norm": 0.008827430196106434,
+      "learning_rate": 3.325601939145069e-05,
+      "loss": 11.9295,
+      "step": 38
+    },
+    {
+      "epoch": 0.6972067039106146,
+      "grad_norm": 0.010021938011050224,
+      "learning_rate": 3.007994550768793e-05,
+      "loss": 11.9299,
+      "step": 39
+    },
+    {
+      "epoch": 0.7150837988826816,
+      "grad_norm": 0.010521038435399532,
+      "learning_rate": 2.6996748113442394e-05,
+      "loss": 11.9308,
+      "step": 40
+    },
+    {
+      "epoch": 0.7329608938547486,
+      "grad_norm": 0.009070714004337788,
+      "learning_rate": 2.4020802498228335e-05,
+      "loss": 11.93,
+      "step": 41
+    },
+    {
+      "epoch": 0.7508379888268156,
+      "grad_norm": 0.008820487186312675,
+      "learning_rate": 2.1165983894256647e-05,
+      "loss": 11.9279,
+      "step": 42
+    },
+    {
+      "epoch": 0.7508379888268156,
+      "eval_loss": 11.928503036499023,
+      "eval_runtime": 0.3804,
+      "eval_samples_per_second": 249.752,
+      "eval_steps_per_second": 126.19,
+      "step": 42
+    },
+    {
+      "epoch": 0.7687150837988826,
+      "grad_norm": 0.010876229964196682,
+      "learning_rate": 1.8445602783697374e-05,
+      "loss": 11.9305,
+      "step": 43
+    },
+    {
+      "epoch": 0.7865921787709497,
+      "grad_norm": 0.008084769360721111,
+      "learning_rate": 1.5872342839067306e-05,
+      "loss": 11.9299,
+      "step": 44
+    },
+    {
+      "epoch": 0.8044692737430168,
+      "grad_norm": 0.009019813500344753,
+      "learning_rate": 1.3458201786093794e-05,
+      "loss": 11.9283,
+      "step": 45
+    },
+    {
+      "epoch": 0.8223463687150838,
+      "grad_norm": 0.008098295889794827,
+      "learning_rate": 1.1214435464779006e-05,
+      "loss": 11.9292,
+      "step": 46
+    },
+    {
+      "epoch": 0.8402234636871508,
+      "grad_norm": 0.008133570663630962,
+      "learning_rate": 9.151505349477902e-06,
+      "loss": 11.9289,
+      "step": 47
+    },
+    {
+      "epoch": 0.8581005586592179,
+      "grad_norm": 0.012650455348193645,
+      "learning_rate": 7.2790297726755716e-06,
+      "loss": 11.9302,
+      "step": 48
+    },
+    {
+      "epoch": 0.8759776536312849,
+      "grad_norm": 0.009691119194030762,
+      "learning_rate": 5.605739079881239e-06,
+      "loss": 11.9307,
+      "step": 49
+    },
+    {
+      "epoch": 0.8938547486033519,
+      "grad_norm": 0.009178046137094498,
+      "learning_rate": 4.139434924727359e-06,
+      "loss": 11.9297,
+      "step": 50
+    },
+    {
+      "epoch": 0.911731843575419,
+      "grad_norm": 0.008271483704447746,
+      "learning_rate": 2.88695389405898e-06,
+      "loss": 11.9291,
+      "step": 51
+    },
+    {
+      "epoch": 0.929608938547486,
+      "grad_norm": 0.00795311015099287,
+      "learning_rate": 1.8541356326100433e-06,
+      "loss": 11.9286,
+      "step": 52
+    },
+    {
+      "epoch": 0.9474860335195531,
+      "grad_norm": 0.008445663377642632,
+      "learning_rate": 1.0457956158838544e-06,
+      "loss": 11.932,
+      "step": 53
+    },
+    {
+      "epoch": 0.9653631284916201,
+      "grad_norm": 0.009014743380248547,
+      "learning_rate": 4.6570269818346224e-07,
+      "loss": 11.9283,
+      "step": 54
+    },
+    {
+      "epoch": 0.9832402234636871,
+      "grad_norm": 0.009628918021917343,
+      "learning_rate": 1.1656154047303691e-07,
+      "loss": 11.9317,
+      "step": 55
+    },
+    {
+      "epoch": 1.0033519553072625,
+      "grad_norm": 0.00985956471413374,
+      "learning_rate": 0.0,
+      "loss": 13.9592,
+      "step": 56
+    },
+    {
+      "epoch": 1.0033519553072625,
+      "eval_loss": 11.928487777709961,
+      "eval_runtime": 0.3738,
+      "eval_samples_per_second": 254.136,
+      "eval_steps_per_second": 128.405,
+      "step": 56
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 56,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 14,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 26468155392.0,
+  "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:b493acda86013cdad96ddc1c8b15ecd048f77916680ceff7b36913b4abf1f138
+size 6776

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:b493acda86013cdad96ddc1c8b15ecd048f77916680ceff7b36913b4abf1f138
+size 6776