Initial upload from old repo

.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 +1,175 @@
+---
+library_name: peft
+license: apache-2.0
+base_model: Qwen/Qwen2.5-1.5B-Instruct
+tags:
+- axolotl
+- generated_from_trainer
+model-index:
+- name: a31007db-719b-45dc-9bf7-47835cd3daab
+  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: Qwen/Qwen2.5-1.5B-Instruct
+bf16: auto
+chat_template: llama3
+cosine_min_lr_ratio: 0.1
+data_processes: 4
+dataset_prepared_path: null
+datasets:
+- data_files:
+  - a30f65943c47e9dd_train_data.json
+  ds_type: json
+  format: custom
+  num_proc: 4
+  path: /workspace/input_data/a30f65943c47e9dd_train_data.json
+  streaming: true
+  type:
+    field_input: original-context
+    field_instruction: original-instruction
+    field_output: original-response
+    format: '{instruction} {input}'
+    no_input_format: '{instruction}'
+    system_format: '{system}'
+    system_prompt: ''
+debug: null
+deepspeed: null
+device_map: balanced
+do_eval: true
+early_stopping_patience: 1
+eval_batch_size: 1
+eval_sample_packing: false
+eval_steps: 25
+evaluation_strategy: steps
+flash_attention: false
+fp16: null
+fsdp: null
+fsdp_config: null
+gradient_accumulation_steps: 16
+gradient_checkpointing: true
+group_by_length: true
+hub_model_id: eeeebbb2/a31007db-719b-45dc-9bf7-47835cd3daab
+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: 64
+lora_dropout: 0.05
+lora_fan_in_fan_out: null
+lora_model_dir: null
+lora_r: 32
+lora_target_linear: true
+lora_target_modules:
+- q_proj
+- v_proj
+lr_scheduler: cosine
+max_grad_norm: 1.0
+max_memory:
+  0: 75GB
+  1: 75GB
+  2: 75GB
+  3: 75GB
+max_steps: 50
+micro_batch_size: 2
+mixed_precision: bf16
+mlflow_experiment_name: /tmp/a30f65943c47e9dd_train_data.json
+model_type: AutoModelForCausalLM
+num_epochs: 3
+optim_args:
+  adam_beta1: 0.9
+  adam_beta2: 0.95
+  adam_epsilon: 1e-5
+optimizer: adamw_torch
+output_dir: miner_id_24
+pad_to_sequence_len: true
+resume_from_checkpoint: null
+s2_attention: null
+sample_packing: false
+save_steps: 25
+save_strategy: steps
+sequence_len: 2048
+strict: false
+tf32: false
+tokenizer_type: AutoTokenizer
+torch_compile: false
+train_on_inputs: false
+trust_remote_code: true
+val_set_size: 50
+wandb_entity: null
+wandb_mode: online
+wandb_name: a31007db-719b-45dc-9bf7-47835cd3daab
+wandb_project: Public_TuningSN
+wandb_runid: a31007db-719b-45dc-9bf7-47835cd3daab
+warmup_ratio: 0.04
+weight_decay: 0.01
+xformers_attention: null
+
+```
+
+</details><br>
+
+# a31007db-719b-45dc-9bf7-47835cd3daab
+
+This model is a fine-tuned version of [Qwen/Qwen2.5-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-1.5B-Instruct) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.7241
+
+## 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: 1
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 4
+- gradient_accumulation_steps: 16
+- total_train_batch_size: 128
+- total_eval_batch_size: 4
+- optimizer: Use OptimizerNames.ADAMW_TORCH 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: 2
+- training_steps: 50
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 1.7415        | 0.0089 | 1    | 3.0793          |
+| 2.6723        | 0.2227 | 25   | 1.8634          |
+| 2.0818        | 0.4454 | 50   | 1.7241          |
+
+
+### 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": "Qwen/Qwen2.5-1.5B-Instruct",
+  "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": 64,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "gate_proj",
+    "down_proj",
+    "up_proj",
+    "v_proj",
+    "o_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10bcf26de16460ea687e7cfc6f7e062ae9abe8c5db8e4176332c9788a3bcf1b5
+size 147859242

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dabca67b4236dbb92fa58b1abea6d65a9638d1b1d4da1922c5467cfd9b01298b
+size 147770496

added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

config.json

@@ -0,0 +1,29 @@
+{
+  "_attn_implementation_autoset": true,
+  "_name_or_path": "Qwen/Qwen2.5-1.5B-Instruct",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 1536,
+  "initializer_range": 0.02,
+  "intermediate_size": 8960,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 21,
+  "model_type": "qwen2",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 28,
+  "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": "bfloat16",
+  "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: Qwen/Qwen2.5-1.5B-Instruct
+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": "Qwen/Qwen2.5-1.5B-Instruct",
+  "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": 64,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "gate_proj",
+    "down_proj",
+    "up_proj",
+    "v_proj",
+    "o_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

last-checkpoint/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dabca67b4236dbb92fa58b1abea6d65a9638d1b1d4da1922c5467cfd9b01298b
+size 147770496

last-checkpoint/added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

last-checkpoint/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2215d87d2c96e6f4cafe20a820bcbe9c87c9d11d3f34e4e654c748c5acaf2a2
+size 295765866

last-checkpoint/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93e8bc109c059b375cfc4c36589e2406d27b96177cacc3ee3626954115c8222f
+size 15024

last-checkpoint/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e3fddc36e661f28d706dec7084e9b54aa1e9b5805428664bab711a349d41fbc
+size 15024

last-checkpoint/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83082907f8fd340708884daedabbd38e5fea3d67daed1eb3b394ef90a463d98d
+size 15024

last-checkpoint/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae25accc62e6aef6fb5caebadc03c016d8136dcac03fe2bb076992fa3c8b3d02
+size 15024

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5607f6de446164d9d9adb8b91c44cec55b14aa391e24ba5637c08b834eedda2a
+size 1064

last-checkpoint/special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "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 sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+size 11421896

last-checkpoint/tokenizer_config.json

@@ -0,0 +1,207 @@
+{
+  "add_bos_token": false,
+  "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
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "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": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

last-checkpoint/trainer_state.json

@@ -0,0 +1,416 @@
+{
+  "best_metric": 1.7241265773773193,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.44543429844098,
+  "eval_steps": 25,
+  "global_step": 50,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.008908685968819599,
+      "grad_norm": 0.18878626823425293,
+      "learning_rate": 5e-05,
+      "loss": 1.7415,
+      "step": 1
+    },
+    {
+      "epoch": 0.008908685968819599,
+      "eval_loss": 3.07926607131958,
+      "eval_runtime": 2.5273,
+      "eval_samples_per_second": 19.784,
+      "eval_steps_per_second": 5.144,
+      "step": 1
+    },
+    {
+      "epoch": 0.017817371937639197,
+      "grad_norm": 0.30595144629478455,
+      "learning_rate": 0.0001,
+      "loss": 1.9616,
+      "step": 2
+    },
+    {
+      "epoch": 0.026726057906458798,
+      "grad_norm": 0.3551925718784332,
+      "learning_rate": 9.990365154573717e-05,
+      "loss": 1.9984,
+      "step": 3
+    },
+    {
+      "epoch": 0.035634743875278395,
+      "grad_norm": 0.5348491072654724,
+      "learning_rate": 9.961501876182148e-05,
+      "loss": 2.1622,
+      "step": 4
+    },
+    {
+      "epoch": 0.044543429844097995,
+      "grad_norm": 0.9069880843162537,
+      "learning_rate": 9.913533761814537e-05,
+      "loss": 2.1843,
+      "step": 5
+    },
+    {
+      "epoch": 0.053452115812917596,
+      "grad_norm": 0.8640651702880859,
+      "learning_rate": 9.846666218300807e-05,
+      "loss": 2.1915,
+      "step": 6
+    },
+    {
+      "epoch": 0.062360801781737196,
+      "grad_norm": 0.8593299984931946,
+      "learning_rate": 9.761185582727977e-05,
+      "loss": 2.2393,
+      "step": 7
+    },
+    {
+      "epoch": 0.07126948775055679,
+      "grad_norm": 0.9860943555831909,
+      "learning_rate": 9.657457896300791e-05,
+      "loss": 2.0448,
+      "step": 8
+    },
+    {
+      "epoch": 0.0801781737193764,
+      "grad_norm": 1.5080639123916626,
+      "learning_rate": 9.535927336897098e-05,
+      "loss": 2.0644,
+      "step": 9
+    },
+    {
+      "epoch": 0.08908685968819599,
+      "grad_norm": 2.0294370651245117,
+      "learning_rate": 9.397114317029975e-05,
+      "loss": 2.0939,
+      "step": 10
+    },
+    {
+      "epoch": 0.09799554565701558,
+      "grad_norm": 3.4236092567443848,
+      "learning_rate": 9.241613255361455e-05,
+      "loss": 2.1193,
+      "step": 11
+    },
+    {
+      "epoch": 0.10690423162583519,
+      "grad_norm": 5.392770767211914,
+      "learning_rate": 9.070090031310558e-05,
+      "loss": 2.4573,
+      "step": 12
+    },
+    {
+      "epoch": 0.11581291759465479,
+      "grad_norm": 2.2885658740997314,
+      "learning_rate": 8.883279133655399e-05,
+      "loss": 1.8833,
+      "step": 13
+    },
+    {
+      "epoch": 0.12472160356347439,
+      "grad_norm": 2.775259494781494,
+      "learning_rate": 8.681980515339464e-05,
+      "loss": 1.8562,
+      "step": 14
+    },
+    {
+      "epoch": 0.133630289532294,
+      "grad_norm": 2.9362523555755615,
+      "learning_rate": 8.467056167950311e-05,
+      "loss": 1.9584,
+      "step": 15
+    },
+    {
+      "epoch": 0.14253897550111358,
+      "grad_norm": 2.638282299041748,
+      "learning_rate": 8.239426430539243e-05,
+      "loss": 1.9635,
+      "step": 16
+    },
+    {
+      "epoch": 0.1514476614699332,
+      "grad_norm": 0.7820598483085632,
+      "learning_rate": 8.000066048588211e-05,
+      "loss": 2.1001,
+      "step": 17
+    },
+    {
+      "epoch": 0.1603563474387528,
+      "grad_norm": 0.8463975787162781,
+      "learning_rate": 7.75e-05,
+      "loss": 1.9806,
+      "step": 18
+    },
+    {
+      "epoch": 0.16926503340757237,
+      "grad_norm": 1.3420571088790894,
+      "learning_rate": 7.490299105985507e-05,
+      "loss": 2.0301,
+      "step": 19
+    },
+    {
+      "epoch": 0.17817371937639198,
+      "grad_norm": 1.5355807542800903,
+      "learning_rate": 7.222075445642904e-05,
+      "loss": 1.9632,
+      "step": 20
+    },
+    {
+      "epoch": 0.1870824053452116,
+      "grad_norm": 1.6824076175689697,
+      "learning_rate": 6.946477593864228e-05,
+      "loss": 1.8468,
+      "step": 21
+    },
+    {
+      "epoch": 0.19599109131403117,
+      "grad_norm": 1.8673253059387207,
+      "learning_rate": 6.664685702961344e-05,
+      "loss": 1.7099,
+      "step": 22
+    },
+    {
+      "epoch": 0.20489977728285078,
+      "grad_norm": 2.989877462387085,
+      "learning_rate": 6.377906449072578e-05,
+      "loss": 1.8987,
+      "step": 23
+    },
+    {
+      "epoch": 0.21380846325167038,
+      "grad_norm": 2.8362205028533936,
+      "learning_rate": 6.087367864990233e-05,
+      "loss": 1.5028,
+      "step": 24
+    },
+    {
+      "epoch": 0.22271714922049,
+      "grad_norm": 12.428902626037598,
+      "learning_rate": 5.794314081535644e-05,
+      "loss": 2.6723,
+      "step": 25
+    },
+    {
+      "epoch": 0.22271714922049,
+      "eval_loss": 1.8634365797042847,
+      "eval_runtime": 1.3435,
+      "eval_samples_per_second": 37.216,
+      "eval_steps_per_second": 9.676,
+      "step": 25
+    },
+    {
+      "epoch": 0.23162583518930957,
+      "grad_norm": 0.4183148443698883,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 1.6019,
+      "step": 26
+    },
+    {
+      "epoch": 0.24053452115812918,
+      "grad_norm": 0.8705766797065735,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 1.7012,
+      "step": 27
+    },
+    {
+      "epoch": 0.24944320712694878,
+      "grad_norm": 0.9665325284004211,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 2.0064,
+      "step": 28
+    },
+    {
+      "epoch": 0.2583518930957684,
+      "grad_norm": 1.193624496459961,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 1.8895,
+      "step": 29
+    },
+    {
+      "epoch": 0.267260579064588,
+      "grad_norm": 0.8913549780845642,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 1.9919,
+      "step": 30
+    },
+    {
+      "epoch": 0.27616926503340755,
+      "grad_norm": 0.6848633885383606,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 2.0122,
+      "step": 31
+    },
+    {
+      "epoch": 0.28507795100222716,
+      "grad_norm": 0.5318528413772583,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 1.98,
+      "step": 32
+    },
+    {
+      "epoch": 0.29398663697104677,
+      "grad_norm": 0.4661291241645813,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 1.7988,
+      "step": 33
+    },
+    {
+      "epoch": 0.3028953229398664,
+      "grad_norm": 0.6594870686531067,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 1.8389,
+      "step": 34
+    },
+    {
+      "epoch": 0.311804008908686,
+      "grad_norm": 0.975502073764801,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 1.7635,
+      "step": 35
+    },
+    {
+      "epoch": 0.3207126948775056,
+      "grad_norm": 1.5235804319381714,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 1.6875,
+      "step": 36
+    },
+    {
+      "epoch": 0.32962138084632514,
+      "grad_norm": 3.2025015354156494,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 1.663,
+      "step": 37
+    },
+    {
+      "epoch": 0.33853006681514475,
+      "grad_norm": 0.32783958315849304,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 1.6698,
+      "step": 38
+    },
+    {
+      "epoch": 0.34743875278396436,
+      "grad_norm": 0.2496582567691803,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 1.4834,
+      "step": 39
+    },
+    {
+      "epoch": 0.35634743875278396,
+      "grad_norm": 0.3414645195007324,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 1.7371,
+      "step": 40
+    },
+    {
+      "epoch": 0.36525612472160357,
+      "grad_norm": 0.3164196312427521,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 1.7891,
+      "step": 41
+    },
+    {
+      "epoch": 0.3741648106904232,
+      "grad_norm": 0.2685292959213257,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 1.9454,
+      "step": 42
+    },
+    {
+      "epoch": 0.3830734966592428,
+      "grad_norm": 0.2867202162742615,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 1.8811,
+      "step": 43
+    },
+    {
+      "epoch": 0.39198218262806234,
+      "grad_norm": 0.3341452479362488,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 1.9291,
+      "step": 44
+    },
+    {
+      "epoch": 0.40089086859688194,
+      "grad_norm": 0.31787121295928955,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 1.8821,
+      "step": 45
+    },
+    {
+      "epoch": 0.40979955456570155,
+      "grad_norm": 0.3769933581352234,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 1.8162,
+      "step": 46
+    },
+    {
+      "epoch": 0.41870824053452116,
+      "grad_norm": 0.5178400278091431,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 1.7686,
+      "step": 47
+    },
+    {
+      "epoch": 0.42761692650334077,
+      "grad_norm": 0.7855275273323059,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 1.8133,
+      "step": 48
+    },
+    {
+      "epoch": 0.4365256124721604,
+      "grad_norm": 1.7718549966812134,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 1.5973,
+      "step": 49
+    },
+    {
+      "epoch": 0.44543429844098,
+      "grad_norm": 4.557711601257324,
+      "learning_rate": 1e-05,
+      "loss": 2.0818,
+      "step": 50
+    },
+    {
+      "epoch": 0.44543429844098,
+      "eval_loss": 1.7241265773773193,
+      "eval_runtime": 1.3369,
+      "eval_samples_per_second": 37.399,
+      "eval_steps_per_second": 9.724,
+      "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": 1,
+        "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": 1.0621851957775565e+17,
+  "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 sha256:49a51af5a1b598836ca58224215879915b7fc5e189cd8073b64d20997f373b20
+size 6840

special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "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 sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+size 11421896

tokenizer_config.json

@@ -0,0 +1,207 @@
+{
+  "add_bos_token": false,
+  "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
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "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": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 131072,
+  "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 sha256:49a51af5a1b598836ca58224215879915b7fc5e189cd8073b64d20997f373b20
+size 6840