Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,5 @@ 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
+checkpoint-180/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,62 @@
+---
+library_name: peft
+license: other
+base_model: deepseek-ai/DeepSeek-R1-Distill-Qwen-14B
+tags:
+- llama-factory
+- lora
+- generated_from_trainer
+model-index:
+- name: DeepSeek-R1-Distill-Qwen-14B
+  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. -->
+
+# DeepSeek-R1-Distill-Qwen-14B
+
+This model is a fine-tuned version of [deepseek-ai/DeepSeek-R1-Distill-Qwen-14B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-14B) on the alpaca_thinking dataset.
+
+## 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: 6
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 4
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 192
+- total_eval_batch_size: 32
+- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 3.0
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.12.0
+- Transformers 4.49.0
+- Pytorch 2.5.1+cu124
+- Datasets 3.2.0
+- Tokenizers 0.21.0

adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "deepseek-ai/DeepSeek-R1-Distill-Qwen-14B",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": "pissa_niter_16",
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "o_proj",
+    "down_proj",
+    "gate_proj",
+    "k_proj",
+    "v_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d75a1e66b33cb626743172c0fb5c676a4015e542bd547ae5b5899a518d4b8311
+size 137714904

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.960662525879917,
+    "total_flos": 4.858579275680317e+18,
+    "train_loss": 0.46919142405192055,
+    "train_runtime": 5669.8178,
+    "train_samples_per_second": 6.132,
+    "train_steps_per_second": 0.032
+}

checkpoint-180/README.md

@@ -0,0 +1,202 @@
+---
+base_model: deepseek-ai/DeepSeek-R1-Distill-Qwen-14B
+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 0.12.0

checkpoint-180/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "deepseek-ai/DeepSeek-R1-Distill-Qwen-14B",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": "pissa_niter_16",
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "o_proj",
+    "down_proj",
+    "gate_proj",
+    "k_proj",
+    "v_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-180/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d75a1e66b33cb626743172c0fb5c676a4015e542bd547ae5b5899a518d4b8311
+size 137714904

checkpoint-180/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec0a6d6e7db80320af9f656b7423909a8d8a93736adbb0fab2b0da279c426a63
+size 275817586

checkpoint-180/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:308f94f9a5c24e1bad5c393d56ae7af7782600f4e791d9c6ac35b22fff2105b6
+size 15024

checkpoint-180/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b056f3c23cb32dc77a2ec9e7651e0b64e4440e21f0fdf969b86bfc56a1cbdf06
+size 15024

checkpoint-180/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3f8a05714bc528f4885a2816181652f2303b3e8150f89b56aaee6bec56aa520
+size 15024

checkpoint-180/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f755bd3c330281961e5c03af9d10ce8c1e1678619d384f6f1fd5fd7dce2ff50
+size 15024

checkpoint-180/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a14a0dd800084fc8ff4e37ab512965705777f05e1aa8549e4415e97045313091
+size 1064

checkpoint-180/special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<｜begin▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<｜end▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<｜end▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-180/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e20ddafc659ba90242154b55275402edeca0715e5dbb30f56815a4ce081f4893
+size 11422778

checkpoint-180/tokenizer_config.json

@@ -0,0 +1,197 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<｜end▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<｜User｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151645": {
+      "content": "<｜Assistant｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151646": {
+      "content": "<｜begin▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|EOT|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151648": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151649": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "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
+    }
+  },
+  "bos_token": "<｜begin▁of▁sentence｜>",
+  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<｜User｜>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<｜Assistant｜><｜tool▁calls▁begin｜><｜tool▁call▁begin��>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{%- set ns.is_first = true -%}{%- else %}{{'\\n' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>' + message['content'] + '<｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '</think>' in content %}{% set content = content.split('</think>')[-1] %}{% endif %}{{'<｜Assistant｜>' + content + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\\n<｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<｜Assistant｜><think>\\n'}}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<｜end▁of▁sentence｜>",
+  "extra_special_tokens": {},
+  "legacy": true,
+  "model_max_length": 4000,
+  "pad_token": "<｜end▁of▁sentence｜>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "split_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizerFast",
+  "unk_token": null,
+  "use_default_system_prompt": false
+}

checkpoint-180/trainer_state.json

@@ -0,0 +1,159 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.960662525879917,
+  "eval_steps": 500,
+  "global_step": 180,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.16563146997929606,
+      "grad_norm": 1.1045403480529785,
+      "learning_rate": 5.555555555555556e-05,
+      "loss": 0.7952,
+      "step": 10
+    },
+    {
+      "epoch": 0.33126293995859213,
+      "grad_norm": 0.3828948438167572,
+      "learning_rate": 9.996239762521151e-05,
+      "loss": 0.5763,
+      "step": 20
+    },
+    {
+      "epoch": 0.4968944099378882,
+      "grad_norm": 0.315212219953537,
+      "learning_rate": 9.865224352899119e-05,
+      "loss": 0.5143,
+      "step": 30
+    },
+    {
+      "epoch": 0.6625258799171843,
+      "grad_norm": 0.28653863072395325,
+      "learning_rate": 9.551814704830734e-05,
+      "loss": 0.4931,
+      "step": 40
+    },
+    {
+      "epoch": 0.8281573498964804,
+      "grad_norm": 0.26458311080932617,
+      "learning_rate": 9.067760351314838e-05,
+      "loss": 0.4686,
+      "step": 50
+    },
+    {
+      "epoch": 0.9937888198757764,
+      "grad_norm": 0.25187617540359497,
+      "learning_rate": 8.43120818934367e-05,
+      "loss": 0.474,
+      "step": 60
+    },
+    {
+      "epoch": 1.1490683229813665,
+      "grad_norm": 0.25587961077690125,
+      "learning_rate": 7.666022164008457e-05,
+      "loss": 0.4457,
+      "step": 70
+    },
+    {
+      "epoch": 1.3146997929606625,
+      "grad_norm": 0.27590256929397583,
+      "learning_rate": 6.800888624023553e-05,
+      "loss": 0.4406,
+      "step": 80
+    },
+    {
+      "epoch": 1.4803312629399585,
+      "grad_norm": 0.25824370980262756,
+      "learning_rate": 5.868240888334653e-05,
+      "loss": 0.4363,
+      "step": 90
+    },
+    {
+      "epoch": 1.6459627329192545,
+      "grad_norm": 0.24047276377677917,
+      "learning_rate": 4.903043341140879e-05,
+      "loss": 0.4315,
+      "step": 100
+    },
+    {
+      "epoch": 1.8115942028985508,
+      "grad_norm": 0.2541721761226654,
+      "learning_rate": 3.941480638852948e-05,
+      "loss": 0.4356,
+      "step": 110
+    },
+    {
+      "epoch": 1.9772256728778468,
+      "grad_norm": 0.26237165927886963,
+      "learning_rate": 3.019601169804216e-05,
+      "loss": 0.4263,
+      "step": 120
+    },
+    {
+      "epoch": 2.132505175983437,
+      "grad_norm": 0.23833103477954865,
+      "learning_rate": 2.171965622567308e-05,
+      "loss": 0.4202,
+      "step": 130
+    },
+    {
+      "epoch": 2.298136645962733,
+      "grad_norm": 0.2733284831047058,
+      "learning_rate": 1.4303513272105057e-05,
+      "loss": 0.4178,
+      "step": 140
+    },
+    {
+      "epoch": 2.463768115942029,
+      "grad_norm": 0.2536739110946655,
+      "learning_rate": 8.225609429353187e-06,
+      "loss": 0.4221,
+      "step": 150
+    },
+    {
+      "epoch": 2.629399585921325,
+      "grad_norm": 0.22531658411026,
+      "learning_rate": 3.7138015365554833e-06,
+      "loss": 0.4202,
+      "step": 160
+    },
+    {
+      "epoch": 2.795031055900621,
+      "grad_norm": 0.23673856258392334,
+      "learning_rate": 9.372344686307655e-07,
+      "loss": 0.4125,
+      "step": 170
+    },
+    {
+      "epoch": 2.960662525879917,
+      "grad_norm": 0.2418087124824524,
+      "learning_rate": 0.0,
+      "loss": 0.4152,
+      "step": 180
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 180,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4.858579275680317e+18,
+  "train_batch_size": 6,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-180/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c113b0f4f6e8dcf9a9e47b59396c7cfeff675a9b04ef064d6bff65f037e19f5a
+size 5688

pissa_backup/README.md

@@ -0,0 +1,202 @@
+---
+base_model: deepseek-ai/DeepSeek-R1-Distill-Qwen-14B
+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 0.12.0

pissa_backup/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "deepseek-ai/DeepSeek-R1-Distill-Qwen-14B",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "o_proj",
+    "down_proj",
+    "gate_proj",
+    "k_proj",
+    "v_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

pissa_backup/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d75a1e66b33cb626743172c0fb5c676a4015e542bd547ae5b5899a518d4b8311
+size 137714904

pissa_converted/README.md

@@ -0,0 +1,202 @@
+---
+base_model: deepseek-ai/DeepSeek-R1-Distill-Qwen-14B
+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 0.12.0

pissa_converted/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "deepseek-ai/DeepSeek-R1-Distill-Qwen-14B",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "o_proj",
+    "down_proj",
+    "gate_proj",
+    "k_proj",
+    "v_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

pissa_converted/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6982fef437ae93a78c82c81cb0b061f9fb152135e801a6b372daacaf98a5b40e
+size 275341720

pissa_init/adapter_config.json

@@ -4,7 +4,7 @@
   "base_model_name_or_path": "deepseek-ai/DeepSeek-R1-Distill-Qwen-14B",
   "bias": "none",
   "fan_in_fan_out": false,
-  "inference_mode": true,
+  "inference_mode": false,
   "init_lora_weights": true,
   "layer_replication": null,
   "layers_pattern": null,
@@ -22,11 +22,11 @@
   "target_modules": [
     "up_proj",
     "o_proj",
-    "k_proj",
-    "q_proj",
-    "gate_proj",
     "down_proj",
-    "v_proj"
+    "gate_proj",
+    "k_proj",
+    "v_proj",
+    "q_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<｜begin▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<｜end▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<｜end▁of▁sentence｜>",
+    "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:e20ddafc659ba90242154b55275402edeca0715e5dbb30f56815a4ce081f4893
+size 11422778

tokenizer_config.json

@@ -0,0 +1,197 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<｜end▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<｜User｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151645": {
+      "content": "<｜Assistant｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151646": {
+      "content": "<｜begin▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|EOT|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151648": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151649": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "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
+    }
+  },
+  "bos_token": "<｜begin▁of▁sentence｜>",
+  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<｜User｜>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<｜Assistant｜><｜tool▁calls▁begin｜><｜tool▁call▁begin��>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{%- set ns.is_first = true -%}{%- else %}{{'\\n' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>' + message['content'] + '<｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '</think>' in content %}{% set content = content.split('</think>')[-1] %}{% endif %}{{'<｜Assistant｜>' + content + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\\n<｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<｜Assistant｜><think>\\n'}}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<｜end▁of▁sentence｜>",
+  "extra_special_tokens": {},
+  "legacy": true,
+  "model_max_length": 4000,
+  "pad_token": "<｜end▁of▁sentence｜>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "split_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizerFast",
+  "unk_token": null,
+  "use_default_system_prompt": false
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.960662525879917,
+    "total_flos": 4.858579275680317e+18,
+    "train_loss": 0.46919142405192055,
+    "train_runtime": 5669.8178,
+    "train_samples_per_second": 6.132,
+    "train_steps_per_second": 0.032
+}

trainer_log.jsonl

@@ -0,0 +1,19 @@
+{"current_steps": 10, "total_steps": 180, "loss": 0.7952, "lr": 5.555555555555556e-05, "epoch": 0.16563146997929606, "percentage": 5.56, "elapsed_time": "0:05:13", "remaining_time": "1:28:55"}
+{"current_steps": 20, "total_steps": 180, "loss": 0.5763, "lr": 9.996239762521151e-05, "epoch": 0.33126293995859213, "percentage": 11.11, "elapsed_time": "0:10:28", "remaining_time": "1:23:46"}
+{"current_steps": 30, "total_steps": 180, "loss": 0.5143, "lr": 9.865224352899119e-05, "epoch": 0.4968944099378882, "percentage": 16.67, "elapsed_time": "0:15:57", "remaining_time": "1:19:45"}
+{"current_steps": 40, "total_steps": 180, "loss": 0.4931, "lr": 9.551814704830734e-05, "epoch": 0.6625258799171843, "percentage": 22.22, "elapsed_time": "0:21:00", "remaining_time": "1:13:32"}
+{"current_steps": 50, "total_steps": 180, "loss": 0.4686, "lr": 9.067760351314838e-05, "epoch": 0.8281573498964804, "percentage": 27.78, "elapsed_time": "0:26:33", "remaining_time": "1:09:03"}
+{"current_steps": 60, "total_steps": 180, "loss": 0.474, "lr": 8.43120818934367e-05, "epoch": 0.9937888198757764, "percentage": 33.33, "elapsed_time": "0:31:28", "remaining_time": "1:02:56"}
+{"current_steps": 70, "total_steps": 180, "loss": 0.4457, "lr": 7.666022164008457e-05, "epoch": 1.1490683229813665, "percentage": 38.89, "elapsed_time": "0:36:22", "remaining_time": "0:57:10"}
+{"current_steps": 80, "total_steps": 180, "loss": 0.4406, "lr": 6.800888624023553e-05, "epoch": 1.3146997929606625, "percentage": 44.44, "elapsed_time": "0:41:21", "remaining_time": "0:51:41"}
+{"current_steps": 90, "total_steps": 180, "loss": 0.4363, "lr": 5.868240888334653e-05, "epoch": 1.4803312629399585, "percentage": 50.0, "elapsed_time": "0:46:26", "remaining_time": "0:46:26"}
+{"current_steps": 100, "total_steps": 180, "loss": 0.4315, "lr": 4.903043341140879e-05, "epoch": 1.6459627329192545, "percentage": 55.56, "elapsed_time": "0:52:00", "remaining_time": "0:41:36"}
+{"current_steps": 110, "total_steps": 180, "loss": 0.4356, "lr": 3.941480638852948e-05, "epoch": 1.8115942028985508, "percentage": 61.11, "elapsed_time": "0:57:36", "remaining_time": "0:36:39"}
+{"current_steps": 120, "total_steps": 180, "loss": 0.4263, "lr": 3.019601169804216e-05, "epoch": 1.9772256728778468, "percentage": 66.67, "elapsed_time": "1:02:57", "remaining_time": "0:31:28"}
+{"current_steps": 130, "total_steps": 180, "loss": 0.4202, "lr": 2.171965622567308e-05, "epoch": 2.132505175983437, "percentage": 72.22, "elapsed_time": "1:07:46", "remaining_time": "0:26:04"}
+{"current_steps": 140, "total_steps": 180, "loss": 0.4178, "lr": 1.4303513272105057e-05, "epoch": 2.298136645962733, "percentage": 77.78, "elapsed_time": "1:12:45", "remaining_time": "0:20:47"}
+{"current_steps": 150, "total_steps": 180, "loss": 0.4221, "lr": 8.225609429353187e-06, "epoch": 2.463768115942029, "percentage": 83.33, "elapsed_time": "1:17:53", "remaining_time": "0:15:34"}
+{"current_steps": 160, "total_steps": 180, "loss": 0.4202, "lr": 3.7138015365554833e-06, "epoch": 2.629399585921325, "percentage": 88.89, "elapsed_time": "1:23:14", "remaining_time": "0:10:24"}
+{"current_steps": 170, "total_steps": 180, "loss": 0.4125, "lr": 9.372344686307655e-07, "epoch": 2.795031055900621, "percentage": 94.44, "elapsed_time": "1:29:08", "remaining_time": "0:05:14"}
+{"current_steps": 180, "total_steps": 180, "loss": 0.4152, "lr": 0.0, "epoch": 2.960662525879917, "percentage": 100.0, "elapsed_time": "1:34:27", "remaining_time": "0:00:00"}
+{"current_steps": 180, "total_steps": 180, "epoch": 2.960662525879917, "percentage": 100.0, "elapsed_time": "1:34:28", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,168 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.960662525879917,
+  "eval_steps": 500,
+  "global_step": 180,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.16563146997929606,
+      "grad_norm": 1.1045403480529785,
+      "learning_rate": 5.555555555555556e-05,
+      "loss": 0.7952,
+      "step": 10
+    },
+    {
+      "epoch": 0.33126293995859213,
+      "grad_norm": 0.3828948438167572,
+      "learning_rate": 9.996239762521151e-05,
+      "loss": 0.5763,
+      "step": 20
+    },
+    {
+      "epoch": 0.4968944099378882,
+      "grad_norm": 0.315212219953537,
+      "learning_rate": 9.865224352899119e-05,
+      "loss": 0.5143,
+      "step": 30
+    },
+    {
+      "epoch": 0.6625258799171843,
+      "grad_norm": 0.28653863072395325,
+      "learning_rate": 9.551814704830734e-05,
+      "loss": 0.4931,
+      "step": 40
+    },
+    {
+      "epoch": 0.8281573498964804,
+      "grad_norm": 0.26458311080932617,
+      "learning_rate": 9.067760351314838e-05,
+      "loss": 0.4686,
+      "step": 50
+    },
+    {
+      "epoch": 0.9937888198757764,
+      "grad_norm": 0.25187617540359497,
+      "learning_rate": 8.43120818934367e-05,
+      "loss": 0.474,
+      "step": 60
+    },
+    {
+      "epoch": 1.1490683229813665,
+      "grad_norm": 0.25587961077690125,
+      "learning_rate": 7.666022164008457e-05,
+      "loss": 0.4457,
+      "step": 70
+    },
+    {
+      "epoch": 1.3146997929606625,
+      "grad_norm": 0.27590256929397583,
+      "learning_rate": 6.800888624023553e-05,
+      "loss": 0.4406,
+      "step": 80
+    },
+    {
+      "epoch": 1.4803312629399585,
+      "grad_norm": 0.25824370980262756,
+      "learning_rate": 5.868240888334653e-05,
+      "loss": 0.4363,
+      "step": 90
+    },
+    {
+      "epoch": 1.6459627329192545,
+      "grad_norm": 0.24047276377677917,
+      "learning_rate": 4.903043341140879e-05,
+      "loss": 0.4315,
+      "step": 100
+    },
+    {
+      "epoch": 1.8115942028985508,
+      "grad_norm": 0.2541721761226654,
+      "learning_rate": 3.941480638852948e-05,
+      "loss": 0.4356,
+      "step": 110
+    },
+    {
+      "epoch": 1.9772256728778468,
+      "grad_norm": 0.26237165927886963,
+      "learning_rate": 3.019601169804216e-05,
+      "loss": 0.4263,
+      "step": 120
+    },
+    {
+      "epoch": 2.132505175983437,
+      "grad_norm": 0.23833103477954865,
+      "learning_rate": 2.171965622567308e-05,
+      "loss": 0.4202,
+      "step": 130
+    },
+    {
+      "epoch": 2.298136645962733,
+      "grad_norm": 0.2733284831047058,
+      "learning_rate": 1.4303513272105057e-05,
+      "loss": 0.4178,
+      "step": 140
+    },
+    {
+      "epoch": 2.463768115942029,
+      "grad_norm": 0.2536739110946655,
+      "learning_rate": 8.225609429353187e-06,
+      "loss": 0.4221,
+      "step": 150
+    },
+    {
+      "epoch": 2.629399585921325,
+      "grad_norm": 0.22531658411026,
+      "learning_rate": 3.7138015365554833e-06,
+      "loss": 0.4202,
+      "step": 160
+    },
+    {
+      "epoch": 2.795031055900621,
+      "grad_norm": 0.23673856258392334,
+      "learning_rate": 9.372344686307655e-07,
+      "loss": 0.4125,
+      "step": 170
+    },
+    {
+      "epoch": 2.960662525879917,
+      "grad_norm": 0.2418087124824524,
+      "learning_rate": 0.0,
+      "loss": 0.4152,
+      "step": 180
+    },
+    {
+      "epoch": 2.960662525879917,
+      "step": 180,
+      "total_flos": 4.858579275680317e+18,
+      "train_loss": 0.46919142405192055,
+      "train_runtime": 5669.8178,
+      "train_samples_per_second": 6.132,
+      "train_steps_per_second": 0.032
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 180,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4.858579275680317e+18,
+  "train_batch_size": 6,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c113b0f4f6e8dcf9a9e47b59396c7cfeff675a9b04ef064d6bff65f037e19f5a
+size 5688