Upload folder using huggingface_hub

README.md

@@ -0,0 +1,60 @@
+---
+license: other
+library_name: peft
+tags:
+- llama-factory
+- lora
+- generated_from_trainer
+base_model: Qwen/Qwen2-7B-Instruct-GPTQ-Int8
+model-index:
+- name: train_2024-06-06-20-45-21
+  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. -->
+
+# train_2024-06-06-20-45-21
+
+This model is a fine-tuned version of [Qwen/Qwen2-7B-Instruct-GPTQ-Int8](https://huggingface.co/Qwen/Qwen2-7B-Instruct-GPTQ-Int8) on the train 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: 5e-05
+- train_batch_size: 2
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 16
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- num_epochs: 3.0
+- mixed_precision_training: Native AMP
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.11.1
+- Transformers 4.41.2
+- Pytorch 2.2.1+cu121
+- Datasets 2.19.2
+- Tokenizers 0.19.1

adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2-7B-Instruct-GPTQ-Int8",
+  "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,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "o_proj",
+    "k_proj",
+    "gate_proj",
+    "down_proj",
+    "up_proj",
+    "v_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 sha256:48043b5bc91911c85972e5443a152db4f35149af33dfda32e60cb3f44980791f
+size 80792096

added_tokens.json

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

all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 0.4033333333333333,
+    "num_input_tokens_seen": 1371584,
+    "total_flos": 4652852538507264.0,
+    "train_loss": 0.040362141964849364,
+    "train_runtime": 4583.2214,
+    "train_samples_per_second": 6.284,
+    "train_steps_per_second": 0.393
+}

checkpoint-100/README.md

@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: Qwen/Qwen2-7B-Instruct-GPTQ-Int8
+---
+
+# 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 0.11.1

checkpoint-100/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2-7B-Instruct-GPTQ-Int8",
+  "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,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "o_proj",
+    "k_proj",
+    "gate_proj",
+    "down_proj",
+    "up_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-100/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3aa41c3c376d848d3ec7f6f5942a0889043579d8d9b7e3cbdc99958e3187f30c
+size 80792096

checkpoint-100/added_tokens.json

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

checkpoint-100/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b18c0080066dc37db88ab1910d6819e385367d313ac13470421cb138868d32d7
+size 161810282

checkpoint-100/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:835f869ea325fd6edf27b48b589309fb66641cb92b45f2fc13d1bb6e8814106c
+size 14244

checkpoint-100/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4051a10dbe4591782639bebdd97dd1262fdf358a1617c8c89f93f1b5f9d6a96
+size 1064

checkpoint-100/special_tokens_map.json

@@ -0,0 +1,20 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "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
+  }
+}

checkpoint-100/tokenizer_config.json

@@ -0,0 +1,44 @@
+{
+  "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": "{% set system_message = 'You are a helpful assistant.' %}{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ '<|im_start|>system\n' + system_message + '<|im_end|>\n' }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|im_start|>user\n' + content + '<|im_end|>\n<|im_start|>assistant\n' }}{% elif message['role'] == 'assistant' %}{{ content + '<|im_end|>' + '\n' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-100/trainer_state.json

@@ -0,0 +1,193 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.16666666666666666,
+  "eval_steps": 500,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.008333333333333333,
+      "grad_norm": 0.48900601267814636,
+      "learning_rate": 4.999904807660428e-05,
+      "loss": 0.4212,
+      "num_input_tokens_seen": 30064,
+      "step": 5
+    },
+    {
+      "epoch": 0.016666666666666666,
+      "grad_norm": 0.3595407009124756,
+      "learning_rate": 4.9996192378909786e-05,
+      "loss": 0.2803,
+      "num_input_tokens_seen": 57376,
+      "step": 10
+    },
+    {
+      "epoch": 0.025,
+      "grad_norm": 0.2623545527458191,
+      "learning_rate": 4.999143312438893e-05,
+      "loss": 0.1484,
+      "num_input_tokens_seen": 86160,
+      "step": 15
+    },
+    {
+      "epoch": 0.03333333333333333,
+      "grad_norm": 0.2743065357208252,
+      "learning_rate": 4.99847706754774e-05,
+      "loss": 0.1151,
+      "num_input_tokens_seen": 110592,
+      "step": 20
+    },
+    {
+      "epoch": 0.041666666666666664,
+      "grad_norm": 0.2651338577270508,
+      "learning_rate": 4.997620553954645e-05,
+      "loss": 0.0751,
+      "num_input_tokens_seen": 138880,
+      "step": 25
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 0.10798148065805435,
+      "learning_rate": 4.996573836886435e-05,
+      "loss": 0.0471,
+      "num_input_tokens_seen": 169600,
+      "step": 30
+    },
+    {
+      "epoch": 0.058333333333333334,
+      "grad_norm": 0.1552838534116745,
+      "learning_rate": 4.9953369960546676e-05,
+      "loss": 0.0368,
+      "num_input_tokens_seen": 201664,
+      "step": 35
+    },
+    {
+      "epoch": 0.06666666666666667,
+      "grad_norm": 0.11832074075937271,
+      "learning_rate": 4.993910125649561e-05,
+      "loss": 0.0311,
+      "num_input_tokens_seen": 229936,
+      "step": 40
+    },
+    {
+      "epoch": 0.075,
+      "grad_norm": 0.10593917220830917,
+      "learning_rate": 4.99229333433282e-05,
+      "loss": 0.0262,
+      "num_input_tokens_seen": 259088,
+      "step": 45
+    },
+    {
+      "epoch": 0.08333333333333333,
+      "grad_norm": 0.09650842100381851,
+      "learning_rate": 4.990486745229364e-05,
+      "loss": 0.0244,
+      "num_input_tokens_seen": 289824,
+      "step": 50
+    },
+    {
+      "epoch": 0.09166666666666666,
+      "grad_norm": 0.14155137538909912,
+      "learning_rate": 4.988490495917947e-05,
+      "loss": 0.0266,
+      "num_input_tokens_seen": 317760,
+      "step": 55
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.1490347981452942,
+      "learning_rate": 4.9867570427929354e-05,
+      "loss": 0.0283,
+      "num_input_tokens_seen": 343120,
+      "step": 60
+    },
+    {
+      "epoch": 0.10833333333333334,
+      "grad_norm": 0.17539122700691223,
+      "learning_rate": 4.984419797901491e-05,
+      "loss": 0.0265,
+      "num_input_tokens_seen": 371600,
+      "step": 65
+    },
+    {
+      "epoch": 0.11666666666666667,
+      "grad_norm": 0.1336919367313385,
+      "learning_rate": 4.981893354823614e-05,
+      "loss": 0.0235,
+      "num_input_tokens_seen": 398720,
+      "step": 70
+    },
+    {
+      "epoch": 0.125,
+      "grad_norm": 0.12203177809715271,
+      "learning_rate": 4.979177905957726e-05,
+      "loss": 0.0229,
+      "num_input_tokens_seen": 426416,
+      "step": 75
+    },
+    {
+      "epoch": 0.13333333333333333,
+      "grad_norm": 0.2557654082775116,
+      "learning_rate": 4.976273658095772e-05,
+      "loss": 0.0238,
+      "num_input_tokens_seen": 452944,
+      "step": 80
+    },
+    {
+      "epoch": 0.14166666666666666,
+      "grad_norm": 0.13327105343341827,
+      "learning_rate": 4.9731808324074717e-05,
+      "loss": 0.0208,
+      "num_input_tokens_seen": 480896,
+      "step": 85
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 0.1262751668691635,
+      "learning_rate": 4.969899664423473e-05,
+      "loss": 0.0191,
+      "num_input_tokens_seen": 510096,
+      "step": 90
+    },
+    {
+      "epoch": 0.15833333333333333,
+      "grad_norm": 0.16084067523479462,
+      "learning_rate": 4.966430404017424e-05,
+      "loss": 0.0205,
+      "num_input_tokens_seen": 536672,
+      "step": 95
+    },
+    {
+      "epoch": 0.16666666666666666,
+      "grad_norm": 0.15870437026023865,
+      "learning_rate": 4.962773315386935e-05,
+      "loss": 0.0193,
+      "num_input_tokens_seen": 566528,
+      "step": 100
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 1800,
+  "num_input_tokens_seen": 566528,
+  "num_train_epochs": 3,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1921844563148800.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-100/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e38936a74c731e02f619889aeaa58a6ba812a6fabdbd18f67b624b496070c73c
+size 5304

checkpoint-200/README.md

@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: Qwen/Qwen2-7B-Instruct-GPTQ-Int8
+---
+
+# 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 0.11.1

checkpoint-200/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2-7B-Instruct-GPTQ-Int8",
+  "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,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "o_proj",
+    "k_proj",
+    "gate_proj",
+    "down_proj",
+    "up_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-200/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a8e39f94ccd45abcb35fbe6819e17966752fbc56ed8611b2f52f0223a375fce
+size 80792096

checkpoint-200/added_tokens.json

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

checkpoint-200/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d90e504f03babc630dad632743174fddb6b74a308e728929f72a3919541acba5
+size 161810282

checkpoint-200/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:835f869ea325fd6edf27b48b589309fb66641cb92b45f2fc13d1bb6e8814106c
+size 14244

checkpoint-200/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72b988391a95053a053fa51ffca08c28862e9f89c4be3fa722e090ac1914d17c
+size 1064

checkpoint-200/special_tokens_map.json

@@ -0,0 +1,20 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "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
+  }
+}

checkpoint-200/tokenizer_config.json

@@ -0,0 +1,44 @@
+{
+  "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": "{% set system_message = 'You are a helpful assistant.' %}{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ '<|im_start|>system\n' + system_message + '<|im_end|>\n' }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|im_start|>user\n' + content + '<|im_end|>\n<|im_start|>assistant\n' }}{% elif message['role'] == 'assistant' %}{{ content + '<|im_end|>' + '\n' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-200/trainer_state.json

@@ -0,0 +1,353 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.3333333333333333,
+  "eval_steps": 500,
+  "global_step": 200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.008333333333333333,
+      "grad_norm": 0.48900601267814636,
+      "learning_rate": 4.999904807660428e-05,
+      "loss": 0.4212,
+      "num_input_tokens_seen": 30064,
+      "step": 5
+    },
+    {
+      "epoch": 0.016666666666666666,
+      "grad_norm": 0.3595407009124756,
+      "learning_rate": 4.9996192378909786e-05,
+      "loss": 0.2803,
+      "num_input_tokens_seen": 57376,
+      "step": 10
+    },
+    {
+      "epoch": 0.025,
+      "grad_norm": 0.2623545527458191,
+      "learning_rate": 4.999143312438893e-05,
+      "loss": 0.1484,
+      "num_input_tokens_seen": 86160,
+      "step": 15
+    },
+    {
+      "epoch": 0.03333333333333333,
+      "grad_norm": 0.2743065357208252,
+      "learning_rate": 4.99847706754774e-05,
+      "loss": 0.1151,
+      "num_input_tokens_seen": 110592,
+      "step": 20
+    },
+    {
+      "epoch": 0.041666666666666664,
+      "grad_norm": 0.2651338577270508,
+      "learning_rate": 4.997620553954645e-05,
+      "loss": 0.0751,
+      "num_input_tokens_seen": 138880,
+      "step": 25
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 0.10798148065805435,
+      "learning_rate": 4.996573836886435e-05,
+      "loss": 0.0471,
+      "num_input_tokens_seen": 169600,
+      "step": 30
+    },
+    {
+      "epoch": 0.058333333333333334,
+      "grad_norm": 0.1552838534116745,
+      "learning_rate": 4.9953369960546676e-05,
+      "loss": 0.0368,
+      "num_input_tokens_seen": 201664,
+      "step": 35
+    },
+    {
+      "epoch": 0.06666666666666667,
+      "grad_norm": 0.11832074075937271,
+      "learning_rate": 4.993910125649561e-05,
+      "loss": 0.0311,
+      "num_input_tokens_seen": 229936,
+      "step": 40
+    },
+    {
+      "epoch": 0.075,
+      "grad_norm": 0.10593917220830917,
+      "learning_rate": 4.99229333433282e-05,
+      "loss": 0.0262,
+      "num_input_tokens_seen": 259088,
+      "step": 45
+    },
+    {
+      "epoch": 0.08333333333333333,
+      "grad_norm": 0.09650842100381851,
+      "learning_rate": 4.990486745229364e-05,
+      "loss": 0.0244,
+      "num_input_tokens_seen": 289824,
+      "step": 50
+    },
+    {
+      "epoch": 0.09166666666666666,
+      "grad_norm": 0.14155137538909912,
+      "learning_rate": 4.988490495917947e-05,
+      "loss": 0.0266,
+      "num_input_tokens_seen": 317760,
+      "step": 55
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.1490347981452942,
+      "learning_rate": 4.9867570427929354e-05,
+      "loss": 0.0283,
+      "num_input_tokens_seen": 343120,
+      "step": 60
+    },
+    {
+      "epoch": 0.10833333333333334,
+      "grad_norm": 0.17539122700691223,
+      "learning_rate": 4.984419797901491e-05,
+      "loss": 0.0265,
+      "num_input_tokens_seen": 371600,
+      "step": 65
+    },
+    {
+      "epoch": 0.11666666666666667,
+      "grad_norm": 0.1336919367313385,
+      "learning_rate": 4.981893354823614e-05,
+      "loss": 0.0235,
+      "num_input_tokens_seen": 398720,
+      "step": 70
+    },
+    {
+      "epoch": 0.125,
+      "grad_norm": 0.12203177809715271,
+      "learning_rate": 4.979177905957726e-05,
+      "loss": 0.0229,
+      "num_input_tokens_seen": 426416,
+      "step": 75
+    },
+    {
+      "epoch": 0.13333333333333333,
+      "grad_norm": 0.2557654082775116,
+      "learning_rate": 4.976273658095772e-05,
+      "loss": 0.0238,
+      "num_input_tokens_seen": 452944,
+      "step": 80
+    },
+    {
+      "epoch": 0.14166666666666666,
+      "grad_norm": 0.13327105343341827,
+      "learning_rate": 4.9731808324074717e-05,
+      "loss": 0.0208,
+      "num_input_tokens_seen": 480896,
+      "step": 85
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 0.1262751668691635,
+      "learning_rate": 4.969899664423473e-05,
+      "loss": 0.0191,
+      "num_input_tokens_seen": 510096,
+      "step": 90
+    },
+    {
+      "epoch": 0.15833333333333333,
+      "grad_norm": 0.16084067523479462,
+      "learning_rate": 4.966430404017424e-05,
+      "loss": 0.0205,
+      "num_input_tokens_seen": 536672,
+      "step": 95
+    },
+    {
+      "epoch": 0.16666666666666666,
+      "grad_norm": 0.15870437026023865,
+      "learning_rate": 4.962773315386935e-05,
+      "loss": 0.0193,
+      "num_input_tokens_seen": 566528,
+      "step": 100
+    },
+    {
+      "epoch": 0.175,
+      "grad_norm": 0.07833187282085419,
+      "learning_rate": 4.9589286770334654e-05,
+      "loss": 0.024,
+      "num_input_tokens_seen": 593584,
+      "step": 105
+    },
+    {
+      "epoch": 0.18333333333333332,
+      "grad_norm": 0.09176061302423477,
+      "learning_rate": 4.954896781741109e-05,
+      "loss": 0.0206,
+      "num_input_tokens_seen": 620992,
+      "step": 110
+    },
+    {
+      "epoch": 0.19166666666666668,
+      "grad_norm": 0.08285439014434814,
+      "learning_rate": 4.9506779365543046e-05,
+      "loss": 0.0188,
+      "num_input_tokens_seen": 647504,
+      "step": 115
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.13359522819519043,
+      "learning_rate": 4.9462724627544466e-05,
+      "loss": 0.0183,
+      "num_input_tokens_seen": 676336,
+      "step": 120
+    },
+    {
+      "epoch": 0.20833333333333334,
+      "grad_norm": 0.07570718228816986,
+      "learning_rate": 4.94168069583542e-05,
+      "loss": 0.0189,
+      "num_input_tokens_seen": 701488,
+      "step": 125
+    },
+    {
+      "epoch": 0.21666666666666667,
+      "grad_norm": 0.11286037415266037,
+      "learning_rate": 4.936902985478055e-05,
+      "loss": 0.0213,
+      "num_input_tokens_seen": 731152,
+      "step": 130
+    },
+    {
+      "epoch": 0.225,
+      "grad_norm": 0.17183929681777954,
+      "learning_rate": 4.931939695523492e-05,
+      "loss": 0.0214,
+      "num_input_tokens_seen": 757792,
+      "step": 135
+    },
+    {
+      "epoch": 0.23333333333333334,
+      "grad_norm": 0.11746834218502045,
+      "learning_rate": 4.926791203945477e-05,
+      "loss": 0.0214,
+      "num_input_tokens_seen": 786064,
+      "step": 140
+    },
+    {
+      "epoch": 0.24166666666666667,
+      "grad_norm": 0.09453292936086655,
+      "learning_rate": 4.9214579028215776e-05,
+      "loss": 0.0203,
+      "num_input_tokens_seen": 814640,
+      "step": 145
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 0.2074723094701767,
+      "learning_rate": 4.915940198303324e-05,
+      "loss": 0.0194,
+      "num_input_tokens_seen": 842656,
+      "step": 150
+    },
+    {
+      "epoch": 0.25833333333333336,
+      "grad_norm": 0.15371476113796234,
+      "learning_rate": 4.910238510585276e-05,
+      "loss": 0.0158,
+      "num_input_tokens_seen": 868512,
+      "step": 155
+    },
+    {
+      "epoch": 0.26666666666666666,
+      "grad_norm": 0.07177837193012238,
+      "learning_rate": 4.9043532738730284e-05,
+      "loss": 0.0172,
+      "num_input_tokens_seen": 896416,
+      "step": 160
+    },
+    {
+      "epoch": 0.275,
+      "grad_norm": 0.07891824096441269,
+      "learning_rate": 4.898284936350144e-05,
+      "loss": 0.0193,
+      "num_input_tokens_seen": 924720,
+      "step": 165
+    },
+    {
+      "epoch": 0.2833333333333333,
+      "grad_norm": 0.08302944153547287,
+      "learning_rate": 4.892033960144019e-05,
+      "loss": 0.0189,
+      "num_input_tokens_seen": 955584,
+      "step": 170
+    },
+    {
+      "epoch": 0.2916666666666667,
+      "grad_norm": 0.25554358959198,
+      "learning_rate": 4.8856008212906925e-05,
+      "loss": 0.019,
+      "num_input_tokens_seen": 985072,
+      "step": 175
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 0.1445908546447754,
+      "learning_rate": 4.878986009698596e-05,
+      "loss": 0.0168,
+      "num_input_tokens_seen": 1013296,
+      "step": 180
+    },
+    {
+      "epoch": 0.30833333333333335,
+      "grad_norm": 0.21417762339115143,
+      "learning_rate": 4.8721900291112415e-05,
+      "loss": 0.0194,
+      "num_input_tokens_seen": 1043664,
+      "step": 185
+    },
+    {
+      "epoch": 0.31666666666666665,
+      "grad_norm": 0.1550753116607666,
+      "learning_rate": 4.8652133970688636e-05,
+      "loss": 0.0155,
+      "num_input_tokens_seen": 1070912,
+      "step": 190
+    },
+    {
+      "epoch": 0.325,
+      "grad_norm": 0.132898211479187,
+      "learning_rate": 4.858056644869002e-05,
+      "loss": 0.0193,
+      "num_input_tokens_seen": 1097856,
+      "step": 195
+    },
+    {
+      "epoch": 0.3333333333333333,
+      "grad_norm": 0.09164389222860336,
+      "learning_rate": 4.850720317526047e-05,
+      "loss": 0.0164,
+      "num_input_tokens_seen": 1126128,
+      "step": 200
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 1800,
+  "num_input_tokens_seen": 1126128,
+  "num_train_epochs": 3,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3820187115585536.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-200/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e38936a74c731e02f619889aeaa58a6ba812a6fabdbd18f67b624b496070c73c
+size 5304

running_log.txt

@@ -0,0 +1,431 @@
+06/06/2024 20:45:49 - INFO - transformers.tokenization_utils_base - loading file vocab.json from cache at /home/zeus/.cache/huggingface/hub/models--Qwen--Qwen2-7B-Instruct-GPTQ-Int8/snapshots/22d9ef924dfae7700c4b620be6600d5c7ea31f88/vocab.json
+
+06/06/2024 20:45:49 - INFO - transformers.tokenization_utils_base - loading file merges.txt from cache at /home/zeus/.cache/huggingface/hub/models--Qwen--Qwen2-7B-Instruct-GPTQ-Int8/snapshots/22d9ef924dfae7700c4b620be6600d5c7ea31f88/merges.txt
+
+06/06/2024 20:45:49 - INFO - transformers.tokenization_utils_base - loading file tokenizer.json from cache at /home/zeus/.cache/huggingface/hub/models--Qwen--Qwen2-7B-Instruct-GPTQ-Int8/snapshots/22d9ef924dfae7700c4b620be6600d5c7ea31f88/tokenizer.json
+
+06/06/2024 20:45:49 - INFO - transformers.tokenization_utils_base - loading file added_tokens.json from cache at None
+
+06/06/2024 20:45:49 - INFO - transformers.tokenization_utils_base - loading file special_tokens_map.json from cache at None
+
+06/06/2024 20:45:49 - INFO - transformers.tokenization_utils_base - loading file tokenizer_config.json from cache at /home/zeus/.cache/huggingface/hub/models--Qwen--Qwen2-7B-Instruct-GPTQ-Int8/snapshots/22d9ef924dfae7700c4b620be6600d5c7ea31f88/tokenizer_config.json
+
+06/06/2024 20:45:49 - WARNING - transformers.tokenization_utils_base - Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
+
+06/06/2024 20:45:49 - INFO - llamafactory.data.template - Replace eos token: <|im_end|>
+
+06/06/2024 20:45:49 - INFO - llamafactory.data.loader - Loading dataset train.json...
+
+06/06/2024 20:45:49 - INFO - transformers.configuration_utils - loading configuration file config.json from cache at /home/zeus/.cache/huggingface/hub/models--Qwen--Qwen2-7B-Instruct-GPTQ-Int8/snapshots/22d9ef924dfae7700c4b620be6600d5c7ea31f88/config.json
+
+06/06/2024 20:45:49 - INFO - transformers.configuration_utils - Model config Qwen2Config {
+  "_name_or_path": "Qwen/Qwen2-7B-Instruct-GPTQ-Int8",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "quantization_config": {
+    "batch_size": 1,
+    "bits": 8,
+    "block_name_to_quantize": null,
+    "cache_block_outputs": true,
+    "damp_percent": 0.1,
+    "dataset": null,
+    "desc_act": false,
+    "exllama_config": {
+      "version": 1
+    },
+    "group_size": 128,
+    "max_input_length": null,
+    "model_seqlen": null,
+    "module_name_preceding_first_block": null,
+    "modules_in_block_to_quantize": null,
+    "pad_token_id": null,
+    "quant_method": "gptq",
+    "sym": true,
+    "tokenizer": null,
+    "true_sequential": true,
+    "use_cuda_fp16": false,
+    "use_exllama": true
+  },
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 1000000.0,
+  "sliding_window": 131072,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.41.2",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}
+
+
+06/06/2024 20:45:49 - WARNING - llamafactory.model.model_utils.attention - FlashAttention-2 is not installed.
+
+06/06/2024 20:45:49 - INFO - llamafactory.model.model_utils.quantization - Loading 8-bit GPTQ-quantized model.
+
+06/06/2024 20:45:49 - INFO - transformers.modeling_utils - loading weights file model.safetensors from cache at /home/zeus/.cache/huggingface/hub/models--Qwen--Qwen2-7B-Instruct-GPTQ-Int8/snapshots/22d9ef924dfae7700c4b620be6600d5c7ea31f88/model.safetensors.index.json
+
+06/06/2024 20:46:15 - INFO - transformers.modeling_utils - Instantiating Qwen2ForCausalLM model under default dtype torch.float16.
+
+06/06/2024 20:46:15 - INFO - transformers.generation.configuration_utils - Generate config GenerationConfig {
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "use_cache": false
+}
+
+
+06/06/2024 20:46:41 - WARNING - transformers.modeling_utils - Some weights of the model checkpoint at Qwen/Qwen2-7B-Instruct-GPTQ-Int8 were not used when initializing Qwen2ForCausalLM: ['model.layers.0.mlp.down_proj.bias', 'model.layers.0.mlp.gate_proj.bias', 'model.layers.0.mlp.up_proj.bias', 'model.layers.0.self_attn.o_proj.bias', 'model.layers.1.mlp.down_proj.bias', 'model.layers.1.mlp.gate_proj.bias', 'model.layers.1.mlp.up_proj.bias', 'model.layers.1.self_attn.o_proj.bias', 'model.layers.10.mlp.down_proj.bias', 'model.layers.10.mlp.gate_proj.bias', 'model.layers.10.mlp.up_proj.bias', 'model.layers.10.self_attn.o_proj.bias', 'model.layers.11.mlp.down_proj.bias', 'model.layers.11.mlp.gate_proj.bias', 'model.layers.11.mlp.up_proj.bias', 'model.layers.11.self_attn.o_proj.bias', 'model.layers.12.mlp.down_proj.bias', 'model.layers.12.mlp.gate_proj.bias', 'model.layers.12.mlp.up_proj.bias', 'model.layers.12.self_attn.o_proj.bias', 'model.layers.13.mlp.down_proj.bias', 'model.layers.13.mlp.gate_proj.bias', 'model.layers.13.mlp.up_proj.bias', 'model.layers.13.self_attn.o_proj.bias', 'model.layers.14.mlp.down_proj.bias', 'model.layers.14.mlp.gate_proj.bias', 'model.layers.14.mlp.up_proj.bias', 'model.layers.14.self_attn.o_proj.bias', 'model.layers.15.mlp.down_proj.bias', 'model.layers.15.mlp.gate_proj.bias', 'model.layers.15.mlp.up_proj.bias', 'model.layers.15.self_attn.o_proj.bias', 'model.layers.16.mlp.down_proj.bias', 'model.layers.16.mlp.gate_proj.bias', 'model.layers.16.mlp.up_proj.bias', 'model.layers.16.self_attn.o_proj.bias', 'model.layers.17.mlp.down_proj.bias', 'model.layers.17.mlp.gate_proj.bias', 'model.layers.17.mlp.up_proj.bias', 'model.layers.17.self_attn.o_proj.bias', 'model.layers.18.mlp.down_proj.bias', 'model.layers.18.mlp.gate_proj.bias', 'model.layers.18.mlp.up_proj.bias', 'model.layers.18.self_attn.o_proj.bias', 'model.layers.19.mlp.down_proj.bias', 'model.layers.19.mlp.gate_proj.bias', 'model.layers.19.mlp.up_proj.bias', 'model.layers.19.self_attn.o_proj.bias', 'model.layers.2.mlp.down_proj.bias', 'model.layers.2.mlp.gate_proj.bias', 'model.layers.2.mlp.up_proj.bias', 'model.layers.2.self_attn.o_proj.bias', 'model.layers.20.mlp.down_proj.bias', 'model.layers.20.mlp.gate_proj.bias', 'model.layers.20.mlp.up_proj.bias', 'model.layers.20.self_attn.o_proj.bias', 'model.layers.21.mlp.down_proj.bias', 'model.layers.21.mlp.gate_proj.bias', 'model.layers.21.mlp.up_proj.bias', 'model.layers.21.self_attn.o_proj.bias', 'model.layers.22.mlp.down_proj.bias', 'model.layers.22.mlp.gate_proj.bias', 'model.layers.22.mlp.up_proj.bias', 'model.layers.22.self_attn.o_proj.bias', 'model.layers.23.mlp.down_proj.bias', 'model.layers.23.mlp.gate_proj.bias', 'model.layers.23.mlp.up_proj.bias', 'model.layers.23.self_attn.o_proj.bias', 'model.layers.24.mlp.down_proj.bias', 'model.layers.24.mlp.gate_proj.bias', 'model.layers.24.mlp.up_proj.bias', 'model.layers.24.self_attn.o_proj.bias', 'model.layers.25.mlp.down_proj.bias', 'model.layers.25.mlp.gate_proj.bias', 'model.layers.25.mlp.up_proj.bias', 'model.layers.25.self_attn.o_proj.bias', 'model.layers.26.mlp.down_proj.bias', 'model.layers.26.mlp.gate_proj.bias', 'model.layers.26.mlp.up_proj.bias', 'model.layers.26.self_attn.o_proj.bias', 'model.layers.27.mlp.down_proj.bias', 'model.layers.27.mlp.gate_proj.bias', 'model.layers.27.mlp.up_proj.bias', 'model.layers.27.self_attn.o_proj.bias', 'model.layers.3.mlp.down_proj.bias', 'model.layers.3.mlp.gate_proj.bias', 'model.layers.3.mlp.up_proj.bias', 'model.layers.3.self_attn.o_proj.bias', 'model.layers.4.mlp.down_proj.bias', 'model.layers.4.mlp.gate_proj.bias', 'model.layers.4.mlp.up_proj.bias', 'model.layers.4.self_attn.o_proj.bias', 'model.layers.5.mlp.down_proj.bias', 'model.layers.5.mlp.gate_proj.bias', 'model.layers.5.mlp.up_proj.bias', 'model.layers.5.self_attn.o_proj.bias', 'model.layers.6.mlp.down_proj.bias', 'model.layers.6.mlp.gate_proj.bias', 'model.layers.6.mlp.up_proj.bias', 'model.layers.6.self_attn.o_proj.bias', 'model.layers.7.mlp.down_proj.bias', 'model.layers.7.mlp.gate_proj.bias', 'model.layers.7.mlp.up_proj.bias', 'model.layers.7.self_attn.o_proj.bias', 'model.layers.8.mlp.down_proj.bias', 'model.layers.8.mlp.gate_proj.bias', 'model.layers.8.mlp.up_proj.bias', 'model.layers.8.self_attn.o_proj.bias', 'model.layers.9.mlp.down_proj.bias', 'model.layers.9.mlp.gate_proj.bias', 'model.layers.9.mlp.up_proj.bias', 'model.layers.9.self_attn.o_proj.bias']
+- This IS expected if you are initializing Qwen2ForCausalLM from the checkpoint of a model trained on another task or with another architecture (e.g. initializing a BertForSequenceClassification model from a BertForPreTraining model).
+- This IS NOT expected if you are initializing Qwen2ForCausalLM from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model).
+
+06/06/2024 20:46:41 - INFO - transformers.modeling_utils - All the weights of Qwen2ForCausalLM were initialized from the model checkpoint at Qwen/Qwen2-7B-Instruct-GPTQ-Int8.
+If your task is similar to the task the model of the checkpoint was trained on, you can already use Qwen2ForCausalLM for predictions without further training.
+
+06/06/2024 20:46:41 - INFO - transformers.generation.configuration_utils - loading configuration file generation_config.json from cache at /home/zeus/.cache/huggingface/hub/models--Qwen--Qwen2-7B-Instruct-GPTQ-Int8/snapshots/22d9ef924dfae7700c4b620be6600d5c7ea31f88/generation_config.json
+
+06/06/2024 20:46:41 - INFO - transformers.generation.configuration_utils - Generate config GenerationConfig {
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.05,
+  "top_p": 0.8
+}
+
+
+06/06/2024 20:46:41 - INFO - llamafactory.model.model_utils.checkpointing - Gradient checkpointing enabled.
+
+06/06/2024 20:46:41 - INFO - llamafactory.model.model_utils.attention - Using torch SDPA for faster training and inference.
+
+06/06/2024 20:46:41 - INFO - llamafactory.model.adapter - Upcasting trainable params to float32.
+
+06/06/2024 20:46:41 - INFO - llamafactory.model.adapter - Fine-tuning method: LoRA
+
+06/06/2024 20:46:41 - INFO - llamafactory.model.model_utils.misc - Found linear modules: q_proj,o_proj,k_proj,gate_proj,down_proj,up_proj,v_proj
+
+06/06/2024 20:46:42 - INFO - llamafactory.model.loader - trainable params: 20185088 || all params: 1110384128 || trainable%: 1.8178
+
+06/06/2024 20:46:42 - INFO - transformers.trainer - Using auto half precision backend
+
+06/06/2024 20:46:42 - INFO - transformers.trainer - ***** Running training *****
+
+06/06/2024 20:46:42 - INFO - transformers.trainer -   Num examples = 9,600
+
+06/06/2024 20:46:42 - INFO - transformers.trainer -   Num Epochs = 3
+
+06/06/2024 20:46:42 - INFO - transformers.trainer -   Instantaneous batch size per device = 2
+
+06/06/2024 20:46:42 - INFO - transformers.trainer -   Total train batch size (w. parallel, distributed & accumulation) = 16
+
+06/06/2024 20:46:42 - INFO - transformers.trainer -   Gradient Accumulation steps = 8
+
+06/06/2024 20:46:42 - INFO - transformers.trainer -   Total optimization steps = 1,800
+
+06/06/2024 20:46:42 - INFO - transformers.trainer -   Number of trainable parameters = 20,185,088
+
+06/06/2024 20:48:17 - INFO - llamafactory.extras.callbacks - {'loss': 0.4212, 'learning_rate': 4.9999e-05, 'epoch': 0.01, 'throughput': 317.96}
+
+06/06/2024 20:49:49 - INFO - llamafactory.extras.callbacks - {'loss': 0.2803, 'learning_rate': 4.9996e-05, 'epoch': 0.02, 'throughput': 307.70}
+
+06/06/2024 20:51:24 - INFO - llamafactory.extras.callbacks - {'loss': 0.1484, 'learning_rate': 4.9991e-05, 'epoch': 0.03, 'throughput': 305.82}
+
+06/06/2024 20:52:54 - INFO - llamafactory.extras.callbacks - {'loss': 0.1151, 'learning_rate': 4.9985e-05, 'epoch': 0.03, 'throughput': 297.64}
+
+06/06/2024 20:54:29 - INFO - llamafactory.extras.callbacks - {'loss': 0.0751, 'learning_rate': 4.9976e-05, 'epoch': 0.04, 'throughput': 297.62}
+
+06/06/2024 20:56:07 - INFO - llamafactory.extras.callbacks - {'loss': 0.0471, 'learning_rate': 4.9966e-05, 'epoch': 0.05, 'throughput': 300.36}
+
+06/06/2024 20:57:47 - INFO - llamafactory.extras.callbacks - {'loss': 0.0368, 'learning_rate': 4.9953e-05, 'epoch': 0.06, 'throughput': 303.39}
+
+06/06/2024 20:59:22 - INFO - llamafactory.extras.callbacks - {'loss': 0.0311, 'learning_rate': 4.9939e-05, 'epoch': 0.07, 'throughput': 302.60}
+
+06/06/2024 21:00:58 - INFO - llamafactory.extras.callbacks - {'loss': 0.0262, 'learning_rate': 4.9923e-05, 'epoch': 0.07, 'throughput': 302.73}
+
+06/06/2024 21:02:36 - INFO - llamafactory.extras.callbacks - {'loss': 0.0244, 'learning_rate': 4.9905e-05, 'epoch': 0.08, 'throughput': 303.83}
+
+06/06/2024 21:04:11 - INFO - llamafactory.extras.callbacks - {'loss': 0.0266, 'learning_rate': 4.9885e-05, 'epoch': 0.09, 'throughput': 303.09}
+
+06/06/2024 21:05:46 - INFO - llamafactory.extras.callbacks - {'loss': 0.0283, 'learning_rate': 4.9868e-05, 'epoch': 0.10, 'throughput': 300.01}
+
+06/06/2024 21:07:21 - INFO - llamafactory.extras.callbacks - {'loss': 0.0265, 'learning_rate': 4.9844e-05, 'epoch': 0.11, 'throughput': 299.96}
+
+06/06/2024 21:08:54 - INFO - llamafactory.extras.callbacks - {'loss': 0.0235, 'learning_rate': 4.9819e-05, 'epoch': 0.12, 'throughput': 299.39}
+
+06/06/2024 21:10:28 - INFO - llamafactory.extras.callbacks - {'loss': 0.0229, 'learning_rate': 4.9792e-05, 'epoch': 0.12, 'throughput': 299.15}
+
+06/06/2024 21:12:01 - INFO - llamafactory.extras.callbacks - {'loss': 0.0238, 'learning_rate': 4.9763e-05, 'epoch': 0.13, 'throughput': 298.31}
+
+06/06/2024 21:13:35 - INFO - llamafactory.extras.callbacks - {'loss': 0.0208, 'learning_rate': 4.9732e-05, 'epoch': 0.14, 'throughput': 298.24}
+
+06/06/2024 21:15:11 - INFO - llamafactory.extras.callbacks - {'loss': 0.0191, 'learning_rate': 4.9699e-05, 'epoch': 0.15, 'throughput': 298.57}
+
+06/06/2024 21:16:43 - INFO - llamafactory.extras.callbacks - {'loss': 0.0205, 'learning_rate': 4.9664e-05, 'epoch': 0.16, 'throughput': 298.01}
+
+06/06/2024 21:18:20 - INFO - llamafactory.extras.callbacks - {'loss': 0.0193, 'learning_rate': 4.9628e-05, 'epoch': 0.17, 'throughput': 298.56}
+
+06/06/2024 21:18:20 - INFO - transformers.trainer - Saving model checkpoint to saves/Qwen2-7B-int8-Chat/lora/train_2024-06-06-20-45-21/checkpoint-100
+
+06/06/2024 21:18:20 - INFO - transformers.configuration_utils - loading configuration file config.json from cache at /home/zeus/.cache/huggingface/hub/models--Qwen--Qwen2-7B-Instruct-GPTQ-Int8/snapshots/22d9ef924dfae7700c4b620be6600d5c7ea31f88/config.json
+
+06/06/2024 21:18:20 - INFO - transformers.configuration_utils - Model config Qwen2Config {
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "quantization_config": {
+    "batch_size": 1,
+    "bits": 8,
+    "block_name_to_quantize": null,
+    "cache_block_outputs": true,
+    "damp_percent": 0.1,
+    "dataset": null,
+    "desc_act": false,
+    "exllama_config": {
+      "version": 1
+    },
+    "group_size": 128,
+    "max_input_length": null,
+    "model_seqlen": null,
+    "module_name_preceding_first_block": null,
+    "modules_in_block_to_quantize": null,
+    "pad_token_id": null,
+    "quant_method": "gptq",
+    "sym": true,
+    "tokenizer": null,
+    "true_sequential": true,
+    "use_cuda_fp16": false,
+    "use_exllama": true
+  },
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 1000000.0,
+  "sliding_window": 131072,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.41.2",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}
+
+
+06/06/2024 21:18:20 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in saves/Qwen2-7B-int8-Chat/lora/train_2024-06-06-20-45-21/checkpoint-100/tokenizer_config.json
+
+06/06/2024 21:18:20 - INFO - transformers.tokenization_utils_base - Special tokens file saved in saves/Qwen2-7B-int8-Chat/lora/train_2024-06-06-20-45-21/checkpoint-100/special_tokens_map.json
+
+06/06/2024 21:19:53 - INFO - llamafactory.extras.callbacks - {'loss': 0.0240, 'learning_rate': 4.9589e-05, 'epoch': 0.17, 'throughput': 298.12}
+
+06/06/2024 21:21:27 - INFO - llamafactory.extras.callbacks - {'loss': 0.0206, 'learning_rate': 4.9549e-05, 'epoch': 0.18, 'throughput': 297.89}
+
+06/06/2024 21:22:59 - INFO - llamafactory.extras.callbacks - {'loss': 0.0188, 'learning_rate': 4.9507e-05, 'epoch': 0.19, 'throughput': 297.43}
+
+06/06/2024 21:24:35 - INFO - llamafactory.extras.callbacks - {'loss': 0.0183, 'learning_rate': 4.9463e-05, 'epoch': 0.20, 'throughput': 297.64}
+
+06/06/2024 21:26:04 - INFO - llamafactory.extras.callbacks - {'loss': 0.0189, 'learning_rate': 4.9417e-05, 'epoch': 0.21, 'throughput': 297.06}
+
+06/06/2024 21:27:40 - INFO - llamafactory.extras.callbacks - {'loss': 0.0213, 'learning_rate': 4.9369e-05, 'epoch': 0.22, 'throughput': 297.53}
+
+06/06/2024 21:29:12 - INFO - llamafactory.extras.callbacks - {'loss': 0.0214, 'learning_rate': 4.9319e-05, 'epoch': 0.23, 'throughput': 297.22}
+
+06/06/2024 21:30:47 - INFO - llamafactory.extras.callbacks - {'loss': 0.0214, 'learning_rate': 4.9268e-05, 'epoch': 0.23, 'throughput': 297.22}
+
+06/06/2024 21:32:22 - INFO - llamafactory.extras.callbacks - {'loss': 0.0203, 'learning_rate': 4.9215e-05, 'epoch': 0.24, 'throughput': 297.36}
+
+06/06/2024 21:33:56 - INFO - llamafactory.extras.callbacks - {'loss': 0.0194, 'learning_rate': 4.9159e-05, 'epoch': 0.25, 'throughput': 297.35}
+
+06/06/2024 21:35:27 - INFO - llamafactory.extras.callbacks - {'loss': 0.0158, 'learning_rate': 4.9102e-05, 'epoch': 0.26, 'throughput': 296.96}
+
+06/06/2024 21:37:01 - INFO - llamafactory.extras.callbacks - {'loss': 0.0172, 'learning_rate': 4.9044e-05, 'epoch': 0.27, 'throughput': 296.94}
+
+06/06/2024 21:38:35 - INFO - llamafactory.extras.callbacks - {'loss': 0.0193, 'learning_rate': 4.8983e-05, 'epoch': 0.28, 'throughput': 297.06}
+
+06/06/2024 21:40:13 - INFO - llamafactory.extras.callbacks - {'loss': 0.0189, 'learning_rate': 4.8920e-05, 'epoch': 0.28, 'throughput': 297.62}
+
+06/06/2024 21:41:49 - INFO - llamafactory.extras.callbacks - {'loss': 0.0190, 'learning_rate': 4.8856e-05, 'epoch': 0.29, 'throughput': 297.91}
+
+06/06/2024 21:43:23 - INFO - llamafactory.extras.callbacks - {'loss': 0.0168, 'learning_rate': 4.8790e-05, 'epoch': 0.30, 'throughput': 297.99}
+
+06/06/2024 21:45:00 - INFO - llamafactory.extras.callbacks - {'loss': 0.0194, 'learning_rate': 4.8722e-05, 'epoch': 0.31, 'throughput': 298.39}
+
+06/06/2024 21:46:33 - INFO - llamafactory.extras.callbacks - {'loss': 0.0155, 'learning_rate': 4.8652e-05, 'epoch': 0.32, 'throughput': 298.24}
+
+06/06/2024 21:48:05 - INFO - llamafactory.extras.callbacks - {'loss': 0.0193, 'learning_rate': 4.8581e-05, 'epoch': 0.33, 'throughput': 298.10}
+
+06/06/2024 21:49:40 - INFO - llamafactory.extras.callbacks - {'loss': 0.0164, 'learning_rate': 4.8507e-05, 'epoch': 0.33, 'throughput': 298.12}
+
+06/06/2024 21:49:40 - INFO - transformers.trainer - Saving model checkpoint to saves/Qwen2-7B-int8-Chat/lora/train_2024-06-06-20-45-21/checkpoint-200
+
+06/06/2024 21:49:40 - INFO - transformers.configuration_utils - loading configuration file config.json from cache at /home/zeus/.cache/huggingface/hub/models--Qwen--Qwen2-7B-Instruct-GPTQ-Int8/snapshots/22d9ef924dfae7700c4b620be6600d5c7ea31f88/config.json
+
+06/06/2024 21:49:40 - INFO - transformers.configuration_utils - Model config Qwen2Config {
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "quantization_config": {
+    "batch_size": 1,
+    "bits": 8,
+    "block_name_to_quantize": null,
+    "cache_block_outputs": true,
+    "damp_percent": 0.1,
+    "dataset": null,
+    "desc_act": false,
+    "exllama_config": {
+      "version": 1
+    },
+    "group_size": 128,
+    "max_input_length": null,
+    "model_seqlen": null,
+    "module_name_preceding_first_block": null,
+    "modules_in_block_to_quantize": null,
+    "pad_token_id": null,
+    "quant_method": "gptq",
+    "sym": true,
+    "tokenizer": null,
+    "true_sequential": true,
+    "use_cuda_fp16": false,
+    "use_exllama": true
+  },
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 1000000.0,
+  "sliding_window": 131072,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.41.2",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}
+
+
+06/06/2024 21:49:40 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in saves/Qwen2-7B-int8-Chat/lora/train_2024-06-06-20-45-21/checkpoint-200/tokenizer_config.json
+
+06/06/2024 21:49:40 - INFO - transformers.tokenization_utils_base - Special tokens file saved in saves/Qwen2-7B-int8-Chat/lora/train_2024-06-06-20-45-21/checkpoint-200/special_tokens_map.json
+
+06/06/2024 21:51:18 - INFO - llamafactory.extras.callbacks - {'loss': 0.0140, 'learning_rate': 4.8432e-05, 'epoch': 0.34, 'throughput': 298.66}
+
+06/06/2024 21:52:51 - INFO - llamafactory.extras.callbacks - {'loss': 0.0154, 'learning_rate': 4.8355e-05, 'epoch': 0.35, 'throughput': 298.57}
+
+06/06/2024 21:54:25 - INFO - llamafactory.extras.callbacks - {'loss': 0.0147, 'learning_rate': 4.8276e-05, 'epoch': 0.36, 'throughput': 298.63}
+
+06/06/2024 21:55:59 - INFO - llamafactory.extras.callbacks - {'loss': 0.0185, 'learning_rate': 4.8196e-05, 'epoch': 0.37, 'throughput': 298.72}
+
+06/06/2024 21:57:34 - INFO - llamafactory.extras.callbacks - {'loss': 0.0160, 'learning_rate': 4.8114e-05, 'epoch': 0.38, 'throughput': 298.74}
+
+06/06/2024 21:59:07 - INFO - llamafactory.extras.callbacks - {'loss': 0.0168, 'learning_rate': 4.8030e-05, 'epoch': 0.38, 'throughput': 298.65}
+
+06/06/2024 22:00:38 - INFO - llamafactory.extras.callbacks - {'loss': 0.0154, 'learning_rate': 4.7944e-05, 'epoch': 0.39, 'throughput': 298.39}
+
+06/06/2024 22:02:21 - INFO - llamafactory.extras.callbacks - {'loss': 0.0149, 'learning_rate': 4.7856e-05, 'epoch': 0.40, 'throughput': 299.32}
+
+06/06/2024 22:03:05 - INFO - transformers.trainer - 
+
+Training completed. Do not forget to share your model on huggingface.co/models =)
+
+
+
+06/06/2024 22:03:05 - INFO - transformers.trainer - Saving model checkpoint to saves/Qwen2-7B-int8-Chat/lora/train_2024-06-06-20-45-21
+
+06/06/2024 22:03:06 - INFO - transformers.configuration_utils - loading configuration file config.json from cache at /home/zeus/.cache/huggingface/hub/models--Qwen--Qwen2-7B-Instruct-GPTQ-Int8/snapshots/22d9ef924dfae7700c4b620be6600d5c7ea31f88/config.json
+
+06/06/2024 22:03:06 - INFO - transformers.configuration_utils - Model config Qwen2Config {
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "quantization_config": {
+    "batch_size": 1,
+    "bits": 8,
+    "block_name_to_quantize": null,
+    "cache_block_outputs": true,
+    "damp_percent": 0.1,
+    "dataset": null,
+    "desc_act": false,
+    "exllama_config": {
+      "version": 1
+    },
+    "group_size": 128,
+    "max_input_length": null,
+    "model_seqlen": null,
+    "module_name_preceding_first_block": null,
+    "modules_in_block_to_quantize": null,
+    "pad_token_id": null,
+    "quant_method": "gptq",
+    "sym": true,
+    "tokenizer": null,
+    "true_sequential": true,
+    "use_cuda_fp16": false,
+    "use_exllama": true
+  },
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 1000000.0,
+  "sliding_window": 131072,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.41.2",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}
+
+
+06/06/2024 22:03:06 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in saves/Qwen2-7B-int8-Chat/lora/train_2024-06-06-20-45-21/tokenizer_config.json
+
+06/06/2024 22:03:06 - INFO - transformers.tokenization_utils_base - Special tokens file saved in saves/Qwen2-7B-int8-Chat/lora/train_2024-06-06-20-45-21/special_tokens_map.json
+
+06/06/2024 22:03:06 - WARNING - llamafactory.extras.ploting - No metric eval_loss to plot.
+
+06/06/2024 22:03:06 - INFO - transformers.modelcard - Dropping the following result as it does not have all the necessary fields:
+{'task': {'name': 'Causal Language Modeling', 'type': 'text-generation'}}
+

special_tokens_map.json

@@ -0,0 +1,20 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "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_config.json

@@ -0,0 +1,44 @@
+{
+  "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": "{% set system_message = 'You are a helpful assistant.' %}{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ '<|im_start|>system\n' + system_message + '<|im_end|>\n' }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|im_start|>user\n' + content + '<|im_end|>\n<|im_start|>assistant\n' }}{% elif message['role'] == 'assistant' %}{{ content + '<|im_end|>' + '\n' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 0.4033333333333333,
+    "num_input_tokens_seen": 1371584,
+    "total_flos": 4652852538507264.0,
+    "train_loss": 0.040362141964849364,
+    "train_runtime": 4583.2214,
+    "train_samples_per_second": 6.284,
+    "train_steps_per_second": 0.393
+}

trainer_config.yaml

@@ -0,0 +1,33 @@
+cutoff_len: 1024
+dataset: train
+dataset_dir: data
+ddp_timeout: 180000000
+do_train: true
+finetuning_type: lora
+flash_attn: fa2
+fp16: true
+gradient_accumulation_steps: 8
+include_num_input_tokens_seen: true
+learning_rate: 5.0e-05
+logging_steps: 5
+lora_alpha: 16
+lora_dropout: 0
+lora_rank: 8
+lora_target: all
+lr_scheduler_type: cosine
+max_grad_norm: 1.0
+max_samples: 100000
+model_name_or_path: Qwen/Qwen2-7B-Instruct-GPTQ-Int8
+num_train_epochs: 3.0
+optim: adamw_torch
+output_dir: saves/Qwen2-7B-int8-Chat/lora/train_2024-06-06-20-45-21
+packing: false
+per_device_train_batch_size: 2
+plot_loss: true
+preprocessing_num_workers: 16
+quantization_bit: 8
+report_to: none
+save_steps: 100
+stage: sft
+template: qwen
+warmup_steps: 0

trainer_log.jsonl

@@ -0,0 +1,49 @@
+{"current_steps": 5, "total_steps": 1800, "loss": 0.4212, "learning_rate": 4.999904807660428e-05, "epoch": 0.008333333333333333, "percentage": 0.28, "elapsed_time": "0:01:34", "remaining_time": "9:25:43", "throughput": "317.96", "total_tokens": 30064}
+{"current_steps": 10, "total_steps": 1800, "loss": 0.2803, "learning_rate": 4.9996192378909786e-05, "epoch": 0.016666666666666666, "percentage": 0.56, "elapsed_time": "0:03:06", "remaining_time": "9:16:17", "throughput": "307.70", "total_tokens": 57376}
+{"current_steps": 15, "total_steps": 1800, "loss": 0.1484, "learning_rate": 4.999143312438893e-05, "epoch": 0.025, "percentage": 0.83, "elapsed_time": "0:04:41", "remaining_time": "9:18:46", "throughput": "305.82", "total_tokens": 86160}
+{"current_steps": 20, "total_steps": 1800, "loss": 0.1151, "learning_rate": 4.99847706754774e-05, "epoch": 0.03333333333333333, "percentage": 1.11, "elapsed_time": "0:06:11", "remaining_time": "9:11:09", "throughput": "297.64", "total_tokens": 110592}
+{"current_steps": 25, "total_steps": 1800, "loss": 0.0751, "learning_rate": 4.997620553954645e-05, "epoch": 0.041666666666666664, "percentage": 1.39, "elapsed_time": "0:07:46", "remaining_time": "9:12:11", "throughput": "297.62", "total_tokens": 138880}
+{"current_steps": 30, "total_steps": 1800, "loss": 0.0471, "learning_rate": 4.996573836886435e-05, "epoch": 0.05, "percentage": 1.67, "elapsed_time": "0:09:24", "remaining_time": "9:15:14", "throughput": "300.36", "total_tokens": 169600}
+{"current_steps": 35, "total_steps": 1800, "loss": 0.0368, "learning_rate": 4.9953369960546676e-05, "epoch": 0.058333333333333334, "percentage": 1.94, "elapsed_time": "0:11:04", "remaining_time": "9:18:40", "throughput": "303.39", "total_tokens": 201664}
+{"current_steps": 40, "total_steps": 1800, "loss": 0.0311, "learning_rate": 4.993910125649561e-05, "epoch": 0.06666666666666667, "percentage": 2.22, "elapsed_time": "0:12:39", "remaining_time": "9:17:14", "throughput": "302.60", "total_tokens": 229936}
+{"current_steps": 45, "total_steps": 1800, "loss": 0.0262, "learning_rate": 4.99229333433282e-05, "epoch": 0.075, "percentage": 2.5, "elapsed_time": "0:14:15", "remaining_time": "9:16:17", "throughput": "302.73", "total_tokens": 259088}
+{"current_steps": 50, "total_steps": 1800, "loss": 0.0244, "learning_rate": 4.990486745229364e-05, "epoch": 0.08333333333333333, "percentage": 2.78, "elapsed_time": "0:15:53", "remaining_time": "9:16:27", "throughput": "303.83", "total_tokens": 289824}
+{"current_steps": 55, "total_steps": 1800, "loss": 0.0266, "learning_rate": 4.988490495917947e-05, "epoch": 0.09166666666666666, "percentage": 3.06, "elapsed_time": "0:17:28", "remaining_time": "9:14:23", "throughput": "303.09", "total_tokens": 317760}
+{"current_steps": 60, "total_steps": 1800, "loss": 0.0283, "learning_rate": 4.9867570427929354e-05, "epoch": 0.1, "percentage": 3.33, "elapsed_time": "0:19:03", "remaining_time": "9:12:47", "throughput": "300.01", "total_tokens": 343120}
+{"current_steps": 65, "total_steps": 1800, "loss": 0.0265, "learning_rate": 4.984419797901491e-05, "epoch": 0.10833333333333334, "percentage": 3.61, "elapsed_time": "0:20:38", "remaining_time": "9:11:06", "throughput": "299.96", "total_tokens": 371600}
+{"current_steps": 70, "total_steps": 1800, "loss": 0.0235, "learning_rate": 4.981893354823614e-05, "epoch": 0.11666666666666667, "percentage": 3.89, "elapsed_time": "0:22:11", "remaining_time": "9:08:34", "throughput": "299.39", "total_tokens": 398720}
+{"current_steps": 75, "total_steps": 1800, "loss": 0.0229, "learning_rate": 4.979177905957726e-05, "epoch": 0.125, "percentage": 4.17, "elapsed_time": "0:23:45", "remaining_time": "9:06:24", "throughput": "299.15", "total_tokens": 426416}
+{"current_steps": 80, "total_steps": 1800, "loss": 0.0238, "learning_rate": 4.976273658095772e-05, "epoch": 0.13333333333333333, "percentage": 4.44, "elapsed_time": "0:25:18", "remaining_time": "9:04:05", "throughput": "298.31", "total_tokens": 452944}
+{"current_steps": 85, "total_steps": 1800, "loss": 0.0208, "learning_rate": 4.9731808324074717e-05, "epoch": 0.14166666666666666, "percentage": 4.72, "elapsed_time": "0:26:52", "remaining_time": "9:02:13", "throughput": "298.24", "total_tokens": 480896}
+{"current_steps": 90, "total_steps": 1800, "loss": 0.0191, "learning_rate": 4.969899664423473e-05, "epoch": 0.15, "percentage": 5.0, "elapsed_time": "0:28:28", "remaining_time": "9:01:00", "throughput": "298.57", "total_tokens": 510096}
+{"current_steps": 95, "total_steps": 1800, "loss": 0.0205, "learning_rate": 4.966430404017424e-05, "epoch": 0.15833333333333333, "percentage": 5.28, "elapsed_time": "0:30:00", "remaining_time": "8:58:40", "throughput": "298.01", "total_tokens": 536672}
+{"current_steps": 100, "total_steps": 1800, "loss": 0.0193, "learning_rate": 4.962773315386935e-05, "epoch": 0.16666666666666666, "percentage": 5.56, "elapsed_time": "0:31:37", "remaining_time": "8:57:37", "throughput": "298.56", "total_tokens": 566528}
+{"current_steps": 105, "total_steps": 1800, "loss": 0.024, "learning_rate": 4.9589286770334654e-05, "epoch": 0.175, "percentage": 5.83, "elapsed_time": "0:33:11", "remaining_time": "8:55:41", "throughput": "298.12", "total_tokens": 593584}
+{"current_steps": 110, "total_steps": 1800, "loss": 0.0206, "learning_rate": 4.954896781741109e-05, "epoch": 0.18333333333333332, "percentage": 6.11, "elapsed_time": "0:34:44", "remaining_time": "8:53:47", "throughput": "297.89", "total_tokens": 620992}
+{"current_steps": 115, "total_steps": 1800, "loss": 0.0188, "learning_rate": 4.9506779365543046e-05, "epoch": 0.19166666666666668, "percentage": 6.39, "elapsed_time": "0:36:17", "remaining_time": "8:51:38", "throughput": "297.43", "total_tokens": 647504}
+{"current_steps": 120, "total_steps": 1800, "loss": 0.0183, "learning_rate": 4.9462724627544466e-05, "epoch": 0.2, "percentage": 6.67, "elapsed_time": "0:37:52", "remaining_time": "8:50:12", "throughput": "297.64", "total_tokens": 676336}
+{"current_steps": 125, "total_steps": 1800, "loss": 0.0189, "learning_rate": 4.94168069583542e-05, "epoch": 0.20833333333333334, "percentage": 6.94, "elapsed_time": "0:39:21", "remaining_time": "8:47:22", "throughput": "297.06", "total_tokens": 701488}
+{"current_steps": 130, "total_steps": 1800, "loss": 0.0213, "learning_rate": 4.936902985478055e-05, "epoch": 0.21666666666666667, "percentage": 7.22, "elapsed_time": "0:40:57", "remaining_time": "8:46:08", "throughput": "297.53", "total_tokens": 731152}
+{"current_steps": 135, "total_steps": 1800, "loss": 0.0214, "learning_rate": 4.931939695523492e-05, "epoch": 0.225, "percentage": 7.5, "elapsed_time": "0:42:29", "remaining_time": "8:44:04", "throughput": "297.22", "total_tokens": 757792}
+{"current_steps": 140, "total_steps": 1800, "loss": 0.0214, "learning_rate": 4.926791203945477e-05, "epoch": 0.23333333333333334, "percentage": 7.78, "elapsed_time": "0:44:04", "remaining_time": "8:42:39", "throughput": "297.22", "total_tokens": 786064}
+{"current_steps": 145, "total_steps": 1800, "loss": 0.0203, "learning_rate": 4.9214579028215776e-05, "epoch": 0.24166666666666667, "percentage": 8.06, "elapsed_time": "0:45:39", "remaining_time": "8:41:09", "throughput": "297.36", "total_tokens": 814640}
+{"current_steps": 150, "total_steps": 1800, "loss": 0.0194, "learning_rate": 4.915940198303324e-05, "epoch": 0.25, "percentage": 8.33, "elapsed_time": "0:47:13", "remaining_time": "8:39:32", "throughput": "297.35", "total_tokens": 842656}
+{"current_steps": 155, "total_steps": 1800, "loss": 0.0158, "learning_rate": 4.910238510585276e-05, "epoch": 0.25833333333333336, "percentage": 8.61, "elapsed_time": "0:48:44", "remaining_time": "8:37:19", "throughput": "296.96", "total_tokens": 868512}
+{"current_steps": 160, "total_steps": 1800, "loss": 0.0172, "learning_rate": 4.9043532738730284e-05, "epoch": 0.26666666666666666, "percentage": 8.89, "elapsed_time": "0:50:18", "remaining_time": "8:35:43", "throughput": "296.94", "total_tokens": 896416}
+{"current_steps": 165, "total_steps": 1800, "loss": 0.0193, "learning_rate": 4.898284936350144e-05, "epoch": 0.275, "percentage": 9.17, "elapsed_time": "0:51:52", "remaining_time": "8:34:06", "throughput": "297.06", "total_tokens": 924720}
+{"current_steps": 170, "total_steps": 1800, "loss": 0.0189, "learning_rate": 4.892033960144019e-05, "epoch": 0.2833333333333333, "percentage": 9.44, "elapsed_time": "0:53:30", "remaining_time": "8:33:05", "throughput": "297.62", "total_tokens": 955584}
+{"current_steps": 175, "total_steps": 1800, "loss": 0.019, "learning_rate": 4.8856008212906925e-05, "epoch": 0.2916666666666667, "percentage": 9.72, "elapsed_time": "0:55:06", "remaining_time": "8:31:43", "throughput": "297.91", "total_tokens": 985072}
+{"current_steps": 180, "total_steps": 1800, "loss": 0.0168, "learning_rate": 4.878986009698596e-05, "epoch": 0.3, "percentage": 10.0, "elapsed_time": "0:56:40", "remaining_time": "8:30:03", "throughput": "297.99", "total_tokens": 1013296}
+{"current_steps": 185, "total_steps": 1800, "loss": 0.0194, "learning_rate": 4.8721900291112415e-05, "epoch": 0.30833333333333335, "percentage": 10.28, "elapsed_time": "0:58:17", "remaining_time": "8:28:53", "throughput": "298.39", "total_tokens": 1043664}
+{"current_steps": 190, "total_steps": 1800, "loss": 0.0155, "learning_rate": 4.8652133970688636e-05, "epoch": 0.31666666666666665, "percentage": 10.56, "elapsed_time": "0:59:50", "remaining_time": "8:27:07", "throughput": "298.24", "total_tokens": 1070912}
+{"current_steps": 195, "total_steps": 1800, "loss": 0.0193, "learning_rate": 4.858056644869002e-05, "epoch": 0.325, "percentage": 10.83, "elapsed_time": "1:01:22", "remaining_time": "8:25:12", "throughput": "298.10", "total_tokens": 1097856}
+{"current_steps": 200, "total_steps": 1800, "loss": 0.0164, "learning_rate": 4.850720317526047e-05, "epoch": 0.3333333333333333, "percentage": 11.11, "elapsed_time": "1:02:57", "remaining_time": "8:23:39", "throughput": "298.12", "total_tokens": 1126128}
+{"current_steps": 205, "total_steps": 1800, "loss": 0.014, "learning_rate": 4.843204973729729e-05, "epoch": 0.3416666666666667, "percentage": 11.39, "elapsed_time": "1:04:35", "remaining_time": "8:22:36", "throughput": "298.66", "total_tokens": 1157584}
+{"current_steps": 210, "total_steps": 1800, "loss": 0.0154, "learning_rate": 4.835511185802574e-05, "epoch": 0.35, "percentage": 11.67, "elapsed_time": "1:06:08", "remaining_time": "8:20:45", "throughput": "298.57", "total_tokens": 1184800}
+{"current_steps": 215, "total_steps": 1800, "loss": 0.0147, "learning_rate": 4.827639539656321e-05, "epoch": 0.35833333333333334, "percentage": 11.94, "elapsed_time": "1:07:42", "remaining_time": "8:19:07", "throughput": "298.63", "total_tokens": 1213104}
+{"current_steps": 220, "total_steps": 1800, "loss": 0.0185, "learning_rate": 4.8195906347473e-05, "epoch": 0.36666666666666664, "percentage": 12.22, "elapsed_time": "1:09:17", "remaining_time": "8:17:35", "throughput": "298.72", "total_tokens": 1241808}
+{"current_steps": 225, "total_steps": 1800, "loss": 0.016, "learning_rate": 4.8113650840307834e-05, "epoch": 0.375, "percentage": 12.5, "elapsed_time": "1:10:51", "remaining_time": "8:16:01", "throughput": "298.74", "total_tokens": 1270160}
+{"current_steps": 230, "total_steps": 1800, "loss": 0.0168, "learning_rate": 4.802963513914304e-05, "epoch": 0.38333333333333336, "percentage": 12.78, "elapsed_time": "1:12:24", "remaining_time": "8:14:14", "throughput": "298.65", "total_tokens": 1297456}
+{"current_steps": 235, "total_steps": 1800, "loss": 0.0154, "learning_rate": 4.794386564209953e-05, "epoch": 0.39166666666666666, "percentage": 13.06, "elapsed_time": "1:13:55", "remaining_time": "8:12:16", "throughput": "298.39", "total_tokens": 1323392}
+{"current_steps": 240, "total_steps": 1800, "loss": 0.0149, "learning_rate": 4.7856348880856595e-05, "epoch": 0.4, "percentage": 13.33, "elapsed_time": "1:15:38", "remaining_time": "8:11:43", "throughput": "299.32", "total_tokens": 1358576}
+{"current_steps": 242, "total_steps": 1800, "epoch": 0.4033333333333333, "percentage": 13.44, "elapsed_time": "1:16:23", "remaining_time": "8:11:46", "throughput": "299.27", "total_tokens": 1371584}

trainer_state.json

@@ -0,0 +1,427 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.4033333333333333,
+  "eval_steps": 500,
+  "global_step": 242,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.008333333333333333,
+      "grad_norm": 0.48900601267814636,
+      "learning_rate": 4.999904807660428e-05,
+      "loss": 0.4212,
+      "num_input_tokens_seen": 30064,
+      "step": 5
+    },
+    {
+      "epoch": 0.016666666666666666,
+      "grad_norm": 0.3595407009124756,
+      "learning_rate": 4.9996192378909786e-05,
+      "loss": 0.2803,
+      "num_input_tokens_seen": 57376,
+      "step": 10
+    },
+    {
+      "epoch": 0.025,
+      "grad_norm": 0.2623545527458191,
+      "learning_rate": 4.999143312438893e-05,
+      "loss": 0.1484,
+      "num_input_tokens_seen": 86160,
+      "step": 15
+    },
+    {
+      "epoch": 0.03333333333333333,
+      "grad_norm": 0.2743065357208252,
+      "learning_rate": 4.99847706754774e-05,
+      "loss": 0.1151,
+      "num_input_tokens_seen": 110592,
+      "step": 20
+    },
+    {
+      "epoch": 0.041666666666666664,
+      "grad_norm": 0.2651338577270508,
+      "learning_rate": 4.997620553954645e-05,
+      "loss": 0.0751,
+      "num_input_tokens_seen": 138880,
+      "step": 25
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 0.10798148065805435,
+      "learning_rate": 4.996573836886435e-05,
+      "loss": 0.0471,
+      "num_input_tokens_seen": 169600,
+      "step": 30
+    },
+    {
+      "epoch": 0.058333333333333334,
+      "grad_norm": 0.1552838534116745,
+      "learning_rate": 4.9953369960546676e-05,
+      "loss": 0.0368,
+      "num_input_tokens_seen": 201664,
+      "step": 35
+    },
+    {
+      "epoch": 0.06666666666666667,
+      "grad_norm": 0.11832074075937271,
+      "learning_rate": 4.993910125649561e-05,
+      "loss": 0.0311,
+      "num_input_tokens_seen": 229936,
+      "step": 40
+    },
+    {
+      "epoch": 0.075,
+      "grad_norm": 0.10593917220830917,
+      "learning_rate": 4.99229333433282e-05,
+      "loss": 0.0262,
+      "num_input_tokens_seen": 259088,
+      "step": 45
+    },
+    {
+      "epoch": 0.08333333333333333,
+      "grad_norm": 0.09650842100381851,
+      "learning_rate": 4.990486745229364e-05,
+      "loss": 0.0244,
+      "num_input_tokens_seen": 289824,
+      "step": 50
+    },
+    {
+      "epoch": 0.09166666666666666,
+      "grad_norm": 0.14155137538909912,
+      "learning_rate": 4.988490495917947e-05,
+      "loss": 0.0266,
+      "num_input_tokens_seen": 317760,
+      "step": 55
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.1490347981452942,
+      "learning_rate": 4.9867570427929354e-05,
+      "loss": 0.0283,
+      "num_input_tokens_seen": 343120,
+      "step": 60
+    },
+    {
+      "epoch": 0.10833333333333334,
+      "grad_norm": 0.17539122700691223,
+      "learning_rate": 4.984419797901491e-05,
+      "loss": 0.0265,
+      "num_input_tokens_seen": 371600,
+      "step": 65
+    },
+    {
+      "epoch": 0.11666666666666667,
+      "grad_norm": 0.1336919367313385,
+      "learning_rate": 4.981893354823614e-05,
+      "loss": 0.0235,
+      "num_input_tokens_seen": 398720,
+      "step": 70
+    },
+    {
+      "epoch": 0.125,
+      "grad_norm": 0.12203177809715271,
+      "learning_rate": 4.979177905957726e-05,
+      "loss": 0.0229,
+      "num_input_tokens_seen": 426416,
+      "step": 75
+    },
+    {
+      "epoch": 0.13333333333333333,
+      "grad_norm": 0.2557654082775116,
+      "learning_rate": 4.976273658095772e-05,
+      "loss": 0.0238,
+      "num_input_tokens_seen": 452944,
+      "step": 80
+    },
+    {
+      "epoch": 0.14166666666666666,
+      "grad_norm": 0.13327105343341827,
+      "learning_rate": 4.9731808324074717e-05,
+      "loss": 0.0208,
+      "num_input_tokens_seen": 480896,
+      "step": 85
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 0.1262751668691635,
+      "learning_rate": 4.969899664423473e-05,
+      "loss": 0.0191,
+      "num_input_tokens_seen": 510096,
+      "step": 90
+    },
+    {
+      "epoch": 0.15833333333333333,
+      "grad_norm": 0.16084067523479462,
+      "learning_rate": 4.966430404017424e-05,
+      "loss": 0.0205,
+      "num_input_tokens_seen": 536672,
+      "step": 95
+    },
+    {
+      "epoch": 0.16666666666666666,
+      "grad_norm": 0.15870437026023865,
+      "learning_rate": 4.962773315386935e-05,
+      "loss": 0.0193,
+      "num_input_tokens_seen": 566528,
+      "step": 100
+    },
+    {
+      "epoch": 0.175,
+      "grad_norm": 0.07833187282085419,
+      "learning_rate": 4.9589286770334654e-05,
+      "loss": 0.024,
+      "num_input_tokens_seen": 593584,
+      "step": 105
+    },
+    {
+      "epoch": 0.18333333333333332,
+      "grad_norm": 0.09176061302423477,
+      "learning_rate": 4.954896781741109e-05,
+      "loss": 0.0206,
+      "num_input_tokens_seen": 620992,
+      "step": 110
+    },
+    {
+      "epoch": 0.19166666666666668,
+      "grad_norm": 0.08285439014434814,
+      "learning_rate": 4.9506779365543046e-05,
+      "loss": 0.0188,
+      "num_input_tokens_seen": 647504,
+      "step": 115
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.13359522819519043,
+      "learning_rate": 4.9462724627544466e-05,
+      "loss": 0.0183,
+      "num_input_tokens_seen": 676336,
+      "step": 120
+    },
+    {
+      "epoch": 0.20833333333333334,
+      "grad_norm": 0.07570718228816986,
+      "learning_rate": 4.94168069583542e-05,
+      "loss": 0.0189,
+      "num_input_tokens_seen": 701488,
+      "step": 125
+    },
+    {
+      "epoch": 0.21666666666666667,
+      "grad_norm": 0.11286037415266037,
+      "learning_rate": 4.936902985478055e-05,
+      "loss": 0.0213,
+      "num_input_tokens_seen": 731152,
+      "step": 130
+    },
+    {
+      "epoch": 0.225,
+      "grad_norm": 0.17183929681777954,
+      "learning_rate": 4.931939695523492e-05,
+      "loss": 0.0214,
+      "num_input_tokens_seen": 757792,
+      "step": 135
+    },
+    {
+      "epoch": 0.23333333333333334,
+      "grad_norm": 0.11746834218502045,
+      "learning_rate": 4.926791203945477e-05,
+      "loss": 0.0214,
+      "num_input_tokens_seen": 786064,
+      "step": 140
+    },
+    {
+      "epoch": 0.24166666666666667,
+      "grad_norm": 0.09453292936086655,
+      "learning_rate": 4.9214579028215776e-05,
+      "loss": 0.0203,
+      "num_input_tokens_seen": 814640,
+      "step": 145
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 0.2074723094701767,
+      "learning_rate": 4.915940198303324e-05,
+      "loss": 0.0194,
+      "num_input_tokens_seen": 842656,
+      "step": 150
+    },
+    {
+      "epoch": 0.25833333333333336,
+      "grad_norm": 0.15371476113796234,
+      "learning_rate": 4.910238510585276e-05,
+      "loss": 0.0158,
+      "num_input_tokens_seen": 868512,
+      "step": 155
+    },
+    {
+      "epoch": 0.26666666666666666,
+      "grad_norm": 0.07177837193012238,
+      "learning_rate": 4.9043532738730284e-05,
+      "loss": 0.0172,
+      "num_input_tokens_seen": 896416,
+      "step": 160
+    },
+    {
+      "epoch": 0.275,
+      "grad_norm": 0.07891824096441269,
+      "learning_rate": 4.898284936350144e-05,
+      "loss": 0.0193,
+      "num_input_tokens_seen": 924720,
+      "step": 165
+    },
+    {
+      "epoch": 0.2833333333333333,
+      "grad_norm": 0.08302944153547287,
+      "learning_rate": 4.892033960144019e-05,
+      "loss": 0.0189,
+      "num_input_tokens_seen": 955584,
+      "step": 170
+    },
+    {
+      "epoch": 0.2916666666666667,
+      "grad_norm": 0.25554358959198,
+      "learning_rate": 4.8856008212906925e-05,
+      "loss": 0.019,
+      "num_input_tokens_seen": 985072,
+      "step": 175
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 0.1445908546447754,
+      "learning_rate": 4.878986009698596e-05,
+      "loss": 0.0168,
+      "num_input_tokens_seen": 1013296,
+      "step": 180
+    },
+    {
+      "epoch": 0.30833333333333335,
+      "grad_norm": 0.21417762339115143,
+      "learning_rate": 4.8721900291112415e-05,
+      "loss": 0.0194,
+      "num_input_tokens_seen": 1043664,
+      "step": 185
+    },
+    {
+      "epoch": 0.31666666666666665,
+      "grad_norm": 0.1550753116607666,
+      "learning_rate": 4.8652133970688636e-05,
+      "loss": 0.0155,
+      "num_input_tokens_seen": 1070912,
+      "step": 190
+    },
+    {
+      "epoch": 0.325,
+      "grad_norm": 0.132898211479187,
+      "learning_rate": 4.858056644869002e-05,
+      "loss": 0.0193,
+      "num_input_tokens_seen": 1097856,
+      "step": 195
+    },
+    {
+      "epoch": 0.3333333333333333,
+      "grad_norm": 0.09164389222860336,
+      "learning_rate": 4.850720317526047e-05,
+      "loss": 0.0164,
+      "num_input_tokens_seen": 1126128,
+      "step": 200
+    },
+    {
+      "epoch": 0.3416666666666667,
+      "grad_norm": 0.07462836056947708,
+      "learning_rate": 4.843204973729729e-05,
+      "loss": 0.014,
+      "num_input_tokens_seen": 1157584,
+      "step": 205
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 0.08473635464906693,
+      "learning_rate": 4.835511185802574e-05,
+      "loss": 0.0154,
+      "num_input_tokens_seen": 1184800,
+      "step": 210
+    },
+    {
+      "epoch": 0.35833333333333334,
+      "grad_norm": 0.07371218502521515,
+      "learning_rate": 4.827639539656321e-05,
+      "loss": 0.0147,
+      "num_input_tokens_seen": 1213104,
+      "step": 215
+    },
+    {
+      "epoch": 0.36666666666666664,
+      "grad_norm": 0.1394609957933426,
+      "learning_rate": 4.8195906347473e-05,
+      "loss": 0.0185,
+      "num_input_tokens_seen": 1241808,
+      "step": 220
+    },
+    {
+      "epoch": 0.375,
+      "grad_norm": 0.11585802584886551,
+      "learning_rate": 4.8113650840307834e-05,
+      "loss": 0.016,
+      "num_input_tokens_seen": 1270160,
+      "step": 225
+    },
+    {
+      "epoch": 0.38333333333333336,
+      "grad_norm": 0.1538001149892807,
+      "learning_rate": 4.802963513914304e-05,
+      "loss": 0.0168,
+      "num_input_tokens_seen": 1297456,
+      "step": 230
+    },
+    {
+      "epoch": 0.39166666666666666,
+      "grad_norm": 0.09096246212720871,
+      "learning_rate": 4.794386564209953e-05,
+      "loss": 0.0154,
+      "num_input_tokens_seen": 1323392,
+      "step": 235
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.11348401010036469,
+      "learning_rate": 4.7856348880856595e-05,
+      "loss": 0.0149,
+      "num_input_tokens_seen": 1358576,
+      "step": 240
+    },
+    {
+      "epoch": 0.4033333333333333,
+      "num_input_tokens_seen": 1371584,
+      "step": 242,
+      "total_flos": 4652852538507264.0,
+      "train_loss": 0.040362141964849364,
+      "train_runtime": 4583.2214,
+      "train_samples_per_second": 6.284,
+      "train_steps_per_second": 0.393
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 1800,
+  "num_input_tokens_seen": 1371584,
+  "num_train_epochs": 3,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4652852538507264.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e38936a74c731e02f619889aeaa58a6ba812a6fabdbd18f67b624b496070c73c
+size 5304