Upload folder using huggingface_hub

README.md

@@ -0,0 +1,59 @@
+---
+license: other
+library_name: peft
+tags:
+- llama-factory
+- lora
+- generated_from_trainer
+base_model: Qwen/Qwen1.5-1.8B
+model-index:
+- name: train_2024-03-15-07-07-32
+  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_2024-03-15-07-07-32
+
+This model is a fine-tuned version of [Qwen/Qwen1.5-1.8B](https://huggingface.co/Qwen/Qwen1.5-1.8B) on the PIPPA 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
+- 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 0.9.0
+- Transformers 4.38.2
+- Pytorch 2.2.1+cu121
+- Datasets 2.18.0
+- Tokenizers 0.15.2

adapter_config.json

@@ -0,0 +1,28 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen1.5-1.8B",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "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 sha256:1e7dd411ac97ecb46eafa6df766860678e727a2c1a568c09165d5307bf734fb3
+size 6304096

added_tokens.json

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

all_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 2.99,
+    "train_loss": 2.5343901483636153,
+    "train_runtime": 1859.0377,
+    "train_samples_per_second": 1.477,
+    "train_steps_per_second": 0.092
+}

checkpoint-100/README.md

@@ -0,0 +1,204 @@
+---
+library_name: peft
+base_model: Qwen/Qwen1.5-1.8B
+---
+
+# 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 0.9.0

checkpoint-100/adapter_config.json

@@ -0,0 +1,28 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen1.5-1.8B",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "q_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:fed755aa35222569f766075cdf782e00aa1396f5753fb9e965ba174e58aea705
+size 6304096

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:c690edbe4210abcf2cc0511fed257b7445eeea1cbbdaa37c6c7c3627728059ed
+size 12663802

checkpoint-100/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc88650b952bfd5edc596d2f98355841769785e4797c356a63440dc1ce193f5e
+size 14244

checkpoint-100/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:630b9f8550a654817bb7ab3c8125fd769893207abe6bf080ff46903cff3db713
+size 1064

checkpoint-100/special_tokens_map.json

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

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": "{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ system_message + '\\n' }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ 'Human: ' + content + '\\nAssistant: ' }}{% elif message['role'] == 'assistant' %}{{ content + '<|endoftext|>' + '\\n' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "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 +1,161 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.7467248908296944,
+  "eval_steps": 500,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.09,
+      "grad_norm": 0.6939600110054016,
+      "learning_rate": 4.9894597202472696e-05,
+      "loss": 2.9255,
+      "step": 5
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 0.8492265343666077,
+      "learning_rate": 4.957927758986888e-05,
+      "loss": 2.8178,
+      "step": 10
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 0.8294272422790527,
+      "learning_rate": 4.905670000773126e-05,
+      "loss": 2.7191,
+      "step": 15
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 0.6167703866958618,
+      "learning_rate": 4.833127094718643e-05,
+      "loss": 2.6713,
+      "step": 20
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 0.49007371068000793,
+      "learning_rate": 4.7409107388425504e-05,
+      "loss": 2.6395,
+      "step": 25
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 0.4197269678115845,
+      "learning_rate": 4.629798522095818e-05,
+      "loss": 2.5998,
+      "step": 30
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 0.35962584614753723,
+      "learning_rate": 4.5007273675572104e-05,
+      "loss": 2.5696,
+      "step": 35
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 0.31397658586502075,
+      "learning_rate": 4.3547856320882044e-05,
+      "loss": 2.5568,
+      "step": 40
+    },
+    {
+      "epoch": 0.79,
+      "grad_norm": 0.2711264193058014,
+      "learning_rate": 4.193203929064353e-05,
+      "loss": 2.4964,
+      "step": 45
+    },
+    {
+      "epoch": 0.87,
+      "grad_norm": 0.29537662863731384,
+      "learning_rate": 4.0173447515678916e-05,
+      "loss": 2.5512,
+      "step": 50
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.28811562061309814,
+      "learning_rate": 3.82869098354114e-05,
+      "loss": 2.5155,
+      "step": 55
+    },
+    {
+      "epoch": 1.05,
+      "grad_norm": 0.2557935118675232,
+      "learning_rate": 3.628833395777224e-05,
+      "loss": 2.5253,
+      "step": 60
+    },
+    {
+      "epoch": 1.14,
+      "grad_norm": 0.243013396859169,
+      "learning_rate": 3.4194572321847336e-05,
+      "loss": 2.5395,
+      "step": 65
+    },
+    {
+      "epoch": 1.22,
+      "grad_norm": 0.26634490489959717,
+      "learning_rate": 3.202327999433924e-05,
+      "loss": 2.4728,
+      "step": 70
+    },
+    {
+      "epoch": 1.31,
+      "grad_norm": 0.288352906703949,
+      "learning_rate": 2.9792765798093465e-05,
+      "loss": 2.5059,
+      "step": 75
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 0.25032252073287964,
+      "learning_rate": 2.752183792800671e-05,
+      "loss": 2.5368,
+      "step": 80
+    },
+    {
+      "epoch": 1.48,
+      "grad_norm": 0.24827222526073456,
+      "learning_rate": 2.5229645356118163e-05,
+      "loss": 2.4811,
+      "step": 85
+    },
+    {
+      "epoch": 1.57,
+      "grad_norm": 0.2552015781402588,
+      "learning_rate": 2.2935516363191693e-05,
+      "loss": 2.5105,
+      "step": 90
+    },
+    {
+      "epoch": 1.66,
+      "grad_norm": 0.2699149549007416,
+      "learning_rate": 2.0658795558326743e-05,
+      "loss": 2.5252,
+      "step": 95
+    },
+    {
+      "epoch": 1.75,
+      "grad_norm": 0.2718549966812134,
+      "learning_rate": 1.8418680760885027e-05,
+      "loss": 2.4448,
+      "step": 100
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 171,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 100,
+  "total_flos": 1.5003963409563648e+16,
+  "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:d328013ce840d512bfda18c4318f213b0268f9ce834a68420ca42557bbe0c0a8
+size 5112

runs/Mar15_07-08-08_90f17ba55fb1/events.out.tfevents.1710486607.90f17ba55fb1.355.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39a038c4fe68687bcfe2a93234ae94b375de9cad6eb2bbff99f70c4c04f6934c
+size 12298

special_tokens_map.json

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

tokenizer_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": "{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ system_message + '\\n' }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ 'Human: ' + content + '\\nAssistant: ' }}{% elif message['role'] == 'assistant' %}{{ content + '<|endoftext|>' + '\\n' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "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 +1,7 @@
+{
+    "epoch": 2.99,
+    "train_loss": 2.5343901483636153,
+    "train_runtime": 1859.0377,
+    "train_samples_per_second": 1.477,
+    "train_steps_per_second": 0.092
+}

trainer_log.jsonl

@@ -0,0 +1,35 @@
+{"current_steps": 5, "total_steps": 171, "loss": 2.9255, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.9894597202472696e-05, "epoch": 0.09, "percentage": 2.92, "elapsed_time": "0:00:51", "remaining_time": "0:28:34"}
+{"current_steps": 10, "total_steps": 171, "loss": 2.8178, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.957927758986888e-05, "epoch": 0.17, "percentage": 5.85, "elapsed_time": "0:01:46", "remaining_time": "0:28:31"}
+{"current_steps": 15, "total_steps": 171, "loss": 2.7191, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.905670000773126e-05, "epoch": 0.26, "percentage": 8.77, "elapsed_time": "0:02:40", "remaining_time": "0:27:47"}
+{"current_steps": 20, "total_steps": 171, "loss": 2.6713, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.833127094718643e-05, "epoch": 0.35, "percentage": 11.7, "elapsed_time": "0:03:34", "remaining_time": "0:27:02"}
+{"current_steps": 25, "total_steps": 171, "loss": 2.6395, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.7409107388425504e-05, "epoch": 0.44, "percentage": 14.62, "elapsed_time": "0:04:29", "remaining_time": "0:26:12"}
+{"current_steps": 30, "total_steps": 171, "loss": 2.5998, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.629798522095818e-05, "epoch": 0.52, "percentage": 17.54, "elapsed_time": "0:05:23", "remaining_time": "0:25:21"}
+{"current_steps": 35, "total_steps": 171, "loss": 2.5696, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.5007273675572104e-05, "epoch": 0.61, "percentage": 20.47, "elapsed_time": "0:06:18", "remaining_time": "0:24:29"}
+{"current_steps": 40, "total_steps": 171, "loss": 2.5568, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.3547856320882044e-05, "epoch": 0.7, "percentage": 23.39, "elapsed_time": "0:07:12", "remaining_time": "0:23:35"}
+{"current_steps": 45, "total_steps": 171, "loss": 2.4964, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.193203929064353e-05, "epoch": 0.79, "percentage": 26.32, "elapsed_time": "0:08:06", "remaining_time": "0:22:43"}
+{"current_steps": 50, "total_steps": 171, "loss": 2.5512, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.0173447515678916e-05, "epoch": 0.87, "percentage": 29.24, "elapsed_time": "0:09:01", "remaining_time": "0:21:49"}
+{"current_steps": 55, "total_steps": 171, "loss": 2.5155, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.82869098354114e-05, "epoch": 0.96, "percentage": 32.16, "elapsed_time": "0:09:55", "remaining_time": "0:20:56"}
+{"current_steps": 60, "total_steps": 171, "loss": 2.5253, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.628833395777224e-05, "epoch": 1.05, "percentage": 35.09, "elapsed_time": "0:10:49", "remaining_time": "0:20:01"}
+{"current_steps": 65, "total_steps": 171, "loss": 2.5395, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.4194572321847336e-05, "epoch": 1.14, "percentage": 38.01, "elapsed_time": "0:11:43", "remaining_time": "0:19:07"}
+{"current_steps": 70, "total_steps": 171, "loss": 2.4728, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.202327999433924e-05, "epoch": 1.22, "percentage": 40.94, "elapsed_time": "0:12:38", "remaining_time": "0:18:13"}
+{"current_steps": 75, "total_steps": 171, "loss": 2.5059, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.9792765798093465e-05, "epoch": 1.31, "percentage": 43.86, "elapsed_time": "0:13:32", "remaining_time": "0:17:20"}
+{"current_steps": 80, "total_steps": 171, "loss": 2.5368, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.752183792800671e-05, "epoch": 1.4, "percentage": 46.78, "elapsed_time": "0:14:27", "remaining_time": "0:16:26"}
+{"current_steps": 85, "total_steps": 171, "loss": 2.4811, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.5229645356118163e-05, "epoch": 1.48, "percentage": 49.71, "elapsed_time": "0:15:21", "remaining_time": "0:15:32"}
+{"current_steps": 90, "total_steps": 171, "loss": 2.5105, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.2935516363191693e-05, "epoch": 1.57, "percentage": 52.63, "elapsed_time": "0:16:15", "remaining_time": "0:14:38"}
+{"current_steps": 95, "total_steps": 171, "loss": 2.5252, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.0658795558326743e-05, "epoch": 1.66, "percentage": 55.56, "elapsed_time": "0:17:10", "remaining_time": "0:13:44"}
+{"current_steps": 100, "total_steps": 171, "loss": 2.4448, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.8418680760885027e-05, "epoch": 1.75, "percentage": 58.48, "elapsed_time": "0:18:04", "remaining_time": "0:12:50"}
+{"current_steps": 105, "total_steps": 171, "loss": 2.438, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.6234061120181142e-05, "epoch": 1.83, "percentage": 61.4, "elapsed_time": "0:19:00", "remaining_time": "0:11:56"}
+{"current_steps": 110, "total_steps": 171, "loss": 2.49, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.4123357837948175e-05, "epoch": 1.92, "percentage": 64.33, "elapsed_time": "0:19:54", "remaining_time": "0:11:02"}
+{"current_steps": 115, "total_steps": 171, "loss": 2.4363, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.2104368836641908e-05, "epoch": 2.01, "percentage": 67.25, "elapsed_time": "0:20:48", "remaining_time": "0:10:08"}
+{"current_steps": 120, "total_steps": 171, "loss": 2.4613, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.0194118683375503e-05, "epoch": 2.1, "percentage": 70.18, "elapsed_time": "0:21:43", "remaining_time": "0:09:13"}
+{"current_steps": 125, "total_steps": 171, "loss": 2.4758, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.40871503495947e-06, "epoch": 2.18, "percentage": 73.1, "elapsed_time": "0:22:37", "remaining_time": "0:08:19"}
+{"current_steps": 130, "total_steps": 171, "loss": 2.4591, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.763212814534484e-06, "epoch": 2.27, "percentage": 76.02, "elapsed_time": "0:23:32", "remaining_time": "0:07:25"}
+{"current_steps": 135, "total_steps": 171, "loss": 2.4655, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.271487265090163e-06, "epoch": 2.36, "percentage": 78.95, "elapsed_time": "0:24:26", "remaining_time": "0:06:31"}
+{"current_steps": 140, "total_steps": 171, "loss": 2.4813, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.94611695031086e-06, "epoch": 2.45, "percentage": 81.87, "elapsed_time": "0:25:21", "remaining_time": "0:05:36"}
+{"current_steps": 145, "total_steps": 171, "loss": 2.4453, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.7982776893115627e-06, "epoch": 2.53, "percentage": 84.8, "elapsed_time": "0:26:15", "remaining_time": "0:04:42"}
+{"current_steps": 150, "total_steps": 171, "loss": 2.4941, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.837648319629956e-06, "epoch": 2.62, "percentage": 87.72, "elapsed_time": "0:27:09", "remaining_time": "0:03:48"}
+{"current_steps": 155, "total_steps": 171, "loss": 2.4701, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.0723290831021471e-06, "epoch": 2.71, "percentage": 90.64, "elapsed_time": "0:28:04", "remaining_time": "0:02:53"}
+{"current_steps": 160, "total_steps": 171, "loss": 2.4543, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.087733228106517e-07, "epoch": 2.79, "percentage": 93.57, "elapsed_time": "0:28:59", "remaining_time": "0:01:59"}
+{"current_steps": 165, "total_steps": 171, "loss": 2.5142, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.517330670512629e-07, "epoch": 2.88, "percentage": 96.49, "elapsed_time": "0:29:53", "remaining_time": "0:01:05"}
+{"current_steps": 170, "total_steps": 171, "loss": 2.4938, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.218959166932268e-09, "epoch": 2.97, "percentage": 99.42, "elapsed_time": "0:30:48", "remaining_time": "0:00:10"}
+{"current_steps": 171, "total_steps": 171, "loss": null, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 2.99, "percentage": 100.0, "elapsed_time": "0:30:58", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,268 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.986899563318777,
+  "eval_steps": 500,
+  "global_step": 171,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.09,
+      "grad_norm": 0.6939600110054016,
+      "learning_rate": 4.9894597202472696e-05,
+      "loss": 2.9255,
+      "step": 5
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 0.8492265343666077,
+      "learning_rate": 4.957927758986888e-05,
+      "loss": 2.8178,
+      "step": 10
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 0.8294272422790527,
+      "learning_rate": 4.905670000773126e-05,
+      "loss": 2.7191,
+      "step": 15
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 0.6167703866958618,
+      "learning_rate": 4.833127094718643e-05,
+      "loss": 2.6713,
+      "step": 20
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 0.49007371068000793,
+      "learning_rate": 4.7409107388425504e-05,
+      "loss": 2.6395,
+      "step": 25
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 0.4197269678115845,
+      "learning_rate": 4.629798522095818e-05,
+      "loss": 2.5998,
+      "step": 30
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 0.35962584614753723,
+      "learning_rate": 4.5007273675572104e-05,
+      "loss": 2.5696,
+      "step": 35
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 0.31397658586502075,
+      "learning_rate": 4.3547856320882044e-05,
+      "loss": 2.5568,
+      "step": 40
+    },
+    {
+      "epoch": 0.79,
+      "grad_norm": 0.2711264193058014,
+      "learning_rate": 4.193203929064353e-05,
+      "loss": 2.4964,
+      "step": 45
+    },
+    {
+      "epoch": 0.87,
+      "grad_norm": 0.29537662863731384,
+      "learning_rate": 4.0173447515678916e-05,
+      "loss": 2.5512,
+      "step": 50
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.28811562061309814,
+      "learning_rate": 3.82869098354114e-05,
+      "loss": 2.5155,
+      "step": 55
+    },
+    {
+      "epoch": 1.05,
+      "grad_norm": 0.2557935118675232,
+      "learning_rate": 3.628833395777224e-05,
+      "loss": 2.5253,
+      "step": 60
+    },
+    {
+      "epoch": 1.14,
+      "grad_norm": 0.243013396859169,
+      "learning_rate": 3.4194572321847336e-05,
+      "loss": 2.5395,
+      "step": 65
+    },
+    {
+      "epoch": 1.22,
+      "grad_norm": 0.26634490489959717,
+      "learning_rate": 3.202327999433924e-05,
+      "loss": 2.4728,
+      "step": 70
+    },
+    {
+      "epoch": 1.31,
+      "grad_norm": 0.288352906703949,
+      "learning_rate": 2.9792765798093465e-05,
+      "loss": 2.5059,
+      "step": 75
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 0.25032252073287964,
+      "learning_rate": 2.752183792800671e-05,
+      "loss": 2.5368,
+      "step": 80
+    },
+    {
+      "epoch": 1.48,
+      "grad_norm": 0.24827222526073456,
+      "learning_rate": 2.5229645356118163e-05,
+      "loss": 2.4811,
+      "step": 85
+    },
+    {
+      "epoch": 1.57,
+      "grad_norm": 0.2552015781402588,
+      "learning_rate": 2.2935516363191693e-05,
+      "loss": 2.5105,
+      "step": 90
+    },
+    {
+      "epoch": 1.66,
+      "grad_norm": 0.2699149549007416,
+      "learning_rate": 2.0658795558326743e-05,
+      "loss": 2.5252,
+      "step": 95
+    },
+    {
+      "epoch": 1.75,
+      "grad_norm": 0.2718549966812134,
+      "learning_rate": 1.8418680760885027e-05,
+      "loss": 2.4448,
+      "step": 100
+    },
+    {
+      "epoch": 1.83,
+      "grad_norm": 0.2571737468242645,
+      "learning_rate": 1.6234061120181142e-05,
+      "loss": 2.438,
+      "step": 105
+    },
+    {
+      "epoch": 1.92,
+      "grad_norm": 0.25729846954345703,
+      "learning_rate": 1.4123357837948175e-05,
+      "loss": 2.49,
+      "step": 110
+    },
+    {
+      "epoch": 2.01,
+      "grad_norm": 0.29407253861427307,
+      "learning_rate": 1.2104368836641908e-05,
+      "loss": 2.4363,
+      "step": 115
+    },
+    {
+      "epoch": 2.1,
+      "grad_norm": 0.2614673376083374,
+      "learning_rate": 1.0194118683375503e-05,
+      "loss": 2.4613,
+      "step": 120
+    },
+    {
+      "epoch": 2.18,
+      "grad_norm": 0.24367694556713104,
+      "learning_rate": 8.40871503495947e-06,
+      "loss": 2.4758,
+      "step": 125
+    },
+    {
+      "epoch": 2.27,
+      "grad_norm": 0.26960763335227966,
+      "learning_rate": 6.763212814534484e-06,
+      "loss": 2.4591,
+      "step": 130
+    },
+    {
+      "epoch": 2.36,
+      "grad_norm": 0.24732153117656708,
+      "learning_rate": 5.271487265090163e-06,
+      "loss": 2.4655,
+      "step": 135
+    },
+    {
+      "epoch": 2.45,
+      "grad_norm": 0.2650165855884552,
+      "learning_rate": 3.94611695031086e-06,
+      "loss": 2.4813,
+      "step": 140
+    },
+    {
+      "epoch": 2.53,
+      "grad_norm": 0.26127758622169495,
+      "learning_rate": 2.7982776893115627e-06,
+      "loss": 2.4453,
+      "step": 145
+    },
+    {
+      "epoch": 2.62,
+      "grad_norm": 0.2666429877281189,
+      "learning_rate": 1.837648319629956e-06,
+      "loss": 2.4941,
+      "step": 150
+    },
+    {
+      "epoch": 2.71,
+      "grad_norm": 0.25974979996681213,
+      "learning_rate": 1.0723290831021471e-06,
+      "loss": 2.4701,
+      "step": 155
+    },
+    {
+      "epoch": 2.79,
+      "grad_norm": 0.2709636092185974,
+      "learning_rate": 5.087733228106517e-07,
+      "loss": 2.4543,
+      "step": 160
+    },
+    {
+      "epoch": 2.88,
+      "grad_norm": 0.24128825962543488,
+      "learning_rate": 1.517330670512629e-07,
+      "loss": 2.5142,
+      "step": 165
+    },
+    {
+      "epoch": 2.97,
+      "grad_norm": 0.26422107219696045,
+      "learning_rate": 4.218959166932268e-09,
+      "loss": 2.4938,
+      "step": 170
+    },
+    {
+      "epoch": 2.99,
+      "step": 171,
+      "total_flos": 2.565405626125517e+16,
+      "train_loss": 2.5343901483636153,
+      "train_runtime": 1859.0377,
+      "train_samples_per_second": 1.477,
+      "train_steps_per_second": 0.092
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 171,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 100,
+  "total_flos": 2.565405626125517e+16,
+  "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:d328013ce840d512bfda18c4318f213b0268f9ce834a68420ca42557bbe0c0a8
+size 5112