Upload folder using huggingface_hub

README.md

@@ -0,0 +1,40 @@
+---
+license: other
+library_name: peft
+tags:
+- llama-factory
+- lora
+- generated_from_trainer
+base_model: mistralai/Mistral-7B-v0.1
+model-index:
+- name: mistral-7b-medwiki-v1
+  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. -->
+
+# mistral-7b-medwiki-v1
+
+This model is a fine-tuned version of [/workspace/model](https://huggingface.co//workspace/model) on the medical_meadow_wikidoc dataset.
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 0.0005
+- train_batch_size: 4
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 16
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- num_epochs: 1.0
+
+### Framework versions
+
+- PEFT 0.8.2
+- Transformers 4.37.2
+- Pytorch 2.1.1+cu121
+- Datasets 2.16.1
+- Tokenizers 0.15.1

adapter_config.json

@@ -0,0 +1,27 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mistral-7B-v0.1",
+  "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": 0.25,
+  "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_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4fdd1a1f26a7294fdd26fcd970b09e345ea5c68ad89c444f8074e6e3d74a131f
+size 13648432

all_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 1.0,
+    "train_loss": 1.5403484671543806,
+    "train_runtime": 1808.2639,
+    "train_samples_per_second": 2.765,
+    "train_steps_per_second": 0.173
+}

checkpoint-300/README.md

@@ -0,0 +1,204 @@
+---
+library_name: peft
+base_model: /workspace/model
+---
+
+# 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 0.8.2

checkpoint-300/adapter_config.json

@@ -0,0 +1,27 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "/workspace/model",
+  "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": 0.25,
+  "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_rslora": false
+}

checkpoint-300/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:207450cd4a8587d36cfaa981932d7876200884bdd09f5313ee42f7ca2d3fd668
+size 13648432

checkpoint-300/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2bbd5fc0c8e7fc3357fc5096d0bd70c7e0f1d9020a44cc359fee95b8e31cc14
+size 27370618

checkpoint-300/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35159074b627a9b5c1f34de17af5db17aabcc37f3ef86b5dad66d2b6c9e97208
+size 14244

checkpoint-300/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81f9efb7d63e8b867db120f8a2c01181a967402ff8810304596216c08ade62da
+size 1064

checkpoint-300/special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "</s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-300/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

checkpoint-300/tokenizer_config.json

@@ -0,0 +1,44 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "split_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

checkpoint-300/trainer_state.json

@@ -0,0 +1,201 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.96,
+  "eval_steps": 500,
+  "global_step": 300,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.0004987337087656614,
+      "loss": 1.7079,
+      "step": 10
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.0004949476630105669,
+      "loss": 1.5881,
+      "step": 20
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.0004886802166271364,
+      "loss": 1.537,
+      "step": 30
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.0004799948609147061,
+      "loss": 1.6139,
+      "step": 40
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.000468979581391722,
+      "loss": 1.5905,
+      "step": 50
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.0004557459664734141,
+      "loss": 1.5532,
+      "step": 60
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.0004404280770443398,
+      "loss": 1.5624,
+      "step": 70
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.00042318108837739987,
+      "loss": 1.566,
+      "step": 80
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.0004041797181571358,
+      "loss": 1.6084,
+      "step": 90
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.00038361645653195025,
+      "loss": 1.5778,
+      "step": 100
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.0003616996161254065,
+      "loss": 1.5952,
+      "step": 110
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.0003386512217606339,
+      "loss": 1.526,
+      "step": 120
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.00031470476127563017,
+      "loss": 1.5188,
+      "step": 130
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.0002901028202144401,
+      "loss": 1.5547,
+      "step": 140
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.00026509462435557154,
+      "loss": 1.4073,
+      "step": 150
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.0002399335149726463,
+      "loss": 1.543,
+      "step": 160
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.0002148743824037269,
+      "loss": 1.4798,
+      "step": 170
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.00019017108392811063,
+      "loss": 1.479,
+      "step": 180
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.00016607387210834887,
+      "loss": 1.5438,
+      "step": 190
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.00014282685964923643,
+      "loss": 1.5179,
+      "step": 200
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.00012066554645558578,
+      "loss": 1.4537,
+      "step": 210
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 9.981443394050524e-05,
+      "loss": 1.5523,
+      "step": 220
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 8.048475075202727e-05,
+      "loss": 1.5372,
+      "step": 230
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 6.28723129572247e-05,
+      "loss": 1.5376,
+      "step": 240
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 4.715554036085673e-05,
+      "loss": 1.5009,
+      "step": 250
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 3.3493649053890325e-05,
+      "loss": 1.5572,
+      "step": 260
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 2.2025038501977485e-05,
+      "loss": 1.5053,
+      "step": 270
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 1.286588951321363e-05,
+      "loss": 1.5444,
+      "step": 280
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 6.108987288226536e-06,
+      "loss": 1.5053,
+      "step": 290
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 1.822781475486507e-06,
+      "loss": 1.4731,
+      "step": 300
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 312,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 100,
+  "total_flos": 1.0028445508042752e+17,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-300/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:601bb395054a08c7476ebf0a0eba1275bdf371fef7931c27b6a44d109cbca497
+size 4920

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "</s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

tokenizer_config.json

@@ -0,0 +1,44 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "split_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

train_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 1.0,
+    "train_loss": 1.5403484671543806,
+    "train_runtime": 1808.2639,
+    "train_samples_per_second": 2.765,
+    "train_steps_per_second": 0.173
+}

trainer_log.jsonl

@@ -0,0 +1,32 @@
+{"current_steps": 10, "total_steps": 312, "loss": 1.7079, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0004987337087656614, "epoch": 0.03, "percentage": 3.21, "elapsed_time": "0:01:01", "remaining_time": "0:30:51"}
+{"current_steps": 20, "total_steps": 312, "loss": 1.5881, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0004949476630105669, "epoch": 0.06, "percentage": 6.41, "elapsed_time": "0:01:54", "remaining_time": "0:27:57"}
+{"current_steps": 30, "total_steps": 312, "loss": 1.537, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0004886802166271364, "epoch": 0.1, "percentage": 9.62, "elapsed_time": "0:02:56", "remaining_time": "0:27:42"}
+{"current_steps": 40, "total_steps": 312, "loss": 1.6139, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0004799948609147061, "epoch": 0.13, "percentage": 12.82, "elapsed_time": "0:03:48", "remaining_time": "0:25:53"}
+{"current_steps": 50, "total_steps": 312, "loss": 1.5905, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.000468979581391722, "epoch": 0.16, "percentage": 16.03, "elapsed_time": "0:04:38", "remaining_time": "0:24:21"}
+{"current_steps": 60, "total_steps": 312, "loss": 1.5532, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0004557459664734141, "epoch": 0.19, "percentage": 19.23, "elapsed_time": "0:05:38", "remaining_time": "0:23:41"}
+{"current_steps": 70, "total_steps": 312, "loss": 1.5624, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0004404280770443398, "epoch": 0.22, "percentage": 22.44, "elapsed_time": "0:06:28", "remaining_time": "0:22:21"}
+{"current_steps": 80, "total_steps": 312, "loss": 1.566, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00042318108837739987, "epoch": 0.26, "percentage": 25.64, "elapsed_time": "0:07:26", "remaining_time": "0:21:34"}
+{"current_steps": 90, "total_steps": 312, "loss": 1.6084, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0004041797181571358, "epoch": 0.29, "percentage": 28.85, "elapsed_time": "0:08:21", "remaining_time": "0:20:35"}
+{"current_steps": 100, "total_steps": 312, "loss": 1.5778, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00038361645653195025, "epoch": 0.32, "percentage": 32.05, "elapsed_time": "0:09:29", "remaining_time": "0:20:08"}
+{"current_steps": 110, "total_steps": 312, "loss": 1.5952, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0003616996161254065, "epoch": 0.35, "percentage": 35.26, "elapsed_time": "0:10:35", "remaining_time": "0:19:27"}
+{"current_steps": 120, "total_steps": 312, "loss": 1.526, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0003386512217606339, "epoch": 0.38, "percentage": 38.46, "elapsed_time": "0:11:46", "remaining_time": "0:18:50"}
+{"current_steps": 130, "total_steps": 312, "loss": 1.5188, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00031470476127563017, "epoch": 0.42, "percentage": 41.67, "elapsed_time": "0:12:45", "remaining_time": "0:17:51"}
+{"current_steps": 140, "total_steps": 312, "loss": 1.5547, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0002901028202144401, "epoch": 0.45, "percentage": 44.87, "elapsed_time": "0:13:48", "remaining_time": "0:16:57"}
+{"current_steps": 150, "total_steps": 312, "loss": 1.4073, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00026509462435557154, "epoch": 0.48, "percentage": 48.08, "elapsed_time": "0:14:41", "remaining_time": "0:15:52"}
+{"current_steps": 160, "total_steps": 312, "loss": 1.543, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0002399335149726463, "epoch": 0.51, "percentage": 51.28, "elapsed_time": "0:15:32", "remaining_time": "0:14:45"}
+{"current_steps": 170, "total_steps": 312, "loss": 1.4798, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0002148743824037269, "epoch": 0.54, "percentage": 54.49, "elapsed_time": "0:16:34", "remaining_time": "0:13:50"}
+{"current_steps": 180, "total_steps": 312, "loss": 1.479, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00019017108392811063, "epoch": 0.58, "percentage": 57.69, "elapsed_time": "0:17:29", "remaining_time": "0:12:49"}
+{"current_steps": 190, "total_steps": 312, "loss": 1.5438, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00016607387210834887, "epoch": 0.61, "percentage": 60.9, "elapsed_time": "0:18:31", "remaining_time": "0:11:53"}
+{"current_steps": 200, "total_steps": 312, "loss": 1.5179, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00014282685964923643, "epoch": 0.64, "percentage": 64.1, "elapsed_time": "0:19:30", "remaining_time": "0:10:55"}
+{"current_steps": 210, "total_steps": 312, "loss": 1.4537, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00012066554645558578, "epoch": 0.67, "percentage": 67.31, "elapsed_time": "0:20:35", "remaining_time": "0:09:59"}
+{"current_steps": 220, "total_steps": 312, "loss": 1.5523, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.981443394050524e-05, "epoch": 0.7, "percentage": 70.51, "elapsed_time": "0:21:29", "remaining_time": "0:08:59"}
+{"current_steps": 230, "total_steps": 312, "loss": 1.5372, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.048475075202727e-05, "epoch": 0.74, "percentage": 73.72, "elapsed_time": "0:22:23", "remaining_time": "0:07:58"}
+{"current_steps": 240, "total_steps": 312, "loss": 1.5376, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.28723129572247e-05, "epoch": 0.77, "percentage": 76.92, "elapsed_time": "0:23:16", "remaining_time": "0:06:59"}
+{"current_steps": 250, "total_steps": 312, "loss": 1.5009, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.715554036085673e-05, "epoch": 0.8, "percentage": 80.13, "elapsed_time": "0:24:15", "remaining_time": "0:06:01"}
+{"current_steps": 260, "total_steps": 312, "loss": 1.5572, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.3493649053890325e-05, "epoch": 0.83, "percentage": 83.33, "elapsed_time": "0:25:07", "remaining_time": "0:05:01"}
+{"current_steps": 270, "total_steps": 312, "loss": 1.5053, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.2025038501977485e-05, "epoch": 0.86, "percentage": 86.54, "elapsed_time": "0:26:01", "remaining_time": "0:04:02"}
+{"current_steps": 280, "total_steps": 312, "loss": 1.5444, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.286588951321363e-05, "epoch": 0.9, "percentage": 89.74, "elapsed_time": "0:27:01", "remaining_time": "0:03:05"}
+{"current_steps": 290, "total_steps": 312, "loss": 1.5053, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.108987288226536e-06, "epoch": 0.93, "percentage": 92.95, "elapsed_time": "0:27:53", "remaining_time": "0:02:06"}
+{"current_steps": 300, "total_steps": 312, "loss": 1.4731, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.822781475486507e-06, "epoch": 0.96, "percentage": 96.15, "elapsed_time": "0:28:55", "remaining_time": "0:01:09"}
+{"current_steps": 310, "total_steps": 312, "loss": 1.5291, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.069275378746796e-08, "epoch": 0.99, "percentage": 99.36, "elapsed_time": "0:29:56", "remaining_time": "0:00:11"}
+{"current_steps": 312, "total_steps": 312, "loss": null, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "0:30:08", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,216 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9984,
+  "eval_steps": 500,
+  "global_step": 312,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.0004987337087656614,
+      "loss": 1.7079,
+      "step": 10
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.0004949476630105669,
+      "loss": 1.5881,
+      "step": 20
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.0004886802166271364,
+      "loss": 1.537,
+      "step": 30
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.0004799948609147061,
+      "loss": 1.6139,
+      "step": 40
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.000468979581391722,
+      "loss": 1.5905,
+      "step": 50
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.0004557459664734141,
+      "loss": 1.5532,
+      "step": 60
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.0004404280770443398,
+      "loss": 1.5624,
+      "step": 70
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.00042318108837739987,
+      "loss": 1.566,
+      "step": 80
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.0004041797181571358,
+      "loss": 1.6084,
+      "step": 90
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.00038361645653195025,
+      "loss": 1.5778,
+      "step": 100
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.0003616996161254065,
+      "loss": 1.5952,
+      "step": 110
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.0003386512217606339,
+      "loss": 1.526,
+      "step": 120
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.00031470476127563017,
+      "loss": 1.5188,
+      "step": 130
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.0002901028202144401,
+      "loss": 1.5547,
+      "step": 140
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.00026509462435557154,
+      "loss": 1.4073,
+      "step": 150
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.0002399335149726463,
+      "loss": 1.543,
+      "step": 160
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.0002148743824037269,
+      "loss": 1.4798,
+      "step": 170
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.00019017108392811063,
+      "loss": 1.479,
+      "step": 180
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.00016607387210834887,
+      "loss": 1.5438,
+      "step": 190
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.00014282685964923643,
+      "loss": 1.5179,
+      "step": 200
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.00012066554645558578,
+      "loss": 1.4537,
+      "step": 210
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 9.981443394050524e-05,
+      "loss": 1.5523,
+      "step": 220
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 8.048475075202727e-05,
+      "loss": 1.5372,
+      "step": 230
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 6.28723129572247e-05,
+      "loss": 1.5376,
+      "step": 240
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 4.715554036085673e-05,
+      "loss": 1.5009,
+      "step": 250
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 3.3493649053890325e-05,
+      "loss": 1.5572,
+      "step": 260
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 2.2025038501977485e-05,
+      "loss": 1.5053,
+      "step": 270
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 1.286588951321363e-05,
+      "loss": 1.5444,
+      "step": 280
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 6.108987288226536e-06,
+      "loss": 1.5053,
+      "step": 290
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 1.822781475486507e-06,
+      "loss": 1.4731,
+      "step": 300
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 5.069275378746796e-08,
+      "loss": 1.5291,
+      "step": 310
+    },
+    {
+      "epoch": 1.0,
+      "step": 312,
+      "total_flos": 1.0452011423603098e+17,
+      "train_loss": 1.5403484671543806,
+      "train_runtime": 1808.2639,
+      "train_samples_per_second": 2.765,
+      "train_steps_per_second": 0.173
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 312,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 100,
+  "total_flos": 1.0452011423603098e+17,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:601bb395054a08c7476ebf0a0eba1275bdf371fef7931c27b6a44d109cbca497
+size 4920