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: mistralai/Mistral-7B-Instruct-v0.1
+model-index:
+- name: train_2024-02-26-08-28-46
+  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_2024-02-26-08-28-46
+
+This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.1](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1) on the docker_NL dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 0.0002
+- 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
+- mixed_precision_training: Native AMP
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.8.2
+- Transformers 4.37.2
+- Pytorch 2.1.0+cu121
+- Datasets 2.17.1
+- Tokenizers 0.15.2

adapter_config.json

@@ -0,0 +1,27 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mistral-7B-Instruct-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": 0.1,
+  "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_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a97ed10a3e2f7be387fb883bddfab1a1d050c36e6dc21963e74762678e29a045
+size 13648432

all_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 1.0,
+    "train_loss": 0.1083572210361626,
+    "train_runtime": 702.143,
+    "train_samples_per_second": 3.439,
+    "train_steps_per_second": 0.215
+}

checkpoint-100/README.md

@@ -0,0 +1,204 @@
+---
+library_name: peft
+base_model: mistralai/Mistral-7B-Instruct-v0.1
+---
+
+# 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-100/adapter_config.json

@@ -0,0 +1,27 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mistral-7B-Instruct-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": 0.1,
+  "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_rslora": false
+}

checkpoint-100/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:abcf32385dc16200df94be61fa230036c0b0b7c708bdd6b5341d0542418bcdfd
+size 13648432

checkpoint-100/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f9187b3934f7a79bb52f568a729563f7e8683a7706a56840564aab4dde924d2
+size 27370618

checkpoint-100/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f59e6cb274ddf6a80c0cda40964656d0c7bb8916758f90c754c15d3a248bfaf
+size 14244

checkpoint-100/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35f52adf1fa501af84b48d31f630e1f3d29b636989b35ff5b721ff049022a89d
+size 1064

checkpoint-100/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-100/tokenizer.model

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

checkpoint-100/tokenizer_config.json

@@ -0,0 +1,45 @@
+{
+  "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>",
+  "chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token + ' ' }}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
+  "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-100/trainer_state.json

@@ -0,0 +1,141 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.6622516556291391,
+  "eval_steps": 500,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.00019945941475610623,
+      "loss": 0.6627,
+      "step": 5
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.00019784350367254322,
+      "loss": 0.3933,
+      "step": 10
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.00019516973750305532,
+      "loss": 0.2526,
+      "step": 15
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.0001914670242183795,
+      "loss": 0.2494,
+      "step": 20
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.00018677539646179707,
+      "loss": 0.1195,
+      "step": 25
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.00018114557872800905,
+      "loss": 0.1413,
+      "step": 30
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.00017463843894486937,
+      "loss": 0.1202,
+      "step": 35
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.00016732433038731242,
+      "loss": 0.1129,
+      "step": 40
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.0001592823310385073,
+      "loss": 0.1156,
+      "step": 45
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.00015059938862204127,
+      "loss": 0.0889,
+      "step": 50
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.00014136938054879283,
+      "loss": 0.0921,
+      "step": 55
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.0001316920989420703,
+      "loss": 0.0577,
+      "step": 60
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.00012167217171462566,
+      "loss": 0.0885,
+      "step": 65
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.00011141793136253986,
+      "loss": 0.0795,
+      "step": 70
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.00010104024370624644,
+      "loss": 0.0613,
+      "step": 75
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 9.065130924199998e-05,
+      "loss": 0.0661,
+      "step": 80
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 8.036345006322359e-05,
+      "loss": 0.0333,
+      "step": 85
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 7.028789546718326e-05,
+      "loss": 0.0512,
+      "step": 90
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 6.053357937665237e-05,
+      "loss": 0.0553,
+      "step": 95
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 5.1205962578487155e-05,
+      "loss": 0.0409,
+      "step": 100
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 151,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 100,
+  "total_flos": 4563475407568896.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-100/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:958a44028e9e507765c0ff813e71751e7147b055850af6aaf4f50ff29284554d
+size 4920

runs/Feb26_08-29-49_e48567a81c6c/events.out.tfevents.1708936364.e48567a81c6c.9041.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ef2c752dd899916e32cdf6f895cf43d68e83e66103e9613752108ac062a6f6c
+size 9993

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 +1,45 @@
+{
+  "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>",
+  "chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token + ' ' }}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
+  "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": 0.1083572210361626,
+    "train_runtime": 702.143,
+    "train_samples_per_second": 3.439,
+    "train_steps_per_second": 0.215
+}

trainer_log.jsonl

@@ -0,0 +1,31 @@
+{"current_steps": 5, "total_steps": 151, "loss": 0.6627, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00019945941475610623, "epoch": 0.03, "percentage": 3.31, "elapsed_time": "0:00:23", "remaining_time": "0:11:18"}
+{"current_steps": 10, "total_steps": 151, "loss": 0.3933, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00019784350367254322, "epoch": 0.07, "percentage": 6.62, "elapsed_time": "0:00:44", "remaining_time": "0:10:29"}
+{"current_steps": 15, "total_steps": 151, "loss": 0.2526, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00019516973750305532, "epoch": 0.1, "percentage": 9.93, "elapsed_time": "0:01:07", "remaining_time": "0:10:10"}
+{"current_steps": 20, "total_steps": 151, "loss": 0.2494, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0001914670242183795, "epoch": 0.13, "percentage": 13.25, "elapsed_time": "0:01:29", "remaining_time": "0:09:44"}
+{"current_steps": 25, "total_steps": 151, "loss": 0.1195, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00018677539646179707, "epoch": 0.17, "percentage": 16.56, "elapsed_time": "0:01:53", "remaining_time": "0:09:29"}
+{"current_steps": 30, "total_steps": 151, "loss": 0.1413, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00018114557872800905, "epoch": 0.2, "percentage": 19.87, "elapsed_time": "0:02:15", "remaining_time": "0:09:08"}
+{"current_steps": 35, "total_steps": 151, "loss": 0.1202, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00017463843894486937, "epoch": 0.23, "percentage": 23.18, "elapsed_time": "0:02:39", "remaining_time": "0:08:48"}
+{"current_steps": 40, "total_steps": 151, "loss": 0.1129, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00016732433038731242, "epoch": 0.26, "percentage": 26.49, "elapsed_time": "0:03:02", "remaining_time": "0:08:27"}
+{"current_steps": 45, "total_steps": 151, "loss": 0.1156, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0001592823310385073, "epoch": 0.3, "percentage": 29.8, "elapsed_time": "0:03:26", "remaining_time": "0:08:06"}
+{"current_steps": 50, "total_steps": 151, "loss": 0.0889, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00015059938862204127, "epoch": 0.33, "percentage": 33.11, "elapsed_time": "0:03:50", "remaining_time": "0:07:46"}
+{"current_steps": 55, "total_steps": 151, "loss": 0.0921, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00014136938054879283, "epoch": 0.36, "percentage": 36.42, "elapsed_time": "0:04:14", "remaining_time": "0:07:23"}
+{"current_steps": 60, "total_steps": 151, "loss": 0.0577, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0001316920989420703, "epoch": 0.4, "percentage": 39.74, "elapsed_time": "0:04:37", "remaining_time": "0:07:01"}
+{"current_steps": 65, "total_steps": 151, "loss": 0.0885, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00012167217171462566, "epoch": 0.43, "percentage": 43.05, "elapsed_time": "0:05:00", "remaining_time": "0:06:37"}
+{"current_steps": 70, "total_steps": 151, "loss": 0.0795, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00011141793136253986, "epoch": 0.46, "percentage": 46.36, "elapsed_time": "0:05:23", "remaining_time": "0:06:14"}
+{"current_steps": 75, "total_steps": 151, "loss": 0.0613, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00010104024370624644, "epoch": 0.5, "percentage": 49.67, "elapsed_time": "0:05:46", "remaining_time": "0:05:51"}
+{"current_steps": 80, "total_steps": 151, "loss": 0.0661, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.065130924199998e-05, "epoch": 0.53, "percentage": 52.98, "elapsed_time": "0:06:10", "remaining_time": "0:05:29"}
+{"current_steps": 85, "total_steps": 151, "loss": 0.0333, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.036345006322359e-05, "epoch": 0.56, "percentage": 56.29, "elapsed_time": "0:06:34", "remaining_time": "0:05:06"}
+{"current_steps": 90, "total_steps": 151, "loss": 0.0512, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.028789546718326e-05, "epoch": 0.6, "percentage": 59.6, "elapsed_time": "0:06:58", "remaining_time": "0:04:43"}
+{"current_steps": 95, "total_steps": 151, "loss": 0.0553, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.053357937665237e-05, "epoch": 0.63, "percentage": 62.91, "elapsed_time": "0:07:21", "remaining_time": "0:04:20"}
+{"current_steps": 100, "total_steps": 151, "loss": 0.0409, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.1205962578487155e-05, "epoch": 0.66, "percentage": 66.23, "elapsed_time": "0:07:44", "remaining_time": "0:03:57"}
+{"current_steps": 105, "total_steps": 151, "loss": 0.0592, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.240589251272342e-05, "epoch": 0.7, "percentage": 69.54, "elapsed_time": "0:08:08", "remaining_time": "0:03:33"}
+{"current_steps": 110, "total_steps": 151, "loss": 0.0536, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.422851293981676e-05, "epoch": 0.73, "percentage": 72.85, "elapsed_time": "0:08:30", "remaining_time": "0:03:10"}
+{"current_steps": 115, "total_steps": 151, "loss": 0.0275, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.6762235274383772e-05, "epoch": 0.76, "percentage": 76.16, "elapsed_time": "0:08:54", "remaining_time": "0:02:47"}
+{"current_steps": 120, "total_steps": 151, "loss": 0.0466, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.008778270707944e-05, "epoch": 0.79, "percentage": 79.47, "elapsed_time": "0:09:18", "remaining_time": "0:02:24"}
+{"current_steps": 125, "total_steps": 151, "loss": 0.0328, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.4277317449282834e-05, "epoch": 0.83, "percentage": 82.78, "elapsed_time": "0:09:41", "remaining_time": "0:02:00"}
+{"current_steps": 130, "total_steps": 151, "loss": 0.0299, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.393660536564408e-06, "epoch": 0.86, "percentage": 86.09, "elapsed_time": "0:10:05", "remaining_time": "0:01:37"}
+{"current_steps": 135, "total_steps": 151, "loss": 0.0258, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.489612626189245e-06, "epoch": 0.89, "percentage": 89.4, "elapsed_time": "0:10:28", "remaining_time": "0:01:14"}
+{"current_steps": 140, "total_steps": 151, "loss": 0.0374, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.607383131993424e-06, "epoch": 0.93, "percentage": 92.72, "elapsed_time": "0:10:52", "remaining_time": "0:00:51"}
+{"current_steps": 145, "total_steps": 151, "loss": 0.037, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.781338686584927e-07, "epoch": 0.96, "percentage": 96.03, "elapsed_time": "0:11:14", "remaining_time": "0:00:27"}
+{"current_steps": 150, "total_steps": 151, "loss": 0.0316, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.164213936770576e-08, "epoch": 0.99, "percentage": 99.34, "elapsed_time": "0:11:37", "remaining_time": "0:00:04"}
+{"current_steps": 151, "total_steps": 151, "loss": null, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "0:11:42", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,210 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 151,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.00019945941475610623,
+      "loss": 0.6627,
+      "step": 5
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.00019784350367254322,
+      "loss": 0.3933,
+      "step": 10
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.00019516973750305532,
+      "loss": 0.2526,
+      "step": 15
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.0001914670242183795,
+      "loss": 0.2494,
+      "step": 20
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.00018677539646179707,
+      "loss": 0.1195,
+      "step": 25
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.00018114557872800905,
+      "loss": 0.1413,
+      "step": 30
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.00017463843894486937,
+      "loss": 0.1202,
+      "step": 35
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.00016732433038731242,
+      "loss": 0.1129,
+      "step": 40
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.0001592823310385073,
+      "loss": 0.1156,
+      "step": 45
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.00015059938862204127,
+      "loss": 0.0889,
+      "step": 50
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.00014136938054879283,
+      "loss": 0.0921,
+      "step": 55
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.0001316920989420703,
+      "loss": 0.0577,
+      "step": 60
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.00012167217171462566,
+      "loss": 0.0885,
+      "step": 65
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.00011141793136253986,
+      "loss": 0.0795,
+      "step": 70
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.00010104024370624644,
+      "loss": 0.0613,
+      "step": 75
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 9.065130924199998e-05,
+      "loss": 0.0661,
+      "step": 80
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 8.036345006322359e-05,
+      "loss": 0.0333,
+      "step": 85
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 7.028789546718326e-05,
+      "loss": 0.0512,
+      "step": 90
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 6.053357937665237e-05,
+      "loss": 0.0553,
+      "step": 95
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 5.1205962578487155e-05,
+      "loss": 0.0409,
+      "step": 100
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 4.240589251272342e-05,
+      "loss": 0.0592,
+      "step": 105
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 3.422851293981676e-05,
+      "loss": 0.0536,
+      "step": 110
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 2.6762235274383772e-05,
+      "loss": 0.0275,
+      "step": 115
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 2.008778270707944e-05,
+      "loss": 0.0466,
+      "step": 120
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1.4277317449282834e-05,
+      "loss": 0.0328,
+      "step": 125
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 9.393660536564408e-06,
+      "loss": 0.0299,
+      "step": 130
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 5.489612626189245e-06,
+      "loss": 0.0258,
+      "step": 135
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 2.607383131993424e-06,
+      "loss": 0.0374,
+      "step": 140
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 7.781338686584927e-07,
+      "loss": 0.037,
+      "step": 145
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 2.164213936770576e-08,
+      "loss": 0.0316,
+      "step": 150
+    },
+    {
+      "epoch": 1.0,
+      "step": 151,
+      "total_flos": 6843505735041024.0,
+      "train_loss": 0.1083572210361626,
+      "train_runtime": 702.143,
+      "train_samples_per_second": 3.439,
+      "train_steps_per_second": 0.215
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 151,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 100,
+  "total_flos": 6843505735041024.0,
+  "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 sha256:958a44028e9e507765c0ff813e71751e7147b055850af6aaf4f50ff29284554d
+size 4920