Upload folder using huggingface_hub

README.md

@@ -1,3 +1,59 @@
 ---
-license: apache-2.0
+license: other
+library_name: peft
+tags:
+- llama-factory
+- lora
+- generated_from_trainer
+base_model: mistralai/Mistral-7B-Instruct-v0.2
+model-index:
+- name: train_2024-04-24-00-09-45
+  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_2024-04-24-00-09-45
+
+This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) on the ali_dataset 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 0.10.0
+- Transformers 4.40.0
+- Pytorch 2.2.2+cu121
+- Datasets 2.19.0
+- Tokenizers 0.19.1

adapter_config.json

@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.2",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.1,
+  "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:a9da2ab2aa2a59462bd61ead8ff3aba18be8fe22c3f8d6513edd6c50548c41a2
+size 13648432

all_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 3.0,
+    "train_loss": 2.231679132075909,
+    "train_runtime": 350.7334,
+    "train_samples_per_second": 8.348,
+    "train_steps_per_second": 0.522
+}

checkpoint-100/README.md

@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: mistralai/Mistral-7B-Instruct-v0.2
+---
+
+# 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 0.10.0

checkpoint-100/adapter_config.json

@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.2",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.1,
+  "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 sha256:83a8bfae52530819b8bb2071a658a754db3cabe2d7ba5b2e616b3a79b7476890
+size 13648432

checkpoint-100/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b199e54f79009e17cdf48d6002dd66e94c8bbad3efab5bc2c6dd54a58cb42cd4
+size 27370618

checkpoint-100/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba16586a11ebfa21ae23496377c3154236bee12f9bb313d291874d0fa40f0032
+size 14244

checkpoint-100/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69e4cf7a20bf78cbea223e9dfef76ad97627a9c398a2d7226880ba66d61fba48
+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": "{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{{ '<s>' + system_message }}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ ' [INST] ' + content + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ content + '</s>' }}{% 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 +1,161 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.639344262295082,
+  "eval_steps": 500,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.08196721311475409,
+      "grad_norm": 8.290995597839355,
+      "learning_rate": 4.990795908619189e-05,
+      "loss": 6.3211,
+      "step": 5
+    },
+    {
+      "epoch": 0.16393442622950818,
+      "grad_norm": 10.25100040435791,
+      "learning_rate": 4.9632514067152726e-05,
+      "loss": 5.8414,
+      "step": 10
+    },
+    {
+      "epoch": 0.2459016393442623,
+      "grad_norm": 9.911712646484375,
+      "learning_rate": 4.928142498664579e-05,
+      "loss": 6.2669,
+      "step": 15
+    },
+    {
+      "epoch": 0.32786885245901637,
+      "grad_norm": 12.882040977478027,
+      "learning_rate": 4.868186180746792e-05,
+      "loss": 4.3475,
+      "step": 20
+    },
+    {
+      "epoch": 0.4098360655737705,
+      "grad_norm": 9.486019134521484,
+      "learning_rate": 4.790792261217512e-05,
+      "loss": 3.6657,
+      "step": 25
+    },
+    {
+      "epoch": 0.4918032786885246,
+      "grad_norm": 4.90289306640625,
+      "learning_rate": 4.696530612642871e-05,
+      "loss": 2.6512,
+      "step": 30
+    },
+    {
+      "epoch": 0.5737704918032787,
+      "grad_norm": 2.928373336791992,
+      "learning_rate": 4.586095309284618e-05,
+      "loss": 2.1788,
+      "step": 35
+    },
+    {
+      "epoch": 0.6557377049180327,
+      "grad_norm": 5.331892967224121,
+      "learning_rate": 4.460299516441777e-05,
+      "loss": 2.0556,
+      "step": 40
+    },
+    {
+      "epoch": 0.7377049180327869,
+      "grad_norm": 3.0905227661132812,
+      "learning_rate": 4.320069502892462e-05,
+      "loss": 2.0827,
+      "step": 45
+    },
+    {
+      "epoch": 0.819672131147541,
+      "grad_norm": 3.840454339981079,
+      "learning_rate": 4.1664378205239085e-05,
+      "loss": 1.9863,
+      "step": 50
+    },
+    {
+      "epoch": 0.9016393442622951,
+      "grad_norm": 2.925448179244995,
+      "learning_rate": 4.000535701370921e-05,
+      "loss": 2.0797,
+      "step": 55
+    },
+    {
+      "epoch": 0.9836065573770492,
+      "grad_norm": 4.124454498291016,
+      "learning_rate": 3.823584728045463e-05,
+      "loss": 1.9855,
+      "step": 60
+    },
+    {
+      "epoch": 1.0655737704918034,
+      "grad_norm": 2.905304431915283,
+      "learning_rate": 3.636887838890265e-05,
+      "loss": 1.8565,
+      "step": 65
+    },
+    {
+      "epoch": 1.1475409836065573,
+      "grad_norm": 2.937238931655884,
+      "learning_rate": 3.4418197340879635e-05,
+      "loss": 1.7846,
+      "step": 70
+    },
+    {
+      "epoch": 1.2295081967213115,
+      "grad_norm": 2.9058425426483154,
+      "learning_rate": 3.239816753368223e-05,
+      "loss": 1.8977,
+      "step": 75
+    },
+    {
+      "epoch": 1.3114754098360657,
+      "grad_norm": 3.247345447540283,
+      "learning_rate": 3.0323662998460393e-05,
+      "loss": 1.6528,
+      "step": 80
+    },
+    {
+      "epoch": 1.3934426229508197,
+      "grad_norm": 3.5700137615203857,
+      "learning_rate": 2.8209958878663778e-05,
+      "loss": 1.7865,
+      "step": 85
+    },
+    {
+      "epoch": 1.4754098360655736,
+      "grad_norm": 3.3404250144958496,
+      "learning_rate": 2.6072618954988866e-05,
+      "loss": 1.6595,
+      "step": 90
+    },
+    {
+      "epoch": 1.5573770491803278,
+      "grad_norm": 2.9976389408111572,
+      "learning_rate": 2.3927381045011136e-05,
+      "loss": 1.795,
+      "step": 95
+    },
+    {
+      "epoch": 1.639344262295082,
+      "grad_norm": 2.907928943634033,
+      "learning_rate": 2.1790041121336225e-05,
+      "loss": 1.6754,
+      "step": 100
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 183,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 100,
+  "total_flos": 5218424960974848.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-100/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:451ea05a0196edc64a345b0220cd5e4f39763b61e221cb2fb962fe82628ca593
+size 5176

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": "{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{{ '<s>' + system_message }}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ ' [INST] ' + content + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ content + '</s>' }}{% 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": 3.0,
+    "train_loss": 2.231679132075909,
+    "train_runtime": 350.7334,
+    "train_samples_per_second": 8.348,
+    "train_steps_per_second": 0.522
+}

trainer_log.jsonl

@@ -0,0 +1,37 @@
+{"current_steps": 5, "total_steps": 183, "loss": 6.3211, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.990795908619189e-05, "epoch": 0.08196721311475409, "percentage": 2.73, "elapsed_time": "0:00:09", "remaining_time": "0:05:44"}
+{"current_steps": 10, "total_steps": 183, "loss": 5.8414, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.9632514067152726e-05, "epoch": 0.16393442622950818, "percentage": 5.46, "elapsed_time": "0:00:18", "remaining_time": "0:05:13"}
+{"current_steps": 15, "total_steps": 183, "loss": 6.2669, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.928142498664579e-05, "epoch": 0.2459016393442623, "percentage": 8.2, "elapsed_time": "0:00:26", "remaining_time": "0:04:58"}
+{"current_steps": 20, "total_steps": 183, "loss": 4.3475, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.868186180746792e-05, "epoch": 0.32786885245901637, "percentage": 10.93, "elapsed_time": "0:00:35", "remaining_time": "0:04:47"}
+{"current_steps": 25, "total_steps": 183, "loss": 3.6657, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.790792261217512e-05, "epoch": 0.4098360655737705, "percentage": 13.66, "elapsed_time": "0:00:44", "remaining_time": "0:04:38"}
+{"current_steps": 30, "total_steps": 183, "loss": 2.6512, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.696530612642871e-05, "epoch": 0.4918032786885246, "percentage": 16.39, "elapsed_time": "0:00:52", "remaining_time": "0:04:29"}
+{"current_steps": 35, "total_steps": 183, "loss": 2.1788, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.586095309284618e-05, "epoch": 0.5737704918032787, "percentage": 19.13, "elapsed_time": "0:01:01", "remaining_time": "0:04:20"}
+{"current_steps": 40, "total_steps": 183, "loss": 2.0556, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.460299516441777e-05, "epoch": 0.6557377049180327, "percentage": 21.86, "elapsed_time": "0:01:10", "remaining_time": "0:04:11"}
+{"current_steps": 45, "total_steps": 183, "loss": 2.0827, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.320069502892462e-05, "epoch": 0.7377049180327869, "percentage": 24.59, "elapsed_time": "0:01:19", "remaining_time": "0:04:05"}
+{"current_steps": 50, "total_steps": 183, "loss": 1.9863, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.1664378205239085e-05, "epoch": 0.819672131147541, "percentage": 27.32, "elapsed_time": "0:01:28", "remaining_time": "0:03:56"}
+{"current_steps": 55, "total_steps": 183, "loss": 2.0797, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.000535701370921e-05, "epoch": 0.9016393442622951, "percentage": 30.05, "elapsed_time": "0:01:38", "remaining_time": "0:03:48"}
+{"current_steps": 60, "total_steps": 183, "loss": 1.9855, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.823584728045463e-05, "epoch": 0.9836065573770492, "percentage": 32.79, "elapsed_time": "0:01:47", "remaining_time": "0:03:40"}
+{"current_steps": 65, "total_steps": 183, "loss": 1.8565, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.636887838890265e-05, "epoch": 1.0655737704918034, "percentage": 35.52, "elapsed_time": "0:01:56", "remaining_time": "0:03:31"}
+{"current_steps": 70, "total_steps": 183, "loss": 1.7846, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.4418197340879635e-05, "epoch": 1.1475409836065573, "percentage": 38.25, "elapsed_time": "0:02:05", "remaining_time": "0:03:23"}
+{"current_steps": 75, "total_steps": 183, "loss": 1.8977, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.239816753368223e-05, "epoch": 1.2295081967213115, "percentage": 40.98, "elapsed_time": "0:02:14", "remaining_time": "0:03:14"}
+{"current_steps": 80, "total_steps": 183, "loss": 1.6528, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.0323662998460393e-05, "epoch": 1.3114754098360657, "percentage": 43.72, "elapsed_time": "0:02:24", "remaining_time": "0:03:06"}
+{"current_steps": 85, "total_steps": 183, "loss": 1.7865, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 2.8209958878663778e-05, "epoch": 1.3934426229508197, "percentage": 46.45, "elapsed_time": "0:02:33", "remaining_time": "0:02:57"}
+{"current_steps": 90, "total_steps": 183, "loss": 1.6595, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 2.6072618954988866e-05, "epoch": 1.4754098360655736, "percentage": 49.18, "elapsed_time": "0:02:43", "remaining_time": "0:02:48"}
+{"current_steps": 95, "total_steps": 183, "loss": 1.795, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 2.3927381045011136e-05, "epoch": 1.5573770491803278, "percentage": 51.91, "elapsed_time": "0:02:52", "remaining_time": "0:02:39"}
+{"current_steps": 100, "total_steps": 183, "loss": 1.6754, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 2.1790041121336225e-05, "epoch": 1.639344262295082, "percentage": 54.64, "elapsed_time": "0:03:02", "remaining_time": "0:02:31"}
+{"current_steps": 105, "total_steps": 183, "loss": 1.6433, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 1.9676337001539612e-05, "epoch": 1.721311475409836, "percentage": 57.38, "elapsed_time": "0:03:12", "remaining_time": "0:02:22"}
+{"current_steps": 110, "total_steps": 183, "loss": 1.5446, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 1.760183246631777e-05, "epoch": 1.8032786885245902, "percentage": 60.11, "elapsed_time": "0:03:21", "remaining_time": "0:02:13"}
+{"current_steps": 115, "total_steps": 183, "loss": 1.5668, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 1.558180265912037e-05, "epoch": 1.8852459016393444, "percentage": 62.84, "elapsed_time": "0:03:31", "remaining_time": "0:02:05"}
+{"current_steps": 120, "total_steps": 183, "loss": 1.5542, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 1.3631121611097364e-05, "epoch": 1.9672131147540983, "percentage": 65.57, "elapsed_time": "0:03:41", "remaining_time": "0:01:56"}
+{"current_steps": 125, "total_steps": 183, "loss": 1.4999, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 1.1764152719545372e-05, "epoch": 2.0491803278688523, "percentage": 68.31, "elapsed_time": "0:03:51", "remaining_time": "0:01:47"}
+{"current_steps": 130, "total_steps": 183, "loss": 1.6873, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 9.994642986290797e-06, "epoch": 2.1311475409836067, "percentage": 71.04, "elapsed_time": "0:04:01", "remaining_time": "0:01:38"}
+{"current_steps": 135, "total_steps": 183, "loss": 1.5267, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 8.33562179476092e-06, "epoch": 2.2131147540983607, "percentage": 73.77, "elapsed_time": "0:04:11", "remaining_time": "0:01:29"}
+{"current_steps": 140, "total_steps": 183, "loss": 1.6676, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 6.799304971075382e-06, "epoch": 2.2950819672131146, "percentage": 76.5, "elapsed_time": "0:04:22", "remaining_time": "0:01:20"}
+{"current_steps": 145, "total_steps": 183, "loss": 1.7066, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 5.397004835582242e-06, "epoch": 2.3770491803278686, "percentage": 79.23, "elapsed_time": "0:04:32", "remaining_time": "0:01:11"}
+{"current_steps": 150, "total_steps": 183, "loss": 1.4762, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.139046907153818e-06, "epoch": 2.459016393442623, "percentage": 81.97, "elapsed_time": "0:04:42", "remaining_time": "0:01:02"}
+{"current_steps": 155, "total_steps": 183, "loss": 1.5355, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.0346938735712954e-06, "epoch": 2.540983606557377, "percentage": 84.7, "elapsed_time": "0:04:53", "remaining_time": "0:00:52"}
+{"current_steps": 160, "total_steps": 183, "loss": 1.708, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 2.092077387824884e-06, "epoch": 2.6229508196721314, "percentage": 87.43, "elapsed_time": "0:05:03", "remaining_time": "0:00:43"}
+{"current_steps": 165, "total_steps": 183, "loss": 1.54, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 1.3181381925320785e-06, "epoch": 2.7049180327868854, "percentage": 90.16, "elapsed_time": "0:05:13", "remaining_time": "0:00:34"}
+{"current_steps": 170, "total_steps": 183, "loss": 1.5244, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 7.185750133542169e-07, "epoch": 2.7868852459016393, "percentage": 92.9, "elapsed_time": "0:05:24", "remaining_time": "0:00:24"}
+{"current_steps": 175, "total_steps": 183, "loss": 1.5209, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 2.978025977230736e-07, "epoch": 2.8688524590163933, "percentage": 95.63, "elapsed_time": "0:05:34", "remaining_time": "0:00:15"}
+{"current_steps": 180, "total_steps": 183, "loss": 1.5363, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 5.891920784984184e-08, "epoch": 2.9508196721311473, "percentage": 98.36, "elapsed_time": "0:05:44", "remaining_time": "0:00:05"}
+{"current_steps": 183, "total_steps": 183, "loss": null, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": null, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "0:05:50", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,282 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 183,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.08196721311475409,
+      "grad_norm": 8.290995597839355,
+      "learning_rate": 4.990795908619189e-05,
+      "loss": 6.3211,
+      "step": 5
+    },
+    {
+      "epoch": 0.16393442622950818,
+      "grad_norm": 10.25100040435791,
+      "learning_rate": 4.9632514067152726e-05,
+      "loss": 5.8414,
+      "step": 10
+    },
+    {
+      "epoch": 0.2459016393442623,
+      "grad_norm": 9.911712646484375,
+      "learning_rate": 4.928142498664579e-05,
+      "loss": 6.2669,
+      "step": 15
+    },
+    {
+      "epoch": 0.32786885245901637,
+      "grad_norm": 12.882040977478027,
+      "learning_rate": 4.868186180746792e-05,
+      "loss": 4.3475,
+      "step": 20
+    },
+    {
+      "epoch": 0.4098360655737705,
+      "grad_norm": 9.486019134521484,
+      "learning_rate": 4.790792261217512e-05,
+      "loss": 3.6657,
+      "step": 25
+    },
+    {
+      "epoch": 0.4918032786885246,
+      "grad_norm": 4.90289306640625,
+      "learning_rate": 4.696530612642871e-05,
+      "loss": 2.6512,
+      "step": 30
+    },
+    {
+      "epoch": 0.5737704918032787,
+      "grad_norm": 2.928373336791992,
+      "learning_rate": 4.586095309284618e-05,
+      "loss": 2.1788,
+      "step": 35
+    },
+    {
+      "epoch": 0.6557377049180327,
+      "grad_norm": 5.331892967224121,
+      "learning_rate": 4.460299516441777e-05,
+      "loss": 2.0556,
+      "step": 40
+    },
+    {
+      "epoch": 0.7377049180327869,
+      "grad_norm": 3.0905227661132812,
+      "learning_rate": 4.320069502892462e-05,
+      "loss": 2.0827,
+      "step": 45
+    },
+    {
+      "epoch": 0.819672131147541,
+      "grad_norm": 3.840454339981079,
+      "learning_rate": 4.1664378205239085e-05,
+      "loss": 1.9863,
+      "step": 50
+    },
+    {
+      "epoch": 0.9016393442622951,
+      "grad_norm": 2.925448179244995,
+      "learning_rate": 4.000535701370921e-05,
+      "loss": 2.0797,
+      "step": 55
+    },
+    {
+      "epoch": 0.9836065573770492,
+      "grad_norm": 4.124454498291016,
+      "learning_rate": 3.823584728045463e-05,
+      "loss": 1.9855,
+      "step": 60
+    },
+    {
+      "epoch": 1.0655737704918034,
+      "grad_norm": 2.905304431915283,
+      "learning_rate": 3.636887838890265e-05,
+      "loss": 1.8565,
+      "step": 65
+    },
+    {
+      "epoch": 1.1475409836065573,
+      "grad_norm": 2.937238931655884,
+      "learning_rate": 3.4418197340879635e-05,
+      "loss": 1.7846,
+      "step": 70
+    },
+    {
+      "epoch": 1.2295081967213115,
+      "grad_norm": 2.9058425426483154,
+      "learning_rate": 3.239816753368223e-05,
+      "loss": 1.8977,
+      "step": 75
+    },
+    {
+      "epoch": 1.3114754098360657,
+      "grad_norm": 3.247345447540283,
+      "learning_rate": 3.0323662998460393e-05,
+      "loss": 1.6528,
+      "step": 80
+    },
+    {
+      "epoch": 1.3934426229508197,
+      "grad_norm": 3.5700137615203857,
+      "learning_rate": 2.8209958878663778e-05,
+      "loss": 1.7865,
+      "step": 85
+    },
+    {
+      "epoch": 1.4754098360655736,
+      "grad_norm": 3.3404250144958496,
+      "learning_rate": 2.6072618954988866e-05,
+      "loss": 1.6595,
+      "step": 90
+    },
+    {
+      "epoch": 1.5573770491803278,
+      "grad_norm": 2.9976389408111572,
+      "learning_rate": 2.3927381045011136e-05,
+      "loss": 1.795,
+      "step": 95
+    },
+    {
+      "epoch": 1.639344262295082,
+      "grad_norm": 2.907928943634033,
+      "learning_rate": 2.1790041121336225e-05,
+      "loss": 1.6754,
+      "step": 100
+    },
+    {
+      "epoch": 1.721311475409836,
+      "grad_norm": 2.8854143619537354,
+      "learning_rate": 1.9676337001539612e-05,
+      "loss": 1.6433,
+      "step": 105
+    },
+    {
+      "epoch": 1.8032786885245902,
+      "grad_norm": 3.0124289989471436,
+      "learning_rate": 1.760183246631777e-05,
+      "loss": 1.5446,
+      "step": 110
+    },
+    {
+      "epoch": 1.8852459016393444,
+      "grad_norm": 3.203061819076538,
+      "learning_rate": 1.558180265912037e-05,
+      "loss": 1.5668,
+      "step": 115
+    },
+    {
+      "epoch": 1.9672131147540983,
+      "grad_norm": 2.9160172939300537,
+      "learning_rate": 1.3631121611097364e-05,
+      "loss": 1.5542,
+      "step": 120
+    },
+    {
+      "epoch": 2.0491803278688523,
+      "grad_norm": 3.249051570892334,
+      "learning_rate": 1.1764152719545372e-05,
+      "loss": 1.4999,
+      "step": 125
+    },
+    {
+      "epoch": 2.1311475409836067,
+      "grad_norm": 3.0132319927215576,
+      "learning_rate": 9.994642986290797e-06,
+      "loss": 1.6873,
+      "step": 130
+    },
+    {
+      "epoch": 2.2131147540983607,
+      "grad_norm": 3.1967945098876953,
+      "learning_rate": 8.33562179476092e-06,
+      "loss": 1.5267,
+      "step": 135
+    },
+    {
+      "epoch": 2.2950819672131146,
+      "grad_norm": 3.5244369506835938,
+      "learning_rate": 6.799304971075382e-06,
+      "loss": 1.6676,
+      "step": 140
+    },
+    {
+      "epoch": 2.3770491803278686,
+      "grad_norm": 3.073401689529419,
+      "learning_rate": 5.397004835582242e-06,
+      "loss": 1.7066,
+      "step": 145
+    },
+    {
+      "epoch": 2.459016393442623,
+      "grad_norm": 2.9026217460632324,
+      "learning_rate": 4.139046907153818e-06,
+      "loss": 1.4762,
+      "step": 150
+    },
+    {
+      "epoch": 2.540983606557377,
+      "grad_norm": 2.8583261966705322,
+      "learning_rate": 3.0346938735712954e-06,
+      "loss": 1.5355,
+      "step": 155
+    },
+    {
+      "epoch": 2.6229508196721314,
+      "grad_norm": 3.106534242630005,
+      "learning_rate": 2.092077387824884e-06,
+      "loss": 1.708,
+      "step": 160
+    },
+    {
+      "epoch": 2.7049180327868854,
+      "grad_norm": 3.100788116455078,
+      "learning_rate": 1.3181381925320785e-06,
+      "loss": 1.54,
+      "step": 165
+    },
+    {
+      "epoch": 2.7868852459016393,
+      "grad_norm": 3.149162530899048,
+      "learning_rate": 7.185750133542169e-07,
+      "loss": 1.5244,
+      "step": 170
+    },
+    {
+      "epoch": 2.8688524590163933,
+      "grad_norm": 3.3356781005859375,
+      "learning_rate": 2.978025977230736e-07,
+      "loss": 1.5209,
+      "step": 175
+    },
+    {
+      "epoch": 2.9508196721311473,
+      "grad_norm": 2.8666839599609375,
+      "learning_rate": 5.891920784984184e-08,
+      "loss": 1.5363,
+      "step": 180
+    },
+    {
+      "epoch": 3.0,
+      "step": 183,
+      "total_flos": 9540135882719232.0,
+      "train_loss": 2.231679132075909,
+      "train_runtime": 350.7334,
+      "train_samples_per_second": 8.348,
+      "train_steps_per_second": 0.522
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 183,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 100,
+  "total_flos": 9540135882719232.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:451ea05a0196edc64a345b0220cd5e4f39763b61e221cb2fb962fe82628ca593
+size 5176