Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+checkpoint-113/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,67 @@
+---
+base_model: mistralai/Mistral-Nemo-Instruct-2407
+library_name: peft
+license: other
+tags:
+- llama-factory
+- lora
+- generated_from_trainer
+model-index:
+- name: heat_transfer_sft_5000_mcq_1epoch
+  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. -->
+
+# heat_transfer_sft_5000_mcq_1epoch
+
+This model is a fine-tuned version of [mistralai/Mistral-Nemo-Instruct-2407](https://huggingface.co/mistralai/Mistral-Nemo-Instruct-2407) on the heat_transfer_5000_mcq dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0035
+
+## 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: 0.0001
+- train_batch_size: 10
+- eval_batch_size: 10
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 4
+- total_train_batch_size: 40
+- total_eval_batch_size: 40
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- num_epochs: 1
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 0.004         | 0.2655 | 30   | 0.0038          |
+| 0.0037        | 0.5310 | 60   | 0.0036          |
+| 0.0035        | 0.7965 | 90   | 0.0035          |
+
+
+### Framework versions
+
+- PEFT 0.12.0
+- Transformers 4.46.0
+- Pytorch 2.4.0+cu121
+- Datasets 2.21.0
+- Tokenizers 0.20.1

adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mistral-Nemo-Instruct-2407",
+  "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": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "down_proj",
+    "k_proj",
+    "o_proj",
+    "gate_proj",
+    "v_proj",
+    "up_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 sha256:52802d6fe841aab344f58af86ae4e93858c4cfa88133b5fa9682f91d0290f6e4
+size 114106856

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 0.0034613024909049273,
+    "eval_runtime": 56.0786,
+    "eval_samples_per_second": 8.916,
+    "eval_steps_per_second": 0.232,
+    "total_flos": 4.179655240942879e+17,
+    "train_loss": 0.042722021724072703,
+    "train_runtime": 1759.0892,
+    "train_samples_per_second": 2.558,
+    "train_steps_per_second": 0.064
+}

checkpoint-113/README.md

@@ -0,0 +1,202 @@
+---
+base_model: mistralai/Mistral-Nemo-Instruct-2407
+library_name: peft
+---
+
+# 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 0.12.0

checkpoint-113/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mistral-Nemo-Instruct-2407",
+  "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": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "down_proj",
+    "k_proj",
+    "o_proj",
+    "gate_proj",
+    "v_proj",
+    "up_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-113/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52802d6fe841aab344f58af86ae4e93858c4cfa88133b5fa9682f91d0290f6e4
+size 114106856

checkpoint-113/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ccb2969b63c6ba3c81bd2d8d6260b6a9b782673417dc4260e73c2ad95cd6e93
+size 228536930

checkpoint-113/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70cc56408014c410353d4dd58ae9b03f4be043f5f800324f66fd8e20e99b840e
+size 15024

checkpoint-113/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49d1438e98cc9c53a6852464635ce62e9788e61eb3646b73e33813f487c4b6ae
+size 15024

checkpoint-113/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4388add9cec90932f8ff0100d27a0574d98e1bad52ff89d44e31967d2b4fbfde
+size 15024

checkpoint-113/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a705d6dfaae4f2c1b4b2be6b25a6eb521ffae6fcba21cc1531e97b60037ed079
+size 15024

checkpoint-113/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f8fe79dd2d524c3a47ebbac1a1fc359d4473e07185866008e654d72a772ea4f
+size 1064

checkpoint-113/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-113/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0240ce510f08e6c2041724e9043e33be9d251d1e4a4d94eb68cd47b954b61d2
+size 17078292

checkpoint-113/trainer_state.json

@@ -0,0 +1,134 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 30,
+  "global_step": 113,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.08849557522123894,
+      "grad_norm": 0.5378276109695435,
+      "learning_rate": 9.808007740920646e-05,
+      "loss": 0.4426,
+      "step": 10
+    },
+    {
+      "epoch": 0.17699115044247787,
+      "grad_norm": 0.08370009064674377,
+      "learning_rate": 9.246775374701139e-05,
+      "loss": 0.0061,
+      "step": 20
+    },
+    {
+      "epoch": 0.26548672566371684,
+      "grad_norm": 0.010601534508168697,
+      "learning_rate": 8.359403809285053e-05,
+      "loss": 0.004,
+      "step": 30
+    },
+    {
+      "epoch": 0.26548672566371684,
+      "eval_loss": 0.0038232754450291395,
+      "eval_runtime": 56.0996,
+      "eval_samples_per_second": 8.913,
+      "eval_steps_per_second": 0.232,
+      "step": 30
+    },
+    {
+      "epoch": 0.35398230088495575,
+      "grad_norm": 0.03688598424196243,
+      "learning_rate": 7.214040433267198e-05,
+      "loss": 0.0038,
+      "step": 40
+    },
+    {
+      "epoch": 0.4424778761061947,
+      "grad_norm": 0.013299869373440742,
+      "learning_rate": 5.8986456074589404e-05,
+      "loss": 0.0038,
+      "step": 50
+    },
+    {
+      "epoch": 0.5309734513274337,
+      "grad_norm": 0.08473875373601913,
+      "learning_rate": 4.5142375815355706e-05,
+      "loss": 0.0037,
+      "step": 60
+    },
+    {
+      "epoch": 0.5309734513274337,
+      "eval_loss": 0.0035941482055932283,
+      "eval_runtime": 56.1024,
+      "eval_samples_per_second": 8.912,
+      "eval_steps_per_second": 0.232,
+      "step": 60
+    },
+    {
+      "epoch": 0.6194690265486725,
+      "grad_norm": 0.008843529969453812,
+      "learning_rate": 3.167134605250938e-05,
+      "loss": 0.0037,
+      "step": 70
+    },
+    {
+      "epoch": 0.7079646017699115,
+      "grad_norm": 0.006533902138471603,
+      "learning_rate": 1.960790016056801e-05,
+      "loss": 0.0036,
+      "step": 80
+    },
+    {
+      "epoch": 0.7964601769911505,
+      "grad_norm": 0.06442264467477798,
+      "learning_rate": 9.878473431161767e-06,
+      "loss": 0.0035,
+      "step": 90
+    },
+    {
+      "epoch": 0.7964601769911505,
+      "eval_loss": 0.003458332037553191,
+      "eval_runtime": 56.0617,
+      "eval_samples_per_second": 8.919,
+      "eval_steps_per_second": 0.232,
+      "step": 90
+    },
+    {
+      "epoch": 0.8849557522123894,
+      "grad_norm": 0.06732333451509476,
+      "learning_rate": 3.230255711220992e-06,
+      "loss": 0.0034,
+      "step": 100
+    },
+    {
+      "epoch": 0.9734513274336283,
+      "grad_norm": 0.01167540717869997,
+      "learning_rate": 1.7380953630678488e-07,
+      "loss": 0.0035,
+      "step": 110
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 113,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4.179655240942879e+17,
+  "train_batch_size": 10,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-113/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01687fe13b6d2acb8aad42cae42ab3c27f8a0188559a24b4698d38478233a06e
+size 5496

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 0.0034613024909049273,
+    "eval_runtime": 56.0786,
+    "eval_samples_per_second": 8.916,
+    "eval_steps_per_second": 0.232
+}

runs/Jan15_22-30-44_ctua-mistral-sft-heat-333c1-hg6rc/events.out.tfevents.1736980852.ctua-mistral-sft-heat-333c1-hg6rc.318.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:027cc5a95d57175d717f2e13f62a904c1541920e6ef4eb1e3373ffb5ad4858a2
+size 8756

runs/Jan15_22-30-44_ctua-mistral-sft-heat-333c1-hg6rc/events.out.tfevents.1736982668.ctua-mistral-sft-heat-333c1-hg6rc.318.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a08812bf12130bb9fc8b2bd93cf0a6d4b8609dc501e4a3d8bb1155b7417cfdc
+size 354

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.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0240ce510f08e6c2041724e9043e33be9d251d1e4a4d94eb68cd47b954b61d2
+size 17078292

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "total_flos": 4.179655240942879e+17,
+    "train_loss": 0.042722021724072703,
+    "train_runtime": 1759.0892,
+    "train_samples_per_second": 2.558,
+    "train_steps_per_second": 0.064
+}

trainer_log.jsonl

@@ -0,0 +1,15 @@
+{"current_steps": 10, "total_steps": 113, "loss": 0.4426, "lr": 9.808007740920646e-05, "epoch": 0.08849557522123894, "percentage": 8.85, "elapsed_time": "0:02:20", "remaining_time": "0:24:02"}
+{"current_steps": 20, "total_steps": 113, "loss": 0.0061, "lr": 9.246775374701139e-05, "epoch": 0.17699115044247787, "percentage": 17.7, "elapsed_time": "0:04:40", "remaining_time": "0:21:44"}
+{"current_steps": 30, "total_steps": 113, "loss": 0.004, "lr": 8.359403809285053e-05, "epoch": 0.26548672566371684, "percentage": 26.55, "elapsed_time": "0:07:01", "remaining_time": "0:19:25"}
+{"current_steps": 30, "total_steps": 113, "eval_loss": 0.0038232754450291395, "epoch": 0.26548672566371684, "percentage": 26.55, "elapsed_time": "0:07:57", "remaining_time": "0:22:00"}
+{"current_steps": 40, "total_steps": 113, "loss": 0.0038, "lr": 7.214040433267198e-05, "epoch": 0.35398230088495575, "percentage": 35.4, "elapsed_time": "0:10:17", "remaining_time": "0:18:47"}
+{"current_steps": 50, "total_steps": 113, "loss": 0.0038, "lr": 5.8986456074589404e-05, "epoch": 0.4424778761061947, "percentage": 44.25, "elapsed_time": "0:12:38", "remaining_time": "0:15:55"}
+{"current_steps": 60, "total_steps": 113, "loss": 0.0037, "lr": 4.5142375815355706e-05, "epoch": 0.5309734513274337, "percentage": 53.1, "elapsed_time": "0:14:58", "remaining_time": "0:13:14"}
+{"current_steps": 60, "total_steps": 113, "eval_loss": 0.0035941482055932283, "epoch": 0.5309734513274337, "percentage": 53.1, "elapsed_time": "0:15:54", "remaining_time": "0:14:03"}
+{"current_steps": 70, "total_steps": 113, "loss": 0.0037, "lr": 3.167134605250938e-05, "epoch": 0.6194690265486725, "percentage": 61.95, "elapsed_time": "0:18:15", "remaining_time": "0:11:12"}
+{"current_steps": 80, "total_steps": 113, "loss": 0.0036, "lr": 1.960790016056801e-05, "epoch": 0.7079646017699115, "percentage": 70.8, "elapsed_time": "0:20:36", "remaining_time": "0:08:29"}
+{"current_steps": 90, "total_steps": 113, "loss": 0.0035, "lr": 9.878473431161767e-06, "epoch": 0.7964601769911505, "percentage": 79.65, "elapsed_time": "0:22:56", "remaining_time": "0:05:51"}
+{"current_steps": 90, "total_steps": 113, "eval_loss": 0.003458332037553191, "epoch": 0.7964601769911505, "percentage": 79.65, "elapsed_time": "0:23:52", "remaining_time": "0:06:06"}
+{"current_steps": 100, "total_steps": 113, "loss": 0.0034, "lr": 3.230255711220992e-06, "epoch": 0.8849557522123894, "percentage": 88.5, "elapsed_time": "0:26:13", "remaining_time": "0:03:24"}
+{"current_steps": 110, "total_steps": 113, "loss": 0.0035, "lr": 1.7380953630678488e-07, "epoch": 0.9734513274336283, "percentage": 97.35, "elapsed_time": "0:28:33", "remaining_time": "0:00:46"}
+{"current_steps": 113, "total_steps": 113, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "0:29:17", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,143 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 30,
+  "global_step": 113,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.08849557522123894,
+      "grad_norm": 0.5378276109695435,
+      "learning_rate": 9.808007740920646e-05,
+      "loss": 0.4426,
+      "step": 10
+    },
+    {
+      "epoch": 0.17699115044247787,
+      "grad_norm": 0.08370009064674377,
+      "learning_rate": 9.246775374701139e-05,
+      "loss": 0.0061,
+      "step": 20
+    },
+    {
+      "epoch": 0.26548672566371684,
+      "grad_norm": 0.010601534508168697,
+      "learning_rate": 8.359403809285053e-05,
+      "loss": 0.004,
+      "step": 30
+    },
+    {
+      "epoch": 0.26548672566371684,
+      "eval_loss": 0.0038232754450291395,
+      "eval_runtime": 56.0996,
+      "eval_samples_per_second": 8.913,
+      "eval_steps_per_second": 0.232,
+      "step": 30
+    },
+    {
+      "epoch": 0.35398230088495575,
+      "grad_norm": 0.03688598424196243,
+      "learning_rate": 7.214040433267198e-05,
+      "loss": 0.0038,
+      "step": 40
+    },
+    {
+      "epoch": 0.4424778761061947,
+      "grad_norm": 0.013299869373440742,
+      "learning_rate": 5.8986456074589404e-05,
+      "loss": 0.0038,
+      "step": 50
+    },
+    {
+      "epoch": 0.5309734513274337,
+      "grad_norm": 0.08473875373601913,
+      "learning_rate": 4.5142375815355706e-05,
+      "loss": 0.0037,
+      "step": 60
+    },
+    {
+      "epoch": 0.5309734513274337,
+      "eval_loss": 0.0035941482055932283,
+      "eval_runtime": 56.1024,
+      "eval_samples_per_second": 8.912,
+      "eval_steps_per_second": 0.232,
+      "step": 60
+    },
+    {
+      "epoch": 0.6194690265486725,
+      "grad_norm": 0.008843529969453812,
+      "learning_rate": 3.167134605250938e-05,
+      "loss": 0.0037,
+      "step": 70
+    },
+    {
+      "epoch": 0.7079646017699115,
+      "grad_norm": 0.006533902138471603,
+      "learning_rate": 1.960790016056801e-05,
+      "loss": 0.0036,
+      "step": 80
+    },
+    {
+      "epoch": 0.7964601769911505,
+      "grad_norm": 0.06442264467477798,
+      "learning_rate": 9.878473431161767e-06,
+      "loss": 0.0035,
+      "step": 90
+    },
+    {
+      "epoch": 0.7964601769911505,
+      "eval_loss": 0.003458332037553191,
+      "eval_runtime": 56.0617,
+      "eval_samples_per_second": 8.919,
+      "eval_steps_per_second": 0.232,
+      "step": 90
+    },
+    {
+      "epoch": 0.8849557522123894,
+      "grad_norm": 0.06732333451509476,
+      "learning_rate": 3.230255711220992e-06,
+      "loss": 0.0034,
+      "step": 100
+    },
+    {
+      "epoch": 0.9734513274336283,
+      "grad_norm": 0.01167540717869997,
+      "learning_rate": 1.7380953630678488e-07,
+      "loss": 0.0035,
+      "step": 110
+    },
+    {
+      "epoch": 1.0,
+      "step": 113,
+      "total_flos": 4.179655240942879e+17,
+      "train_loss": 0.042722021724072703,
+      "train_runtime": 1759.0892,
+      "train_samples_per_second": 2.558,
+      "train_steps_per_second": 0.064
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 113,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4.179655240942879e+17,
+  "train_batch_size": 10,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01687fe13b6d2acb8aad42cae42ab3c27f8a0188559a24b4698d38478233a06e
+size 5496