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-219/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,68 @@
+---
+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_u_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_u_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_u dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0042
+
+## 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: 2
+- total_train_batch_size: 20
+- total_eval_batch_size: 20
+- 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 |
+|:-------------:|:------:|:----:|:---------------:|
+| 0.0075        | 0.2283 | 50   | 0.0059          |
+| 0.0057        | 0.4566 | 100  | 0.0054          |
+| 0.0051        | 0.6849 | 150  | 0.0049          |
+| 0.0043        | 0.9132 | 200  | 0.0042          |
+
+
+### 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",
+    "gate_proj",
+    "k_proj",
+    "up_proj",
+    "o_proj",
+    "v_proj",
+    "down_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:edd469932dbcef3fe4de908caabd615a305dc2db865690f80ef63eefcaf9c815
+size 114106856

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 0.00418016966432333,
+    "eval_runtime": 62.5337,
+    "eval_samples_per_second": 7.788,
+    "eval_steps_per_second": 0.4,
+    "total_flos": 4.685177916793815e+17,
+    "train_loss": 0.03597381513684852,
+    "train_runtime": 2055.0645,
+    "train_samples_per_second": 2.13,
+    "train_steps_per_second": 0.107
+}

checkpoint-219/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-219/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",
+    "gate_proj",
+    "k_proj",
+    "up_proj",
+    "o_proj",
+    "v_proj",
+    "down_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-219/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:edd469932dbcef3fe4de908caabd615a305dc2db865690f80ef63eefcaf9c815
+size 114106856

checkpoint-219/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e3a62989a28ecdf951d72ea0fd5a90d21b11e17fe4f0cd58f286a429aa9f735
+size 228536930

checkpoint-219/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7e52325e9d729519836af640f8f754a93ee06730fb2953b5309434b53b17562
+size 14512

checkpoint-219/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a93593cf0342eb47876986e1063102e1546354426a2324c46ddcf1cbecae803
+size 14512

checkpoint-219/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb42eaa476d66164742d8e57c54ee1c2ea541bedefcf1ea63778a36c221c9563
+size 1064

checkpoint-219/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-219/tokenizer.json

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

checkpoint-219/trainer_state.json

@@ -0,0 +1,135 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 50,
+  "global_step": 219,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.091324200913242,
+      "grad_norm": 0.17780767381191254,
+      "learning_rate": 9.79562374273544e-05,
+      "loss": 0.3412,
+      "step": 20
+    },
+    {
+      "epoch": 0.182648401826484,
+      "grad_norm": 0.06632925570011139,
+      "learning_rate": 9.19920283275515e-05,
+      "loss": 0.0075,
+      "step": 40
+    },
+    {
+      "epoch": 0.228310502283105,
+      "eval_loss": 0.005886094179004431,
+      "eval_runtime": 62.5805,
+      "eval_samples_per_second": 7.782,
+      "eval_steps_per_second": 0.399,
+      "step": 50
+    },
+    {
+      "epoch": 0.273972602739726,
+      "grad_norm": 0.0776129812002182,
+      "learning_rate": 8.259494979393563e-05,
+      "loss": 0.0059,
+      "step": 60
+    },
+    {
+      "epoch": 0.365296803652968,
+      "grad_norm": 0.025069398805499077,
+      "learning_rate": 7.053321772247545e-05,
+      "loss": 0.0054,
+      "step": 80
+    },
+    {
+      "epoch": 0.45662100456621,
+      "grad_norm": 0.06095319241285324,
+      "learning_rate": 5.679288477592815e-05,
+      "loss": 0.0057,
+      "step": 100
+    },
+    {
+      "epoch": 0.45662100456621,
+      "eval_loss": 0.00544710224494338,
+      "eval_runtime": 62.5695,
+      "eval_samples_per_second": 7.783,
+      "eval_steps_per_second": 0.4,
+      "step": 100
+    },
+    {
+      "epoch": 0.547945205479452,
+      "grad_norm": 0.034162312746047974,
+      "learning_rate": 4.249723008276737e-05,
+      "loss": 0.0053,
+      "step": 120
+    },
+    {
+      "epoch": 0.639269406392694,
+      "grad_norm": 0.030082939192652702,
+      "learning_rate": 2.8814930603527068e-05,
+      "loss": 0.0051,
+      "step": 140
+    },
+    {
+      "epoch": 0.684931506849315,
+      "eval_loss": 0.0049239168874919415,
+      "eval_runtime": 62.5741,
+      "eval_samples_per_second": 7.783,
+      "eval_steps_per_second": 0.4,
+      "step": 150
+    },
+    {
+      "epoch": 0.730593607305936,
+      "grad_norm": 0.026808856055140495,
+      "learning_rate": 1.6864521201543197e-05,
+      "loss": 0.005,
+      "step": 160
+    },
+    {
+      "epoch": 0.821917808219178,
+      "grad_norm": 0.0478011779487133,
+      "learning_rate": 7.6229538553584556e-06,
+      "loss": 0.0045,
+      "step": 180
+    },
+    {
+      "epoch": 0.91324200913242,
+      "grad_norm": 0.05524557828903198,
+      "learning_rate": 1.8457313431614498e-06,
+      "loss": 0.0043,
+      "step": 200
+    },
+    {
+      "epoch": 0.91324200913242,
+      "eval_loss": 0.00419235322624445,
+      "eval_runtime": 62.5256,
+      "eval_samples_per_second": 7.789,
+      "eval_steps_per_second": 0.4,
+      "step": 200
+    }
+  ],
+  "logging_steps": 20,
+  "max_steps": 219,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 2000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4.685177916793815e+17,
+  "train_batch_size": 10,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-219/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d5745adeac0a583efb8c7e43be81c0c942e5339d60a828e8a9f67d31cdb7653a
+size 5496

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 0.00418016966432333,
+    "eval_runtime": 62.5337,
+    "eval_samples_per_second": 7.788,
+    "eval_steps_per_second": 0.4
+}

runs/Feb01_00-50-55_ctua-interactive-pod-1/events.out.tfevents.1738371070.ctua-interactive-pod-1.1693.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dfa0e221f2093961b36a4fca1099735fbc5353afb844b63594ba623b06355b64
+size 8843

runs/Feb01_00-50-55_ctua-interactive-pod-1/events.out.tfevents.1738373188.ctua-interactive-pod-1.1693.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb392e957fddba59c1556b9162c8d2076ff3d977bb465278c3f4a54a1367a03d
+size 359

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": 4.685177916793815e+17,
+    "train_loss": 0.03597381513684852,
+    "train_runtime": 2055.0645,
+    "train_samples_per_second": 2.13,
+    "train_steps_per_second": 0.107
+}

trainer_log.jsonl

@@ -0,0 +1,15 @@
+{"current_steps": 20, "total_steps": 219, "loss": 0.3412, "lr": 9.79562374273544e-05, "epoch": 0.091324200913242, "percentage": 9.13, "elapsed_time": "0:02:45", "remaining_time": "0:27:29"}
+{"current_steps": 40, "total_steps": 219, "loss": 0.0075, "lr": 9.19920283275515e-05, "epoch": 0.182648401826484, "percentage": 18.26, "elapsed_time": "0:05:30", "remaining_time": "0:24:40"}
+{"current_steps": 50, "total_steps": 219, "eval_loss": 0.005886094179004431, "epoch": 0.228310502283105, "percentage": 22.83, "elapsed_time": "0:07:55", "remaining_time": "0:26:46"}
+{"current_steps": 60, "total_steps": 219, "loss": 0.0059, "lr": 8.259494979393563e-05, "epoch": 0.273972602739726, "percentage": 27.4, "elapsed_time": "0:09:17", "remaining_time": "0:24:37"}
+{"current_steps": 80, "total_steps": 219, "loss": 0.0054, "lr": 7.053321772247545e-05, "epoch": 0.365296803652968, "percentage": 36.53, "elapsed_time": "0:12:02", "remaining_time": "0:20:55"}
+{"current_steps": 100, "total_steps": 219, "loss": 0.0057, "lr": 5.679288477592815e-05, "epoch": 0.45662100456621, "percentage": 45.66, "elapsed_time": "0:14:47", "remaining_time": "0:17:35"}
+{"current_steps": 100, "total_steps": 219, "eval_loss": 0.00544710224494338, "epoch": 0.45662100456621, "percentage": 45.66, "elapsed_time": "0:15:49", "remaining_time": "0:18:49"}
+{"current_steps": 120, "total_steps": 219, "loss": 0.0053, "lr": 4.249723008276737e-05, "epoch": 0.547945205479452, "percentage": 54.79, "elapsed_time": "0:18:34", "remaining_time": "0:15:19"}
+{"current_steps": 140, "total_steps": 219, "loss": 0.0051, "lr": 2.8814930603527068e-05, "epoch": 0.639269406392694, "percentage": 63.93, "elapsed_time": "0:21:18", "remaining_time": "0:12:01"}
+{"current_steps": 150, "total_steps": 219, "eval_loss": 0.0049239168874919415, "epoch": 0.684931506849315, "percentage": 68.49, "elapsed_time": "0:23:43", "remaining_time": "0:10:54"}
+{"current_steps": 160, "total_steps": 219, "loss": 0.005, "lr": 1.6864521201543197e-05, "epoch": 0.730593607305936, "percentage": 73.06, "elapsed_time": "0:25:06", "remaining_time": "0:09:15"}
+{"current_steps": 180, "total_steps": 219, "loss": 0.0045, "lr": 7.6229538553584556e-06, "epoch": 0.821917808219178, "percentage": 82.19, "elapsed_time": "0:27:50", "remaining_time": "0:06:01"}
+{"current_steps": 200, "total_steps": 219, "loss": 0.0043, "lr": 1.8457313431614498e-06, "epoch": 0.91324200913242, "percentage": 91.32, "elapsed_time": "0:30:34", "remaining_time": "0:02:54"}
+{"current_steps": 200, "total_steps": 219, "eval_loss": 0.00419235322624445, "epoch": 0.91324200913242, "percentage": 91.32, "elapsed_time": "0:31:36", "remaining_time": "0:03:00"}
+{"current_steps": 219, "total_steps": 219, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "0:34:14", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,144 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 50,
+  "global_step": 219,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.091324200913242,
+      "grad_norm": 0.17780767381191254,
+      "learning_rate": 9.79562374273544e-05,
+      "loss": 0.3412,
+      "step": 20
+    },
+    {
+      "epoch": 0.182648401826484,
+      "grad_norm": 0.06632925570011139,
+      "learning_rate": 9.19920283275515e-05,
+      "loss": 0.0075,
+      "step": 40
+    },
+    {
+      "epoch": 0.228310502283105,
+      "eval_loss": 0.005886094179004431,
+      "eval_runtime": 62.5805,
+      "eval_samples_per_second": 7.782,
+      "eval_steps_per_second": 0.399,
+      "step": 50
+    },
+    {
+      "epoch": 0.273972602739726,
+      "grad_norm": 0.0776129812002182,
+      "learning_rate": 8.259494979393563e-05,
+      "loss": 0.0059,
+      "step": 60
+    },
+    {
+      "epoch": 0.365296803652968,
+      "grad_norm": 0.025069398805499077,
+      "learning_rate": 7.053321772247545e-05,
+      "loss": 0.0054,
+      "step": 80
+    },
+    {
+      "epoch": 0.45662100456621,
+      "grad_norm": 0.06095319241285324,
+      "learning_rate": 5.679288477592815e-05,
+      "loss": 0.0057,
+      "step": 100
+    },
+    {
+      "epoch": 0.45662100456621,
+      "eval_loss": 0.00544710224494338,
+      "eval_runtime": 62.5695,
+      "eval_samples_per_second": 7.783,
+      "eval_steps_per_second": 0.4,
+      "step": 100
+    },
+    {
+      "epoch": 0.547945205479452,
+      "grad_norm": 0.034162312746047974,
+      "learning_rate": 4.249723008276737e-05,
+      "loss": 0.0053,
+      "step": 120
+    },
+    {
+      "epoch": 0.639269406392694,
+      "grad_norm": 0.030082939192652702,
+      "learning_rate": 2.8814930603527068e-05,
+      "loss": 0.0051,
+      "step": 140
+    },
+    {
+      "epoch": 0.684931506849315,
+      "eval_loss": 0.0049239168874919415,
+      "eval_runtime": 62.5741,
+      "eval_samples_per_second": 7.783,
+      "eval_steps_per_second": 0.4,
+      "step": 150
+    },
+    {
+      "epoch": 0.730593607305936,
+      "grad_norm": 0.026808856055140495,
+      "learning_rate": 1.6864521201543197e-05,
+      "loss": 0.005,
+      "step": 160
+    },
+    {
+      "epoch": 0.821917808219178,
+      "grad_norm": 0.0478011779487133,
+      "learning_rate": 7.6229538553584556e-06,
+      "loss": 0.0045,
+      "step": 180
+    },
+    {
+      "epoch": 0.91324200913242,
+      "grad_norm": 0.05524557828903198,
+      "learning_rate": 1.8457313431614498e-06,
+      "loss": 0.0043,
+      "step": 200
+    },
+    {
+      "epoch": 0.91324200913242,
+      "eval_loss": 0.00419235322624445,
+      "eval_runtime": 62.5256,
+      "eval_samples_per_second": 7.789,
+      "eval_steps_per_second": 0.4,
+      "step": 200
+    },
+    {
+      "epoch": 1.0,
+      "step": 219,
+      "total_flos": 4.685177916793815e+17,
+      "train_loss": 0.03597381513684852,
+      "train_runtime": 2055.0645,
+      "train_samples_per_second": 2.13,
+      "train_steps_per_second": 0.107
+    }
+  ],
+  "logging_steps": 20,
+  "max_steps": 219,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 2000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4.685177916793815e+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:d5745adeac0a583efb8c7e43be81c0c942e5339d60a828e8a9f67d31cdb7653a
+size 5496