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-450/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,73 @@
+---
+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_10000_mcq_f_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_10000_mcq_f_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_10000_mcq_f dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0006
+
+## 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 |
+|:-------------:|:------:|:----:|:---------------:|
+| 0.0024        | 0.1111 | 50   | 0.0013          |
+| 0.0011        | 0.2222 | 100  | 0.0010          |
+| 0.0009        | 0.3333 | 150  | 0.0008          |
+| 0.001         | 0.4444 | 200  | 0.0008          |
+| 0.0009        | 0.5556 | 250  | 0.0008          |
+| 0.0006        | 0.6667 | 300  | 0.0007          |
+| 0.0007        | 0.7778 | 350  | 0.0007          |
+| 0.0007        | 0.8889 | 400  | 0.0006          |
+| 0.0009        | 1.0    | 450  | 0.0006          |
+
+
+### 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": [
+    "k_proj",
+    "q_proj",
+    "down_proj",
+    "v_proj",
+    "gate_proj",
+    "o_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:d5e7c84c8cdbec83fe3908d5e37d47b4dc81a88de4ae7a29044f5dbe32ce20d7
+size 114106856

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 0.0006301100365817547,
+    "eval_runtime": 232.4954,
+    "eval_samples_per_second": 4.301,
+    "eval_steps_per_second": 0.215,
+    "total_flos": 9.625596140737004e+17,
+    "train_loss": 0.014024514413128297,
+    "train_runtime": 8823.7876,
+    "train_samples_per_second": 1.02,
+    "train_steps_per_second": 0.051
+}

checkpoint-450/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-450/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": [
+    "k_proj",
+    "q_proj",
+    "down_proj",
+    "v_proj",
+    "gate_proj",
+    "o_proj",
+    "up_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-450/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d5e7c84c8cdbec83fe3908d5e37d47b4dc81a88de4ae7a29044f5dbe32ce20d7
+size 114106856

checkpoint-450/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1cd37b5b577649f766dac29859ce40dff0e0b6ba62d7e0407dfe3211e7595e3
+size 228536930

checkpoint-450/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b074bf97f241c2662caa5ce956b03d1249c3cc0713b6aef7796673362754f98
+size 14512

checkpoint-450/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58aed9e8d78903cb12015375021c729c3f6c5fd1a1e19e7aee6ddde57c3310b9
+size 14512

checkpoint-450/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9636ae38b683f4b5b714bdf172e563b0c593e0efe94f07eea78547963bfbfae
+size 1064

checkpoint-450/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-450/tokenizer.json

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

checkpoint-450/trainer_state.json

@@ -0,0 +1,259 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 50,
+  "global_step": 450,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.044444444444444446,
+      "grad_norm": 0.17305362224578857,
+      "learning_rate": 9.951340343707852e-05,
+      "loss": 0.2942,
+      "step": 20
+    },
+    {
+      "epoch": 0.08888888888888889,
+      "grad_norm": 0.042544737458229065,
+      "learning_rate": 9.806308479691595e-05,
+      "loss": 0.0024,
+      "step": 40
+    },
+    {
+      "epoch": 0.1111111111111111,
+      "eval_loss": 0.0013170767342671752,
+      "eval_runtime": 232.8005,
+      "eval_samples_per_second": 4.296,
+      "eval_steps_per_second": 0.215,
+      "step": 50
+    },
+    {
+      "epoch": 0.13333333333333333,
+      "grad_norm": 0.03146813064813614,
+      "learning_rate": 9.567727288213005e-05,
+      "loss": 0.0012,
+      "step": 60
+    },
+    {
+      "epoch": 0.17777777777777778,
+      "grad_norm": 0.03375430032610893,
+      "learning_rate": 9.24024048078213e-05,
+      "loss": 0.0012,
+      "step": 80
+    },
+    {
+      "epoch": 0.2222222222222222,
+      "grad_norm": 0.0878819078207016,
+      "learning_rate": 8.83022221559489e-05,
+      "loss": 0.0011,
+      "step": 100
+    },
+    {
+      "epoch": 0.2222222222222222,
+      "eval_loss": 0.000957556301727891,
+      "eval_runtime": 232.4585,
+      "eval_samples_per_second": 4.302,
+      "eval_steps_per_second": 0.215,
+      "step": 100
+    },
+    {
+      "epoch": 0.26666666666666666,
+      "grad_norm": 0.03542569652199745,
+      "learning_rate": 8.345653031794292e-05,
+      "loss": 0.0012,
+      "step": 120
+    },
+    {
+      "epoch": 0.3111111111111111,
+      "grad_norm": 0.015578300692141056,
+      "learning_rate": 7.795964517353735e-05,
+      "loss": 0.0009,
+      "step": 140
+    },
+    {
+      "epoch": 0.3333333333333333,
+      "eval_loss": 0.0007864935323596001,
+      "eval_runtime": 232.695,
+      "eval_samples_per_second": 4.297,
+      "eval_steps_per_second": 0.215,
+      "step": 150
+    },
+    {
+      "epoch": 0.35555555555555557,
+      "grad_norm": 0.029168328270316124,
+      "learning_rate": 7.191855733945387e-05,
+      "loss": 0.001,
+      "step": 160
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.05920561030507088,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 0.001,
+      "step": 180
+    },
+    {
+      "epoch": 0.4444444444444444,
+      "grad_norm": 0.03357287123799324,
+      "learning_rate": 5.868240888334653e-05,
+      "loss": 0.001,
+      "step": 200
+    },
+    {
+      "epoch": 0.4444444444444444,
+      "eval_loss": 0.0008135823300108314,
+      "eval_runtime": 232.395,
+      "eval_samples_per_second": 4.303,
+      "eval_steps_per_second": 0.215,
+      "step": 200
+    },
+    {
+      "epoch": 0.4888888888888889,
+      "grad_norm": 0.019826048985123634,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 0.0011,
+      "step": 220
+    },
+    {
+      "epoch": 0.5333333333333333,
+      "grad_norm": 0.025309834629297256,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 0.0009,
+      "step": 240
+    },
+    {
+      "epoch": 0.5555555555555556,
+      "eval_loss": 0.0007757659768685699,
+      "eval_runtime": 232.3457,
+      "eval_samples_per_second": 4.304,
+      "eval_steps_per_second": 0.215,
+      "step": 250
+    },
+    {
+      "epoch": 0.5777777777777777,
+      "grad_norm": 0.016265789046883583,
+      "learning_rate": 3.790390522001662e-05,
+      "loss": 0.0011,
+      "step": 260
+    },
+    {
+      "epoch": 0.6222222222222222,
+      "grad_norm": 0.0712108463048935,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 0.0008,
+      "step": 280
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 0.04358217492699623,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.0006,
+      "step": 300
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "eval_loss": 0.000731022737454623,
+      "eval_runtime": 232.45,
+      "eval_samples_per_second": 4.302,
+      "eval_steps_per_second": 0.215,
+      "step": 300
+    },
+    {
+      "epoch": 0.7111111111111111,
+      "grad_norm": 0.02700887806713581,
+      "learning_rate": 1.9216926233717085e-05,
+      "loss": 0.0008,
+      "step": 320
+    },
+    {
+      "epoch": 0.7555555555555555,
+      "grad_norm": 0.02106143906712532,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 0.0007,
+      "step": 340
+    },
+    {
+      "epoch": 0.7777777777777778,
+      "eval_loss": 0.0006801169947721064,
+      "eval_runtime": 232.1532,
+      "eval_samples_per_second": 4.307,
+      "eval_steps_per_second": 0.215,
+      "step": 350
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.020221324637532234,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.0007,
+      "step": 360
+    },
+    {
+      "epoch": 0.8444444444444444,
+      "grad_norm": 0.020666765049099922,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 0.0008,
+      "step": 380
+    },
+    {
+      "epoch": 0.8888888888888888,
+      "grad_norm": 0.00924940500408411,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 0.0007,
+      "step": 400
+    },
+    {
+      "epoch": 0.8888888888888888,
+      "eval_loss": 0.0006416882388293743,
+      "eval_runtime": 232.5441,
+      "eval_samples_per_second": 4.3,
+      "eval_steps_per_second": 0.215,
+      "step": 400
+    },
+    {
+      "epoch": 0.9333333333333333,
+      "grad_norm": 0.028802907094359398,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 0.0007,
+      "step": 420
+    },
+    {
+      "epoch": 0.9777777777777777,
+      "grad_norm": 0.035981908440589905,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 0.0009,
+      "step": 440
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.0006301100365817547,
+      "eval_runtime": 232.5439,
+      "eval_samples_per_second": 4.3,
+      "eval_steps_per_second": 0.215,
+      "step": 450
+    }
+  ],
+  "logging_steps": 20,
+  "max_steps": 450,
+  "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": 9.625596140737004e+17,
+  "train_batch_size": 10,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-450/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad19aba8a23cc06b0e2c26d83432b5ddb611baa6e7757f637c6010516477c92d
+size 5496

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 0.0006301100365817547,
+    "eval_runtime": 232.4954,
+    "eval_samples_per_second": 4.301,
+    "eval_steps_per_second": 0.215
+}

runs/Jan31_21-28-47_ctua-interactive-pod/events.out.tfevents.1738358944.ctua-interactive-pod.2612.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd99495bef2a222439a674f04fece843af3e33b937b291eb64e72b97b312c90e
+size 9394

runs/Jan31_23-07-26_ctua-interactive-pod/events.out.tfevents.1738364865.ctua-interactive-pod.3233.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed34c0ee819e2a36d2d634a7c422d53e1eb8071d31378d344f3612b18a5ba3c5
+size 12731

runs/Jan31_23-07-26_ctua-interactive-pod/events.out.tfevents.1738373922.ctua-interactive-pod.3233.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:030e02c8a9fb515b6c8b57d2519ce40694d4757a01b16d09e733d5de507ba36a
+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": 9.625596140737004e+17,
+    "train_loss": 0.014024514413128297,
+    "train_runtime": 8823.7876,
+    "train_samples_per_second": 1.02,
+    "train_steps_per_second": 0.051
+}

trainer_log.jsonl

@@ -0,0 +1,32 @@
+{"current_steps": 20, "total_steps": 450, "loss": 0.2942, "lr": 9.951340343707852e-05, "epoch": 0.044444444444444446, "percentage": 4.44, "elapsed_time": "0:04:59", "remaining_time": "1:47:13"}
+{"current_steps": 40, "total_steps": 450, "loss": 0.0024, "lr": 9.806308479691595e-05, "epoch": 0.08888888888888889, "percentage": 8.89, "elapsed_time": "0:09:58", "remaining_time": "1:42:13"}
+{"current_steps": 50, "total_steps": 450, "eval_loss": 0.0013170767342671752, "epoch": 0.1111111111111111, "percentage": 11.11, "elapsed_time": "0:16:20", "remaining_time": "2:10:46"}
+{"current_steps": 60, "total_steps": 450, "loss": 0.0012, "lr": 9.567727288213005e-05, "epoch": 0.13333333333333333, "percentage": 13.33, "elapsed_time": "0:18:50", "remaining_time": "2:02:27"}
+{"current_steps": 80, "total_steps": 450, "loss": 0.0012, "lr": 9.24024048078213e-05, "epoch": 0.17777777777777778, "percentage": 17.78, "elapsed_time": "0:23:49", "remaining_time": "1:50:10"}
+{"current_steps": 100, "total_steps": 450, "loss": 0.0011, "lr": 8.83022221559489e-05, "epoch": 0.2222222222222222, "percentage": 22.22, "elapsed_time": "0:28:48", "remaining_time": "1:40:49"}
+{"current_steps": 100, "total_steps": 450, "eval_loss": 0.000957556301727891, "epoch": 0.2222222222222222, "percentage": 22.22, "elapsed_time": "0:32:40", "remaining_time": "1:54:23"}
+{"current_steps": 120, "total_steps": 450, "loss": 0.0012, "lr": 8.345653031794292e-05, "epoch": 0.26666666666666666, "percentage": 26.67, "elapsed_time": "0:37:39", "remaining_time": "1:43:34"}
+{"current_steps": 140, "total_steps": 450, "loss": 0.0009, "lr": 7.795964517353735e-05, "epoch": 0.3111111111111111, "percentage": 31.11, "elapsed_time": "0:42:39", "remaining_time": "1:34:26"}
+{"current_steps": 150, "total_steps": 450, "eval_loss": 0.0007864935323596001, "epoch": 0.3333333333333333, "percentage": 33.33, "elapsed_time": "0:49:01", "remaining_time": "1:38:03"}
+{"current_steps": 160, "total_steps": 450, "loss": 0.001, "lr": 7.191855733945387e-05, "epoch": 0.35555555555555557, "percentage": 35.56, "elapsed_time": "0:51:31", "remaining_time": "1:33:22"}
+{"current_steps": 180, "total_steps": 450, "loss": 0.001, "lr": 6.545084971874738e-05, "epoch": 0.4, "percentage": 40.0, "elapsed_time": "0:56:30", "remaining_time": "1:24:45"}
+{"current_steps": 200, "total_steps": 450, "loss": 0.001, "lr": 5.868240888334653e-05, "epoch": 0.4444444444444444, "percentage": 44.44, "elapsed_time": "1:01:29", "remaining_time": "1:16:51"}
+{"current_steps": 200, "total_steps": 450, "eval_loss": 0.0008135823300108314, "epoch": 0.4444444444444444, "percentage": 44.44, "elapsed_time": "1:05:21", "remaining_time": "1:21:42"}
+{"current_steps": 220, "total_steps": 450, "loss": 0.0011, "lr": 5.174497483512506e-05, "epoch": 0.4888888888888889, "percentage": 48.89, "elapsed_time": "1:10:20", "remaining_time": "1:13:32"}
+{"current_steps": 240, "total_steps": 450, "loss": 0.0009, "lr": 4.477357683661734e-05, "epoch": 0.5333333333333333, "percentage": 53.33, "elapsed_time": "1:15:19", "remaining_time": "1:05:54"}
+{"current_steps": 250, "total_steps": 450, "eval_loss": 0.0007757659768685699, "epoch": 0.5555555555555556, "percentage": 55.56, "elapsed_time": "1:21:41", "remaining_time": "1:05:21"}
+{"current_steps": 260, "total_steps": 450, "loss": 0.0011, "lr": 3.790390522001662e-05, "epoch": 0.5777777777777777, "percentage": 57.78, "elapsed_time": "1:24:11", "remaining_time": "1:01:31"}
+{"current_steps": 280, "total_steps": 450, "loss": 0.0008, "lr": 3.12696703292044e-05, "epoch": 0.6222222222222222, "percentage": 62.22, "elapsed_time": "1:29:10", "remaining_time": "0:54:08"}
+{"current_steps": 300, "total_steps": 450, "loss": 0.0006, "lr": 2.500000000000001e-05, "epoch": 0.6666666666666666, "percentage": 66.67, "elapsed_time": "1:34:09", "remaining_time": "0:47:04"}
+{"current_steps": 300, "total_steps": 450, "eval_loss": 0.000731022737454623, "epoch": 0.6666666666666666, "percentage": 66.67, "elapsed_time": "1:38:01", "remaining_time": "0:49:00"}
+{"current_steps": 320, "total_steps": 450, "loss": 0.0008, "lr": 1.9216926233717085e-05, "epoch": 0.7111111111111111, "percentage": 71.11, "elapsed_time": "1:43:00", "remaining_time": "0:41:50"}
+{"current_steps": 340, "total_steps": 450, "loss": 0.0007, "lr": 1.4033009983067452e-05, "epoch": 0.7555555555555555, "percentage": 75.56, "elapsed_time": "1:47:59", "remaining_time": "0:34:56"}
+{"current_steps": 350, "total_steps": 450, "eval_loss": 0.0006801169947721064, "epoch": 0.7777777777777778, "percentage": 77.78, "elapsed_time": "1:54:20", "remaining_time": "0:32:40"}
+{"current_steps": 360, "total_steps": 450, "loss": 0.0007, "lr": 9.549150281252633e-06, "epoch": 0.8, "percentage": 80.0, "elapsed_time": "1:56:50", "remaining_time": "0:29:12"}
+{"current_steps": 380, "total_steps": 450, "loss": 0.0008, "lr": 5.852620357053651e-06, "epoch": 0.8444444444444444, "percentage": 84.44, "elapsed_time": "2:01:48", "remaining_time": "0:22:26"}
+{"current_steps": 400, "total_steps": 450, "loss": 0.0007, "lr": 3.0153689607045845e-06, "epoch": 0.8888888888888888, "percentage": 88.89, "elapsed_time": "2:06:47", "remaining_time": "0:15:50"}
+{"current_steps": 400, "total_steps": 450, "eval_loss": 0.0006416882388293743, "epoch": 0.8888888888888888, "percentage": 88.89, "elapsed_time": "2:10:40", "remaining_time": "0:16:20"}
+{"current_steps": 420, "total_steps": 450, "loss": 0.0007, "lr": 1.0926199633097157e-06, "epoch": 0.9333333333333333, "percentage": 93.33, "elapsed_time": "2:15:39", "remaining_time": "0:09:41"}
+{"current_steps": 440, "total_steps": 450, "loss": 0.0009, "lr": 1.2179748700879012e-07, "epoch": 0.9777777777777777, "percentage": 97.78, "elapsed_time": "2:20:38", "remaining_time": "0:03:11"}
+{"current_steps": 450, "total_steps": 450, "eval_loss": 0.0006301100365817547, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "2:27:00", "remaining_time": "0:00:00"}
+{"current_steps": 450, "total_steps": 450, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "2:27:01", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,268 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 50,
+  "global_step": 450,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.044444444444444446,
+      "grad_norm": 0.17305362224578857,
+      "learning_rate": 9.951340343707852e-05,
+      "loss": 0.2942,
+      "step": 20
+    },
+    {
+      "epoch": 0.08888888888888889,
+      "grad_norm": 0.042544737458229065,
+      "learning_rate": 9.806308479691595e-05,
+      "loss": 0.0024,
+      "step": 40
+    },
+    {
+      "epoch": 0.1111111111111111,
+      "eval_loss": 0.0013170767342671752,
+      "eval_runtime": 232.8005,
+      "eval_samples_per_second": 4.296,
+      "eval_steps_per_second": 0.215,
+      "step": 50
+    },
+    {
+      "epoch": 0.13333333333333333,
+      "grad_norm": 0.03146813064813614,
+      "learning_rate": 9.567727288213005e-05,
+      "loss": 0.0012,
+      "step": 60
+    },
+    {
+      "epoch": 0.17777777777777778,
+      "grad_norm": 0.03375430032610893,
+      "learning_rate": 9.24024048078213e-05,
+      "loss": 0.0012,
+      "step": 80
+    },
+    {
+      "epoch": 0.2222222222222222,
+      "grad_norm": 0.0878819078207016,
+      "learning_rate": 8.83022221559489e-05,
+      "loss": 0.0011,
+      "step": 100
+    },
+    {
+      "epoch": 0.2222222222222222,
+      "eval_loss": 0.000957556301727891,
+      "eval_runtime": 232.4585,
+      "eval_samples_per_second": 4.302,
+      "eval_steps_per_second": 0.215,
+      "step": 100
+    },
+    {
+      "epoch": 0.26666666666666666,
+      "grad_norm": 0.03542569652199745,
+      "learning_rate": 8.345653031794292e-05,
+      "loss": 0.0012,
+      "step": 120
+    },
+    {
+      "epoch": 0.3111111111111111,
+      "grad_norm": 0.015578300692141056,
+      "learning_rate": 7.795964517353735e-05,
+      "loss": 0.0009,
+      "step": 140
+    },
+    {
+      "epoch": 0.3333333333333333,
+      "eval_loss": 0.0007864935323596001,
+      "eval_runtime": 232.695,
+      "eval_samples_per_second": 4.297,
+      "eval_steps_per_second": 0.215,
+      "step": 150
+    },
+    {
+      "epoch": 0.35555555555555557,
+      "grad_norm": 0.029168328270316124,
+      "learning_rate": 7.191855733945387e-05,
+      "loss": 0.001,
+      "step": 160
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.05920561030507088,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 0.001,
+      "step": 180
+    },
+    {
+      "epoch": 0.4444444444444444,
+      "grad_norm": 0.03357287123799324,
+      "learning_rate": 5.868240888334653e-05,
+      "loss": 0.001,
+      "step": 200
+    },
+    {
+      "epoch": 0.4444444444444444,
+      "eval_loss": 0.0008135823300108314,
+      "eval_runtime": 232.395,
+      "eval_samples_per_second": 4.303,
+      "eval_steps_per_second": 0.215,
+      "step": 200
+    },
+    {
+      "epoch": 0.4888888888888889,
+      "grad_norm": 0.019826048985123634,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 0.0011,
+      "step": 220
+    },
+    {
+      "epoch": 0.5333333333333333,
+      "grad_norm": 0.025309834629297256,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 0.0009,
+      "step": 240
+    },
+    {
+      "epoch": 0.5555555555555556,
+      "eval_loss": 0.0007757659768685699,
+      "eval_runtime": 232.3457,
+      "eval_samples_per_second": 4.304,
+      "eval_steps_per_second": 0.215,
+      "step": 250
+    },
+    {
+      "epoch": 0.5777777777777777,
+      "grad_norm": 0.016265789046883583,
+      "learning_rate": 3.790390522001662e-05,
+      "loss": 0.0011,
+      "step": 260
+    },
+    {
+      "epoch": 0.6222222222222222,
+      "grad_norm": 0.0712108463048935,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 0.0008,
+      "step": 280
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 0.04358217492699623,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.0006,
+      "step": 300
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "eval_loss": 0.000731022737454623,
+      "eval_runtime": 232.45,
+      "eval_samples_per_second": 4.302,
+      "eval_steps_per_second": 0.215,
+      "step": 300
+    },
+    {
+      "epoch": 0.7111111111111111,
+      "grad_norm": 0.02700887806713581,
+      "learning_rate": 1.9216926233717085e-05,
+      "loss": 0.0008,
+      "step": 320
+    },
+    {
+      "epoch": 0.7555555555555555,
+      "grad_norm": 0.02106143906712532,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 0.0007,
+      "step": 340
+    },
+    {
+      "epoch": 0.7777777777777778,
+      "eval_loss": 0.0006801169947721064,
+      "eval_runtime": 232.1532,
+      "eval_samples_per_second": 4.307,
+      "eval_steps_per_second": 0.215,
+      "step": 350
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.020221324637532234,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.0007,
+      "step": 360
+    },
+    {
+      "epoch": 0.8444444444444444,
+      "grad_norm": 0.020666765049099922,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 0.0008,
+      "step": 380
+    },
+    {
+      "epoch": 0.8888888888888888,
+      "grad_norm": 0.00924940500408411,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 0.0007,
+      "step": 400
+    },
+    {
+      "epoch": 0.8888888888888888,
+      "eval_loss": 0.0006416882388293743,
+      "eval_runtime": 232.5441,
+      "eval_samples_per_second": 4.3,
+      "eval_steps_per_second": 0.215,
+      "step": 400
+    },
+    {
+      "epoch": 0.9333333333333333,
+      "grad_norm": 0.028802907094359398,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 0.0007,
+      "step": 420
+    },
+    {
+      "epoch": 0.9777777777777777,
+      "grad_norm": 0.035981908440589905,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 0.0009,
+      "step": 440
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.0006301100365817547,
+      "eval_runtime": 232.5439,
+      "eval_samples_per_second": 4.3,
+      "eval_steps_per_second": 0.215,
+      "step": 450
+    },
+    {
+      "epoch": 1.0,
+      "step": 450,
+      "total_flos": 9.625596140737004e+17,
+      "train_loss": 0.014024514413128297,
+      "train_runtime": 8823.7876,
+      "train_samples_per_second": 1.02,
+      "train_steps_per_second": 0.051
+    }
+  ],
+  "logging_steps": 20,
+  "max_steps": 450,
+  "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": 9.625596140737004e+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:ad19aba8a23cc06b0e2c26d83432b5ddb611baa6e7757f637c6010516477c92d
+size 5496