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-375/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,82 @@
+---
+base_model: mistralai/Mistral-Nemo-Instruct-2407
+library_name: peft
+license: other
+tags:
+- llama-factory
+- lora
+- generated_from_trainer
+model-index:
+- name: sft_10000_fs
+  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. -->
+
+# sft_10000_fs
+
+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_fs 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: 12
+- eval_batch_size: 12
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 2
+- total_train_batch_size: 24
+- total_eval_batch_size: 24
+- 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 |
+|:-------------:|:------:|:----:|:---------------:|
+| 0.0107        | 0.0533 | 20   | 0.0043          |
+| 0.0035        | 0.1067 | 40   | 0.0034          |
+| 0.0033        | 0.16   | 60   | 0.0027          |
+| 0.0018        | 0.2133 | 80   | 0.0018          |
+| 0.0025        | 0.2667 | 100  | 0.0019          |
+| 0.0019        | 0.32   | 120  | 0.0017          |
+| 0.0015        | 0.3733 | 140  | 0.0016          |
+| 0.0015        | 0.4267 | 160  | 0.0014          |
+| 0.0015        | 0.48   | 180  | 0.0017          |
+| 0.001         | 0.5333 | 200  | 0.0009          |
+| 0.0007        | 0.5867 | 220  | 0.0008          |
+| 0.0011        | 0.64   | 240  | 0.0008          |
+| 0.0008        | 0.6933 | 260  | 0.0011          |
+| 0.0006        | 0.7467 | 280  | 0.0009          |
+| 0.0008        | 0.8    | 300  | 0.0006          |
+| 0.0006        | 0.8533 | 320  | 0.0007          |
+| 0.0005        | 0.9067 | 340  | 0.0006          |
+| 0.0006        | 0.96   | 360  | 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": [
+    "q_proj",
+    "k_proj",
+    "v_proj",
+    "o_proj",
+    "up_proj",
+    "gate_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:a09837d818b51e7676d86a18f73f638c09c03291beb3409f36dbe763098bd816
+size 114106856

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 0.0005918259848840535,
+    "eval_runtime": 95.7064,
+    "eval_samples_per_second": 10.449,
+    "eval_steps_per_second": 0.439,
+    "total_flos": 7.369767647728108e+17,
+    "train_loss": 0.01518383183144033,
+    "train_runtime": 4516.1364,
+    "train_samples_per_second": 1.993,
+    "train_steps_per_second": 0.083
+}

checkpoint-375/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-375/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",
+    "k_proj",
+    "v_proj",
+    "o_proj",
+    "up_proj",
+    "gate_proj",
+    "down_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-375/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a09837d818b51e7676d86a18f73f638c09c03291beb3409f36dbe763098bd816
+size 114106856

checkpoint-375/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d366187047c79b3808cca503ab341418f806f1c04c9eade83a6991fb0e7918a6
+size 228536930

checkpoint-375/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55f6ef5fd81f87dc8a69f1b9a751ba37cc49c37318322e45ba4733ff23a92208
+size 14512

checkpoint-375/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f510db96e40d7f66609c96cf485c13417fc4eaf253603d2b6591466c3fb5f63a
+size 14512

checkpoint-375/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fb26bc53ca799837614c1432e218cd021d6e4c5d40aec448ad8c2526891e592
+size 1064

checkpoint-375/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-375/tokenizer.json

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

checkpoint-375/trainer_state.json

@@ -0,0 +1,436 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 20,
+  "global_step": 375,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02666666666666667,
+      "grad_norm": 0.6144651174545288,
+      "learning_rate": 9.982464296247522e-05,
+      "loss": 0.5086,
+      "step": 10
+    },
+    {
+      "epoch": 0.05333333333333334,
+      "grad_norm": 0.041260600090026855,
+      "learning_rate": 9.929980185352526e-05,
+      "loss": 0.0107,
+      "step": 20
+    },
+    {
+      "epoch": 0.05333333333333334,
+      "eval_loss": 0.004315248690545559,
+      "eval_runtime": 95.7488,
+      "eval_samples_per_second": 10.444,
+      "eval_steps_per_second": 0.439,
+      "step": 20
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.00790360290557146,
+      "learning_rate": 9.842915805643155e-05,
+      "loss": 0.004,
+      "step": 30
+    },
+    {
+      "epoch": 0.10666666666666667,
+      "grad_norm": 0.022915204986929893,
+      "learning_rate": 9.721881851187406e-05,
+      "loss": 0.0035,
+      "step": 40
+    },
+    {
+      "epoch": 0.10666666666666667,
+      "eval_loss": 0.0034025884233415127,
+      "eval_runtime": 95.7394,
+      "eval_samples_per_second": 10.445,
+      "eval_steps_per_second": 0.439,
+      "step": 40
+    },
+    {
+      "epoch": 0.13333333333333333,
+      "grad_norm": 0.026596330106258392,
+      "learning_rate": 9.567727288213005e-05,
+      "loss": 0.0034,
+      "step": 50
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.10935429483652115,
+      "learning_rate": 9.381533400219318e-05,
+      "loss": 0.0033,
+      "step": 60
+    },
+    {
+      "epoch": 0.16,
+      "eval_loss": 0.0027047081384807825,
+      "eval_runtime": 95.776,
+      "eval_samples_per_second": 10.441,
+      "eval_steps_per_second": 0.439,
+      "step": 60
+    },
+    {
+      "epoch": 0.18666666666666668,
+      "grad_norm": 0.1983339935541153,
+      "learning_rate": 9.164606203550497e-05,
+      "loss": 0.0024,
+      "step": 70
+    },
+    {
+      "epoch": 0.21333333333333335,
+      "grad_norm": 0.11285419017076492,
+      "learning_rate": 8.9184672866292e-05,
+      "loss": 0.0018,
+      "step": 80
+    },
+    {
+      "epoch": 0.21333333333333335,
+      "eval_loss": 0.001777145778760314,
+      "eval_runtime": 95.7123,
+      "eval_samples_per_second": 10.448,
+      "eval_steps_per_second": 0.439,
+      "step": 80
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 0.09023458510637283,
+      "learning_rate": 8.644843137107059e-05,
+      "loss": 0.0022,
+      "step": 90
+    },
+    {
+      "epoch": 0.26666666666666666,
+      "grad_norm": 0.0411541648209095,
+      "learning_rate": 8.345653031794292e-05,
+      "loss": 0.0025,
+      "step": 100
+    },
+    {
+      "epoch": 0.26666666666666666,
+      "eval_loss": 0.0019247803138568997,
+      "eval_runtime": 95.7325,
+      "eval_samples_per_second": 10.446,
+      "eval_steps_per_second": 0.439,
+      "step": 100
+    },
+    {
+      "epoch": 0.29333333333333333,
+      "grad_norm": 0.05165160447359085,
+      "learning_rate": 8.022995574311876e-05,
+      "loss": 0.0015,
+      "step": 110
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.11784542351961136,
+      "learning_rate": 7.679133974894983e-05,
+      "loss": 0.0019,
+      "step": 120
+    },
+    {
+      "epoch": 0.32,
+      "eval_loss": 0.00168008788023144,
+      "eval_runtime": 95.7517,
+      "eval_samples_per_second": 10.444,
+      "eval_steps_per_second": 0.439,
+      "step": 120
+    },
+    {
+      "epoch": 0.3466666666666667,
+      "grad_norm": 0.1648288369178772,
+      "learning_rate": 7.316480175599309e-05,
+      "loss": 0.0015,
+      "step": 130
+    },
+    {
+      "epoch": 0.37333333333333335,
+      "grad_norm": 0.064679816365242,
+      "learning_rate": 6.937577932260515e-05,
+      "loss": 0.0015,
+      "step": 140
+    },
+    {
+      "epoch": 0.37333333333333335,
+      "eval_loss": 0.001629200647585094,
+      "eval_runtime": 95.7474,
+      "eval_samples_per_second": 10.444,
+      "eval_steps_per_second": 0.439,
+      "step": 140
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.10296431183815002,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 0.0012,
+      "step": 150
+    },
+    {
+      "epoch": 0.4266666666666667,
+      "grad_norm": 0.020578118041157722,
+      "learning_rate": 6.141754350553279e-05,
+      "loss": 0.0015,
+      "step": 160
+    },
+    {
+      "epoch": 0.4266666666666667,
+      "eval_loss": 0.001399434870108962,
+      "eval_runtime": 95.7645,
+      "eval_samples_per_second": 10.442,
+      "eval_steps_per_second": 0.439,
+      "step": 160
+    },
+    {
+      "epoch": 0.4533333333333333,
+      "grad_norm": 0.036092739552259445,
+      "learning_rate": 5.730415142812059e-05,
+      "loss": 0.0015,
+      "step": 170
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.07469587028026581,
+      "learning_rate": 5.313952597646568e-05,
+      "loss": 0.0015,
+      "step": 180
+    },
+    {
+      "epoch": 0.48,
+      "eval_loss": 0.001668238895945251,
+      "eval_runtime": 95.6093,
+      "eval_samples_per_second": 10.459,
+      "eval_steps_per_second": 0.439,
+      "step": 180
+    },
+    {
+      "epoch": 0.5066666666666667,
+      "grad_norm": 0.012558485381305218,
+      "learning_rate": 4.895287900583216e-05,
+      "loss": 0.0013,
+      "step": 190
+    },
+    {
+      "epoch": 0.5333333333333333,
+      "grad_norm": 0.026587937027215958,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 0.001,
+      "step": 200
+    },
+    {
+      "epoch": 0.5333333333333333,
+      "eval_loss": 0.0009001157595776021,
+      "eval_runtime": 95.6055,
+      "eval_samples_per_second": 10.46,
+      "eval_steps_per_second": 0.439,
+      "step": 200
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.057403530925512314,
+      "learning_rate": 4.063093427071376e-05,
+      "loss": 0.001,
+      "step": 210
+    },
+    {
+      "epoch": 0.5866666666666667,
+      "grad_norm": 0.03403661027550697,
+      "learning_rate": 3.655400896923672e-05,
+      "loss": 0.0007,
+      "step": 220
+    },
+    {
+      "epoch": 0.5866666666666667,
+      "eval_loss": 0.0007602078258059919,
+      "eval_runtime": 95.6123,
+      "eval_samples_per_second": 10.459,
+      "eval_steps_per_second": 0.439,
+      "step": 220
+    },
+    {
+      "epoch": 0.6133333333333333,
+      "grad_norm": 0.0659874901175499,
+      "learning_rate": 3.257139763390925e-05,
+      "loss": 0.0008,
+      "step": 230
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.06739695370197296,
+      "learning_rate": 2.8711035421746367e-05,
+      "loss": 0.0011,
+      "step": 240
+    },
+    {
+      "epoch": 0.64,
+      "eval_loss": 0.0008268249221146107,
+      "eval_runtime": 95.5979,
+      "eval_samples_per_second": 10.46,
+      "eval_steps_per_second": 0.439,
+      "step": 240
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 0.03626958280801773,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.0006,
+      "step": 250
+    },
+    {
+      "epoch": 0.6933333333333334,
+      "grad_norm": 0.04814556986093521,
+      "learning_rate": 2.1464321615778422e-05,
+      "loss": 0.0008,
+      "step": 260
+    },
+    {
+      "epoch": 0.6933333333333334,
+      "eval_loss": 0.0010607398580759764,
+      "eval_runtime": 95.6167,
+      "eval_samples_per_second": 10.458,
+      "eval_steps_per_second": 0.439,
+      "step": 260
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 0.0736890509724617,
+      "learning_rate": 1.8128800512565513e-05,
+      "loss": 0.001,
+      "step": 270
+    },
+    {
+      "epoch": 0.7466666666666667,
+      "grad_norm": 0.00970852468162775,
+      "learning_rate": 1.5016832974331724e-05,
+      "loss": 0.0006,
+      "step": 280
+    },
+    {
+      "epoch": 0.7466666666666667,
+      "eval_loss": 0.000896115496288985,
+      "eval_runtime": 95.5995,
+      "eval_samples_per_second": 10.46,
+      "eval_steps_per_second": 0.439,
+      "step": 280
+    },
+    {
+      "epoch": 0.7733333333333333,
+      "grad_norm": 0.0626436322927475,
+      "learning_rate": 1.2150247217412186e-05,
+      "loss": 0.0007,
+      "step": 290
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.028112420812249184,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.0008,
+      "step": 300
+    },
+    {
+      "epoch": 0.8,
+      "eval_loss": 0.0006250065052881837,
+      "eval_runtime": 95.5927,
+      "eval_samples_per_second": 10.461,
+      "eval_steps_per_second": 0.439,
+      "step": 300
+    },
+    {
+      "epoch": 0.8266666666666667,
+      "grad_norm": 0.04174938425421715,
+      "learning_rate": 7.2317869919746705e-06,
+      "loss": 0.0005,
+      "step": 310
+    },
+    {
+      "epoch": 0.8533333333333334,
+      "grad_norm": 0.024150365963578224,
+      "learning_rate": 5.214411988029355e-06,
+      "loss": 0.0006,
+      "step": 320
+    },
+    {
+      "epoch": 0.8533333333333334,
+      "eval_loss": 0.0006509472732432187,
+      "eval_runtime": 95.6069,
+      "eval_samples_per_second": 10.459,
+      "eval_steps_per_second": 0.439,
+      "step": 320
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 0.03418087959289551,
+      "learning_rate": 3.511175705587433e-06,
+      "loss": 0.0008,
+      "step": 330
+    },
+    {
+      "epoch": 0.9066666666666666,
+      "grad_norm": 0.043204039335250854,
+      "learning_rate": 2.134025123396638e-06,
+      "loss": 0.0005,
+      "step": 340
+    },
+    {
+      "epoch": 0.9066666666666666,
+      "eval_loss": 0.0005842947866767645,
+      "eval_runtime": 95.6059,
+      "eval_samples_per_second": 10.46,
+      "eval_steps_per_second": 0.439,
+      "step": 340
+    },
+    {
+      "epoch": 0.9333333333333333,
+      "grad_norm": 0.07010845839977264,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 0.0006,
+      "step": 350
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.0437210276722908,
+      "learning_rate": 3.9426493427611177e-07,
+      "loss": 0.0006,
+      "step": 360
+    },
+    {
+      "epoch": 0.96,
+      "eval_loss": 0.0006073525873944163,
+      "eval_runtime": 95.5779,
+      "eval_samples_per_second": 10.463,
+      "eval_steps_per_second": 0.439,
+      "step": 360
+    },
+    {
+      "epoch": 0.9866666666666667,
+      "grad_norm": 0.022227060049772263,
+      "learning_rate": 4.385849505708084e-08,
+      "loss": 0.0005,
+      "step": 370
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 375,
+  "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": 7.369767647728108e+17,
+  "train_batch_size": 12,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-375/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ef28760fa4bf6cdb59bddec6b4ba9552fa013f1867d1986d349ce8175e64e31
+size 5432

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 0.0005918259848840535,
+    "eval_runtime": 95.7064,
+    "eval_samples_per_second": 10.449,
+    "eval_steps_per_second": 0.439
+}

runs/Dec18_17-58-14_ctua-interactive-pod/events.out.tfevents.1734544712.ctua-interactive-pod.1022.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1c1cb93cf4bcba97ca912d631042deb8f4b73ebe855c2dc7f23468604946ddc
+size 18218

runs/Dec18_17-58-14_ctua-interactive-pod/events.out.tfevents.1734549324.ctua-interactive-pod.1022.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92d82949824c4106105645f23aa0492773761f53b10ea4433ab214a95d29ef8c
+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": 7.369767647728108e+17,
+    "train_loss": 0.01518383183144033,
+    "train_runtime": 4516.1364,
+    "train_samples_per_second": 1.993,
+    "train_steps_per_second": 0.083
+}

trainer_log.jsonl

@@ -0,0 +1,56 @@
+{"current_steps": 10, "total_steps": 375, "loss": 0.5086, "lr": 9.982464296247522e-05, "epoch": 0.02666666666666667, "percentage": 2.67, "elapsed_time": "0:01:14", "remaining_time": "0:45:23"}
+{"current_steps": 20, "total_steps": 375, "loss": 0.0107, "lr": 9.929980185352526e-05, "epoch": 0.05333333333333334, "percentage": 5.33, "elapsed_time": "0:02:29", "remaining_time": "0:44:06"}
+{"current_steps": 20, "total_steps": 375, "eval_loss": 0.004315248690545559, "epoch": 0.05333333333333334, "percentage": 5.33, "elapsed_time": "0:04:04", "remaining_time": "1:12:25"}
+{"current_steps": 30, "total_steps": 375, "loss": 0.004, "lr": 9.842915805643155e-05, "epoch": 0.08, "percentage": 8.0, "elapsed_time": "0:05:19", "remaining_time": "1:01:11"}
+{"current_steps": 40, "total_steps": 375, "loss": 0.0035, "lr": 9.721881851187406e-05, "epoch": 0.10666666666666667, "percentage": 10.67, "elapsed_time": "0:06:33", "remaining_time": "0:54:57"}
+{"current_steps": 40, "total_steps": 375, "eval_loss": 0.0034025884233415127, "epoch": 0.10666666666666667, "percentage": 10.67, "elapsed_time": "0:08:09", "remaining_time": "1:08:19"}
+{"current_steps": 50, "total_steps": 375, "loss": 0.0034, "lr": 9.567727288213005e-05, "epoch": 0.13333333333333333, "percentage": 13.33, "elapsed_time": "0:09:23", "remaining_time": "1:01:05"}
+{"current_steps": 60, "total_steps": 375, "loss": 0.0033, "lr": 9.381533400219318e-05, "epoch": 0.16, "percentage": 16.0, "elapsed_time": "0:10:38", "remaining_time": "0:55:51"}
+{"current_steps": 60, "total_steps": 375, "eval_loss": 0.0027047081384807825, "epoch": 0.16, "percentage": 16.0, "elapsed_time": "0:12:14", "remaining_time": "1:04:14"}
+{"current_steps": 70, "total_steps": 375, "loss": 0.0024, "lr": 9.164606203550497e-05, "epoch": 0.18666666666666668, "percentage": 18.67, "elapsed_time": "0:13:28", "remaining_time": "0:58:43"}
+{"current_steps": 80, "total_steps": 375, "loss": 0.0018, "lr": 8.9184672866292e-05, "epoch": 0.21333333333333335, "percentage": 21.33, "elapsed_time": "0:14:43", "remaining_time": "0:54:16"}
+{"current_steps": 80, "total_steps": 375, "eval_loss": 0.001777145778760314, "epoch": 0.21333333333333335, "percentage": 21.33, "elapsed_time": "0:16:18", "remaining_time": "1:00:09"}
+{"current_steps": 90, "total_steps": 375, "loss": 0.0022, "lr": 8.644843137107059e-05, "epoch": 0.24, "percentage": 24.0, "elapsed_time": "0:17:33", "remaining_time": "0:55:35"}
+{"current_steps": 100, "total_steps": 375, "loss": 0.0025, "lr": 8.345653031794292e-05, "epoch": 0.26666666666666666, "percentage": 26.67, "elapsed_time": "0:18:47", "remaining_time": "0:51:41"}
+{"current_steps": 100, "total_steps": 375, "eval_loss": 0.0019247803138568997, "epoch": 0.26666666666666666, "percentage": 26.67, "elapsed_time": "0:20:23", "remaining_time": "0:56:04"}
+{"current_steps": 110, "total_steps": 375, "loss": 0.0015, "lr": 8.022995574311876e-05, "epoch": 0.29333333333333333, "percentage": 29.33, "elapsed_time": "0:21:37", "remaining_time": "0:52:06"}
+{"current_steps": 120, "total_steps": 375, "loss": 0.0019, "lr": 7.679133974894983e-05, "epoch": 0.32, "percentage": 32.0, "elapsed_time": "0:22:52", "remaining_time": "0:48:36"}
+{"current_steps": 120, "total_steps": 375, "eval_loss": 0.00168008788023144, "epoch": 0.32, "percentage": 32.0, "elapsed_time": "0:24:28", "remaining_time": "0:51:59"}
+{"current_steps": 130, "total_steps": 375, "loss": 0.0015, "lr": 7.316480175599309e-05, "epoch": 0.3466666666666667, "percentage": 34.67, "elapsed_time": "0:25:42", "remaining_time": "0:48:27"}
+{"current_steps": 140, "total_steps": 375, "loss": 0.0015, "lr": 6.937577932260515e-05, "epoch": 0.37333333333333335, "percentage": 37.33, "elapsed_time": "0:26:57", "remaining_time": "0:45:14"}
+{"current_steps": 140, "total_steps": 375, "eval_loss": 0.001629200647585094, "epoch": 0.37333333333333335, "percentage": 37.33, "elapsed_time": "0:28:32", "remaining_time": "0:47:55"}
+{"current_steps": 150, "total_steps": 375, "loss": 0.0012, "lr": 6.545084971874738e-05, "epoch": 0.4, "percentage": 40.0, "elapsed_time": "0:29:47", "remaining_time": "0:44:41"}
+{"current_steps": 160, "total_steps": 375, "loss": 0.0015, "lr": 6.141754350553279e-05, "epoch": 0.4266666666666667, "percentage": 42.67, "elapsed_time": "0:31:01", "remaining_time": "0:41:41"}
+{"current_steps": 160, "total_steps": 375, "eval_loss": 0.001399434870108962, "epoch": 0.4266666666666667, "percentage": 42.67, "elapsed_time": "0:32:37", "remaining_time": "0:43:50"}
+{"current_steps": 170, "total_steps": 375, "loss": 0.0015, "lr": 5.730415142812059e-05, "epoch": 0.4533333333333333, "percentage": 45.33, "elapsed_time": "0:33:52", "remaining_time": "0:40:50"}
+{"current_steps": 180, "total_steps": 375, "loss": 0.0015, "lr": 5.313952597646568e-05, "epoch": 0.48, "percentage": 48.0, "elapsed_time": "0:35:07", "remaining_time": "0:38:02"}
+{"current_steps": 180, "total_steps": 375, "eval_loss": 0.001668238895945251, "epoch": 0.48, "percentage": 48.0, "elapsed_time": "0:36:42", "remaining_time": "0:39:46"}
+{"current_steps": 190, "total_steps": 375, "loss": 0.0013, "lr": 4.895287900583216e-05, "epoch": 0.5066666666666667, "percentage": 50.67, "elapsed_time": "0:37:57", "remaining_time": "0:36:57"}
+{"current_steps": 200, "total_steps": 375, "loss": 0.001, "lr": 4.477357683661734e-05, "epoch": 0.5333333333333333, "percentage": 53.33, "elapsed_time": "0:39:11", "remaining_time": "0:34:17"}
+{"current_steps": 200, "total_steps": 375, "eval_loss": 0.0009001157595776021, "epoch": 0.5333333333333333, "percentage": 53.33, "elapsed_time": "0:40:47", "remaining_time": "0:35:41"}
+{"current_steps": 210, "total_steps": 375, "loss": 0.001, "lr": 4.063093427071376e-05, "epoch": 0.56, "percentage": 56.0, "elapsed_time": "0:42:01", "remaining_time": "0:33:01"}
+{"current_steps": 220, "total_steps": 375, "loss": 0.0007, "lr": 3.655400896923672e-05, "epoch": 0.5866666666666667, "percentage": 58.67, "elapsed_time": "0:43:16", "remaining_time": "0:30:29"}
+{"current_steps": 220, "total_steps": 375, "eval_loss": 0.0007602078258059919, "epoch": 0.5866666666666667, "percentage": 58.67, "elapsed_time": "0:44:51", "remaining_time": "0:31:36"}
+{"current_steps": 230, "total_steps": 375, "loss": 0.0008, "lr": 3.257139763390925e-05, "epoch": 0.6133333333333333, "percentage": 61.33, "elapsed_time": "0:46:06", "remaining_time": "0:29:03"}
+{"current_steps": 240, "total_steps": 375, "loss": 0.0011, "lr": 2.8711035421746367e-05, "epoch": 0.64, "percentage": 64.0, "elapsed_time": "0:47:20", "remaining_time": "0:26:37"}
+{"current_steps": 240, "total_steps": 375, "eval_loss": 0.0008268249221146107, "epoch": 0.64, "percentage": 64.0, "elapsed_time": "0:48:56", "remaining_time": "0:27:31"}
+{"current_steps": 250, "total_steps": 375, "loss": 0.0006, "lr": 2.500000000000001e-05, "epoch": 0.6666666666666666, "percentage": 66.67, "elapsed_time": "0:50:10", "remaining_time": "0:25:05"}
+{"current_steps": 260, "total_steps": 375, "loss": 0.0008, "lr": 2.1464321615778422e-05, "epoch": 0.6933333333333334, "percentage": 69.33, "elapsed_time": "0:51:24", "remaining_time": "0:22:44"}
+{"current_steps": 260, "total_steps": 375, "eval_loss": 0.0010607398580759764, "epoch": 0.6933333333333334, "percentage": 69.33, "elapsed_time": "0:53:00", "remaining_time": "0:23:26"}
+{"current_steps": 270, "total_steps": 375, "loss": 0.001, "lr": 1.8128800512565513e-05, "epoch": 0.72, "percentage": 72.0, "elapsed_time": "0:54:14", "remaining_time": "0:21:05"}
+{"current_steps": 280, "total_steps": 375, "loss": 0.0006, "lr": 1.5016832974331724e-05, "epoch": 0.7466666666666667, "percentage": 74.67, "elapsed_time": "0:55:29", "remaining_time": "0:18:49"}
+{"current_steps": 280, "total_steps": 375, "eval_loss": 0.000896115496288985, "epoch": 0.7466666666666667, "percentage": 74.67, "elapsed_time": "0:57:04", "remaining_time": "0:19:22"}
+{"current_steps": 290, "total_steps": 375, "loss": 0.0007, "lr": 1.2150247217412186e-05, "epoch": 0.7733333333333333, "percentage": 77.33, "elapsed_time": "0:58:19", "remaining_time": "0:17:05"}
+{"current_steps": 300, "total_steps": 375, "loss": 0.0008, "lr": 9.549150281252633e-06, "epoch": 0.8, "percentage": 80.0, "elapsed_time": "0:59:33", "remaining_time": "0:14:53"}
+{"current_steps": 300, "total_steps": 375, "eval_loss": 0.0006250065052881837, "epoch": 0.8, "percentage": 80.0, "elapsed_time": "1:01:09", "remaining_time": "0:15:17"}
+{"current_steps": 310, "total_steps": 375, "loss": 0.0005, "lr": 7.2317869919746705e-06, "epoch": 0.8266666666666667, "percentage": 82.67, "elapsed_time": "1:02:23", "remaining_time": "0:13:04"}
+{"current_steps": 320, "total_steps": 375, "loss": 0.0006, "lr": 5.214411988029355e-06, "epoch": 0.8533333333333334, "percentage": 85.33, "elapsed_time": "1:03:38", "remaining_time": "0:10:56"}
+{"current_steps": 320, "total_steps": 375, "eval_loss": 0.0006509472732432187, "epoch": 0.8533333333333334, "percentage": 85.33, "elapsed_time": "1:05:13", "remaining_time": "0:11:12"}
+{"current_steps": 330, "total_steps": 375, "loss": 0.0008, "lr": 3.511175705587433e-06, "epoch": 0.88, "percentage": 88.0, "elapsed_time": "1:06:28", "remaining_time": "0:09:03"}
+{"current_steps": 340, "total_steps": 375, "loss": 0.0005, "lr": 2.134025123396638e-06, "epoch": 0.9066666666666666, "percentage": 90.67, "elapsed_time": "1:07:42", "remaining_time": "0:06:58"}
+{"current_steps": 340, "total_steps": 375, "eval_loss": 0.0005842947866767645, "epoch": 0.9066666666666666, "percentage": 90.67, "elapsed_time": "1:09:18", "remaining_time": "0:07:08"}
+{"current_steps": 350, "total_steps": 375, "loss": 0.0006, "lr": 1.0926199633097157e-06, "epoch": 0.9333333333333333, "percentage": 93.33, "elapsed_time": "1:10:32", "remaining_time": "0:05:02"}
+{"current_steps": 360, "total_steps": 375, "loss": 0.0006, "lr": 3.9426493427611177e-07, "epoch": 0.96, "percentage": 96.0, "elapsed_time": "1:11:46", "remaining_time": "0:02:59"}
+{"current_steps": 360, "total_steps": 375, "eval_loss": 0.0006073525873944163, "epoch": 0.96, "percentage": 96.0, "elapsed_time": "1:13:22", "remaining_time": "0:03:03"}
+{"current_steps": 370, "total_steps": 375, "loss": 0.0005, "lr": 4.385849505708084e-08, "epoch": 0.9866666666666667, "percentage": 98.67, "elapsed_time": "1:14:36", "remaining_time": "0:01:00"}
+{"current_steps": 375, "total_steps": 375, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "1:15:14", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,445 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 20,
+  "global_step": 375,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02666666666666667,
+      "grad_norm": 0.6144651174545288,
+      "learning_rate": 9.982464296247522e-05,
+      "loss": 0.5086,
+      "step": 10
+    },
+    {
+      "epoch": 0.05333333333333334,
+      "grad_norm": 0.041260600090026855,
+      "learning_rate": 9.929980185352526e-05,
+      "loss": 0.0107,
+      "step": 20
+    },
+    {
+      "epoch": 0.05333333333333334,
+      "eval_loss": 0.004315248690545559,
+      "eval_runtime": 95.7488,
+      "eval_samples_per_second": 10.444,
+      "eval_steps_per_second": 0.439,
+      "step": 20
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.00790360290557146,
+      "learning_rate": 9.842915805643155e-05,
+      "loss": 0.004,
+      "step": 30
+    },
+    {
+      "epoch": 0.10666666666666667,
+      "grad_norm": 0.022915204986929893,
+      "learning_rate": 9.721881851187406e-05,
+      "loss": 0.0035,
+      "step": 40
+    },
+    {
+      "epoch": 0.10666666666666667,
+      "eval_loss": 0.0034025884233415127,
+      "eval_runtime": 95.7394,
+      "eval_samples_per_second": 10.445,
+      "eval_steps_per_second": 0.439,
+      "step": 40
+    },
+    {
+      "epoch": 0.13333333333333333,
+      "grad_norm": 0.026596330106258392,
+      "learning_rate": 9.567727288213005e-05,
+      "loss": 0.0034,
+      "step": 50
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.10935429483652115,
+      "learning_rate": 9.381533400219318e-05,
+      "loss": 0.0033,
+      "step": 60
+    },
+    {
+      "epoch": 0.16,
+      "eval_loss": 0.0027047081384807825,
+      "eval_runtime": 95.776,
+      "eval_samples_per_second": 10.441,
+      "eval_steps_per_second": 0.439,
+      "step": 60
+    },
+    {
+      "epoch": 0.18666666666666668,
+      "grad_norm": 0.1983339935541153,
+      "learning_rate": 9.164606203550497e-05,
+      "loss": 0.0024,
+      "step": 70
+    },
+    {
+      "epoch": 0.21333333333333335,
+      "grad_norm": 0.11285419017076492,
+      "learning_rate": 8.9184672866292e-05,
+      "loss": 0.0018,
+      "step": 80
+    },
+    {
+      "epoch": 0.21333333333333335,
+      "eval_loss": 0.001777145778760314,
+      "eval_runtime": 95.7123,
+      "eval_samples_per_second": 10.448,
+      "eval_steps_per_second": 0.439,
+      "step": 80
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 0.09023458510637283,
+      "learning_rate": 8.644843137107059e-05,
+      "loss": 0.0022,
+      "step": 90
+    },
+    {
+      "epoch": 0.26666666666666666,
+      "grad_norm": 0.0411541648209095,
+      "learning_rate": 8.345653031794292e-05,
+      "loss": 0.0025,
+      "step": 100
+    },
+    {
+      "epoch": 0.26666666666666666,
+      "eval_loss": 0.0019247803138568997,
+      "eval_runtime": 95.7325,
+      "eval_samples_per_second": 10.446,
+      "eval_steps_per_second": 0.439,
+      "step": 100
+    },
+    {
+      "epoch": 0.29333333333333333,
+      "grad_norm": 0.05165160447359085,
+      "learning_rate": 8.022995574311876e-05,
+      "loss": 0.0015,
+      "step": 110
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.11784542351961136,
+      "learning_rate": 7.679133974894983e-05,
+      "loss": 0.0019,
+      "step": 120
+    },
+    {
+      "epoch": 0.32,
+      "eval_loss": 0.00168008788023144,
+      "eval_runtime": 95.7517,
+      "eval_samples_per_second": 10.444,
+      "eval_steps_per_second": 0.439,
+      "step": 120
+    },
+    {
+      "epoch": 0.3466666666666667,
+      "grad_norm": 0.1648288369178772,
+      "learning_rate": 7.316480175599309e-05,
+      "loss": 0.0015,
+      "step": 130
+    },
+    {
+      "epoch": 0.37333333333333335,
+      "grad_norm": 0.064679816365242,
+      "learning_rate": 6.937577932260515e-05,
+      "loss": 0.0015,
+      "step": 140
+    },
+    {
+      "epoch": 0.37333333333333335,
+      "eval_loss": 0.001629200647585094,
+      "eval_runtime": 95.7474,
+      "eval_samples_per_second": 10.444,
+      "eval_steps_per_second": 0.439,
+      "step": 140
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.10296431183815002,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 0.0012,
+      "step": 150
+    },
+    {
+      "epoch": 0.4266666666666667,
+      "grad_norm": 0.020578118041157722,
+      "learning_rate": 6.141754350553279e-05,
+      "loss": 0.0015,
+      "step": 160
+    },
+    {
+      "epoch": 0.4266666666666667,
+      "eval_loss": 0.001399434870108962,
+      "eval_runtime": 95.7645,
+      "eval_samples_per_second": 10.442,
+      "eval_steps_per_second": 0.439,
+      "step": 160
+    },
+    {
+      "epoch": 0.4533333333333333,
+      "grad_norm": 0.036092739552259445,
+      "learning_rate": 5.730415142812059e-05,
+      "loss": 0.0015,
+      "step": 170
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.07469587028026581,
+      "learning_rate": 5.313952597646568e-05,
+      "loss": 0.0015,
+      "step": 180
+    },
+    {
+      "epoch": 0.48,
+      "eval_loss": 0.001668238895945251,
+      "eval_runtime": 95.6093,
+      "eval_samples_per_second": 10.459,
+      "eval_steps_per_second": 0.439,
+      "step": 180
+    },
+    {
+      "epoch": 0.5066666666666667,
+      "grad_norm": 0.012558485381305218,
+      "learning_rate": 4.895287900583216e-05,
+      "loss": 0.0013,
+      "step": 190
+    },
+    {
+      "epoch": 0.5333333333333333,
+      "grad_norm": 0.026587937027215958,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 0.001,
+      "step": 200
+    },
+    {
+      "epoch": 0.5333333333333333,
+      "eval_loss": 0.0009001157595776021,
+      "eval_runtime": 95.6055,
+      "eval_samples_per_second": 10.46,
+      "eval_steps_per_second": 0.439,
+      "step": 200
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.057403530925512314,
+      "learning_rate": 4.063093427071376e-05,
+      "loss": 0.001,
+      "step": 210
+    },
+    {
+      "epoch": 0.5866666666666667,
+      "grad_norm": 0.03403661027550697,
+      "learning_rate": 3.655400896923672e-05,
+      "loss": 0.0007,
+      "step": 220
+    },
+    {
+      "epoch": 0.5866666666666667,
+      "eval_loss": 0.0007602078258059919,
+      "eval_runtime": 95.6123,
+      "eval_samples_per_second": 10.459,
+      "eval_steps_per_second": 0.439,
+      "step": 220
+    },
+    {
+      "epoch": 0.6133333333333333,
+      "grad_norm": 0.0659874901175499,
+      "learning_rate": 3.257139763390925e-05,
+      "loss": 0.0008,
+      "step": 230
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.06739695370197296,
+      "learning_rate": 2.8711035421746367e-05,
+      "loss": 0.0011,
+      "step": 240
+    },
+    {
+      "epoch": 0.64,
+      "eval_loss": 0.0008268249221146107,
+      "eval_runtime": 95.5979,
+      "eval_samples_per_second": 10.46,
+      "eval_steps_per_second": 0.439,
+      "step": 240
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 0.03626958280801773,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.0006,
+      "step": 250
+    },
+    {
+      "epoch": 0.6933333333333334,
+      "grad_norm": 0.04814556986093521,
+      "learning_rate": 2.1464321615778422e-05,
+      "loss": 0.0008,
+      "step": 260
+    },
+    {
+      "epoch": 0.6933333333333334,
+      "eval_loss": 0.0010607398580759764,
+      "eval_runtime": 95.6167,
+      "eval_samples_per_second": 10.458,
+      "eval_steps_per_second": 0.439,
+      "step": 260
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 0.0736890509724617,
+      "learning_rate": 1.8128800512565513e-05,
+      "loss": 0.001,
+      "step": 270
+    },
+    {
+      "epoch": 0.7466666666666667,
+      "grad_norm": 0.00970852468162775,
+      "learning_rate": 1.5016832974331724e-05,
+      "loss": 0.0006,
+      "step": 280
+    },
+    {
+      "epoch": 0.7466666666666667,
+      "eval_loss": 0.000896115496288985,
+      "eval_runtime": 95.5995,
+      "eval_samples_per_second": 10.46,
+      "eval_steps_per_second": 0.439,
+      "step": 280
+    },
+    {
+      "epoch": 0.7733333333333333,
+      "grad_norm": 0.0626436322927475,
+      "learning_rate": 1.2150247217412186e-05,
+      "loss": 0.0007,
+      "step": 290
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.028112420812249184,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.0008,
+      "step": 300
+    },
+    {
+      "epoch": 0.8,
+      "eval_loss": 0.0006250065052881837,
+      "eval_runtime": 95.5927,
+      "eval_samples_per_second": 10.461,
+      "eval_steps_per_second": 0.439,
+      "step": 300
+    },
+    {
+      "epoch": 0.8266666666666667,
+      "grad_norm": 0.04174938425421715,
+      "learning_rate": 7.2317869919746705e-06,
+      "loss": 0.0005,
+      "step": 310
+    },
+    {
+      "epoch": 0.8533333333333334,
+      "grad_norm": 0.024150365963578224,
+      "learning_rate": 5.214411988029355e-06,
+      "loss": 0.0006,
+      "step": 320
+    },
+    {
+      "epoch": 0.8533333333333334,
+      "eval_loss": 0.0006509472732432187,
+      "eval_runtime": 95.6069,
+      "eval_samples_per_second": 10.459,
+      "eval_steps_per_second": 0.439,
+      "step": 320
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 0.03418087959289551,
+      "learning_rate": 3.511175705587433e-06,
+      "loss": 0.0008,
+      "step": 330
+    },
+    {
+      "epoch": 0.9066666666666666,
+      "grad_norm": 0.043204039335250854,
+      "learning_rate": 2.134025123396638e-06,
+      "loss": 0.0005,
+      "step": 340
+    },
+    {
+      "epoch": 0.9066666666666666,
+      "eval_loss": 0.0005842947866767645,
+      "eval_runtime": 95.6059,
+      "eval_samples_per_second": 10.46,
+      "eval_steps_per_second": 0.439,
+      "step": 340
+    },
+    {
+      "epoch": 0.9333333333333333,
+      "grad_norm": 0.07010845839977264,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 0.0006,
+      "step": 350
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.0437210276722908,
+      "learning_rate": 3.9426493427611177e-07,
+      "loss": 0.0006,
+      "step": 360
+    },
+    {
+      "epoch": 0.96,
+      "eval_loss": 0.0006073525873944163,
+      "eval_runtime": 95.5779,
+      "eval_samples_per_second": 10.463,
+      "eval_steps_per_second": 0.439,
+      "step": 360
+    },
+    {
+      "epoch": 0.9866666666666667,
+      "grad_norm": 0.022227060049772263,
+      "learning_rate": 4.385849505708084e-08,
+      "loss": 0.0005,
+      "step": 370
+    },
+    {
+      "epoch": 1.0,
+      "step": 375,
+      "total_flos": 7.369767647728108e+17,
+      "train_loss": 0.01518383183144033,
+      "train_runtime": 4516.1364,
+      "train_samples_per_second": 1.993,
+      "train_steps_per_second": 0.083
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 375,
+  "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": 7.369767647728108e+17,
+  "train_batch_size": 12,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ef28760fa4bf6cdb59bddec6b4ba9552fa013f1867d1986d349ce8175e64e31
+size 5432