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 +1,79 @@
+---
+base_model: mistralai/Mistral-Nemo-Instruct-2407
+library_name: peft
+license: other
+tags:
+- llama-factory
+- lora
+- generated_from_trainer
+model-index:
+- name: epidemiology_sft_10000_mcq_1epoch
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# epidemiology_sft_10000_mcq_1epoch
+
+This model is a fine-tuned version of [mistralai/Mistral-Nemo-Instruct-2407](https://huggingface.co/mistralai/Mistral-Nemo-Instruct-2407) on the epidemiology_10000_mcq dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0024
+
+## 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 |
+|:-------------:|:------:|:----:|:---------------:|
+| 0.0041        | 0.0667 | 30   | 0.0040          |
+| 0.0039        | 0.1333 | 60   | 0.0039          |
+| 0.0039        | 0.2    | 90   | 0.0039          |
+| 0.0039        | 0.2667 | 120  | 0.0039          |
+| 0.0038        | 0.3333 | 150  | 0.0041          |
+| 0.0038        | 0.4    | 180  | 0.0038          |
+| 0.003         | 0.4667 | 210  | 0.0028          |
+| 0.0029        | 0.5333 | 240  | 0.0026          |
+| 0.0027        | 0.6    | 270  | 0.0026          |
+| 0.0027        | 0.6667 | 300  | 0.0025          |
+| 0.0027        | 0.7333 | 330  | 0.0025          |
+| 0.0026        | 0.8    | 360  | 0.0025          |
+| 0.0026        | 0.8667 | 390  | 0.0024          |
+| 0.0024        | 0.9333 | 420  | 0.0024          |
+| 0.0025        | 1.0    | 450  | 0.0024          |
+
+
+### 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": [
+    "up_proj",
+    "k_proj",
+    "gate_proj",
+    "o_proj",
+    "v_proj",
+    "q_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 sha256:9cf844fac290b95d0cb5b679382373929ebc07a5e2eef9f80d62ee2f845cd28a
+size 114106856

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 0.0023939567618072033,
+    "eval_runtime": 103.9198,
+    "eval_samples_per_second": 9.623,
+    "eval_steps_per_second": 0.481,
+    "total_flos": 7.36157876644479e+17,
+    "train_loss": 0.00987041109551986,
+    "train_runtime": 4750.9394,
+    "train_samples_per_second": 1.894,
+    "train_steps_per_second": 0.095
+}

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": [
+    "up_proj",
+    "k_proj",
+    "gate_proj",
+    "o_proj",
+    "v_proj",
+    "q_proj",
+    "down_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 sha256:9cf844fac290b95d0cb5b679382373929ebc07a5e2eef9f80d62ee2f845cd28a
+size 114106856

checkpoint-450/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04b5f8b7ffd7a3f126a9d1438fdd2200c1f2785b2a8e803d91451fa437d07961
+size 228536930

checkpoint-450/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9281be04f2316562db36bd289b226e07237cabe0e64c821e5b8cfedcb5f17669
+size 14512

checkpoint-450/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:658f78ca761388a441a3eaf439ede5c9b4dc1f731762e906f81abe29d7755ff1
+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 +1,468 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 30,
+  "global_step": 450,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.022222222222222223,
+      "grad_norm": 0.46052348613739014,
+      "learning_rate": 9.987820251299122e-05,
+      "loss": 0.3017,
+      "step": 10
+    },
+    {
+      "epoch": 0.044444444444444446,
+      "grad_norm": 0.0518617108464241,
+      "learning_rate": 9.951340343707852e-05,
+      "loss": 0.0063,
+      "step": 20
+    },
+    {
+      "epoch": 0.06666666666666667,
+      "grad_norm": 0.02703821286559105,
+      "learning_rate": 9.890738003669029e-05,
+      "loss": 0.0041,
+      "step": 30
+    },
+    {
+      "epoch": 0.06666666666666667,
+      "eval_loss": 0.004034009762108326,
+      "eval_runtime": 104.0521,
+      "eval_samples_per_second": 9.611,
+      "eval_steps_per_second": 0.481,
+      "step": 30
+    },
+    {
+      "epoch": 0.08888888888888889,
+      "grad_norm": 0.011427383869886398,
+      "learning_rate": 9.806308479691595e-05,
+      "loss": 0.004,
+      "step": 40
+    },
+    {
+      "epoch": 0.1111111111111111,
+      "grad_norm": 0.022027652710676193,
+      "learning_rate": 9.698463103929542e-05,
+      "loss": 0.004,
+      "step": 50
+    },
+    {
+      "epoch": 0.13333333333333333,
+      "grad_norm": 0.001629775040782988,
+      "learning_rate": 9.567727288213005e-05,
+      "loss": 0.0039,
+      "step": 60
+    },
+    {
+      "epoch": 0.13333333333333333,
+      "eval_loss": 0.0039054970256984234,
+      "eval_runtime": 104.0544,
+      "eval_samples_per_second": 9.61,
+      "eval_steps_per_second": 0.481,
+      "step": 60
+    },
+    {
+      "epoch": 0.15555555555555556,
+      "grad_norm": 0.04784173518419266,
+      "learning_rate": 9.414737964294636e-05,
+      "loss": 0.0039,
+      "step": 70
+    },
+    {
+      "epoch": 0.17777777777777778,
+      "grad_norm": 0.020441358909010887,
+      "learning_rate": 9.24024048078213e-05,
+      "loss": 0.0039,
+      "step": 80
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.0022530381102114916,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 0.0039,
+      "step": 90
+    },
+    {
+      "epoch": 0.2,
+      "eval_loss": 0.0038894277531653643,
+      "eval_runtime": 169.6744,
+      "eval_samples_per_second": 5.894,
+      "eval_steps_per_second": 0.295,
+      "step": 90
+    },
+    {
+      "epoch": 0.2222222222222222,
+      "grad_norm": 0.006415847223252058,
+      "learning_rate": 8.83022221559489e-05,
+      "loss": 0.0039,
+      "step": 100
+    },
+    {
+      "epoch": 0.24444444444444444,
+      "grad_norm": 0.0103780971840024,
+      "learning_rate": 8.596699001693255e-05,
+      "loss": 0.0039,
+      "step": 110
+    },
+    {
+      "epoch": 0.26666666666666666,
+      "grad_norm": 0.016158604994416237,
+      "learning_rate": 8.345653031794292e-05,
+      "loss": 0.0039,
+      "step": 120
+    },
+    {
+      "epoch": 0.26666666666666666,
+      "eval_loss": 0.00390805397182703,
+      "eval_runtime": 104.1821,
+      "eval_samples_per_second": 9.599,
+      "eval_steps_per_second": 0.48,
+      "step": 120
+    },
+    {
+      "epoch": 0.28888888888888886,
+      "grad_norm": 0.004166940692812204,
+      "learning_rate": 8.07830737662829e-05,
+      "loss": 0.0039,
+      "step": 130
+    },
+    {
+      "epoch": 0.3111111111111111,
+      "grad_norm": 0.0024945680052042007,
+      "learning_rate": 7.795964517353735e-05,
+      "loss": 0.0039,
+      "step": 140
+    },
+    {
+      "epoch": 0.3333333333333333,
+      "grad_norm": 0.024202220141887665,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 0.0038,
+      "step": 150
+    },
+    {
+      "epoch": 0.3333333333333333,
+      "eval_loss": 0.00407786201685667,
+      "eval_runtime": 104.0841,
+      "eval_samples_per_second": 9.608,
+      "eval_steps_per_second": 0.48,
+      "step": 150
+    },
+    {
+      "epoch": 0.35555555555555557,
+      "grad_norm": 0.005438762251287699,
+      "learning_rate": 7.191855733945387e-05,
+      "loss": 0.0039,
+      "step": 160
+    },
+    {
+      "epoch": 0.37777777777777777,
+      "grad_norm": 0.008657037280499935,
+      "learning_rate": 6.873032967079561e-05,
+      "loss": 0.0039,
+      "step": 170
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.014475060626864433,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 0.0038,
+      "step": 180
+    },
+    {
+      "epoch": 0.4,
+      "eval_loss": 0.0037861280143260956,
+      "eval_runtime": 104.145,
+      "eval_samples_per_second": 9.602,
+      "eval_steps_per_second": 0.48,
+      "step": 180
+    },
+    {
+      "epoch": 0.4222222222222222,
+      "grad_norm": 0.013048152439296246,
+      "learning_rate": 6.209609477998338e-05,
+      "loss": 0.0037,
+      "step": 190
+    },
+    {
+      "epoch": 0.4444444444444444,
+      "grad_norm": 0.04640911519527435,
+      "learning_rate": 5.868240888334653e-05,
+      "loss": 0.0034,
+      "step": 200
+    },
+    {
+      "epoch": 0.4666666666666667,
+      "grad_norm": 0.019521236419677734,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 0.003,
+      "step": 210
+    },
+    {
+      "epoch": 0.4666666666666667,
+      "eval_loss": 0.002776140347123146,
+      "eval_runtime": 104.0124,
+      "eval_samples_per_second": 9.614,
+      "eval_steps_per_second": 0.481,
+      "step": 210
+    },
+    {
+      "epoch": 0.4888888888888889,
+      "grad_norm": 0.03593623265624046,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 0.0031,
+      "step": 220
+    },
+    {
+      "epoch": 0.5111111111111111,
+      "grad_norm": 0.06989370286464691,
+      "learning_rate": 4.825502516487497e-05,
+      "loss": 0.0028,
+      "step": 230
+    },
+    {
+      "epoch": 0.5333333333333333,
+      "grad_norm": 0.022669225931167603,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 0.0029,
+      "step": 240
+    },
+    {
+      "epoch": 0.5333333333333333,
+      "eval_loss": 0.0026384310331195593,
+      "eval_runtime": 104.0301,
+      "eval_samples_per_second": 9.613,
+      "eval_steps_per_second": 0.481,
+      "step": 240
+    },
+    {
+      "epoch": 0.5555555555555556,
+      "grad_norm": 0.030363447964191437,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 0.0028,
+      "step": 250
+    },
+    {
+      "epoch": 0.5777777777777777,
+      "grad_norm": 0.0183635912835598,
+      "learning_rate": 3.790390522001662e-05,
+      "loss": 0.0027,
+      "step": 260
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.04144422709941864,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 0.0027,
+      "step": 270
+    },
+    {
+      "epoch": 0.6,
+      "eval_loss": 0.0025762419681996107,
+      "eval_runtime": 104.0363,
+      "eval_samples_per_second": 9.612,
+      "eval_steps_per_second": 0.481,
+      "step": 270
+    },
+    {
+      "epoch": 0.6222222222222222,
+      "grad_norm": 0.030761701986193657,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 0.0027,
+      "step": 280
+    },
+    {
+      "epoch": 0.6444444444444445,
+      "grad_norm": 0.017133990302681923,
+      "learning_rate": 2.8081442660546125e-05,
+      "loss": 0.0024,
+      "step": 290
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 0.03892870247364044,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.0027,
+      "step": 300
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "eval_loss": 0.002488846192136407,
+      "eval_runtime": 104.0584,
+      "eval_samples_per_second": 9.61,
+      "eval_steps_per_second": 0.48,
+      "step": 300
+    },
+    {
+      "epoch": 0.6888888888888889,
+      "grad_norm": 0.04978968948125839,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 0.0024,
+      "step": 310
+    },
+    {
+      "epoch": 0.7111111111111111,
+      "grad_norm": 0.059906598180532455,
+      "learning_rate": 1.9216926233717085e-05,
+      "loss": 0.0029,
+      "step": 320
+    },
+    {
+      "epoch": 0.7333333333333333,
+      "grad_norm": 0.015218794345855713,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 0.0027,
+      "step": 330
+    },
+    {
+      "epoch": 0.7333333333333333,
+      "eval_loss": 0.002476006979122758,
+      "eval_runtime": 103.9799,
+      "eval_samples_per_second": 9.617,
+      "eval_steps_per_second": 0.481,
+      "step": 330
+    },
+    {
+      "epoch": 0.7555555555555555,
+      "grad_norm": 0.019350852817296982,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 0.0025,
+      "step": 340
+    },
+    {
+      "epoch": 0.7777777777777778,
+      "grad_norm": 0.013380717486143112,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 0.0028,
+      "step": 350
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.02001432701945305,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.0026,
+      "step": 360
+    },
+    {
+      "epoch": 0.8,
+      "eval_loss": 0.0024831434711813927,
+      "eval_runtime": 103.9994,
+      "eval_samples_per_second": 9.615,
+      "eval_steps_per_second": 0.481,
+      "step": 360
+    },
+    {
+      "epoch": 0.8222222222222222,
+      "grad_norm": 0.015223371796309948,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 0.0028,
+      "step": 370
+    },
+    {
+      "epoch": 0.8444444444444444,
+      "grad_norm": 0.025087540969252586,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 0.0023,
+      "step": 380
+    },
+    {
+      "epoch": 0.8666666666666667,
+      "grad_norm": 0.02467016503214836,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 0.0026,
+      "step": 390
+    },
+    {
+      "epoch": 0.8666666666666667,
+      "eval_loss": 0.0023999777622520924,
+      "eval_runtime": 104.097,
+      "eval_samples_per_second": 9.606,
+      "eval_steps_per_second": 0.48,
+      "step": 390
+    },
+    {
+      "epoch": 0.8888888888888888,
+      "grad_norm": 0.043387334793806076,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 0.0025,
+      "step": 400
+    },
+    {
+      "epoch": 0.9111111111111111,
+      "grad_norm": 0.07373631745576859,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 0.0028,
+      "step": 410
+    },
+    {
+      "epoch": 0.9333333333333333,
+      "grad_norm": 0.05141167715191841,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 0.0024,
+      "step": 420
+    },
+    {
+      "epoch": 0.9333333333333333,
+      "eval_loss": 0.002397245028987527,
+      "eval_runtime": 104.0308,
+      "eval_samples_per_second": 9.613,
+      "eval_steps_per_second": 0.481,
+      "step": 420
+    },
+    {
+      "epoch": 0.9555555555555556,
+      "grad_norm": 0.03251807764172554,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 0.0024,
+      "step": 430
+    },
+    {
+      "epoch": 0.9777777777777777,
+      "grad_norm": 0.028111129999160767,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 0.0023,
+      "step": 440
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.022347470745444298,
+      "learning_rate": 0.0,
+      "loss": 0.0025,
+      "step": 450
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.0023939567618072033,
+      "eval_runtime": 103.9872,
+      "eval_samples_per_second": 9.617,
+      "eval_steps_per_second": 0.481,
+      "step": 450
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 450,
+  "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": 7.36157876644479e+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:b9086e5af163f5bc4483cd783f0f97a051476139f0401e2d1aa270b47047834e
+size 5432

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 0.0023939567618072033,
+    "eval_runtime": 103.9198,
+    "eval_samples_per_second": 9.623,
+    "eval_steps_per_second": 0.481
+}

runs/Jan16_01-13-50_yadi/events.out.tfevents.1736990148.yadi.670631.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f056b672dfcf2d9f968c54346f0b0b83598be91f84bcdec481090b5d07e5e301
+size 19150

runs/Jan16_01-13-50_yadi/events.out.tfevents.1736995003.yadi.670631.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df4c3f2071d994a8d1d268311e0e43e56650a4208f3ad3fe17a15038799e386f
+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": 7.36157876644479e+17,
+    "train_loss": 0.00987041109551986,
+    "train_runtime": 4750.9394,
+    "train_samples_per_second": 1.894,
+    "train_steps_per_second": 0.095
+}

trainer_log.jsonl

@@ -0,0 +1,61 @@
+{"current_steps": 10, "total_steps": 450, "loss": 0.3017, "lr": 9.987820251299122e-05, "epoch": 0.022222222222222223, "percentage": 2.22, "elapsed_time": "0:01:08", "remaining_time": "0:50:10"}
+{"current_steps": 20, "total_steps": 450, "loss": 0.0063, "lr": 9.951340343707852e-05, "epoch": 0.044444444444444446, "percentage": 4.44, "elapsed_time": "0:02:16", "remaining_time": "0:48:45"}
+{"current_steps": 30, "total_steps": 450, "loss": 0.0041, "lr": 9.890738003669029e-05, "epoch": 0.06666666666666667, "percentage": 6.67, "elapsed_time": "0:03:24", "remaining_time": "0:47:36"}
+{"current_steps": 30, "total_steps": 450, "eval_loss": 0.004034009762108326, "epoch": 0.06666666666666667, "percentage": 6.67, "elapsed_time": "0:05:08", "remaining_time": "1:11:53"}
+{"current_steps": 40, "total_steps": 450, "loss": 0.004, "lr": 9.806308479691595e-05, "epoch": 0.08888888888888889, "percentage": 8.89, "elapsed_time": "0:06:16", "remaining_time": "1:04:15"}
+{"current_steps": 50, "total_steps": 450, "loss": 0.004, "lr": 9.698463103929542e-05, "epoch": 0.1111111111111111, "percentage": 11.11, "elapsed_time": "0:07:24", "remaining_time": "0:59:14"}
+{"current_steps": 60, "total_steps": 450, "loss": 0.0039, "lr": 9.567727288213005e-05, "epoch": 0.13333333333333333, "percentage": 13.33, "elapsed_time": "0:08:32", "remaining_time": "0:55:30"}
+{"current_steps": 60, "total_steps": 450, "eval_loss": 0.0039054970256984234, "epoch": 0.13333333333333333, "percentage": 13.33, "elapsed_time": "0:10:16", "remaining_time": "1:06:46"}
+{"current_steps": 70, "total_steps": 450, "loss": 0.0039, "lr": 9.414737964294636e-05, "epoch": 0.15555555555555556, "percentage": 15.56, "elapsed_time": "0:11:24", "remaining_time": "1:01:55"}
+{"current_steps": 80, "total_steps": 450, "loss": 0.0039, "lr": 9.24024048078213e-05, "epoch": 0.17777777777777778, "percentage": 17.78, "elapsed_time": "0:12:32", "remaining_time": "0:58:00"}
+{"current_steps": 90, "total_steps": 450, "loss": 0.0039, "lr": 9.045084971874738e-05, "epoch": 0.2, "percentage": 20.0, "elapsed_time": "0:13:40", "remaining_time": "0:54:42"}
+{"current_steps": 90, "total_steps": 450, "eval_loss": 0.0038894277531653643, "epoch": 0.2, "percentage": 20.0, "elapsed_time": "0:16:30", "remaining_time": "1:06:01"}
+{"current_steps": 100, "total_steps": 450, "loss": 0.0039, "lr": 8.83022221559489e-05, "epoch": 0.2222222222222222, "percentage": 22.22, "elapsed_time": "0:18:36", "remaining_time": "1:05:08"}
+{"current_steps": 110, "total_steps": 450, "loss": 0.0039, "lr": 8.596699001693255e-05, "epoch": 0.24444444444444444, "percentage": 24.44, "elapsed_time": "0:19:44", "remaining_time": "1:01:01"}
+{"current_steps": 120, "total_steps": 450, "loss": 0.0039, "lr": 8.345653031794292e-05, "epoch": 0.26666666666666666, "percentage": 26.67, "elapsed_time": "0:20:52", "remaining_time": "0:57:25"}
+{"current_steps": 120, "total_steps": 450, "eval_loss": 0.00390805397182703, "epoch": 0.26666666666666666, "percentage": 26.67, "elapsed_time": "0:22:37", "remaining_time": "1:02:11"}
+{"current_steps": 130, "total_steps": 450, "loss": 0.0039, "lr": 8.07830737662829e-05, "epoch": 0.28888888888888886, "percentage": 28.89, "elapsed_time": "0:23:45", "remaining_time": "0:58:27"}
+{"current_steps": 140, "total_steps": 450, "loss": 0.0039, "lr": 7.795964517353735e-05, "epoch": 0.3111111111111111, "percentage": 31.11, "elapsed_time": "0:24:53", "remaining_time": "0:55:06"}
+{"current_steps": 150, "total_steps": 450, "loss": 0.0038, "lr": 7.500000000000001e-05, "epoch": 0.3333333333333333, "percentage": 33.33, "elapsed_time": "0:26:01", "remaining_time": "0:52:02"}
+{"current_steps": 150, "total_steps": 450, "eval_loss": 0.00407786201685667, "epoch": 0.3333333333333333, "percentage": 33.33, "elapsed_time": "0:27:45", "remaining_time": "0:55:30"}
+{"current_steps": 160, "total_steps": 450, "loss": 0.0039, "lr": 7.191855733945387e-05, "epoch": 0.35555555555555557, "percentage": 35.56, "elapsed_time": "0:28:53", "remaining_time": "0:52:21"}
+{"current_steps": 170, "total_steps": 450, "loss": 0.0039, "lr": 6.873032967079561e-05, "epoch": 0.37777777777777777, "percentage": 37.78, "elapsed_time": "0:30:01", "remaining_time": "0:49:27"}
+{"current_steps": 180, "total_steps": 450, "loss": 0.0038, "lr": 6.545084971874738e-05, "epoch": 0.4, "percentage": 40.0, "elapsed_time": "0:31:09", "remaining_time": "0:46:44"}
+{"current_steps": 180, "total_steps": 450, "eval_loss": 0.0037861280143260956, "epoch": 0.4, "percentage": 40.0, "elapsed_time": "0:32:53", "remaining_time": "0:49:20"}
+{"current_steps": 190, "total_steps": 450, "loss": 0.0037, "lr": 6.209609477998338e-05, "epoch": 0.4222222222222222, "percentage": 42.22, "elapsed_time": "0:34:01", "remaining_time": "0:46:34"}
+{"current_steps": 200, "total_steps": 450, "loss": 0.0034, "lr": 5.868240888334653e-05, "epoch": 0.4444444444444444, "percentage": 44.44, "elapsed_time": "0:35:09", "remaining_time": "0:43:57"}
+{"current_steps": 210, "total_steps": 450, "loss": 0.003, "lr": 5.522642316338268e-05, "epoch": 0.4666666666666667, "percentage": 46.67, "elapsed_time": "0:36:18", "remaining_time": "0:41:29"}
+{"current_steps": 210, "total_steps": 450, "eval_loss": 0.002776140347123146, "epoch": 0.4666666666666667, "percentage": 46.67, "elapsed_time": "0:38:02", "remaining_time": "0:43:28"}
+{"current_steps": 220, "total_steps": 450, "loss": 0.0031, "lr": 5.174497483512506e-05, "epoch": 0.4888888888888889, "percentage": 48.89, "elapsed_time": "0:39:10", "remaining_time": "0:40:56"}
+{"current_steps": 230, "total_steps": 450, "loss": 0.0028, "lr": 4.825502516487497e-05, "epoch": 0.5111111111111111, "percentage": 51.11, "elapsed_time": "0:40:18", "remaining_time": "0:38:33"}
+{"current_steps": 240, "total_steps": 450, "loss": 0.0029, "lr": 4.477357683661734e-05, "epoch": 0.5333333333333333, "percentage": 53.33, "elapsed_time": "0:41:26", "remaining_time": "0:36:15"}
+{"current_steps": 240, "total_steps": 450, "eval_loss": 0.0026384310331195593, "epoch": 0.5333333333333333, "percentage": 53.33, "elapsed_time": "0:43:10", "remaining_time": "0:37:46"}
+{"current_steps": 250, "total_steps": 450, "loss": 0.0028, "lr": 4.131759111665349e-05, "epoch": 0.5555555555555556, "percentage": 55.56, "elapsed_time": "0:44:18", "remaining_time": "0:35:26"}
+{"current_steps": 260, "total_steps": 450, "loss": 0.0027, "lr": 3.790390522001662e-05, "epoch": 0.5777777777777777, "percentage": 57.78, "elapsed_time": "0:45:26", "remaining_time": "0:33:12"}
+{"current_steps": 270, "total_steps": 450, "loss": 0.0027, "lr": 3.4549150281252636e-05, "epoch": 0.6, "percentage": 60.0, "elapsed_time": "0:46:34", "remaining_time": "0:31:02"}
+{"current_steps": 270, "total_steps": 450, "eval_loss": 0.0025762419681996107, "epoch": 0.6, "percentage": 60.0, "elapsed_time": "0:48:18", "remaining_time": "0:32:12"}
+{"current_steps": 280, "total_steps": 450, "loss": 0.0027, "lr": 3.12696703292044e-05, "epoch": 0.6222222222222222, "percentage": 62.22, "elapsed_time": "0:49:26", "remaining_time": "0:30:01"}
+{"current_steps": 290, "total_steps": 450, "loss": 0.0024, "lr": 2.8081442660546125e-05, "epoch": 0.6444444444444445, "percentage": 64.44, "elapsed_time": "0:50:34", "remaining_time": "0:27:54"}
+{"current_steps": 300, "total_steps": 450, "loss": 0.0027, "lr": 2.500000000000001e-05, "epoch": 0.6666666666666666, "percentage": 66.67, "elapsed_time": "0:51:42", "remaining_time": "0:25:51"}
+{"current_steps": 300, "total_steps": 450, "eval_loss": 0.002488846192136407, "epoch": 0.6666666666666666, "percentage": 66.67, "elapsed_time": "0:53:26", "remaining_time": "0:26:43"}
+{"current_steps": 310, "total_steps": 450, "loss": 0.0024, "lr": 2.2040354826462668e-05, "epoch": 0.6888888888888889, "percentage": 68.89, "elapsed_time": "0:54:34", "remaining_time": "0:24:38"}
+{"current_steps": 320, "total_steps": 450, "loss": 0.0029, "lr": 1.9216926233717085e-05, "epoch": 0.7111111111111111, "percentage": 71.11, "elapsed_time": "0:55:42", "remaining_time": "0:22:37"}
+{"current_steps": 330, "total_steps": 450, "loss": 0.0027, "lr": 1.6543469682057106e-05, "epoch": 0.7333333333333333, "percentage": 73.33, "elapsed_time": "0:56:50", "remaining_time": "0:20:40"}
+{"current_steps": 330, "total_steps": 450, "eval_loss": 0.002476006979122758, "epoch": 0.7333333333333333, "percentage": 73.33, "elapsed_time": "0:58:34", "remaining_time": "0:21:18"}
+{"current_steps": 340, "total_steps": 450, "loss": 0.0025, "lr": 1.4033009983067452e-05, "epoch": 0.7555555555555555, "percentage": 75.56, "elapsed_time": "0:59:42", "remaining_time": "0:19:19"}
+{"current_steps": 350, "total_steps": 450, "loss": 0.0028, "lr": 1.1697777844051105e-05, "epoch": 0.7777777777777778, "percentage": 77.78, "elapsed_time": "1:00:50", "remaining_time": "0:17:23"}
+{"current_steps": 360, "total_steps": 450, "loss": 0.0026, "lr": 9.549150281252633e-06, "epoch": 0.8, "percentage": 80.0, "elapsed_time": "1:01:58", "remaining_time": "0:15:29"}
+{"current_steps": 360, "total_steps": 450, "eval_loss": 0.0024831434711813927, "epoch": 0.8, "percentage": 80.0, "elapsed_time": "1:03:42", "remaining_time": "0:15:55"}
+{"current_steps": 370, "total_steps": 450, "loss": 0.0028, "lr": 7.597595192178702e-06, "epoch": 0.8222222222222222, "percentage": 82.22, "elapsed_time": "1:04:50", "remaining_time": "0:14:01"}
+{"current_steps": 380, "total_steps": 450, "loss": 0.0023, "lr": 5.852620357053651e-06, "epoch": 0.8444444444444444, "percentage": 84.44, "elapsed_time": "1:05:58", "remaining_time": "0:12:09"}
+{"current_steps": 390, "total_steps": 450, "loss": 0.0026, "lr": 4.322727117869951e-06, "epoch": 0.8666666666666667, "percentage": 86.67, "elapsed_time": "1:07:07", "remaining_time": "0:10:19"}
+{"current_steps": 390, "total_steps": 450, "eval_loss": 0.0023999777622520924, "epoch": 0.8666666666666667, "percentage": 86.67, "elapsed_time": "1:08:51", "remaining_time": "0:10:35"}
+{"current_steps": 400, "total_steps": 450, "loss": 0.0025, "lr": 3.0153689607045845e-06, "epoch": 0.8888888888888888, "percentage": 88.89, "elapsed_time": "1:09:59", "remaining_time": "0:08:44"}
+{"current_steps": 410, "total_steps": 450, "loss": 0.0028, "lr": 1.9369152030840556e-06, "epoch": 0.9111111111111111, "percentage": 91.11, "elapsed_time": "1:11:07", "remaining_time": "0:06:56"}
+{"current_steps": 420, "total_steps": 450, "loss": 0.0024, "lr": 1.0926199633097157e-06, "epoch": 0.9333333333333333, "percentage": 93.33, "elapsed_time": "1:12:15", "remaining_time": "0:05:09"}
+{"current_steps": 420, "total_steps": 450, "eval_loss": 0.002397245028987527, "epoch": 0.9333333333333333, "percentage": 93.33, "elapsed_time": "1:13:59", "remaining_time": "0:05:17"}
+{"current_steps": 430, "total_steps": 450, "loss": 0.0024, "lr": 4.865965629214819e-07, "epoch": 0.9555555555555556, "percentage": 95.56, "elapsed_time": "1:15:07", "remaining_time": "0:03:29"}
+{"current_steps": 440, "total_steps": 450, "loss": 0.0023, "lr": 1.2179748700879012e-07, "epoch": 0.9777777777777777, "percentage": 97.78, "elapsed_time": "1:16:15", "remaining_time": "0:01:43"}
+{"current_steps": 450, "total_steps": 450, "loss": 0.0025, "lr": 0.0, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "1:17:23", "remaining_time": "0:00:00"}
+{"current_steps": 450, "total_steps": 450, "eval_loss": 0.0023939567618072033, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "1:19:07", "remaining_time": "0:00:00"}
+{"current_steps": 450, "total_steps": 450, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "1:19:09", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,477 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 30,
+  "global_step": 450,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.022222222222222223,
+      "grad_norm": 0.46052348613739014,
+      "learning_rate": 9.987820251299122e-05,
+      "loss": 0.3017,
+      "step": 10
+    },
+    {
+      "epoch": 0.044444444444444446,
+      "grad_norm": 0.0518617108464241,
+      "learning_rate": 9.951340343707852e-05,
+      "loss": 0.0063,
+      "step": 20
+    },
+    {
+      "epoch": 0.06666666666666667,
+      "grad_norm": 0.02703821286559105,
+      "learning_rate": 9.890738003669029e-05,
+      "loss": 0.0041,
+      "step": 30
+    },
+    {
+      "epoch": 0.06666666666666667,
+      "eval_loss": 0.004034009762108326,
+      "eval_runtime": 104.0521,
+      "eval_samples_per_second": 9.611,
+      "eval_steps_per_second": 0.481,
+      "step": 30
+    },
+    {
+      "epoch": 0.08888888888888889,
+      "grad_norm": 0.011427383869886398,
+      "learning_rate": 9.806308479691595e-05,
+      "loss": 0.004,
+      "step": 40
+    },
+    {
+      "epoch": 0.1111111111111111,
+      "grad_norm": 0.022027652710676193,
+      "learning_rate": 9.698463103929542e-05,
+      "loss": 0.004,
+      "step": 50
+    },
+    {
+      "epoch": 0.13333333333333333,
+      "grad_norm": 0.001629775040782988,
+      "learning_rate": 9.567727288213005e-05,
+      "loss": 0.0039,
+      "step": 60
+    },
+    {
+      "epoch": 0.13333333333333333,
+      "eval_loss": 0.0039054970256984234,
+      "eval_runtime": 104.0544,
+      "eval_samples_per_second": 9.61,
+      "eval_steps_per_second": 0.481,
+      "step": 60
+    },
+    {
+      "epoch": 0.15555555555555556,
+      "grad_norm": 0.04784173518419266,
+      "learning_rate": 9.414737964294636e-05,
+      "loss": 0.0039,
+      "step": 70
+    },
+    {
+      "epoch": 0.17777777777777778,
+      "grad_norm": 0.020441358909010887,
+      "learning_rate": 9.24024048078213e-05,
+      "loss": 0.0039,
+      "step": 80
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.0022530381102114916,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 0.0039,
+      "step": 90
+    },
+    {
+      "epoch": 0.2,
+      "eval_loss": 0.0038894277531653643,
+      "eval_runtime": 169.6744,
+      "eval_samples_per_second": 5.894,
+      "eval_steps_per_second": 0.295,
+      "step": 90
+    },
+    {
+      "epoch": 0.2222222222222222,
+      "grad_norm": 0.006415847223252058,
+      "learning_rate": 8.83022221559489e-05,
+      "loss": 0.0039,
+      "step": 100
+    },
+    {
+      "epoch": 0.24444444444444444,
+      "grad_norm": 0.0103780971840024,
+      "learning_rate": 8.596699001693255e-05,
+      "loss": 0.0039,
+      "step": 110
+    },
+    {
+      "epoch": 0.26666666666666666,
+      "grad_norm": 0.016158604994416237,
+      "learning_rate": 8.345653031794292e-05,
+      "loss": 0.0039,
+      "step": 120
+    },
+    {
+      "epoch": 0.26666666666666666,
+      "eval_loss": 0.00390805397182703,
+      "eval_runtime": 104.1821,
+      "eval_samples_per_second": 9.599,
+      "eval_steps_per_second": 0.48,
+      "step": 120
+    },
+    {
+      "epoch": 0.28888888888888886,
+      "grad_norm": 0.004166940692812204,
+      "learning_rate": 8.07830737662829e-05,
+      "loss": 0.0039,
+      "step": 130
+    },
+    {
+      "epoch": 0.3111111111111111,
+      "grad_norm": 0.0024945680052042007,
+      "learning_rate": 7.795964517353735e-05,
+      "loss": 0.0039,
+      "step": 140
+    },
+    {
+      "epoch": 0.3333333333333333,
+      "grad_norm": 0.024202220141887665,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 0.0038,
+      "step": 150
+    },
+    {
+      "epoch": 0.3333333333333333,
+      "eval_loss": 0.00407786201685667,
+      "eval_runtime": 104.0841,
+      "eval_samples_per_second": 9.608,
+      "eval_steps_per_second": 0.48,
+      "step": 150
+    },
+    {
+      "epoch": 0.35555555555555557,
+      "grad_norm": 0.005438762251287699,
+      "learning_rate": 7.191855733945387e-05,
+      "loss": 0.0039,
+      "step": 160
+    },
+    {
+      "epoch": 0.37777777777777777,
+      "grad_norm": 0.008657037280499935,
+      "learning_rate": 6.873032967079561e-05,
+      "loss": 0.0039,
+      "step": 170
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.014475060626864433,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 0.0038,
+      "step": 180
+    },
+    {
+      "epoch": 0.4,
+      "eval_loss": 0.0037861280143260956,
+      "eval_runtime": 104.145,
+      "eval_samples_per_second": 9.602,
+      "eval_steps_per_second": 0.48,
+      "step": 180
+    },
+    {
+      "epoch": 0.4222222222222222,
+      "grad_norm": 0.013048152439296246,
+      "learning_rate": 6.209609477998338e-05,
+      "loss": 0.0037,
+      "step": 190
+    },
+    {
+      "epoch": 0.4444444444444444,
+      "grad_norm": 0.04640911519527435,
+      "learning_rate": 5.868240888334653e-05,
+      "loss": 0.0034,
+      "step": 200
+    },
+    {
+      "epoch": 0.4666666666666667,
+      "grad_norm": 0.019521236419677734,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 0.003,
+      "step": 210
+    },
+    {
+      "epoch": 0.4666666666666667,
+      "eval_loss": 0.002776140347123146,
+      "eval_runtime": 104.0124,
+      "eval_samples_per_second": 9.614,
+      "eval_steps_per_second": 0.481,
+      "step": 210
+    },
+    {
+      "epoch": 0.4888888888888889,
+      "grad_norm": 0.03593623265624046,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 0.0031,
+      "step": 220
+    },
+    {
+      "epoch": 0.5111111111111111,
+      "grad_norm": 0.06989370286464691,
+      "learning_rate": 4.825502516487497e-05,
+      "loss": 0.0028,
+      "step": 230
+    },
+    {
+      "epoch": 0.5333333333333333,
+      "grad_norm": 0.022669225931167603,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 0.0029,
+      "step": 240
+    },
+    {
+      "epoch": 0.5333333333333333,
+      "eval_loss": 0.0026384310331195593,
+      "eval_runtime": 104.0301,
+      "eval_samples_per_second": 9.613,
+      "eval_steps_per_second": 0.481,
+      "step": 240
+    },
+    {
+      "epoch": 0.5555555555555556,
+      "grad_norm": 0.030363447964191437,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 0.0028,
+      "step": 250
+    },
+    {
+      "epoch": 0.5777777777777777,
+      "grad_norm": 0.0183635912835598,
+      "learning_rate": 3.790390522001662e-05,
+      "loss": 0.0027,
+      "step": 260
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.04144422709941864,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 0.0027,
+      "step": 270
+    },
+    {
+      "epoch": 0.6,
+      "eval_loss": 0.0025762419681996107,
+      "eval_runtime": 104.0363,
+      "eval_samples_per_second": 9.612,
+      "eval_steps_per_second": 0.481,
+      "step": 270
+    },
+    {
+      "epoch": 0.6222222222222222,
+      "grad_norm": 0.030761701986193657,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 0.0027,
+      "step": 280
+    },
+    {
+      "epoch": 0.6444444444444445,
+      "grad_norm": 0.017133990302681923,
+      "learning_rate": 2.8081442660546125e-05,
+      "loss": 0.0024,
+      "step": 290
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 0.03892870247364044,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.0027,
+      "step": 300
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "eval_loss": 0.002488846192136407,
+      "eval_runtime": 104.0584,
+      "eval_samples_per_second": 9.61,
+      "eval_steps_per_second": 0.48,
+      "step": 300
+    },
+    {
+      "epoch": 0.6888888888888889,
+      "grad_norm": 0.04978968948125839,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 0.0024,
+      "step": 310
+    },
+    {
+      "epoch": 0.7111111111111111,
+      "grad_norm": 0.059906598180532455,
+      "learning_rate": 1.9216926233717085e-05,
+      "loss": 0.0029,
+      "step": 320
+    },
+    {
+      "epoch": 0.7333333333333333,
+      "grad_norm": 0.015218794345855713,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 0.0027,
+      "step": 330
+    },
+    {
+      "epoch": 0.7333333333333333,
+      "eval_loss": 0.002476006979122758,
+      "eval_runtime": 103.9799,
+      "eval_samples_per_second": 9.617,
+      "eval_steps_per_second": 0.481,
+      "step": 330
+    },
+    {
+      "epoch": 0.7555555555555555,
+      "grad_norm": 0.019350852817296982,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 0.0025,
+      "step": 340
+    },
+    {
+      "epoch": 0.7777777777777778,
+      "grad_norm": 0.013380717486143112,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 0.0028,
+      "step": 350
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.02001432701945305,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.0026,
+      "step": 360
+    },
+    {
+      "epoch": 0.8,
+      "eval_loss": 0.0024831434711813927,
+      "eval_runtime": 103.9994,
+      "eval_samples_per_second": 9.615,
+      "eval_steps_per_second": 0.481,
+      "step": 360
+    },
+    {
+      "epoch": 0.8222222222222222,
+      "grad_norm": 0.015223371796309948,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 0.0028,
+      "step": 370
+    },
+    {
+      "epoch": 0.8444444444444444,
+      "grad_norm": 0.025087540969252586,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 0.0023,
+      "step": 380
+    },
+    {
+      "epoch": 0.8666666666666667,
+      "grad_norm": 0.02467016503214836,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 0.0026,
+      "step": 390
+    },
+    {
+      "epoch": 0.8666666666666667,
+      "eval_loss": 0.0023999777622520924,
+      "eval_runtime": 104.097,
+      "eval_samples_per_second": 9.606,
+      "eval_steps_per_second": 0.48,
+      "step": 390
+    },
+    {
+      "epoch": 0.8888888888888888,
+      "grad_norm": 0.043387334793806076,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 0.0025,
+      "step": 400
+    },
+    {
+      "epoch": 0.9111111111111111,
+      "grad_norm": 0.07373631745576859,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 0.0028,
+      "step": 410
+    },
+    {
+      "epoch": 0.9333333333333333,
+      "grad_norm": 0.05141167715191841,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 0.0024,
+      "step": 420
+    },
+    {
+      "epoch": 0.9333333333333333,
+      "eval_loss": 0.002397245028987527,
+      "eval_runtime": 104.0308,
+      "eval_samples_per_second": 9.613,
+      "eval_steps_per_second": 0.481,
+      "step": 420
+    },
+    {
+      "epoch": 0.9555555555555556,
+      "grad_norm": 0.03251807764172554,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 0.0024,
+      "step": 430
+    },
+    {
+      "epoch": 0.9777777777777777,
+      "grad_norm": 0.028111129999160767,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 0.0023,
+      "step": 440
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.022347470745444298,
+      "learning_rate": 0.0,
+      "loss": 0.0025,
+      "step": 450
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.0023939567618072033,
+      "eval_runtime": 103.9872,
+      "eval_samples_per_second": 9.617,
+      "eval_steps_per_second": 0.481,
+      "step": 450
+    },
+    {
+      "epoch": 1.0,
+      "step": 450,
+      "total_flos": 7.36157876644479e+17,
+      "train_loss": 0.00987041109551986,
+      "train_runtime": 4750.9394,
+      "train_samples_per_second": 1.894,
+      "train_steps_per_second": 0.095
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 450,
+  "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": 7.36157876644479e+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:b9086e5af163f5bc4483cd783f0f97a051476139f0401e2d1aa270b47047834e
+size 5432