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-225/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,71 @@
+---
+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_u_1epoch
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# epidemiology_sft_10000_mcq_u_1epoch
+
+This model is a fine-tuned version of [mistralai/Mistral-Nemo-Instruct-2407](https://huggingface.co/mistralai/Mistral-Nemo-Instruct-2407) on the epidemiology_10000_mcq_u dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0035
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 0.0001
+- train_batch_size: 10
+- eval_batch_size: 10
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 4
+- total_train_batch_size: 40
+- total_eval_batch_size: 40
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- num_epochs: 1
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 0.0039        | 0.1333 | 30   | 0.0036          |
+| 0.0038        | 0.2667 | 60   | 0.0037          |
+| 0.0036        | 0.4    | 90   | 0.0036          |
+| 0.0036        | 0.5333 | 120  | 0.0035          |
+| 0.0036        | 0.6667 | 150  | 0.0035          |
+| 0.0035        | 0.8    | 180  | 0.0035          |
+| 0.0035        | 0.9333 | 210  | 0.0035          |
+
+
+### Framework versions
+
+- PEFT 0.12.0
+- Transformers 4.46.0
+- Pytorch 2.4.0+cu121
+- Datasets 2.21.0
+- Tokenizers 0.20.1

adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mistral-Nemo-Instruct-2407",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "up_proj",
+    "down_proj",
+    "gate_proj",
+    "q_proj",
+    "v_proj",
+    "o_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 sha256:7e8786eeb1bd79d8b7ea9d63e87f3e18ebe7e757f516d657b5e0929ce5dd4222
+size 114106856

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 0.003535117954015732,
+    "eval_runtime": 53.3197,
+    "eval_samples_per_second": 18.755,
+    "eval_steps_per_second": 0.469,
+    "total_flos": 7.559164517091901e+17,
+    "train_loss": 0.017044952660799025,
+    "train_runtime": 1944.9953,
+    "train_samples_per_second": 4.627,
+    "train_steps_per_second": 0.116
+}

checkpoint-225/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-225/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mistral-Nemo-Instruct-2407",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "up_proj",
+    "down_proj",
+    "gate_proj",
+    "q_proj",
+    "v_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-225/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e8786eeb1bd79d8b7ea9d63e87f3e18ebe7e757f516d657b5e0929ce5dd4222
+size 114106856

checkpoint-225/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f6d72333a085ce0afc0f592fc91d6a2eca268977a16740d4447c1172db2980b
+size 228536930

checkpoint-225/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee97cd82dba4d425fdd8dfdb88d4a43d0d4b1979b5c81ab4a24914fb00d4f332
+size 15024

checkpoint-225/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91dad95440fb85dc4a31745642117165c1a72173b2e389679ea8c0b2b6fcd7e2
+size 15024

checkpoint-225/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98698326b023c2af02c94f18726ce52c7f7a6fe290734dd7edbe99bc807fcfa0
+size 15024

checkpoint-225/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:708e7c6b5bf8a327e688779ebc08830ce249928bcb1ff5c82b1b1d0bf6d2660b
+size 15024

checkpoint-225/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d2e8e1082d3099d4c132f9a515dd7fe70d2d06f17c6cff03af92316d8601f12
+size 1064

checkpoint-225/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-225/tokenizer.json

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

checkpoint-225/trainer_state.json

@@ -0,0 +1,243 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 30,
+  "global_step": 225,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.044444444444444446,
+      "grad_norm": 0.2802587151527405,
+      "learning_rate": 9.951340343707852e-05,
+      "loss": 0.3045,
+      "step": 10
+    },
+    {
+      "epoch": 0.08888888888888889,
+      "grad_norm": 0.021381886675953865,
+      "learning_rate": 9.806308479691595e-05,
+      "loss": 0.0054,
+      "step": 20
+    },
+    {
+      "epoch": 0.13333333333333333,
+      "grad_norm": 0.017750784754753113,
+      "learning_rate": 9.567727288213005e-05,
+      "loss": 0.0039,
+      "step": 30
+    },
+    {
+      "epoch": 0.13333333333333333,
+      "eval_loss": 0.0036237684544175863,
+      "eval_runtime": 53.377,
+      "eval_samples_per_second": 18.735,
+      "eval_steps_per_second": 0.468,
+      "step": 30
+    },
+    {
+      "epoch": 0.17777777777777778,
+      "grad_norm": 0.009207488968968391,
+      "learning_rate": 9.24024048078213e-05,
+      "loss": 0.0036,
+      "step": 40
+    },
+    {
+      "epoch": 0.2222222222222222,
+      "grad_norm": 0.03058847412467003,
+      "learning_rate": 8.83022221559489e-05,
+      "loss": 0.0037,
+      "step": 50
+    },
+    {
+      "epoch": 0.26666666666666666,
+      "grad_norm": 0.023914409801363945,
+      "learning_rate": 8.345653031794292e-05,
+      "loss": 0.0038,
+      "step": 60
+    },
+    {
+      "epoch": 0.26666666666666666,
+      "eval_loss": 0.0036710596177726984,
+      "eval_runtime": 53.396,
+      "eval_samples_per_second": 18.728,
+      "eval_steps_per_second": 0.468,
+      "step": 60
+    },
+    {
+      "epoch": 0.3111111111111111,
+      "grad_norm": 0.0324842669069767,
+      "learning_rate": 7.795964517353735e-05,
+      "loss": 0.0036,
+      "step": 70
+    },
+    {
+      "epoch": 0.35555555555555557,
+      "grad_norm": 0.002750804414972663,
+      "learning_rate": 7.191855733945387e-05,
+      "loss": 0.0036,
+      "step": 80
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.0023576547391712666,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 0.0036,
+      "step": 90
+    },
+    {
+      "epoch": 0.4,
+      "eval_loss": 0.003560666460543871,
+      "eval_runtime": 53.4786,
+      "eval_samples_per_second": 18.699,
+      "eval_steps_per_second": 0.467,
+      "step": 90
+    },
+    {
+      "epoch": 0.4444444444444444,
+      "grad_norm": 0.016149163246154785,
+      "learning_rate": 5.868240888334653e-05,
+      "loss": 0.0036,
+      "step": 100
+    },
+    {
+      "epoch": 0.4888888888888889,
+      "grad_norm": 0.0039548748172819614,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 0.0035,
+      "step": 110
+    },
+    {
+      "epoch": 0.5333333333333333,
+      "grad_norm": 0.0059623029083013535,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 0.0036,
+      "step": 120
+    },
+    {
+      "epoch": 0.5333333333333333,
+      "eval_loss": 0.00353414099663496,
+      "eval_runtime": 53.3696,
+      "eval_samples_per_second": 18.737,
+      "eval_steps_per_second": 0.468,
+      "step": 120
+    },
+    {
+      "epoch": 0.5777777777777777,
+      "grad_norm": 0.01755256950855255,
+      "learning_rate": 3.790390522001662e-05,
+      "loss": 0.0035,
+      "step": 130
+    },
+    {
+      "epoch": 0.6222222222222222,
+      "grad_norm": 0.005563901271671057,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 0.0035,
+      "step": 140
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 0.004853326827287674,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.0036,
+      "step": 150
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "eval_loss": 0.0035362462513148785,
+      "eval_runtime": 53.3856,
+      "eval_samples_per_second": 18.732,
+      "eval_steps_per_second": 0.468,
+      "step": 150
+    },
+    {
+      "epoch": 0.7111111111111111,
+      "grad_norm": 0.0062214070931077,
+      "learning_rate": 1.9216926233717085e-05,
+      "loss": 0.0036,
+      "step": 160
+    },
+    {
+      "epoch": 0.7555555555555555,
+      "grad_norm": 0.0025808655191212893,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 0.0035,
+      "step": 170
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.00887165404856205,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.0035,
+      "step": 180
+    },
+    {
+      "epoch": 0.8,
+      "eval_loss": 0.0035414749290794134,
+      "eval_runtime": 53.35,
+      "eval_samples_per_second": 18.744,
+      "eval_steps_per_second": 0.469,
+      "step": 180
+    },
+    {
+      "epoch": 0.8444444444444444,
+      "grad_norm": 0.005598729941993952,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 0.0035,
+      "step": 190
+    },
+    {
+      "epoch": 0.8888888888888888,
+      "grad_norm": 0.010787834413349628,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 0.0035,
+      "step": 200
+    },
+    {
+      "epoch": 0.9333333333333333,
+      "grad_norm": 0.00533076049759984,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 0.0035,
+      "step": 210
+    },
+    {
+      "epoch": 0.9333333333333333,
+      "eval_loss": 0.003532670671120286,
+      "eval_runtime": 53.3444,
+      "eval_samples_per_second": 18.746,
+      "eval_steps_per_second": 0.469,
+      "step": 210
+    },
+    {
+      "epoch": 0.9777777777777777,
+      "grad_norm": 0.006618449930101633,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 0.0035,
+      "step": 220
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 225,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 2000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 7.559164517091901e+17,
+  "train_batch_size": 10,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-225/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1953d1ec3706f1ae90fd4a711244fa77dd5bcf8c5e0658c6dee454a0e6cc3097
+size 5432

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 0.003535117954015732,
+    "eval_runtime": 53.3197,
+    "eval_samples_per_second": 18.755,
+    "eval_steps_per_second": 0.469
+}

runs/Jan28_00-23-21_yadi/events.out.tfevents.1738023974.yadi.354353.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9654cb361ae5052a580e7b1bea1016a78e93c0280646c98b148ee92ed193804
+size 12136

runs/Jan28_00-23-21_yadi/events.out.tfevents.1738025972.yadi.354353.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53ca1e7a1ddd3bd72f57063f6dc90860daeb886f68a575eb1887bd1bf5de6b9e
+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": 7.559164517091901e+17,
+    "train_loss": 0.017044952660799025,
+    "train_runtime": 1944.9953,
+    "train_samples_per_second": 4.627,
+    "train_steps_per_second": 0.116
+}

trainer_log.jsonl

@@ -0,0 +1,30 @@
+{"current_steps": 10, "total_steps": 225, "loss": 0.3045, "lr": 9.951340343707852e-05, "epoch": 0.044444444444444446, "percentage": 4.44, "elapsed_time": "0:01:09", "remaining_time": "0:24:57"}
+{"current_steps": 20, "total_steps": 225, "loss": 0.0054, "lr": 9.806308479691595e-05, "epoch": 0.08888888888888889, "percentage": 8.89, "elapsed_time": "0:02:19", "remaining_time": "0:23:46"}
+{"current_steps": 30, "total_steps": 225, "loss": 0.0039, "lr": 9.567727288213005e-05, "epoch": 0.13333333333333333, "percentage": 13.33, "elapsed_time": "0:03:28", "remaining_time": "0:22:37"}
+{"current_steps": 30, "total_steps": 225, "eval_loss": 0.0036237684544175863, "epoch": 0.13333333333333333, "percentage": 13.33, "elapsed_time": "0:04:22", "remaining_time": "0:28:24"}
+{"current_steps": 40, "total_steps": 225, "loss": 0.0036, "lr": 9.24024048078213e-05, "epoch": 0.17777777777777778, "percentage": 17.78, "elapsed_time": "0:05:31", "remaining_time": "0:25:35"}
+{"current_steps": 50, "total_steps": 225, "loss": 0.0037, "lr": 8.83022221559489e-05, "epoch": 0.2222222222222222, "percentage": 22.22, "elapsed_time": "0:06:41", "remaining_time": "0:23:26"}
+{"current_steps": 60, "total_steps": 225, "loss": 0.0038, "lr": 8.345653031794292e-05, "epoch": 0.26666666666666666, "percentage": 26.67, "elapsed_time": "0:07:51", "remaining_time": "0:21:36"}
+{"current_steps": 60, "total_steps": 225, "eval_loss": 0.0036710596177726984, "epoch": 0.26666666666666666, "percentage": 26.67, "elapsed_time": "0:08:44", "remaining_time": "0:24:03"}
+{"current_steps": 70, "total_steps": 225, "loss": 0.0036, "lr": 7.795964517353735e-05, "epoch": 0.3111111111111111, "percentage": 31.11, "elapsed_time": "0:09:54", "remaining_time": "0:21:56"}
+{"current_steps": 80, "total_steps": 225, "loss": 0.0036, "lr": 7.191855733945387e-05, "epoch": 0.35555555555555557, "percentage": 35.56, "elapsed_time": "0:11:04", "remaining_time": "0:20:04"}
+{"current_steps": 90, "total_steps": 225, "loss": 0.0036, "lr": 6.545084971874738e-05, "epoch": 0.4, "percentage": 40.0, "elapsed_time": "0:12:14", "remaining_time": "0:18:21"}
+{"current_steps": 90, "total_steps": 225, "eval_loss": 0.003560666460543871, "epoch": 0.4, "percentage": 40.0, "elapsed_time": "0:13:07", "remaining_time": "0:19:41"}
+{"current_steps": 100, "total_steps": 225, "loss": 0.0036, "lr": 5.868240888334653e-05, "epoch": 0.4444444444444444, "percentage": 44.44, "elapsed_time": "0:14:17", "remaining_time": "0:17:51"}
+{"current_steps": 110, "total_steps": 225, "loss": 0.0035, "lr": 5.174497483512506e-05, "epoch": 0.4888888888888889, "percentage": 48.89, "elapsed_time": "0:15:27", "remaining_time": "0:16:09"}
+{"current_steps": 120, "total_steps": 225, "loss": 0.0036, "lr": 4.477357683661734e-05, "epoch": 0.5333333333333333, "percentage": 53.33, "elapsed_time": "0:16:36", "remaining_time": "0:14:32"}
+{"current_steps": 120, "total_steps": 225, "eval_loss": 0.00353414099663496, "epoch": 0.5333333333333333, "percentage": 53.33, "elapsed_time": "0:17:30", "remaining_time": "0:15:18"}
+{"current_steps": 130, "total_steps": 225, "loss": 0.0035, "lr": 3.790390522001662e-05, "epoch": 0.5777777777777777, "percentage": 57.78, "elapsed_time": "0:18:40", "remaining_time": "0:13:38"}
+{"current_steps": 140, "total_steps": 225, "loss": 0.0035, "lr": 3.12696703292044e-05, "epoch": 0.6222222222222222, "percentage": 62.22, "elapsed_time": "0:19:49", "remaining_time": "0:12:02"}
+{"current_steps": 150, "total_steps": 225, "loss": 0.0036, "lr": 2.500000000000001e-05, "epoch": 0.6666666666666666, "percentage": 66.67, "elapsed_time": "0:20:59", "remaining_time": "0:10:29"}
+{"current_steps": 150, "total_steps": 225, "eval_loss": 0.0035362462513148785, "epoch": 0.6666666666666666, "percentage": 66.67, "elapsed_time": "0:21:52", "remaining_time": "0:10:56"}
+{"current_steps": 160, "total_steps": 225, "loss": 0.0036, "lr": 1.9216926233717085e-05, "epoch": 0.7111111111111111, "percentage": 71.11, "elapsed_time": "0:23:02", "remaining_time": "0:09:21"}
+{"current_steps": 170, "total_steps": 225, "loss": 0.0035, "lr": 1.4033009983067452e-05, "epoch": 0.7555555555555555, "percentage": 75.56, "elapsed_time": "0:24:11", "remaining_time": "0:07:49"}
+{"current_steps": 180, "total_steps": 225, "loss": 0.0035, "lr": 9.549150281252633e-06, "epoch": 0.8, "percentage": 80.0, "elapsed_time": "0:25:21", "remaining_time": "0:06:20"}
+{"current_steps": 180, "total_steps": 225, "eval_loss": 0.0035414749290794134, "epoch": 0.8, "percentage": 80.0, "elapsed_time": "0:26:14", "remaining_time": "0:06:33"}
+{"current_steps": 190, "total_steps": 225, "loss": 0.0035, "lr": 5.852620357053651e-06, "epoch": 0.8444444444444444, "percentage": 84.44, "elapsed_time": "0:27:24", "remaining_time": "0:05:02"}
+{"current_steps": 200, "total_steps": 225, "loss": 0.0035, "lr": 3.0153689607045845e-06, "epoch": 0.8888888888888888, "percentage": 88.89, "elapsed_time": "0:28:34", "remaining_time": "0:03:34"}
+{"current_steps": 210, "total_steps": 225, "loss": 0.0035, "lr": 1.0926199633097157e-06, "epoch": 0.9333333333333333, "percentage": 93.33, "elapsed_time": "0:29:43", "remaining_time": "0:02:07"}
+{"current_steps": 210, "total_steps": 225, "eval_loss": 0.003532670671120286, "epoch": 0.9333333333333333, "percentage": 93.33, "elapsed_time": "0:30:37", "remaining_time": "0:02:11"}
+{"current_steps": 220, "total_steps": 225, "loss": 0.0035, "lr": 1.2179748700879012e-07, "epoch": 0.9777777777777777, "percentage": 97.78, "elapsed_time": "0:31:46", "remaining_time": "0:00:43"}
+{"current_steps": 225, "total_steps": 225, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "0:32:22", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,252 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 30,
+  "global_step": 225,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.044444444444444446,
+      "grad_norm": 0.2802587151527405,
+      "learning_rate": 9.951340343707852e-05,
+      "loss": 0.3045,
+      "step": 10
+    },
+    {
+      "epoch": 0.08888888888888889,
+      "grad_norm": 0.021381886675953865,
+      "learning_rate": 9.806308479691595e-05,
+      "loss": 0.0054,
+      "step": 20
+    },
+    {
+      "epoch": 0.13333333333333333,
+      "grad_norm": 0.017750784754753113,
+      "learning_rate": 9.567727288213005e-05,
+      "loss": 0.0039,
+      "step": 30
+    },
+    {
+      "epoch": 0.13333333333333333,
+      "eval_loss": 0.0036237684544175863,
+      "eval_runtime": 53.377,
+      "eval_samples_per_second": 18.735,
+      "eval_steps_per_second": 0.468,
+      "step": 30
+    },
+    {
+      "epoch": 0.17777777777777778,
+      "grad_norm": 0.009207488968968391,
+      "learning_rate": 9.24024048078213e-05,
+      "loss": 0.0036,
+      "step": 40
+    },
+    {
+      "epoch": 0.2222222222222222,
+      "grad_norm": 0.03058847412467003,
+      "learning_rate": 8.83022221559489e-05,
+      "loss": 0.0037,
+      "step": 50
+    },
+    {
+      "epoch": 0.26666666666666666,
+      "grad_norm": 0.023914409801363945,
+      "learning_rate": 8.345653031794292e-05,
+      "loss": 0.0038,
+      "step": 60
+    },
+    {
+      "epoch": 0.26666666666666666,
+      "eval_loss": 0.0036710596177726984,
+      "eval_runtime": 53.396,
+      "eval_samples_per_second": 18.728,
+      "eval_steps_per_second": 0.468,
+      "step": 60
+    },
+    {
+      "epoch": 0.3111111111111111,
+      "grad_norm": 0.0324842669069767,
+      "learning_rate": 7.795964517353735e-05,
+      "loss": 0.0036,
+      "step": 70
+    },
+    {
+      "epoch": 0.35555555555555557,
+      "grad_norm": 0.002750804414972663,
+      "learning_rate": 7.191855733945387e-05,
+      "loss": 0.0036,
+      "step": 80
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.0023576547391712666,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 0.0036,
+      "step": 90
+    },
+    {
+      "epoch": 0.4,
+      "eval_loss": 0.003560666460543871,
+      "eval_runtime": 53.4786,
+      "eval_samples_per_second": 18.699,
+      "eval_steps_per_second": 0.467,
+      "step": 90
+    },
+    {
+      "epoch": 0.4444444444444444,
+      "grad_norm": 0.016149163246154785,
+      "learning_rate": 5.868240888334653e-05,
+      "loss": 0.0036,
+      "step": 100
+    },
+    {
+      "epoch": 0.4888888888888889,
+      "grad_norm": 0.0039548748172819614,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 0.0035,
+      "step": 110
+    },
+    {
+      "epoch": 0.5333333333333333,
+      "grad_norm": 0.0059623029083013535,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 0.0036,
+      "step": 120
+    },
+    {
+      "epoch": 0.5333333333333333,
+      "eval_loss": 0.00353414099663496,
+      "eval_runtime": 53.3696,
+      "eval_samples_per_second": 18.737,
+      "eval_steps_per_second": 0.468,
+      "step": 120
+    },
+    {
+      "epoch": 0.5777777777777777,
+      "grad_norm": 0.01755256950855255,
+      "learning_rate": 3.790390522001662e-05,
+      "loss": 0.0035,
+      "step": 130
+    },
+    {
+      "epoch": 0.6222222222222222,
+      "grad_norm": 0.005563901271671057,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 0.0035,
+      "step": 140
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 0.004853326827287674,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.0036,
+      "step": 150
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "eval_loss": 0.0035362462513148785,
+      "eval_runtime": 53.3856,
+      "eval_samples_per_second": 18.732,
+      "eval_steps_per_second": 0.468,
+      "step": 150
+    },
+    {
+      "epoch": 0.7111111111111111,
+      "grad_norm": 0.0062214070931077,
+      "learning_rate": 1.9216926233717085e-05,
+      "loss": 0.0036,
+      "step": 160
+    },
+    {
+      "epoch": 0.7555555555555555,
+      "grad_norm": 0.0025808655191212893,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 0.0035,
+      "step": 170
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.00887165404856205,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.0035,
+      "step": 180
+    },
+    {
+      "epoch": 0.8,
+      "eval_loss": 0.0035414749290794134,
+      "eval_runtime": 53.35,
+      "eval_samples_per_second": 18.744,
+      "eval_steps_per_second": 0.469,
+      "step": 180
+    },
+    {
+      "epoch": 0.8444444444444444,
+      "grad_norm": 0.005598729941993952,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 0.0035,
+      "step": 190
+    },
+    {
+      "epoch": 0.8888888888888888,
+      "grad_norm": 0.010787834413349628,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 0.0035,
+      "step": 200
+    },
+    {
+      "epoch": 0.9333333333333333,
+      "grad_norm": 0.00533076049759984,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 0.0035,
+      "step": 210
+    },
+    {
+      "epoch": 0.9333333333333333,
+      "eval_loss": 0.003532670671120286,
+      "eval_runtime": 53.3444,
+      "eval_samples_per_second": 18.746,
+      "eval_steps_per_second": 0.469,
+      "step": 210
+    },
+    {
+      "epoch": 0.9777777777777777,
+      "grad_norm": 0.006618449930101633,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 0.0035,
+      "step": 220
+    },
+    {
+      "epoch": 1.0,
+      "step": 225,
+      "total_flos": 7.559164517091901e+17,
+      "train_loss": 0.017044952660799025,
+      "train_runtime": 1944.9953,
+      "train_samples_per_second": 4.627,
+      "train_steps_per_second": 0.116
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 225,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 2000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 7.559164517091901e+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 sha256:1953d1ec3706f1ae90fd4a711244fa77dd5bcf8c5e0658c6dee454a0e6cc3097
+size 5432