Model save
Browse files- README.md +75 -0
- all_results.json +9 -0
- train_results.json +9 -0
- trainer_state.json +396 -0
README.md
ADDED
|
@@ -0,0 +1,75 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
license: mit
|
| 4 |
+
base_model: jhu-clsp/mmBERT-small
|
| 5 |
+
tags:
|
| 6 |
+
- generated_from_trainer
|
| 7 |
+
metrics:
|
| 8 |
+
- accuracy
|
| 9 |
+
- precision
|
| 10 |
+
- recall
|
| 11 |
+
- f1
|
| 12 |
+
model-index:
|
| 13 |
+
- name: router-mmBERT-small-text-only-v3
|
| 14 |
+
results: []
|
| 15 |
+
---
|
| 16 |
+
|
| 17 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 18 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 19 |
+
|
| 20 |
+
# router-mmBERT-small-text-only-v3
|
| 21 |
+
|
| 22 |
+
This model is a fine-tuned version of [jhu-clsp/mmBERT-small](https://huggingface.co/jhu-clsp/mmBERT-small) on an unknown dataset.
|
| 23 |
+
It achieves the following results on the evaluation set:
|
| 24 |
+
- Loss: 0.5264
|
| 25 |
+
- Accuracy: 0.7443
|
| 26 |
+
- Precision: 0.7422
|
| 27 |
+
- Recall: 0.7443
|
| 28 |
+
- F1: 0.7282
|
| 29 |
+
|
| 30 |
+
## Model description
|
| 31 |
+
|
| 32 |
+
More information needed
|
| 33 |
+
|
| 34 |
+
## Intended uses & limitations
|
| 35 |
+
|
| 36 |
+
More information needed
|
| 37 |
+
|
| 38 |
+
## Training and evaluation data
|
| 39 |
+
|
| 40 |
+
More information needed
|
| 41 |
+
|
| 42 |
+
## Training procedure
|
| 43 |
+
|
| 44 |
+
### Training hyperparameters
|
| 45 |
+
|
| 46 |
+
The following hyperparameters were used during training:
|
| 47 |
+
- learning_rate: 0.0001
|
| 48 |
+
- train_batch_size: 16
|
| 49 |
+
- eval_batch_size: 32
|
| 50 |
+
- seed: 42
|
| 51 |
+
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 52 |
+
- lr_scheduler_type: cosine
|
| 53 |
+
- num_epochs: 2
|
| 54 |
+
|
| 55 |
+
### Training results
|
| 56 |
+
|
| 57 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
|
| 58 |
+
|:-------------:|:------:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
|
| 59 |
+
| No log | 0 | 0 | 1.5114 | 0.4432 | 0.4804 | 0.4432 | 0.4537 |
|
| 60 |
+
| 0.7931 | 0.2273 | 20 | 0.9312 | 0.6648 | 0.6848 | 0.6648 | 0.5784 |
|
| 61 |
+
| 0.7752 | 0.4545 | 40 | 0.9223 | 0.4886 | 0.7377 | 0.4886 | 0.4320 |
|
| 62 |
+
| 0.5251 | 0.6818 | 60 | 0.5346 | 0.6989 | 0.6940 | 0.6989 | 0.6659 |
|
| 63 |
+
| 0.5975 | 0.9091 | 80 | 0.5975 | 0.6534 | 0.7276 | 0.6534 | 0.6573 |
|
| 64 |
+
| 0.551 | 1.1364 | 100 | 0.5680 | 0.7273 | 0.7225 | 0.7273 | 0.7090 |
|
| 65 |
+
| 0.5093 | 1.3636 | 120 | 0.5872 | 0.7045 | 0.6952 | 0.7045 | 0.6951 |
|
| 66 |
+
| 0.5315 | 1.5909 | 140 | 0.5398 | 0.75 | 0.7593 | 0.75 | 0.7265 |
|
| 67 |
+
| 0.5231 | 1.8182 | 160 | 0.5264 | 0.7443 | 0.7422 | 0.7443 | 0.7282 |
|
| 68 |
+
|
| 69 |
+
|
| 70 |
+
### Framework versions
|
| 71 |
+
|
| 72 |
+
- Transformers 4.57.1
|
| 73 |
+
- Pytorch 2.8.0+cu128
|
| 74 |
+
- Datasets 4.2.0
|
| 75 |
+
- Tokenizers 0.22.1
|
all_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.0,
|
| 3 |
+
"total_flos": 315928015988940.0,
|
| 4 |
+
"train_loss": 0.7388186820528724,
|
| 5 |
+
"train_runtime": 87.4213,
|
| 6 |
+
"train_samples": 1407,
|
| 7 |
+
"train_samples_per_second": 32.189,
|
| 8 |
+
"train_steps_per_second": 2.013
|
| 9 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.0,
|
| 3 |
+
"total_flos": 315928015988940.0,
|
| 4 |
+
"train_loss": 0.7388186820528724,
|
| 5 |
+
"train_runtime": 87.4213,
|
| 6 |
+
"train_samples": 1407,
|
| 7 |
+
"train_samples_per_second": 32.189,
|
| 8 |
+
"train_steps_per_second": 2.013
|
| 9 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,396 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": 160,
|
| 3 |
+
"best_metric": 0.7282191492717808,
|
| 4 |
+
"best_model_checkpoint": "runs/router-mmBERT-small-text-only-v3/checkpoint-160",
|
| 5 |
+
"epoch": 2.0,
|
| 6 |
+
"eval_steps": 20,
|
| 7 |
+
"global_step": 176,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0,
|
| 14 |
+
"eval_accuracy": 0.4431818181818182,
|
| 15 |
+
"eval_f1": 0.45373205741626793,
|
| 16 |
+
"eval_loss": 1.5113513469696045,
|
| 17 |
+
"eval_precision": 0.48037190082644626,
|
| 18 |
+
"eval_recall": 0.4431818181818182,
|
| 19 |
+
"eval_runtime": 4.7496,
|
| 20 |
+
"eval_samples_per_second": 37.056,
|
| 21 |
+
"eval_steps_per_second": 1.263,
|
| 22 |
+
"step": 0
|
| 23 |
+
},
|
| 24 |
+
{
|
| 25 |
+
"epoch": 0.056818181818181816,
|
| 26 |
+
"grad_norm": 12.686948776245117,
|
| 27 |
+
"learning_rate": 9.987260573051269e-05,
|
| 28 |
+
"loss": 3.2334,
|
| 29 |
+
"step": 5
|
| 30 |
+
},
|
| 31 |
+
{
|
| 32 |
+
"epoch": 0.11363636363636363,
|
| 33 |
+
"grad_norm": 104.65008544921875,
|
| 34 |
+
"learning_rate": 9.935617890443557e-05,
|
| 35 |
+
"loss": 2.5264,
|
| 36 |
+
"step": 10
|
| 37 |
+
},
|
| 38 |
+
{
|
| 39 |
+
"epoch": 0.17045454545454544,
|
| 40 |
+
"grad_norm": 77.57421112060547,
|
| 41 |
+
"learning_rate": 9.844686508907537e-05,
|
| 42 |
+
"loss": 0.9934,
|
| 43 |
+
"step": 15
|
| 44 |
+
},
|
| 45 |
+
{
|
| 46 |
+
"epoch": 0.22727272727272727,
|
| 47 |
+
"grad_norm": 25.431455612182617,
|
| 48 |
+
"learning_rate": 9.715190263989561e-05,
|
| 49 |
+
"loss": 0.7931,
|
| 50 |
+
"step": 20
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.22727272727272727,
|
| 54 |
+
"eval_accuracy": 0.6647727272727273,
|
| 55 |
+
"eval_f1": 0.5783962367355869,
|
| 56 |
+
"eval_loss": 0.9312057495117188,
|
| 57 |
+
"eval_precision": 0.6848484848484849,
|
| 58 |
+
"eval_recall": 0.6647727272727273,
|
| 59 |
+
"eval_runtime": 0.302,
|
| 60 |
+
"eval_samples_per_second": 582.771,
|
| 61 |
+
"eval_steps_per_second": 19.867,
|
| 62 |
+
"step": 20
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.2840909090909091,
|
| 66 |
+
"grad_norm": 59.058265686035156,
|
| 67 |
+
"learning_rate": 9.548159976772592e-05,
|
| 68 |
+
"loss": 0.9107,
|
| 69 |
+
"step": 25
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.3409090909090909,
|
| 73 |
+
"grad_norm": 47.96800231933594,
|
| 74 |
+
"learning_rate": 9.344925248293837e-05,
|
| 75 |
+
"loss": 0.708,
|
| 76 |
+
"step": 30
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"epoch": 0.3977272727272727,
|
| 80 |
+
"grad_norm": 23.16752815246582,
|
| 81 |
+
"learning_rate": 9.107103875602459e-05,
|
| 82 |
+
"loss": 0.5048,
|
| 83 |
+
"step": 35
|
| 84 |
+
},
|
| 85 |
+
{
|
| 86 |
+
"epoch": 0.45454545454545453,
|
| 87 |
+
"grad_norm": 66.16763305664062,
|
| 88 |
+
"learning_rate": 8.836588973708129e-05,
|
| 89 |
+
"loss": 0.7752,
|
| 90 |
+
"step": 40
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 0.45454545454545453,
|
| 94 |
+
"eval_accuracy": 0.48863636363636365,
|
| 95 |
+
"eval_f1": 0.43204905618558603,
|
| 96 |
+
"eval_loss": 0.9223223328590393,
|
| 97 |
+
"eval_precision": 0.7377156177156178,
|
| 98 |
+
"eval_recall": 0.48863636363636365,
|
| 99 |
+
"eval_runtime": 0.321,
|
| 100 |
+
"eval_samples_per_second": 548.336,
|
| 101 |
+
"eval_steps_per_second": 18.693,
|
| 102 |
+
"step": 40
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 0.5113636363636364,
|
| 106 |
+
"grad_norm": 9.133078575134277,
|
| 107 |
+
"learning_rate": 8.535533905932738e-05,
|
| 108 |
+
"loss": 0.6457,
|
| 109 |
+
"step": 45
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 0.5681818181818182,
|
| 113 |
+
"grad_norm": 6.507447719573975,
|
| 114 |
+
"learning_rate": 8.206335142623305e-05,
|
| 115 |
+
"loss": 0.8555,
|
| 116 |
+
"step": 50
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.625,
|
| 120 |
+
"grad_norm": 7.759437561035156,
|
| 121 |
+
"learning_rate": 7.85161318467482e-05,
|
| 122 |
+
"loss": 0.5602,
|
| 123 |
+
"step": 55
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.6818181818181818,
|
| 127 |
+
"grad_norm": 3.4017348289489746,
|
| 128 |
+
"learning_rate": 7.474191703716339e-05,
|
| 129 |
+
"loss": 0.5251,
|
| 130 |
+
"step": 60
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 0.6818181818181818,
|
| 134 |
+
"eval_accuracy": 0.6988636363636364,
|
| 135 |
+
"eval_f1": 0.6658946623722376,
|
| 136 |
+
"eval_loss": 0.5345972180366516,
|
| 137 |
+
"eval_precision": 0.6939832136717565,
|
| 138 |
+
"eval_recall": 0.6988636363636364,
|
| 139 |
+
"eval_runtime": 0.4317,
|
| 140 |
+
"eval_samples_per_second": 407.665,
|
| 141 |
+
"eval_steps_per_second": 13.898,
|
| 142 |
+
"step": 60
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.7386363636363636,
|
| 146 |
+
"grad_norm": 38.210453033447266,
|
| 147 |
+
"learning_rate": 7.077075065009433e-05,
|
| 148 |
+
"loss": 0.7065,
|
| 149 |
+
"step": 65
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.7954545454545454,
|
| 153 |
+
"grad_norm": 10.191884994506836,
|
| 154 |
+
"learning_rate": 6.663424411982121e-05,
|
| 155 |
+
"loss": 0.6372,
|
| 156 |
+
"step": 70
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.8522727272727273,
|
| 160 |
+
"grad_norm": 20.093486785888672,
|
| 161 |
+
"learning_rate": 6.236532502771078e-05,
|
| 162 |
+
"loss": 0.5907,
|
| 163 |
+
"step": 75
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.9090909090909091,
|
| 167 |
+
"grad_norm": 8.867379188537598,
|
| 168 |
+
"learning_rate": 5.799797499079301e-05,
|
| 169 |
+
"loss": 0.5975,
|
| 170 |
+
"step": 80
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.9090909090909091,
|
| 174 |
+
"eval_accuracy": 0.6534090909090909,
|
| 175 |
+
"eval_f1": 0.6573467315982285,
|
| 176 |
+
"eval_loss": 0.5975217223167419,
|
| 177 |
+
"eval_precision": 0.7275870824215018,
|
| 178 |
+
"eval_recall": 0.6534090909090909,
|
| 179 |
+
"eval_runtime": 0.3987,
|
| 180 |
+
"eval_samples_per_second": 441.426,
|
| 181 |
+
"eval_steps_per_second": 15.049,
|
| 182 |
+
"step": 80
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 0.9659090909090909,
|
| 186 |
+
"grad_norm": 10.983565330505371,
|
| 187 |
+
"learning_rate": 5.3566959159961615e-05,
|
| 188 |
+
"loss": 0.6915,
|
| 189 |
+
"step": 85
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 1.0227272727272727,
|
| 193 |
+
"grad_norm": 5.20986795425415,
|
| 194 |
+
"learning_rate": 4.9107549481057696e-05,
|
| 195 |
+
"loss": 0.5815,
|
| 196 |
+
"step": 90
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 1.0795454545454546,
|
| 200 |
+
"grad_norm": 4.2207183837890625,
|
| 201 |
+
"learning_rate": 4.4655243921744374e-05,
|
| 202 |
+
"loss": 0.4689,
|
| 203 |
+
"step": 95
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 1.1363636363636362,
|
| 207 |
+
"grad_norm": 17.133651733398438,
|
| 208 |
+
"learning_rate": 4.0245483899193595e-05,
|
| 209 |
+
"loss": 0.551,
|
| 210 |
+
"step": 100
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 1.1363636363636362,
|
| 214 |
+
"eval_accuracy": 0.7272727272727273,
|
| 215 |
+
"eval_f1": 0.7090006767426121,
|
| 216 |
+
"eval_loss": 0.5679962635040283,
|
| 217 |
+
"eval_precision": 0.7224598930481284,
|
| 218 |
+
"eval_recall": 0.7272727272727273,
|
| 219 |
+
"eval_runtime": 0.3507,
|
| 220 |
+
"eval_samples_per_second": 501.913,
|
| 221 |
+
"eval_steps_per_second": 17.111,
|
| 222 |
+
"step": 100
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"epoch": 1.1931818181818181,
|
| 226 |
+
"grad_norm": 6.083935737609863,
|
| 227 |
+
"learning_rate": 3.591337215792852e-05,
|
| 228 |
+
"loss": 0.5319,
|
| 229 |
+
"step": 105
|
| 230 |
+
},
|
| 231 |
+
{
|
| 232 |
+
"epoch": 1.25,
|
| 233 |
+
"grad_norm": 37.91518020629883,
|
| 234 |
+
"learning_rate": 3.1693393343581044e-05,
|
| 235 |
+
"loss": 0.571,
|
| 236 |
+
"step": 110
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 1.3068181818181819,
|
| 240 |
+
"grad_norm": 10.03105640411377,
|
| 241 |
+
"learning_rate": 2.7619139496864378e-05,
|
| 242 |
+
"loss": 0.5283,
|
| 243 |
+
"step": 115
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 1.3636363636363638,
|
| 247 |
+
"grad_norm": 3.3100969791412354,
|
| 248 |
+
"learning_rate": 2.3723042652894362e-05,
|
| 249 |
+
"loss": 0.5093,
|
| 250 |
+
"step": 120
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"epoch": 1.3636363636363638,
|
| 254 |
+
"eval_accuracy": 0.7045454545454546,
|
| 255 |
+
"eval_f1": 0.6950933483441223,
|
| 256 |
+
"eval_loss": 0.5871580243110657,
|
| 257 |
+
"eval_precision": 0.6951515151515152,
|
| 258 |
+
"eval_recall": 0.7045454545454546,
|
| 259 |
+
"eval_runtime": 0.3979,
|
| 260 |
+
"eval_samples_per_second": 442.333,
|
| 261 |
+
"eval_steps_per_second": 15.08,
|
| 262 |
+
"step": 120
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 1.4204545454545454,
|
| 266 |
+
"grad_norm": 16.1977596282959,
|
| 267 |
+
"learning_rate": 2.0036116674432654e-05,
|
| 268 |
+
"loss": 0.5697,
|
| 269 |
+
"step": 125
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 1.4772727272727273,
|
| 273 |
+
"grad_norm": 4.914312362670898,
|
| 274 |
+
"learning_rate": 1.6587710374121203e-05,
|
| 275 |
+
"loss": 0.4587,
|
| 276 |
+
"step": 130
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 1.5340909090909092,
|
| 280 |
+
"grad_norm": 6.9654645919799805,
|
| 281 |
+
"learning_rate": 1.340527389091374e-05,
|
| 282 |
+
"loss": 0.7103,
|
| 283 |
+
"step": 135
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 1.5909090909090908,
|
| 287 |
+
"grad_norm": 8.979105949401855,
|
| 288 |
+
"learning_rate": 1.0514140180404204e-05,
|
| 289 |
+
"loss": 0.5315,
|
| 290 |
+
"step": 140
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 1.5909090909090908,
|
| 294 |
+
"eval_accuracy": 0.75,
|
| 295 |
+
"eval_f1": 0.72649847340511,
|
| 296 |
+
"eval_loss": 0.5397942066192627,
|
| 297 |
+
"eval_precision": 0.7593206296603149,
|
| 298 |
+
"eval_recall": 0.75,
|
| 299 |
+
"eval_runtime": 0.3718,
|
| 300 |
+
"eval_samples_per_second": 473.373,
|
| 301 |
+
"eval_steps_per_second": 16.138,
|
| 302 |
+
"step": 140
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 1.6477272727272727,
|
| 306 |
+
"grad_norm": 31.318988800048828,
|
| 307 |
+
"learning_rate": 7.937323358440935e-06,
|
| 308 |
+
"loss": 0.5135,
|
| 309 |
+
"step": 145
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 1.7045454545454546,
|
| 313 |
+
"grad_norm": 2.2285165786743164,
|
| 314 |
+
"learning_rate": 5.69533550325988e-06,
|
| 315 |
+
"loss": 0.481,
|
| 316 |
+
"step": 150
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 1.7613636363636362,
|
| 320 |
+
"grad_norm": 16.231529235839844,
|
| 321 |
+
"learning_rate": 3.8060233744356633e-06,
|
| 322 |
+
"loss": 0.5126,
|
| 323 |
+
"step": 155
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"epoch": 1.8181818181818183,
|
| 327 |
+
"grad_norm": 31.868896484375,
|
| 328 |
+
"learning_rate": 2.2844263484068096e-06,
|
| 329 |
+
"loss": 0.5231,
|
| 330 |
+
"step": 160
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 1.8181818181818183,
|
| 334 |
+
"eval_accuracy": 0.7443181818181818,
|
| 335 |
+
"eval_f1": 0.7282191492717808,
|
| 336 |
+
"eval_loss": 0.5264365673065186,
|
| 337 |
+
"eval_precision": 0.7421696641208836,
|
| 338 |
+
"eval_recall": 0.7443181818181818,
|
| 339 |
+
"eval_runtime": 0.3604,
|
| 340 |
+
"eval_samples_per_second": 488.355,
|
| 341 |
+
"eval_steps_per_second": 16.648,
|
| 342 |
+
"step": 160
|
| 343 |
+
},
|
| 344 |
+
{
|
| 345 |
+
"epoch": 1.875,
|
| 346 |
+
"grad_norm": 26.505346298217773,
|
| 347 |
+
"learning_rate": 1.1426567014420297e-06,
|
| 348 |
+
"loss": 0.5943,
|
| 349 |
+
"step": 165
|
| 350 |
+
},
|
| 351 |
+
{
|
| 352 |
+
"epoch": 1.9318181818181817,
|
| 353 |
+
"grad_norm": 23.811979293823242,
|
| 354 |
+
"learning_rate": 3.8980319302407977e-07,
|
| 355 |
+
"loss": 0.5122,
|
| 356 |
+
"step": 170
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 1.9886363636363638,
|
| 360 |
+
"grad_norm": 7.987723350524902,
|
| 361 |
+
"learning_rate": 3.185871715041255e-08,
|
| 362 |
+
"loss": 0.5237,
|
| 363 |
+
"step": 175
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 2.0,
|
| 367 |
+
"step": 176,
|
| 368 |
+
"total_flos": 315928015988940.0,
|
| 369 |
+
"train_loss": 0.7388186820528724,
|
| 370 |
+
"train_runtime": 87.4213,
|
| 371 |
+
"train_samples_per_second": 32.189,
|
| 372 |
+
"train_steps_per_second": 2.013
|
| 373 |
+
}
|
| 374 |
+
],
|
| 375 |
+
"logging_steps": 5,
|
| 376 |
+
"max_steps": 176,
|
| 377 |
+
"num_input_tokens_seen": 0,
|
| 378 |
+
"num_train_epochs": 2,
|
| 379 |
+
"save_steps": 20,
|
| 380 |
+
"stateful_callbacks": {
|
| 381 |
+
"TrainerControl": {
|
| 382 |
+
"args": {
|
| 383 |
+
"should_epoch_stop": false,
|
| 384 |
+
"should_evaluate": false,
|
| 385 |
+
"should_log": false,
|
| 386 |
+
"should_save": true,
|
| 387 |
+
"should_training_stop": true
|
| 388 |
+
},
|
| 389 |
+
"attributes": {}
|
| 390 |
+
}
|
| 391 |
+
},
|
| 392 |
+
"total_flos": 315928015988940.0,
|
| 393 |
+
"train_batch_size": 16,
|
| 394 |
+
"trial_name": null,
|
| 395 |
+
"trial_params": null
|
| 396 |
+
}
|