Model save
Browse files- README.md +71 -0
- all_results.json +9 -0
- train_results.json +9 -0
- trainer_state.json +376 -0
README.md
ADDED
|
@@ -0,0 +1,71 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: LLM-PBE/Llama3.1-8b-instruct-LLMPC-Red-Team
|
| 3 |
+
library_name: peft
|
| 4 |
+
license: llama3.1
|
| 5 |
+
tags:
|
| 6 |
+
- trl
|
| 7 |
+
- sft
|
| 8 |
+
- generated_from_trainer
|
| 9 |
+
model-index:
|
| 10 |
+
- name: zephyr-7b-sft-qlora
|
| 11 |
+
results: []
|
| 12 |
+
---
|
| 13 |
+
|
| 14 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 15 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 16 |
+
|
| 17 |
+
# zephyr-7b-sft-qlora
|
| 18 |
+
|
| 19 |
+
This model is a fine-tuned version of [LLM-PBE/Llama3.1-8b-instruct-LLMPC-Red-Team](https://huggingface.co/LLM-PBE/Llama3.1-8b-instruct-LLMPC-Red-Team) on the None dataset.
|
| 20 |
+
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 0.2536
|
| 22 |
+
|
| 23 |
+
## Model description
|
| 24 |
+
|
| 25 |
+
More information needed
|
| 26 |
+
|
| 27 |
+
## Intended uses & limitations
|
| 28 |
+
|
| 29 |
+
More information needed
|
| 30 |
+
|
| 31 |
+
## Training and evaluation data
|
| 32 |
+
|
| 33 |
+
More information needed
|
| 34 |
+
|
| 35 |
+
## Training procedure
|
| 36 |
+
|
| 37 |
+
### Training hyperparameters
|
| 38 |
+
|
| 39 |
+
The following hyperparameters were used during training:
|
| 40 |
+
- learning_rate: 5e-05
|
| 41 |
+
- train_batch_size: 4
|
| 42 |
+
- eval_batch_size: 8
|
| 43 |
+
- seed: 42
|
| 44 |
+
- distributed_type: multi-GPU
|
| 45 |
+
- num_devices: 4
|
| 46 |
+
- gradient_accumulation_steps: 2
|
| 47 |
+
- total_train_batch_size: 32
|
| 48 |
+
- total_eval_batch_size: 32
|
| 49 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 50 |
+
- lr_scheduler_type: cosine
|
| 51 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 52 |
+
- num_epochs: 5.0
|
| 53 |
+
|
| 54 |
+
### Training results
|
| 55 |
+
|
| 56 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 57 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
| 58 |
+
| 0.3835 | 1.0 | 41 | 0.3792 |
|
| 59 |
+
| 0.3431 | 2.0 | 82 | 0.3488 |
|
| 60 |
+
| 0.2489 | 3.0 | 123 | 0.2568 |
|
| 61 |
+
| 0.2468 | 4.0 | 164 | 0.2538 |
|
| 62 |
+
| 0.2454 | 5.0 | 205 | 0.2536 |
|
| 63 |
+
|
| 64 |
+
|
| 65 |
+
### Framework versions
|
| 66 |
+
|
| 67 |
+
- PEFT 0.10.0
|
| 68 |
+
- Transformers 4.45.2
|
| 69 |
+
- Pytorch 2.4.0+cu121
|
| 70 |
+
- Datasets 3.0.0
|
| 71 |
+
- Tokenizers 0.20.0
|
all_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 5.0,
|
| 3 |
+
"total_flos": 7.472149011177144e+17,
|
| 4 |
+
"train_loss": 0.12734018942204917,
|
| 5 |
+
"train_runtime": 865.1722,
|
| 6 |
+
"train_samples": 1305,
|
| 7 |
+
"train_samples_per_second": 7.542,
|
| 8 |
+
"train_steps_per_second": 0.237
|
| 9 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 5.0,
|
| 3 |
+
"total_flos": 7.472149011177144e+17,
|
| 4 |
+
"train_loss": 0.12734018942204917,
|
| 5 |
+
"train_runtime": 865.1722,
|
| 6 |
+
"train_samples": 1305,
|
| 7 |
+
"train_samples_per_second": 7.542,
|
| 8 |
+
"train_steps_per_second": 0.237
|
| 9 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,376 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 5.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 205,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.024390243902439025,
|
| 13 |
+
"grad_norm": 0.2731004059314728,
|
| 14 |
+
"learning_rate": 2.3809523809523808e-06,
|
| 15 |
+
"loss": 0.6255,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.12195121951219512,
|
| 20 |
+
"grad_norm": 0.27167728543281555,
|
| 21 |
+
"learning_rate": 1.1904761904761905e-05,
|
| 22 |
+
"loss": 0.6283,
|
| 23 |
+
"step": 5
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.24390243902439024,
|
| 27 |
+
"grad_norm": 0.24203768372535706,
|
| 28 |
+
"learning_rate": 2.380952380952381e-05,
|
| 29 |
+
"loss": 0.6021,
|
| 30 |
+
"step": 10
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.36585365853658536,
|
| 34 |
+
"grad_norm": 0.1512613147497177,
|
| 35 |
+
"learning_rate": 3.571428571428572e-05,
|
| 36 |
+
"loss": 0.5736,
|
| 37 |
+
"step": 15
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.4878048780487805,
|
| 41 |
+
"grad_norm": 0.13210485875606537,
|
| 42 |
+
"learning_rate": 4.761904761904762e-05,
|
| 43 |
+
"loss": 0.5307,
|
| 44 |
+
"step": 20
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.6097560975609756,
|
| 48 |
+
"grad_norm": 0.11809483170509338,
|
| 49 |
+
"learning_rate": 4.994171922976348e-05,
|
| 50 |
+
"loss": 0.4787,
|
| 51 |
+
"step": 25
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.7317073170731707,
|
| 55 |
+
"grad_norm": 0.1285855919122696,
|
| 56 |
+
"learning_rate": 4.9705419236058825e-05,
|
| 57 |
+
"loss": 0.4354,
|
| 58 |
+
"step": 30
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.8536585365853658,
|
| 62 |
+
"grad_norm": 0.10194303095340729,
|
| 63 |
+
"learning_rate": 4.9289177234948535e-05,
|
| 64 |
+
"loss": 0.4031,
|
| 65 |
+
"step": 35
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.975609756097561,
|
| 69 |
+
"grad_norm": 0.0670081079006195,
|
| 70 |
+
"learning_rate": 4.8696024926503396e-05,
|
| 71 |
+
"loss": 0.3835,
|
| 72 |
+
"step": 40
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 1.0,
|
| 76 |
+
"eval_loss": 0.37915876507759094,
|
| 77 |
+
"eval_runtime": 7.8362,
|
| 78 |
+
"eval_samples_per_second": 18.631,
|
| 79 |
+
"eval_steps_per_second": 0.638,
|
| 80 |
+
"step": 41
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 1.0975609756097562,
|
| 84 |
+
"grad_norm": 0.07868604362010956,
|
| 85 |
+
"learning_rate": 4.793028253763633e-05,
|
| 86 |
+
"loss": 0.367,
|
| 87 |
+
"step": 45
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 1.2195121951219512,
|
| 91 |
+
"grad_norm": 0.08379828184843063,
|
| 92 |
+
"learning_rate": 4.69975273557146e-05,
|
| 93 |
+
"loss": 0.3689,
|
| 94 |
+
"step": 50
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 1.3414634146341464,
|
| 98 |
+
"grad_norm": 0.089637391269207,
|
| 99 |
+
"learning_rate": 4.5904553106367774e-05,
|
| 100 |
+
"loss": 0.3695,
|
| 101 |
+
"step": 55
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 1.4634146341463414,
|
| 105 |
+
"grad_norm": 0.08855098485946655,
|
| 106 |
+
"learning_rate": 4.4659320471363314e-05,
|
| 107 |
+
"loss": 0.3615,
|
| 108 |
+
"step": 60
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 1.5853658536585367,
|
| 112 |
+
"grad_norm": 0.09250541776418686,
|
| 113 |
+
"learning_rate": 4.3270899106953105e-05,
|
| 114 |
+
"loss": 0.3584,
|
| 115 |
+
"step": 65
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 1.7073170731707317,
|
| 119 |
+
"grad_norm": 0.08777391910552979,
|
| 120 |
+
"learning_rate": 4.174940158500041e-05,
|
| 121 |
+
"loss": 0.3443,
|
| 122 |
+
"step": 70
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 1.8292682926829267,
|
| 126 |
+
"grad_norm": 0.08619946986436844,
|
| 127 |
+
"learning_rate": 4.0105909738027365e-05,
|
| 128 |
+
"loss": 0.3491,
|
| 129 |
+
"step": 75
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 1.951219512195122,
|
| 133 |
+
"grad_norm": 0.09870754927396774,
|
| 134 |
+
"learning_rate": 3.835239394464901e-05,
|
| 135 |
+
"loss": 0.3431,
|
| 136 |
+
"step": 80
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 2.0,
|
| 140 |
+
"eval_loss": 0.3487952947616577,
|
| 141 |
+
"eval_runtime": 7.7885,
|
| 142 |
+
"eval_samples_per_second": 18.746,
|
| 143 |
+
"eval_steps_per_second": 0.642,
|
| 144 |
+
"step": 82
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 2.073170731707317,
|
| 148 |
+
"grad_norm": 0.08834455162286758,
|
| 149 |
+
"learning_rate": 3.6501625943278805e-05,
|
| 150 |
+
"loss": 0.3355,
|
| 151 |
+
"step": 85
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 2.1951219512195124,
|
| 155 |
+
"grad_norm": 0.07206975668668747,
|
| 156 |
+
"learning_rate": 3.456708580912725e-05,
|
| 157 |
+
"loss": 0.3394,
|
| 158 |
+
"step": 90
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 2.317073170731707,
|
| 162 |
+
"grad_norm": 0.05374612286686897,
|
| 163 |
+
"learning_rate": 3.25628637720269e-05,
|
| 164 |
+
"loss": 0.3462,
|
| 165 |
+
"step": 95
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 2.4390243902439024,
|
| 169 |
+
"grad_norm": 0.050639085471630096,
|
| 170 |
+
"learning_rate": 3.0503557590194143e-05,
|
| 171 |
+
"loss": 0.3246,
|
| 172 |
+
"step": 100
|
| 173 |
+
},
|
| 174 |
+
{
|
| 175 |
+
"epoch": 2.5609756097560976,
|
| 176 |
+
"grad_norm": 0.06731884926557541,
|
| 177 |
+
"learning_rate": 2.840416622740617e-05,
|
| 178 |
+
"loss": 0.2627,
|
| 179 |
+
"step": 105
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 2.682926829268293,
|
| 183 |
+
"grad_norm": 0.047202687710523605,
|
| 184 |
+
"learning_rate": 2.6279980607995836e-05,
|
| 185 |
+
"loss": 0.268,
|
| 186 |
+
"step": 110
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 2.8048780487804876,
|
| 190 |
+
"grad_norm": 0.045556213706731796,
|
| 191 |
+
"learning_rate": 2.4146472245350805e-05,
|
| 192 |
+
"loss": 0.2513,
|
| 193 |
+
"step": 115
|
| 194 |
+
},
|
| 195 |
+
{
|
| 196 |
+
"epoch": 2.926829268292683,
|
| 197 |
+
"grad_norm": 0.043327976018190384,
|
| 198 |
+
"learning_rate": 2.201918055509173e-05,
|
| 199 |
+
"loss": 0.2489,
|
| 200 |
+
"step": 120
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 3.0,
|
| 204 |
+
"eval_loss": 0.2567618787288666,
|
| 205 |
+
"eval_runtime": 13.2824,
|
| 206 |
+
"eval_samples_per_second": 10.992,
|
| 207 |
+
"eval_steps_per_second": 0.376,
|
| 208 |
+
"step": 123
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 3.048780487804878,
|
| 212 |
+
"grad_norm": 0.045429013669490814,
|
| 213 |
+
"learning_rate": 1.991359967368416e-05,
|
| 214 |
+
"loss": 0.2556,
|
| 215 |
+
"step": 125
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 3.1707317073170733,
|
| 219 |
+
"grad_norm": 0.03991298750042915,
|
| 220 |
+
"learning_rate": 1.7845065606841472e-05,
|
| 221 |
+
"loss": 0.2418,
|
| 222 |
+
"step": 130
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"epoch": 3.292682926829268,
|
| 226 |
+
"grad_norm": 0.04288507252931595,
|
| 227 |
+
"learning_rate": 1.582864452967359e-05,
|
| 228 |
+
"loss": 0.2455,
|
| 229 |
+
"step": 135
|
| 230 |
+
},
|
| 231 |
+
{
|
| 232 |
+
"epoch": 3.4146341463414633,
|
| 233 |
+
"grad_norm": 0.04243966192007065,
|
| 234 |
+
"learning_rate": 1.3879023052147899e-05,
|
| 235 |
+
"loss": 0.2494,
|
| 236 |
+
"step": 140
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 3.5365853658536586,
|
| 240 |
+
"grad_norm": 0.041205402463674545,
|
| 241 |
+
"learning_rate": 1.2010401249114167e-05,
|
| 242 |
+
"loss": 0.241,
|
| 243 |
+
"step": 145
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 3.658536585365854,
|
| 247 |
+
"grad_norm": 0.04464095085859299,
|
| 248 |
+
"learning_rate": 1.0236389234009727e-05,
|
| 249 |
+
"loss": 0.2512,
|
| 250 |
+
"step": 150
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"epoch": 3.7804878048780486,
|
| 254 |
+
"grad_norm": 0.04085472226142883,
|
| 255 |
+
"learning_rate": 8.569908029550685e-06,
|
| 256 |
+
"loss": 0.2461,
|
| 257 |
+
"step": 155
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 3.902439024390244,
|
| 261 |
+
"grad_norm": 0.041141241788864136,
|
| 262 |
+
"learning_rate": 7.02309545741773e-06,
|
| 263 |
+
"loss": 0.2468,
|
| 264 |
+
"step": 160
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 4.0,
|
| 268 |
+
"eval_loss": 0.2538050413131714,
|
| 269 |
+
"eval_runtime": 11.622,
|
| 270 |
+
"eval_samples_per_second": 12.562,
|
| 271 |
+
"eval_steps_per_second": 0.43,
|
| 272 |
+
"step": 164
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 4.024390243902439,
|
| 276 |
+
"grad_norm": 0.042266517877578735,
|
| 277 |
+
"learning_rate": 5.607217732389503e-06,
|
| 278 |
+
"loss": 0.2496,
|
| 279 |
+
"step": 165
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 4.146341463414634,
|
| 283 |
+
"grad_norm": 0.039677053689956665,
|
| 284 |
+
"learning_rate": 4.332587404827854e-06,
|
| 285 |
+
"loss": 0.2429,
|
| 286 |
+
"step": 170
|
| 287 |
+
},
|
| 288 |
+
{
|
| 289 |
+
"epoch": 4.2682926829268295,
|
| 290 |
+
"grad_norm": 0.0383627712726593,
|
| 291 |
+
"learning_rate": 3.208488249181216e-06,
|
| 292 |
+
"loss": 0.2452,
|
| 293 |
+
"step": 175
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 4.390243902439025,
|
| 297 |
+
"grad_norm": 0.039468664675951004,
|
| 298 |
+
"learning_rate": 2.2431076455809467e-06,
|
| 299 |
+
"loss": 0.2438,
|
| 300 |
+
"step": 180
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 4.512195121951219,
|
| 304 |
+
"grad_norm": 0.0408608578145504,
|
| 305 |
+
"learning_rate": 1.44347694702949e-06,
|
| 306 |
+
"loss": 0.2451,
|
| 307 |
+
"step": 185
|
| 308 |
+
},
|
| 309 |
+
{
|
| 310 |
+
"epoch": 4.634146341463414,
|
| 311 |
+
"grad_norm": 0.03901852294802666,
|
| 312 |
+
"learning_rate": 8.154202665162147e-07,
|
| 313 |
+
"loss": 0.2531,
|
| 314 |
+
"step": 190
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 4.7560975609756095,
|
| 318 |
+
"grad_norm": 0.039755210280418396,
|
| 319 |
+
"learning_rate": 3.635120570700784e-07,
|
| 320 |
+
"loss": 0.243,
|
| 321 |
+
"step": 195
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 4.878048780487805,
|
| 325 |
+
"grad_norm": 0.04330005869269371,
|
| 326 |
+
"learning_rate": 9.104379371500105e-08,
|
| 327 |
+
"loss": 0.2447,
|
| 328 |
+
"step": 200
|
| 329 |
+
},
|
| 330 |
+
{
|
| 331 |
+
"epoch": 5.0,
|
| 332 |
+
"grad_norm": 0.04034363478422165,
|
| 333 |
+
"learning_rate": 0.0,
|
| 334 |
+
"loss": 0.2454,
|
| 335 |
+
"step": 205
|
| 336 |
+
},
|
| 337 |
+
{
|
| 338 |
+
"epoch": 5.0,
|
| 339 |
+
"eval_loss": 0.2536194324493408,
|
| 340 |
+
"eval_runtime": 11.5668,
|
| 341 |
+
"eval_samples_per_second": 12.622,
|
| 342 |
+
"eval_steps_per_second": 0.432,
|
| 343 |
+
"step": 205
|
| 344 |
+
},
|
| 345 |
+
{
|
| 346 |
+
"epoch": 5.0,
|
| 347 |
+
"step": 205,
|
| 348 |
+
"total_flos": 7.472149011177144e+17,
|
| 349 |
+
"train_loss": 0.12734018942204917,
|
| 350 |
+
"train_runtime": 865.1722,
|
| 351 |
+
"train_samples_per_second": 7.542,
|
| 352 |
+
"train_steps_per_second": 0.237
|
| 353 |
+
}
|
| 354 |
+
],
|
| 355 |
+
"logging_steps": 5,
|
| 356 |
+
"max_steps": 205,
|
| 357 |
+
"num_input_tokens_seen": 0,
|
| 358 |
+
"num_train_epochs": 5,
|
| 359 |
+
"save_steps": 100,
|
| 360 |
+
"stateful_callbacks": {
|
| 361 |
+
"TrainerControl": {
|
| 362 |
+
"args": {
|
| 363 |
+
"should_epoch_stop": false,
|
| 364 |
+
"should_evaluate": false,
|
| 365 |
+
"should_log": false,
|
| 366 |
+
"should_save": true,
|
| 367 |
+
"should_training_stop": true
|
| 368 |
+
},
|
| 369 |
+
"attributes": {}
|
| 370 |
+
}
|
| 371 |
+
},
|
| 372 |
+
"total_flos": 7.472149011177144e+17,
|
| 373 |
+
"train_batch_size": 4,
|
| 374 |
+
"trial_name": null,
|
| 375 |
+
"trial_params": null
|
| 376 |
+
}
|