Model save
Browse files- README.md +69 -0
- all_results.json +9 -0
- train_results.json +9 -0
- trainer_state.json +358 -0
README.md
ADDED
|
@@ -0,0 +1,69 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
license: apache-2.0
|
| 4 |
+
base_model: mistralai/Mistral-7B-v0.3
|
| 5 |
+
tags:
|
| 6 |
+
- trl
|
| 7 |
+
- sft
|
| 8 |
+
- generated_from_trainer
|
| 9 |
+
datasets:
|
| 10 |
+
- generator
|
| 11 |
+
model-index:
|
| 12 |
+
- name: mistral7b-pissa-coding-11-v1
|
| 13 |
+
results: []
|
| 14 |
+
---
|
| 15 |
+
|
| 16 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 17 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 18 |
+
|
| 19 |
+
# mistral7b-pissa-coding-11-v1
|
| 20 |
+
|
| 21 |
+
This model is a fine-tuned version of [mistralai/Mistral-7B-v0.3](https://huggingface.co/mistralai/Mistral-7B-v0.3) on the generator dataset.
|
| 22 |
+
It achieves the following results on the evaluation set:
|
| 23 |
+
- Loss: 1.3727
|
| 24 |
+
|
| 25 |
+
## Model description
|
| 26 |
+
|
| 27 |
+
More information needed
|
| 28 |
+
|
| 29 |
+
## Intended uses & limitations
|
| 30 |
+
|
| 31 |
+
More information needed
|
| 32 |
+
|
| 33 |
+
## Training and evaluation data
|
| 34 |
+
|
| 35 |
+
More information needed
|
| 36 |
+
|
| 37 |
+
## Training procedure
|
| 38 |
+
|
| 39 |
+
### Training hyperparameters
|
| 40 |
+
|
| 41 |
+
The following hyperparameters were used during training:
|
| 42 |
+
- learning_rate: 0.0002
|
| 43 |
+
- train_batch_size: 12
|
| 44 |
+
- eval_batch_size: 12
|
| 45 |
+
- seed: 42
|
| 46 |
+
- distributed_type: multi-GPU
|
| 47 |
+
- num_devices: 8
|
| 48 |
+
- gradient_accumulation_steps: 2
|
| 49 |
+
- total_train_batch_size: 192
|
| 50 |
+
- total_eval_batch_size: 96
|
| 51 |
+
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 52 |
+
- lr_scheduler_type: cosine
|
| 53 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 54 |
+
- num_epochs: 1
|
| 55 |
+
|
| 56 |
+
### Training results
|
| 57 |
+
|
| 58 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 59 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
| 60 |
+
| 0.8727 | 1.0 | 216 | 1.3727 |
|
| 61 |
+
|
| 62 |
+
|
| 63 |
+
### Framework versions
|
| 64 |
+
|
| 65 |
+
- PEFT 0.13.2
|
| 66 |
+
- Transformers 4.46.3
|
| 67 |
+
- Pytorch 2.3.1+cu121
|
| 68 |
+
- Datasets 3.1.0
|
| 69 |
+
- Tokenizers 0.20.3
|
all_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"total_flos": 9.06748200373715e+17,
|
| 4 |
+
"train_loss": 0.9395653671688504,
|
| 5 |
+
"train_runtime": 729.0361,
|
| 6 |
+
"train_samples": 116368,
|
| 7 |
+
"train_samples_per_second": 56.83,
|
| 8 |
+
"train_steps_per_second": 0.296
|
| 9 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"total_flos": 9.06748200373715e+17,
|
| 4 |
+
"train_loss": 0.9395653671688504,
|
| 5 |
+
"train_runtime": 729.0361,
|
| 6 |
+
"train_samples": 116368,
|
| 7 |
+
"train_samples_per_second": 56.83,
|
| 8 |
+
"train_steps_per_second": 0.296
|
| 9 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,358 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 216,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.004629629629629629,
|
| 13 |
+
"grad_norm": 4.558699607849121,
|
| 14 |
+
"learning_rate": 9.090909090909091e-06,
|
| 15 |
+
"loss": 1.4478,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.023148148148148147,
|
| 20 |
+
"grad_norm": 3.5731630325317383,
|
| 21 |
+
"learning_rate": 4.545454545454546e-05,
|
| 22 |
+
"loss": 1.4229,
|
| 23 |
+
"step": 5
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.046296296296296294,
|
| 27 |
+
"grad_norm": 2.504847288131714,
|
| 28 |
+
"learning_rate": 9.090909090909092e-05,
|
| 29 |
+
"loss": 1.346,
|
| 30 |
+
"step": 10
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.06944444444444445,
|
| 34 |
+
"grad_norm": 1.5195527076721191,
|
| 35 |
+
"learning_rate": 0.00013636363636363637,
|
| 36 |
+
"loss": 1.2411,
|
| 37 |
+
"step": 15
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.09259259259259259,
|
| 41 |
+
"grad_norm": 1.1458969116210938,
|
| 42 |
+
"learning_rate": 0.00018181818181818183,
|
| 43 |
+
"loss": 1.1481,
|
| 44 |
+
"step": 20
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.11574074074074074,
|
| 48 |
+
"grad_norm": 1.0300581455230713,
|
| 49 |
+
"learning_rate": 0.0001998820159279591,
|
| 50 |
+
"loss": 1.0637,
|
| 51 |
+
"step": 25
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.1388888888888889,
|
| 55 |
+
"grad_norm": 0.5588775873184204,
|
| 56 |
+
"learning_rate": 0.00019916201012264254,
|
| 57 |
+
"loss": 1.0107,
|
| 58 |
+
"step": 30
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.16203703703703703,
|
| 62 |
+
"grad_norm": 0.6917332410812378,
|
| 63 |
+
"learning_rate": 0.00019779225723955707,
|
| 64 |
+
"loss": 0.9795,
|
| 65 |
+
"step": 35
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.18518518518518517,
|
| 69 |
+
"grad_norm": 0.4281361997127533,
|
| 70 |
+
"learning_rate": 0.00019578173241879872,
|
| 71 |
+
"loss": 0.9527,
|
| 72 |
+
"step": 40
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.20833333333333334,
|
| 76 |
+
"grad_norm": 0.42266684770584106,
|
| 77 |
+
"learning_rate": 0.00019314360938108425,
|
| 78 |
+
"loss": 0.9431,
|
| 79 |
+
"step": 45
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.23148148148148148,
|
| 83 |
+
"grad_norm": 0.4428061246871948,
|
| 84 |
+
"learning_rate": 0.00018989517410853955,
|
| 85 |
+
"loss": 0.9236,
|
| 86 |
+
"step": 50
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.25462962962962965,
|
| 90 |
+
"grad_norm": 0.41992688179016113,
|
| 91 |
+
"learning_rate": 0.00018605771158039253,
|
| 92 |
+
"loss": 0.9225,
|
| 93 |
+
"step": 55
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.2777777777777778,
|
| 97 |
+
"grad_norm": 0.3743288815021515,
|
| 98 |
+
"learning_rate": 0.0001816563663057211,
|
| 99 |
+
"loss": 0.9176,
|
| 100 |
+
"step": 60
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.30092592592592593,
|
| 104 |
+
"grad_norm": 0.4716743528842926,
|
| 105 |
+
"learning_rate": 0.00017671997756709863,
|
| 106 |
+
"loss": 0.9112,
|
| 107 |
+
"step": 65
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.32407407407407407,
|
| 111 |
+
"grad_norm": 0.3897479176521301,
|
| 112 |
+
"learning_rate": 0.00017128089045468294,
|
| 113 |
+
"loss": 0.9079,
|
| 114 |
+
"step": 70
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.3472222222222222,
|
| 118 |
+
"grad_norm": 0.40086159110069275,
|
| 119 |
+
"learning_rate": 0.00016537474392892528,
|
| 120 |
+
"loss": 0.9065,
|
| 121 |
+
"step": 75
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.37037037037037035,
|
| 125 |
+
"grad_norm": 0.3658371865749359,
|
| 126 |
+
"learning_rate": 0.00015904023730059228,
|
| 127 |
+
"loss": 0.8987,
|
| 128 |
+
"step": 80
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.39351851851851855,
|
| 132 |
+
"grad_norm": 0.392740935087204,
|
| 133 |
+
"learning_rate": 0.000152318876658213,
|
| 134 |
+
"loss": 0.9045,
|
| 135 |
+
"step": 85
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.4166666666666667,
|
| 139 |
+
"grad_norm": 0.37253740429878235,
|
| 140 |
+
"learning_rate": 0.00014525470290445392,
|
| 141 |
+
"loss": 0.9038,
|
| 142 |
+
"step": 90
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.4398148148148148,
|
| 146 |
+
"grad_norm": 0.3818472623825073,
|
| 147 |
+
"learning_rate": 0.00013789400318343068,
|
| 148 |
+
"loss": 0.897,
|
| 149 |
+
"step": 95
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.46296296296296297,
|
| 153 |
+
"grad_norm": 1.4701107740402222,
|
| 154 |
+
"learning_rate": 0.00013028500758979506,
|
| 155 |
+
"loss": 0.8999,
|
| 156 |
+
"step": 100
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.4861111111111111,
|
| 160 |
+
"grad_norm": 0.3863574266433716,
|
| 161 |
+
"learning_rate": 0.00012247757314687297,
|
| 162 |
+
"loss": 0.8896,
|
| 163 |
+
"step": 105
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.5092592592592593,
|
| 167 |
+
"grad_norm": 0.3857921063899994,
|
| 168 |
+
"learning_rate": 0.00011452285712454904,
|
| 169 |
+
"loss": 0.8936,
|
| 170 |
+
"step": 110
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.5324074074074074,
|
| 174 |
+
"grad_norm": 0.4537260830402374,
|
| 175 |
+
"learning_rate": 0.00010647298183744359,
|
| 176 |
+
"loss": 0.8841,
|
| 177 |
+
"step": 115
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.5555555555555556,
|
| 181 |
+
"grad_norm": 0.41398969292640686,
|
| 182 |
+
"learning_rate": 9.838069311974986e-05,
|
| 183 |
+
"loss": 0.8853,
|
| 184 |
+
"step": 120
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.5787037037037037,
|
| 188 |
+
"grad_norm": 0.5760473608970642,
|
| 189 |
+
"learning_rate": 9.02990147145352e-05,
|
| 190 |
+
"loss": 0.8869,
|
| 191 |
+
"step": 125
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.6018518518518519,
|
| 195 |
+
"grad_norm": 0.3519139289855957,
|
| 196 |
+
"learning_rate": 8.228090084207774e-05,
|
| 197 |
+
"loss": 0.8862,
|
| 198 |
+
"step": 130
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.625,
|
| 202 |
+
"grad_norm": 0.3705141842365265,
|
| 203 |
+
"learning_rate": 7.437888922374276e-05,
|
| 204 |
+
"loss": 0.8942,
|
| 205 |
+
"step": 135
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.6481481481481481,
|
| 209 |
+
"grad_norm": 0.3546064794063568,
|
| 210 |
+
"learning_rate": 6.664475683491796e-05,
|
| 211 |
+
"loss": 0.8858,
|
| 212 |
+
"step": 140
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.6712962962962963,
|
| 216 |
+
"grad_norm": 0.4081316292285919,
|
| 217 |
+
"learning_rate": 5.9129180642644414e-05,
|
| 218 |
+
"loss": 0.8873,
|
| 219 |
+
"step": 145
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.6944444444444444,
|
| 223 |
+
"grad_norm": 0.3876301646232605,
|
| 224 |
+
"learning_rate": 5.1881405550919493e-05,
|
| 225 |
+
"loss": 0.8873,
|
| 226 |
+
"step": 150
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.7175925925925926,
|
| 230 |
+
"grad_norm": 0.37546050548553467,
|
| 231 |
+
"learning_rate": 4.494892172941965e-05,
|
| 232 |
+
"loss": 0.8877,
|
| 233 |
+
"step": 155
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.7407407407407407,
|
| 237 |
+
"grad_norm": 0.3889768123626709,
|
| 238 |
+
"learning_rate": 3.8377153439907266e-05,
|
| 239 |
+
"loss": 0.8835,
|
| 240 |
+
"step": 160
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.7638888888888888,
|
| 244 |
+
"grad_norm": 0.37897348403930664,
|
| 245 |
+
"learning_rate": 3.2209161399249674e-05,
|
| 246 |
+
"loss": 0.8714,
|
| 247 |
+
"step": 165
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.7870370370370371,
|
| 251 |
+
"grad_norm": 0.3686477839946747,
|
| 252 |
+
"learning_rate": 2.6485360629279987e-05,
|
| 253 |
+
"loss": 0.8789,
|
| 254 |
+
"step": 170
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.8101851851851852,
|
| 258 |
+
"grad_norm": 0.33174994587898254,
|
| 259 |
+
"learning_rate": 2.1243255642254578e-05,
|
| 260 |
+
"loss": 0.8797,
|
| 261 |
+
"step": 175
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.8333333333333334,
|
| 265 |
+
"grad_norm": 0.35853928327560425,
|
| 266 |
+
"learning_rate": 1.65171946970729e-05,
|
| 267 |
+
"loss": 0.8841,
|
| 268 |
+
"step": 180
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.8564814814814815,
|
| 272 |
+
"grad_norm": 0.3387424051761627,
|
| 273 |
+
"learning_rate": 1.233814473646524e-05,
|
| 274 |
+
"loss": 0.8852,
|
| 275 |
+
"step": 185
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.8796296296296297,
|
| 279 |
+
"grad_norm": 0.40066128969192505,
|
| 280 |
+
"learning_rate": 8.733488479845997e-06,
|
| 281 |
+
"loss": 0.8811,
|
| 282 |
+
"step": 190
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.9027777777777778,
|
| 286 |
+
"grad_norm": 0.341008722782135,
|
| 287 |
+
"learning_rate": 5.726845001356573e-06,
|
| 288 |
+
"loss": 0.8743,
|
| 289 |
+
"step": 195
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.9259259259259259,
|
| 293 |
+
"grad_norm": 0.3468351364135742,
|
| 294 |
+
"learning_rate": 3.3379149687388867e-06,
|
| 295 |
+
"loss": 0.8731,
|
| 296 |
+
"step": 200
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.9490740740740741,
|
| 300 |
+
"grad_norm": 0.37516307830810547,
|
| 301 |
+
"learning_rate": 1.5823515570925763e-06,
|
| 302 |
+
"loss": 0.8711,
|
| 303 |
+
"step": 205
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.9722222222222222,
|
| 307 |
+
"grad_norm": 0.34528055787086487,
|
| 308 |
+
"learning_rate": 4.7165788333860536e-07,
|
| 309 |
+
"loss": 0.8752,
|
| 310 |
+
"step": 210
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.9953703703703703,
|
| 314 |
+
"grad_norm": 0.35141706466674805,
|
| 315 |
+
"learning_rate": 1.3111633436779791e-08,
|
| 316 |
+
"loss": 0.8727,
|
| 317 |
+
"step": 215
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 1.0,
|
| 321 |
+
"eval_loss": 1.372731328010559,
|
| 322 |
+
"eval_runtime": 0.567,
|
| 323 |
+
"eval_samples_per_second": 19.4,
|
| 324 |
+
"eval_steps_per_second": 1.764,
|
| 325 |
+
"step": 216
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 1.0,
|
| 329 |
+
"step": 216,
|
| 330 |
+
"total_flos": 9.06748200373715e+17,
|
| 331 |
+
"train_loss": 0.9395653671688504,
|
| 332 |
+
"train_runtime": 729.0361,
|
| 333 |
+
"train_samples_per_second": 56.83,
|
| 334 |
+
"train_steps_per_second": 0.296
|
| 335 |
+
}
|
| 336 |
+
],
|
| 337 |
+
"logging_steps": 5,
|
| 338 |
+
"max_steps": 216,
|
| 339 |
+
"num_input_tokens_seen": 0,
|
| 340 |
+
"num_train_epochs": 1,
|
| 341 |
+
"save_steps": 100,
|
| 342 |
+
"stateful_callbacks": {
|
| 343 |
+
"TrainerControl": {
|
| 344 |
+
"args": {
|
| 345 |
+
"should_epoch_stop": false,
|
| 346 |
+
"should_evaluate": false,
|
| 347 |
+
"should_log": false,
|
| 348 |
+
"should_save": true,
|
| 349 |
+
"should_training_stop": true
|
| 350 |
+
},
|
| 351 |
+
"attributes": {}
|
| 352 |
+
}
|
| 353 |
+
},
|
| 354 |
+
"total_flos": 9.06748200373715e+17,
|
| 355 |
+
"train_batch_size": 12,
|
| 356 |
+
"trial_name": null,
|
| 357 |
+
"trial_params": null
|
| 358 |
+
}
|