Model save
Browse files- README.md +69 -0
- all_results.json +9 -0
- train_results.json +9 -0
- trainer_state.json +309 -0
README.md
ADDED
|
@@ -0,0 +1,69 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: llama3
|
| 3 |
+
library_name: peft
|
| 4 |
+
tags:
|
| 5 |
+
- trl
|
| 6 |
+
- sft
|
| 7 |
+
- generated_from_trainer
|
| 8 |
+
base_model: meta-llama/Meta-Llama-3-8B
|
| 9 |
+
datasets:
|
| 10 |
+
- generator
|
| 11 |
+
model-index:
|
| 12 |
+
- name: downstream-7b-p0.1_seed42_syntax_level1
|
| 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 |
+
# downstream-7b-p0.1_seed42_syntax_level1
|
| 20 |
+
|
| 21 |
+
This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B) on the generator dataset.
|
| 22 |
+
It achieves the following results on the evaluation set:
|
| 23 |
+
- Loss: 1.1019
|
| 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: 4
|
| 44 |
+
- eval_batch_size: 1
|
| 45 |
+
- seed: 42
|
| 46 |
+
- distributed_type: multi-GPU
|
| 47 |
+
- num_devices: 4
|
| 48 |
+
- gradient_accumulation_steps: 4
|
| 49 |
+
- total_train_batch_size: 64
|
| 50 |
+
- total_eval_batch_size: 4
|
| 51 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 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 |
+
| 1.0662 | 0.9986 | 180 | 1.1019 |
|
| 61 |
+
|
| 62 |
+
|
| 63 |
+
### Framework versions
|
| 64 |
+
|
| 65 |
+
- PEFT 0.11.1
|
| 66 |
+
- Transformers 4.43.4
|
| 67 |
+
- Pytorch 2.3.1+cu121
|
| 68 |
+
- Datasets 2.19.1
|
| 69 |
+
- Tokenizers 0.19.1
|
all_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 0.9986130374479889,
|
| 3 |
+
"total_flos": 371612650045440.0,
|
| 4 |
+
"train_loss": 1.0954518543349372,
|
| 5 |
+
"train_runtime": 5437.2544,
|
| 6 |
+
"train_samples": 19747,
|
| 7 |
+
"train_samples_per_second": 2.121,
|
| 8 |
+
"train_steps_per_second": 0.033
|
| 9 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 0.9986130374479889,
|
| 3 |
+
"total_flos": 371612650045440.0,
|
| 4 |
+
"train_loss": 1.0954518543349372,
|
| 5 |
+
"train_runtime": 5437.2544,
|
| 6 |
+
"train_samples": 19747,
|
| 7 |
+
"train_samples_per_second": 2.121,
|
| 8 |
+
"train_steps_per_second": 0.033
|
| 9 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,309 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.9986130374479889,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 180,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.005547850208044383,
|
| 13 |
+
"grad_norm": 4.195843084105169,
|
| 14 |
+
"learning_rate": 1.1111111111111112e-05,
|
| 15 |
+
"loss": 1.4047,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.027739251040221916,
|
| 20 |
+
"grad_norm": 0.7369275637110823,
|
| 21 |
+
"learning_rate": 5.555555555555556e-05,
|
| 22 |
+
"loss": 1.331,
|
| 23 |
+
"step": 5
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.05547850208044383,
|
| 27 |
+
"grad_norm": 0.4333227696075342,
|
| 28 |
+
"learning_rate": 0.00011111111111111112,
|
| 29 |
+
"loss": 1.2277,
|
| 30 |
+
"step": 10
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.08321775312066575,
|
| 34 |
+
"grad_norm": 0.24055777481676408,
|
| 35 |
+
"learning_rate": 0.0001666666666666667,
|
| 36 |
+
"loss": 1.1721,
|
| 37 |
+
"step": 15
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.11095700416088766,
|
| 41 |
+
"grad_norm": 0.21061480866876423,
|
| 42 |
+
"learning_rate": 0.00019992479525042303,
|
| 43 |
+
"loss": 1.1489,
|
| 44 |
+
"step": 20
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.13869625520110956,
|
| 48 |
+
"grad_norm": 0.1977619665262726,
|
| 49 |
+
"learning_rate": 0.00019908004033648453,
|
| 50 |
+
"loss": 1.1261,
|
| 51 |
+
"step": 25
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.1664355062413315,
|
| 55 |
+
"grad_norm": 0.19642061090412125,
|
| 56 |
+
"learning_rate": 0.00019730448705798239,
|
| 57 |
+
"loss": 1.1668,
|
| 58 |
+
"step": 30
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.1941747572815534,
|
| 62 |
+
"grad_norm": 0.19926537287762208,
|
| 63 |
+
"learning_rate": 0.00019461481568757506,
|
| 64 |
+
"loss": 1.1308,
|
| 65 |
+
"step": 35
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.22191400832177532,
|
| 69 |
+
"grad_norm": 0.18005042043286312,
|
| 70 |
+
"learning_rate": 0.0001910362940966147,
|
| 71 |
+
"loss": 1.1118,
|
| 72 |
+
"step": 40
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.24965325936199723,
|
| 76 |
+
"grad_norm": 0.17482654378958667,
|
| 77 |
+
"learning_rate": 0.00018660254037844388,
|
| 78 |
+
"loss": 1.1127,
|
| 79 |
+
"step": 45
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.27739251040221913,
|
| 83 |
+
"grad_norm": 0.17841493887510787,
|
| 84 |
+
"learning_rate": 0.00018135520702629675,
|
| 85 |
+
"loss": 1.0927,
|
| 86 |
+
"step": 50
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.30513176144244103,
|
| 90 |
+
"grad_norm": 0.17654138755144574,
|
| 91 |
+
"learning_rate": 0.00017534358963276607,
|
| 92 |
+
"loss": 1.1281,
|
| 93 |
+
"step": 55
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.332871012482663,
|
| 97 |
+
"grad_norm": 0.18093646794731982,
|
| 98 |
+
"learning_rate": 0.0001686241637868734,
|
| 99 |
+
"loss": 1.1027,
|
| 100 |
+
"step": 60
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.3606102635228849,
|
| 104 |
+
"grad_norm": 0.17282395865206962,
|
| 105 |
+
"learning_rate": 0.0001612600545193203,
|
| 106 |
+
"loss": 1.0791,
|
| 107 |
+
"step": 65
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.3883495145631068,
|
| 111 |
+
"grad_norm": 0.2130133899623223,
|
| 112 |
+
"learning_rate": 0.00015332044328016914,
|
| 113 |
+
"loss": 1.0707,
|
| 114 |
+
"step": 70
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.4160887656033287,
|
| 118 |
+
"grad_norm": 0.17620893249441422,
|
| 119 |
+
"learning_rate": 0.00014487991802004623,
|
| 120 |
+
"loss": 1.0764,
|
| 121 |
+
"step": 75
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.44382801664355065,
|
| 125 |
+
"grad_norm": 0.17824570150374044,
|
| 126 |
+
"learning_rate": 0.00013601777248047105,
|
| 127 |
+
"loss": 1.0786,
|
| 128 |
+
"step": 80
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.47156726768377255,
|
| 132 |
+
"grad_norm": 0.17908199389292137,
|
| 133 |
+
"learning_rate": 0.00012681726127606376,
|
| 134 |
+
"loss": 1.075,
|
| 135 |
+
"step": 85
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.49930651872399445,
|
| 139 |
+
"grad_norm": 0.16536298826240392,
|
| 140 |
+
"learning_rate": 0.00011736481776669306,
|
| 141 |
+
"loss": 1.0495,
|
| 142 |
+
"step": 90
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.5270457697642164,
|
| 146 |
+
"grad_norm": 0.16772226493789477,
|
| 147 |
+
"learning_rate": 0.0001077492420671931,
|
| 148 |
+
"loss": 1.0621,
|
| 149 |
+
"step": 95
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.5547850208044383,
|
| 153 |
+
"grad_norm": 0.16400769234594714,
|
| 154 |
+
"learning_rate": 9.806086682281758e-05,
|
| 155 |
+
"loss": 1.0733,
|
| 156 |
+
"step": 100
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.5825242718446602,
|
| 160 |
+
"grad_norm": 0.17398111998791801,
|
| 161 |
+
"learning_rate": 8.839070858747697e-05,
|
| 162 |
+
"loss": 1.0807,
|
| 163 |
+
"step": 105
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.6102635228848821,
|
| 167 |
+
"grad_norm": 0.1667519248225914,
|
| 168 |
+
"learning_rate": 7.882961277705895e-05,
|
| 169 |
+
"loss": 1.0587,
|
| 170 |
+
"step": 110
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.6380027739251041,
|
| 174 |
+
"grad_norm": 0.17276811075234527,
|
| 175 |
+
"learning_rate": 6.94674002304887e-05,
|
| 176 |
+
"loss": 1.0696,
|
| 177 |
+
"step": 115
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.665742024965326,
|
| 181 |
+
"grad_norm": 0.1778606830836011,
|
| 182 |
+
"learning_rate": 6.039202339608432e-05,
|
| 183 |
+
"loss": 1.0749,
|
| 184 |
+
"step": 120
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.6934812760055479,
|
| 188 |
+
"grad_norm": 0.15999213488751612,
|
| 189 |
+
"learning_rate": 5.168874007033615e-05,
|
| 190 |
+
"loss": 1.0611,
|
| 191 |
+
"step": 125
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.7212205270457698,
|
| 195 |
+
"grad_norm": 0.162094501109682,
|
| 196 |
+
"learning_rate": 4.343931245134616e-05,
|
| 197 |
+
"loss": 1.0655,
|
| 198 |
+
"step": 130
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.7489597780859917,
|
| 202 |
+
"grad_norm": 0.16199274412290549,
|
| 203 |
+
"learning_rate": 3.5721239031346066e-05,
|
| 204 |
+
"loss": 1.0524,
|
| 205 |
+
"step": 135
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.7766990291262136,
|
| 209 |
+
"grad_norm": 0.1641358791714059,
|
| 210 |
+
"learning_rate": 2.8607026544210114e-05,
|
| 211 |
+
"loss": 1.0519,
|
| 212 |
+
"step": 140
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.8044382801664355,
|
| 216 |
+
"grad_norm": 0.17454488135701385,
|
| 217 |
+
"learning_rate": 2.2163508807583998e-05,
|
| 218 |
+
"loss": 1.0758,
|
| 219 |
+
"step": 145
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.8321775312066574,
|
| 223 |
+
"grad_norm": 0.16940543249627216,
|
| 224 |
+
"learning_rate": 1.6451218858706374e-05,
|
| 225 |
+
"loss": 1.051,
|
| 226 |
+
"step": 150
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.8599167822468793,
|
| 230 |
+
"grad_norm": 0.1699983346793352,
|
| 231 |
+
"learning_rate": 1.1523820282334219e-05,
|
| 232 |
+
"loss": 1.0548,
|
| 233 |
+
"step": 155
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.8876560332871013,
|
| 237 |
+
"grad_norm": 0.16182400427483473,
|
| 238 |
+
"learning_rate": 7.427603073110967e-06,
|
| 239 |
+
"loss": 1.0578,
|
| 240 |
+
"step": 160
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.9153952843273232,
|
| 244 |
+
"grad_norm": 0.16401094680605324,
|
| 245 |
+
"learning_rate": 4.20104876845111e-06,
|
| 246 |
+
"loss": 1.0958,
|
| 247 |
+
"step": 165
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.9431345353675451,
|
| 251 |
+
"grad_norm": 0.1620592393374915,
|
| 252 |
+
"learning_rate": 1.874468937261531e-06,
|
| 253 |
+
"loss": 1.0457,
|
| 254 |
+
"step": 170
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.970873786407767,
|
| 258 |
+
"grad_norm": 0.16185102522208447,
|
| 259 |
+
"learning_rate": 4.6972042068341714e-07,
|
| 260 |
+
"loss": 1.0434,
|
| 261 |
+
"step": 175
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.9986130374479889,
|
| 265 |
+
"grad_norm": 0.16341103139774715,
|
| 266 |
+
"learning_rate": 0.0,
|
| 267 |
+
"loss": 1.0662,
|
| 268 |
+
"step": 180
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.9986130374479889,
|
| 272 |
+
"eval_loss": 1.101938009262085,
|
| 273 |
+
"eval_runtime": 1905.3768,
|
| 274 |
+
"eval_samples_per_second": 3.52,
|
| 275 |
+
"eval_steps_per_second": 0.88,
|
| 276 |
+
"step": 180
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.9986130374479889,
|
| 280 |
+
"step": 180,
|
| 281 |
+
"total_flos": 371612650045440.0,
|
| 282 |
+
"train_loss": 1.0954518543349372,
|
| 283 |
+
"train_runtime": 5437.2544,
|
| 284 |
+
"train_samples_per_second": 2.121,
|
| 285 |
+
"train_steps_per_second": 0.033
|
| 286 |
+
}
|
| 287 |
+
],
|
| 288 |
+
"logging_steps": 5,
|
| 289 |
+
"max_steps": 180,
|
| 290 |
+
"num_input_tokens_seen": 0,
|
| 291 |
+
"num_train_epochs": 1,
|
| 292 |
+
"save_steps": 100,
|
| 293 |
+
"stateful_callbacks": {
|
| 294 |
+
"TrainerControl": {
|
| 295 |
+
"args": {
|
| 296 |
+
"should_epoch_stop": false,
|
| 297 |
+
"should_evaluate": false,
|
| 298 |
+
"should_log": false,
|
| 299 |
+
"should_save": true,
|
| 300 |
+
"should_training_stop": true
|
| 301 |
+
},
|
| 302 |
+
"attributes": {}
|
| 303 |
+
}
|
| 304 |
+
},
|
| 305 |
+
"total_flos": 371612650045440.0,
|
| 306 |
+
"train_batch_size": 4,
|
| 307 |
+
"trial_name": null,
|
| 308 |
+
"trial_params": null
|
| 309 |
+
}
|