Model save
Browse files- README.md +70 -0
- all_results.json +9 -0
- train_results.json +9 -0
- trainer_state.json +307 -0
README.md
ADDED
|
@@ -0,0 +1,70 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: barc0/Llama-3.1-ARC-Potpourri-Transduction-8B
|
| 3 |
+
library_name: peft
|
| 4 |
+
license: llama3.1
|
| 5 |
+
tags:
|
| 6 |
+
- trl
|
| 7 |
+
- sft
|
| 8 |
+
- generated_from_trainer
|
| 9 |
+
model-index:
|
| 10 |
+
- name: problem347_model_mit
|
| 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 |
+
# problem347_model_mit
|
| 18 |
+
|
| 19 |
+
This model is a fine-tuned version of [barc0/Llama-3.1-ARC-Potpourri-Transduction-8B](https://huggingface.co/barc0/Llama-3.1-ARC-Potpourri-Transduction-8B) on an unknown dataset.
|
| 20 |
+
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 0.0292
|
| 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: 1
|
| 42 |
+
- eval_batch_size: 1
|
| 43 |
+
- seed: 42
|
| 44 |
+
- distributed_type: multi-GPU
|
| 45 |
+
- gradient_accumulation_steps: 2
|
| 46 |
+
- total_train_batch_size: 2
|
| 47 |
+
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 48 |
+
- lr_scheduler_type: cosine
|
| 49 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 50 |
+
- num_epochs: 2
|
| 51 |
+
|
| 52 |
+
### Training results
|
| 53 |
+
|
| 54 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 55 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
| 56 |
+
| No log | 0 | 0 | 0.1121 |
|
| 57 |
+
| 0.1136 | 0.4 | 30 | 0.0323 |
|
| 58 |
+
| 0.0854 | 0.8 | 60 | 0.0274 |
|
| 59 |
+
| 0.0524 | 1.2 | 90 | 0.0294 |
|
| 60 |
+
| 0.0612 | 1.6 | 120 | 0.0289 |
|
| 61 |
+
| 0.082 | 2.0 | 150 | 0.0292 |
|
| 62 |
+
|
| 63 |
+
|
| 64 |
+
### Framework versions
|
| 65 |
+
|
| 66 |
+
- PEFT 0.13.2
|
| 67 |
+
- Transformers 4.47.0.dev0
|
| 68 |
+
- Pytorch 2.4.0+cu121
|
| 69 |
+
- Datasets 3.1.0
|
| 70 |
+
- Tokenizers 0.20.3
|
all_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.0,
|
| 3 |
+
"total_flos": 8212577402880.0,
|
| 4 |
+
"train_loss": 0.09479607075452805,
|
| 5 |
+
"train_runtime": 682.7157,
|
| 6 |
+
"train_samples": 150,
|
| 7 |
+
"train_samples_per_second": 0.439,
|
| 8 |
+
"train_steps_per_second": 0.22
|
| 9 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.0,
|
| 3 |
+
"total_flos": 8212577402880.0,
|
| 4 |
+
"train_loss": 0.09479607075452805,
|
| 5 |
+
"train_runtime": 682.7157,
|
| 6 |
+
"train_samples": 150,
|
| 7 |
+
"train_samples_per_second": 0.439,
|
| 8 |
+
"train_steps_per_second": 0.22
|
| 9 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,307 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.0,
|
| 5 |
+
"eval_steps": 30,
|
| 6 |
+
"global_step": 150,
|
| 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,
|
| 13 |
+
"eval_loss": 0.11211773008108139,
|
| 14 |
+
"eval_runtime": 0.9743,
|
| 15 |
+
"eval_samples_per_second": 1.026,
|
| 16 |
+
"eval_steps_per_second": 1.026,
|
| 17 |
+
"step": 0
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.013333333333333334,
|
| 21 |
+
"grad_norm": 0.031030020275519335,
|
| 22 |
+
"learning_rate": 3.3333333333333333e-06,
|
| 23 |
+
"loss": 0.1667,
|
| 24 |
+
"step": 1
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.06666666666666667,
|
| 28 |
+
"grad_norm": 0.03834570557711562,
|
| 29 |
+
"learning_rate": 1.6666666666666667e-05,
|
| 30 |
+
"loss": 0.2058,
|
| 31 |
+
"step": 5
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.13333333333333333,
|
| 35 |
+
"grad_norm": 0.028094023294595035,
|
| 36 |
+
"learning_rate": 3.3333333333333335e-05,
|
| 37 |
+
"loss": 0.1865,
|
| 38 |
+
"step": 10
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.2,
|
| 42 |
+
"grad_norm": 0.04762041128095506,
|
| 43 |
+
"learning_rate": 5e-05,
|
| 44 |
+
"loss": 0.1856,
|
| 45 |
+
"step": 15
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.26666666666666666,
|
| 49 |
+
"grad_norm": 0.028418698028222177,
|
| 50 |
+
"learning_rate": 4.983095894354858e-05,
|
| 51 |
+
"loss": 0.0908,
|
| 52 |
+
"step": 20
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.3333333333333333,
|
| 56 |
+
"grad_norm": 0.034568736978493136,
|
| 57 |
+
"learning_rate": 4.9326121764495596e-05,
|
| 58 |
+
"loss": 0.1115,
|
| 59 |
+
"step": 25
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.4,
|
| 63 |
+
"grad_norm": 0.016206653452619863,
|
| 64 |
+
"learning_rate": 4.849231551964771e-05,
|
| 65 |
+
"loss": 0.1136,
|
| 66 |
+
"step": 30
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.4,
|
| 70 |
+
"eval_loss": 0.032250553369522095,
|
| 71 |
+
"eval_runtime": 1.0414,
|
| 72 |
+
"eval_samples_per_second": 0.96,
|
| 73 |
+
"eval_steps_per_second": 0.96,
|
| 74 |
+
"step": 30
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.4666666666666667,
|
| 78 |
+
"grad_norm": 0.021469934923105765,
|
| 79 |
+
"learning_rate": 4.734081600808531e-05,
|
| 80 |
+
"loss": 0.0643,
|
| 81 |
+
"step": 35
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.5333333333333333,
|
| 85 |
+
"grad_norm": 0.055096082731337134,
|
| 86 |
+
"learning_rate": 4.588719528532342e-05,
|
| 87 |
+
"loss": 0.1261,
|
| 88 |
+
"step": 40
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 0.6,
|
| 92 |
+
"grad_norm": 0.05031835137603206,
|
| 93 |
+
"learning_rate": 4.415111107797445e-05,
|
| 94 |
+
"loss": 0.1096,
|
| 95 |
+
"step": 45
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 0.6666666666666666,
|
| 99 |
+
"grad_norm": 0.05516939025833793,
|
| 100 |
+
"learning_rate": 4.215604094671835e-05,
|
| 101 |
+
"loss": 0.0866,
|
| 102 |
+
"step": 50
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 0.7333333333333333,
|
| 106 |
+
"grad_norm": 0.032766685078341795,
|
| 107 |
+
"learning_rate": 3.9928964792569655e-05,
|
| 108 |
+
"loss": 0.083,
|
| 109 |
+
"step": 55
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 0.8,
|
| 113 |
+
"grad_norm": 0.062414929894008056,
|
| 114 |
+
"learning_rate": 3.7500000000000003e-05,
|
| 115 |
+
"loss": 0.0854,
|
| 116 |
+
"step": 60
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.8,
|
| 120 |
+
"eval_loss": 0.02738812565803528,
|
| 121 |
+
"eval_runtime": 0.8308,
|
| 122 |
+
"eval_samples_per_second": 1.204,
|
| 123 |
+
"eval_steps_per_second": 1.204,
|
| 124 |
+
"step": 60
|
| 125 |
+
},
|
| 126 |
+
{
|
| 127 |
+
"epoch": 0.8666666666666667,
|
| 128 |
+
"grad_norm": 0.04592653742748478,
|
| 129 |
+
"learning_rate": 3.490199415097892e-05,
|
| 130 |
+
"loss": 0.0982,
|
| 131 |
+
"step": 65
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 0.9333333333333333,
|
| 135 |
+
"grad_norm": 0.050049367221732345,
|
| 136 |
+
"learning_rate": 3.217008081777726e-05,
|
| 137 |
+
"loss": 0.0871,
|
| 138 |
+
"step": 70
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 1.0,
|
| 142 |
+
"grad_norm": 0.05998266046794504,
|
| 143 |
+
"learning_rate": 2.9341204441673266e-05,
|
| 144 |
+
"loss": 0.1206,
|
| 145 |
+
"step": 75
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 1.0666666666666667,
|
| 149 |
+
"grad_norm": 0.019636243300368693,
|
| 150 |
+
"learning_rate": 2.6453620722761896e-05,
|
| 151 |
+
"loss": 0.088,
|
| 152 |
+
"step": 80
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 1.1333333333333333,
|
| 156 |
+
"grad_norm": 0.043655221641392454,
|
| 157 |
+
"learning_rate": 2.3546379277238107e-05,
|
| 158 |
+
"loss": 0.0855,
|
| 159 |
+
"step": 85
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 1.2,
|
| 163 |
+
"grad_norm": 0.04216235250268384,
|
| 164 |
+
"learning_rate": 2.0658795558326743e-05,
|
| 165 |
+
"loss": 0.0524,
|
| 166 |
+
"step": 90
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 1.2,
|
| 170 |
+
"eval_loss": 0.029387038201093674,
|
| 171 |
+
"eval_runtime": 0.8351,
|
| 172 |
+
"eval_samples_per_second": 1.197,
|
| 173 |
+
"eval_steps_per_second": 1.197,
|
| 174 |
+
"step": 90
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 1.2666666666666666,
|
| 178 |
+
"grad_norm": 0.06963947213522952,
|
| 179 |
+
"learning_rate": 1.7829919182222752e-05,
|
| 180 |
+
"loss": 0.071,
|
| 181 |
+
"step": 95
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 1.3333333333333333,
|
| 185 |
+
"grad_norm": 0.043611217695380816,
|
| 186 |
+
"learning_rate": 1.509800584902108e-05,
|
| 187 |
+
"loss": 0.0664,
|
| 188 |
+
"step": 100
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 1.4,
|
| 192 |
+
"grad_norm": 0.04198147697434117,
|
| 193 |
+
"learning_rate": 1.2500000000000006e-05,
|
| 194 |
+
"loss": 0.0678,
|
| 195 |
+
"step": 105
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 1.4666666666666668,
|
| 199 |
+
"grad_norm": 0.07071909102500858,
|
| 200 |
+
"learning_rate": 1.0071035207430352e-05,
|
| 201 |
+
"loss": 0.0654,
|
| 202 |
+
"step": 110
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 1.5333333333333332,
|
| 206 |
+
"grad_norm": 0.06390301372675955,
|
| 207 |
+
"learning_rate": 7.843959053281663e-06,
|
| 208 |
+
"loss": 0.0827,
|
| 209 |
+
"step": 115
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 1.6,
|
| 213 |
+
"grad_norm": 0.049604240366544386,
|
| 214 |
+
"learning_rate": 5.848888922025553e-06,
|
| 215 |
+
"loss": 0.0612,
|
| 216 |
+
"step": 120
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 1.6,
|
| 220 |
+
"eval_loss": 0.02892993949353695,
|
| 221 |
+
"eval_runtime": 0.839,
|
| 222 |
+
"eval_samples_per_second": 1.192,
|
| 223 |
+
"eval_steps_per_second": 1.192,
|
| 224 |
+
"step": 120
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 1.6666666666666665,
|
| 228 |
+
"grad_norm": 0.07360390322146955,
|
| 229 |
+
"learning_rate": 4.112804714676594e-06,
|
| 230 |
+
"loss": 0.0845,
|
| 231 |
+
"step": 125
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 1.7333333333333334,
|
| 235 |
+
"grad_norm": 0.06226824488391461,
|
| 236 |
+
"learning_rate": 2.659183991914696e-06,
|
| 237 |
+
"loss": 0.0926,
|
| 238 |
+
"step": 130
|
| 239 |
+
},
|
| 240 |
+
{
|
| 241 |
+
"epoch": 1.8,
|
| 242 |
+
"grad_norm": 0.05406489110230538,
|
| 243 |
+
"learning_rate": 1.5076844803522922e-06,
|
| 244 |
+
"loss": 0.0688,
|
| 245 |
+
"step": 135
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 1.8666666666666667,
|
| 249 |
+
"grad_norm": 0.06035274580908478,
|
| 250 |
+
"learning_rate": 6.738782355044049e-07,
|
| 251 |
+
"loss": 0.0741,
|
| 252 |
+
"step": 140
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 1.9333333333333333,
|
| 256 |
+
"grad_norm": 0.06719978224301647,
|
| 257 |
+
"learning_rate": 1.6904105645142444e-07,
|
| 258 |
+
"loss": 0.0547,
|
| 259 |
+
"step": 145
|
| 260 |
+
},
|
| 261 |
+
{
|
| 262 |
+
"epoch": 2.0,
|
| 263 |
+
"grad_norm": 0.09296641078603293,
|
| 264 |
+
"learning_rate": 0.0,
|
| 265 |
+
"loss": 0.082,
|
| 266 |
+
"step": 150
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 2.0,
|
| 270 |
+
"eval_loss": 0.02918284200131893,
|
| 271 |
+
"eval_runtime": 0.839,
|
| 272 |
+
"eval_samples_per_second": 1.192,
|
| 273 |
+
"eval_steps_per_second": 1.192,
|
| 274 |
+
"step": 150
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 2.0,
|
| 278 |
+
"step": 150,
|
| 279 |
+
"total_flos": 8212577402880.0,
|
| 280 |
+
"train_loss": 0.09479607075452805,
|
| 281 |
+
"train_runtime": 682.7157,
|
| 282 |
+
"train_samples_per_second": 0.439,
|
| 283 |
+
"train_steps_per_second": 0.22
|
| 284 |
+
}
|
| 285 |
+
],
|
| 286 |
+
"logging_steps": 5,
|
| 287 |
+
"max_steps": 150,
|
| 288 |
+
"num_input_tokens_seen": 0,
|
| 289 |
+
"num_train_epochs": 2,
|
| 290 |
+
"save_steps": 500,
|
| 291 |
+
"stateful_callbacks": {
|
| 292 |
+
"TrainerControl": {
|
| 293 |
+
"args": {
|
| 294 |
+
"should_epoch_stop": false,
|
| 295 |
+
"should_evaluate": false,
|
| 296 |
+
"should_log": false,
|
| 297 |
+
"should_save": true,
|
| 298 |
+
"should_training_stop": true
|
| 299 |
+
},
|
| 300 |
+
"attributes": {}
|
| 301 |
+
}
|
| 302 |
+
},
|
| 303 |
+
"total_flos": 8212577402880.0,
|
| 304 |
+
"train_batch_size": 1,
|
| 305 |
+
"trial_name": null,
|
| 306 |
+
"trial_params": null
|
| 307 |
+
}
|