Model save
Browse files- trainer_state.json +100 -0
trainer_state.json
ADDED
|
@@ -0,0 +1,100 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 10.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 100,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 1.0,
|
| 13 |
+
"grad_norm": 0.5378170013427734,
|
| 14 |
+
"learning_rate": 0.00019510565162951537,
|
| 15 |
+
"loss": 0.8601,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 2.0,
|
| 20 |
+
"grad_norm": 0.21907852590084076,
|
| 21 |
+
"learning_rate": 0.00018090169943749476,
|
| 22 |
+
"loss": 0.6658,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 3.0,
|
| 27 |
+
"grad_norm": 0.2130054235458374,
|
| 28 |
+
"learning_rate": 0.00015877852522924732,
|
| 29 |
+
"loss": 0.6321,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 4.0,
|
| 34 |
+
"grad_norm": 0.2033412605524063,
|
| 35 |
+
"learning_rate": 0.00013090169943749476,
|
| 36 |
+
"loss": 0.6132,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 5.0,
|
| 41 |
+
"grad_norm": 0.23296789824962616,
|
| 42 |
+
"learning_rate": 0.0001,
|
| 43 |
+
"loss": 0.5994,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 6.0,
|
| 48 |
+
"grad_norm": 0.23752418160438538,
|
| 49 |
+
"learning_rate": 6.909830056250527e-05,
|
| 50 |
+
"loss": 0.588,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 7.0,
|
| 55 |
+
"grad_norm": 0.24876683950424194,
|
| 56 |
+
"learning_rate": 4.12214747707527e-05,
|
| 57 |
+
"loss": 0.5797,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 8.0,
|
| 62 |
+
"grad_norm": 0.2501850128173828,
|
| 63 |
+
"learning_rate": 1.9098300562505266e-05,
|
| 64 |
+
"loss": 0.5734,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 9.0,
|
| 69 |
+
"grad_norm": 0.2533394396305084,
|
| 70 |
+
"learning_rate": 4.8943483704846475e-06,
|
| 71 |
+
"loss": 0.5706,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 10.0,
|
| 76 |
+
"grad_norm": 0.24403364956378937,
|
| 77 |
+
"learning_rate": 0.0,
|
| 78 |
+
"loss": 0.5691,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 10.0,
|
| 83 |
+
"step": 100,
|
| 84 |
+
"total_flos": 2.023641298501632e+16,
|
| 85 |
+
"train_loss": 0.625129919052124,
|
| 86 |
+
"train_runtime": 1025.9433,
|
| 87 |
+
"train_samples_per_second": 3.09,
|
| 88 |
+
"train_steps_per_second": 0.097
|
| 89 |
+
}
|
| 90 |
+
],
|
| 91 |
+
"logging_steps": 10,
|
| 92 |
+
"max_steps": 100,
|
| 93 |
+
"num_input_tokens_seen": 0,
|
| 94 |
+
"num_train_epochs": 10,
|
| 95 |
+
"save_steps": 500,
|
| 96 |
+
"total_flos": 2.023641298501632e+16,
|
| 97 |
+
"train_batch_size": 8,
|
| 98 |
+
"trial_name": null,
|
| 99 |
+
"trial_params": null
|
| 100 |
+
}
|