Delete trainer_state.json
Browse files- trainer_state.json +0 -96
trainer_state.json
DELETED
|
@@ -1,96 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"best_metric": null,
|
| 3 |
-
"best_model_checkpoint": null,
|
| 4 |
-
"epoch": 14.76121562952243,
|
| 5 |
-
"eval_steps": 500,
|
| 6 |
-
"global_step": 2550,
|
| 7 |
-
"is_hyper_param_search": false,
|
| 8 |
-
"is_local_process_zero": true,
|
| 9 |
-
"is_world_process_zero": true,
|
| 10 |
-
"log_history": [
|
| 11 |
-
{
|
| 12 |
-
"epoch": 2.89,
|
| 13 |
-
"grad_norm": 1.0645270347595215,
|
| 14 |
-
"learning_rate": 8.486332109343125e-06,
|
| 15 |
-
"loss": 3.4851,
|
| 16 |
-
"step": 500
|
| 17 |
-
},
|
| 18 |
-
{
|
| 19 |
-
"epoch": 2.89,
|
| 20 |
-
"eval_loss": 0.5308476686477661,
|
| 21 |
-
"eval_runtime": 54.8537,
|
| 22 |
-
"eval_samples_per_second": 17.264,
|
| 23 |
-
"eval_steps_per_second": 1.094,
|
| 24 |
-
"step": 500
|
| 25 |
-
},
|
| 26 |
-
{
|
| 27 |
-
"epoch": 5.79,
|
| 28 |
-
"grad_norm": 1.1767557859420776,
|
| 29 |
-
"learning_rate": 6.446348429212567e-06,
|
| 30 |
-
"loss": 0.4272,
|
| 31 |
-
"step": 1000
|
| 32 |
-
},
|
| 33 |
-
{
|
| 34 |
-
"epoch": 5.79,
|
| 35 |
-
"eval_loss": 0.48605769872665405,
|
| 36 |
-
"eval_runtime": 54.7929,
|
| 37 |
-
"eval_samples_per_second": 17.283,
|
| 38 |
-
"eval_steps_per_second": 1.095,
|
| 39 |
-
"step": 1000
|
| 40 |
-
},
|
| 41 |
-
{
|
| 42 |
-
"epoch": 8.68,
|
| 43 |
-
"grad_norm": 1.228811264038086,
|
| 44 |
-
"learning_rate": 4.406364749082008e-06,
|
| 45 |
-
"loss": 0.3706,
|
| 46 |
-
"step": 1500
|
| 47 |
-
},
|
| 48 |
-
{
|
| 49 |
-
"epoch": 8.68,
|
| 50 |
-
"eval_loss": 0.47189345955848694,
|
| 51 |
-
"eval_runtime": 54.8284,
|
| 52 |
-
"eval_samples_per_second": 17.272,
|
| 53 |
-
"eval_steps_per_second": 1.094,
|
| 54 |
-
"step": 1500
|
| 55 |
-
},
|
| 56 |
-
{
|
| 57 |
-
"epoch": 11.58,
|
| 58 |
-
"grad_norm": 1.4037022590637207,
|
| 59 |
-
"learning_rate": 2.3663810689514487e-06,
|
| 60 |
-
"loss": 0.345,
|
| 61 |
-
"step": 2000
|
| 62 |
-
},
|
| 63 |
-
{
|
| 64 |
-
"epoch": 11.58,
|
| 65 |
-
"eval_loss": 0.4648812413215637,
|
| 66 |
-
"eval_runtime": 54.9124,
|
| 67 |
-
"eval_samples_per_second": 17.246,
|
| 68 |
-
"eval_steps_per_second": 1.093,
|
| 69 |
-
"step": 2000
|
| 70 |
-
},
|
| 71 |
-
{
|
| 72 |
-
"epoch": 14.47,
|
| 73 |
-
"grad_norm": 1.5453025102615356,
|
| 74 |
-
"learning_rate": 3.263973888208895e-07,
|
| 75 |
-
"loss": 0.3283,
|
| 76 |
-
"step": 2500
|
| 77 |
-
},
|
| 78 |
-
{
|
| 79 |
-
"epoch": 14.47,
|
| 80 |
-
"eval_loss": 0.4620264172554016,
|
| 81 |
-
"eval_runtime": 55.0096,
|
| 82 |
-
"eval_samples_per_second": 17.215,
|
| 83 |
-
"eval_steps_per_second": 1.091,
|
| 84 |
-
"step": 2500
|
| 85 |
-
}
|
| 86 |
-
],
|
| 87 |
-
"logging_steps": 500,
|
| 88 |
-
"max_steps": 2580,
|
| 89 |
-
"num_input_tokens_seen": 0,
|
| 90 |
-
"num_train_epochs": 15,
|
| 91 |
-
"save_steps": 50,
|
| 92 |
-
"total_flos": 9.936487691845632e+16,
|
| 93 |
-
"train_batch_size": 2,
|
| 94 |
-
"trial_name": null,
|
| 95 |
-
"trial_params": null
|
| 96 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|