Upload trainer_state.json
Browse files- trainer_state.json +74 -0
trainer_state.json
ADDED
|
@@ -0,0 +1,74 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 4.948616600790514,
|
| 5 |
+
"global_step": 1500,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 1.0,
|
| 12 |
+
"eval_bleu": 25.8406,
|
| 13 |
+
"eval_gen_len": 37.7921,
|
| 14 |
+
"eval_loss": 1.0771484375,
|
| 15 |
+
"eval_runtime": 90.1252,
|
| 16 |
+
"eval_samples_per_second": 4.483,
|
| 17 |
+
"eval_steps_per_second": 0.288,
|
| 18 |
+
"step": 303
|
| 19 |
+
},
|
| 20 |
+
{
|
| 21 |
+
"epoch": 1.65,
|
| 22 |
+
"learning_rate": 2e-05,
|
| 23 |
+
"loss": 1.1552,
|
| 24 |
+
"step": 500
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 2.0,
|
| 28 |
+
"eval_bleu": 27.5846,
|
| 29 |
+
"eval_gen_len": 37.9579,
|
| 30 |
+
"eval_loss": 0.99169921875,
|
| 31 |
+
"eval_runtime": 87.9875,
|
| 32 |
+
"eval_samples_per_second": 4.592,
|
| 33 |
+
"eval_steps_per_second": 0.295,
|
| 34 |
+
"step": 606
|
| 35 |
+
},
|
| 36 |
+
{
|
| 37 |
+
"epoch": 3.0,
|
| 38 |
+
"eval_bleu": 28.1347,
|
| 39 |
+
"eval_gen_len": 38.3317,
|
| 40 |
+
"eval_loss": 0.97314453125,
|
| 41 |
+
"eval_runtime": 92.4432,
|
| 42 |
+
"eval_samples_per_second": 4.37,
|
| 43 |
+
"eval_steps_per_second": 0.281,
|
| 44 |
+
"step": 909
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 3.3,
|
| 48 |
+
"learning_rate": 2e-05,
|
| 49 |
+
"loss": 0.679,
|
| 50 |
+
"step": 1000
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 4.0,
|
| 54 |
+
"eval_bleu": 28.081,
|
| 55 |
+
"eval_gen_len": 37.651,
|
| 56 |
+
"eval_loss": 0.99169921875,
|
| 57 |
+
"eval_runtime": 85.9085,
|
| 58 |
+
"eval_samples_per_second": 4.703,
|
| 59 |
+
"eval_steps_per_second": 0.303,
|
| 60 |
+
"step": 1212
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"epoch": 4.95,
|
| 64 |
+
"learning_rate": 2e-05,
|
| 65 |
+
"loss": 0.5046,
|
| 66 |
+
"step": 1500
|
| 67 |
+
}
|
| 68 |
+
],
|
| 69 |
+
"max_steps": 1515,
|
| 70 |
+
"num_train_epochs": 5,
|
| 71 |
+
"total_flos": 1.2130831043867443e+17,
|
| 72 |
+
"trial_name": null,
|
| 73 |
+
"trial_params": null
|
| 74 |
+
}
|