Upload trainer_state.json
Browse files- trainer_state.json +50 -0
trainer_state.json
ADDED
|
@@ -0,0 +1,50 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.0,
|
| 5 |
+
"global_step": 2075,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.24,
|
| 12 |
+
"learning_rate": 3.7951807228915666e-05,
|
| 13 |
+
"loss": 1.7836,
|
| 14 |
+
"step": 500
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.48,
|
| 18 |
+
"learning_rate": 2.5903614457831325e-05,
|
| 19 |
+
"loss": 1.7368,
|
| 20 |
+
"step": 1000
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.72,
|
| 24 |
+
"learning_rate": 1.3855421686746989e-05,
|
| 25 |
+
"loss": 1.72,
|
| 26 |
+
"step": 1500
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.96,
|
| 30 |
+
"learning_rate": 1.8072289156626506e-06,
|
| 31 |
+
"loss": 1.6937,
|
| 32 |
+
"step": 2000
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.96,
|
| 36 |
+
"eval_bleu": 21.3823,
|
| 37 |
+
"eval_gen_len": 28.2551,
|
| 38 |
+
"eval_loss": 1.8005332946777344,
|
| 39 |
+
"eval_runtime": 121.1926,
|
| 40 |
+
"eval_samples_per_second": 10.867,
|
| 41 |
+
"eval_steps_per_second": 0.091,
|
| 42 |
+
"step": 2000
|
| 43 |
+
}
|
| 44 |
+
],
|
| 45 |
+
"max_steps": 2075,
|
| 46 |
+
"num_train_epochs": 1,
|
| 47 |
+
"total_flos": 7080945498390528.0,
|
| 48 |
+
"trial_name": null,
|
| 49 |
+
"trial_params": null
|
| 50 |
+
}
|