End of training
Browse files- all_results.json +8 -0
- train_results.json +8 -0
- trainer_state.json +78 -0
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 30.0,
|
| 3 |
+
"total_flos": 7.832575533868646e+17,
|
| 4 |
+
"train_loss": 0.009042149140476817,
|
| 5 |
+
"train_runtime": 1040.7829,
|
| 6 |
+
"train_samples_per_second": 150.81,
|
| 7 |
+
"train_steps_per_second": 2.364
|
| 8 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 30.0,
|
| 3 |
+
"total_flos": 7.832575533868646e+17,
|
| 4 |
+
"train_loss": 0.009042149140476817,
|
| 5 |
+
"train_runtime": 1040.7829,
|
| 6 |
+
"train_samples_per_second": 150.81,
|
| 7 |
+
"train_steps_per_second": 2.364
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,78 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 30.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 2460,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.012195121951219513,
|
| 14 |
+
"grad_norm": 32.47914123535156,
|
| 15 |
+
"learning_rate": 5e-05,
|
| 16 |
+
"loss": 2.2038,
|
| 17 |
+
"step": 1
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 6.097560975609756,
|
| 21 |
+
"grad_norm": 0.004238747991621494,
|
| 22 |
+
"learning_rate": 3.9857723577235775e-05,
|
| 23 |
+
"loss": 0.0401,
|
| 24 |
+
"step": 500
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 12.195121951219512,
|
| 28 |
+
"grad_norm": 0.0014152198564261198,
|
| 29 |
+
"learning_rate": 2.969512195121951e-05,
|
| 30 |
+
"loss": 0.0,
|
| 31 |
+
"step": 1000
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 18.29268292682927,
|
| 35 |
+
"grad_norm": 0.0011360333301126957,
|
| 36 |
+
"learning_rate": 1.953252032520325e-05,
|
| 37 |
+
"loss": 0.0,
|
| 38 |
+
"step": 1500
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 24.390243902439025,
|
| 42 |
+
"grad_norm": 0.000390420900657773,
|
| 43 |
+
"learning_rate": 9.369918699186993e-06,
|
| 44 |
+
"loss": 0.0,
|
| 45 |
+
"step": 2000
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 30.0,
|
| 49 |
+
"step": 2460,
|
| 50 |
+
"total_flos": 7.832575533868646e+17,
|
| 51 |
+
"train_loss": 0.009042149140476817,
|
| 52 |
+
"train_runtime": 1040.7829,
|
| 53 |
+
"train_samples_per_second": 150.81,
|
| 54 |
+
"train_steps_per_second": 2.364
|
| 55 |
+
}
|
| 56 |
+
],
|
| 57 |
+
"logging_steps": 500,
|
| 58 |
+
"max_steps": 2460,
|
| 59 |
+
"num_input_tokens_seen": 0,
|
| 60 |
+
"num_train_epochs": 30,
|
| 61 |
+
"save_steps": 500,
|
| 62 |
+
"stateful_callbacks": {
|
| 63 |
+
"TrainerControl": {
|
| 64 |
+
"args": {
|
| 65 |
+
"should_epoch_stop": false,
|
| 66 |
+
"should_evaluate": false,
|
| 67 |
+
"should_log": false,
|
| 68 |
+
"should_save": true,
|
| 69 |
+
"should_training_stop": true
|
| 70 |
+
},
|
| 71 |
+
"attributes": {}
|
| 72 |
+
}
|
| 73 |
+
},
|
| 74 |
+
"total_flos": 7.832575533868646e+17,
|
| 75 |
+
"train_batch_size": 64,
|
| 76 |
+
"trial_name": null,
|
| 77 |
+
"trial_params": null
|
| 78 |
+
}
|