End of training
Browse files- all_results.json +8 -0
- train_results.json +8 -0
- trainer_state.json +77 -0
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.0,
|
| 3 |
+
"total_flos": 9.4894217943552e+17,
|
| 4 |
+
"train_loss": 1.8031856994628905,
|
| 5 |
+
"train_runtime": 142.4314,
|
| 6 |
+
"train_samples_per_second": 13.944,
|
| 7 |
+
"train_steps_per_second": 1.755
|
| 8 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.0,
|
| 3 |
+
"total_flos": 9.4894217943552e+17,
|
| 4 |
+
"train_loss": 1.8031856994628905,
|
| 5 |
+
"train_runtime": 142.4314,
|
| 6 |
+
"train_samples_per_second": 13.944,
|
| 7 |
+
"train_steps_per_second": 1.755
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,77 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 250,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.4,
|
| 13 |
+
"grad_norm": 30.619651794433594,
|
| 14 |
+
"learning_rate": 8.16e-06,
|
| 15 |
+
"loss": 1.8291,
|
| 16 |
+
"step": 50
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.8,
|
| 20 |
+
"grad_norm": 155.9861297607422,
|
| 21 |
+
"learning_rate": 6.24e-06,
|
| 22 |
+
"loss": 1.8251,
|
| 23 |
+
"step": 100
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 1.2,
|
| 27 |
+
"grad_norm": 59.954654693603516,
|
| 28 |
+
"learning_rate": 4.2800000000000005e-06,
|
| 29 |
+
"loss": 1.8171,
|
| 30 |
+
"step": 150
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 1.6,
|
| 34 |
+
"grad_norm": 32.81400680541992,
|
| 35 |
+
"learning_rate": 2.28e-06,
|
| 36 |
+
"loss": 1.7688,
|
| 37 |
+
"step": 200
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 2.0,
|
| 41 |
+
"grad_norm": 64.24483489990234,
|
| 42 |
+
"learning_rate": 2.8e-07,
|
| 43 |
+
"loss": 1.7759,
|
| 44 |
+
"step": 250
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 2.0,
|
| 48 |
+
"step": 250,
|
| 49 |
+
"total_flos": 9.4894217943552e+17,
|
| 50 |
+
"train_loss": 1.8031856994628905,
|
| 51 |
+
"train_runtime": 142.4314,
|
| 52 |
+
"train_samples_per_second": 13.944,
|
| 53 |
+
"train_steps_per_second": 1.755
|
| 54 |
+
}
|
| 55 |
+
],
|
| 56 |
+
"logging_steps": 50,
|
| 57 |
+
"max_steps": 250,
|
| 58 |
+
"num_input_tokens_seen": 0,
|
| 59 |
+
"num_train_epochs": 2,
|
| 60 |
+
"save_steps": 200,
|
| 61 |
+
"stateful_callbacks": {
|
| 62 |
+
"TrainerControl": {
|
| 63 |
+
"args": {
|
| 64 |
+
"should_epoch_stop": false,
|
| 65 |
+
"should_evaluate": false,
|
| 66 |
+
"should_log": false,
|
| 67 |
+
"should_save": true,
|
| 68 |
+
"should_training_stop": true
|
| 69 |
+
},
|
| 70 |
+
"attributes": {}
|
| 71 |
+
}
|
| 72 |
+
},
|
| 73 |
+
"total_flos": 9.4894217943552e+17,
|
| 74 |
+
"train_batch_size": 8,
|
| 75 |
+
"trial_name": null,
|
| 76 |
+
"trial_params": null
|
| 77 |
+
}
|