End of training
Browse files- all_results.json +9 -0
- train_results.json +9 -0
- trainer_state.json +71 -0
all_results.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 2.0,
|
3 |
+
"total_flos": 2.898875076784947e+16,
|
4 |
+
"train_loss": 0.1999838718148165,
|
5 |
+
"train_runtime": 196.4851,
|
6 |
+
"train_samples": 55000,
|
7 |
+
"train_samples_per_second": 559.839,
|
8 |
+
"train_steps_per_second": 2.188
|
9 |
+
}
|
train_results.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 2.0,
|
3 |
+
"total_flos": 2.898875076784947e+16,
|
4 |
+
"train_loss": 0.1999838718148165,
|
5 |
+
"train_runtime": 196.4851,
|
6 |
+
"train_samples": 55000,
|
7 |
+
"train_samples_per_second": 559.839,
|
8 |
+
"train_steps_per_second": 2.188
|
9 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,71 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.0,
|
3 |
+
"best_model_checkpoint": "logs/eurlex/roberta-base/seed_1/checkpoint-215",
|
4 |
+
"epoch": 2.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 430,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 1.0,
|
13 |
+
"eval_loss": 0.17694051563739777,
|
14 |
+
"eval_macro-f1": 0.0,
|
15 |
+
"eval_micro-f1": 0.0,
|
16 |
+
"eval_runtime": 3.944,
|
17 |
+
"eval_samples_per_second": 1267.741,
|
18 |
+
"eval_steps_per_second": 5.071,
|
19 |
+
"step": 215
|
20 |
+
},
|
21 |
+
{
|
22 |
+
"epoch": 2.0,
|
23 |
+
"eval_loss": 0.17320719361305237,
|
24 |
+
"eval_macro-f1": 0.0,
|
25 |
+
"eval_micro-f1": 0.0,
|
26 |
+
"eval_runtime": 3.964,
|
27 |
+
"eval_samples_per_second": 1261.34,
|
28 |
+
"eval_steps_per_second": 5.045,
|
29 |
+
"step": 430
|
30 |
+
},
|
31 |
+
{
|
32 |
+
"epoch": 2.0,
|
33 |
+
"step": 430,
|
34 |
+
"total_flos": 2.898875076784947e+16,
|
35 |
+
"train_loss": 0.1999838718148165,
|
36 |
+
"train_runtime": 196.4851,
|
37 |
+
"train_samples_per_second": 559.839,
|
38 |
+
"train_steps_per_second": 2.188
|
39 |
+
}
|
40 |
+
],
|
41 |
+
"logging_steps": 500,
|
42 |
+
"max_steps": 430,
|
43 |
+
"num_input_tokens_seen": 0,
|
44 |
+
"num_train_epochs": 2,
|
45 |
+
"save_steps": 500,
|
46 |
+
"stateful_callbacks": {
|
47 |
+
"EarlyStoppingCallback": {
|
48 |
+
"args": {
|
49 |
+
"early_stopping_patience": 3,
|
50 |
+
"early_stopping_threshold": 0.0
|
51 |
+
},
|
52 |
+
"attributes": {
|
53 |
+
"early_stopping_patience_counter": 0
|
54 |
+
}
|
55 |
+
},
|
56 |
+
"TrainerControl": {
|
57 |
+
"args": {
|
58 |
+
"should_epoch_stop": false,
|
59 |
+
"should_evaluate": false,
|
60 |
+
"should_log": false,
|
61 |
+
"should_save": true,
|
62 |
+
"should_training_stop": true
|
63 |
+
},
|
64 |
+
"attributes": {}
|
65 |
+
}
|
66 |
+
},
|
67 |
+
"total_flos": 2.898875076784947e+16,
|
68 |
+
"train_batch_size": 128,
|
69 |
+
"trial_name": null,
|
70 |
+
"trial_params": null
|
71 |
+
}
|