jnmrr commited on
Commit
aa43e0c
·
verified ·
1 Parent(s): 71517e8

End of training

Browse files
Files changed (3) hide show
  1. all_results.json +8 -0
  2. train_results.json +8 -0
  3. trainer_state.json +74 -0
all_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 0.9855072463768116,
3
+ "total_flos": 1.686437022030889e+17,
4
+ "train_loss": 1.278389811515808,
5
+ "train_runtime": 157.5351,
6
+ "train_samples_per_second": 13.933,
7
+ "train_steps_per_second": 0.108
8
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 0.9855072463768116,
3
+ "total_flos": 1.686437022030889e+17,
4
+ "train_loss": 1.278389811515808,
5
+ "train_runtime": 157.5351,
6
+ "train_samples_per_second": 13.933,
7
+ "train_steps_per_second": 0.108
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,74 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.4713114754098361,
3
+ "best_model_checkpoint": "doc-img-classification/checkpoint-17",
4
+ "epoch": 0.9855072463768116,
5
+ "eval_steps": 500,
6
+ "global_step": 17,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.057971014492753624,
13
+ "grad_norm": 5.505029678344727,
14
+ "learning_rate": 0.0005,
15
+ "loss": 1.1994,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.6956521739130435,
20
+ "grad_norm": 2.7396085262298584,
21
+ "learning_rate": 0.0003333333333333333,
22
+ "loss": 1.368,
23
+ "step": 12
24
+ },
25
+ {
26
+ "epoch": 0.9855072463768116,
27
+ "eval_Macro F1": 0.40616472075035376,
28
+ "eval_Macro Precision": 0.5783758769965667,
29
+ "eval_Macro Recall": 0.4887518477457502,
30
+ "eval_Micro F1": 0.4713114754098361,
31
+ "eval_Micro Precision": 0.4713114754098361,
32
+ "eval_Micro Recall": 0.4713114754098361,
33
+ "eval_Weighted F1": 0.3905898342459797,
34
+ "eval_Weighted Precision": 0.5995358005476717,
35
+ "eval_Weighted Recall": 0.4713114754098361,
36
+ "eval_accuracy": 0.4713114754098361,
37
+ "eval_loss": 1.069409728050232,
38
+ "eval_runtime": 12.9224,
39
+ "eval_samples_per_second": 18.882,
40
+ "eval_steps_per_second": 0.619,
41
+ "step": 17
42
+ },
43
+ {
44
+ "epoch": 0.9855072463768116,
45
+ "step": 17,
46
+ "total_flos": 1.686437022030889e+17,
47
+ "train_loss": 1.278389811515808,
48
+ "train_runtime": 157.5351,
49
+ "train_samples_per_second": 13.933,
50
+ "train_steps_per_second": 0.108
51
+ }
52
+ ],
53
+ "logging_steps": 12,
54
+ "max_steps": 17,
55
+ "num_input_tokens_seen": 0,
56
+ "num_train_epochs": 1,
57
+ "save_steps": 500,
58
+ "stateful_callbacks": {
59
+ "TrainerControl": {
60
+ "args": {
61
+ "should_epoch_stop": false,
62
+ "should_evaluate": false,
63
+ "should_log": false,
64
+ "should_save": true,
65
+ "should_training_stop": true
66
+ },
67
+ "attributes": {}
68
+ }
69
+ },
70
+ "total_flos": 1.686437022030889e+17,
71
+ "train_batch_size": 32,
72
+ "trial_name": null,
73
+ "trial_params": null
74
+ }