Hugging Face's logo

nlparabic
/
test-egy_aragpt

Safetensors
gpt2
Generated from Trainer
Model card Files Community
nlparabic commited on
Commit
71919df
·
verified ·
1 Parent(s): bb3eb2c

End of training

Browse files
Files changed (4) hide show
  1. all_results.json +15 -12
  2. eval_results.json +10 -7
  3. train_results.json +6 -6
  4. trainer_state.json +42 -14
all_results.json CHANGED
@@ -1,16 +1,19 @@
1
  {
2
- "epoch": 1.0,
3
- "eval_bleu": 0.10603800831832183,
4
- "eval_loss": 3.326219081878662,
5
- "eval_runtime": 15.6341,
 
 
 
6
  "eval_samples": 847,
7
- "eval_samples_per_second": 54.177,
8
- "eval_steps_per_second": 6.78,
9
- "perplexity": 27.832908563445223,
10
- "total_flos": 1000225898496000.0,
11
- "train_loss": 3.812888405539773,
12
- "train_runtime": 118.532,
13
  "train_samples": 2552,
14
- "train_samples_per_second": 21.53,
15
- "train_steps_per_second": 2.691
16
  }
 
1
  {
2
+ "epoch": 2.0,
3
+ "eval_bleu": 0.11424056852356153,
4
+ "eval_loss": 3.128293514251709,
5
+ "eval_rouge1": 0.3297614987151056,
6
+ "eval_rouge2": 0.08429294540985294,
7
+ "eval_rougeL": 0.2561476738686219,
8
+ "eval_runtime": 26.9033,
9
  "eval_samples": 847,
10
+ "eval_samples_per_second": 31.483,
11
+ "eval_steps_per_second": 3.94,
12
+ "perplexity": 22.834978708992665,
13
+ "total_flos": 2000451796992000.0,
14
+ "train_loss": 4.0498331004175645,
15
+ "train_runtime": 264.5821,
16
  "train_samples": 2552,
17
+ "train_samples_per_second": 19.291,
18
+ "train_steps_per_second": 2.411
19
  }
eval_results.json CHANGED
@@ -1,10 +1,13 @@
1
  {
2
- "epoch": 1.0,
3
- "eval_bleu": 0.10603800831832183,
4
- "eval_loss": 3.326219081878662,
5
- "eval_runtime": 15.6341,
 
 
 
6
  "eval_samples": 847,
7
- "eval_samples_per_second": 54.177,
8
- "eval_steps_per_second": 6.78,
9
- "perplexity": 27.832908563445223
10
  }
 
1
  {
2
+ "epoch": 2.0,
3
+ "eval_bleu": 0.11424056852356153,
4
+ "eval_loss": 3.128293514251709,
5
+ "eval_rouge1": 0.3297614987151056,
6
+ "eval_rouge2": 0.08429294540985294,
7
+ "eval_rougeL": 0.2561476738686219,
8
+ "eval_runtime": 26.9033,
9
  "eval_samples": 847,
10
+ "eval_samples_per_second": 31.483,
11
+ "eval_steps_per_second": 3.94,
12
+ "perplexity": 22.834978708992665
13
  }
train_results.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "epoch": 1.0,
3
- "total_flos": 1000225898496000.0,
4
- "train_loss": 3.812888405539773,
5
- "train_runtime": 118.532,
6
  "train_samples": 2552,
7
- "train_samples_per_second": 21.53,
8
- "train_steps_per_second": 2.691
9
  }
 
1
  {
2
+ "epoch": 2.0,
3
+ "total_flos": 2000451796992000.0,
4
+ "train_loss": 4.0498331004175645,
5
+ "train_runtime": 264.5821,
6
  "train_samples": 2552,
7
+ "train_samples_per_second": 19.291,
8
+ "train_steps_per_second": 2.411
9
  }
trainer_state.json CHANGED
@@ -1,29 +1,57 @@
1
  {
2
- "best_metric": null,
3
- "best_model_checkpoint": null,
4
- "epoch": 1.0,
5
  "eval_steps": 500,
6
- "global_step": 319,
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
- "step": 319,
14
- "total_flos": 1000225898496000.0,
15
- "train_loss": 3.812888405539773,
16
- "train_runtime": 118.532,
17
- "train_samples_per_second": 21.53,
18
- "train_steps_per_second": 2.691
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
19
  }
20
  ],
21
  "logging_steps": 500,
22
- "max_steps": 319,
23
  "num_input_tokens_seen": 0,
24
- "num_train_epochs": 1,
25
  "save_steps": 500,
26
  "stateful_callbacks": {
 
 
 
 
 
 
 
 
 
27
  "TrainerControl": {
28
  "args": {
29
  "should_epoch_stop": false,
@@ -35,7 +63,7 @@
35
  "attributes": {}
36
  }
37
  },
38
- "total_flos": 1000225898496000.0,
39
  "train_batch_size": 8,
40
  "trial_name": null,
41
  "trial_params": null
 
1
  {
2
+ "best_metric": 3.128293514251709,
3
+ "best_model_checkpoint": "/tmp/test-egy_aragpt/checkpoint-500",
4
+ "epoch": 2.0,
5
  "eval_steps": 500,
6
+ "global_step": 638,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
10
  "log_history": [
11
  {
12
+ "epoch": 1.567398119122257,
13
+ "grad_norm": 1.3536421060562134,
14
+ "learning_rate": 5e-05,
15
+ "loss": 4.3013,
16
+ "step": 500
17
+ },
18
+ {
19
+ "epoch": 1.567398119122257,
20
+ "eval_bleu": 0.11424056852356153,
21
+ "eval_loss": 3.128293514251709,
22
+ "eval_rouge1": 0.3297614987151056,
23
+ "eval_rouge2": 0.08429294540985294,
24
+ "eval_rougeL": 0.2561476738686219,
25
+ "eval_runtime": 27.454,
26
+ "eval_samples_per_second": 30.852,
27
+ "eval_steps_per_second": 3.861,
28
+ "step": 500
29
+ },
30
+ {
31
+ "epoch": 2.0,
32
+ "step": 638,
33
+ "total_flos": 2000451796992000.0,
34
+ "train_loss": 4.0498331004175645,
35
+ "train_runtime": 264.5821,
36
+ "train_samples_per_second": 19.291,
37
+ "train_steps_per_second": 2.411
38
  }
39
  ],
40
  "logging_steps": 500,
41
+ "max_steps": 638,
42
  "num_input_tokens_seen": 0,
43
+ "num_train_epochs": 2,
44
  "save_steps": 500,
45
  "stateful_callbacks": {
46
+ "EarlyStoppingCallback": {
47
+ "args": {
48
+ "early_stopping_patience": 3,
49
+ "early_stopping_threshold": 0.0
50
+ },
51
+ "attributes": {
52
+ "early_stopping_patience_counter": 0
53
+ }
54
+ },
55
  "TrainerControl": {
56
  "args": {
57
  "should_epoch_stop": false,
 
63
  "attributes": {}
64
  }
65
  },
66
+ "total_flos": 2000451796992000.0,
67
  "train_batch_size": 8,
68
  "trial_name": null,
69
  "trial_params": null