tlkh commited on
Commit
5002684
1 Parent(s): c2c3394

Updated weights

Browse files
all_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
- "epoch": 4.0,
3
- "train_loss": 0.3329931234673552,
4
- "train_runtime": 29997.8117,
5
- "train_samples": 20570,
6
- "train_samples_per_second": 2.743,
7
- "train_steps_per_second": 0.343
8
  }
 
1
  {
2
+ "epoch": 2.0,
3
+ "train_loss": 0.8575281141719833,
4
+ "train_runtime": 49942.9507,
5
+ "train_samples": 72734,
6
+ "train_samples_per_second": 2.913,
7
+ "train_steps_per_second": 0.364
8
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2f262ea9df8f665326b842bc36f068da8d181fbf1d0b128794e406351892eb2b
3
  size 5312750093
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c0bb060f3933c45920f1f9536c9587bc81b5a85b5912c953b74744519fa19a34
3
  size 5312750093
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
- "epoch": 4.0,
3
- "train_loss": 0.3329931234673552,
4
- "train_runtime": 29997.8117,
5
- "train_samples": 20570,
6
- "train_samples_per_second": 2.743,
7
- "train_steps_per_second": 0.343
8
  }
 
1
  {
2
+ "epoch": 2.0,
3
+ "train_loss": 0.8575281141719833,
4
+ "train_runtime": 49942.9507,
5
+ "train_samples": 72734,
6
+ "train_samples_per_second": 2.913,
7
+ "train_steps_per_second": 0.364
8
  }
trainer_state.json CHANGED
@@ -1,81 +1,53 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 3.9999027710257655,
5
- "global_step": 10284,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
9
  "log_history": [
10
  {
11
  "epoch": 1.0,
12
- "learning_rate": 7.500000000000001e-06,
13
- "loss": 0.5574,
14
- "step": 2571
15
  },
16
  {
17
  "epoch": 1.0,
18
- "eval_loss": 0.37848538160324097,
19
- "eval_runtime": 338.4836,
20
- "eval_samples_per_second": 6.677,
21
- "eval_steps_per_second": 6.677,
22
- "step": 2571
23
  },
24
  {
25
  "epoch": 2.0,
26
- "learning_rate": 5.00194476857254e-06,
27
- "loss": 0.3059,
28
- "step": 5142
29
  },
30
  {
31
  "epoch": 2.0,
32
- "eval_loss": 0.30628740787506104,
33
- "eval_runtime": 338.8936,
34
- "eval_samples_per_second": 6.669,
35
- "eval_steps_per_second": 6.669,
36
- "step": 5142
37
  },
38
  {
39
- "epoch": 3.0,
40
- "learning_rate": 2.50194476857254e-06,
41
- "loss": 0.2494,
42
- "step": 7713
43
- },
44
- {
45
- "epoch": 3.0,
46
- "eval_loss": 0.2887383997440338,
47
- "eval_runtime": 339.1381,
48
- "eval_samples_per_second": 6.664,
49
- "eval_steps_per_second": 6.664,
50
- "step": 7713
51
- },
52
- {
53
- "epoch": 4.0,
54
- "learning_rate": 1.9447685725398677e-09,
55
- "loss": 0.2192,
56
- "step": 10284
57
- },
58
- {
59
- "epoch": 4.0,
60
- "eval_loss": 0.2874472737312317,
61
- "eval_runtime": 339.3338,
62
- "eval_samples_per_second": 6.66,
63
- "eval_steps_per_second": 6.66,
64
- "step": 10284
65
- },
66
- {
67
- "epoch": 4.0,
68
- "step": 10284,
69
- "total_flos": 6.108934613772534e+17,
70
- "train_loss": 0.3329931234673552,
71
- "train_runtime": 29997.8117,
72
- "train_samples_per_second": 2.743,
73
- "train_steps_per_second": 0.343
74
  }
75
  ],
76
- "max_steps": 10284,
77
- "num_train_epochs": 4,
78
- "total_flos": 6.108934613772534e+17,
79
  "trial_name": null,
80
  "trial_params": null
81
  }
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 1.9999175076305442,
5
+ "global_step": 18182,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
9
  "log_history": [
10
  {
11
  "epoch": 1.0,
12
+ "learning_rate": 5.000549994500056e-06,
13
+ "loss": 0.9118,
14
+ "step": 9091
15
  },
16
  {
17
  "epoch": 1.0,
18
+ "eval_loss": 0.8586767315864563,
19
+ "eval_runtime": 1119.8237,
20
+ "eval_samples_per_second": 7.183,
21
+ "eval_steps_per_second": 7.183,
22
+ "step": 9091
23
  },
24
  {
25
  "epoch": 2.0,
26
+ "learning_rate": 3.2999670003299967e-09,
27
+ "loss": 0.8033,
28
+ "step": 18182
29
  },
30
  {
31
  "epoch": 2.0,
32
+ "eval_loss": 0.8357626795768738,
33
+ "eval_runtime": 1139.4211,
34
+ "eval_samples_per_second": 7.06,
35
+ "eval_steps_per_second": 7.06,
36
+ "step": 18182
37
  },
38
  {
39
+ "epoch": 2.0,
40
+ "step": 18182,
41
+ "total_flos": 1.0800187738989527e+18,
42
+ "train_loss": 0.8575281141719833,
43
+ "train_runtime": 49942.9507,
44
+ "train_samples_per_second": 2.913,
45
+ "train_steps_per_second": 0.364
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
46
  }
47
  ],
48
+ "max_steps": 18182,
49
+ "num_train_epochs": 2,
50
+ "total_flos": 1.0800187738989527e+18,
51
  "trial_name": null,
52
  "trial_params": null
53
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4b831bc7f6412d45e31fc72354fb0af17de6f851bcef6bfd84ff9bb535903229
3
- size 3567
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6080be0eca2944f3ed18c2e01e9b2bca0ce11eea2eb48800c638b68deec9f977
3
+ size 3631