gavrilstep commited on
Commit
f50670d
·
verified ·
1 Parent(s): 18b50ae

Training in progress, step 20, checkpoint

Browse files
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:94e1b261f896b2732d77065096c5f36bec71f098215a806d86f6a53b24ec40d6
3
  size 335922386
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e12ef96034ad2097f1f42387fd4576db0d8ced23dc7aba4ebd2536cf84b7a3af
3
  size 335922386
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:66b4911e0df8fb18bad039615da17421c8ecf279f4d20538a007939be8f38431
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2fc0af0558fc1c926455d798de9b7d1b8cf007f5ad3184db0e0746a0c75b7a51
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6b28ee0addfe1fdb5c9554035d0aace280dc61b8aded9640b8ddc91a063558e8
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22e67cb47ff12ababb2db5752a0059510ef75c13ebd9ed242d32d1eb2ba8aa08
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 0.012982797792924375,
5
  "eval_steps": 8,
6
- "global_step": 10,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -44,6 +44,35 @@
44
  "learning_rate": 0.00027,
45
  "loss": 0.0,
46
  "step": 9
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
47
  }
48
  ],
49
  "logging_steps": 3,
@@ -63,7 +92,7 @@
63
  "attributes": {}
64
  }
65
  },
66
- "total_flos": 1.582043183972352e+16,
67
  "train_batch_size": 3,
68
  "trial_name": null,
69
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.02596559558584875,
5
  "eval_steps": 8,
6
+ "global_step": 20,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
44
  "learning_rate": 0.00027,
45
  "loss": 0.0,
46
  "step": 9
47
+ },
48
+ {
49
+ "epoch": 0.01557935735150925,
50
+ "grad_norm": NaN,
51
+ "learning_rate": 0.00029265847744427303,
52
+ "loss": 0.0,
53
+ "step": 12
54
+ },
55
+ {
56
+ "epoch": 0.019474196689386564,
57
+ "grad_norm": NaN,
58
+ "learning_rate": 0.00025606601717798207,
59
+ "loss": 0.0,
60
+ "step": 15
61
+ },
62
+ {
63
+ "epoch": 0.020772476468679,
64
+ "eval_loss": NaN,
65
+ "eval_runtime": 107.3747,
66
+ "eval_samples_per_second": 13.597,
67
+ "eval_steps_per_second": 4.536,
68
+ "step": 16
69
+ },
70
+ {
71
+ "epoch": 0.023369036027263874,
72
+ "grad_norm": NaN,
73
+ "learning_rate": 0.0001963525491562421,
74
+ "loss": 0.0,
75
+ "step": 18
76
  }
77
  ],
78
  "logging_steps": 3,
 
92
  "attributes": {}
93
  }
94
  },
95
+ "total_flos": 3.164086367944704e+16,
96
  "train_batch_size": 3,
97
  "trial_name": null,
98
  "trial_params": null