dimasik87 commited on
Commit
052debe
·
verified ·
1 Parent(s): 8393a88

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:aabdf806b6dc8aa08fcc47aa653cd3948303217ffc47cd4409799423b279d04f
3
  size 335922386
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:53590e2d62b9c7c6849c90cf431d1bc80555b8303247bbb4b042a3994b74d366
3
  size 335922386
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3afb383c7427b2624c032eb9cec3a33da0380c9292fc9c147c59c840fa8dd709
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8232c99b3b9bd101763ab8cfa0b9f26a6a08232b451d165ce3fa8ae3b32d33cd
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a62e6ea25099651400ff4a3142a50e40bef5b52ba883be53b2fcb9d1a5b0a98c
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": 0.0036127167630057803,
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": 0.00018,
45
  "loss": 0.0,
46
  "step": 9
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
47
  }
48
  ],
49
  "logging_steps": 3,
@@ -63,7 +92,7 @@
63
  "attributes": {}
64
  }
65
  },
66
- "total_flos": 3515651519938560.0,
67
  "train_batch_size": 2,
68
  "trial_name": null,
69
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.0072254335260115606,
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": 0.00018,
45
  "loss": 0.0,
46
  "step": 9
47
+ },
48
+ {
49
+ "epoch": 0.004335260115606936,
50
+ "grad_norm": NaN,
51
+ "learning_rate": 0.00019510565162951537,
52
+ "loss": 0.0,
53
+ "step": 12
54
+ },
55
+ {
56
+ "epoch": 0.00541907514450867,
57
+ "grad_norm": NaN,
58
+ "learning_rate": 0.00017071067811865476,
59
+ "loss": 0.0,
60
+ "step": 15
61
+ },
62
+ {
63
+ "epoch": 0.005780346820809248,
64
+ "eval_loss": NaN,
65
+ "eval_runtime": 67.7288,
66
+ "eval_samples_per_second": 17.216,
67
+ "eval_steps_per_second": 8.608,
68
+ "step": 16
69
+ },
70
+ {
71
+ "epoch": 0.006502890173410405,
72
+ "grad_norm": NaN,
73
+ "learning_rate": 0.00013090169943749476,
74
+ "loss": 0.0,
75
+ "step": 18
76
  }
77
  ],
78
  "logging_steps": 3,
 
92
  "attributes": {}
93
  }
94
  },
95
+ "total_flos": 7119194327875584.0,
96
  "train_batch_size": 2,
97
  "trial_name": null,
98
  "trial_params": null