ardaspear commited on
Commit
0c29c7a
·
verified ·
1 Parent(s): 6fa46ae

Training in progress, step 10, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3de2ab81d4e59954d2b6be5ab285012934b7355091cd0dbe65ab05f89a376256
3
  size 2373352
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c2ccff7ededc6e01ea1ae33064ce4e51cc953bc0ed479da8a5a0c8adfb9aebee
3
  size 2373352
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e9da05d88e4c27f6c8e715d8f44fbe39684b5ba0b36a8068986baf839e969bba
3
  size 4830714
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:86343d0c02e42f3997efd0b445ab1d7f216017cc295f11dd418c7c9cc228b55f
3
  size 4830714
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0190c48acbac7fba03c62e2a2a9df68f5df9c200ead69af6631aa7c118ff881b
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b2ac488ce1f441ca1ae6806867cc0d824ea5a04d174d746efdffa5a728cba642
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2d63217b923cb177f669d6bc2174b89abdc6a56d968d279b505491b37976d9bb
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b4849a6ac0a1d895740f1ab4eba9d346b8d898008d0cfe93dd108cd928d7c63e
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": 0.0029476787030213707,
5
  "eval_steps": 5,
6
- "global_step": 5,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -30,6 +30,28 @@
30
  "eval_samples_per_second": 134.675,
31
  "eval_steps_per_second": 16.876,
32
  "step": 5
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
33
  }
34
  ],
35
  "logging_steps": 3,
@@ -49,7 +71,7 @@
49
  "attributes": {}
50
  }
51
  },
52
- "total_flos": 5508956160000.0,
53
  "train_batch_size": 8,
54
  "trial_name": null,
55
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.0058953574060427415,
5
  "eval_steps": 5,
6
+ "global_step": 10,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
30
  "eval_samples_per_second": 134.675,
31
  "eval_steps_per_second": 16.876,
32
  "step": 5
33
+ },
34
+ {
35
+ "epoch": 0.003537214443625645,
36
+ "grad_norm": 0.31879347562789917,
37
+ "learning_rate": 6e-05,
38
+ "loss": 11.9335,
39
+ "step": 6
40
+ },
41
+ {
42
+ "epoch": 0.005305821665438467,
43
+ "grad_norm": 0.3556462526321411,
44
+ "learning_rate": 9e-05,
45
+ "loss": 11.9286,
46
+ "step": 9
47
+ },
48
+ {
49
+ "epoch": 0.0058953574060427415,
50
+ "eval_loss": 11.923737525939941,
51
+ "eval_runtime": 21.1557,
52
+ "eval_samples_per_second": 135.047,
53
+ "eval_steps_per_second": 16.922,
54
+ "step": 10
55
  }
56
  ],
57
  "logging_steps": 3,
 
71
  "attributes": {}
72
  }
73
  },
74
+ "total_flos": 11017912320000.0,
75
  "train_batch_size": 8,
76
  "trial_name": null,
77
  "trial_params": null