Nexspear commited on
Commit
c005134
·
verified ·
1 Parent(s): 43c5ef6

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 sha256:4f3442822b166a69103052feae744998a88c7f025e6c5e899357d0ec5f5ba4fb
3
  size 201892112
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:218c8cf44601c32795abed0ab2628f7678394aa92662230afe1484bca6930b59
3
  size 201892112
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:573468733df07810a8607ea0c5ce9a2beca32ff384f01ee3b7920529635b8d2e
3
  size 102864548
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e64288ec675b5ffa587a7b70c78d2cda495c4b7437141d79a69f823f8b024e34
3
  size 102864548
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f429c8cb11a3ad1395b79b77d408231b1f7f51590e11f713d6605906192503f0
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:359f88406f363fc6c9eb07a6622f1ae622ffd0fa054e681698b03e8645ebf202
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": 0.0023512814483893723,
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": 49.451,
31
  "eval_steps_per_second": 6.185,
32
  "step": 5
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
33
  }
34
  ],
35
  "logging_steps": 3,
@@ -49,7 +71,7 @@
49
  "attributes": {}
50
  }
51
  },
52
- "total_flos": 1066573926236160.0,
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": 0.0047025628967787446,
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": 49.451,
31
  "eval_steps_per_second": 6.185,
32
  "step": 5
33
+ },
34
+ {
35
+ "epoch": 0.0028215377380672465,
36
+ "grad_norm": 0.8181892037391663,
37
+ "learning_rate": 6e-05,
38
+ "loss": 1.2521,
39
+ "step": 6
40
+ },
41
+ {
42
+ "epoch": 0.00423230660710087,
43
+ "grad_norm": 0.6588422060012817,
44
+ "learning_rate": 9e-05,
45
+ "loss": 1.2152,
46
+ "step": 9
47
+ },
48
+ {
49
+ "epoch": 0.0047025628967787446,
50
+ "eval_loss": 1.1770787239074707,
51
+ "eval_runtime": 72.7257,
52
+ "eval_samples_per_second": 49.254,
53
+ "eval_steps_per_second": 6.16,
54
+ "step": 10
55
  }
56
  ],
57
  "logging_steps": 3,
 
71
  "attributes": {}
72
  }
73
  },
74
+ "total_flos": 2133147852472320.0,
75
  "train_batch_size": 8,
76
  "trial_name": null,
77
  "trial_params": null