ardaspear commited on
Commit
27cb179
·
verified ·
1 Parent(s): c96b8f8

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 sha256:19b11b2376183e3fb876defa8321707852a50b93cdc05b93e8163e81cf2552d5
3
  size 645975704
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:beab01d89610a52b3862f2e77a6ef3be450bfa3b43dcc6d1a6f904436aa5a31d
3
  size 645975704
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3e7eaa65f1ab49223a1312f005311b26915812cb9040830a10bfd28b78a09ae5
3
  size 328468404
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb9be936ad05cf25e71d007ca6e0e79aa971269a3670b1cc8477c0944677584e
3
  size 328468404
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:df7c7a0477345fa3104ef2f5f202f6d59a77ff7f828a7473f1b48ea42b77cdf9
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e472d8ab49f81694f1178644979fba35dbe5dabefc2f415ac8c406211723d57d
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": 0.00046643422694357315,
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": 16.02,
31
  "eval_steps_per_second": 4.005,
32
  "step": 5
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
33
  }
34
  ],
35
  "logging_steps": 3,
@@ -49,7 +71,7 @@
49
  "attributes": {}
50
  }
51
  },
52
- "total_flos": 5776422784204800.0,
53
  "train_batch_size": 4,
54
  "trial_name": null,
55
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.0009328684538871463,
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": 16.02,
31
  "eval_steps_per_second": 4.005,
32
  "step": 5
33
+ },
34
+ {
35
+ "epoch": 0.0005597210723322877,
36
+ "grad_norm": 5.414619445800781,
37
+ "learning_rate": 6e-05,
38
+ "loss": 5.0959,
39
+ "step": 6
40
+ },
41
+ {
42
+ "epoch": 0.0008395816084984316,
43
+ "grad_norm": 3.53025484085083,
44
+ "learning_rate": 9e-05,
45
+ "loss": 3.4984,
46
+ "step": 9
47
+ },
48
+ {
49
+ "epoch": 0.0009328684538871463,
50
+ "eval_loss": 2.2199866771698,
51
+ "eval_runtime": 1127.2384,
52
+ "eval_samples_per_second": 16.017,
53
+ "eval_steps_per_second": 4.004,
54
+ "step": 10
55
  }
56
  ],
57
  "logging_steps": 3,
 
71
  "attributes": {}
72
  }
73
  },
74
+ "total_flos": 1.19971857825792e+16,
75
  "train_batch_size": 4,
76
  "trial_name": null,
77
  "trial_params": null