kk-aivio commited on
Commit
c3e733c
·
verified ·
1 Parent(s): 70b8b88

Training in progress, step 26, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:52e8755165305e43500c8b088337b16698da2249d22d9f98a9fea6406d85f099
3
  size 47235968
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5abae79191be6b78b8961f9b230e56f289dc4eb02ca7e78880d4fd4f4e922460
3
  size 47235968
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7c001678e1fb6a37153da2ae1c68ebc6eb8add80b6d95ef1e3ba2b93bdb9a539
3
  size 24410836
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4aab36ed1daafd83e304cc46429c93dfb72984ecf7a0138fe84f1cb7bcf49898
3
  size 24410836
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fb455e15592227d8eaf1e43a4199dbb8af98056c0db1d63586f65087ae172d1c
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:20fabbd3530b65abbae13570a3d6b6023989d569ba9d0b8340cc65b704944cb0
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fec74e92563bbe4b510ec939dc1c78d591826119d26043cc49e0a868b67121a2
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:59af5f5d66ecb18e9abb84f5d5074a625502d490e59b29de1e9974286a967cbf
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": 0.0021938151288866388,
5
  "eval_steps": 13,
6
- "global_step": 13,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -30,6 +30,21 @@
30
  "eval_samples_per_second": 44.124,
31
  "eval_steps_per_second": 22.071,
32
  "step": 13
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
33
  }
34
  ],
35
  "logging_steps": 10,
@@ -49,7 +64,7 @@
49
  "attributes": {}
50
  }
51
  },
52
- "total_flos": 849968533340160.0,
53
  "train_batch_size": 2,
54
  "trial_name": null,
55
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.0043876302577732776,
5
  "eval_steps": 13,
6
+ "global_step": 26,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
30
  "eval_samples_per_second": 44.124,
31
  "eval_steps_per_second": 22.071,
32
  "step": 13
33
+ },
34
+ {
35
+ "epoch": 0.0033751001982871365,
36
+ "grad_norm": 5.268524169921875,
37
+ "learning_rate": 0.00015000000000000001,
38
+ "loss": 1.5099,
39
+ "step": 20
40
+ },
41
+ {
42
+ "epoch": 0.0043876302577732776,
43
+ "eval_loss": 1.3147406578063965,
44
+ "eval_runtime": 56.6894,
45
+ "eval_samples_per_second": 44.012,
46
+ "eval_steps_per_second": 22.015,
47
+ "step": 26
48
  }
49
  ],
50
  "logging_steps": 10,
 
64
  "attributes": {}
65
  }
66
  },
67
+ "total_flos": 1699937066680320.0,
68
  "train_batch_size": 2,
69
  "trial_name": null,
70
  "trial_params": null