ardaspear commited on
Commit
67bcf90
·
verified ·
1 Parent(s): 47d08cd

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 sha256:375a8688cf4e38539dcb1f42ce8277c7e67bf4a4ce8735ecba8d89a0da4795c3
3
  size 201892112
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eebc945d9b883655db1b224e7846e86a3c885ca31652323c1a261d4a94e6a58a
3
  size 201892112
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bb94e8442c9f358b3894bb60f7f887a25d910d731709442985f42ea3a5e25ec0
3
  size 102864548
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1864a564fa619425a9f29b261e5edabd8d2f140eb88e4bb05ef3dbe83653f649
3
  size 102864548
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6f89ccb70ce55c299bb933977d267a495c00ac5ea171676a9b7fa3fd6cff25e3
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:31a8059683c2b5138637352137e92dbf364cfc59afc90c9e7a10fafdb11fceed
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": 0.0008753118298393803,
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": 23.643,
31
  "eval_steps_per_second": 2.956,
32
  "step": 5
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
33
  }
34
  ],
35
  "logging_steps": 3,
@@ -49,7 +71,7 @@
49
  "attributes": {}
50
  }
51
  },
52
- "total_flos": 2133147852472320.0,
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": 0.0017506236596787606,
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": 23.643,
31
  "eval_steps_per_second": 2.956,
32
  "step": 5
33
+ },
34
+ {
35
+ "epoch": 0.0010503741958072562,
36
+ "grad_norm": 50.95747375488281,
37
+ "learning_rate": 6e-05,
38
+ "loss": 4.875,
39
+ "step": 6
40
+ },
41
+ {
42
+ "epoch": 0.0015755612937108845,
43
+ "grad_norm": 10.002364158630371,
44
+ "learning_rate": 9e-05,
45
+ "loss": 3.2756,
46
+ "step": 9
47
+ },
48
+ {
49
+ "epoch": 0.0017506236596787606,
50
+ "eval_loss": 2.5834808349609375,
51
+ "eval_runtime": 406.3149,
52
+ "eval_samples_per_second": 23.679,
53
+ "eval_steps_per_second": 2.961,
54
+ "step": 10
55
  }
56
  ],
57
  "logging_steps": 3,
 
71
  "attributes": {}
72
  }
73
  },
74
+ "total_flos": 4266295704944640.0,
75
  "train_batch_size": 8,
76
  "trial_name": null,
77
  "trial_params": null