samoline commited on
Commit
c095bb2
·
verified ·
1 Parent(s): 9842de9

Training in progress, step 2, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2e107a660eeb6a58ad5b7f4e105897950b64f8efb5b73b65d917371f0ef7a5ef
3
  size 14194992
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:25f784a1c90e4cf7e9b507caf159f2767bc1094e9447ee88eacdf23bd8a3bab3
3
  size 14194992
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:370f26c8a01a9200ff72869de033ab321b79aa9fd1d633379e9598b2ab34f570
3
  size 7525204
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c69e5b5012858a1995f5c5cd13fd34fe7622fae022f560680597a5d2e923ca9
3
  size 7525204
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4300da514a99c2823d6f25df4bbb8e4590ee5b62eb8152c5e99f3cc495b6078c
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:67c80ba702e0383c0c611edab20d5886bd99dc38ac83d1611b9f1e996af13a14
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:764cf599d0b83c5d302be0978d09e435a466a8511dc1f7e86d5ee3704818d46f
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a2972d8cacb091bd0e98bfff54b2e4933301753087ce149a9bf9a205a5e2d795
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": 1.058985491898761e-05,
5
  "eval_steps": 1,
6
- "global_step": 1,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -22,6 +22,21 @@
22
  "eval_samples_per_second": 23.074,
23
  "eval_steps_per_second": 23.074,
24
  "step": 1
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
25
  }
26
  ],
27
  "logging_steps": 1,
@@ -36,12 +51,12 @@
36
  "should_evaluate": false,
37
  "should_log": false,
38
  "should_save": true,
39
- "should_training_stop": false
40
  },
41
  "attributes": {}
42
  }
43
  },
44
- "total_flos": 7447397793792.0,
45
  "train_batch_size": 1,
46
  "trial_name": null,
47
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 2.117970983797522e-05,
5
  "eval_steps": 1,
6
+ "global_step": 2,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
22
  "eval_samples_per_second": 23.074,
23
  "eval_steps_per_second": 23.074,
24
  "step": 1
25
+ },
26
+ {
27
+ "epoch": 2.117970983797522e-05,
28
+ "grad_norm": 0.5196658372879028,
29
+ "learning_rate": 4e-05,
30
+ "loss": 2.4762,
31
+ "step": 2
32
+ },
33
+ {
34
+ "epoch": 2.117970983797522e-05,
35
+ "eval_loss": 2.691673755645752,
36
+ "eval_runtime": 213.1666,
37
+ "eval_samples_per_second": 23.315,
38
+ "eval_steps_per_second": 23.315,
39
+ "step": 2
40
  }
41
  ],
42
  "logging_steps": 1,
 
51
  "should_evaluate": false,
52
  "should_log": false,
53
  "should_save": true,
54
+ "should_training_stop": true
55
  },
56
  "attributes": {}
57
  }
58
  },
59
+ "total_flos": 11171096690688.0,
60
  "train_batch_size": 1,
61
  "trial_name": null,
62
  "trial_params": null