adammandic87 commited on
Commit
aa32e96
·
verified ·
1 Parent(s): 6629e05

Training in progress, step 39, 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:e0478b3c2a15ee2dd84fae855a26f587e719980b72028492941fd99f66810b37
3
  size 125248064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b9016285e1f31231898eb518172873cc78658cc614a66dba64b8515e134bd862
3
  size 125248064
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8d5769d552778381545fc4746fba9fa23587d42cb391d3c7a1558848d4343058
3
  size 64219860
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:397a2770f026b07ba8f908a07b4515b95e3208b81b6d55a2b496485931a90bd6
3
  size 64219860
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:02cfb08abee12b17337b98567ba9f28dd70ea9e907b1536d2d444555c87a1e6f
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:354fcbfab35beb320321fc72abe28e2ba17d63b820a2c10b34cfe337af85be52
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:59af5f5d66ecb18e9abb84f5d5074a625502d490e59b29de1e9974286a967cbf
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:216e1a9a1c53e7de93f56319b4855910155cb98dd7ebb5fa08b3717fd303059f
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": 0.007267137167214032,
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,
@@ -45,6 +45,21 @@
45
  "eval_samples_per_second": 20.604,
46
  "eval_steps_per_second": 10.309,
47
  "step": 26
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
48
  }
49
  ],
50
  "logging_steps": 10,
@@ -64,7 +79,7 @@
64
  "attributes": {}
65
  }
66
  },
67
- "total_flos": 8232134120570880.0,
68
  "train_batch_size": 2,
69
  "trial_name": null,
70
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.010900705750821046,
5
  "eval_steps": 13,
6
+ "global_step": 39,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
45
  "eval_samples_per_second": 20.604,
46
  "eval_steps_per_second": 10.309,
47
  "step": 26
48
+ },
49
+ {
50
+ "epoch": 0.008385158269862344,
51
+ "grad_norm": 2.1668341159820557,
52
+ "learning_rate": 8.263518223330697e-05,
53
+ "loss": 0.7354,
54
+ "step": 30
55
+ },
56
+ {
57
+ "epoch": 0.010900705750821046,
58
+ "eval_loss": 0.48577263951301575,
59
+ "eval_runtime": 73.1489,
60
+ "eval_samples_per_second": 20.602,
61
+ "eval_steps_per_second": 10.308,
62
+ "step": 39
63
  }
64
  ],
65
  "logging_steps": 10,
 
79
  "attributes": {}
80
  }
81
  },
82
+ "total_flos": 1.234820118085632e+16,
83
  "train_batch_size": 2,
84
  "trial_name": null,
85
  "trial_params": null