shibajustfor commited on
Commit
2c6ebd7
·
verified ·
1 Parent(s): df2f2ac

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 sha256:5e992d7ffe7a8558b35818ab3f95e52c217a75bb20c81be3ac973712c08006bf
3
  size 100059752
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0586490fbc5484ba43050565017deddd8704367fc684c7a306ad6f14d93cdf2f
3
  size 100059752
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7638cffaa6f47a002caa182d9817adff74254ef8a89cfb73a18044cc2dfa0665
3
  size 51244020
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:52ed578e7732f37ad703f496165158d88ee261835da675f8baf4b0a2da61999e
3
  size 51244020
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9fb619c020e84cbcdb558e07165cb0a310cb5ef5dd3db209892cfb268346fbb6
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:413c2acc7eea6176a73d0cbe494456450e343301052fed2289eb3a7b9b3d8b3f
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": 0.0005232414809746379,
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": 24.058,
46
  "eval_steps_per_second": 12.029,
47
  "step": 26
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
48
  }
49
  ],
50
  "logging_steps": 10,
@@ -64,7 +79,7 @@
64
  "attributes": {}
65
  }
66
  },
67
- "total_flos": 6115492532060160.0,
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": 0.0007848622214619568,
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": 24.058,
46
  "eval_steps_per_second": 12.029,
47
  "step": 26
48
+ },
49
+ {
50
+ "epoch": 0.0006037401703553514,
51
+ "grad_norm": 0.6607839465141296,
52
+ "learning_rate": 8.263518223330697e-05,
53
+ "loss": 1.2162,
54
+ "step": 30
55
+ },
56
+ {
57
+ "epoch": 0.0007848622214619568,
58
+ "eval_loss": 1.4915814399719238,
59
+ "eval_runtime": 870.7377,
60
+ "eval_samples_per_second": 24.029,
61
+ "eval_steps_per_second": 12.015,
62
+ "step": 39
63
  }
64
  ],
65
  "logging_steps": 10,
 
79
  "attributes": {}
80
  }
81
  },
82
+ "total_flos": 9029906941870080.0,
83
  "train_batch_size": 2,
84
  "trial_name": null,
85
  "trial_params": null