lesso commited on
Commit
030a137
·
verified ·
1 Parent(s): 5218f2c

Training in progress, step 6, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9bdf912a81a8c6f951dcf34001e5cf73bd020115bca0a3daa8584634441b76e3
3
  size 767856
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:acae508858dd3e461721fc512b8fa6e6bff8ae03f0d5387d34d691d3573023c3
3
  size 767856
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2f1dcdd15b76db955d741278ad8d3bb95ed70ae1a383dc22f3106f81f9ee933f
3
  size 1003002
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f475e9a613b138efd5f93385ab70af8135ea7cd389b55dd228d75468933d2ea
3
  size 1003002
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b57c7f5d43bf7daadabf2da6f96b4632b95a7e7bde83c3e8f0cb2baea8f08d40
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f146e771caadf61177d3f4ac41547e6e67b9b4f5456644cb35680903e92b1413
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ffd8c58e5d02492554dbaa495f8cf80dff41fabc0e1288cb2fd18a103d402219
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
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": 0.0005186273662373585,
5
  "eval_steps": 3,
6
- "global_step": 3,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -44,6 +44,35 @@
44
  "eval_samples_per_second": 24.247,
45
  "eval_steps_per_second": 12.123,
46
  "step": 3
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
47
  }
48
  ],
49
  "logging_steps": 1,
@@ -63,7 +92,7 @@
63
  "attributes": {}
64
  }
65
  },
66
- "total_flos": 1628971204608.0,
67
  "train_batch_size": 2,
68
  "trial_name": null,
69
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.001037254732474717,
5
  "eval_steps": 3,
6
+ "global_step": 6,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
44
  "eval_samples_per_second": 24.247,
45
  "eval_steps_per_second": 12.123,
46
  "step": 3
47
+ },
48
+ {
49
+ "epoch": 0.0006915031549831446,
50
+ "grad_norm": 3.5533785820007324,
51
+ "learning_rate": 8e-05,
52
+ "loss": 10.1142,
53
+ "step": 4
54
+ },
55
+ {
56
+ "epoch": 0.0008643789437289308,
57
+ "grad_norm": 3.568767786026001,
58
+ "learning_rate": 0.0001,
59
+ "loss": 10.1969,
60
+ "step": 5
61
+ },
62
+ {
63
+ "epoch": 0.001037254732474717,
64
+ "grad_norm": 3.5537147521972656,
65
+ "learning_rate": 0.00012,
66
+ "loss": 10.2579,
67
+ "step": 6
68
+ },
69
+ {
70
+ "epoch": 0.001037254732474717,
71
+ "eval_loss": 10.108320236206055,
72
+ "eval_runtime": 105.2129,
73
+ "eval_samples_per_second": 23.153,
74
+ "eval_steps_per_second": 11.577,
75
+ "step": 6
76
  }
77
  ],
78
  "logging_steps": 1,
 
92
  "attributes": {}
93
  }
94
  },
95
+ "total_flos": 3257942409216.0,
96
  "train_batch_size": 2,
97
  "trial_name": null,
98
  "trial_params": null