lesso commited on
Commit
62359c7
·
verified ·
1 Parent(s): 73d4300

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:e7be0397816fab85eb25df21d3365cd5f5761836482f90c96e738e970978292d
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f40b6a27ce45800aac91ae6a52e2c5d952bc98cc1743faf4bc03d21170e50d58
3
  size 83945296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b5a100df018efb9b0e5c56ff8650b047c711a47622ba63f68136793907011631
3
  size 168037178
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:98c0d06ca17a9800ad29c0ec22d7d949f44f2c2a6bd2de7148eba1856cd04077
3
  size 168037178
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:631dfb2aa9ae256eca5748a1b2ab04547dfc14e5e8346db748407ed5d049499d
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a68cd2a0196a6713af61a6a5ec57d388549ceab000d778970629ba70bc0f12ea
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 sha256:917587e2c0a52fd7c3d6680e02e388879c84c249a215f319208d6a9951b36ba9
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": 0.009009009009009009,
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": 13.701,
45
  "eval_steps_per_second": 13.701,
46
  "step": 3
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
47
  }
48
  ],
49
  "logging_steps": 1,
@@ -63,7 +92,7 @@
63
  "attributes": {}
64
  }
65
  },
66
- "total_flos": 554869274443776.0,
67
  "train_batch_size": 1,
68
  "trial_name": null,
69
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.018018018018018018,
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": 13.701,
45
  "eval_steps_per_second": 13.701,
46
  "step": 3
47
+ },
48
+ {
49
+ "epoch": 0.012012012012012012,
50
+ "grad_norm": 3.1249139308929443,
51
+ "learning_rate": 4e-05,
52
+ "loss": 2.0188,
53
+ "step": 4
54
+ },
55
+ {
56
+ "epoch": 0.015015015015015015,
57
+ "grad_norm": 2.0706639289855957,
58
+ "learning_rate": 6e-05,
59
+ "loss": 1.4195,
60
+ "step": 5
61
+ },
62
+ {
63
+ "epoch": 0.018018018018018018,
64
+ "grad_norm": 4.249810218811035,
65
+ "learning_rate": 8e-05,
66
+ "loss": 2.6119,
67
+ "step": 6
68
+ },
69
+ {
70
+ "epoch": 0.018018018018018018,
71
+ "eval_loss": 2.254021644592285,
72
+ "eval_runtime": 5.358,
73
+ "eval_samples_per_second": 13.251,
74
+ "eval_steps_per_second": 13.251,
75
+ "step": 6
76
  }
77
  ],
78
  "logging_steps": 1,
 
92
  "attributes": {}
93
  }
94
  },
95
+ "total_flos": 1109738548887552.0,
96
  "train_batch_size": 1,
97
  "trial_name": null,
98
  "trial_params": null