jssky commited on
Commit
e960e46
·
verified ·
1 Parent(s): 8833ceb

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 sha256:219b9f0e459b868765a01a211ee2bc2d5ebf84f55e823f89bdb08745eb1f30e7
3
  size 50624
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:facb6e0c86dec722d960899a058ad59d907d94e03aa7e595b5d18d4041579c8e
3
  size 50624
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ace0984194701cd6403c64423281a76e7fe0657328478964eb0fae142dd3cc6b
3
  size 111142
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:049145118a6a27dc28e8ab15310932729870c864ce5b9d3eb8acf4037bd8678c
3
  size 111142
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:464e6cdff3f8548ba79ace3859c72e6b06d1e045e69932eb75c584ad0e8918c8
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e9b931b5fc0c1bd85ac8b5cf7dfdfe32425d1d78ecf18cf7fdcddc467f06765e
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": 0.0020083682008368202,
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": 55.624,
45
  "eval_steps_per_second": 55.624,
46
  "step": 3
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
47
  }
48
  ],
49
  "logging_steps": 1,
@@ -63,7 +92,7 @@
63
  "attributes": {}
64
  }
65
  },
66
- "total_flos": 156907339776.0,
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": 0.0040167364016736404,
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": 55.624,
45
  "eval_steps_per_second": 55.624,
46
  "step": 3
47
+ },
48
+ {
49
+ "epoch": 0.002677824267782427,
50
+ "grad_norm": 0.28410905599594116,
51
+ "learning_rate": 8e-05,
52
+ "loss": 10.3661,
53
+ "step": 4
54
+ },
55
+ {
56
+ "epoch": 0.0033472803347280333,
57
+ "grad_norm": 0.2462787628173828,
58
+ "learning_rate": 0.0001,
59
+ "loss": 10.381,
60
+ "step": 5
61
+ },
62
+ {
63
+ "epoch": 0.0040167364016736404,
64
+ "grad_norm": 0.22651918232440948,
65
+ "learning_rate": 0.00012,
66
+ "loss": 10.4118,
67
+ "step": 6
68
+ },
69
+ {
70
+ "epoch": 0.0040167364016736404,
71
+ "eval_loss": 10.36028003692627,
72
+ "eval_runtime": 8.3625,
73
+ "eval_samples_per_second": 37.668,
74
+ "eval_steps_per_second": 37.668,
75
+ "step": 6
76
  }
77
  ],
78
  "logging_steps": 1,
 
92
  "attributes": {}
93
  }
94
  },
95
+ "total_flos": 313814679552.0,
96
  "train_batch_size": 1,
97
  "trial_name": null,
98
  "trial_params": null