VERSIL91 commited on
Commit
8bfa0a4
·
verified ·
1 Parent(s): fe3f431

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 sha256:1b4651c586ae59311275128665aae56b1614c5d020c8270f05aef915992317ee
3
  size 100059752
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e26370cf1ca06f471ac7e1d4ff5fc81f91cb8ee9327245024c65c278ed21d71
3
  size 100059752
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:10c82b5d1fdfdc3f5fdd65167abac73cd41f38d700eac39c5992db4f9af4e7a2
3
  size 51244020
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e9ccea4625bdb170e75ad4cc45a4fec95d32ccbca1266037de48d13d1146c7b0
3
  size 51244020
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4ca82a561ff77829be4f53f199829857bccfb693ef73aa2d0668f096c355cee4
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7824cda9b09088755df9c1fad3a0258c249f3861ebeb526074259caef60b1595
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dc78163c347c258a17d5fa38a4e22e79b63c35d2cfce0e026e30c38b9ae55f80
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92b4cf85d7ba7a497f88ff799bf4dec5af7dd95be6e00f78bf46ba5deb56bbf8
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": 0.0002310280265874754,
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": 25.842,
45
  "eval_steps_per_second": 12.922,
46
  "step": 3
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
47
  }
48
  ],
49
  "logging_steps": 1,
@@ -63,7 +92,7 @@
63
  "attributes": {}
64
  }
65
  },
66
- "total_flos": 3726628261724160.0,
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": 0.0004620560531749508,
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": 25.842,
45
  "eval_steps_per_second": 12.922,
46
  "step": 3
47
+ },
48
+ {
49
+ "epoch": 0.00030803736878330055,
50
+ "grad_norm": 0.6603010892868042,
51
+ "learning_rate": 4e-05,
52
+ "loss": 1.0077,
53
+ "step": 4
54
+ },
55
+ {
56
+ "epoch": 0.00038504671097912567,
57
+ "grad_norm": 0.45248380303382874,
58
+ "learning_rate": 5e-05,
59
+ "loss": 0.9375,
60
+ "step": 5
61
+ },
62
+ {
63
+ "epoch": 0.0004620560531749508,
64
+ "grad_norm": 0.43786242604255676,
65
+ "learning_rate": 6e-05,
66
+ "loss": 0.8561,
67
+ "step": 6
68
+ },
69
+ {
70
+ "epoch": 0.0004620560531749508,
71
+ "eval_loss": 1.0127555131912231,
72
+ "eval_runtime": 848.2642,
73
+ "eval_samples_per_second": 25.783,
74
+ "eval_steps_per_second": 12.892,
75
+ "step": 6
76
  }
77
  ],
78
  "logging_steps": 1,
 
92
  "attributes": {}
93
  }
94
  },
95
+ "total_flos": 7405479238041600.0,
96
  "train_batch_size": 2,
97
  "trial_name": null,
98
  "trial_params": null