trenden commited on
Commit
2a2b50e
·
verified ·
1 Parent(s): 2562c06

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:e728a7abda3c3a661c50575b0595bd1328f5f7fdb0060ae969e189e1f807b768
3
  size 50365768
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:66f989918e8e0b6096baccd096c01465d332b856890928ded20303b7628d5bf1
3
  size 50365768
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:319e657f4c4a33389babd5794533208cac8c770ff68a48bc94e0fa256f737c07
3
  size 25859156
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:25d384874b8b7e146a78d52714a10b002ae7cb5969307d3a4d2c6d2a26f68b17
3
  size 25859156
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fbe010737447c5131864f2612d0dab966c8e3fbaba128b1a164ef5865118ae7f
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b08313bc423e4e749b1be6f1d16ebae8bf798fe463157da525e99306fd0b9592
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": 0.07228915662650602,
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": 33.363,
45
  "eval_steps_per_second": 16.681,
46
  "step": 3
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
47
  }
48
  ],
49
  "logging_steps": 1,
@@ -63,7 +92,7 @@
63
  "attributes": {}
64
  }
65
  },
66
- "total_flos": 275386013319168.0,
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": 0.14457831325301204,
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": 33.363,
45
  "eval_steps_per_second": 16.681,
46
  "step": 3
47
+ },
48
+ {
49
+ "epoch": 0.0963855421686747,
50
+ "grad_norm": 5.104182720184326,
51
+ "learning_rate": 8e-05,
52
+ "loss": 7.499,
53
+ "step": 4
54
+ },
55
+ {
56
+ "epoch": 0.12048192771084337,
57
+ "grad_norm": 4.862856864929199,
58
+ "learning_rate": 0.0001,
59
+ "loss": 7.0174,
60
+ "step": 5
61
+ },
62
+ {
63
+ "epoch": 0.14457831325301204,
64
+ "grad_norm": 4.303590297698975,
65
+ "learning_rate": 0.00012,
66
+ "loss": 6.874,
67
+ "step": 6
68
+ },
69
+ {
70
+ "epoch": 0.14457831325301204,
71
+ "eval_loss": 1.6066994667053223,
72
+ "eval_runtime": 0.5558,
73
+ "eval_samples_per_second": 32.386,
74
+ "eval_steps_per_second": 16.193,
75
+ "step": 6
76
  }
77
  ],
78
  "logging_steps": 1,
 
92
  "attributes": {}
93
  }
94
  },
95
+ "total_flos": 550772026638336.0,
96
  "train_batch_size": 2,
97
  "trial_name": null,
98
  "trial_params": null