great0001 commited on
Commit
55fbd68
·
verified ·
1 Parent(s): 187ab01

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 sha256:35492ad3aef0d082acda80341f646111979e8b797e607d57caef7ce87c4ca564
3
  size 80013120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7027e7dd1f2209561ae04a25d9b174da245833f6d62ffd10c90ddecc88f961b2
3
  size 80013120
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3cd52c415a40b0963757a7c7cc5498d3ae2d4382d8a3bd63d461bbf46af32930
3
  size 41119636
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e2c6e0d9fca2b88234dee4601e7bb1957d381f68e64145ce8535d191f303d7a
3
  size 41119636
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3d93d600975602b7dc557ea6bf2be1af32b3a49c58755d50746f1058367b602f
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d68d2a8ec68d97e9f6781386cdc5d11673589bf128caf93d024b660045d53f99
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": 0.00010374520178441747,
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": 19.435,
45
  "eval_steps_per_second": 9.718,
46
  "step": 3
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
47
  }
48
  ],
49
  "logging_steps": 1,
@@ -63,7 +92,7 @@
63
  "attributes": {}
64
  }
65
  },
66
- "total_flos": 977239881547776.0,
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": 0.00020749040356883493,
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": 19.435,
45
  "eval_steps_per_second": 9.718,
46
  "step": 3
47
+ },
48
+ {
49
+ "epoch": 0.00013832693571255662,
50
+ "grad_norm": 0.12160821259021759,
51
+ "learning_rate": 8e-05,
52
+ "loss": 0.3099,
53
+ "step": 4
54
+ },
55
+ {
56
+ "epoch": 0.00017290866964069578,
57
+ "grad_norm": 0.1576390117406845,
58
+ "learning_rate": 0.0001,
59
+ "loss": 0.438,
60
+ "step": 5
61
+ },
62
+ {
63
+ "epoch": 0.00020749040356883493,
64
+ "grad_norm": 0.14320649206638336,
65
+ "learning_rate": 0.00012,
66
+ "loss": 0.2759,
67
+ "step": 6
68
+ },
69
+ {
70
+ "epoch": 0.00020749040356883493,
71
+ "eval_loss": 0.3893989622592926,
72
+ "eval_runtime": 626.4853,
73
+ "eval_samples_per_second": 19.435,
74
+ "eval_steps_per_second": 9.718,
75
+ "step": 6
76
  }
77
  ],
78
  "logging_steps": 1,
 
92
  "attributes": {}
93
  }
94
  },
95
+ "total_flos": 1954479763095552.0,
96
  "train_batch_size": 2,
97
  "trial_name": null,
98
  "trial_params": null