nathanialhunt commited on
Commit
4000095
·
verified ·
1 Parent(s): 1ea90de

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 sha256:6365ba4637508bbdfb67fa447d77beede3bdb2c18d14400678bbf74f76de14a9
3
  size 80013120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:97655619f276cf07dd74303cef1a2e8b9eb486b8b5614fd8bd542e81382e9b5a
3
  size 80013120
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:16896b6ad89bda1dcb5a21c8c4fd76b9f5736ab7bb2ff6085dee8e152af964ba
3
  size 41119636
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:57968477739757c979ede231a5b871e08b98c236d50df18952fffae891efbb67
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:e0ee036ff0ee84b856bf170bd29b04fc3f19ca29270e9b6b9cc560ad52ca9320
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22be724394db6e642de832ed7542359686b82cb9f2cb2cb2229385db0ba25a2f
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": 0.00045243750706933604,
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": 23.86,
45
  "eval_steps_per_second": 11.93,
46
  "step": 3
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
47
  }
48
  ],
49
  "logging_steps": 1,
@@ -63,7 +92,7 @@
63
  "attributes": {}
64
  }
65
  },
66
- "total_flos": 659129169346560.0,
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": 0.0009048750141386721,
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": 23.86,
45
  "eval_steps_per_second": 11.93,
46
  "step": 3
47
+ },
48
+ {
49
+ "epoch": 0.0006032500094257814,
50
+ "grad_norm": 0.5396704077720642,
51
+ "learning_rate": 8e-05,
52
+ "loss": 1.4807,
53
+ "step": 4
54
+ },
55
+ {
56
+ "epoch": 0.0007540625117822267,
57
+ "grad_norm": 0.5223986506462097,
58
+ "learning_rate": 0.0001,
59
+ "loss": 1.1522,
60
+ "step": 5
61
+ },
62
+ {
63
+ "epoch": 0.0009048750141386721,
64
+ "grad_norm": 0.5262135863304138,
65
+ "learning_rate": 0.00012,
66
+ "loss": 1.2866,
67
+ "step": 6
68
+ },
69
+ {
70
+ "epoch": 0.0009048750141386721,
71
+ "eval_loss": 1.2506712675094604,
72
+ "eval_runtime": 117.1884,
73
+ "eval_samples_per_second": 23.825,
74
+ "eval_steps_per_second": 11.912,
75
+ "step": 6
76
  }
77
  ],
78
  "logging_steps": 1,
 
92
  "attributes": {}
93
  }
94
  },
95
+ "total_flos": 1441845057945600.0,
96
  "train_batch_size": 2,
97
  "trial_name": null,
98
  "trial_params": null