trenden commited on
Commit
d8cc45f
·
verified ·
1 Parent(s): 4d2088b

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 sha256:8b20c32fce5224d98ec509c3f19e6cd444c887f64ee06d7e169de2a2d1c8f99e
3
  size 94412008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:25869fe564bf44371eb585742c998f025f6e4b2857ea2401bea37c4ec0e5f1e1
3
  size 94412008
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1cd7543b11cf4fa61cf1c0d583dc0f8878b4b75a6579cffc3f813bd99735220e
3
  size 48260756
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a979119ab3a134bd31bc8682c81ddd13938f428d0c36a40740777cf8f75cb440
3
  size 48260756
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ebe200c5ba3a22a53719ac76b0ae335d0a9965fa38706dea5e5efafa7b35b5e7
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b5817e34a23dad8579be74f67510479ce037dc285a340462762d7eaee096563e
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": 0.0012244897959183673,
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": 24.92,
45
  "eval_steps_per_second": 12.46,
46
  "step": 3
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
47
  }
48
  ],
49
  "logging_steps": 1,
@@ -63,7 +92,7 @@
63
  "attributes": {}
64
  }
65
  },
66
- "total_flos": 998481875435520.0,
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": 0.0024489795918367346,
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": 24.92,
45
  "eval_steps_per_second": 12.46,
46
  "step": 3
47
+ },
48
+ {
49
+ "epoch": 0.0016326530612244899,
50
+ "grad_norm": 1.6692824363708496,
51
+ "learning_rate": 8e-05,
52
+ "loss": 4.3543,
53
+ "step": 4
54
+ },
55
+ {
56
+ "epoch": 0.0020408163265306124,
57
+ "grad_norm": 1.6006004810333252,
58
+ "learning_rate": 0.0001,
59
+ "loss": 4.6853,
60
+ "step": 5
61
+ },
62
+ {
63
+ "epoch": 0.0024489795918367346,
64
+ "grad_norm": 1.3115887641906738,
65
+ "learning_rate": 0.00012,
66
+ "loss": 3.5072,
67
+ "step": 6
68
+ },
69
+ {
70
+ "epoch": 0.0024489795918367346,
71
+ "eval_loss": 1.0073992013931274,
72
+ "eval_runtime": 41.4927,
73
+ "eval_samples_per_second": 24.872,
74
+ "eval_steps_per_second": 12.436,
75
+ "step": 6
76
  }
77
  ],
78
  "logging_steps": 1,
 
92
  "attributes": {}
93
  }
94
  },
95
+ "total_flos": 2139604018790400.0,
96
  "train_batch_size": 2,
97
  "trial_name": null,
98
  "trial_params": null