adammandic87 commited on
Commit
a6ea778
·
verified ·
1 Parent(s): 81374e1

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 sha256:0caf4ed4b89fa16477c89065560dcd343d1fdce03cef7d73f2727248950b6798
3
  size 80013120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:18cc85e47404372b1eb259099d3852eb1dd54e8b1b3a4289083fdba084358cc1
3
  size 80013120
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4a3fba1d0cac41591d9a0976abbf004baba56cdb8b44296c394186b69dafc3a1
3
  size 41119636
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7bb457845b97e753ec538d17ee88698131dbaefdfe05739b69db23dec6b4d135
3
  size 41119636
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3e2355e43fd44f1d9860c59f45b4d1039afaad0a42f79d076c0667863cd27cb0
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:73aa535a34327d8ff7e12fc9f716f24d876cbdb9f9fc9bc13d972c1b7c68dd32
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": 0.12244897959183673,
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": 29.201,
45
  "eval_steps_per_second": 15.928,
46
  "step": 3
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
47
  }
48
  ],
49
  "logging_steps": 1,
@@ -63,7 +92,7 @@
63
  "attributes": {}
64
  }
65
  },
66
- "total_flos": 494346877009920.0,
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": 0.24489795918367346,
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": 29.201,
45
  "eval_steps_per_second": 15.928,
46
  "step": 3
47
+ },
48
+ {
49
+ "epoch": 0.16326530612244897,
50
+ "grad_norm": 2.0054235458374023,
51
+ "learning_rate": 8e-05,
52
+ "loss": 1.3989,
53
+ "step": 4
54
+ },
55
+ {
56
+ "epoch": 0.20408163265306123,
57
+ "grad_norm": 2.624239206314087,
58
+ "learning_rate": 0.0001,
59
+ "loss": 1.2946,
60
+ "step": 5
61
+ },
62
+ {
63
+ "epoch": 0.24489795918367346,
64
+ "grad_norm": 3.491370916366577,
65
+ "learning_rate": 0.00012,
66
+ "loss": 1.2136,
67
+ "step": 6
68
+ },
69
+ {
70
+ "epoch": 0.24489795918367346,
71
+ "eval_loss": 1.9611179828643799,
72
+ "eval_runtime": 0.3833,
73
+ "eval_samples_per_second": 28.695,
74
+ "eval_steps_per_second": 15.652,
75
+ "step": 6
76
  }
77
  ],
78
  "logging_steps": 1,
 
92
  "attributes": {}
93
  }
94
  },
95
+ "total_flos": 988693754019840.0,
96
  "train_batch_size": 2,
97
  "trial_name": null,
98
  "trial_params": null