ebobo commited on
Commit
d7a6bb8
·
verified ·
1 Parent(s): d6169f6

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 sha256:818ac9273d7964c25102e464481a152a15169ff2fdbcd7fb8a313a8800ee7369
3
  size 159967880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06f67bb2d37064c0ca1dadc058430a1da30e19464a55198831f97bac39f9e657
3
  size 159967880
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2d9d0f1adde18cb00f3f066b11a00b8d47271b7df87b4ce3e6c41816daee0b20
3
  size 81730196
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91eb086e4f2a517351c821c05f087f8d9321c14cd3b6b2d8f473598e6dc78a70
3
  size 81730196
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3dbcb6cce85814c21071761b4173f649d9682f2c49347d501f1df252029199a3
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b8aefa3075f62c4cd00dd5263713be019055862c4e14255d03ba1618ba3077b5
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": 0.028037383177570093,
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": 4.635,
45
  "eval_steps_per_second": 2.369,
46
  "step": 3
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
47
  }
48
  ],
49
  "logging_steps": 1,
@@ -63,7 +92,7 @@
63
  "attributes": {}
64
  }
65
  },
66
- "total_flos": 3920749211418624.0,
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": 0.056074766355140186,
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": 4.635,
45
  "eval_steps_per_second": 2.369,
46
  "step": 3
47
+ },
48
+ {
49
+ "epoch": 0.037383177570093455,
50
+ "grad_norm": 3.4488842487335205,
51
+ "learning_rate": 8e-05,
52
+ "loss": 1.718,
53
+ "step": 4
54
+ },
55
+ {
56
+ "epoch": 0.04672897196261682,
57
+ "grad_norm": 2.8154029846191406,
58
+ "learning_rate": 0.0001,
59
+ "loss": 1.355,
60
+ "step": 5
61
+ },
62
+ {
63
+ "epoch": 0.056074766355140186,
64
+ "grad_norm": 3.2244303226470947,
65
+ "learning_rate": 0.00012,
66
+ "loss": 1.1568,
67
+ "step": 6
68
+ },
69
+ {
70
+ "epoch": 0.056074766355140186,
71
+ "eval_loss": 0.9131178259849548,
72
+ "eval_runtime": 9.8418,
73
+ "eval_samples_per_second": 4.572,
74
+ "eval_steps_per_second": 2.337,
75
+ "step": 6
76
  }
77
  ],
78
  "logging_steps": 1,
 
92
  "attributes": {}
93
  }
94
  },
95
+ "total_flos": 7841498422837248.0,
96
  "train_batch_size": 2,
97
  "trial_name": null,
98
  "trial_params": null