nathanialhunt commited on
Commit
64fe0e1
·
verified ·
1 Parent(s): 015a245

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 sha256:60ae0e614fd9ea062e68c06ab17739a0db98ae32996a67e6bedf107b74817d33
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c9d7ba46be11c1ea416637c318bfce16ffad9864fe3ffaf45190b21648b029de
3
  size 83945296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e26908e4806ddff15a98865dbf6032da6fb59c9b3cfd3113b7b276bc9c573ea3
3
  size 43122580
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a631301624f93887fa01046cc13a4f93c6d24a90cfc1c64acdae15e2d905089f
3
  size 43122580
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9bfb4cc0c317cbad244c7ab49ee125c6bbae21d937536e8ee5c950edc6176278
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a02d055fd1532df55c5a8db423d165f840db8dc41c6f626c052a7498079b221a
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": 0.0003696743784849512,
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": 20.545,
45
  "eval_steps_per_second": 10.275,
46
  "step": 3
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
47
  }
48
  ],
49
  "logging_steps": 1,
@@ -63,7 +92,7 @@
63
  "attributes": {}
64
  }
65
  },
66
- "total_flos": 788702309646336.0,
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": 0.0007393487569699024,
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": 20.545,
45
  "eval_steps_per_second": 10.275,
46
  "step": 3
47
+ },
48
+ {
49
+ "epoch": 0.0004928991713132682,
50
+ "grad_norm": 8.990937232971191,
51
+ "learning_rate": 8e-05,
52
+ "loss": 7.1099,
53
+ "step": 4
54
+ },
55
+ {
56
+ "epoch": 0.0006161239641415853,
57
+ "grad_norm": 9.329360961914062,
58
+ "learning_rate": 0.0001,
59
+ "loss": 7.2767,
60
+ "step": 5
61
+ },
62
+ {
63
+ "epoch": 0.0007393487569699024,
64
+ "grad_norm": 9.28650951385498,
65
+ "learning_rate": 0.00012,
66
+ "loss": 7.1402,
67
+ "step": 6
68
+ },
69
+ {
70
+ "epoch": 0.0007393487569699024,
71
+ "eval_loss": 1.6262080669403076,
72
+ "eval_runtime": 166.2864,
73
+ "eval_samples_per_second": 20.549,
74
+ "eval_steps_per_second": 10.277,
75
+ "step": 6
76
  }
77
  ],
78
  "logging_steps": 1,
 
92
  "attributes": {}
93
  }
94
  },
95
+ "total_flos": 1665038209253376.0,
96
  "train_batch_size": 2,
97
  "trial_name": null,
98
  "trial_params": null