Aivesa commited on
Commit
0ab7403
·
verified ·
1 Parent(s): 79cff1e

Training in progress, step 9, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:990b729c7df307815eb99475a7b71f24896562265db90da7893e25d2ee7d727d
3
  size 17640136
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff563d185105de41889b4762e1ded9938c1ce948e748409689d4b9f1275b9321
3
  size 17640136
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3c9ccf7c39d1d84bbb43058ba4ec02759154d477343d432e7fad4c9b6585a9fb
3
  size 9568884
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e656a2f998336f4a55707835f53e53266fbefc03045b0b7fa535c98d82c32840
3
  size 9568884
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4a9c01bb08fabdb4105f03cc42a9544dca7c722b687afb8cabdeaf14862f778a
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:85b0ae6c3bd2ac4ea01467a5edbc086cdc303e1ace1b12b41ab97be3e932f8c7
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c8e6b04902f17ae368c3e6cfd97a31ad4de2f025d673daea8c033ce0e260946
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": 0.008333333333333333,
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,
@@ -65,6 +65,35 @@
65
  "eval_samples_per_second": 22.979,
66
  "eval_steps_per_second": 11.489,
67
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
68
  }
69
  ],
70
  "logging_steps": 1,
@@ -84,7 +113,7 @@
84
  "attributes": {}
85
  }
86
  },
87
- "total_flos": 53422898282496.0,
88
  "train_batch_size": 2,
89
  "trial_name": null,
90
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.0125,
5
  "eval_steps": 3,
6
+ "global_step": 9,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
65
  "eval_samples_per_second": 22.979,
66
  "eval_steps_per_second": 11.489,
67
  "step": 6
68
+ },
69
+ {
70
+ "epoch": 0.009722222222222222,
71
+ "grad_norm": 2.6992099285125732,
72
+ "learning_rate": 0.00014,
73
+ "loss": 2.9552,
74
+ "step": 7
75
+ },
76
+ {
77
+ "epoch": 0.011111111111111112,
78
+ "grad_norm": 2.701378107070923,
79
+ "learning_rate": 0.00016,
80
+ "loss": 2.8407,
81
+ "step": 8
82
+ },
83
+ {
84
+ "epoch": 0.0125,
85
+ "grad_norm": 3.067340135574341,
86
+ "learning_rate": 0.00018,
87
+ "loss": 2.6516,
88
+ "step": 9
89
+ },
90
+ {
91
+ "epoch": 0.0125,
92
+ "eval_loss": 2.6926474571228027,
93
+ "eval_runtime": 13.8071,
94
+ "eval_samples_per_second": 22.018,
95
+ "eval_steps_per_second": 11.009,
96
+ "step": 9
97
  }
98
  ],
99
  "logging_steps": 1,
 
113
  "attributes": {}
114
  }
115
  },
116
+ "total_flos": 80134347423744.0,
117
  "train_batch_size": 2,
118
  "trial_name": null,
119
  "trial_params": null