Aivesa commited on
Commit
9a73635
·
verified ·
1 Parent(s): ce05819

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:db6c29a9d64ca31d96964f771f5bce3abd20c659e7f71155884c20d42efdab1e
3
  size 5327744
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ccbdd80c67d29832b346402d88768c809a027bb5297c183dbfbcb12b6b3baad
3
  size 5327744
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bb70e938f12a76d1acb04ca39a7e2f1cc95fba43a4b206d0fdd58df811accacb
3
  size 2857722
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3477bdf9e4a3d94ed3422acf3ebb96d004c853b2e28d0bca1c399f41c6d6437e
3
  size 2857722
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5b0a994958b749c6835759055d2f8d66b0e72c415d690ee7a3ec1cc293934cd1
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5bdefab5aa8d905d152c0bac1bafc70c7308dfeec0e2f67ed1564906f50f6085
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": 0.00022067139271232726,
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": 42.387,
66
  "eval_steps_per_second": 21.195,
67
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
68
  }
69
  ],
70
  "logging_steps": 1,
@@ -84,7 +113,7 @@
84
  "attributes": {}
85
  }
86
  },
87
- "total_flos": 25475413966848.0,
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": 0.0003310070890684909,
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": 42.387,
66
  "eval_steps_per_second": 21.195,
67
  "step": 6
68
+ },
69
+ {
70
+ "epoch": 0.0002574499581643818,
71
+ "grad_norm": 3.9010391235351562,
72
+ "learning_rate": 0.00014,
73
+ "loss": 13.6335,
74
+ "step": 7
75
+ },
76
+ {
77
+ "epoch": 0.00029422852361643635,
78
+ "grad_norm": 3.8734169006347656,
79
+ "learning_rate": 0.00016,
80
+ "loss": 14.7722,
81
+ "step": 8
82
+ },
83
+ {
84
+ "epoch": 0.0003310070890684909,
85
+ "grad_norm": 3.584049940109253,
86
+ "learning_rate": 0.00018,
87
+ "loss": 14.5072,
88
+ "step": 9
89
+ },
90
+ {
91
+ "epoch": 0.0003310070890684909,
92
+ "eval_loss": 3.5576627254486084,
93
+ "eval_runtime": 288.1142,
94
+ "eval_samples_per_second": 39.738,
95
+ "eval_steps_per_second": 19.871,
96
+ "step": 9
97
  }
98
  ],
99
  "logging_steps": 1,
 
113
  "attributes": {}
114
  }
115
  },
116
+ "total_flos": 38213120950272.0,
117
  "train_batch_size": 2,
118
  "trial_name": null,
119
  "trial_params": null