Aivesa commited on
Commit
c9fbb42
·
verified ·
1 Parent(s): 820b5ad

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:ac31732d45e058a294c049e09e628d87818eede9b0e41b824a4052aca4e09fb9
3
  size 36981072
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b603eadcf2b75f3707ce5a64115142455347827f14b17d14e22e8eea2139b3e
3
  size 36981072
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9cf57c5b21bbe7902a9aa4f4e17dbf5a5e0d66c0c4588eb27f705a1112aa8ea5
3
  size 19859140
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:73c94f1ca503fd9ca973ad0422a2be989216bebb1bce93b55ac5a388a6468e19
3
  size 19859140
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b72209a0ef07e646c4de33cbbfe4b4d8a262be6d499edc700653a7c04dc79dab
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7488249a173aa3a68e75b7fc67895bff57ea66b904aac2ae135d49c25f884c96
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": 0.0007437939690705675,
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": 14.094,
66
  "eval_steps_per_second": 7.049,
67
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
68
  }
69
  ],
70
  "logging_steps": 1,
@@ -84,7 +113,7 @@
84
  "attributes": {}
85
  }
86
  },
87
- "total_flos": 243223693885440.0,
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": 0.001115690953605851,
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": 14.094,
66
  "eval_steps_per_second": 7.049,
67
  "step": 6
68
+ },
69
+ {
70
+ "epoch": 0.0008677596305823287,
71
+ "grad_norm": 1.189100980758667,
72
+ "learning_rate": 0.00014,
73
+ "loss": 2.1755,
74
+ "step": 7
75
+ },
76
+ {
77
+ "epoch": 0.00099172529209409,
78
+ "grad_norm": 1.5066560506820679,
79
+ "learning_rate": 0.00016,
80
+ "loss": 2.777,
81
+ "step": 8
82
+ },
83
+ {
84
+ "epoch": 0.001115690953605851,
85
+ "grad_norm": 1.7966433763504028,
86
+ "learning_rate": 0.00018,
87
+ "loss": 2.856,
88
+ "step": 9
89
+ },
90
+ {
91
+ "epoch": 0.001115690953605851,
92
+ "eval_loss": 2.3698041439056396,
93
+ "eval_runtime": 240.7146,
94
+ "eval_samples_per_second": 14.112,
95
+ "eval_steps_per_second": 7.058,
96
+ "step": 9
97
  }
98
  ],
99
  "logging_steps": 1,
 
113
  "attributes": {}
114
  }
115
  },
116
+ "total_flos": 364835540828160.0,
117
  "train_batch_size": 2,
118
  "trial_name": null,
119
  "trial_params": null