Aivesa commited on
Commit
2d44cc9
·
verified ·
1 Parent(s): 1ad3bff

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:bb8a38ffc09fd85f2ff96e37b434e754a17b3b9a2d270ab7e303ed7b47045d4f
3
  size 81576
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c74bb3b4f9da4327c2f51245c8a8eef2de98c0f9c1837901361cb37bdde4baa7
3
  size 81576
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c5b61b8878926140cbd671f42ff4a12c4b4a0138951aca3c0989a57fab476163
3
  size 173094
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:08673bafed238e6e8c5693d8c26a89ae8ae31ff4e8be70dfc90a2b253be2deef
3
  size 173094
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1ea8f278f29641100a56e280ef65934b0fccc8f8d9851be121c701ebed8ce795
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9df170cb6acde393f26f26d8b291e01ba34281d10b477edb2225f4b80d02e472
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": 0.008018710324089542,
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": 61.861,
66
  "eval_steps_per_second": 31.029,
67
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
68
  }
69
  ],
70
  "logging_steps": 1,
@@ -84,7 +113,7 @@
84
  "attributes": {}
85
  }
86
  },
87
- "total_flos": 963847520256.0,
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": 0.012028065486134313,
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": 61.861,
66
  "eval_steps_per_second": 31.029,
67
  "step": 6
68
+ },
69
+ {
70
+ "epoch": 0.009355162044771133,
71
+ "grad_norm": 0.2414633184671402,
72
+ "learning_rate": 0.00014,
73
+ "loss": 10.8399,
74
+ "step": 7
75
+ },
76
+ {
77
+ "epoch": 0.010691613765452723,
78
+ "grad_norm": 0.2134893238544464,
79
+ "learning_rate": 0.00016,
80
+ "loss": 10.8369,
81
+ "step": 8
82
+ },
83
+ {
84
+ "epoch": 0.012028065486134313,
85
+ "grad_norm": 0.20277711749076843,
86
+ "learning_rate": 0.00018,
87
+ "loss": 10.8212,
88
+ "step": 9
89
+ },
90
+ {
91
+ "epoch": 0.012028065486134313,
92
+ "eval_loss": 10.8336763381958,
93
+ "eval_runtime": 5.0773,
94
+ "eval_samples_per_second": 62.041,
95
+ "eval_steps_per_second": 31.119,
96
+ "step": 9
97
  }
98
  ],
99
  "logging_steps": 1,
 
113
  "attributes": {}
114
  }
115
  },
116
+ "total_flos": 1456024977408.0,
117
  "train_batch_size": 2,
118
  "trial_name": null,
119
  "trial_params": null