laquythang commited on
Commit
4a4c5ac
·
verified ·
1 Parent(s): 8ba9606

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:a9d4a4a496b5af04e04416d63e2101ea643afbdacd673dd6e1ba4ff65978ae4d
3
  size 247944
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e4a0a2a457d9ada2e7d52e1fe2e2192641f48f10384e78697dfc30b6d16ad782
3
  size 247944
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:60afefeedc65a49c5987d0e5980d27a9201472f2405cfaf3be6874f1ed4773dc
3
  size 263088
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a3c33f1f17534145de7a079d679ae4727ddbe251715bdc58ceeca77d9976dc3e
3
  size 263088
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fbe38599c452d9ae6dc34f6e1fc26d8c070f9321d6d7b5ad8731beaf1827578f
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:59d799f504d9e96669c3b322ccf044cf42ed69181feb6c152cba674fa2359f08
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": 0.0016252454797860093,
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,
@@ -73,6 +73,35 @@
73
  "eval_samples_per_second": 58.727,
74
  "eval_steps_per_second": 29.382,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 499189284864.0,
96
  "train_batch_size": 2,
97
  "trial_name": null,
98
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.002437868219679014,
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,
 
73
  "eval_samples_per_second": 58.727,
74
  "eval_steps_per_second": 29.382,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.0018961197264170109,
79
+ "grad_norm": 6.361030101776123,
80
+ "learning_rate": 0.00014,
81
+ "loss": 44.4097,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.0021669939730480123,
86
+ "grad_norm": 7.421581745147705,
87
+ "learning_rate": 0.00016,
88
+ "loss": 44.2708,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.002437868219679014,
93
+ "grad_norm": 8.107527732849121,
94
+ "learning_rate": 0.00018,
95
+ "loss": 44.3208,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.002437868219679014,
100
+ "eval_loss": 11.058432579040527,
101
+ "eval_runtime": 26.4941,
102
+ "eval_samples_per_second": 58.692,
103
+ "eval_steps_per_second": 29.365,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 748783927296.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null