cwaud commited on
Commit
107e827
·
verified ·
1 Parent(s): b66d386

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 sha256:988a7a3626c2bb4dd44b88a73511539ba8dd35430220e95483bd47565f57cdf1
3
  size 80792096
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:488492cc19aa86d9ee2d86b230e5c3fefb8a2c3205482d8d0068cbf7c12c86ec
3
  size 80792096
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0b2b52bd6ad55e8c14435661f6bd50b5505ca385bf87f318fa30a9440943916d
3
  size 41459700
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:407dbf7b2358a6c8b076692e9321d4a738f2db92b98fefedf10d05a56c435877
3
  size 41459700
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:942af8987e356e19a3198ec111fa703c2d54a92114bb8091448dcaa07a5fe22e
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:738e8aa3a250c36bbe2e3641de11e87e2cd295a1ad9e5633a0ed9d9c3b037779
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": 0.00030167050039594254,
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": 7.224,
74
  "eval_steps_per_second": 3.613,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 1350542935719936.0,
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": 0.0004525057505939138,
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": 7.224,
74
  "eval_steps_per_second": 3.613,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.0003519489171285996,
79
+ "grad_norm": 0.31961575150489807,
80
+ "learning_rate": 0.00014,
81
+ "loss": 1.777,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.0004022273338612567,
86
+ "grad_norm": 0.4506252110004425,
87
+ "learning_rate": 0.00016,
88
+ "loss": 1.7637,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.0004525057505939138,
93
+ "grad_norm": 0.5181860327720642,
94
+ "learning_rate": 0.00018,
95
+ "loss": 1.6113,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.0004525057505939138,
100
+ "eval_loss": 1.6632812023162842,
101
+ "eval_runtime": 1157.8037,
102
+ "eval_samples_per_second": 7.234,
103
+ "eval_steps_per_second": 3.617,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 1960465551851520.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null