ClarenceDan commited on
Commit
805b7ad
·
verified ·
1 Parent(s): 60743ad

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:c34b1b7a8c22a8e91652cc675f49d9c8c894f3949f65698d5bd8850f72bfd1f1
3
  size 17640136
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d1a58ba8fa57f5a7f1718433e84de8bb686cd00c868b54c8830e112972f7871
3
  size 17640136
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ed03d0ad6f325917bb4f99a5d0804e2275b4ff99961ed8cb625d46883431af5c
3
  size 9568884
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9de33468729b5705ba3b5a1538d1431a2711b893fbb4ceb51d9f5edcd353c7ae
3
  size 9568884
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:59dfd7e3c5f47e9c59dd82d5934b354dca1792ccd6d53d936783c3e96fc445c8
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fda5437f05e2eaed0597b85f69532d5c06b3025917ba7357f9b3d1d946872746
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": 9.524187467756657e-05,
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": 50.955,
74
  "eval_steps_per_second": 25.478,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 53422898282496.0,
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": 0.00014286281201634986,
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": 50.955,
74
  "eval_steps_per_second": 25.478,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.000111115520457161,
79
+ "grad_norm": 2.729943037033081,
80
+ "learning_rate": 0.00014,
81
+ "loss": 3.3698,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.00012698916623675544,
86
+ "grad_norm": 1.4825519323349,
87
+ "learning_rate": 0.00016,
88
+ "loss": 2.4287,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.00014286281201634986,
93
+ "grad_norm": 1.5584574937820435,
94
+ "learning_rate": 0.00018,
95
+ "loss": 2.221,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.00014286281201634986,
100
+ "eval_loss": 2.539081573486328,
101
+ "eval_runtime": 431.5948,
102
+ "eval_samples_per_second": 61.46,
103
+ "eval_steps_per_second": 30.73,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 80134347423744.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null