ClarenceDan commited on
Commit
76db441
·
verified ·
1 Parent(s): a531b34

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 sha256:56702f5b12d2a701e109e8b9dfd9424d22cbccfad425c263040fff5c9b688777
3
  size 125248064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a0aa5a1072b4fb9a0db9dfe651b7606e0624431412965c22f983f249688fc93f
3
  size 125248064
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a50dcb6020213e50bad0435ed00d7d05302b00357a6bbbb420e721c750851123
3
  size 64219860
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e1f51a56700b4282e5db10ebb0a066be278916e97a2273f8fe7588b5d3997e2
3
  size 64219860
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:27d776c8cc8c19ee4cf945ef22e749c46eac2116aa5a9db2f8ab1fcc9c5a3069
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f797822d7f90ddd36d01752f52a725432b47768e1274ee0905f5c20838530138
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": 0.0002764722145424385,
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": 9.312,
74
  "eval_steps_per_second": 4.656,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 3245379912990720.0,
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": 0.0004147083218136577,
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": 9.312,
74
  "eval_steps_per_second": 4.656,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.00032255091696617823,
79
+ "grad_norm": 0.8704009652137756,
80
+ "learning_rate": 0.00014,
81
+ "loss": 4.4659,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.000368629619389918,
86
+ "grad_norm": 0.5341410040855408,
87
+ "learning_rate": 0.00016,
88
+ "loss": 5.1402,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.0004147083218136577,
93
+ "grad_norm": 0.5640665888786316,
94
+ "learning_rate": 0.00018,
95
+ "loss": 4.77,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.0004147083218136577,
100
+ "eval_loss": 1.1383893489837646,
101
+ "eval_runtime": 690.0329,
102
+ "eval_samples_per_second": 13.243,
103
+ "eval_steps_per_second": 6.621,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 4591025242767360.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null