Nexspear commited on
Commit
1189a9a
·
verified ·
1 Parent(s): 3b46402

Training in progress, step 27, 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:bb112ac8cc94492bb1e98fb3d48ec799222720e576f81e94accdd03c8c188e45
3
  size 159967880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:11c4d594833855b876f3de4cb794e7f0b8e9ed7d6883bafc6697762f882f2d89
3
  size 159967880
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:faa400c07149d31e66aa2e4f7e98ebb1837c7c5681cccc2024893ca4f8cb03e6
3
  size 81730196
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:755576e2942a21fc96bb71e9d413a6a0a0e2a41ca2deab181a8ebfcb9481ed34
3
  size 81730196
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7f3e0d009e0ec3fd5ee7f335d17337d83548753eb73ecf4cd0160baac45f5971
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c535d322f74c9d3b81f5ae8eda9978ae89ee98f7142986d1695029a6439098ec
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e7f75dad5b4fa698adb63b89c53682112a536ec6b4f570bd7793123dfd2a0133
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:95e5b5e126f269e3dd52e13e2ce68743557810f4e2bb59a1eda63231c7828066
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": 0.012651555086979441,
5
  "eval_steps": 9,
6
- "global_step": 18,
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": 7.123,
74
  "eval_steps_per_second": 0.891,
75
  "step": 18
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 3,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 4.759877641568256e+16,
96
  "train_batch_size": 8,
97
  "trial_name": null,
98
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.018977332630469163,
5
  "eval_steps": 9,
6
+ "global_step": 27,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
73
  "eval_samples_per_second": 7.123,
74
  "eval_steps_per_second": 0.891,
75
  "step": 18
76
+ },
77
+ {
78
+ "epoch": 0.014760147601476014,
79
+ "grad_norm": 0.2650648057460785,
80
+ "learning_rate": 4.817959636416969e-05,
81
+ "loss": 0.8897,
82
+ "step": 21
83
+ },
84
+ {
85
+ "epoch": 0.01686874011597259,
86
+ "grad_norm": 0.2767353355884552,
87
+ "learning_rate": 4.707368982147318e-05,
88
+ "loss": 0.805,
89
+ "step": 24
90
+ },
91
+ {
92
+ "epoch": 0.018977332630469163,
93
+ "grad_norm": 0.21788977086544037,
94
+ "learning_rate": 4.572593931387604e-05,
95
+ "loss": 0.8363,
96
+ "step": 27
97
+ },
98
+ {
99
+ "epoch": 0.018977332630469163,
100
+ "eval_loss": 0.8280394673347473,
101
+ "eval_runtime": 336.3295,
102
+ "eval_samples_per_second": 7.127,
103
+ "eval_steps_per_second": 0.892,
104
+ "step": 27
105
  }
106
  ],
107
  "logging_steps": 3,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 7.139816462352384e+16,
125
  "train_batch_size": 8,
126
  "trial_name": null,
127
  "trial_params": null