Nexspear commited on
Commit
d50e453
·
verified ·
1 Parent(s): e984c45

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:a3ab11b8c73ee400173269240a9ee526a173fe24b4846ec6276209d48e3921c8
3
  size 167832240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78113b6b9f05cf728925cf04fb8d89357e4d4151e7bff11078c485d02ec651b0
3
  size 167832240
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:14f55a19caca743c769bc49611fea58f1c0c84160ec7d085287e4f98fbeacc39
3
  size 85723284
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec179fa89eba52e27f9750fc5c6f685942551a326ab588957b9c453fc886d977
3
  size 85723284
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b5007a051c4c84b8c41ca3a808e63a3b0686551683b6849b8ef5d494e7531a3a
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ca7c5e7dc5e5189b4d93f8446a5f87a55539e50c722fb044c91197f97026cec
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": 0.011188811188811189,
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": 10.042,
74
  "eval_steps_per_second": 1.256,
75
  "step": 18
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 3,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 3.783625146158285e+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": 0.016783216783216783,
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": 10.042,
74
  "eval_steps_per_second": 1.256,
75
  "step": 18
76
+ },
77
+ {
78
+ "epoch": 0.013053613053613054,
79
+ "grad_norm": 2.995809555053711,
80
+ "learning_rate": 4.817959636416969e-05,
81
+ "loss": 3.7813,
82
+ "step": 21
83
+ },
84
+ {
85
+ "epoch": 0.014918414918414918,
86
+ "grad_norm": 3.6315479278564453,
87
+ "learning_rate": 4.707368982147318e-05,
88
+ "loss": 3.5566,
89
+ "step": 24
90
+ },
91
+ {
92
+ "epoch": 0.016783216783216783,
93
+ "grad_norm": 3.4310660362243652,
94
+ "learning_rate": 4.572593931387604e-05,
95
+ "loss": 3.4073,
96
+ "step": 27
97
+ },
98
+ {
99
+ "epoch": 0.016783216783216783,
100
+ "eval_loss": 3.389742851257324,
101
+ "eval_runtime": 269.8486,
102
+ "eval_samples_per_second": 10.043,
103
+ "eval_steps_per_second": 1.256,
104
+ "step": 27
105
  }
106
  ],
107
  "logging_steps": 3,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 5.41577716999127e+16,
125
  "train_batch_size": 8,
126
  "trial_name": null,
127
  "trial_params": null