cwaud commited on
Commit
8ace448
1 Parent(s): 4c6d67c

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 sha256:2c02baacc74d6c9f776cbed22bbd67922bf559a12b266d258255076194d2c56c
3
  size 100059752
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca43d21084be50bee747efb87c3d0ce96cb035fe3cf5c6baf083200a498470ed
3
  size 100059752
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f7cf782fb652d29cfa09f24c3a5dde53797edaf0f49d03d0a91a7ab2af4c0349
3
  size 51244020
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cbf5a2fdf94b816554b1ed43267c6a21755fa282233b371a01e4fba5be0620b3
3
  size 51244020
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e0caa368076448ba6b6469dad0a6fe6ed5c7e7d736afe86bf7dfbe020c700de8
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:763f8e5e1764f8fe266a2cfc69a07a7744dcf177e3e51c837cea1db60fa9ebeb
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": 0.009153318077803204,
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": 5.397,
74
  "eval_steps_per_second": 2.708,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 1289986705981440.0,
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": 0.013729977116704805,
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": 5.397,
74
  "eval_steps_per_second": 2.708,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.010678871090770405,
79
+ "grad_norm": 3.708185911178589,
80
+ "learning_rate": 0.00014,
81
+ "loss": 1.4473,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.012204424103737605,
86
+ "grad_norm": 4.481770038604736,
87
+ "learning_rate": 0.00016,
88
+ "loss": 1.8168,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.013729977116704805,
93
+ "grad_norm": 8.652414321899414,
94
+ "learning_rate": 0.00018,
95
+ "loss": 1.4997,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.013729977116704805,
100
+ "eval_loss": 2.371807336807251,
101
+ "eval_runtime": 50.9338,
102
+ "eval_samples_per_second": 5.438,
103
+ "eval_steps_per_second": 2.729,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 2006645987082240.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null