ClarenceDan commited on
Commit
3a68bdf
·
verified ·
1 Parent(s): f8e5ce6

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 sha256:5b9711c722d84275e6e89817fea489034c2d682f0742fe3e750a5a2bcc859041
3
  size 80013120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cbd7baa8634732cc0a7f6375bddcfb50539aac00f1ed1f10e5526a92cd6c9997
3
  size 80013120
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6a629304c1028de0929e415efe73a1837c0b1b3f8529b0e9be51dfa7dd9d2ddf
3
  size 41119636
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b54089e0df952f71971fb56b31e8ec00a9dfff7f67f89939826627f02633e60
3
  size 41119636
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:73aa535a34327d8ff7e12fc9f716f24d876cbdb9f9fc9bc13d972c1b7c68dd32
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:200897803867d9476163ce84baa477ea4bfc2d20fbca1d606afa2d969206fa8c
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": 0.00022771694783384254,
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": 34.777,
74
  "eval_steps_per_second": 17.39,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 977239881547776.0,
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": 0.0003415754217507638,
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": 34.777,
74
  "eval_steps_per_second": 17.39,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.0002656697724728163,
79
+ "grad_norm": 0.8088058829307556,
80
+ "learning_rate": 0.00014,
81
+ "loss": 1.8175,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.00030362259711179005,
86
+ "grad_norm": 0.9813876152038574,
87
+ "learning_rate": 0.00016,
88
+ "loss": 1.8924,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.0003415754217507638,
93
+ "grad_norm": 0.9991794228553772,
94
+ "learning_rate": 0.00018,
95
+ "loss": 1.765,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.0003415754217507638,
100
+ "eval_loss": 1.7914650440216064,
101
+ "eval_runtime": 319.0034,
102
+ "eval_samples_per_second": 34.78,
103
+ "eval_steps_per_second": 17.392,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 1465859822321664.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null