kk-aivio commited on
Commit
1a31ca3
·
verified ·
1 Parent(s): 1e2088c

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:c6fb01fb2b2fa6cf07d3294c0869d39f701c109225a45f31d0afc61f3f4e083d
3
  size 25271744
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2dff01153873da707395bca6bf96a30ca92ec32043387ec4568ad55128a0bdb
3
  size 25271744
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c957805c52ffea6cfd3526ce4c61b3956afc25a71eb79ce20b416f09f7ffd7a1
3
  size 13685516
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:efe1ca1a057dbb9f049a0cd15b912f8f1b7f38ee99c6c7dfc30e1e5fe7b185d6
3
  size 13685516
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ed43c0eb7864ed11fb41b41896f9546cefc706bb7c4143ad690b4e62652daf0e
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:915103fe450d953b29e1d31a1d1e65678aaa8be9d58fd089a14a19ed1a7723ea
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": 0.000224716997031863,
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": 53.907,
74
  "eval_steps_per_second": 26.956,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 281371176075264.0,
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": 0.00033707549554779447,
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": 53.907,
74
  "eval_steps_per_second": 26.956,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.0002621698298705068,
79
+ "grad_norm": 0.14891448616981506,
80
+ "learning_rate": 0.00014,
81
+ "loss": 1.2866,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.00029962266270915067,
86
+ "grad_norm": 0.14372538030147552,
87
+ "learning_rate": 0.00016,
88
+ "loss": 1.5797,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.00033707549554779447,
93
+ "grad_norm": 0.11284895986318588,
94
+ "learning_rate": 0.00018,
95
+ "loss": 0.8815,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.00033707549554779447,
100
+ "eval_loss": 1.2854689359664917,
101
+ "eval_runtime": 205.8891,
102
+ "eval_samples_per_second": 54.607,
103
+ "eval_steps_per_second": 27.306,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 402872365744128.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null