trenden commited on
Commit
71ae875
·
verified ·
1 Parent(s): d1b7c5b

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 sha256:26d0a9108900a4e38b08d4459b23b2c0aaf7ac903d8c6bef8a8107beb5c95e0e
3
  size 108113968
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5574b8b779893f55727b832ffb472da68c853ae52580a806a5ee13e840ab7e63
3
  size 108113968
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9a25232dc9df814476b152e807805d0f8c07741eb4675abbd4ee70cdeaa51bd4
3
  size 55549892
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:72bf240c3c602fe5cd97fb48d89a204031a490c803dbc3bc20691a42d656087d
3
  size 55549892
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:02b1a38c667864732c35a632d783572ee170a842d44852d6998851e458eb237e
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b516ee8f10ceccfbca5101eaa83b15aeaaf0d99aae9917e9c1ed5d270eb8c37f
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": 0.0003428767358134751,
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": 11.577,
74
  "eval_steps_per_second": 5.789,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 2411562500358144.0,
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": 0.0005143151037202125,
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": 11.577,
74
  "eval_steps_per_second": 5.789,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.00040002285844905423,
79
+ "grad_norm": 3.785672664642334,
80
+ "learning_rate": 0.00014,
81
+ "loss": 2.5692,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.0004571689810846334,
86
+ "grad_norm": 5.170735836029053,
87
+ "learning_rate": 0.00016,
88
+ "loss": 3.3098,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.0005143151037202125,
93
+ "grad_norm": 3.0438833236694336,
94
+ "learning_rate": 0.00018,
95
+ "loss": 2.1233,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.0005143151037202125,
100
+ "eval_loss": 3.933885097503662,
101
+ "eval_runtime": 636.4373,
102
+ "eval_samples_per_second": 11.577,
103
+ "eval_steps_per_second": 5.788,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 3642998670753792.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null