ClarenceDan commited on
Commit
dffad81
·
verified ·
1 Parent(s): 5ac2ea4

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:cb503ccfa210215d360d27f8c47131d03eb5c5667576cdd6b8b900270751c898
3
  size 59933632
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bfd3d6d005432ba9897bdcb4c7043c3e487e8f40fdbe71621b867faec1d37edc
3
  size 59933632
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:65b4dbbe2e571456e44afa3246a60f181ffdaffef8805fdf1303389b146c5d8d
3
  size 31822948
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d0214d7c3b8a1f401987557a64dd876b1a37cd3bd6786591e5e7c1a95d24b20d
3
  size 31822948
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a7a168dfcfd0ce1ccbacd396224b03b5e80f0ddf15f2d4e9f23c73a23afec595
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:930ecffcf53b9b309da4cbacd3e32aa53eac7f2224a5a4cb32ac9d960a3c629f
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": 0.015247776365946633,
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": 39.945,
74
  "eval_steps_per_second": 19.972,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 445644313460736.0,
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": 0.022871664548919948,
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": 39.945,
74
  "eval_steps_per_second": 19.972,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.017789072426937738,
79
+ "grad_norm": 0.33637258410453796,
80
+ "learning_rate": 0.00014,
81
+ "loss": 5.4078,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.020330368487928845,
86
+ "grad_norm": 0.4484331011772156,
87
+ "learning_rate": 0.00016,
88
+ "loss": 5.4027,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.022871664548919948,
93
+ "grad_norm": 0.40409019589424133,
94
+ "learning_rate": 0.00018,
95
+ "loss": 5.3888,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.022871664548919948,
100
+ "eval_loss": 5.433940410614014,
101
+ "eval_runtime": 4.1558,
102
+ "eval_samples_per_second": 39.944,
103
+ "eval_steps_per_second": 19.972,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 651326304288768.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null