philip-hightech commited on
Commit
27e2e4f
·
verified ·
1 Parent(s): 75f01d2

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 sha256:2f1a721d8a8dc0c7b8813a9bab80f0441e02088c44f69b4ed64d9e5cdf3302ea
3
  size 41581360
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db3aafcc8424408185296a52488109694a18b32756d10a423a213b30e6e4d115
3
  size 41581360
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0cbea21424b967657cdbf002197085e222050fc4741cb3d30d25c90f2ae4735d
3
  size 21505540
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:45ce9a87d734a1a181d35925ed996886fb0848dcf317d816715481c7de64d502
3
  size 21505540
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:eece1d4d0b0c5cf475a608f4a69f986bfcf2b490c032d12bd994063c25d49dd4
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f53c88b371bd57f14aedc06e3e77ac609414f14225ee671f98bc7e7ba0edb00c
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": 0.0001581850897370832,
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": 26.945,
74
  "eval_steps_per_second": 13.473,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 525102197243904.0,
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": 0.0002372776346056248,
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": 26.945,
74
  "eval_steps_per_second": 13.473,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.0001845492713599304,
79
+ "grad_norm": 4.0232625007629395,
80
+ "learning_rate": 0.00014,
81
+ "loss": 3.1844,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.0002109134529827776,
86
+ "grad_norm": 3.1623497009277344,
87
+ "learning_rate": 0.00016,
88
+ "loss": 2.5837,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.0002372776346056248,
93
+ "grad_norm": 3.2371985912323,
94
+ "learning_rate": 0.00018,
95
+ "loss": 2.6483,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.0002372776346056248,
100
+ "eval_loss": 1.8183720111846924,
101
+ "eval_runtime": 593.4027,
102
+ "eval_samples_per_second": 26.914,
103
+ "eval_steps_per_second": 13.458,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 825160595668992.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null