nblinh commited on
Commit
6d0054b
1 Parent(s): a8aa4d1

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 sha256:6a0bfe1cc814095700ec3f0b3bdc80051daf687d368353fe67425e6f543fba49
3
  size 101752088
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d659ca35eb5a657687ae7553515882c754653f737128f2e7a48c242ed0415a44
3
  size 101752088
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c6cd1eb4c61793a2c7309aef0a4b451526eeb4e9ff1638d0047137c59150395b
3
  size 52046596
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:35d85d4d6843816035b7f1c17007f3f15c7d5a277246448192d191ac66ef1aa0
3
  size 52046596
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:96d6c3490071a525ca6e5c4cd9f2685e5d3d363a4357eea800161a6e9da2c951
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d667d834c40be4f29c0c338bfb48af43a7c6e83e4b812ca94a4a148c58b863d
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": 0.00045974369289121313,
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": 5.778,
74
  "eval_steps_per_second": 2.89,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 1975615204884480.0,
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": 0.0006896155393368198,
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": 5.778,
74
  "eval_steps_per_second": 2.89,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.0005363676417064154,
79
+ "grad_norm": 1.984823226928711,
80
+ "learning_rate": 0.00014,
81
+ "loss": 0.3711,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.0006129915905216175,
86
+ "grad_norm": 1.396019458770752,
87
+ "learning_rate": 0.00016,
88
+ "loss": 0.2359,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.0006896155393368198,
93
+ "grad_norm": 1.4580814838409424,
94
+ "learning_rate": 0.00018,
95
+ "loss": 0.1361,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.0006896155393368198,
100
+ "eval_loss": 0.08926785737276077,
101
+ "eval_runtime": 935.1615,
102
+ "eval_samples_per_second": 5.876,
103
+ "eval_steps_per_second": 2.939,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 2963422807326720.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null