mb00g commited on
Commit
8fc68dd
·
verified ·
1 Parent(s): 59281c8

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:f7fcbfaac9c0476eb81b40585b339c56ab7c3d01061e377c552d1ba8a00bea10
3
  size 114106856
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5b3b07b5c167e8ded7435f88a7d93ec78d631e2529ef440869e32d8883029cd
3
  size 114106856
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:46efc5495d7433d98d83b12d9afec1209cf20f347e0a1541fcb256ce4d87c5df
3
  size 58562260
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0dd8ede2b13fa7fbdbcbc48492e7382d568dd439f54216d0c10245deb980796a
3
  size 58562260
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:310bb6727fee8c47ab830d63c0d0fb961145c0365ca0793daf588b90a402b171
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a59ccec7033553ae34d84603591a8663aa3252c7b3a14c2ca59ac6a3e005c0d
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": 0.0002765996680803983,
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": 1.898,
74
  "eval_steps_per_second": 1.898,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 3422513308631040.0,
96
  "train_batch_size": 1,
97
  "trial_name": null,
98
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.0004148995021205975,
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": 1.898,
74
  "eval_steps_per_second": 1.898,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.0003226996127604647,
79
+ "grad_norm": 68.54777526855469,
80
+ "learning_rate": 0.00014,
81
+ "loss": 3.5579,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.0003687995574405311,
86
+ "grad_norm": 37.80275344848633,
87
+ "learning_rate": 0.00016,
88
+ "loss": 6.1531,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.0004148995021205975,
93
+ "grad_norm": 25.41352081298828,
94
+ "learning_rate": 0.00018,
95
+ "loss": 2.361,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.0004148995021205975,
100
+ "eval_loss": 0.9192412495613098,
101
+ "eval_runtime": 2377.3456,
102
+ "eval_samples_per_second": 1.921,
103
+ "eval_steps_per_second": 1.921,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 5133769962946560.0,
125
  "train_batch_size": 1,
126
  "trial_name": null,
127
  "trial_params": null