kostiantynk-out commited on
Commit
8bfb56f
·
verified ·
1 Parent(s): 1645c95

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 sha256:67f335ad51383fe9d96215bf8c29dda0c33f08def8f5ce1a5fa62baa732d0d6a
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2573c92d62855f37be2c91366133c22b9d5837d32d23d88490a68d6aa5b03d0e
3
  size 83945296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fefa57ae3498996966aa6f87d04c3a11f5b0cde88755ee7f1c412bfc8f6f2843
3
  size 43122580
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:845e50847680f95490c420a4b5c540519c6081de5729f559dae6151c8ff2810f
3
  size 43122580
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:20911ca91ea1cdbb81acbe54f05a1245788489144f858e8e56a7eb8a4d073e18
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f299d7d715a9da57119827362cd20a3ee73249d6a1cc12c0e77d7674bfec06b3
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": 0.00041421445953642496,
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": 27.357,
74
  "eval_steps_per_second": 13.681,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 1387197345300480.0,
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": 0.0006213216893046374,
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": 27.357,
74
  "eval_steps_per_second": 13.681,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.0004832502027924958,
79
+ "grad_norm": 3.845686197280884,
80
+ "learning_rate": 0.00014,
81
+ "loss": 1.6431,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.0005522859460485666,
86
+ "grad_norm": 1.3479456901550293,
87
+ "learning_rate": 0.00016,
88
+ "loss": 0.3864,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.0006213216893046374,
93
+ "grad_norm": 2.227390766143799,
94
+ "learning_rate": 0.00018,
95
+ "loss": 0.4494,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.0006213216893046374,
100
+ "eval_loss": 0.3269291818141937,
101
+ "eval_runtime": 222.7301,
102
+ "eval_samples_per_second": 27.383,
103
+ "eval_steps_per_second": 13.694,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 1988316194930688.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null