Paladiso commited on
Commit
a10aff5
·
verified ·
1 Parent(s): b86a4fe

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 sha256:50348f38cb084cf7eac37349c3e22bbd6564120b7a81c3d9b963fcbdda0bf84a
3
  size 80013120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:788d6c431bc3a767c745905b4e7ed555f8414be5ad33a75e048c2a99e3480105
3
  size 80013120
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:14a398eaa5a726600c58b3e9e6d33ddbcc9adc35a59d5583abab619c17778d13
3
  size 41119636
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8224398a35326ca85824385ac38b716ad595cceedf9e8fdc2a14af90136f1230
3
  size 41119636
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:09acce823b858db1a079a05549bd8528f2fec468928dba778f7e8bdddcd10eea
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:332d05b227720963e561614b208f5e39d94130cc5b67b712d8aec704897dc6e6
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": 0.021957913998170174,
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,
@@ -65,6 +65,35 @@
65
  "eval_samples_per_second": 22.037,
66
  "eval_steps_per_second": 11.114,
67
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
68
  }
69
  ],
70
  "logging_steps": 1,
@@ -84,7 +113,7 @@
84
  "attributes": {}
85
  }
86
  },
87
- "total_flos": 988693754019840.0,
88
  "train_batch_size": 2,
89
  "trial_name": null,
90
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.03293687099725526,
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,
 
65
  "eval_samples_per_second": 22.037,
66
  "eval_steps_per_second": 11.114,
67
  "step": 6
68
+ },
69
+ {
70
+ "epoch": 0.025617566331198535,
71
+ "grad_norm": 12.137740135192871,
72
+ "learning_rate": 0.00014,
73
+ "loss": 3.0612,
74
+ "step": 7
75
+ },
76
+ {
77
+ "epoch": 0.0292772186642269,
78
+ "grad_norm": 7.033312797546387,
79
+ "learning_rate": 0.00016,
80
+ "loss": 1.7614,
81
+ "step": 8
82
+ },
83
+ {
84
+ "epoch": 0.03293687099725526,
85
+ "grad_norm": 4.264461994171143,
86
+ "learning_rate": 0.00018,
87
+ "loss": 1.0696,
88
+ "step": 9
89
+ },
90
+ {
91
+ "epoch": 0.03293687099725526,
92
+ "eval_loss": 0.7656844854354858,
93
+ "eval_runtime": 8.1274,
94
+ "eval_samples_per_second": 14.15,
95
+ "eval_steps_per_second": 7.136,
96
+ "step": 9
97
  }
98
  ],
99
  "logging_steps": 1,
 
113
  "attributes": {}
114
  }
115
  },
116
+ "total_flos": 1483040631029760.0,
117
  "train_batch_size": 2,
118
  "trial_name": null,
119
  "trial_params": null