great0001 commited on
Commit
6881852
·
verified ·
1 Parent(s): a32dc79

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:e27aa093f8187dba30ac859a7a129b4cabf11a23821ba75819b417e973ddf788
3
  size 108113968
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:220ed8f8b76e0aa8ee0fba66e2a93b39ed896dac4eb6caa6cb3ca800d1ee47d2
3
  size 108113968
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1beb024ea330cb595b724438b157eef94fc53b1a189042458d63e519a84702eb
3
  size 55549892
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:713799702c88b64d476034f25492b2905c10d28ec40c240d645594c61a170cbb
3
  size 55549892
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d5a9038fcf89af2bea248b0af78dd99eab32293b3fc2a806df35e3b4356df4b7
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:215659ca3bf8cc95ac7f721ab7c95f29349357dfed8b3e1cd548301b28ff57a7
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": 0.022492970946579195,
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": 19.171,
74
  "eval_steps_per_second": 9.67,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 1282746010828800.0,
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": 0.033739456419868794,
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": 19.171,
74
  "eval_steps_per_second": 9.67,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.026241799437675725,
79
+ "grad_norm": 1.1654192209243774,
80
+ "learning_rate": 0.00014,
81
+ "loss": 2.6991,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.02999062792877226,
86
+ "grad_norm": 1.303310513496399,
87
+ "learning_rate": 0.00016,
88
+ "loss": 2.822,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.033739456419868794,
93
+ "grad_norm": 1.9169182777404785,
94
+ "learning_rate": 0.00018,
95
+ "loss": 2.9408,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.033739456419868794,
100
+ "eval_loss": 2.7414324283599854,
101
+ "eval_runtime": 5.8876,
102
+ "eval_samples_per_second": 19.193,
103
+ "eval_steps_per_second": 9.681,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 1898464096026624.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null