ClarenceDan commited on
Commit
7ebda51
·
verified ·
1 Parent(s): cf57bb9

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:e249c81284e5ca5415c2ec49d268cb1da4efcb34261c613e40774789ebed138c
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76efa16fa42c779dc2ca87bc40c3ba126f4982a7b953b0d616d49e0d526db307
3
  size 83945296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:44ba8849942cda0766e876ad3d1bed5757782f003c337c8523f08bafca3b1f22
3
  size 43122580
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a4945c993af4dc984763dfe2aac8dc29280af34649c5b295006d0d0e1eeaa7a6
3
  size 43122580
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:02a921066ba995ceface607eb302fe5fbc656882a0c65440f7d36f790f14c392
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad50d6cf06913bd0bd4258afcb318b70f1ccc0899d991e7012fdad252831c348
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": 0.0025367297325864075,
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": 19.995,
74
  "eval_steps_per_second": 9.998,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 1884122184155136.0,
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": 0.003805094598879611,
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": 19.995,
74
  "eval_steps_per_second": 9.998,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.0029595180213508087,
79
+ "grad_norm": 14.319456100463867,
80
+ "learning_rate": 0.00014,
81
+ "loss": 3.54,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.00338230631011521,
86
+ "grad_norm": 9.163406372070312,
87
+ "learning_rate": 0.00016,
88
+ "loss": 3.3994,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.003805094598879611,
93
+ "grad_norm": 11.519614219665527,
94
+ "learning_rate": 0.00018,
95
+ "loss": 4.0177,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.003805094598879611,
100
+ "eval_loss": 0.9554546475410461,
101
+ "eval_runtime": 49.824,
102
+ "eval_samples_per_second": 19.99,
103
+ "eval_steps_per_second": 9.995,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 2848091673722880.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null