cwaud commited on
Commit
27d85d9
1 Parent(s): 513e884

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 sha256:5af87d658ccf46306447c62ae3d066dfa6ef4687119288bf64b7c5096308cca3
3
  size 41581360
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f9ea23e1bfed38918a043875292d64eaf18a4f38d88b351068cdab4f7fbbf066
3
  size 41581360
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ddec1fe8ff6b92dec81a4c516a13b01cd4d307f19c57e7bfddd6daa0fc8516ff
3
  size 21505540
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a0c9452bd9cfaf31ce02fc71f6a8e6052d1773e432c5828fe5a67070a02bf15c
3
  size 21505540
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c92d6d1e1b87396b0e067b3d5724aa6108c00b67b400cf4276964e62941d80b5
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a7fa4cc5e4c54240a40a09fd5dcfbbb810da4a034b6346087aa3ef80ea319364
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": 0.004245533345126481,
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": 15.863,
74
  "eval_steps_per_second": 7.945,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 400077864566784.0,
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": 0.006368300017689722,
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": 15.863,
74
  "eval_steps_per_second": 7.945,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.004953122235980895,
79
+ "grad_norm": 0.6149312257766724,
80
+ "learning_rate": 0.00014,
81
+ "loss": 0.8125,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.0056607111268353084,
86
+ "grad_norm": 0.556087076663971,
87
+ "learning_rate": 0.00016,
88
+ "loss": 0.8279,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.006368300017689722,
93
+ "grad_norm": 0.4917399287223816,
94
+ "learning_rate": 0.00018,
95
+ "loss": 0.6637,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.006368300017689722,
100
+ "eval_loss": 0.8577017188072205,
101
+ "eval_runtime": 37.799,
102
+ "eval_samples_per_second": 15.741,
103
+ "eval_steps_per_second": 7.884,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 637624096653312.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null