flytech commited on
Commit
32628c0
·
1 Parent(s): ad23f6f

Training in progress, step 500, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:18fa6a65850dab1c05036e8bac809548fca653db7a272f68349e86158ce0d9cf
3
  size 40036040
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e61644999d20947b325c32c729fc35461ccfe86753d680cc7eddfe8f525ac6ab
3
  size 40036040
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:331e83bc041dabe058244bcfb49b1c892e1d26c195e8a37df97faeca0905d105
3
  size 20524127
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e6289a4d857f2fca98577d7d6c5dfee43f2bd6b301cdef3d618b986e89d6f0a
3
  size 20524127
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:32e21b38c318f56a7e150b3009763225142c9419c02a0292361c205788d37860
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e9cb949c8ad1fdceaf96981759b8ff42882e1cbc3455d7d289052761730e50f4
3
  size 14575
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8325774c5216d42461f4f0d2f46a295a9e74d21ab580cd43104c1ce37b007328
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b3fb62e1a686af03a6294538f23b0512dc4df0d77f62afb535a9f3732c29458d
3
  size 627
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 1.2539184952978055,
5
  "eval_steps": 100,
6
- "global_step": 400,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -59,13 +59,26 @@
59
  "eval_samples_per_second": 1.757,
60
  "eval_steps_per_second": 0.221,
61
  "step": 400
 
 
 
 
 
 
 
 
 
 
 
 
 
62
  }
63
  ],
64
  "logging_steps": 100,
65
  "max_steps": 957,
66
  "num_train_epochs": 3,
67
  "save_steps": 100,
68
- "total_flos": 6.639890760047002e+16,
69
  "trial_name": null,
70
  "trial_params": null
71
  }
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 1.567398119122257,
5
  "eval_steps": 100,
6
+ "global_step": 500,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
59
  "eval_samples_per_second": 1.757,
60
  "eval_steps_per_second": 0.221,
61
  "step": 400
62
+ },
63
+ {
64
+ "epoch": 1.57,
65
+ "learning_rate": 0.0002,
66
+ "loss": 0.561,
67
+ "step": 500
68
+ },
69
+ {
70
+ "epoch": 1.57,
71
+ "eval_runtime": 512.2603,
72
+ "eval_samples_per_second": 1.757,
73
+ "eval_steps_per_second": 0.221,
74
+ "step": 500
75
  }
76
  ],
77
  "logging_steps": 100,
78
  "max_steps": 957,
79
  "num_train_epochs": 3,
80
  "save_steps": 100,
81
+ "total_flos": 8.300901581822362e+16,
82
  "trial_name": null,
83
  "trial_params": null
84
  }