cwaud commited on
Commit
fa70e97
·
verified ·
1 Parent(s): e2d8d32

Training in progress, step 6, 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:ca6a8cd89b3ca0e67e8d8f15bf462c414af02e994b7f48b5c7d7382c3c9a3690
3
  size 100059752
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c02baacc74d6c9f776cbed22bbd67922bf559a12b266d258255076194d2c56c
3
  size 100059752
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:043cdd8043ded7cb3121795beaa0c616542898151389b0c0e18f46529009412a
3
  size 51244020
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f7cf782fb652d29cfa09f24c3a5dde53797edaf0f49d03d0a91a7ab2af4c0349
3
  size 51244020
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:42f9bab28ff7022e6301adf39129844e7d8f12ec0cd48a5d730a6def52382883
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0caa368076448ba6b6469dad0a6fe6ed5c7e7d736afe86bf7dfbe020c700de8
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ffd8c58e5d02492554dbaa495f8cf80dff41fabc0e1288cb2fd18a103d402219
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
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": 0.004576659038901602,
5
  "eval_steps": 3,
6
- "global_step": 3,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -44,6 +44,35 @@
44
  "eval_samples_per_second": 5.5,
45
  "eval_steps_per_second": 2.76,
46
  "step": 3
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
47
  }
48
  ],
49
  "logging_steps": 1,
@@ -63,7 +92,7 @@
63
  "attributes": {}
64
  }
65
  },
66
- "total_flos": 621104710287360.0,
67
  "train_batch_size": 2,
68
  "trial_name": null,
69
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.009153318077803204,
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,
 
44
  "eval_samples_per_second": 5.5,
45
  "eval_steps_per_second": 2.76,
46
  "step": 3
47
+ },
48
+ {
49
+ "epoch": 0.006102212051868803,
50
+ "grad_norm": 4.932255744934082,
51
+ "learning_rate": 8e-05,
52
+ "loss": 3.0787,
53
+ "step": 4
54
+ },
55
+ {
56
+ "epoch": 0.007627765064836003,
57
+ "grad_norm": 6.312702655792236,
58
+ "learning_rate": 0.0001,
59
+ "loss": 3.8769,
60
+ "step": 5
61
+ },
62
+ {
63
+ "epoch": 0.009153318077803204,
64
+ "grad_norm": 7.200475215911865,
65
+ "learning_rate": 0.00012,
66
+ "loss": 3.5321,
67
+ "step": 6
68
+ },
69
+ {
70
+ "epoch": 0.009153318077803204,
71
+ "eval_loss": 2.6806535720825195,
72
+ "eval_runtime": 51.326,
73
+ "eval_samples_per_second": 5.397,
74
+ "eval_steps_per_second": 2.708,
75
+ "step": 6
76
  }
77
  ],
78
  "logging_steps": 1,
 
92
  "attributes": {}
93
  }
94
  },
95
+ "total_flos": 1289986705981440.0,
96
  "train_batch_size": 2,
97
  "trial_name": null,
98
  "trial_params": null