kk-aivio commited on
Commit
be36774
·
verified ·
1 Parent(s): 6960466

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:d0546b0c26a24c97f73db9e488fb715beac993a1a1df375132a4c5171a4c5911
3
  size 17640136
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8959adaa21ee0e747134904cb3d229e4e11a9d06b07ed68cd7c88e766a908e3c
3
  size 17640136
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1044b605b236d2b5fae3178c36d736b93d224bbff86bf03364c817c15bfdc39b
3
  size 9568884
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f28cc7c3c13794b8ea0a950d936ea41691f5b3f807c81f1d23611e653f17cfeb
3
  size 9568884
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:17e0861aebd8f70471b6ac1f8c0c2719b7ec5eff68f23ec0b15040ecc5439eef
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c432173c3e03ab35f379f99e76ec96a95398876df77ad2334860facd5d9a0fd
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": 0.00031127597208892115,
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": 49.738,
45
  "eval_steps_per_second": 24.869,
46
  "step": 3
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
47
  }
48
  ],
49
  "logging_steps": 1,
@@ -63,7 +92,7 @@
63
  "attributes": {}
64
  }
65
  },
66
- "total_flos": 33389311426560.0,
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": 0.0006225519441778423,
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": 49.738,
45
  "eval_steps_per_second": 24.869,
46
  "step": 3
47
+ },
48
+ {
49
+ "epoch": 0.0004150346294518949,
50
+ "grad_norm": 1.0359632968902588,
51
+ "learning_rate": 8e-05,
52
+ "loss": 1.933,
53
+ "step": 4
54
+ },
55
+ {
56
+ "epoch": 0.0005187932868148687,
57
+ "grad_norm": 1.3015316724777222,
58
+ "learning_rate": 0.0001,
59
+ "loss": 2.0539,
60
+ "step": 5
61
+ },
62
+ {
63
+ "epoch": 0.0006225519441778423,
64
+ "grad_norm": 1.0627121925354004,
65
+ "learning_rate": 0.00012,
66
+ "loss": 2.1394,
67
+ "step": 6
68
+ },
69
+ {
70
+ "epoch": 0.0006225519441778423,
71
+ "eval_loss": 2.040466070175171,
72
+ "eval_runtime": 81.4488,
73
+ "eval_samples_per_second": 49.823,
74
+ "eval_steps_per_second": 24.911,
75
+ "step": 6
76
  }
77
  ],
78
  "logging_steps": 1,
 
92
  "attributes": {}
93
  }
94
  },
95
+ "total_flos": 71230531043328.0,
96
  "train_batch_size": 2,
97
  "trial_name": null,
98
  "trial_params": null