trenden commited on
Commit
8eef055
·
verified ·
1 Parent(s): bd4fac4

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 sha256:838af0c694bb429986cf7165e531d0acd224f08830ceefec5f29e1501a670082
3
  size 17640136
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0015db75b00059c3f110e70095a6c6d7d36d96cd2d6563588ae4d5dd02d91712
3
  size 17640136
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7bca1db947ac8459cd82a434f7c75c0969541b90cb5dc95d6d373367a868e679
3
  size 9568884
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:55e660754751563d5fea2d94b32d11bfb3c3e16890918e7783da0230afc62f13
3
  size 9568884
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:424f739be4501cfe7d354e89eb7c2636e769fe1c10cff142c347b71521f5cff2
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:59dfd7e3c5f47e9c59dd82d5934b354dca1792ccd6d53d936783c3e96fc445c8
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": 0.000641094133988674,
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": 48.394,
45
  "eval_steps_per_second": 24.209,
46
  "step": 3
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
47
  }
48
  ],
49
  "logging_steps": 1,
@@ -63,7 +92,7 @@
63
  "attributes": {}
64
  }
65
  },
66
- "total_flos": 26711449141248.0,
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": 0.001282188267977348,
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": 48.394,
45
  "eval_steps_per_second": 24.209,
46
  "step": 3
47
+ },
48
+ {
49
+ "epoch": 0.0008547921786515654,
50
+ "grad_norm": 6.316955089569092,
51
+ "learning_rate": 8e-05,
52
+ "loss": 4.6077,
53
+ "step": 4
54
+ },
55
+ {
56
+ "epoch": 0.0010684902233144566,
57
+ "grad_norm": 7.403411388397217,
58
+ "learning_rate": 0.0001,
59
+ "loss": 4.6353,
60
+ "step": 5
61
+ },
62
+ {
63
+ "epoch": 0.001282188267977348,
64
+ "grad_norm": 6.7435688972473145,
65
+ "learning_rate": 0.00012,
66
+ "loss": 4.498,
67
+ "step": 6
68
+ },
69
+ {
70
+ "epoch": 0.001282188267977348,
71
+ "eval_loss": 3.760186195373535,
72
+ "eval_runtime": 38.4186,
73
+ "eval_samples_per_second": 51.303,
74
+ "eval_steps_per_second": 25.665,
75
+ "step": 6
76
  }
77
  ],
78
  "logging_steps": 1,
 
92
  "attributes": {}
93
  }
94
  },
95
+ "total_flos": 53422898282496.0,
96
  "train_batch_size": 2,
97
  "trial_name": null,
98
  "trial_params": null