adammandic87 commited on
Commit
df851ec
·
verified ·
1 Parent(s): d0513ab

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 sha256:8ad07a1ad2c7e2fb1896ee9ee5836afdf225f1cf6eda3825f446ea84b48ab75e
3
  size 100059752
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d130055bcb9ba023fbbf2646464d5774f89c66f08eccbf4a7dfe8b1e8492900
3
  size 100059752
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9bb265b9c18b1f30a14c18855f044535e57cc356d906fa3a72b71d75207a684e
3
  size 51244020
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c850e599dd5e92b30493ebd4239aeb277b8c1640883e0048738757a7451f594
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:f443aa61c0b62c8ce46a45f05c924349ef1098c9769a4e87bef2a843ccd40e1d
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:049ef9d402621f8d67191fa7981b9705ec1748fcb4431765ca3a28fee3882315
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": 0.02810304449648712,
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": 28.553,
45
  "eval_steps_per_second": 14.594,
46
  "step": 3
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
47
  }
48
  ],
49
  "logging_steps": 1,
@@ -63,7 +92,7 @@
63
  "attributes": {}
64
  }
65
  },
66
- "total_flos": 573327424880640.0,
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": 0.05620608899297424,
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": 28.553,
45
  "eval_steps_per_second": 14.594,
46
  "step": 3
47
+ },
48
+ {
49
+ "epoch": 0.03747072599531616,
50
+ "grad_norm": 7.36662483215332,
51
+ "learning_rate": 8e-05,
52
+ "loss": 4.5219,
53
+ "step": 4
54
+ },
55
+ {
56
+ "epoch": 0.0468384074941452,
57
+ "grad_norm": 5.468144416809082,
58
+ "learning_rate": 0.0001,
59
+ "loss": 4.2752,
60
+ "step": 5
61
+ },
62
+ {
63
+ "epoch": 0.05620608899297424,
64
+ "grad_norm": 7.327942848205566,
65
+ "learning_rate": 0.00012,
66
+ "loss": 3.9791,
67
+ "step": 6
68
+ },
69
+ {
70
+ "epoch": 0.05620608899297424,
71
+ "eval_loss": 3.585860252380371,
72
+ "eval_runtime": 1.5859,
73
+ "eval_samples_per_second": 28.376,
74
+ "eval_steps_per_second": 14.503,
75
+ "step": 6
76
  }
77
  ],
78
  "logging_steps": 1,
 
92
  "attributes": {}
93
  }
94
  },
95
+ "total_flos": 1146654849761280.0,
96
  "train_batch_size": 2,
97
  "trial_name": null,
98
  "trial_params": null