havinash-ai commited on
Commit
3ce6887
·
verified ·
1 Parent(s): c135cb0

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:f1d6a2b86dc97ba64a5b4c58a9312c95d8117392240ba872c4dfa278ba9213bd
3
  size 100059752
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca250a788c01e70adbc87d664fa4eb762bab8fc0f2819286a7228f41dbb3cd2f
3
  size 100059752
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:981364387b01d5a336e1647b0d100608ab5da4982b6dbcdaebe410a11c68829c
3
  size 51244020
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:210e0da44084e1a16a795d5ef20791b1a4ccc2abb52d59bdf06d347d4365e399
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": 0.00294045577064445,
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": 27.857,
45
  "eval_steps_per_second": 13.928,
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": 0.0058809115412889,
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": 27.857,
45
  "eval_steps_per_second": 13.928,
46
  "step": 3
47
+ },
48
+ {
49
+ "epoch": 0.0039206076941926,
50
+ "grad_norm": 3.7689459323883057,
51
+ "learning_rate": 8e-05,
52
+ "loss": 1.4737,
53
+ "step": 4
54
+ },
55
+ {
56
+ "epoch": 0.00490075961774075,
57
+ "grad_norm": 3.5083603858947754,
58
+ "learning_rate": 0.0001,
59
+ "loss": 1.3285,
60
+ "step": 5
61
+ },
62
+ {
63
+ "epoch": 0.0058809115412889,
64
+ "grad_norm": 3.1085927486419678,
65
+ "learning_rate": 0.00012,
66
+ "loss": 1.2179,
67
+ "step": 6
68
+ },
69
+ {
70
+ "epoch": 0.0058809115412889,
71
+ "eval_loss": 0.8347481489181519,
72
+ "eval_runtime": 15.465,
73
+ "eval_samples_per_second": 27.805,
74
+ "eval_steps_per_second": 13.902,
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