trenden commited on
Commit
48543a3
·
verified ·
1 Parent(s): d753b8a

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 sha256:155410467c0211ae12af973681d2f5965c4ecc66503a7f3df0988db92a03e7de
3
  size 14696
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c3a7594bd9ddbdc72d8b4f4820597d122f53dcc455ff24077bd0ece1710ace4
3
  size 14696
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fc9c1d6d0507c58d43a02c5850bad66a7c2ce285c544990d06eaf005a2f9cfd3
3
  size 39398
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d5b3ac76dc7b1f9a97a8d9dd8ef5431c76a9bc92f913e567bd574d32a3b77e2d
3
  size 39398
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:464e6cdff3f8548ba79ace3859c72e6b06d1e045e69932eb75c584ad0e8918c8
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e9b931b5fc0c1bd85ac8b5cf7dfdfe32425d1d78ecf18cf7fdcddc467f06765e
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": 0.004392386530014641,
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": 248.983,
45
  "eval_steps_per_second": 124.491,
46
  "step": 3
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
47
  }
48
  ],
49
  "logging_steps": 1,
@@ -63,7 +92,7 @@
63
  "attributes": {}
64
  }
65
  },
66
- "total_flos": 354484224.0,
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": 0.008784773060029283,
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": 248.983,
45
  "eval_steps_per_second": 124.491,
46
  "step": 3
47
+ },
48
+ {
49
+ "epoch": 0.005856515373352855,
50
+ "grad_norm": 0.009967818856239319,
51
+ "learning_rate": 8e-05,
52
+ "loss": 11.9306,
53
+ "step": 4
54
+ },
55
+ {
56
+ "epoch": 0.007320644216691069,
57
+ "grad_norm": 0.00853413064032793,
58
+ "learning_rate": 0.0001,
59
+ "loss": 11.9301,
60
+ "step": 5
61
+ },
62
+ {
63
+ "epoch": 0.008784773060029283,
64
+ "grad_norm": 0.01145976223051548,
65
+ "learning_rate": 0.00012,
66
+ "loss": 11.9311,
67
+ "step": 6
68
+ },
69
+ {
70
+ "epoch": 0.008784773060029283,
71
+ "eval_loss": 11.931822776794434,
72
+ "eval_runtime": 1.189,
73
+ "eval_samples_per_second": 242.217,
74
+ "eval_steps_per_second": 121.109,
75
+ "step": 6
76
  }
77
  ],
78
  "logging_steps": 1,
 
92
  "attributes": {}
93
  }
94
  },
95
+ "total_flos": 708968448.0,
96
  "train_batch_size": 2,
97
  "trial_name": null,
98
  "trial_params": null