duyphu commited on
Commit
140ab15
·
verified ·
1 Parent(s): 281f34f

Training in progress, step 26, 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:dbbe11c7faa14bc2666160cd0dd3f5302162bc764ca90c433472fc324f3ddc24
3
  size 80013120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:670dd61e53ce95406b752c5220db2f0a83799bce8d2faf1c4e35bd919659bc9a
3
  size 80013120
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:585da478320c694e67a8234a0ba678beaeb0945f77f7c333244078f0d1f8fd01
3
  size 41119636
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:917074b70458c93678a7b4d9c758c4da09235a4c23e73361045d1aa1d3999a91
3
  size 41119636
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8916b5c337d5043d5ea5fa5ff20dd9b858b5e4c47f410453676f5e01172a7c24
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b673c711547b35a519b3d8cb23444c14dd7567b9d6f2ab5ed7fb2b77cef601f
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4395bafb1cf8adc0d9dbfe550d1b98763496e37a8fadb76c1ca1168a4a757f4e
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37841e69eda911caeb33edeefa0b2f140e72dcce247aeb757b2fe89c00d7887b
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": 0.008899537908608592,
5
  "eval_steps": 10,
6
- "global_step": 13,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -37,6 +37,35 @@
37
  "eval_samples_per_second": 13.609,
38
  "eval_steps_per_second": 6.816,
39
  "step": 10
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
40
  }
41
  ],
42
  "logging_steps": 5,
@@ -56,7 +85,7 @@
56
  "attributes": {}
57
  }
58
  },
59
- "total_flos": 2565280056213504.0,
60
  "train_batch_size": 2,
61
  "trial_name": null,
62
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.017799075817217184,
5
  "eval_steps": 10,
6
+ "global_step": 26,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
37
  "eval_samples_per_second": 13.609,
38
  "eval_steps_per_second": 6.816,
39
  "step": 10
40
+ },
41
+ {
42
+ "epoch": 0.010268697586856067,
43
+ "grad_norm": 0.24866552650928497,
44
+ "learning_rate": 9.619397662556435e-05,
45
+ "loss": 0.9587,
46
+ "step": 15
47
+ },
48
+ {
49
+ "epoch": 0.013691596782474755,
50
+ "grad_norm": 0.24181249737739563,
51
+ "learning_rate": 8.535533905932738e-05,
52
+ "loss": 0.8373,
53
+ "step": 20
54
+ },
55
+ {
56
+ "epoch": 0.013691596782474755,
57
+ "eval_loss": 0.9192121028900146,
58
+ "eval_runtime": 45.4474,
59
+ "eval_samples_per_second": 13.532,
60
+ "eval_steps_per_second": 6.777,
61
+ "step": 20
62
+ },
63
+ {
64
+ "epoch": 0.017114495978093443,
65
+ "grad_norm": 0.30564218759536743,
66
+ "learning_rate": 6.91341716182545e-05,
67
+ "loss": 0.8905,
68
+ "step": 25
69
  }
70
  ],
71
  "logging_steps": 5,
 
85
  "attributes": {}
86
  }
87
  },
88
+ "total_flos": 5456309960835072.0,
89
  "train_batch_size": 2,
90
  "trial_name": null,
91
  "trial_params": null