robiulawaldev commited on
Commit
5c98aaa
·
verified ·
1 Parent(s): b35fe8d

Training in progress, step 42, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4dc2abd43a7f5e2cf517e48419808f6454bee730ce0699dc0097ec463df88dc5
3
  size 156926880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f81be0283c81b4f501dd92faf31d9ff154b3b467b79947b1b56ba80dfd05348d
3
  size 156926880
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5e56f7124a2c8f8ed257486fd9be89855a7281818bd8d955ca6f02400019337a
3
  size 79968772
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d3d39d9c0a6479d8de7cf899e056c60acc96448a97af87168f88489a8749edb5
3
  size 79968772
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ac89f89a58a817d3f419d9d909dc621b13cf3f09bb98ef23d41d0399236d41fa
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:46cd6548cf57356d06110dd9ff05533c4bb7eef30ad20289e6c41822d13ac4ad
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7ed58e5b5053e09a44cd1fe67ab0f07cc790b003abec6db1f957ea4f926e4423
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:43352a0ea01b8f309df99bb65027960564fe5f2f452a04b8b6c955b0ecfed4cf
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": 0.09427609427609428,
5
  "eval_steps": 14,
6
- "global_step": 28,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -45,6 +45,28 @@
45
  "eval_samples_per_second": 74.374,
46
  "eval_steps_per_second": 19.04,
47
  "step": 28
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
48
  }
49
  ],
50
  "logging_steps": 10,
@@ -64,7 +86,7 @@
64
  "attributes": {}
65
  }
66
  },
67
- "total_flos": 1390780807643136.0,
68
  "train_batch_size": 4,
69
  "trial_name": null,
70
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.1414141414141414,
5
  "eval_steps": 14,
6
+ "global_step": 42,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
45
  "eval_samples_per_second": 74.374,
46
  "eval_steps_per_second": 19.04,
47
  "step": 28
48
+ },
49
+ {
50
+ "epoch": 0.10101010101010101,
51
+ "grad_norm": 0.6324484944343567,
52
+ "learning_rate": 0.0002,
53
+ "loss": 0.0586,
54
+ "step": 30
55
+ },
56
+ {
57
+ "epoch": 0.13468013468013468,
58
+ "grad_norm": 0.5158538818359375,
59
+ "learning_rate": 0.0002,
60
+ "loss": 0.0582,
61
+ "step": 40
62
+ },
63
+ {
64
+ "epoch": 0.1414141414141414,
65
+ "eval_loss": 0.04505711793899536,
66
+ "eval_runtime": 1.6866,
67
+ "eval_samples_per_second": 74.112,
68
+ "eval_steps_per_second": 18.973,
69
+ "step": 42
70
  }
71
  ],
72
  "logging_steps": 10,
 
86
  "attributes": {}
87
  }
88
  },
89
+ "total_flos": 2086171211464704.0,
90
  "train_batch_size": 4,
91
  "trial_name": null,
92
  "trial_params": null