tuanna08go commited on
Commit
d4238d8
·
verified ·
1 Parent(s): 1329d30

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:e358913b62184ba3142216e265d2a3582465d95a35e1e18c1e3474c5121f167a
3
  size 111454040
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ecbd7148db217dba76b4da53f202e21dace6cdb184bb4a129ff65c6c30d5a8e7
3
  size 111454040
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:78143e170decc0978c9cff279903e23c5b7e8ae81e0dd6c8a6dfbd30c98418ff
3
  size 56950676
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d3c12fbb3eef38ac49a987197fe2a7397e93b14c585c849956bc875064b8814
3
  size 56950676
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f2a3d0f18704952f5e489fd373140093b1ec2232d5123df9941b8b0ec34244b4
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a96dad86e01dbeb27d77db2c012113e6871dc51cfe6cded422e77fffd55844d9
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": 0.00044068170069237874,
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": 5.776,
38
  "eval_steps_per_second": 2.888,
39
  "step": 10
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
40
  }
41
  ],
42
  "logging_steps": 5,
@@ -56,7 +85,7 @@
56
  "attributes": {}
57
  }
58
  },
59
- "total_flos": 4416577575321600.0,
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": 0.0008813634013847575,
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": 5.776,
38
  "eval_steps_per_second": 2.888,
39
  "step": 10
40
+ },
41
+ {
42
+ "epoch": 0.0005084788854142832,
43
+ "grad_norm": 2.420238494873047,
44
+ "learning_rate": 9.619397662556435e-05,
45
+ "loss": 4.989,
46
+ "step": 15
47
+ },
48
+ {
49
+ "epoch": 0.0006779718472190442,
50
+ "grad_norm": 2.4367876052856445,
51
+ "learning_rate": 8.535533905932738e-05,
52
+ "loss": 4.665,
53
+ "step": 20
54
+ },
55
+ {
56
+ "epoch": 0.0006779718472190442,
57
+ "eval_loss": 0.9922406673431396,
58
+ "eval_runtime": 2149.762,
59
+ "eval_samples_per_second": 5.778,
60
+ "eval_steps_per_second": 2.889,
61
+ "step": 20
62
+ },
63
+ {
64
+ "epoch": 0.0008474648090238053,
65
+ "grad_norm": 3.69812273979187,
66
+ "learning_rate": 6.91341716182545e-05,
67
+ "loss": 4.0104,
68
+ "step": 25
69
  }
70
  ],
71
  "logging_steps": 5,
 
85
  "attributes": {}
86
  }
87
  },
88
+ "total_flos": 8833155150643200.0,
89
  "train_batch_size": 2,
90
  "trial_name": null,
91
  "trial_params": null