tuanna08go commited on
Commit
cc9a0d2
·
verified ·
1 Parent(s): 2032e1f

Training in progress, step 39, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:747ab789691efb20ef3d65d0ace3282e61c46e2ba68fc387a7688220332d90d9
3
  size 125040
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:11845dc913272a6da93b32010973366a4fb2e08c278605e549f76b741f73b4f5
3
  size 125040
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2b996f03c7f29dd90b4fd097ca479be3b5cb7a79f889e49216b2e0d0416a11e5
3
  size 162868
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:472515aeccff66855ab21a952a9abf5911de5b3336d99c6f9eb021e9a2710eaf
3
  size 162868
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:30429798f04cb50527135470f09401e1763a2227b112ad239a908ad5ae3800ed
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b385e88134a54e838c615db48cf9a55f7814e6c0bc1908eff83a1138778e088
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6e65bdb10468d12c8b6afa89fe8730e38a94a4f704431de04b0c1bf27440afce
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:75c3c8ae7ddabeca3cb69703f6b35f00b9125a4c27b56ccba4ed0e4669bb5433
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": 0.02178466694595727,
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,
@@ -45,6 +45,21 @@
45
  "eval_samples_per_second": 141.185,
46
  "eval_steps_per_second": 17.664,
47
  "step": 20
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
48
  }
49
  ],
50
  "logging_steps": 10,
@@ -64,7 +79,7 @@
64
  "attributes": {}
65
  }
66
  },
67
- "total_flos": 8024475303936.0,
68
  "train_batch_size": 8,
69
  "trial_name": null,
70
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.032677000418935905,
5
  "eval_steps": 10,
6
+ "global_step": 39,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
45
  "eval_samples_per_second": 141.185,
46
  "eval_steps_per_second": 17.664,
47
  "step": 20
48
+ },
49
+ {
50
+ "epoch": 0.025136154168412233,
51
+ "grad_norm": 5.889796257019043,
52
+ "learning_rate": 3.705904774487396e-05,
53
+ "loss": 176.8012,
54
+ "step": 30
55
+ },
56
+ {
57
+ "epoch": 0.025136154168412233,
58
+ "eval_loss": 11.03995418548584,
59
+ "eval_runtime": 57.0124,
60
+ "eval_samples_per_second": 141.039,
61
+ "eval_steps_per_second": 17.645,
62
+ "step": 30
63
  }
64
  ],
65
  "logging_steps": 10,
 
79
  "attributes": {}
80
  }
81
  },
82
+ "total_flos": 12036712955904.0,
83
  "train_batch_size": 8,
84
  "trial_name": null,
85
  "trial_params": null