tuanna08go commited on
Commit
966e34c
·
verified ·
1 Parent(s): 2d9d228

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:f0aad5ea861ca95f02e164a636e7f4f55b3c9542806c936c4a02a81a9b76203c
3
  size 80013120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2cda9f1f5120389e25f34d4bead67255b2f0f66997979e23e4c929ed6c2eee02
3
  size 80013120
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:420d46b1d517ea00cf021c320254bab4ecd2c4399be72dd1c32ca6a13b70c1bb
3
  size 41119636
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7337898e244a6fd6d9c42b28a6810c8c64f5822c5418ad7bd57a9daaf7da59a7
3
  size 41119636
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6c7cbbb04512bd9b58eb37215dd24c52eccba02c770c21d16b116ae65aab2177
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:65aa5c0b92d89456129ebd9520dd0ffb8ac2f18cbdc8beceb40b593a4a4bf305
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": 0.008902394658563205,
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": 19.846,
46
  "eval_steps_per_second": 2.481,
47
  "step": 20
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
48
  }
49
  ],
50
  "logging_steps": 10,
@@ -64,7 +79,7 @@
64
  "attributes": {}
65
  }
66
  },
67
- "total_flos": 6.871421590437888e+16,
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": 0.013353591987844807,
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": 19.846,
46
  "eval_steps_per_second": 2.481,
47
  "step": 20
48
+ },
49
+ {
50
+ "epoch": 0.010271993836803698,
51
+ "grad_norm": 0.6428648829460144,
52
+ "learning_rate": 3.705904774487396e-05,
53
+ "loss": 0.0686,
54
+ "step": 30
55
+ },
56
+ {
57
+ "epoch": 0.010271993836803698,
58
+ "eval_loss": 0.060449112206697464,
59
+ "eval_runtime": 989.4637,
60
+ "eval_samples_per_second": 19.886,
61
+ "eval_steps_per_second": 2.486,
62
+ "step": 30
63
  }
64
  ],
65
  "logging_steps": 10,
 
79
  "attributes": {}
80
  }
81
  },
82
+ "total_flos": 1.029889327104e+17,
83
  "train_batch_size": 8,
84
  "trial_name": null,
85
  "trial_params": null