tuanna08go commited on
Commit
7063de8
·
verified ·
1 Parent(s): be0d8e9

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 sha256:2c0e0bcd5d88a3500231ff55b4f0ae557a84604ca8c798fc9265f3b46f0448d6
3
  size 25271744
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6813fdbe8bdc8489de4b64f15ce24261dd873e6b848088555a29a119ace00a54
3
  size 25271744
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5277051a519761231b9a075d5fba93dfc965af3536520aebf560a1b7763031b4
3
  size 13685516
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5905f32d61f5500b36cdf11068219588a57abff5c8fb51ea2dbb46eaacce0605
3
  size 13685516
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:891a60711995466ede70ee8fe95ed9d1d8e59808b0ae6ea01a40ca4ead79ea82
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92a42c33445a7e2c9138790db707c29bb8500bafdae7c74040b6354c5f251439
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": 0.07204710772428126,
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": 41.055,
46
  "eval_steps_per_second": 5.134,
47
  "step": 20
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
48
  }
49
  ],
50
  "logging_steps": 10,
@@ -64,7 +79,7 @@
64
  "attributes": {}
65
  }
66
  },
67
- "total_flos": 2.0309883073069056e+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": 0.1080706615864219,
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": 41.055,
46
  "eval_steps_per_second": 5.134,
47
  "step": 20
48
+ },
49
+ {
50
+ "epoch": 0.08313127814340146,
51
+ "grad_norm": 1.0012503862380981,
52
+ "learning_rate": 3.705904774487396e-05,
53
+ "loss": 2.4681,
54
+ "step": 30
55
+ },
56
+ {
57
+ "epoch": 0.08313127814340146,
58
+ "eval_loss": 2.379477024078369,
59
+ "eval_runtime": 59.1704,
60
+ "eval_samples_per_second": 41.085,
61
+ "eval_steps_per_second": 5.138,
62
+ "step": 30
63
  }
64
  ],
65
  "logging_steps": 10,
 
79
  "attributes": {}
80
  }
81
  },
82
+ "total_flos": 3.0209032631353344e+16,
83
  "train_batch_size": 8,
84
  "trial_name": null,
85
  "trial_params": null