tuanna08go commited on
Commit
3d87c65
·
verified ·
1 Parent(s): 7814191

Training in progress, step 50, 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:e33e2708c3af3e54970b202f97b21ea2cd83a9d3103eb7966f3faf1da730a518
3
  size 22573704
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:07d2c39499c97cef9dd8fbb5c8e56e86a759f2c99ea87ddc84a9c574545652c2
3
  size 22573704
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:000eb5564a3cfb51840d11e184695a79b8884927c58046f38ba8bf3a2103d1a3
3
  size 11710970
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f63ea2acf29912ae21072f2a8710140a1bc29ad5ba8c4b7b677ab3a2d9ca6e2
3
  size 11710970
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:257ed8c990aa5fffc5db8005023dbcea76e1e48a345b61bc3de290562f0522f1
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed3750dfe15289c6e0fbec8e825ca0d114706fcd47c6b6a6517d3ca12300da3f
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:75c3c8ae7ddabeca3cb69703f6b35f00b9125a4c27b56ccba4ed0e4669bb5433
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
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": 0.0850715746421268,
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,
@@ -60,6 +60,36 @@
60
  "eval_samples_per_second": 37.722,
61
  "eval_steps_per_second": 4.726,
62
  "step": 30
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
63
  }
64
  ],
65
  "logging_steps": 10,
@@ -74,12 +104,12 @@
74
  "should_evaluate": false,
75
  "should_log": false,
76
  "should_save": true,
77
- "should_training_stop": false
78
  },
79
  "attributes": {}
80
  }
81
  },
82
- "total_flos": 2.997197122358477e+16,
83
  "train_batch_size": 8,
84
  "trial_name": null,
85
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.10906612133605999,
5
  "eval_steps": 10,
6
+ "global_step": 50,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
60
  "eval_samples_per_second": 37.722,
61
  "eval_steps_per_second": 4.726,
62
  "step": 30
63
+ },
64
+ {
65
+ "epoch": 0.08725289706884799,
66
+ "grad_norm": 0.222714364528656,
67
+ "learning_rate": 1.0332332985438248e-05,
68
+ "loss": 1.7566,
69
+ "step": 40
70
+ },
71
+ {
72
+ "epoch": 0.08725289706884799,
73
+ "eval_loss": 1.7374491691589355,
74
+ "eval_runtime": 81.9879,
75
+ "eval_samples_per_second": 37.676,
76
+ "eval_steps_per_second": 4.72,
77
+ "step": 40
78
+ },
79
+ {
80
+ "epoch": 0.10906612133605999,
81
+ "grad_norm": 0.21956880390644073,
82
+ "learning_rate": 0.0,
83
+ "loss": 1.7245,
84
+ "step": 50
85
+ },
86
+ {
87
+ "epoch": 0.10906612133605999,
88
+ "eval_loss": 1.736304759979248,
89
+ "eval_runtime": 82.283,
90
+ "eval_samples_per_second": 37.541,
91
+ "eval_steps_per_second": 4.703,
92
+ "step": 50
93
  }
94
  ],
95
  "logging_steps": 10,
 
104
  "should_evaluate": false,
105
  "should_log": false,
106
  "should_save": true,
107
+ "should_training_stop": true
108
  },
109
  "attributes": {}
110
  }
111
  },
112
+ "total_flos": 3.843917336700518e+16,
113
  "train_batch_size": 8,
114
  "trial_name": null,
115
  "trial_params": null