phungkhaccuong commited on
Commit
c5d72d7
·
verified ·
1 Parent(s): 0ba6a90

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 sha256:1cf4fbf79a944b585e54b912e4c399340fda6f4f1d9fff63d91127825ebca587
3
  size 80013120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:24f277894086c4abe781e72f14c16384b0cdd1f9eab2c4ba7e9e8f244f25caeb
3
  size 80013120
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:48fc2f148179aad1f9b41671524cd870999f80f5d5df34c0dff460867d520ce4
3
  size 41119636
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e9f03293fd35654d39b714a8dc71a10c3f48683c1df48f438f467634c77c0759
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:ce9dfc8adce920ba5fd4aca5c17171c4b3e478757ea251f53f9c8a91fb6f9fb0
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5fcac41dbd9142df5390346c9aeb20da7424d647bb3d8dc6eede3f489ba85d01
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:37841e69eda911caeb33edeefa0b2f140e72dcce247aeb757b2fe89c00d7887b
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c50dbaa792cda4a28fbbc2acb2a3e03c59530712bbc5107212d33064d193da4
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": 0.001529749209384423,
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,
@@ -66,6 +66,28 @@
66
  "learning_rate": 6.91341716182545e-05,
67
  "loss": 0.9424,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 6942368854966272.0,
89
  "train_batch_size": 2,
90
  "trial_name": null,
91
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.0022946238140766346,
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,
 
66
  "learning_rate": 6.91341716182545e-05,
67
  "loss": 0.9424,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.0017650952415974113,
72
+ "grad_norm": 0.42146557569503784,
73
+ "learning_rate": 5e-05,
74
+ "loss": 0.9118,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.0017650952415974113,
79
+ "eval_loss": 0.9101587533950806,
80
+ "eval_runtime": 660.4632,
81
+ "eval_samples_per_second": 10.836,
82
+ "eval_steps_per_second": 5.419,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.0020592777818636463,
87
+ "grad_norm": 0.3509317934513092,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 0.8626,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 1.047517194092544e+16,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null