duyphu commited on
Commit
3304fff
·
verified ·
1 Parent(s): 44a686e

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 sha256:86db86d126704f71d7ce67df52f76afaf795583c194aa35ace6d879022dfa4da
3
  size 36981072
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa8dcaa92cdad44f692e7a53ade4409827565ab12d249564503e3381902a885f
3
  size 36981072
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6dd22ceba07ad49c57664517e736a71ff713c05b47f2102ebcc60a2ab463703f
3
  size 19859140
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:453d294245b806d60124f5a22e7a38b6bc868b32fe28fdb1b6abb19484242db4
3
  size 19859140
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:98d7e8dc13fb88a66657b51555417af417488f16f0f54045d6e78e2ba8bc5eaf
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c158abb1290faa386d5662dd18d37e1778c62c35aba6e76d3ce8d6145626bb6e
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": 0.0006992066693559231,
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": 0.9479,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 1159366274187264.0,
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": 0.0010488100040338846,
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": 0.9479,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.0008067769261799112,
72
+ "grad_norm": 0.5627620816230774,
73
+ "learning_rate": 5e-05,
74
+ "loss": 1.298,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.0008067769261799112,
79
+ "eval_loss": 1.2116531133651733,
80
+ "eval_runtime": 644.377,
81
+ "eval_samples_per_second": 24.298,
82
+ "eval_steps_per_second": 12.15,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.0009412397472098965,
87
+ "grad_norm": 0.4738096296787262,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 1.0158,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 1743103139512320.0,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null