duyphu commited on
Commit
c13bdaf
·
verified ·
1 Parent(s): c7612ac

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 sha256:7eeb336a1507cdbed69ad61a08866a1af8a88e819651251ec149036ac1868e6b
3
  size 1134088
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd486cb7baac43b8cd310a5e79caaa468a71d2dd8d2b3d9ba4a0e193c37d36f0
3
  size 1134088
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1047db65da64c5a881074b3781a9389a63645030f3c94857fa826944f4013d52
3
  size 608186
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e9d3434ce16d8a09768175d9b857dc5d895366a281bf83f930a6f71c31f9e19
3
  size 608186
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:703743d253433b91505ce02a6f9a755873aae0546d14a95ca4fcce864fe29b0e
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71f25f8eea8571597026dda96f73b919287a9200c6e4dab4ab5ef591c476ce27
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": 0.019392131269811673,
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": 3.0526,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 55893571928064.0,
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": 0.02908819690471751,
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": 3.0526,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.02237553608055193,
72
+ "grad_norm": 1.051188349723816,
73
+ "learning_rate": 5e-05,
74
+ "loss": 3.0883,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.02237553608055193,
79
+ "eval_loss": 2.9902172088623047,
80
+ "eval_runtime": 4.1854,
81
+ "eval_samples_per_second": 134.993,
82
+ "eval_steps_per_second": 67.616,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.02610479209397725,
87
+ "grad_norm": 1.1222662925720215,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 2.9688,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 83571638796288.0,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null