chauhoang commited on
Commit
3376fee
·
verified ·
1 Parent(s): ad6d143

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 sha256:796bc67de81bbe1310feabb48945f5402deb012f97bc9e997a7a35147e91d4f5
3
  size 36981072
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:774ff2bac770fd8dc773fc0b29448fbfb81aa0a54738d35635429ff3bab64b00
3
  size 36981072
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d33f2e844352c9fe788379f77f6554aa6f00fd6547182d713c17edaa44e2c4ba
3
  size 19859140
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b75e97a3e708f309224568b813a377ec13f1abe4909b5ab7d08fb8c40d34bd85
3
  size 19859140
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:11f0a30926f234c2a4db9e467908574bcd4eb62fb1cc00a7f5b42a5dbe9aadf5
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f71c9d3267baf9c2b8096c6d7b74a49bbde096860c2ee8125089e1ffc5081e8f
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": 0.011057947900053162,
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": 3.7952,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 1248548295278592.0,
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": 0.016586921850079744,
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": 3.7952,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.012759170653907496,
72
+ "grad_norm": 8.149195671081543,
73
+ "learning_rate": 5e-05,
74
+ "loss": 3.42,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.012759170653907496,
79
+ "eval_loss": 2.458000898361206,
80
+ "eval_runtime": 41.9164,
81
+ "eval_samples_per_second": 23.618,
82
+ "eval_steps_per_second": 11.809,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.014885699096225412,
87
+ "grad_norm": 3.334670066833496,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 2.7604,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 1905252268769280.0,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null