chauhoang commited on
Commit
658e60b
·
verified ·
1 Parent(s): 3c690da

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:bd6d62aad03d0e0423b5849ec96c452e609427299322605a52be997257a5e37a
3
  size 80792096
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b5aee7aecd283f8674263498ed3b5848d03c74fe00609e375d73f8841b28b43
3
  size 80792096
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0b364d6bd08284248cb0cd1b8c039e9d31fa36365fe93e28a82b2db7b6ab09b3
3
  size 41459700
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c743d82648288a5303848f7fca3db5a78a32ccdf0ad12dd807bf47cd9d75502
3
  size 41459700
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a4f9d764cb3acebe75d12b91abc648df304746f9312e4b658e96b458a79bf2fe
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e8a4b404b2f718e4760b85a9d4524024371d3145138fb5bbfbef7e27c53fe48c
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": 0.02347629796839729,
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": 3.7253,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 4748683225595904.0,
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": 0.035214446952595936,
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": 3.7253,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.02708803611738149,
72
+ "grad_norm": 1.6034352779388428,
73
+ "learning_rate": 5e-05,
74
+ "loss": 3.6864,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.02708803611738149,
79
+ "eval_loss": 3.522407293319702,
80
+ "eval_runtime": 32.0421,
81
+ "eval_samples_per_second": 14.575,
82
+ "eval_steps_per_second": 7.303,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.03160270880361174,
87
+ "grad_norm": 1.329637050628662,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 3.4754,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 7188373690122240.0,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null