tuanna08go commited on
Commit
b65e1ed
·
verified ·
1 Parent(s): 2921712

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:a7ccfea7493079d4335aaa57d4ded75f730d46fd3dcdb73a48b322472c6c6220
3
  size 161714
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd4503d16d5d4b0b3861d9b4482221daef5687e4ac143b2354e5783ba693d71c
3
  size 161714
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dbcb299686bb604f5db327dce91d5b66b41072b0497e8307b8bea23dbd90232a
3
  size 64750
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:447d4078c3c85ecc1387b0e324fb2a9083966ca601a85f61a9eed8f6747e2233
3
  size 64750
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:27e993de387eaf1c76836fe66cd1e5dad0a9ea203c11a45d9654a843d94d4d08
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6427ffbd65b4be1b2f3fbb643f167933e7260181d95492a2b6d8cd2d25b75737
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": 0.00044023213779265916,
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": 6.9273,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 44164067328.0,
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": 0.0006603482066889887,
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": 6.9273,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.0005079601589915298,
72
+ "grad_norm": 0.29080092906951904,
73
+ "learning_rate": 5e-05,
74
+ "loss": 6.9242,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.0005079601589915298,
79
+ "eval_loss": 6.923147201538086,
80
+ "eval_runtime": 292.5271,
81
+ "eval_samples_per_second": 85.011,
82
+ "eval_steps_per_second": 42.505,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.000592620185490118,
87
+ "grad_norm": 0.29354530572891235,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 6.9219,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 66905266176.0,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null