tuanna08go commited on
Commit
35ccdcc
·
verified ·
1 Parent(s): 5e9452d

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 sha256:93921e634bc6673a73bd6ebb2938a93357768a6c99dcc9edd13403f6978e46a8
3
  size 80013120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3bc580818bfb479bd731aadc1471a2880f7a82dd4b3e85bf908fae6c41152c3f
3
  size 80013120
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:023971267dd3c330e8c239e57c5969e79e48b0ddd254a377f7997db009655554
3
  size 41119636
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:752cd4ba9d2ff84a5fc447196e6bfff7dcf8f70f3f91e5c06a60c9c9681fa416
3
  size 41119636
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8077dc599d0e2178961c634ebb1554fd0bb63f56537a068f9b3ec5adbcb0bb0f
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:059688c5b89a22ab2e2602a267dd96c2a801fe63905fbb03177d1507e4d9479a
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": 0.0008592910848549946,
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": 0.9747,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 8428693978349568.0,
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": 0.0012889366272824919,
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": 0.9747,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.0009914897132942246,
72
+ "grad_norm": 0.3675839304924011,
73
+ "learning_rate": 5e-05,
74
+ "loss": 0.9272,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.0009914897132942246,
79
+ "eval_loss": 0.9233540296554565,
80
+ "eval_runtime": 2045.7232,
81
+ "eval_samples_per_second": 6.228,
82
+ "eval_steps_per_second": 3.114,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.001156737998843262,
87
+ "grad_norm": 0.40750598907470703,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 0.9225,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 1.2663400131723264e+16,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null