duyphu commited on
Commit
c423a22
·
verified ·
1 Parent(s): c164666

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:f56ccce1dcf27662e75a57bc9d4238a03e368b7eea3892ae30b868cfd5e2caf0
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a72a279f9a35c2bdd48f9f9e8ea40d1d8b621e8d4bdd1b18c72721501e72f783
3
  size 83945296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b45b89cf854452adb1c528b6418ab0e781aca321abda5f8706b1e6c6974f98c9
3
  size 43122580
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87ce8fcbb04e5914e206fa08e19175160137bb94b40ef428cf12938b8a98b770
3
  size 43122580
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:30490fbf5f8b5a427e6d64a372c12a1fd3b956afbd1f3673002c963d05c423b0
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:35552c50ff79cc09f2acf301684a9e8a362c314175fe567dd47dfc8a2b97e52b
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": 0.015865751334858888,
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": 2.7421,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 6334867876872192.0,
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": 0.02379862700228833,
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": 2.7421,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.018306636155606407,
72
+ "grad_norm": 1.9517594575881958,
73
+ "learning_rate": 5e-05,
74
+ "loss": 2.5708,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.018306636155606407,
79
+ "eval_loss": 2.8241217136383057,
80
+ "eval_runtime": 56.6612,
81
+ "eval_samples_per_second": 12.178,
82
+ "eval_steps_per_second": 6.089,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.02135774218154081,
87
+ "grad_norm": 2.5954267978668213,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 2.6296,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 9063022655963136.0,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null