tuanna08go commited on
Commit
3ff57e6
·
verified ·
1 Parent(s): 3cbc37b

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 sha256:951472d114bd0e88585f2bb1264d71aea5ce1d73a31c3f89231b8b4dd429c4b7
3
  size 80013120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:acac4ca303b0458f4fe07a1aee3c0a55716ff9b88155be4c27e0d813e6e2f7b1
3
  size 80013120
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7949722c2862fc9761df3613bd894ab5c056041f26b4ac5f0f9d67c4e4e69ba9
3
  size 41119636
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a583cc0858d83456cc4fc52c9ffc80cc92f9bc01e4893e1c65a040c2016a27c7
3
  size 41119636
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2bc49e406d40d15d4c77a549f46af25554828e4ccf4a2549a6e443a9a7b138dc
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:944fe94c0494d2a85ccff394bd6aba27772336200e013252b50fe03d2f0feeb7
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": 0.05260495700556399,
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": 0.2888,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 6591291693465600.0,
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": 0.07890743550834597,
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": 0.2888,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.06069802731411229,
72
+ "grad_norm": 0.5705128908157349,
73
+ "learning_rate": 5e-05,
74
+ "loss": 0.2478,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.06069802731411229,
79
+ "eval_loss": 0.24784217774868011,
80
+ "eval_runtime": 24.6368,
81
+ "eval_samples_per_second": 8.483,
82
+ "eval_steps_per_second": 4.262,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.07081436519979767,
87
+ "grad_norm": 0.3076908588409424,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 0.2376,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 9969328686366720.0,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null