tuanna08go commited on
Commit
b0c90ff
·
verified ·
1 Parent(s): b685fe2

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:e6f1e9609c76427b4e9321d7ca96b3728837e18c4998f7ed9b835fac4954b154
3
  size 6804608
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a9d481e876caac87340ef9faadd0f7dff7c1335184b1f27afba575993d721cc
3
  size 6804608
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:67c7e3f6e6565b727e3777f8494a619da68df96be545a61ed22ed8bf089e3b6f
3
  size 3633530
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:59c3ca7731520af02cf8db8236db071c8b1e8b3fe50616634862f8684eb04ee4
3
  size 3633530
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6ed361f2d63bb82818e33c366fb6b15db6cde149e93fdff111aa1f4ea8e127b1
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:087abc3a4df12662fc626ac5e265ecf304ec53b044c94ecf55c64e219c224944
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": 0.0003320519533594718,
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": 3.0394,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 89160891236352.0,
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": 0.0004980779300392076,
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": 3.0394,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.000383136869260929,
72
+ "grad_norm": 1.2555519342422485,
73
+ "learning_rate": 5e-05,
74
+ "loss": 2.8423,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.000383136869260929,
79
+ "eval_loss": 2.883232831954956,
80
+ "eval_runtime": 505.1532,
81
+ "eval_samples_per_second": 65.265,
82
+ "eval_steps_per_second": 32.634,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.00044699301413775045,
87
+ "grad_norm": 1.251326560974121,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 2.762,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 133741336854528.0,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null