duyphu commited on
Commit
9c9eeed
·
verified ·
1 Parent(s): 68d215d

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 sha256:7c42c6d4351b7cb5b2ca616a904310748c0b8bae3cdd531ce6371bbcb02941e3
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78005766bda1c739dad93794e92e8286153b893a593efce80caae94e8c492a00
3
  size 83945296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f82e4ab5bf0328544cf23475f5d90bfb3ad74e7b34551a11968eb6b1b74fdb9f
3
  size 43122580
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f4e148b54344c95f4acfee9cbeb2029415f986cf6409bf49bbd4ef0b69d59291
3
  size 43122580
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:883282ec1042f5d86ab3689aa84987d49f9ce467f1797aa846e4a8f53f7f78fa
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af94d499a050b6a8a9066e579e13dcfb887ae2196c78f1d893708bc5d8136dbf
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": 0.001198819623755072,
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": 0.0025,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 4819847447838720.0,
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": 0.0017982294356326078,
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": 0.0025,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.001383253412025083,
72
+ "grad_norm": 0.0038050950970500708,
73
+ "learning_rate": 5e-05,
74
+ "loss": 0.5105,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.001383253412025083,
79
+ "eval_loss": 0.1813499480485916,
80
+ "eval_runtime": 639.5032,
81
+ "eval_samples_per_second": 14.28,
82
+ "eval_steps_per_second": 7.14,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.0016137956473625968,
87
+ "grad_norm": 0.07985703647136688,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 0.5504,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 7317404761718784.0,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null