tuanna08go commited on
Commit
3aa9e49
·
verified ·
1 Parent(s): abd36b0

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 sha256:37b909605757049b2ad7c5c35aa90e0734b56a391c0f8f3e34dc0356b6d1006c
3
  size 10624
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f975073a4841062b5daf91657dfe14caee96e290d27a9c5a4d81065bd0ce73d
3
  size 10624
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e00bc501155a871263325b9f73447a9865e4e8a92b11bd6f56a2ae09ba372c61
3
  size 26562
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:81a719e44549c7062cb371247272e0d7ebc8b096072a7d67bf308f69420f05a1
3
  size 26562
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d89522b47809a91fe7c1a8e13c7a08b66001bc90bc6baddd21c8494e3990fa02
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0142a686d2f42ce8f779f95a994c62a8be5e12e27afd368335d9d4d2472185ef
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": 0.001363308645212034,
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": 12.4515,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 2735800320.0,
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": 0.0020449629678180505,
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": 12.4515,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.001573048436783116,
72
+ "grad_norm": 0.008840982802212238,
73
+ "learning_rate": 5e-05,
74
+ "loss": 12.4552,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.001573048436783116,
79
+ "eval_loss": 12.453033447265625,
80
+ "eval_runtime": 110.6772,
81
+ "eval_samples_per_second": 72.553,
82
+ "eval_steps_per_second": 36.277,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.0018352231762469686,
87
+ "grad_norm": 0.007563808001577854,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 12.4549,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 4252925952.0,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null