phungkhaccuong commited on
Commit
71957dc
·
verified ·
1 Parent(s): cfabfc2

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 sha256:726696375002f9afffef3fcc5543439c2ad0a1ad12b690426c373d44f233b16d
3
  size 100059752
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc6b654ff14e976d522e251b01091a3bbeae59f4fff69f9a5ecf3db921da8a5f
3
  size 100059752
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3db267443c011ee162d1f6e53571c5c7672c99a25e1647e7f946b1d54d57b625
3
  size 51244020
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b970652f113f071dd04123a2f677a8fade3a165d164867626a49060d903474b
3
  size 51244020
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9c258a0c5c31051e0f2674f157215beb7e114f204c893817b8cb1a4070e5515d
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5563048afcc16f4f0723f94a4657fc683031fc640e6031a09b62d44c93264f19
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": 0.04589585172109444,
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": 0.5021,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 9937675364597760.0,
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": 0.06884377758164166,
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": 0.5021,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.0529567519858782,
72
+ "grad_norm": 4.586399078369141,
73
+ "learning_rate": 5e-05,
74
+ "loss": 0.4014,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.0529567519858782,
79
+ "eval_loss": 0.47897952795028687,
80
+ "eval_runtime": 62.9044,
81
+ "eval_samples_per_second": 3.799,
82
+ "eval_steps_per_second": 1.908,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.0617828773168579,
87
+ "grad_norm": 8.578695297241211,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 0.3658,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 1.490651304689664e+16,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null