tuantmdev commited on
Commit
0d828f5
·
verified ·
1 Parent(s): 50c6364

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:fd8cda08d1dbc19ff45c2de8d2e6975f91319e09dc8dae9625675162f929d3d9
3
  size 39256456
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:04ddf1e9f0fb238a137f958cf30901e693809cfa3b30cf06c53fd915c3e75aac
3
  size 39256456
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:87b832993e1a5f8f31a1029f65001ce48543eb0c30f801d82b1a3553e2d13b51
3
  size 20632826
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c012d13bb8060984790c3570e79e2499e1c03430dac0bb1cc9f443e47d877284
3
  size 20632826
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4cea0cb4ed3ce99681ba0fd79886d58ee027da91468a3da1c0373781b5a6103c
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6262ab7a2c890a47ec0fa3c4e272fd834b906cfbebf7abfe585a8f4ba8efeb6e
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": 0.0019222949244020553,
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": 0.1608,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 1651987552665600.0,
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": 0.0028834423866030833,
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": 0.1608,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.002218032605079295,
72
+ "grad_norm": 0.5097475051879883,
73
+ "learning_rate": 5e-05,
74
+ "loss": 0.1769,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.002218032605079295,
79
+ "eval_loss": 0.15877409279346466,
80
+ "eval_runtime": 466.9517,
81
+ "eval_samples_per_second": 12.196,
82
+ "eval_steps_per_second": 6.099,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.002587704705925844,
87
+ "grad_norm": 0.34562817215919495,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 0.1384,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 2422915077242880.0,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null