duyphu commited on
Commit
79e1128
·
verified ·
1 Parent(s): c0ec2a9

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:b85805cd72bc2ba9d623463042720909ffb8051da77912c91e317ee8d0294da0
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bea198105f92924a30d4f551d4055439c99ab6c6668408aa2532e5ce9c99298f
3
  size 83945296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a7c2b78473b84b0f713e93a1eb56a31cd1ed61f3436d0bae928f08d629cc4e95
3
  size 43122580
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4463e4ee68cb384264e491d2361058b54024478dd3294a3136f6ef330d2a5769
3
  size 43122580
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2fe6cca490e6fa13d53ae6eb09e57db4f1767a72358e96edbf5d69f6c2d1789a
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a5f891767aaacfb795fc4c851c74f7dcf55cd20474ec59a43d271975d0645cf
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": 0.006959780499230409,
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": 0.9522,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 4808867045179392.0,
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": 0.010439670748845614,
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": 0.9522,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.008030515960650473,
72
+ "grad_norm": 1.0536712408065796,
73
+ "learning_rate": 5e-05,
74
+ "loss": 0.866,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.008030515960650473,
79
+ "eval_loss": 0.8299655914306641,
80
+ "eval_runtime": 106.13,
81
+ "eval_samples_per_second": 14.821,
82
+ "eval_steps_per_second": 7.415,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.00936893528742555,
87
+ "grad_norm": 1.1671494245529175,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 0.7397,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 7213300567769088.0,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null