duyphu commited on
Commit
30a473b
·
verified ·
1 Parent(s): c22d391

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:be64442affaa7115dbccddf4a167acc68721dc88a8a4113a7842534cabe0f39b
3
  size 14696
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e2b4d091ed5ada88e701de15f54e2c279d09148b4b63bdc4fbccae00a1a9b5fc
3
  size 14696
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4070e8565b737103d1629b59c63f0ee883e5154b5b94f3d589cfb1ed8d37079b
3
  size 39398
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b2df7c5e9d8a5ff17cb791dd582536f9f53916b10cb71eccea88625ae558606
3
  size 39398
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:be7005cc3fc15acfdf82dddf063b2d2565e65e391024dc8176c777dcd11198a3
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c1039e96a4ec12087edaa8ab2d18eba7c359b91687856664d415beaa872acc5
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": 0.08858603066439523,
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": 11.9344,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 3072196608.0,
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": 0.13287904599659284,
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": 11.9344,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.10221465076660988,
72
+ "grad_norm": 0.012346740812063217,
73
+ "learning_rate": 5e-05,
74
+ "loss": 11.933,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.10221465076660988,
79
+ "eval_loss": 11.934558868408203,
80
+ "eval_runtime": 1.1662,
81
+ "eval_samples_per_second": 106.33,
82
+ "eval_steps_per_second": 53.165,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.11925042589437819,
87
+ "grad_norm": 0.007833733223378658,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 11.9338,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 4608294912.0,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null