duyphu commited on
Commit
64a8c66
·
verified ·
1 Parent(s): 5061fd1

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:d67ffe544affa210a474de7fba939d39fa008f3150d49ee366105a5c30b75b65
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e30ab7e04461699fbed29b5aed89c6cd4c5e95e23df8ead9cb8bc83097317b0
3
  size 83945296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:abd5e90b1bbe6c2c0c128358e40388a3b14ffb02f24b74633d04d33be8d66581
3
  size 43122580
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd1a20bf64256624cf44f3dcd3c6c61054c5c87753771fdbdc9aace73cf2c7ae
3
  size 43122580
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4ab39d8fbd2c874407a81c5039399b6ff46c2237e5cccded63b3457667cba4d0
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab423bf67e2c5e85eb32f5af0f6128c31e26227abaf51e1b653a551268fea34f
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": 0.019563581640331076,
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": 3.0601,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 5317497213419520.0,
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": 0.029345372460496615,
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": 3.0601,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.022573363431151242,
72
+ "grad_norm": 1.301674246788025,
73
+ "learning_rate": 5e-05,
74
+ "loss": 2.939,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.022573363431151242,
79
+ "eval_loss": 3.0064544677734375,
80
+ "eval_runtime": 42.6624,
81
+ "eval_samples_per_second": 13.126,
82
+ "eval_steps_per_second": 6.563,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.02633559066967645,
87
+ "grad_norm": 1.780302882194519,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 2.8201,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 7953126267027456.0,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null