duyphu commited on
Commit
040d273
·
verified ·
1 Parent(s): d886c54

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:a869b2e9012b0369f1ed7dd0ee551eccfae8ea250569dc5a53e1fc24df3fcd3f
3
  size 22573704
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:711ba2ed111992db44c6b8861958d1310ea4c5da2806caaa3c7a12c806fa58cf
3
  size 22573704
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:df40fe8cd24c3046ba9d857a432d130a57aab90a255e8a8215774b5f0a3c08d0
3
  size 11710970
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0cad5495380466e4e2b04200c1c671bfc8de431126186a8c0548d4b453961e0b
3
  size 11710970
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7915dda52f0f144d56978f79d3b3cd71e5191c10ec4cb1ec3809a04bb97b3396
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ec43f4672338489ffc2fb9e78a21600f7984e0fdd84b8c64a9942db8e3f67e6
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": 0.00422661139559457,
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": 2.402,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 865963855577088.0,
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": 0.0063399170933918555,
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": 2.402,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.00487685930260912,
72
+ "grad_norm": 1.4835270643234253,
73
+ "learning_rate": 5e-05,
74
+ "loss": 2.4308,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.00487685930260912,
79
+ "eval_loss": 2.5327956676483154,
80
+ "eval_runtime": 80.3325,
81
+ "eval_samples_per_second": 32.253,
82
+ "eval_steps_per_second": 16.133,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.0056896691863773064,
87
+ "grad_norm": 1.7618451118469238,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 2.3475,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 1274891231821824.0,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null