duyphu commited on
Commit
5de8768
·
verified ·
1 Parent(s): 65c125f

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:bb27add6e59d1ab1779f9c76f19d32afbd5a70d126ac25c65da940b5198c3cc3
3
  size 31064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c33769eefd16d3edc64d9d2b70aaa5a80f3a3d4b86906ce478aa07dae2e12431
3
  size 31064
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:54a696d480d93cffdc678727bb3b925c6a9ab17953968f8aa20f6ab9cabf1efc
3
  size 71718
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e8748df23a9ad4c0540390869b778a10d062e2753820d59830b7fbc1bf5a8102
3
  size 71718
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4ce9ec22e0051f976ac081d26951edb3de92acba5c29f4c684fe32b805e5bc15
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48d41985628b63b1f03308534e42f5f4fade1dc9f1a7ca147144af3b829d1153
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": 0.006125574272588055,
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": 41.493,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 1334570385408.0,
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": 0.009188361408882083,
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": 41.493,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.007067970314524679,
72
+ "grad_norm": 0.47753089666366577,
73
+ "learning_rate": 5e-05,
74
+ "loss": 41.493,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.007067970314524679,
79
+ "eval_loss": 10.372749328613281,
80
+ "eval_runtime": 11.1057,
81
+ "eval_samples_per_second": 160.999,
82
+ "eval_steps_per_second": 80.499,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.00824596536694546,
87
+ "grad_norm": 0.4785812497138977,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 41.4795,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 2001855578112.0,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null