adammandic87 commited on
Commit
f2ba59a
·
verified ·
1 Parent(s): 6bb2a78

Training in progress, step 50, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:525b55c396c3a3ad897e078a619571115c50e58283d7df1411e1898446f077ac
3
  size 109009752
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ea156e4b387443791ce93955b55119de2ffa64853fbd0107a98cf6a4b8e993e9
3
  size 109009752
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:afba76d8f5d64d206f49e7e548dbf7a06828ec1dbd0b202983e84e2ec6d6f71c
3
  size 56088148
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d5285874553946be1c6ba2bb1357f6775f752fcf6bb260fed128025127cc94d7
3
  size 56088148
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8e9a0298ce1f5239bff29210b1df36c4c4d8fcaea2534cfd59acbe3a0872f2c2
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3d1e2f62bcd8f9c4f40a4b2bf8d3b1487ddade040a76030966ec7ebea410fbb
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0c50dbaa792cda4a28fbbc2acb2a3e03c59530712bbc5107212d33064d193da4
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
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": 0.007238307349665924,
5
  "eval_steps": 13,
6
- "global_step": 39,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -60,6 +60,20 @@
60
  "eval_samples_per_second": 16.16,
61
  "eval_steps_per_second": 8.084,
62
  "step": 39
 
 
 
 
 
 
 
 
 
 
 
 
 
 
63
  }
64
  ],
65
  "logging_steps": 10,
@@ -74,12 +88,12 @@
74
  "should_evaluate": false,
75
  "should_log": false,
76
  "should_save": true,
77
- "should_training_stop": false
78
  },
79
  "attributes": {}
80
  }
81
  },
82
- "total_flos": 1.409881957466112e+16,
83
  "train_batch_size": 2,
84
  "trial_name": null,
85
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.009279881217520415,
5
  "eval_steps": 13,
6
+ "global_step": 50,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
60
  "eval_samples_per_second": 16.16,
61
  "eval_steps_per_second": 8.084,
62
  "step": 39
63
+ },
64
+ {
65
+ "epoch": 0.007423904974016332,
66
+ "grad_norm": 0.621334969997406,
67
+ "learning_rate": 1.4644660940672627e-05,
68
+ "loss": 1.205,
69
+ "step": 40
70
+ },
71
+ {
72
+ "epoch": 0.009279881217520415,
73
+ "grad_norm": 0.7359839081764221,
74
+ "learning_rate": 0.0,
75
+ "loss": 1.2033,
76
+ "step": 50
77
  }
78
  ],
79
  "logging_steps": 10,
 
88
  "should_evaluate": false,
89
  "should_log": false,
90
  "should_save": true,
91
+ "should_training_stop": true
92
  },
93
  "attributes": {}
94
  }
95
  },
96
+ "total_flos": 1.76895301779456e+16,
97
  "train_batch_size": 2,
98
  "trial_name": null,
99
  "trial_params": null