jssky commited on
Commit
c9a22cd
·
verified ·
1 Parent(s): 6b84759

Training in progress, step 10, 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:cd60d78ff832ad6ec59c7d3b45984ab86641437a3a6b56146371d7b006f6232f
3
  size 250422888
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8514a13e9a86f1b424d9b8833f0facc01348cae569904571f424a83580860ad0
3
  size 250422888
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:62a0fba6379e40c5279a500ae9a4f45f54d63218a5f8070b2a23d3dd39571e10
3
  size 127788180
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:19476736ad0b61a0eff2189b040995e9546de074648ba33c74950fa22b271396
3
  size 127788180
last-checkpoint/rng_state_0.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a87d4da7c7f64682ae1dec8a15e6dce7d60ebc44de3f843d98b9f380b7fdf1b7
3
  size 15984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d28950fc4340ae99c29a00bcada50089c1566dd2b9b7c4cce2d7506cfd0f624
3
  size 15984
last-checkpoint/rng_state_1.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:326aee700fb60fbb46a592907a2b8a99c1af83ca40cb5363c762d5a69722ae4e
3
  size 15984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:88467e874cc2005afdaf34b1325ce6e5a687220080119af75e49bfaa72a36959
3
  size 15984
last-checkpoint/rng_state_2.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:946c2ecf8cc694e76dd59fd1512c3017f65fe8966cdde509f24fb12b045e3d96
3
  size 15984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:427fb24248ad03bb2b9b50ead4bb1a9b8300952231e1b763ecc377b7f9424875
3
  size 15984
last-checkpoint/rng_state_3.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:62eab200b6e2aa6fa66c59aff6254b93c735bf629489c4bf2bc1cbc8fa900a79
3
  size 15984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:502136e8954381392d0aaba37635f43b0a5dc47a58dc2c9bad5e285c651c647e
3
  size 15984
last-checkpoint/rng_state_4.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d4d514fca05d4c250f5ade3e05f2831748efca323d99ffb1243bbd3f62ea98bb
3
  size 15984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4fe8fb2201d485c1ee38b2965c0f70fe3d8777b6497771f938bbe54613957a02
3
  size 15984
last-checkpoint/rng_state_5.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:367a39d46e2c9b5b56c6b0276d2ddf1c9c83c1fab7d750fc5f7310307c5cbdec
3
  size 15984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9bd4b77cf7e3354cd00276fcd17ac0cb0072fac7f43dd5f30e83fe619f6371a7
3
  size 15984
last-checkpoint/rng_state_6.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5248f48742af9a7b60d01515e81de943006014943e15dfaa064b8dd18631fe81
3
  size 15984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1af9a2da214b905464fab6004a54569adcfd036e673e63427f4a65582abf2063
3
  size 15984
last-checkpoint/rng_state_7.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8d4aa3892e656c1278ad035aebd4016e18bc788d34249ada3e08d7af6cc56d60
3
  size 15984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:109cfaa3e511a2f48ecbc4252741073ab24840b8f4f81f23dff156925ed71100
3
  size 15984
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:26a93b2a1f4b5368650119fe6e0d6eec6d19cda6badeba4d21943ab48964fa00
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c8e6b04902f17ae368c3e6cfd97a31ad4de2f025d673daea8c033ce0e260946
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": 0.005897771952817824,
5
  "eval_steps": 3,
6
- "global_step": 9,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -102,6 +102,13 @@
102
  "eval_samples_per_second": 24.417,
103
  "eval_steps_per_second": 3.058,
104
  "step": 9
 
 
 
 
 
 
 
105
  }
106
  ],
107
  "logging_steps": 1,
@@ -116,12 +123,12 @@
116
  "should_evaluate": false,
117
  "should_log": false,
118
  "should_save": true,
119
- "should_training_stop": false
120
  },
121
  "attributes": {}
122
  }
123
  },
124
- "total_flos": 9.161227089897062e+16,
125
  "train_batch_size": 1,
126
  "trial_name": null,
127
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.00655307994757536,
5
  "eval_steps": 3,
6
+ "global_step": 10,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
102
  "eval_samples_per_second": 24.417,
103
  "eval_steps_per_second": 3.058,
104
  "step": 9
105
+ },
106
+ {
107
+ "epoch": 0.00655307994757536,
108
+ "grad_norm": 0.394959419965744,
109
+ "learning_rate": 0.00018,
110
+ "loss": 0.4039,
111
+ "step": 10
112
  }
113
  ],
114
  "logging_steps": 1,
 
123
  "should_evaluate": false,
124
  "should_log": false,
125
  "should_save": true,
126
+ "should_training_stop": true
127
  },
128
  "attributes": {}
129
  }
130
  },
131
+ "total_flos": 1.0179141210996736e+17,
132
  "train_batch_size": 1,
133
  "trial_name": null,
134
  "trial_params": null