jssky commited on
Commit
19cd0d3
1 Parent(s): 69e4fd5

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:fa8646cfe55f64b3a6c57958c653f73d38f54ddda9366931b6578a3d714d4eb1
3
  size 167832240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:24bd7d653c9ce5836572db173b47143401a21b38b155435605ddd62d8ff72716
3
  size 167832240
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1d18fac1bc9609412e625f51458b57e0cb252eb09cd447176227cc0736a21ec0
3
  size 85723284
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc6819c4d56e2b4133bf6a0a983a126541749f3273aed922ed427e4b6a087f5c
3
  size 85723284
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:094837089fa2ed1c4f9dc6c25bac04422ed41c22630725ca5cdf86ffa65f03cf
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:787ef78ee12881294c4aa83ed64603709fff88fc133de1a040e06eba2a245935
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cda2d7da3ce8a95be6df505b84eace6ccd5aa18ffc6d1bcc9a79572045c8d78f
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
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": 0.003184431667403804,
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": 5.103,
103
  "eval_steps_per_second": 5.103,
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": 6330948626939904.0,
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": 0.0035382574082264487,
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": 5.103,
103
  "eval_steps_per_second": 5.103,
104
  "step": 9
105
+ },
106
+ {
107
+ "epoch": 0.0035382574082264487,
108
+ "grad_norm": 60.3310546875,
109
+ "learning_rate": 0.00012,
110
+ "loss": 7.6766,
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": 7034387363266560.0,
132
  "train_batch_size": 1,
133
  "trial_name": null,
134
  "trial_params": null