mamung commited on
Commit
3fd1128
·
verified ·
1 Parent(s): a0f2c42

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 sha256:0ba9371fadafa567efd85a743d1b12feeeccf0cbd92353936575986a194486d8
3
  size 167832240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06994b59abab92b0ed7eb0f111a1c4041f3a33b6b7cbe8c67330788e9a080838
3
  size 167832240
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:54efab0e27271c5ca4441d5b8015f801f3d18f830b70544dae5a472f89efa81a
3
  size 85723284
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d9a40c0abec607f9e1256b968f4c42c7bc6b259d5ee17427aa4bcbb460cb6174
3
  size 85723284
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3a863630364a7135b46ef32308a2fa185916dd292a6377f2cb605faf2f8420f9
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:77820273899338f3cb44d8b61f14d2376760c84be6dcbd25e712a3423d224d4a
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:df9efd4f37a043dfc96628fc1473d78ea88e2b3d21a6dd72d93347b508cabd10
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:532e5390730184467246878a5a6585bd11078f953a794f07e5dbd0719b0521bd
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": 0.00012332103548562797,
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": 11.774,
103
  "eval_steps_per_second": 5.887,
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": 3338492776022016.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.00013702337276180884,
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": 11.774,
103
  "eval_steps_per_second": 5.887,
104
  "step": 9
105
+ },
106
+ {
107
+ "epoch": 0.00013702337276180884,
108
+ "grad_norm": 0.5824243426322937,
109
+ "learning_rate": 5.9999999999999995e-05,
110
+ "loss": 0.2023,
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": 3709436417802240.0,
132
  "train_batch_size": 2,
133
  "trial_name": null,
134
  "trial_params": null