nadejdatarabukina commited on
Commit
05b1d96
·
verified ·
1 Parent(s): a52daed

Training in progress, step 30, 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:b2c5297ee9466e06e7e53b508afa7dce7e61df38c7227a754a7315d88bf1c431
3
  size 9864
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de0e5053c2ada225d892e12c12d4b973bc8f951ee557c4f3d542d91a6e046cb6
3
  size 9864
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cef7786197ef3124b84e7dee00a55fca504612468dfa7e302ffa2062d4b45c20
3
  size 27002
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:97d353794da2e0b8f629099d5be8deb959ac46346d734037d66ad21b2082f039
3
  size 27002
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2edc13c60910e9acd555e90579b2ee1807926bb393c7c79b1e24163c3f5bfc9f
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca99bebeea385ce2c1d4db38b17f7a71d082f2093a6dc4945fbf7655d2c5b44a
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:95758e6aadaa863940ee26d7d4bc2716664c72b77251097ec968b5c9819c88ad
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
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": 0.015878056525881232,
5
  "eval_steps": 8,
6
- "global_step": 25,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -95,6 +95,20 @@
95
  "eval_samples_per_second": 93.542,
96
  "eval_steps_per_second": 46.842,
97
  "step": 24
 
 
 
 
 
 
 
 
 
 
 
 
 
 
98
  }
99
  ],
100
  "logging_steps": 3,
@@ -109,12 +123,12 @@
109
  "should_evaluate": false,
110
  "should_log": false,
111
  "should_save": true,
112
- "should_training_stop": false
113
  },
114
  "attributes": {}
115
  }
116
  },
117
- "total_flos": 997402214400.0,
118
  "train_batch_size": 2,
119
  "trial_name": null,
120
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.01905366783105748,
5
  "eval_steps": 8,
6
+ "global_step": 30,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
95
  "eval_samples_per_second": 93.542,
96
  "eval_steps_per_second": 46.842,
97
  "step": 24
98
+ },
99
+ {
100
+ "epoch": 0.01714830104795173,
101
+ "grad_norm": 4.935485776513815e-05,
102
+ "learning_rate": 7.022351411174866e-06,
103
+ "loss": 46.0,
104
+ "step": 27
105
+ },
106
+ {
107
+ "epoch": 0.01905366783105748,
108
+ "grad_norm": 2.9111788535374217e-05,
109
+ "learning_rate": 0.0,
110
+ "loss": 46.0,
111
+ "step": 30
112
  }
113
  ],
114
  "logging_steps": 3,
 
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": 1196882657280.0,
132
  "train_batch_size": 2,
133
  "trial_name": null,
134
  "trial_params": null