nadejdatarabukina commited on
Commit
94f0e16
·
verified ·
1 Parent(s): e5f5e98

Training in progress, step 25, 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:d4f8e1ed4984690180aa15ea1905b74f5f8b0501f95db93b1229808ff9894618
3
  size 9864
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b1434ef6cf88095ae0ce02ef09b45681a36834dda8255d1daaa09297564fb4f
3
  size 9864
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c34b021f7c34e33bc4fb2204925cafd276d6ff36bc8113fc1189df0f004eb33e
3
  size 27002
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc3c179834f791d6e80829679c60e0175dfb8db82349162b7a3a3b43eb878cc9
3
  size 27002
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:11e71cead5a7fcc376909c83446602574c8bdf1bd2d38d471d24ab6cfd202c92
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a016715ccb0112ab1394743f94acfb298ac9ccf9cd4cd745ca6d3b1bffe35a3
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1d95f3fb1f9df4cdd5f470d1684a242bf1d1940d47b9622802f603a91ffa5bc0
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4521b8db9cc205e54aa606d85e707c024abd2d8ad4a20bec4b2cff365dc59cdf
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": 0.0022456770716370988,
5
  "eval_steps": 7,
6
- "global_step": 20,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -73,6 +73,28 @@
73
  "learning_rate": 8.954715367323468e-05,
74
  "loss": 46.0,
75
  "step": 18
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 3,
@@ -87,12 +109,12 @@
87
  "should_evaluate": false,
88
  "should_log": false,
89
  "should_save": true,
90
- "should_training_stop": false
91
  },
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 807895793664.0,
96
  "train_batch_size": 2,
97
  "trial_name": null,
98
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.002807096339546373,
5
  "eval_steps": 7,
6
+ "global_step": 25,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
73
  "learning_rate": 8.954715367323468e-05,
74
  "loss": 46.0,
75
  "step": 18
76
+ },
77
+ {
78
+ "epoch": 0.0023579609252189536,
79
+ "grad_norm": 1.7780568668968044e-05,
80
+ "learning_rate": 3.308693936411421e-05,
81
+ "loss": 46.0,
82
+ "step": 21
83
+ },
84
+ {
85
+ "epoch": 0.0023579609252189536,
86
+ "eval_loss": 11.5,
87
+ "eval_runtime": 39.8123,
88
+ "eval_samples_per_second": 94.192,
89
+ "eval_steps_per_second": 47.096,
90
+ "step": 21
91
+ },
92
+ {
93
+ "epoch": 0.002694812485964518,
94
+ "grad_norm": 1.709483694867231e-05,
95
+ "learning_rate": 2.1852399266194314e-06,
96
+ "loss": 46.0,
97
+ "step": 24
98
  }
99
  ],
100
  "logging_steps": 3,
 
109
  "should_evaluate": false,
110
  "should_log": false,
111
  "should_save": true,
112
+ "should_training_stop": true
113
  },
114
  "attributes": {}
115
  }
116
  },
117
+ "total_flos": 1007376236544.0,
118
  "train_batch_size": 2,
119
  "trial_name": null,
120
  "trial_params": null