tensor24 commited on
Commit
393b6c1
1 Parent(s): 3dd0590

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 sha256:888b368de7cb2201a1b7d4380e079ab302498c000802efb1d44741c47b4b249c
3
  size 13587864
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:17d0d98541a3b654508722b5feb8f3c5988daa1a32ac7572ba8a2665f6691ecb
3
  size 13587864
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:977d7f2806c6cdd23ef8c6ea8ae5b15bd1faee401028443644d6cd25dc172f36
3
  size 7086458
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bff2201c97cd5caf470ebcfb8ee8e5190086475e47c753f855cf0219cf3269e7
3
  size 7086458
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e5bf32784e874d54ada3ba03f47fd6da65734a246fe744b0bb3b93e5778e3831
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:384a12ffcb6ac818fd74480f543b115207aa89ef97521de78ef716f236dd5f9f
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9c8e6b04902f17ae368c3e6cfd97a31ad4de2f025d673daea8c033ce0e260946
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
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": 0.012779552715654952,
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": 15.615,
103
  "eval_steps_per_second": 7.834,
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": 249907654950912.0,
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": 0.014199503017394392,
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": 15.615,
103
  "eval_steps_per_second": 7.834,
104
  "step": 9
105
+ },
106
+ {
107
+ "epoch": 0.014199503017394392,
108
+ "grad_norm": 1.9056304693222046,
109
+ "learning_rate": 0.0002,
110
+ "loss": 2.2443,
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": 277675172167680.0,
132
  "train_batch_size": 2,
133
  "trial_name": null,
134
  "trial_params": null