kostiantynk1205 commited on
Commit
7bb50ac
·
verified ·
1 Parent(s): 9436f53

Training in progress, step 9, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7d8771f17b5ebf8d3e1fed6937ef1ab82b2f9b60ccc307781c9d5721a49278b8
3
  size 556856304
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ceabc6dd1e2e8db18d983cd5e50c76b99c24d70a1f1beab60bf6caf91c52d88
3
  size 556856304
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:75b6fbd1fe85a9aab9293f4b26697c0e13d636c8bc1fd9082950c85d19752efc
3
  size 21599060
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0cca5c8e10dd029a75a732d0b2885ee15bfd31fda10577f500188d2593d564e3
3
  size 21599060
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9ca5557df48bad83ea6fc20618e57f78b74056a1a5464656055e25ac8f74628d
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb91e2e45c651d389a1f4a7175eaa9b1cb7c3752127424640499fdf51987e759
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c8e6b04902f17ae368c3e6cfd97a31ad4de2f025d673daea8c033ce0e260946
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": 0.00019681810726586847,
5
  "eval_steps": 3,
6
- "global_step": 6,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -73,6 +73,35 @@
73
  "eval_samples_per_second": 54.39,
74
  "eval_steps_per_second": 27.195,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 391769594265600.0,
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": 0.0002952271608988027,
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,
 
73
  "eval_samples_per_second": 54.39,
74
  "eval_steps_per_second": 27.195,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.0002296211251435132,
79
+ "grad_norm": 18.766361236572266,
80
+ "learning_rate": 0.00014,
81
+ "loss": 15.4928,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.00026242414302115794,
86
+ "grad_norm": 14.135737419128418,
87
+ "learning_rate": 0.00016,
88
+ "loss": 12.9572,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.0002952271608988027,
93
+ "grad_norm": 16.682376861572266,
94
+ "learning_rate": 0.00018,
95
+ "loss": 13.6494,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.0002952271608988027,
100
+ "eval_loss": 3.110774278640747,
101
+ "eval_runtime": 234.4718,
102
+ "eval_samples_per_second": 54.744,
103
+ "eval_steps_per_second": 27.372,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 587654391398400.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null