Best000 commited on
Commit
59c8af6
·
verified ·
1 Parent(s): 1fb98c8

Training in progress, step 50, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:65203c1405a15f6a39bc3c944df6bdeb0e5e9be36db9cafded4dab59b6ad512b
3
  size 124756544
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:818f72aaea494d4630765c4b44af0fcafde459a001701e355c60290975300369
3
  size 124756544
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9684c0744ad6938c2b6e2b1da26c7b7fe43c7be62120b787f81b49de3eb86c3b
3
  size 63958740
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9dcf772d33504e45972c8c0d611719ec138ecc3a760646697026c2f999f1f75a
3
  size 63958740
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:35d3fa2f4cbe6e7a72d26d52a018a7c379bce90098ae7ed4220a1e3711183792
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5080fd1d8965d299188528bb8b71d1f7ad59265e9538d8a96df95a13cc340047
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ccc7e73cc5879da996ace4c3a10d9efe08a100111973e801d61997747e95e982
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e69e2b49ea642509f0c688c16fb190b7cf27dac0a18903a5e2d1467d0343d8b8
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": 0.0010269576379974327,
5
  "eval_steps": 13,
6
- "global_step": 39,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -60,6 +60,20 @@
60
  "eval_samples_per_second": 10.615,
61
  "eval_steps_per_second": 5.308,
62
  "step": 39
 
 
 
 
 
 
 
 
 
 
 
 
 
 
63
  }
64
  ],
65
  "logging_steps": 10,
@@ -74,12 +88,12 @@
74
  "should_evaluate": false,
75
  "should_log": false,
76
  "should_save": true,
77
- "should_training_stop": false
78
  },
79
  "attributes": {}
80
  }
81
  },
82
- "total_flos": 2.572497010556928e+16,
83
  "train_batch_size": 2,
84
  "trial_name": null,
85
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.001316612356406965,
5
  "eval_steps": 13,
6
+ "global_step": 50,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
60
  "eval_samples_per_second": 10.615,
61
  "eval_steps_per_second": 5.308,
62
  "step": 39
63
+ },
64
+ {
65
+ "epoch": 0.0010532898851255718,
66
+ "grad_norm": 0.30030256509780884,
67
+ "learning_rate": 2.9289321881345254e-05,
68
+ "loss": 0.3052,
69
+ "step": 40
70
+ },
71
+ {
72
+ "epoch": 0.001316612356406965,
73
+ "grad_norm": 0.33745142817497253,
74
+ "learning_rate": 0.0,
75
+ "loss": 0.3199,
76
+ "step": 50
77
  }
78
  ],
79
  "logging_steps": 10,
 
88
  "should_evaluate": false,
89
  "should_log": false,
90
  "should_save": true,
91
+ "should_training_stop": true
92
  },
93
  "attributes": {}
94
  }
95
  },
96
+ "total_flos": 3.289827907731456e+16,
97
  "train_batch_size": 2,
98
  "trial_name": null,
99
  "trial_params": null