daniel40 commited on
Commit
4aa271f
·
verified ·
1 Parent(s): 0d69444

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 sha256:61f19ff94499888e941370a962b5651b7c9729ad981a363101efbd6b63fb69cf
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87d7f036a4bfc666ccf0525812318820b6d9b1660f3b44d1281f36454ddf30a5
3
  size 83945296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1aca1bf583f0c14290e413a19f285a528f6c828ac8ba5e7428d8bb65fc8403d0
3
  size 43122580
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50045c6f31918d945110a0854df64ce7c41f244c9bf974b822cfcdd52f7cebcf
3
  size 43122580
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:104b09cc6df95f3b0d5e3d0e48bc90e51a986bbda4ae0fd0e8e48388960641a8
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba93f8db423cb3b679c79a7db27151bfbed53e821114d602901acf9157000a85
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": 0.10331125827814569,
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": 24.742,
61
  "eval_steps_per_second": 12.449,
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": 7843197292118016.0,
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": 0.13245033112582782,
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": 24.742,
61
  "eval_steps_per_second": 12.449,
62
  "step": 39
63
+ },
64
+ {
65
+ "epoch": 0.10596026490066225,
66
+ "grad_norm": 7.373494625091553,
67
+ "learning_rate": 2.9289321881345254e-05,
68
+ "loss": 7.258,
69
+ "step": 40
70
+ },
71
+ {
72
+ "epoch": 0.13245033112582782,
73
+ "grad_norm": 8.604551315307617,
74
+ "learning_rate": 0.0,
75
+ "loss": 7.0096,
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": 9858767545958400.0,
97
  "train_batch_size": 2,
98
  "trial_name": null,
99
  "trial_params": null