vertings6 commited on
Commit
7c997d3
·
verified ·
1 Parent(s): fd09139

Training in progress, step 30, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1bf00bd1729e93096ba65d420e90a901035c7cde995818109e307db01e41fa9c
3
  size 222865880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e38ba09f3080c3cf4845143f85cdc1b1eba526bafdc0665a85aaa408c8debfb
3
  size 222865880
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5799b844a7352f37c92e44621a1173ea3584fd158ec0e52694ab64fda2dcdbe8
3
  size 445914554
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:05af45455b0c2309cd78267957aa1baa133f27606337876c7b5d2927aac6ded5
3
  size 445914554
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:90457f2aa05b0bf6c779e9c18eabfb4d5b3e6a7ed4d46f5f4d989d3f73ffe883
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5629383624f3805eabef5e5d7e7466a69938ec72628a6783a5c66bfb70731669
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:46d68217ddf3e899bf1495ee33b9ec14e2c91ed912ffcb460a7bb01192b04b7d
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f0e9cc72c20ddd925ef39b6005e82a4d8730b1dde32cfcd070d74c83a8a3564a
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": 0.0006779718472190442,
5
  "eval_steps": 8,
6
- "global_step": 20,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -73,6 +73,42 @@
73
  "learning_rate": 6.545084971874738e-05,
74
  "loss": 5.5828,
75
  "step": 18
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 3,
@@ -87,12 +123,12 @@
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": 1.361684987904e+16,
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": 0.0010169577708285663,
5
  "eval_steps": 8,
6
+ "global_step": 30,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
73
  "learning_rate": 6.545084971874738e-05,
74
  "loss": 5.5828,
75
  "step": 18
76
+ },
77
+ {
78
+ "epoch": 0.0007118704395799964,
79
+ "grad_norm": 1.8414465188980103,
80
+ "learning_rate": 4.2178276747988446e-05,
81
+ "loss": 5.3067,
82
+ "step": 21
83
+ },
84
+ {
85
+ "epoch": 0.0008135662166628531,
86
+ "grad_norm": 2.2933406829833984,
87
+ "learning_rate": 2.061073738537635e-05,
88
+ "loss": 5.2307,
89
+ "step": 24
90
+ },
91
+ {
92
+ "epoch": 0.0008135662166628531,
93
+ "eval_loss": 1.2488714456558228,
94
+ "eval_runtime": 2929.3994,
95
+ "eval_samples_per_second": 4.24,
96
+ "eval_steps_per_second": 2.12,
97
+ "step": 24
98
+ },
99
+ {
100
+ "epoch": 0.0009152619937457097,
101
+ "grad_norm": 2.308497190475464,
102
+ "learning_rate": 5.449673790581611e-06,
103
+ "loss": 5.3056,
104
+ "step": 27
105
+ },
106
+ {
107
+ "epoch": 0.0010169577708285663,
108
+ "grad_norm": 2.603907585144043,
109
+ "learning_rate": 0.0,
110
+ "loss": 4.5462,
111
+ "step": 30
112
  }
113
  ],
114
  "logging_steps": 3,
 
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": 2.042527481856e+16,
132
  "train_batch_size": 2,
133
  "trial_name": null,
134
  "trial_params": null