dimasik2987 commited on
Commit
9369afc
·
verified ·
1 Parent(s): aa0005b

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:ba6e3e7b0b3db904a75b7b7f672093292e9b94f8d52f666348a4eaaa7e25a445
3
  size 50624
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5fe7cb1631e2605b7a9c93c343e23129a6b8aca601ea5c24c0572f2ff40c6890
3
  size 50624
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f89ce4a9ac9690a0a349478c68d909ac5e179a031966799d0ce5c9db447e6f9c
3
  size 118090
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fcfe6eb19f53ddfcc50720f9595e1d6d97d2b554d0a44f994b4fc11ee5c7773f
3
  size 118090
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a8d9358611d5238c19c59fb3aa3eac2040cbac245a7cfcfe56e1467f677e36cf
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:372c9c91189dafe7a0013b948ff9907e60fc7ad4b32cc7ac3bccb3f603cf2268
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a62e6ea25099651400ff4a3142a50e40bef5b52ba883be53b2fcb9d1a5b0a98c
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
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": 0.00598623166716552,
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": 0.00013090169943749476,
74
  "loss": 10.3743,
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": 1046048931840.0,
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": 0.008979347500748278,
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": 0.00013090169943749476,
74
  "loss": 10.3743,
75
  "step": 18
76
+ },
77
+ {
78
+ "epoch": 0.0062855432505237955,
79
+ "grad_norm": 0.04413003474473953,
80
+ "learning_rate": 8.435655349597689e-05,
81
+ "loss": 10.3742,
82
+ "step": 21
83
+ },
84
+ {
85
+ "epoch": 0.007183478000598623,
86
+ "grad_norm": 0.04242898151278496,
87
+ "learning_rate": 4.12214747707527e-05,
88
+ "loss": 10.3731,
89
+ "step": 24
90
+ },
91
+ {
92
+ "epoch": 0.007183478000598623,
93
+ "eval_loss": 10.373275756835938,
94
+ "eval_runtime": 12.7555,
95
+ "eval_samples_per_second": 110.305,
96
+ "eval_steps_per_second": 55.192,
97
+ "step": 24
98
+ },
99
+ {
100
+ "epoch": 0.008081412750673452,
101
+ "grad_norm": 0.046601515263319016,
102
+ "learning_rate": 1.0899347581163221e-05,
103
+ "loss": 10.3728,
104
+ "step": 27
105
+ },
106
+ {
107
+ "epoch": 0.008979347500748278,
108
+ "grad_norm": 0.04899485409259796,
109
+ "learning_rate": 0.0,
110
+ "loss": 10.3722,
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": 1569073397760.0,
132
  "train_batch_size": 2,
133
  "trial_name": null,
134
  "trial_params": null