vmpsergio commited on
Commit
e57134f
·
verified ·
1 Parent(s): ddcbaad

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 sha256:908fd24026f5451bd03cada7988fd41b8e05cd3c81d741b3b5845a994bad50e0
3
  size 167832240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:82234c803df1879cf4aa64fedb7e88ea33ce663552c5f96a92554255fb07ea09
3
  size 167832240
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:273abb3cf228a216d7741d78e29dedbc75edc0ea76bcc0ff0ae4ec4a64901a7d
3
  size 335810490
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:66bbd6dcb6cb8c0936b3c6dc0a2740d6632b2b92b15d29d66d17e3722452f4f3
3
  size 335810490
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:21fff8de22d0ff9ed9e786be67a3f53c9ff83a47147f58569fe0298fd057ed81
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af5bfdae06c4df1c32effe183639b54f9e9d621cf4821fc0bf2b7906c11602d8
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": 0.004564646810453041,
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": 2.0524,
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": 8068024208719872.0,
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": 0.006846970215679562,
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": 2.0524,
75
  "step": 18
76
+ },
77
+ {
78
+ "epoch": 0.004792879150975694,
79
+ "grad_norm": 0.5455082058906555,
80
+ "learning_rate": 8.435655349597689e-05,
81
+ "loss": 2.0345,
82
+ "step": 21
83
+ },
84
+ {
85
+ "epoch": 0.005477576172543649,
86
+ "grad_norm": 1.0996414422988892,
87
+ "learning_rate": 4.12214747707527e-05,
88
+ "loss": 2.0625,
89
+ "step": 24
90
+ },
91
+ {
92
+ "epoch": 0.005477576172543649,
93
+ "eval_loss": 2.0255534648895264,
94
+ "eval_runtime": 258.4482,
95
+ "eval_samples_per_second": 7.139,
96
+ "eval_steps_per_second": 3.571,
97
+ "step": 24
98
+ },
99
+ {
100
+ "epoch": 0.0061622731941116055,
101
+ "grad_norm": 0.6625553965568542,
102
+ "learning_rate": 1.0899347581163221e-05,
103
+ "loss": 2.0498,
104
+ "step": 27
105
+ },
106
+ {
107
+ "epoch": 0.006846970215679562,
108
+ "grad_norm": 0.5361489057540894,
109
+ "learning_rate": 0.0,
110
+ "loss": 2.124,
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": 1.2148404268302336e+16,
132
  "train_batch_size": 2,
133
  "trial_name": null,
134
  "trial_params": null