duyphu commited on
Commit
6589db7
·
verified ·
1 Parent(s): 3d38897

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 sha256:22c6034b33d2c004348fdfa291076bb6da556faebb2036f22edd582f50bebee4
3
  size 48679352
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5495022b94a48ac4ef79902a60ca60df5b03913b7518070b21a790c1db12715d
3
  size 48679352
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4f1afca020a835e7efe6b318a7cb88ba59995e32de72f36f19ee06700f4a37fe
3
  size 25152500
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2666c5f63e109b7246051e9627476f830b8d8789584bd880f1e4d78b33da74c8
3
  size 25152500
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:07826b0a1715771cf8401779e148b2e054e92f43284fa32f35d7a2caedc00d70
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ae91c81bb1bda2bfa96330f9b07ba8a071665d1b8c7a5fc225f5ea9c74fbbc2
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0c50dbaa792cda4a28fbbc2acb2a3e03c59530712bbc5107212d33064d193da4
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
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": 0.006594800253646164,
5
  "eval_steps": 10,
6
- "global_step": 39,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -88,6 +88,43 @@
88
  "learning_rate": 3.086582838174551e-05,
89
  "loss": 0.469,
90
  "step": 35
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
91
  }
92
  ],
93
  "logging_steps": 5,
@@ -102,12 +139,12 @@
102
  "should_evaluate": false,
103
  "should_log": false,
104
  "should_save": true,
105
- "should_training_stop": false
106
  },
107
  "attributes": {}
108
  }
109
  },
110
- "total_flos": 4417841340088320.0,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.008454872120059184,
5
  "eval_steps": 10,
6
+ "global_step": 50,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
88
  "learning_rate": 3.086582838174551e-05,
89
  "loss": 0.469,
90
  "step": 35
91
+ },
92
+ {
93
+ "epoch": 0.006763897696047347,
94
+ "grad_norm": 0.46769002079963684,
95
+ "learning_rate": 1.4644660940672627e-05,
96
+ "loss": 0.4661,
97
+ "step": 40
98
+ },
99
+ {
100
+ "epoch": 0.006763897696047347,
101
+ "eval_loss": 0.504737913608551,
102
+ "eval_runtime": 143.4632,
103
+ "eval_samples_per_second": 17.356,
104
+ "eval_steps_per_second": 8.678,
105
+ "step": 40
106
+ },
107
+ {
108
+ "epoch": 0.007609384908053266,
109
+ "grad_norm": 0.384360671043396,
110
+ "learning_rate": 3.8060233744356633e-06,
111
+ "loss": 0.5072,
112
+ "step": 45
113
+ },
114
+ {
115
+ "epoch": 0.008454872120059184,
116
+ "grad_norm": 0.3384287357330322,
117
+ "learning_rate": 0.0,
118
+ "loss": 0.4794,
119
+ "step": 50
120
+ },
121
+ {
122
+ "epoch": 0.008454872120059184,
123
+ "eval_loss": 0.5036466121673584,
124
+ "eval_runtime": 143.0377,
125
+ "eval_samples_per_second": 17.408,
126
+ "eval_steps_per_second": 8.704,
127
+ "step": 50
128
  }
129
  ],
130
  "logging_steps": 5,
 
139
  "should_evaluate": false,
140
  "should_log": false,
141
  "should_save": true,
142
+ "should_training_stop": true
143
  },
144
  "attributes": {}
145
  }
146
  },
147
+ "total_flos": 5600570517749760.0,
148
  "train_batch_size": 2,
149
  "trial_name": null,
150
  "trial_params": null