tuanna08go commited on
Commit
d3e5d32
·
verified ·
1 Parent(s): 875506d

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:b2a59d1ccda8f97151165a11e69ca69caaf25f50ab9e81f1332ea0dc7433c3f1
3
  size 50899792
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b7595f3a61fbf5805f9ce76882ea6cfde3a1d5851721c8197c0bdcb7b4ae802a
3
  size 50899792
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:43024a5dfc3df453167764bdac4032f2c73238136ca3bafec3e98dec3993ff30
3
  size 26231300
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b2439603d6ba8643d130d976fd729cbc595e533599fe86cb43142aee53d996a
3
  size 26231300
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5e7e00ca5fad72cfd20c0e9e378736a9bbd2ee075722d6217cb57cfca1974f1d
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd98ea5de01b63c70cc53082a7e61abf25c3dfbb96bea03337b421f29ca94647
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": 0.18034682080924855,
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": 1.388,
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": 3833727508807680.0,
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": 0.23121387283236994,
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": 1.388,
90
  "step": 35
91
+ },
92
+ {
93
+ "epoch": 0.18497109826589594,
94
+ "grad_norm": 7.144972801208496,
95
+ "learning_rate": 1.4644660940672627e-05,
96
+ "loss": 1.3442,
97
+ "step": 40
98
+ },
99
+ {
100
+ "epoch": 0.18497109826589594,
101
+ "eval_loss": 1.1969767808914185,
102
+ "eval_runtime": 4.4389,
103
+ "eval_samples_per_second": 20.726,
104
+ "eval_steps_per_second": 10.363,
105
+ "step": 40
106
+ },
107
+ {
108
+ "epoch": 0.20809248554913296,
109
+ "grad_norm": 13.571349143981934,
110
+ "learning_rate": 3.8060233744356633e-06,
111
+ "loss": 1.1415,
112
+ "step": 45
113
+ },
114
+ {
115
+ "epoch": 0.23121387283236994,
116
+ "grad_norm": 5.618630409240723,
117
+ "learning_rate": 0.0,
118
+ "loss": 1.2559,
119
+ "step": 50
120
+ },
121
+ {
122
+ "epoch": 0.23121387283236994,
123
+ "eval_loss": 1.1580039262771606,
124
+ "eval_runtime": 4.4498,
125
+ "eval_samples_per_second": 20.675,
126
+ "eval_steps_per_second": 10.338,
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": 4817785906790400.0,
148
  "train_batch_size": 2,
149
  "trial_name": null,
150
  "trial_params": null