duyphu commited on
Commit
e77fcec
·
verified ·
1 Parent(s): dd5640d

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 sha256:3627bb0249f1432f24d597e26dc9f3aa5635f899383447f4d5953a476dc48756
3
  size 144805440
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9bfd9356bceeb54b4f7caa2acc504c09196c37a1971b6b19ae5561758a9a8d50
3
  size 144805440
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:eeaf5dfc9f4c1252e10c73f9f208e162778cfed7c108cc1413c493cf547bf0ab
3
  size 74291604
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fbe16573dbf67cb844727cae6593dca8ef7b15f398c46b9adf3d368ad7de6310
3
  size 74291604
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8cce00927943e545f38db920e14c68afdcbd9c32a13585978045f5eaff63d9c2
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b6fdb25d8aaba00761ed5aca09337bb966cfac27797928fea61ca14ae2db0cb4
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": 0.10283454185893211,
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": 0.1221,
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": 1.2631125277016064e+16,
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": 0.13183915622940012,
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": 0.1221,
90
  "step": 35
91
+ },
92
+ {
93
+ "epoch": 0.1054713249835201,
94
+ "grad_norm": 8.429944038391113,
95
+ "learning_rate": 1.4644660940672627e-05,
96
+ "loss": 0.1087,
97
+ "step": 40
98
+ },
99
+ {
100
+ "epoch": 0.1054713249835201,
101
+ "eval_loss": 0.09574756771326065,
102
+ "eval_runtime": 20.1599,
103
+ "eval_samples_per_second": 7.937,
104
+ "eval_steps_per_second": 3.968,
105
+ "step": 40
106
+ },
107
+ {
108
+ "epoch": 0.11865524060646011,
109
+ "grad_norm": 20.386011123657227,
110
+ "learning_rate": 3.8060233744356633e-06,
111
+ "loss": 0.1,
112
+ "step": 45
113
+ },
114
+ {
115
+ "epoch": 0.13183915622940012,
116
+ "grad_norm": 8.91682243347168,
117
+ "learning_rate": 0.0,
118
+ "loss": 0.2509,
119
+ "step": 50
120
+ },
121
+ {
122
+ "epoch": 0.13183915622940012,
123
+ "eval_loss": 0.0755360797047615,
124
+ "eval_runtime": 19.9856,
125
+ "eval_samples_per_second": 8.006,
126
+ "eval_steps_per_second": 4.003,
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": 1.61937503551488e+16,
148
  "train_batch_size": 2,
149
  "trial_name": null,
150
  "trial_params": null