tuanna08go commited on
Commit
06e6669
·
verified ·
1 Parent(s): faf276d

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 sha256:04e3e90a19e1b7b51ebf2797b0006f89f11e878ec74d42441e8b1041a07dbd94
3
  size 25271744
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ae5193aef9c2ac01aa93455254e3c21b3eea1b7982f0dc5960d6dd42a8115bd
3
  size 25271744
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ab0f6fb866f6b81109c70d104caa89e258bfd426197dd78ccf631f81ef33d2cd
3
  size 13685516
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e896deee6297f4975c80877830fdd2d73db14fff46752ee96a6947e105655721
3
  size 13685516
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:551c6190aa7460da0f5f87f766f1e262863111d15319ee98d5b09ac189feeb2f
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d6a9101315bed33e0f3a0fc84fd93cd1f88e425b915b76ec585cd3942cf27abe
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": 0.14233576642335766,
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": 1.9102,
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": 997588715175936.0,
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": 0.18248175182481752,
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": 1.9102,
90
  "step": 35
91
+ },
92
+ {
93
+ "epoch": 0.145985401459854,
94
+ "grad_norm": 0.5841451287269592,
95
+ "learning_rate": 1.4644660940672627e-05,
96
+ "loss": 1.93,
97
+ "step": 40
98
+ },
99
+ {
100
+ "epoch": 0.145985401459854,
101
+ "eval_loss": 1.834256649017334,
102
+ "eval_runtime": 2.2161,
103
+ "eval_samples_per_second": 52.343,
104
+ "eval_steps_per_second": 26.172,
105
+ "step": 40
106
+ },
107
+ {
108
+ "epoch": 0.16423357664233576,
109
+ "grad_norm": 0.5830029845237732,
110
+ "learning_rate": 3.8060233744356633e-06,
111
+ "loss": 1.7527,
112
+ "step": 45
113
+ },
114
+ {
115
+ "epoch": 0.18248175182481752,
116
+ "grad_norm": 0.643513560295105,
117
+ "learning_rate": 0.0,
118
+ "loss": 1.8492,
119
+ "step": 50
120
+ },
121
+ {
122
+ "epoch": 0.18248175182481752,
123
+ "eval_loss": 1.8075827360153198,
124
+ "eval_runtime": 2.3061,
125
+ "eval_samples_per_second": 50.302,
126
+ "eval_steps_per_second": 25.151,
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": 1278959891251200.0,
148
  "train_batch_size": 2,
149
  "trial_name": null,
150
  "trial_params": null