leixa commited on
Commit
6eef394
·
verified ·
1 Parent(s): 7072cf4

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 sha256:4e07bc591852d0e285d8b0eb7533e265ec163731062b7868d98b73ad5510c105
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ee58f8e27f2fc1059ae70606fe51d0fd203ef2401c92881cd2b4cf032c9a337
3
  size 83945296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3192ff0b296efa5ad603bf7066f835a61f40619b5a81c11c11be416f18ebb56c
3
  size 43122580
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c3b4e44b5d84728f926b187b2d908494b487af982e13674e179107dd7a181ab
3
  size 43122580
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:072bfc605f4863f84b71593319f5d30a58b3bf32c4e6fabdb0e59c181f4cf9e8
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ad98cf992223f8ad553f8ddb570a53036ebcca6530831805bb5790abefc00b3
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": 0.43213296398891965,
5
  "eval_steps": 13,
6
- "global_step": 39,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -88,6 +88,27 @@
88
  "eval_samples_per_second": 21.678,
89
  "eval_steps_per_second": 10.839,
90
  "step": 39
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
91
  }
92
  ],
93
  "logging_steps": 5,
@@ -102,12 +123,12 @@
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": 7259539673972736.0,
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": 0.554016620498615,
5
  "eval_steps": 13,
6
+ "global_step": 50,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
88
  "eval_samples_per_second": 21.678,
89
  "eval_steps_per_second": 10.839,
90
  "step": 39
91
+ },
92
+ {
93
+ "epoch": 0.44321329639889195,
94
+ "grad_norm": 1.2946439981460571,
95
+ "learning_rate": 1.4644660940672627e-05,
96
+ "loss": 0.1537,
97
+ "step": 40
98
+ },
99
+ {
100
+ "epoch": 0.4986149584487535,
101
+ "grad_norm": 2.3463804721832275,
102
+ "learning_rate": 3.8060233744356633e-06,
103
+ "loss": 0.1233,
104
+ "step": 45
105
+ },
106
+ {
107
+ "epoch": 0.554016620498615,
108
+ "grad_norm": 2.3438780307769775,
109
+ "learning_rate": 0.0,
110
+ "loss": 0.1106,
111
+ "step": 50
112
  }
113
  ],
114
  "logging_steps": 5,
 
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": 9294060346933248.0,
132
  "train_batch_size": 2,
133
  "trial_name": null,
134
  "trial_params": null