tuantmdev commited on
Commit
263614f
·
verified ·
1 Parent(s): e96a920

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:f0c59b0d8ba090ed0182d463d590b0db1cacc42c22d7606e724247be6b15eba7
3
  size 50899792
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:86b91976de11bcfab03d758455ab28e3fec389bfa74b3d9c4ce0bf57b49fb29a
3
  size 50899792
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:84e01a9de579fc0c7b23ee8028c21d18b6ab866aaeee24e95657face43288f3d
3
  size 26231300
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ec63f962f6222b3f3f440ccc86806d1c831842eea41056ecf7d926846c7170d
3
  size 26231300
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:68317d59c2b9af9805bb4ff062aac86de13742bfffebe094c69ff1c04aab965e
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:70019406248dc5229d953975eae433cd322f8b78c327470ffe9aaf75600c2018
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:053f8a597fb71bde446a175404cc18fe6996cf501293c3abfb94953dfd03d780
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c9b23fe3d7c8cff984a05b7865b1b491bac693fd2f496a4e0e24b70ad75a25bd
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": 0.3823178016726404,
5
  "eval_steps": 10,
6
- "global_step": 40,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -75,6 +75,21 @@
75
  "eval_samples_per_second": 9.524,
76
  "eval_steps_per_second": 4.789,
77
  "step": 40
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
78
  }
79
  ],
80
  "logging_steps": 10,
@@ -89,12 +104,12 @@
89
  "should_evaluate": false,
90
  "should_log": false,
91
  "should_save": true,
92
- "should_training_stop": false
93
  },
94
  "attributes": {}
95
  }
96
  },
97
- "total_flos": 1.31207786397696e+16,
98
  "train_batch_size": 2,
99
  "trial_name": null,
100
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.4778972520908005,
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,
 
75
  "eval_samples_per_second": 9.524,
76
  "eval_steps_per_second": 4.789,
77
  "step": 40
78
+ },
79
+ {
80
+ "epoch": 0.4778972520908005,
81
+ "grad_norm": 1.7326736450195312,
82
+ "learning_rate": 0.0,
83
+ "loss": 2.5816,
84
+ "step": 50
85
+ },
86
+ {
87
+ "epoch": 0.4778972520908005,
88
+ "eval_loss": 2.640730619430542,
89
+ "eval_runtime": 18.6037,
90
+ "eval_samples_per_second": 9.514,
91
+ "eval_steps_per_second": 4.784,
92
+ "step": 50
93
  }
94
  ],
95
  "logging_steps": 10,
 
104
  "should_evaluate": false,
105
  "should_log": false,
106
  "should_save": true,
107
+ "should_training_stop": true
108
  },
109
  "attributes": {}
110
  }
111
  },
112
+ "total_flos": 1.6400973299712e+16,
113
  "train_batch_size": 2,
114
  "trial_name": null,
115
  "trial_params": null