tuantmdev commited on
Commit
e05c48e
·
verified ·
1 Parent(s): 8b07beb

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 sha256:2e4e05c39b33b91b5a411641353cd595b0dc08c99113192a97f3c4f5f2e0ba75
3
  size 47235968
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71d1d02720144ca34cf33efaa4a951ebf0a454fd7760aee3c971c6dd43e4f709
3
  size 47235968
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9d823f1b068afae847feef2ef5219c352ecf5617204a1f6348b6d70439675401
3
  size 24410836
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:53d8f496a6fbf2c787b6aaed405073c08fce1752c4e6d5a46306124a396c111a
3
  size 24410836
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7acff8847d7154263f9f5e43bc4e1a58d495150178d68bfd78122f6c5b2f79b3
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c83389032cb360a20a445f7dea9b8d251034a0ba7eea8f9d0052124c8029af30
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": 0.14193834553115992,
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": 8.712,
76
  "eval_steps_per_second": 4.365,
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": 1.04611511795712e+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": 0.17742293191394987,
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": 8.712,
76
  "eval_steps_per_second": 4.365,
77
  "step": 40
78
+ },
79
+ {
80
+ "epoch": 0.17742293191394987,
81
+ "grad_norm": 4.46636962890625,
82
+ "learning_rate": 0.0,
83
+ "loss": 1.7662,
84
+ "step": 50
85
+ },
86
+ {
87
+ "epoch": 0.17742293191394987,
88
+ "eval_loss": 1.8663088083267212,
89
+ "eval_runtime": 54.7312,
90
+ "eval_samples_per_second": 8.679,
91
+ "eval_steps_per_second": 4.349,
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": 1.3076438974464e+16,
113
  "train_batch_size": 2,
114
  "trial_name": null,
115
  "trial_params": null