tuantmdev commited on
Commit
4d5d37d
·
verified ·
1 Parent(s): 101bd49

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 sha256:5d7b7a0da61877e28c87cc4ffd9f2e9dfaf8830874125edd72e4be83b1223073
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f570be6304b4910fd01806eed136db58ce71dfe236b605514fd53cf07a19e57
3
  size 83945296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:996282b583a294e344d85f611821584bb03426ac5932218086b3b12f57604192
3
  size 43122580
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:86abd70d39503544523bcd57b6261178b3a9f9a789bad929d2a6fecc4445e742
3
  size 43122580
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:16ae7958aba3908f89853844262201daac04359d589f99dfb497f6e44d009b6c
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:659d9f2835294122437b61bd8003b4573b82c4689de3dbfb15ab6c897fb9d74d
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": 0.09425625920471281,
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": 3.948,
76
  "eval_steps_per_second": 1.977,
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": 3.974178739637453e+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": 0.11782032400589101,
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": 3.948,
76
  "eval_steps_per_second": 1.977,
77
  "step": 40
78
+ },
79
+ {
80
+ "epoch": 0.11782032400589101,
81
+ "grad_norm": 13.211586952209473,
82
+ "learning_rate": 0.0,
83
+ "loss": 18.4396,
84
+ "step": 50
85
+ },
86
+ {
87
+ "epoch": 0.11782032400589101,
88
+ "eval_loss": 1.1526776552200317,
89
+ "eval_runtime": 180.9851,
90
+ "eval_samples_per_second": 3.951,
91
+ "eval_steps_per_second": 1.978,
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": 4.955673819768422e+16,
113
  "train_batch_size": 2,
114
  "trial_name": null,
115
  "trial_params": null