tuantmdev commited on
Commit
c905152
·
verified ·
1 Parent(s): b2a5248

Training in progress, step 200, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:639387f07a7ab6584af739c8f8f450f59120c19eac2f4f757acc6c05707ad77c
3
  size 4731640
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6fe9759b2629e44c4c1615cf84df163cfbf71f18f1a18f085275af23b84f5b15
3
  size 4731640
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:646b4513c0675b30d34cbb9b8bf0a97d544e8d3b4ec4e6ac547b7a1c7b48a99c
3
  size 2505722
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:72e248e94ae8ae1967e08d876a13c23d5d538de2a6261f4f7509a4207910ff59
3
  size 2505722
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:44742a0187788cb9dbab199764793d5537e59da257357a7dada4bfd1170f3f17
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e1ec98e58e70ae9d80fa4a66c28ee0ff6b9f7ffe364b13669792b06d6237b1b
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:500b1c78c9d3af1c55fbf9cc6e380394ac567579f265e54ad9607c3dc9f74108
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb148ad6cd6502048dc3eee274a6708e5b4f6b72c0d56ebc272935446c220acd
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": 0.02697434276381645,
5
  "eval_steps": 40,
6
- "global_step": 160,
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": 37.769,
76
  "eval_steps_per_second": 18.884,
77
  "step": 160
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
78
  }
79
  ],
80
  "logging_steps": 40,
@@ -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": 3278995162398720.0,
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": 0.03371792845477056,
5
  "eval_steps": 40,
6
+ "global_step": 200,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
75
  "eval_samples_per_second": 37.769,
76
  "eval_steps_per_second": 18.884,
77
  "step": 160
78
+ },
79
+ {
80
+ "epoch": 0.03371792845477056,
81
+ "grad_norm": 363.8813171386719,
82
+ "learning_rate": 0.0,
83
+ "loss": 43.8402,
84
+ "step": 200
85
+ },
86
+ {
87
+ "epoch": 0.03371792845477056,
88
+ "eval_loss": 2.733341932296753,
89
+ "eval_runtime": 263.2649,
90
+ "eval_samples_per_second": 37.947,
91
+ "eval_steps_per_second": 18.973,
92
+ "step": 200
93
  }
94
  ],
95
  "logging_steps": 40,
 
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": 4109101097287680.0,
113
  "train_batch_size": 2,
114
  "trial_name": null,
115
  "trial_params": null