tuantmdev commited on
Commit
bb839e7
·
verified ·
1 Parent(s): 5841430

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 sha256:710ec4e03eb8a1329108f3caba576d4ae4c94af7679d016dbf0ba318396f818c
3
  size 125248064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:554f8744e55bc370acdf6ac8b4f4c1249188b08fd41d78b810fdacbf68d626fe
3
  size 125248064
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7de3a0324555635d139d010ae1ff1034492289a5f889595d0cf58cd5e24f89ef
3
  size 64219860
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5acad660bdba05240a8a8df938e21e1d6be80a17b90ab257e17c2cdeb6f5fb21
3
  size 64219860
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7147ce296746812fb661325c4991f7755b45ce4a53a4d8bba05f4e3f80c1bd78
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c24ce8ab1fffd0afbe6422c86a29aeeac3b49f935d61dbe73b5fa3c3fc8efaba
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": 0.17410228509249184,
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": 3.514,
76
  "eval_steps_per_second": 1.761,
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": 9.364108383092736e+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": 0.2176278563656148,
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": 3.514,
76
  "eval_steps_per_second": 1.761,
77
  "step": 40
78
+ },
79
+ {
80
+ "epoch": 0.2176278563656148,
81
+ "grad_norm": 1.763027548789978,
82
+ "learning_rate": 0.0,
83
+ "loss": 3.4624,
84
+ "step": 50
85
+ },
86
+ {
87
+ "epoch": 0.2176278563656148,
88
+ "eval_loss": 0.20506860315799713,
89
+ "eval_runtime": 110.6033,
90
+ "eval_samples_per_second": 3.499,
91
+ "eval_steps_per_second": 1.754,
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": 1.1651705443713024e+17,
113
  "train_batch_size": 2,
114
  "trial_name": null,
115
  "trial_params": null