tuantmdev commited on
Commit
c1fe78a
·
verified ·
1 Parent(s): 2a5b4e4

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 sha256:54ad9ce7ee48c544024263e856db146d4fe299e49d64c1d53a4f83d60039fa23
3
  size 80013120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:11abd353a969caf103be84084e194859eca39b1c9b8f543076a0f8f679ac085f
3
  size 80013120
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:175543af9e11714a2c3386976cbcc2714cdf25800c6bab5827d344a78c753b97
3
  size 41119636
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b44ba4f992330a7532cc4d3124b24b903b500ee5cf6aa903cc9a8de7665b743
3
  size 41119636
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:293f7bf9fcecc3ab745508812aa10de0e20eefbfd21dc5078d377caf6769f573
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:20fa914ab91d256fb8888425428ffbffd71b3fcfb9d92168eff6baf8f39ad3cb
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": 0.015111803735448986,
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,
@@ -54,6 +54,14 @@
54
  "eval_samples_per_second": 7.488,
55
  "eval_steps_per_second": 3.744,
56
  "step": 40
 
 
 
 
 
 
 
 
57
  }
58
  ],
59
  "logging_steps": 40,
@@ -68,12 +76,12 @@
68
  "should_evaluate": false,
69
  "should_log": false,
70
  "should_save": true,
71
- "should_training_stop": false
72
  },
73
  "attributes": {}
74
  }
75
  },
76
- "total_flos": 2.63651667738624e+16,
77
  "train_batch_size": 2,
78
  "trial_name": null,
79
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.018889754669311233,
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,
 
54
  "eval_samples_per_second": 7.488,
55
  "eval_steps_per_second": 3.744,
56
  "step": 40
57
+ },
58
+ {
59
+ "epoch": 0.018889754669311233,
60
+ "eval_loss": 1.2388581037521362,
61
+ "eval_runtime": 597.804,
62
+ "eval_samples_per_second": 7.457,
63
+ "eval_steps_per_second": 3.729,
64
+ "step": 50
65
  }
66
  ],
67
  "logging_steps": 40,
 
76
  "should_evaluate": false,
77
  "should_log": false,
78
  "should_save": true,
79
+ "should_training_stop": true
80
  },
81
  "attributes": {}
82
  }
83
  },
84
+ "total_flos": 3.2956458467328e+16,
85
  "train_batch_size": 2,
86
  "trial_name": null,
87
  "trial_params": null