tuantmdev commited on
Commit
e9daa9b
·
verified ·
1 Parent(s): 316fca5

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 sha256:4ff2a6763b1ee26cc26d38899637fa3ac9cf9472b92d8d26a3e504dd7dda9d0e
3
  size 36981072
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e07712248df52263b637656f3cc81a1698924f4ecce785e75103e212f14b768
3
  size 36981072
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dfdb20c8bfd22eb2ae48cdf0a886a58ce915d8e1e0991ca24cab1b408a9b0e17
3
  size 19859140
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7052ca1bc69ff704412dd7fb50685bfdc5a32fed9433d71f1697c98967400b5b
3
  size 19859140
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2b8c1e4d49ae7d61d5cfdf7dfbc7f61e119056a1cdfbe71a53667da1470f8ba7
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d84581470cbcfce923b6b2c5157d18116f6934ed620d6194c1295f707b71fbf6
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": 0.03659861611482816,
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": 3.837,
55
  "eval_steps_per_second": 1.92,
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": 5188772136222720.0,
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": 0.0457482701435352,
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": 3.837,
55
  "eval_steps_per_second": 1.92,
56
  "step": 40
57
+ },
58
+ {
59
+ "epoch": 0.0457482701435352,
60
+ "eval_loss": 0.23447348177433014,
61
+ "eval_runtime": 473.8929,
62
+ "eval_samples_per_second": 3.885,
63
+ "eval_steps_per_second": 1.943,
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": 6485965170278400.0,
85
  "train_batch_size": 2,
86
  "trial_name": null,
87
  "trial_params": null