kostiantynk commited on
Commit
e05b7ec
·
verified ·
1 Parent(s): b133677

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:dff24b6b05d5a63308067832da6cdb48c63a52688635f4f8118642967bb9c40b
3
  size 159967880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b8e0bee3b216ac2245bc49cfbe22750f2c632d69507c35fe1a8205b70bfa2e69
3
  size 159967880
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:84fac1852db1e17742ad0dba07d06619a6ea79eba997d26d9a25b970ac251a69
3
  size 81730196
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:57e2ae1d5c2d1ee5b31c7491a918def5317ccfb3fb2e442b89715f076d55a74c
3
  size 81730196
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a4c2def82317e76f5437c5ec08617a234bd54bf365c5bbe035a79848052de777
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c92209bf681178360be9c06aac83b2077ed2a430d8af468a3be8ba47bb4d05e
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:216e1a9a1c53e7de93f56319b4855910155cb98dd7ebb5fa08b3717fd303059f
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e69e2b49ea642509f0c688c16fb190b7cf27dac0a18903a5e2d1467d0343d8b8
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": 0.00809884747170595,
5
  "eval_steps": 13,
6
- "global_step": 39,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -60,6 +60,20 @@
60
  "eval_samples_per_second": 17.698,
61
  "eval_steps_per_second": 8.849,
62
  "step": 39
 
 
 
 
 
 
 
 
 
 
 
 
 
 
63
  }
64
  ],
65
  "logging_steps": 10,
@@ -74,12 +88,12 @@
74
  "should_evaluate": false,
75
  "should_log": false,
76
  "should_save": true,
77
- "should_training_stop": false
78
  },
79
  "attributes": {}
80
  }
81
  },
82
- "total_flos": 6445667639623680.0,
83
  "train_batch_size": 2,
84
  "trial_name": null,
85
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.010383137784238397,
5
  "eval_steps": 13,
6
+ "global_step": 50,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
60
  "eval_samples_per_second": 17.698,
61
  "eval_steps_per_second": 8.849,
62
  "step": 39
63
+ },
64
+ {
65
+ "epoch": 0.008306510227390717,
66
+ "grad_norm": 0.41418689489364624,
67
+ "learning_rate": 2.339555568810221e-05,
68
+ "loss": 0.5865,
69
+ "step": 40
70
+ },
71
+ {
72
+ "epoch": 0.010383137784238397,
73
+ "grad_norm": 0.37036439776420593,
74
+ "learning_rate": 0.0,
75
+ "loss": 0.5723,
76
+ "step": 50
77
  }
78
  ],
79
  "logging_steps": 10,
 
88
  "should_evaluate": false,
89
  "should_log": false,
90
  "should_save": true,
91
+ "should_training_stop": true
92
  },
93
  "attributes": {}
94
  }
95
  },
96
+ "total_flos": 8263676461056000.0,
97
  "train_batch_size": 2,
98
  "trial_name": null,
99
  "trial_params": null