Best000 commited on
Commit
4000a5a
·
verified ·
1 Parent(s): a2274fb

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:c53f69c0685f85cda688a3f507446787d6f1874abad76753a0b2887789154ec7
3
  size 111454040
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aef18dae2ed5363a2c85ebf14b785911e49d898a97cd02645b866046bfdd1e2a
3
  size 111454040
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8198630de214651781b34c55413089f5daedd8a8635598cfc22de19683d9892b
3
  size 56950676
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:069e61fe79d72ade76156f8f8b678deae62c3aa117c5a5311d7b63c1a5f69ea3
3
  size 56950676
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2075dc3c78e257ad6cd111a44653d45cf19468a8afefec8449d7f5528186c504
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a8e9326efed4b8b174f8cd20eac8ea6327adbd5b9a38abb6099979394893c86b
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8a31de681372f89725884c16f61509c8be9fe1aabdebb5de708e80e690a719fa
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0dab003e9948eca4252e780eaf54f5324b8b378549ca6bfe1415f38792ae85c0
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": 0.06018518518518518,
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": 16.07,
61
  "eval_steps_per_second": 8.064,
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": 1.42689429356544e+16,
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": 0.07716049382716049,
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": 16.07,
61
  "eval_steps_per_second": 8.064,
62
  "step": 39
63
+ },
64
+ {
65
+ "epoch": 0.06172839506172839,
66
+ "grad_norm": 2.977293014526367,
67
+ "learning_rate": 0.00016,
68
+ "loss": 2.0573,
69
+ "step": 40
70
+ },
71
+ {
72
+ "epoch": 0.07716049382716049,
73
+ "grad_norm": 1.9982236623764038,
74
+ "learning_rate": 0.0002,
75
+ "loss": 1.5576,
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": 1.84307179585536e+16,
97
  "train_batch_size": 2,
98
  "trial_name": null,
99
  "trial_params": null