Best000 commited on
Commit
399a15b
·
verified ·
1 Parent(s): bd6af44

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 sha256:1768afbd8f52fee9d41030742dab94e5f55a854fd2d6042420e9a32cb120ab87
3
  size 80792096
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d1ce3c24bb2cda0b69a4dc28f0f6aeceb04d00560f30277856cc3273ce9b60d
3
  size 80792096
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5d017b73d91b33f88359c8c23f551321a7a7e71ff7dff7ce2902a2c3c2768b79
3
  size 41459700
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1fb3c4cf77ad59b9ac29bb05a7a15eb389479c16450947c2d53195a6a56bd184
3
  size 41459700
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7569a9cdb08554d4a832d7202284fc3bca41833a2f4143b049eb740311660cd6
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e4b20db99410b026a6041e9a9ccf84ba5c120b659e9abc07176004a9d2c01275
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": 0.00252423099949839,
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": 32.815,
61
  "eval_steps_per_second": 16.408,
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": 7319071393579008.0,
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": 0.0032361935891005,
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": 32.815,
61
  "eval_steps_per_second": 16.408,
62
  "step": 39
63
+ },
64
+ {
65
+ "epoch": 0.0025889548712804,
66
+ "grad_norm": 0.729310929775238,
67
+ "learning_rate": 0.00016,
68
+ "loss": 1.3415,
69
+ "step": 40
70
+ },
71
+ {
72
+ "epoch": 0.0032361935891005,
73
+ "grad_norm": 1.144256353378296,
74
+ "learning_rate": 0.0002,
75
+ "loss": 1.204,
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": 9323102846582784.0,
97
  "train_batch_size": 2,
98
  "trial_name": null,
99
  "trial_params": null