oldiday commited on
Commit
752ed18
·
verified ·
1 Parent(s): a9c7a85

Training in progress, step 27, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:789ac4e6f3c49815c5a9abe4ec8daa964addf983b71c92963e8acfa0f3a67a41
3
  size 159967880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:51b6838d5a8de26b4b4ecd8cceaa880bc60b4bf96e5d4c72c4a11f2f920abb07
3
  size 159967880
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:22ade805d22eec73ef3454d33f34b81b5b46c9a12be43ba3954a593c61512ed9
3
  size 81730196
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e1f564eb14032574f6d339cb07f8f6f3ef1ac347e27078c543fe02561fd15d6b
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:eb6a79165f04c95155eea3cef232d7ad5b7fcc152b03a61b93df3fbc7438c096
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e53bb1bec5a15dde25e11aada4e558caf150777408abe7fff1952dcd58e5b1dc
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e7f75dad5b4fa698adb63b89c53682112a536ec6b4f570bd7793123dfd2a0133
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:95e5b5e126f269e3dd52e13e2ce68743557810f4e2bb59a1eda63231c7828066
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": 0.3582089552238806,
5
  "eval_steps": 9,
6
- "global_step": 18,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -73,6 +73,35 @@
73
  "eval_samples_per_second": 15.057,
74
  "eval_steps_per_second": 1.949,
75
  "step": 18
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 3,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 2.3524495268511744e+16,
96
  "train_batch_size": 8,
97
  "trial_name": null,
98
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.5373134328358209,
5
  "eval_steps": 9,
6
+ "global_step": 27,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
73
  "eval_samples_per_second": 15.057,
74
  "eval_steps_per_second": 1.949,
75
  "step": 18
76
+ },
77
+ {
78
+ "epoch": 0.417910447761194,
79
+ "grad_norm": 0.6026838421821594,
80
+ "learning_rate": 4.817959636416969e-05,
81
+ "loss": 1.2678,
82
+ "step": 21
83
+ },
84
+ {
85
+ "epoch": 0.47761194029850745,
86
+ "grad_norm": 0.6281826496124268,
87
+ "learning_rate": 4.707368982147318e-05,
88
+ "loss": 1.2053,
89
+ "step": 24
90
+ },
91
+ {
92
+ "epoch": 0.5373134328358209,
93
+ "grad_norm": 0.626505434513092,
94
+ "learning_rate": 4.572593931387604e-05,
95
+ "loss": 1.1997,
96
+ "step": 27
97
+ },
98
+ {
99
+ "epoch": 0.5373134328358209,
100
+ "eval_loss": 1.1615190505981445,
101
+ "eval_runtime": 5.6361,
102
+ "eval_samples_per_second": 15.081,
103
+ "eval_steps_per_second": 1.952,
104
+ "step": 27
105
  }
106
  ],
107
  "logging_steps": 3,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 3.5286742902767616e+16,
125
  "train_batch_size": 8,
126
  "trial_name": null,
127
  "trial_params": null