brixeus commited on
Commit
63756d1
·
verified ·
1 Parent(s): 17e10b2

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 sha256:3cd07fc9abbcf0b6325202e9d3bca29b46f0d35ed09f02774cf508c5001093d8
3
  size 167832240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a7eb505748dbb7bf16de72e0124352b954e4c7a31ece36a1b7a20eb2cc290c8d
3
  size 167832240
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d6110de3eb64ae128b36129dd44fdfd96feade4e846827ec523ffe42c82c4268
3
  size 85723284
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe4d78d527927b40739df46012adad2bf9f679b3375fcb423d6526ebe5d74bc3
3
  size 85723284
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6cf30c4e1dfd3b199f004d48c615f0058d9d8168fc7715316fa0d2b53a3286f2
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b4f63aec6d8b3291c19fe2b4497f750eeddd6b87b84886cefc94a6bfc39de55
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": 0.0054869684499314125,
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": 13.896,
74
  "eval_steps_per_second": 1.738,
75
  "step": 18
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 3,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 2.531269094355763e+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": 0.00823045267489712,
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": 13.896,
74
  "eval_steps_per_second": 1.738,
75
  "step": 18
76
+ },
77
+ {
78
+ "epoch": 0.006401463191586648,
79
+ "grad_norm": 4.237952709197998,
80
+ "learning_rate": 4.817959636416969e-05,
81
+ "loss": 5.1144,
82
+ "step": 21
83
+ },
84
+ {
85
+ "epoch": 0.007315957933241884,
86
+ "grad_norm": 4.633209228515625,
87
+ "learning_rate": 4.707368982147318e-05,
88
+ "loss": 5.8178,
89
+ "step": 24
90
+ },
91
+ {
92
+ "epoch": 0.00823045267489712,
93
+ "grad_norm": 3.6630399227142334,
94
+ "learning_rate": 4.572593931387604e-05,
95
+ "loss": 5.1011,
96
+ "step": 27
97
+ },
98
+ {
99
+ "epoch": 0.00823045267489712,
100
+ "eval_loss": 1.3356471061706543,
101
+ "eval_runtime": 397.6104,
102
+ "eval_samples_per_second": 13.896,
103
+ "eval_steps_per_second": 1.738,
104
+ "step": 27
105
  }
106
  ],
107
  "logging_steps": 3,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 3.796903641533645e+16,
125
  "train_batch_size": 8,
126
  "trial_name": null,
127
  "trial_params": null