ardaspear commited on
Commit
0897871
·
verified ·
1 Parent(s): 216dbaa

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 sha256:383ea962f92e8fc5acdd508dc5d7f7f75a761dfaaa3051b195e72d3641e8df33
3
  size 72396376
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef6ee9b4fa312dc8d2b1ac0d9bacd3b6868eb8fd5db2204b95d2f173a3359aaa
3
  size 72396376
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6a29ed8ea3e92c7e18588f95fdcc6845689c79c1a1fc351fcfecfd32dd2145cc
3
  size 37134420
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a7127605096f8d1648931add3c1995fda8931947b6f52052ff0aa196b19231f0
3
  size 37134420
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:631b5f120753a03c3d31ac5890e9122e30e9812cfe106e22a3de761e8a80e371
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb40773f3e0d9ff84c1a29aea2fad96cc8c7e46be03bcae9e0e2ce0f7eb2757a
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": 0.036308623298033284,
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": 17.571,
74
  "eval_steps_per_second": 2.21,
75
  "step": 18
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 3,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 1.1528471222157312e+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": 0.05446293494704992,
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": 17.571,
74
  "eval_steps_per_second": 2.21,
75
  "step": 18
76
+ },
77
+ {
78
+ "epoch": 0.04236006051437216,
79
+ "grad_norm": 0.07574637979269028,
80
+ "learning_rate": 4.817959636416969e-05,
81
+ "loss": 1.3475,
82
+ "step": 21
83
+ },
84
+ {
85
+ "epoch": 0.048411497730711045,
86
+ "grad_norm": 0.06648290902376175,
87
+ "learning_rate": 4.707368982147318e-05,
88
+ "loss": 1.2828,
89
+ "step": 24
90
+ },
91
+ {
92
+ "epoch": 0.05446293494704992,
93
+ "grad_norm": 0.07902548462152481,
94
+ "learning_rate": 4.572593931387604e-05,
95
+ "loss": 1.3281,
96
+ "step": 27
97
+ },
98
+ {
99
+ "epoch": 0.05446293494704992,
100
+ "eval_loss": 1.3498567342758179,
101
+ "eval_runtime": 47.5478,
102
+ "eval_samples_per_second": 17.561,
103
+ "eval_steps_per_second": 2.208,
104
+ "step": 27
105
  }
106
  ],
107
  "logging_steps": 3,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 1.7292706833235968e+16,
125
  "train_batch_size": 8,
126
  "trial_name": null,
127
  "trial_params": null