ardaspear commited on
Commit
db7897c
·
verified ·
1 Parent(s): 3fe0115

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:f0973623cc8dc43bc5e669047561c39d8f0afbf1b60f121d20121ae4429d673a
3
  size 247936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f450d5ec238678dd53c81fa4760afc43aa1ffac31a2d444d17525b1dcc3c52cd
3
  size 247936
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f8b62de692ba4f4e3af2c1323ed977e0efc4274204bf835012cba70f20786f2b
3
  size 263024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a135c56bd4b58247709c2526b74e6a9391f2c7d0369c1ca7f306fd289ac187e
3
  size 263024
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5d38d3e87897391be07ecebae20ad9e6a748f69c706e993d8ddaf8a08f395a21
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22eafc848cda5c1757f4581f969ead3b635c07c9c3eee6774c9e5ff8cf8e1bbf
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5ed723721bc2dad2381ab5522e40123ba4aa738fa3e449c48809fa9c2697eb95
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd4a07944f7914b974e23583756a2e0907223f4627a9b1ba247bd8f732140689
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": 0.020460358056265986,
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": 155.569,
74
  "eval_steps_per_second": 39.05,
75
  "step": 18
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 3,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 165465292800.0,
96
  "train_batch_size": 4,
97
  "trial_name": null,
98
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.030690537084398978,
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": 155.569,
74
  "eval_steps_per_second": 39.05,
75
  "step": 18
76
+ },
77
+ {
78
+ "epoch": 0.023870417732310314,
79
+ "grad_norm": 1.5570883750915527,
80
+ "learning_rate": 9.635919272833938e-05,
81
+ "loss": 44.1426,
82
+ "step": 21
83
+ },
84
+ {
85
+ "epoch": 0.027280477408354646,
86
+ "grad_norm": 1.5581414699554443,
87
+ "learning_rate": 9.414737964294636e-05,
88
+ "loss": 44.0753,
89
+ "step": 24
90
+ },
91
+ {
92
+ "epoch": 0.030690537084398978,
93
+ "grad_norm": 1.6539247035980225,
94
+ "learning_rate": 9.145187862775209e-05,
95
+ "loss": 44.0163,
96
+ "step": 27
97
+ },
98
+ {
99
+ "epoch": 0.030690537084398978,
100
+ "eval_loss": 10.998085021972656,
101
+ "eval_runtime": 4.7738,
102
+ "eval_samples_per_second": 155.223,
103
+ "eval_steps_per_second": 38.963,
104
+ "step": 27
105
  }
106
  ],
107
  "logging_steps": 3,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 244061306880.0,
125
  "train_batch_size": 4,
126
  "trial_name": null,
127
  "trial_params": null