TachyHealthResearch commited on
Commit
6089c77
·
1 Parent(s): cbe41fe

Training in progress, step 20, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:487e75bd246e2976f4e859e009711ff15c623e88c65c7c1fbb980e8f93a91051
3
  size 125248064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a545a2334935f0ceb44fd22576f243dfbfd282afb137f3852f6c8b158d7cdf0
3
  size 125248064
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0b289b7aa2599ab41117530c1f5895e6c5c358e2557c76eb45a57cac5c138ee1
3
  size 63350356
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3db121c88e5d683427da5b417de88dc4e6caf0fd38255739d5034394bdb437ff
3
  size 63350356
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e5d185880e7fabcea80425635bb46b445f79d8628025d1e32bd0c3c1a767c69f
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4af710ad4f274faa9b58f6cf20fac7055b576fc6d71184444a1ebd38ff3ab5cf
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:015297debedbc8276e2c5e791423807492998247cf413641fcbc7e97c9f4f567
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f71f4cdd57db93caa0e11efdf70fa4ba465ba18c8a6ada689ee3d6ac9256e694
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": 0.006,
5
  "eval_steps": 1000,
6
- "global_step": 15,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -97,13 +97,43 @@
97
  "learning_rate": 0.00018367346938775512,
98
  "loss": 1.7967,
99
  "step": 15
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
100
  }
101
  ],
102
  "logging_steps": 1,
103
  "max_steps": 150,
104
  "num_train_epochs": 1,
105
  "save_steps": 5,
106
- "total_flos": 1808974570045440.0,
107
  "trial_name": null,
108
  "trial_params": null
109
  }
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.008,
5
  "eval_steps": 1000,
6
+ "global_step": 20,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
97
  "learning_rate": 0.00018367346938775512,
98
  "loss": 1.7967,
99
  "step": 15
100
+ },
101
+ {
102
+ "epoch": 0.01,
103
+ "learning_rate": 0.00018231292517006804,
104
+ "loss": 1.5366,
105
+ "step": 16
106
+ },
107
+ {
108
+ "epoch": 0.01,
109
+ "learning_rate": 0.00018095238095238095,
110
+ "loss": 1.7421,
111
+ "step": 17
112
+ },
113
+ {
114
+ "epoch": 0.01,
115
+ "learning_rate": 0.0001795918367346939,
116
+ "loss": 2.5308,
117
+ "step": 18
118
+ },
119
+ {
120
+ "epoch": 0.01,
121
+ "learning_rate": 0.00017823129251700681,
122
+ "loss": 1.5277,
123
+ "step": 19
124
+ },
125
+ {
126
+ "epoch": 0.01,
127
+ "learning_rate": 0.00017687074829931973,
128
+ "loss": 1.9084,
129
+ "step": 20
130
  }
131
  ],
132
  "logging_steps": 1,
133
  "max_steps": 150,
134
  "num_train_epochs": 1,
135
  "save_steps": 5,
136
+ "total_flos": 2841084152954880.0,
137
  "trial_name": null,
138
  "trial_params": null
139
  }