TachyHealthResearch
commited on
Commit
•
d42255b
1
Parent(s):
d36b871
Training in progress, step 30, 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:
|
3 |
size 83945296
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:78e965f8a6390205972f53c9273588c19457c6759b764c5ca0f1fe62c45d1080
|
3 |
size 83945296
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 42545748
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4055c9a5a8c092ddc7343a6df05131a34a767e5a7a220836aa4b69f8cc814e91
|
3 |
size 42545748
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14244
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:db05f4be4bfd57c6db9f1684109ea8219cb794f0abafbe3b2696e0554a780ed9
|
3 |
size 14244
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1064
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:85ee19ea163e868f40d9ecdcecd226ea53d13afff03ee0a58dfaa5fb6cd5af1e
|
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.
|
5 |
"eval_steps": 1000,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -127,13 +127,73 @@
|
|
127 |
"learning_rate": 0.00016842105263157895,
|
128 |
"loss": 2.0619,
|
129 |
"step": 20
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
130 |
}
|
131 |
],
|
132 |
"logging_steps": 1,
|
133 |
"max_steps": 100,
|
134 |
"num_train_epochs": 1,
|
135 |
"save_steps": 10,
|
136 |
-
"total_flos":
|
137 |
"trial_name": null,
|
138 |
"trial_params": null
|
139 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.012,
|
5 |
"eval_steps": 1000,
|
6 |
+
"global_step": 30,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
127 |
"learning_rate": 0.00016842105263157895,
|
128 |
"loss": 2.0619,
|
129 |
"step": 20
|
130 |
+
},
|
131 |
+
{
|
132 |
+
"epoch": 0.01,
|
133 |
+
"learning_rate": 0.00016631578947368423,
|
134 |
+
"loss": 2.1024,
|
135 |
+
"step": 21
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.01,
|
139 |
+
"learning_rate": 0.00016421052631578948,
|
140 |
+
"loss": 1.8859,
|
141 |
+
"step": 22
|
142 |
+
},
|
143 |
+
{
|
144 |
+
"epoch": 0.01,
|
145 |
+
"learning_rate": 0.00016210526315789473,
|
146 |
+
"loss": 1.8444,
|
147 |
+
"step": 23
|
148 |
+
},
|
149 |
+
{
|
150 |
+
"epoch": 0.01,
|
151 |
+
"learning_rate": 0.00016,
|
152 |
+
"loss": 2.0529,
|
153 |
+
"step": 24
|
154 |
+
},
|
155 |
+
{
|
156 |
+
"epoch": 0.01,
|
157 |
+
"learning_rate": 0.00015789473684210527,
|
158 |
+
"loss": 1.6784,
|
159 |
+
"step": 25
|
160 |
+
},
|
161 |
+
{
|
162 |
+
"epoch": 0.01,
|
163 |
+
"learning_rate": 0.00015578947368421052,
|
164 |
+
"loss": 1.9135,
|
165 |
+
"step": 26
|
166 |
+
},
|
167 |
+
{
|
168 |
+
"epoch": 0.01,
|
169 |
+
"learning_rate": 0.0001536842105263158,
|
170 |
+
"loss": 1.5979,
|
171 |
+
"step": 27
|
172 |
+
},
|
173 |
+
{
|
174 |
+
"epoch": 0.01,
|
175 |
+
"learning_rate": 0.00015157894736842108,
|
176 |
+
"loss": 1.6566,
|
177 |
+
"step": 28
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 0.01,
|
181 |
+
"learning_rate": 0.00014947368421052633,
|
182 |
+
"loss": 1.766,
|
183 |
+
"step": 29
|
184 |
+
},
|
185 |
+
{
|
186 |
+
"epoch": 0.01,
|
187 |
+
"learning_rate": 0.00014736842105263158,
|
188 |
+
"loss": 1.6827,
|
189 |
+
"step": 30
|
190 |
}
|
191 |
],
|
192 |
"logging_steps": 1,
|
193 |
"max_steps": 100,
|
194 |
"num_train_epochs": 1,
|
195 |
"save_steps": 10,
|
196 |
+
"total_flos": 2104744175566848.0,
|
197 |
"trial_name": null,
|
198 |
"trial_params": null
|
199 |
}
|