Training in progress, step 15000, 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 18915040
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:da7c0bd2147c7b3c6459f3053adc8b9c28441ca2d5a2b544fa249ab614d64181
|
3 |
size 18915040
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 37990394
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cc6aa1633c82ea829665db3a7b8ff7fad3d38040119298296b0cb31a9dd15bd8
|
3 |
size 37990394
|
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 sha256:371d7d31c4d289bd5947ddb669187d33a7a9f7a4a5ee671257538ec83fe03ea5
|
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:b9b9d8461afd25ace0a8409edccf52ff6a1864065ea747ab7226e5bd71843798
|
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": 500,
|
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": 7.94544839653823e-05,
|
128 |
"loss": 3.2599,
|
129 |
"step": 10000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
130 |
}
|
131 |
],
|
132 |
"logging_steps": 500,
|
133 |
"max_steps": 172005,
|
134 |
"num_train_epochs": 5,
|
135 |
"save_steps": 5000,
|
136 |
-
"total_flos":
|
137 |
"trial_name": null,
|
138 |
"trial_params": null
|
139 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.4360274988009244,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 15000,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
127 |
"learning_rate": 7.94544839653823e-05,
|
128 |
"loss": 3.2599,
|
129 |
"step": 10000
|
130 |
+
},
|
131 |
+
{
|
132 |
+
"epoch": 0.31,
|
133 |
+
"learning_rate": 7.939234556610201e-05,
|
134 |
+
"loss": 3.3353,
|
135 |
+
"step": 10500
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.32,
|
139 |
+
"learning_rate": 7.932688339712721e-05,
|
140 |
+
"loss": 3.1893,
|
141 |
+
"step": 11000
|
142 |
+
},
|
143 |
+
{
|
144 |
+
"epoch": 0.33,
|
145 |
+
"learning_rate": 7.925810298189578e-05,
|
146 |
+
"loss": 3.2074,
|
147 |
+
"step": 11500
|
148 |
+
},
|
149 |
+
{
|
150 |
+
"epoch": 0.35,
|
151 |
+
"learning_rate": 7.918601012382602e-05,
|
152 |
+
"loss": 3.2427,
|
153 |
+
"step": 12000
|
154 |
+
},
|
155 |
+
{
|
156 |
+
"epoch": 0.36,
|
157 |
+
"learning_rate": 7.911061090582703e-05,
|
158 |
+
"loss": 3.3292,
|
159 |
+
"step": 12500
|
160 |
+
},
|
161 |
+
{
|
162 |
+
"epoch": 0.38,
|
163 |
+
"learning_rate": 7.90319116897854e-05,
|
164 |
+
"loss": 3.2498,
|
165 |
+
"step": 13000
|
166 |
+
},
|
167 |
+
{
|
168 |
+
"epoch": 0.39,
|
169 |
+
"learning_rate": 7.89499191160285e-05,
|
170 |
+
"loss": 3.2745,
|
171 |
+
"step": 13500
|
172 |
+
},
|
173 |
+
{
|
174 |
+
"epoch": 0.41,
|
175 |
+
"learning_rate": 7.88646401027641e-05,
|
176 |
+
"loss": 3.2645,
|
177 |
+
"step": 14000
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 0.42,
|
181 |
+
"learning_rate": 7.87760818454967e-05,
|
182 |
+
"loss": 3.2276,
|
183 |
+
"step": 14500
|
184 |
+
},
|
185 |
+
{
|
186 |
+
"epoch": 0.44,
|
187 |
+
"learning_rate": 7.868425181642037e-05,
|
188 |
+
"loss": 3.235,
|
189 |
+
"step": 15000
|
190 |
}
|
191 |
],
|
192 |
"logging_steps": 500,
|
193 |
"max_steps": 172005,
|
194 |
"num_train_epochs": 5,
|
195 |
"save_steps": 5000,
|
196 |
+
"total_flos": 5.1400868364288e+17,
|
197 |
"trial_name": null,
|
198 |
"trial_params": null
|
199 |
}
|