Training in progress, step 26, 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 50358592
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:baaaa5f8fc5fb86c2a0355f35ded415535e9465522bcde9b32b470ad787b9fb4
|
3 |
size 50358592
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 25784826
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d1a13bade6aa84cd22229c27985a95607536c889bb393661c28a8e128fb88ff3
|
3 |
size 25784826
|
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 sha256:719020131bf833c90632c6b01b06c5301e1876ba50a1273eb06ec350ba411a1a
|
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 sha256:37841e69eda911caeb33edeefa0b2f140e72dcce247aeb757b2fe89c00d7887b
|
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": 13,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -114,6 +114,105 @@
|
|
114 |
"eval_samples_per_second": 6.784,
|
115 |
"eval_steps_per_second": 3.393,
|
116 |
"step": 13
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
117 |
}
|
118 |
],
|
119 |
"logging_steps": 1,
|
@@ -133,7 +232,7 @@
|
|
133 |
"attributes": {}
|
134 |
}
|
135 |
},
|
136 |
-
"total_flos":
|
137 |
"train_batch_size": 2,
|
138 |
"trial_name": null,
|
139 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.007263203841117416,
|
5 |
"eval_steps": 13,
|
6 |
+
"global_step": 26,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
114 |
"eval_samples_per_second": 6.784,
|
115 |
"eval_steps_per_second": 3.393,
|
116 |
"step": 13
|
117 |
+
},
|
118 |
+
{
|
119 |
+
"epoch": 0.003910955914447839,
|
120 |
+
"grad_norm": 8.404040336608887,
|
121 |
+
"learning_rate": 9.755282581475769e-05,
|
122 |
+
"loss": 18.8438,
|
123 |
+
"step": 14
|
124 |
+
},
|
125 |
+
{
|
126 |
+
"epoch": 0.0041903099083369704,
|
127 |
+
"grad_norm": 23.96065902709961,
|
128 |
+
"learning_rate": 9.619397662556435e-05,
|
129 |
+
"loss": 21.5391,
|
130 |
+
"step": 15
|
131 |
+
},
|
132 |
+
{
|
133 |
+
"epoch": 0.0044696639022261024,
|
134 |
+
"grad_norm": 8.518821716308594,
|
135 |
+
"learning_rate": 9.45503262094184e-05,
|
136 |
+
"loss": 17.5547,
|
137 |
+
"step": 16
|
138 |
+
},
|
139 |
+
{
|
140 |
+
"epoch": 0.004749017896115234,
|
141 |
+
"grad_norm": 9.683491706848145,
|
142 |
+
"learning_rate": 9.263200821770461e-05,
|
143 |
+
"loss": 18.3867,
|
144 |
+
"step": 17
|
145 |
+
},
|
146 |
+
{
|
147 |
+
"epoch": 0.005028371890004365,
|
148 |
+
"grad_norm": 12.909642219543457,
|
149 |
+
"learning_rate": 9.045084971874738e-05,
|
150 |
+
"loss": 20.334,
|
151 |
+
"step": 18
|
152 |
+
},
|
153 |
+
{
|
154 |
+
"epoch": 0.005307725883893497,
|
155 |
+
"grad_norm": 6.089707851409912,
|
156 |
+
"learning_rate": 8.802029828000156e-05,
|
157 |
+
"loss": 18.9375,
|
158 |
+
"step": 19
|
159 |
+
},
|
160 |
+
{
|
161 |
+
"epoch": 0.005587079877782628,
|
162 |
+
"grad_norm": 8.212544441223145,
|
163 |
+
"learning_rate": 8.535533905932738e-05,
|
164 |
+
"loss": 19.8164,
|
165 |
+
"step": 20
|
166 |
+
},
|
167 |
+
{
|
168 |
+
"epoch": 0.005866433871671759,
|
169 |
+
"grad_norm": 8.69490909576416,
|
170 |
+
"learning_rate": 8.247240241650918e-05,
|
171 |
+
"loss": 19.0977,
|
172 |
+
"step": 21
|
173 |
+
},
|
174 |
+
{
|
175 |
+
"epoch": 0.00614578786556089,
|
176 |
+
"grad_norm": 6.588229179382324,
|
177 |
+
"learning_rate": 7.938926261462366e-05,
|
178 |
+
"loss": 18.7383,
|
179 |
+
"step": 22
|
180 |
+
},
|
181 |
+
{
|
182 |
+
"epoch": 0.006425141859450022,
|
183 |
+
"grad_norm": 6.510587215423584,
|
184 |
+
"learning_rate": 7.612492823579745e-05,
|
185 |
+
"loss": 19.0391,
|
186 |
+
"step": 23
|
187 |
+
},
|
188 |
+
{
|
189 |
+
"epoch": 0.006704495853339153,
|
190 |
+
"grad_norm": 10.146479606628418,
|
191 |
+
"learning_rate": 7.269952498697734e-05,
|
192 |
+
"loss": 20.457,
|
193 |
+
"step": 24
|
194 |
+
},
|
195 |
+
{
|
196 |
+
"epoch": 0.006983849847228284,
|
197 |
+
"grad_norm": 6.790075302124023,
|
198 |
+
"learning_rate": 6.91341716182545e-05,
|
199 |
+
"loss": 19.5586,
|
200 |
+
"step": 25
|
201 |
+
},
|
202 |
+
{
|
203 |
+
"epoch": 0.007263203841117416,
|
204 |
+
"grad_norm": 6.229572296142578,
|
205 |
+
"learning_rate": 6.545084971874738e-05,
|
206 |
+
"loss": 19.375,
|
207 |
+
"step": 26
|
208 |
+
},
|
209 |
+
{
|
210 |
+
"epoch": 0.007263203841117416,
|
211 |
+
"eval_loss": 1.168168306350708,
|
212 |
+
"eval_runtime": 888.7918,
|
213 |
+
"eval_samples_per_second": 6.783,
|
214 |
+
"eval_steps_per_second": 3.392,
|
215 |
+
"step": 26
|
216 |
}
|
217 |
],
|
218 |
"logging_steps": 1,
|
|
|
232 |
"attributes": {}
|
233 |
}
|
234 |
},
|
235 |
+
"total_flos": 2.647045675627315e+16,
|
236 |
"train_batch_size": 2,
|
237 |
"trial_name": null,
|
238 |
"trial_params": null
|