Training in progress, step 45, 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 167832240
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f7daaf51f3cc455e2138ff58283519d242cd7e85f565d08f363ae131f5abbc20
|
3 |
size 167832240
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 85723284
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0288ad511b4a2a84815dde298475ee9c70959c7b339b8ab9a53c544506c21672
|
3 |
size 85723284
|
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:d478d6bfdc4a22cc9744896e3b50e5ddeee0db93a0a74564602341cc9b34247e
|
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 sha256:9776c8df8be516beee92201f32f4a3f5d90539bf47f8ef27e1636cdc132a851e
|
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": 9,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -131,6 +131,35 @@
|
|
131 |
"eval_samples_per_second": 12.082,
|
132 |
"eval_steps_per_second": 1.549,
|
133 |
"step": 36
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
134 |
}
|
135 |
],
|
136 |
"logging_steps": 3,
|
@@ -150,7 +179,7 @@
|
|
150 |
"attributes": {}
|
151 |
}
|
152 |
},
|
153 |
-
"total_flos":
|
154 |
"train_batch_size": 8,
|
155 |
"trial_name": null,
|
156 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.3237410071942446,
|
5 |
"eval_steps": 9,
|
6 |
+
"global_step": 45,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
131 |
"eval_samples_per_second": 12.082,
|
132 |
"eval_steps_per_second": 1.549,
|
133 |
"step": 36
|
134 |
+
},
|
135 |
+
{
|
136 |
+
"epoch": 0.2805755395683453,
|
137 |
+
"grad_norm": 2.292299270629883,
|
138 |
+
"learning_rate": 3.824798160583012e-05,
|
139 |
+
"loss": 4.446,
|
140 |
+
"step": 39
|
141 |
+
},
|
142 |
+
{
|
143 |
+
"epoch": 0.302158273381295,
|
144 |
+
"grad_norm": 2.913973808288574,
|
145 |
+
"learning_rate": 3.5959278669726935e-05,
|
146 |
+
"loss": 4.0109,
|
147 |
+
"step": 42
|
148 |
+
},
|
149 |
+
{
|
150 |
+
"epoch": 0.3237410071942446,
|
151 |
+
"grad_norm": 2.1814777851104736,
|
152 |
+
"learning_rate": 3.355050358314172e-05,
|
153 |
+
"loss": 4.2421,
|
154 |
+
"step": 45
|
155 |
+
},
|
156 |
+
{
|
157 |
+
"epoch": 0.3237410071942446,
|
158 |
+
"eval_loss": 1.0296789407730103,
|
159 |
+
"eval_runtime": 19.3399,
|
160 |
+
"eval_samples_per_second": 12.099,
|
161 |
+
"eval_steps_per_second": 1.551,
|
162 |
+
"step": 45
|
163 |
}
|
164 |
],
|
165 |
"logging_steps": 3,
|
|
|
179 |
"attributes": {}
|
180 |
}
|
181 |
},
|
182 |
+
"total_flos": 7.66411153562665e+16,
|
183 |
"train_batch_size": 8,
|
184 |
"trial_name": null,
|
185 |
"trial_params": null
|