Training in progress, step 50, 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 159967880
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2be66bdef4fd26a71eb19866e56fd3eab53ffa63d418b7f120e4fcdb0e0ac5e5
|
3 |
size 159967880
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 320194002
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f87e002b7a5ad10404f62ada79c4283039d335fa48c12694b55b7347ed949420
|
3 |
size 320194002
|
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 sha256:3638402d120ea57e57ec245007069ddaabc6ebb72bf6f1d67e6e98724d754ffe
|
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:e69e2b49ea642509f0c688c16fb190b7cf27dac0a18903a5e2d1467d0343d8b8
|
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,
|
@@ -130,6 +130,27 @@
|
|
130 |
"eval_samples_per_second": 10.195,
|
131 |
"eval_steps_per_second": 5.098,
|
132 |
"step": 39
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
133 |
}
|
134 |
],
|
135 |
"logging_steps": 3,
|
@@ -144,12 +165,12 @@
|
|
144 |
"should_evaluate": false,
|
145 |
"should_log": false,
|
146 |
"should_save": true,
|
147 |
-
"should_training_stop":
|
148 |
},
|
149 |
"attributes": {}
|
150 |
}
|
151 |
},
|
152 |
-
"total_flos": 1.
|
153 |
"train_batch_size": 2,
|
154 |
"trial_name": null,
|
155 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.002158288908553299,
|
5 |
"eval_steps": 13,
|
6 |
+
"global_step": 50,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
130 |
"eval_samples_per_second": 10.195,
|
131 |
"eval_steps_per_second": 5.098,
|
132 |
"step": 39
|
133 |
+
},
|
134 |
+
{
|
135 |
+
"epoch": 0.0018129626831847711,
|
136 |
+
"grad_norm": 3.094237804412842,
|
137 |
+
"learning_rate": 1.9098300562505266e-05,
|
138 |
+
"loss": 6.1102,
|
139 |
+
"step": 42
|
140 |
+
},
|
141 |
+
{
|
142 |
+
"epoch": 0.001942460017697969,
|
143 |
+
"grad_norm": 3.035853862762451,
|
144 |
+
"learning_rate": 7.612046748871327e-06,
|
145 |
+
"loss": 6.36,
|
146 |
+
"step": 45
|
147 |
+
},
|
148 |
+
{
|
149 |
+
"epoch": 0.002071957352211167,
|
150 |
+
"grad_norm": 2.3664188385009766,
|
151 |
+
"learning_rate": 1.231165940486234e-06,
|
152 |
+
"loss": 6.046,
|
153 |
+
"step": 48
|
154 |
}
|
155 |
],
|
156 |
"logging_steps": 3,
|
|
|
165 |
"should_evaluate": false,
|
166 |
"should_log": false,
|
167 |
"should_save": true,
|
168 |
+
"should_training_stop": true
|
169 |
},
|
170 |
"attributes": {}
|
171 |
}
|
172 |
},
|
173 |
+
"total_flos": 1.63366161088512e+16,
|
174 |
"train_batch_size": 2,
|
175 |
"trial_name": null,
|
176 |
"trial_params": null
|