Commit
·
d2fa2de
1
Parent(s):
fbb85cb
Training in progress, step 25, 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 125248064
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:40d5693affa8c3c7b723c5daf60ed0b746f97958aee56ec5b5ea1f3ad326b755
|
3 |
size 125248064
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 63350356
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6de35a1438d91fac87e649ba5c3d5a90121e6ce3ca86df298c35f641323d5759
|
3 |
size 63350356
|
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:a14f694512fc40766d9fafd579c27dac8ba7e3555b949d256edd6441aadd30ee
|
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 sha256:33c2ffac78fadf1567b17338549b0e2194f2cf0e411216d20570b3e79a5739ee
|
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 +127,43 @@
|
|
127 |
"learning_rate": 0.00016494845360824742,
|
128 |
"loss": 1.9081,
|
129 |
"step": 20
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
130 |
}
|
131 |
],
|
132 |
"logging_steps": 1,
|
133 |
"max_steps": 100,
|
134 |
"num_train_epochs": 1,
|
135 |
"save_steps": 5,
|
136 |
-
"total_flos":
|
137 |
"trial_name": null,
|
138 |
"trial_params": null
|
139 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.01,
|
5 |
"eval_steps": 1000,
|
6 |
+
"global_step": 25,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
127 |
"learning_rate": 0.00016494845360824742,
|
128 |
"loss": 1.9081,
|
129 |
"step": 20
|
130 |
+
},
|
131 |
+
{
|
132 |
+
"epoch": 0.01,
|
133 |
+
"learning_rate": 0.00016288659793814434,
|
134 |
+
"loss": 1.9725,
|
135 |
+
"step": 21
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.01,
|
139 |
+
"learning_rate": 0.00016082474226804125,
|
140 |
+
"loss": 1.8649,
|
141 |
+
"step": 22
|
142 |
+
},
|
143 |
+
{
|
144 |
+
"epoch": 0.01,
|
145 |
+
"learning_rate": 0.00015876288659793814,
|
146 |
+
"loss": 1.5654,
|
147 |
+
"step": 23
|
148 |
+
},
|
149 |
+
{
|
150 |
+
"epoch": 0.01,
|
151 |
+
"learning_rate": 0.00015670103092783506,
|
152 |
+
"loss": 1.8573,
|
153 |
+
"step": 24
|
154 |
+
},
|
155 |
+
{
|
156 |
+
"epoch": 0.01,
|
157 |
+
"learning_rate": 0.00015463917525773197,
|
158 |
+
"loss": 1.6624,
|
159 |
+
"step": 25
|
160 |
}
|
161 |
],
|
162 |
"logging_steps": 1,
|
163 |
"max_steps": 100,
|
164 |
"num_train_epochs": 1,
|
165 |
"save_steps": 5,
|
166 |
+
"total_flos": 3557655141089280.0,
|
167 |
"trial_name": null,
|
168 |
"trial_params": null
|
169 |
}
|