Training in progress, step 15, 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 27024
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bd737ef4c3ee27dec3ee08c4fc96729c1e2cb508dafc14218c564105444d36fb
|
3 |
size 27024
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 70922
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:785ba4c0191a7f5aa9ec0b13e3bceac618303e38f62a6049a8503f4df0c3dc15
|
3 |
size 70922
|
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 sha256:10ed6906c4acfb0c3cdd369787177e342f514af039ed6186f2d8e3f0a6ff89b3
|
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 sha256:8bb840dbc65c27ef8840855786e35bfea033749e5d7571cf601f6645aa29cc1e
|
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": 3,
|
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": 136.202,
|
132 |
"eval_steps_per_second": 136.202,
|
133 |
"step": 12
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
134 |
}
|
135 |
],
|
136 |
"logging_steps": 1,
|
@@ -150,7 +179,7 @@
|
|
150 |
"attributes": {}
|
151 |
}
|
152 |
},
|
153 |
-
"total_flos":
|
154 |
"train_batch_size": 1,
|
155 |
"trial_name": null,
|
156 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.001063264221158958,
|
5 |
"eval_steps": 3,
|
6 |
+
"global_step": 15,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
131 |
"eval_samples_per_second": 136.202,
|
132 |
"eval_steps_per_second": 136.202,
|
133 |
"step": 12
|
134 |
+
},
|
135 |
+
{
|
136 |
+
"epoch": 0.0009214956583377636,
|
137 |
+
"grad_norm": 0.08635301142930984,
|
138 |
+
"learning_rate": 0.00018090169943749476,
|
139 |
+
"loss": 10.3813,
|
140 |
+
"step": 13
|
141 |
+
},
|
142 |
+
{
|
143 |
+
"epoch": 0.0009923799397483608,
|
144 |
+
"grad_norm": 0.07206328958272934,
|
145 |
+
"learning_rate": 0.00016691306063588583,
|
146 |
+
"loss": 10.3874,
|
147 |
+
"step": 14
|
148 |
+
},
|
149 |
+
{
|
150 |
+
"epoch": 0.001063264221158958,
|
151 |
+
"grad_norm": 0.09540396928787231,
|
152 |
+
"learning_rate": 0.00015000000000000001,
|
153 |
+
"loss": 10.3825,
|
154 |
+
"step": 15
|
155 |
+
},
|
156 |
+
{
|
157 |
+
"epoch": 0.001063264221158958,
|
158 |
+
"eval_loss": 10.38329792022705,
|
159 |
+
"eval_runtime": 23.4703,
|
160 |
+
"eval_samples_per_second": 126.543,
|
161 |
+
"eval_steps_per_second": 126.543,
|
162 |
+
"step": 15
|
163 |
}
|
164 |
],
|
165 |
"logging_steps": 1,
|
|
|
179 |
"attributes": {}
|
180 |
}
|
181 |
},
|
182 |
+
"total_flos": 387927244800.0,
|
183 |
"train_batch_size": 1,
|
184 |
"trial_name": null,
|
185 |
"trial_params": null
|