Training in progress, step 52, checkpoint
Browse files
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 150486964
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1501b3eb8d216af70c020ad20220edf6fefb2af2c5abde1695b7191ffd997993
|
3 |
size 150486964
|
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 sha256:5c87d052c61336e5f4eed49f8684dc218013ed8627df5aac854dc09f34705ac8
|
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 sha256:792ad29798cba378feffa861e2939c0c9205d97b89b46c0161cdef16a3d333a2
|
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 +130,42 @@
|
|
130 |
"eval_samples_per_second": 36.421,
|
131 |
"eval_steps_per_second": 4.635,
|
132 |
"step": 39
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
133 |
}
|
134 |
],
|
135 |
"logging_steps": 3,
|
@@ -149,7 +185,7 @@
|
|
149 |
"attributes": {}
|
150 |
}
|
151 |
},
|
152 |
-
"total_flos": 1.
|
153 |
"train_batch_size": 8,
|
154 |
"trial_name": null,
|
155 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.5306122448979592,
|
5 |
"eval_steps": 13,
|
6 |
+
"global_step": 52,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
130 |
"eval_samples_per_second": 36.421,
|
131 |
"eval_steps_per_second": 4.635,
|
132 |
"step": 39
|
133 |
+
},
|
134 |
+
{
|
135 |
+
"epoch": 0.42857142857142855,
|
136 |
+
"grad_norm": NaN,
|
137 |
+
"learning_rate": 8.765357330018056e-05,
|
138 |
+
"loss": 0.0,
|
139 |
+
"step": 42
|
140 |
+
},
|
141 |
+
{
|
142 |
+
"epoch": 0.45918367346938777,
|
143 |
+
"grad_norm": NaN,
|
144 |
+
"learning_rate": 8.535533905932738e-05,
|
145 |
+
"loss": 0.0,
|
146 |
+
"step": 45
|
147 |
+
},
|
148 |
+
{
|
149 |
+
"epoch": 0.4897959183673469,
|
150 |
+
"grad_norm": NaN,
|
151 |
+
"learning_rate": 8.289693629698564e-05,
|
152 |
+
"loss": 0.0,
|
153 |
+
"step": 48
|
154 |
+
},
|
155 |
+
{
|
156 |
+
"epoch": 0.5204081632653061,
|
157 |
+
"grad_norm": NaN,
|
158 |
+
"learning_rate": 8.0289502192041e-05,
|
159 |
+
"loss": 0.0,
|
160 |
+
"step": 51
|
161 |
+
},
|
162 |
+
{
|
163 |
+
"epoch": 0.5306122448979592,
|
164 |
+
"eval_loss": NaN,
|
165 |
+
"eval_runtime": 4.5333,
|
166 |
+
"eval_samples_per_second": 36.397,
|
167 |
+
"eval_steps_per_second": 4.632,
|
168 |
+
"step": 52
|
169 |
}
|
170 |
],
|
171 |
"logging_steps": 3,
|
|
|
185 |
"attributes": {}
|
186 |
}
|
187 |
},
|
188 |
+
"total_flos": 1.415152599564288e+16,
|
189 |
"train_batch_size": 8,
|
190 |
"trial_name": null,
|
191 |
"trial_params": null
|