Training in progress, step 45, 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 328468404
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:39b60b8de0890f9945b9abe187160b7623af2eb90aa6d2def12bcbc4d83eba06
|
3 |
size 328468404
|
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 sha256:4f28d8fa2e8a1951654f8671d631d1d79f21c8364ce4113c741da1519130a64c
|
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 sha256:0896677f34f08366c4c71a3f69133212afc490296ec7ee225b8aefde1f38f24c
|
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": 6.857,
|
132 |
"eval_steps_per_second": 0.894,
|
133 |
"step": 36
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
134 |
}
|
135 |
],
|
136 |
"logging_steps": 3,
|
@@ -150,7 +179,7 @@
|
|
150 |
"attributes": {}
|
151 |
}
|
152 |
},
|
153 |
-
"total_flos": 1.
|
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": 0.6617647058823529,
|
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": 6.857,
|
132 |
"eval_steps_per_second": 0.894,
|
133 |
"step": 36
|
134 |
+
},
|
135 |
+
{
|
136 |
+
"epoch": 0.5735294117647058,
|
137 |
+
"grad_norm": NaN,
|
138 |
+
"learning_rate": 7.649596321166024e-05,
|
139 |
+
"loss": 4.2828,
|
140 |
+
"step": 39
|
141 |
+
},
|
142 |
+
{
|
143 |
+
"epoch": 0.6176470588235294,
|
144 |
+
"grad_norm": NaN,
|
145 |
+
"learning_rate": 7.191855733945387e-05,
|
146 |
+
"loss": 0.9355,
|
147 |
+
"step": 42
|
148 |
+
},
|
149 |
+
{
|
150 |
+
"epoch": 0.6617647058823529,
|
151 |
+
"grad_norm": NaN,
|
152 |
+
"learning_rate": 6.710100716628344e-05,
|
153 |
+
"loss": 10.799,
|
154 |
+
"step": 45
|
155 |
+
},
|
156 |
+
{
|
157 |
+
"epoch": 0.6617647058823529,
|
158 |
+
"eval_loss": NaN,
|
159 |
+
"eval_runtime": 16.7722,
|
160 |
+
"eval_samples_per_second": 6.857,
|
161 |
+
"eval_steps_per_second": 0.894,
|
162 |
+
"step": 45
|
163 |
}
|
164 |
],
|
165 |
"logging_steps": 3,
|
|
|
179 |
"attributes": {}
|
180 |
}
|
181 |
},
|
182 |
+
"total_flos": 1.279699816808448e+17,
|
183 |
"train_batch_size": 8,
|
184 |
"trial_name": null,
|
185 |
"trial_params": null
|