Training in progress, step 3500
Browse files- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/pytorch_model.bin +1 -1
- last-checkpoint/rng_state.pth +1 -1
- last-checkpoint/scaler.pt +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +25 -5
- pytorch_model.bin +1 -1
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 484015877
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6413b446cd4cf9555dcc70e093250592683c054ac330b802b68b79522db341d1
|
3 |
size 484015877
|
last-checkpoint/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 242014297
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b573b82c4722ab456322756912925fd8af33c728c413d87733bb7b99f08ae499
|
3 |
size 242014297
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14575
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:40b5adfb915bd56ca45aa103901c57ec3fa114d95a597006e52879a68aa6590a
|
3 |
size 14575
|
last-checkpoint/scaler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 557
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b8910ac4d4e368661aaca00b9d59b975c6b600a74099129e4a39e35e40ad9e9d
|
3 |
size 557
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 627
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:14a52e7813087beccf319e8483ed659abb6bbb1fda8eb608a9bf0241413c19ba
|
3 |
size 627
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
-
"best_metric": 0.
|
3 |
-
"best_model_checkpoint": "results/checkpoint-
|
4 |
-
"epoch": 0.
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -126,11 +126,31 @@
|
|
126 |
"eval_samples_per_second": 35.119,
|
127 |
"eval_steps_per_second": 1.756,
|
128 |
"step": 3000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
129 |
}
|
130 |
],
|
131 |
"max_steps": 15000,
|
132 |
"num_train_epochs": 3,
|
133 |
-
"total_flos":
|
134 |
"trial_name": null,
|
135 |
"trial_params": null
|
136 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.5598750842730023,
|
3 |
+
"best_model_checkpoint": "results/checkpoint-3500",
|
4 |
+
"epoch": 0.7,
|
5 |
+
"global_step": 3500,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
126 |
"eval_samples_per_second": 35.119,
|
127 |
"eval_steps_per_second": 1.756,
|
128 |
"step": 3000
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.7,
|
132 |
+
"learning_rate": 8.073684210526316e-05,
|
133 |
+
"loss": 0.6923,
|
134 |
+
"step": 3500
|
135 |
+
},
|
136 |
+
{
|
137 |
+
"epoch": 0.7,
|
138 |
+
"eval_bleu": 0.1269094917224047,
|
139 |
+
"eval_exact_match": 0.156,
|
140 |
+
"eval_loss": 0.8161399960517883,
|
141 |
+
"eval_rouge1": 0.5598750842730023,
|
142 |
+
"eval_rouge2": 0.38392351740583797,
|
143 |
+
"eval_rougeL": 0.5409288136858783,
|
144 |
+
"eval_rougeLsum": 0.5484962105303921,
|
145 |
+
"eval_runtime": 55.0573,
|
146 |
+
"eval_samples_per_second": 36.326,
|
147 |
+
"eval_steps_per_second": 1.816,
|
148 |
+
"step": 3500
|
149 |
}
|
150 |
],
|
151 |
"max_steps": 15000,
|
152 |
"num_train_epochs": 3,
|
153 |
+
"total_flos": 8985722848542720.0,
|
154 |
"trial_name": null,
|
155 |
"trial_params": null
|
156 |
}
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 242014297
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b573b82c4722ab456322756912925fd8af33c728c413d87733bb7b99f08ae499
|
3 |
size 242014297
|