mprzibilla
commited on
Commit
•
34188f2
1
Parent(s):
7e04817
Training in progress, step 253000
Browse files- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/pytorch_model.bin +1 -1
- last-checkpoint/rng_state.pth +2 -2
- last-checkpoint/scaler.pt +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +19 -3
- 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 174303
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:388bd495779c635d92b8b205e680b77c3f1bfab35ea510932d89ca31c5ddc44e
|
3 |
size 174303
|
last-checkpoint/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 377644503
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:804f5bf7419f8a372aa88b22397e3d90f6fabffb7c4cfdf6488d88770701396b
|
3 |
size 377644503
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7ea70ed9280c12cd12fbcab48baf0f73b6b95b5c739aae22db8aee504cb07a30
|
3 |
+
size 14567
|
last-checkpoint/scaler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 559
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b4e7fc9cbae8d2a52769f62d26282c6279fa2b6f27e451041ffe84c4854b2d2d
|
3 |
size 559
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 623
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f2ebe698f52b0c8b82a4138a896e5905ffe8f78bfa76ddbb42f4e9d92fc35fc2
|
3 |
size 623
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch":
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -150,11 +150,27 @@
|
|
150 |
"eval_steps_per_second": 26.884,
|
151 |
"eval_wer": 1.0,
|
152 |
"step": 227700
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
153 |
}
|
154 |
],
|
155 |
"max_steps": 253000,
|
156 |
"num_train_epochs": 1000,
|
157 |
-
"total_flos": 2.
|
158 |
"trial_name": null,
|
159 |
"trial_params": null
|
160 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1000.0,
|
5 |
+
"global_step": 253000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
150 |
"eval_steps_per_second": 26.884,
|
151 |
"eval_wer": 1.0,
|
152 |
"step": 227700
|
153 |
+
},
|
154 |
+
{
|
155 |
+
"epoch": 1000.0,
|
156 |
+
"learning_rate": 4.951112960266278e-08,
|
157 |
+
"loss": 2.3067,
|
158 |
+
"step": 253000
|
159 |
+
},
|
160 |
+
{
|
161 |
+
"epoch": 1000.0,
|
162 |
+
"eval_cer": 0.8883116883116883,
|
163 |
+
"eval_loss": 2.9747302532196045,
|
164 |
+
"eval_runtime": 0.6721,
|
165 |
+
"eval_samples_per_second": 208.293,
|
166 |
+
"eval_steps_per_second": 26.781,
|
167 |
+
"eval_wer": 1.0,
|
168 |
+
"step": 253000
|
169 |
}
|
170 |
],
|
171 |
"max_steps": 253000,
|
172 |
"num_train_epochs": 1000,
|
173 |
+
"total_flos": 2.3383716160651048e+20,
|
174 |
"trial_name": null,
|
175 |
"trial_params": null
|
176 |
}
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 377644503
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:804f5bf7419f8a372aa88b22397e3d90f6fabffb7c4cfdf6488d88770701396b
|
3 |
size 377644503
|