Training in progress, step 42000, checkpoint
Browse files
last-checkpoint/model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 660850056
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:489a33fe5b4d9949d7d8cf45817f8df21fbb24ce4c59ed68427b7ad007e9658e
|
| 3 |
size 660850056
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1321899418
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:21d6821f6bbdc52d29a4a476f322fd950fd344e28471c64194433f3e69b58ee5
|
| 3 |
size 1321899418
|
last-checkpoint/rng_state_0.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14917
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f0cfd135018a8c5759dbb24769ea1a4507552afcdf59c53835a717a9518092d5
|
| 3 |
size 14917
|
last-checkpoint/rng_state_1.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14917
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d7270bebb7879406385313caabc33424824b6596823e70b856e82c0a6cbdf49d
|
| 3 |
size 14917
|
last-checkpoint/scaler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1383
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:be4e201aefd3c1792e3738645032552fbb09408c3ecf4782affb4f4ea0ffdcf5
|
| 3 |
size 1383
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1465
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f1d269e7b95a1e2eb4af3a1896b969d3cabd9f6a736a29e36d9bba066417786d
|
| 3 |
size 1465
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,10 +1,10 @@
|
|
| 1 |
{
|
| 2 |
-
"best_global_step":
|
| 3 |
-
"best_metric": 0.
|
| 4 |
-
"best_model_checkpoint": "./speecht5/urdu-tts-phonemes-speecht5-finetuned/checkpoint-
|
| 5 |
-
"epoch":
|
| 6 |
"eval_steps": 1000,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
@@ -1771,6 +1771,49 @@
|
|
| 1771 |
"eval_samples_per_second": 33.133,
|
| 1772 |
"eval_steps_per_second": 8.284,
|
| 1773 |
"step": 41000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1774 |
}
|
| 1775 |
],
|
| 1776 |
"logging_steps": 200,
|
|
@@ -1790,7 +1833,7 @@
|
|
| 1790 |
"attributes": {}
|
| 1791 |
}
|
| 1792 |
},
|
| 1793 |
-
"total_flos": 2.
|
| 1794 |
"train_batch_size": 6,
|
| 1795 |
"trial_name": null,
|
| 1796 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_global_step": 42000,
|
| 3 |
+
"best_metric": 0.9448174834251404,
|
| 4 |
+
"best_model_checkpoint": "./speecht5/urdu-tts-phonemes-speecht5-finetuned/checkpoint-42000",
|
| 5 |
+
"epoch": 18.308732148697263,
|
| 6 |
"eval_steps": 1000,
|
| 7 |
+
"global_step": 42000,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 1771 |
"eval_samples_per_second": 33.133,
|
| 1772 |
"eval_steps_per_second": 8.284,
|
| 1773 |
"step": 41000
|
| 1774 |
+
},
|
| 1775 |
+
{
|
| 1776 |
+
"epoch": 17.96020930993132,
|
| 1777 |
+
"grad_norm": 37.53486251831055,
|
| 1778 |
+
"learning_rate": 5.570846187747907e-06,
|
| 1779 |
+
"loss": 3.959051513671875,
|
| 1780 |
+
"step": 41200
|
| 1781 |
+
},
|
| 1782 |
+
{
|
| 1783 |
+
"epoch": 18.04709473454704,
|
| 1784 |
+
"grad_norm": 33.98725891113281,
|
| 1785 |
+
"learning_rate": 5.548810048479507e-06,
|
| 1786 |
+
"loss": 3.937330322265625,
|
| 1787 |
+
"step": 41400
|
| 1788 |
+
},
|
| 1789 |
+
{
|
| 1790 |
+
"epoch": 18.134307205930448,
|
| 1791 |
+
"grad_norm": 25.65367317199707,
|
| 1792 |
+
"learning_rate": 5.526773909211106e-06,
|
| 1793 |
+
"loss": 3.947315673828125,
|
| 1794 |
+
"step": 41600
|
| 1795 |
+
},
|
| 1796 |
+
{
|
| 1797 |
+
"epoch": 18.221519677313857,
|
| 1798 |
+
"grad_norm": 27.725730895996094,
|
| 1799 |
+
"learning_rate": 5.504737769942706e-06,
|
| 1800 |
+
"loss": 3.957863464355469,
|
| 1801 |
+
"step": 41800
|
| 1802 |
+
},
|
| 1803 |
+
{
|
| 1804 |
+
"epoch": 18.308732148697263,
|
| 1805 |
+
"grad_norm": 30.85365104675293,
|
| 1806 |
+
"learning_rate": 5.482701630674306e-06,
|
| 1807 |
+
"loss": 3.950794982910156,
|
| 1808 |
+
"step": 42000
|
| 1809 |
+
},
|
| 1810 |
+
{
|
| 1811 |
+
"epoch": 18.308732148697263,
|
| 1812 |
+
"eval_loss": 0.9448174834251404,
|
| 1813 |
+
"eval_runtime": 358.5243,
|
| 1814 |
+
"eval_samples_per_second": 34.115,
|
| 1815 |
+
"eval_steps_per_second": 8.529,
|
| 1816 |
+
"step": 42000
|
| 1817 |
}
|
| 1818 |
],
|
| 1819 |
"logging_steps": 200,
|
|
|
|
| 1833 |
"attributes": {}
|
| 1834 |
}
|
| 1835 |
},
|
| 1836 |
+
"total_flos": 2.783882407575552e+16,
|
| 1837 |
"train_batch_size": 6,
|
| 1838 |
"trial_name": null,
|
| 1839 |
"trial_params": null
|