"auto-commit"
Browse files- model-bin/finetune/base/{checkpoint-22893 → checkpoint-23765}/config.json +0 -0
- model-bin/finetune/base/{checkpoint-22893 → checkpoint-23765}/optimizer.pt +1 -1
- model-bin/finetune/base/{checkpoint-22893 → checkpoint-23765}/preprocessor_config.json +0 -0
- model-bin/finetune/base/{checkpoint-23266 → checkpoint-23765}/pytorch_model.bin +1 -1
- model-bin/finetune/base/{checkpoint-22893 → checkpoint-23765}/rng_state.pth +2 -2
- model-bin/finetune/base/{checkpoint-23266 → checkpoint-23765}/scaler.pt +1 -1
- model-bin/finetune/base/{checkpoint-22893 → checkpoint-23765}/scheduler.pt +1 -1
- model-bin/finetune/base/{checkpoint-23266 → checkpoint-23765}/trainer_state.json +340 -4
- model-bin/finetune/base/{checkpoint-22893 → checkpoint-23765}/training_args.bin +0 -0
- model-bin/finetune/base/{checkpoint-23266 → checkpoint-23890}/config.json +0 -0
- model-bin/finetune/base/{checkpoint-23266 → checkpoint-23890}/optimizer.pt +1 -1
- model-bin/finetune/base/{checkpoint-23266 → checkpoint-23890}/preprocessor_config.json +0 -0
- model-bin/finetune/base/{checkpoint-22893 → checkpoint-23890}/pytorch_model.bin +1 -1
- model-bin/finetune/base/{checkpoint-23266 → checkpoint-23890}/rng_state.pth +1 -1
- model-bin/finetune/base/{checkpoint-22893 → checkpoint-23890}/scaler.pt +1 -1
- model-bin/finetune/base/{checkpoint-23266 → checkpoint-23890}/scheduler.pt +1 -1
- model-bin/finetune/base/{checkpoint-22893 → checkpoint-23890}/trainer_state.json +677 -5
- model-bin/finetune/base/{checkpoint-23266 → checkpoint-23890}/training_args.bin +0 -0
- model-bin/finetune/base/log/1629594380.404467/events.out.tfevents.1629594380.91f414e9573a.903.11 +3 -0
- model-bin/finetune/base/log/1629595044.6201167/events.out.tfevents.1629595044.91f414e9573a.903.13 +3 -0
- model-bin/finetune/base/log/1629595706.141513/events.out.tfevents.1629595706.91f414e9573a.903.15 +3 -0
- model-bin/finetune/base/log/1629596366.4482682/events.out.tfevents.1629596366.91f414e9573a.903.17 +3 -0
- model-bin/finetune/base/log/1629597034.2743096/events.out.tfevents.1629597034.91f414e9573a.903.19 +3 -0
- model-bin/finetune/base/log/events.out.tfevents.1629594380.91f414e9573a.903.10 +3 -0
- model-bin/finetune/base/log/events.out.tfevents.1629595044.91f414e9573a.903.12 +3 -0
- model-bin/finetune/base/log/events.out.tfevents.1629595706.91f414e9573a.903.14 +3 -0
- model-bin/finetune/base/log/events.out.tfevents.1629596366.91f414e9573a.903.16 +3 -0
- model-bin/finetune/base/log/events.out.tfevents.1629597034.91f414e9573a.903.18 +3 -0
model-bin/finetune/base/{checkpoint-22893 → checkpoint-23765}/config.json
RENAMED
|
File without changes
|
model-bin/finetune/base/{checkpoint-22893 → checkpoint-23765}/optimizer.pt
RENAMED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 722165009
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1e4194ca8bc8fa5462df7d7d7aa80ebb1cca2b041f02e785784ddc9dd1f776fd
|
| 3 |
size 722165009
|
model-bin/finetune/base/{checkpoint-22893 → checkpoint-23765}/preprocessor_config.json
RENAMED
|
File without changes
|
model-bin/finetune/base/{checkpoint-23266 → checkpoint-23765}/pytorch_model.bin
RENAMED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 377909911
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:461058b03963bd18f1ebc28225abde9bc05e5ad1b1f0b9667701f137f7a206b8
|
| 3 |
size 377909911
|
model-bin/finetune/base/{checkpoint-22893 → checkpoint-23765}/rng_state.pth
RENAMED
|
@@ -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 sha256:33ed3284effcb49b3b24e297a453636e91813b415b95761648ab08713b133289
|
| 3 |
+
size 14503
|
model-bin/finetune/base/{checkpoint-23266 → checkpoint-23765}/scaler.pt
RENAMED
|
@@ -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 sha256:068b3f6a1364ee3a2aaaf0b72c0c5b3749099a73ddfd7fcd2f4937e239990da0
|
| 3 |
size 559
|
model-bin/finetune/base/{checkpoint-22893 → checkpoint-23765}/scheduler.pt
RENAMED
|
@@ -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 sha256:36b21802c775d6647e07bcdac78b7e45f230392c1894a7d088e01370a1bb57bd
|
| 3 |
size 623
|
model-bin/finetune/base/{checkpoint-23266 → checkpoint-23765}/trainer_state.json
RENAMED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": 0.22373344847438112,
|
| 3 |
"best_model_checkpoint": "./model-bin/finetune/base/checkpoint-22893",
|
| 4 |
-
"epoch":
|
| 5 |
-
"global_step":
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
@@ -137925,11 +137925,347 @@
|
|
| 137925 |
"eval_steps_per_second": 0.658,
|
| 137926 |
"eval_wer": 0.2345039771874531,
|
| 137927 |
"step": 23266
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 137928 |
}
|
| 137929 |
],
|
| 137930 |
-
"max_steps":
|
| 137931 |
"num_train_epochs": 5000,
|
| 137932 |
-
"total_flos": 6.
|
| 137933 |
"trial_name": null,
|
| 137934 |
"trial_params": null
|
| 137935 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": 0.22373344847438112,
|
| 3 |
"best_model_checkpoint": "./model-bin/finetune/base/checkpoint-22893",
|
| 4 |
+
"epoch": 190.0,
|
| 5 |
+
"global_step": 23765,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
|
|
| 137925 |
"eval_steps_per_second": 0.658,
|
| 137926 |
"eval_wer": 0.2345039771874531,
|
| 137927 |
"step": 23266
|
| 137928 |
+
},
|
| 137929 |
+
{
|
| 137930 |
+
"epoch": 186.03,
|
| 137931 |
+
"learning_rate": 9.640371567043619e-06,
|
| 137932 |
+
"loss": 0.439,
|
| 137933 |
+
"step": 23270
|
| 137934 |
+
},
|
| 137935 |
+
{
|
| 137936 |
+
"epoch": 186.11,
|
| 137937 |
+
"learning_rate": 9.640210016155089e-06,
|
| 137938 |
+
"loss": 0.461,
|
| 137939 |
+
"step": 23280
|
| 137940 |
+
},
|
| 137941 |
+
{
|
| 137942 |
+
"epoch": 186.19,
|
| 137943 |
+
"learning_rate": 9.640048465266559e-06,
|
| 137944 |
+
"loss": 0.8283,
|
| 137945 |
+
"step": 23290
|
| 137946 |
+
},
|
| 137947 |
+
{
|
| 137948 |
+
"epoch": 186.27,
|
| 137949 |
+
"learning_rate": 9.639886914378029e-06,
|
| 137950 |
+
"loss": 0.6584,
|
| 137951 |
+
"step": 23300
|
| 137952 |
+
},
|
| 137953 |
+
{
|
| 137954 |
+
"epoch": 186.35,
|
| 137955 |
+
"learning_rate": 9.6397253634895e-06,
|
| 137956 |
+
"loss": 0.542,
|
| 137957 |
+
"step": 23310
|
| 137958 |
+
},
|
| 137959 |
+
{
|
| 137960 |
+
"epoch": 186.43,
|
| 137961 |
+
"learning_rate": 9.63956381260097e-06,
|
| 137962 |
+
"loss": 0.955,
|
| 137963 |
+
"step": 23320
|
| 137964 |
+
},
|
| 137965 |
+
{
|
| 137966 |
+
"epoch": 186.51,
|
| 137967 |
+
"learning_rate": 9.63940226171244e-06,
|
| 137968 |
+
"loss": 0.4646,
|
| 137969 |
+
"step": 23330
|
| 137970 |
+
},
|
| 137971 |
+
{
|
| 137972 |
+
"epoch": 186.59,
|
| 137973 |
+
"learning_rate": 9.63924071082391e-06,
|
| 137974 |
+
"loss": 0.7872,
|
| 137975 |
+
"step": 23340
|
| 137976 |
+
},
|
| 137977 |
+
{
|
| 137978 |
+
"epoch": 186.67,
|
| 137979 |
+
"learning_rate": 9.63907915993538e-06,
|
| 137980 |
+
"loss": 0.9723,
|
| 137981 |
+
"step": 23350
|
| 137982 |
+
},
|
| 137983 |
+
{
|
| 137984 |
+
"epoch": 186.75,
|
| 137985 |
+
"learning_rate": 9.63891760904685e-06,
|
| 137986 |
+
"loss": 0.5465,
|
| 137987 |
+
"step": 23360
|
| 137988 |
+
},
|
| 137989 |
+
{
|
| 137990 |
+
"epoch": 186.83,
|
| 137991 |
+
"learning_rate": 9.63875605815832e-06,
|
| 137992 |
+
"loss": 1.1675,
|
| 137993 |
+
"step": 23370
|
| 137994 |
+
},
|
| 137995 |
+
{
|
| 137996 |
+
"epoch": 186.91,
|
| 137997 |
+
"learning_rate": 9.63859450726979e-06,
|
| 137998 |
+
"loss": 0.4183,
|
| 137999 |
+
"step": 23380
|
| 138000 |
+
},
|
| 138001 |
+
{
|
| 138002 |
+
"epoch": 186.99,
|
| 138003 |
+
"learning_rate": 9.63843295638126e-06,
|
| 138004 |
+
"loss": 0.7856,
|
| 138005 |
+
"step": 23390
|
| 138006 |
+
},
|
| 138007 |
+
{
|
| 138008 |
+
"epoch": 187.0,
|
| 138009 |
+
"eval_loss": 0.549532413482666,
|
| 138010 |
+
"eval_runtime": 41.1758,
|
| 138011 |
+
"eval_samples_per_second": 20.303,
|
| 138012 |
+
"eval_steps_per_second": 0.656,
|
| 138013 |
+
"eval_wer": 0.2319283686394409,
|
| 138014 |
+
"step": 23391
|
| 138015 |
+
},
|
| 138016 |
+
{
|
| 138017 |
+
"epoch": 188.07,
|
| 138018 |
+
"learning_rate": 9.63827140549273e-06,
|
| 138019 |
+
"loss": 0.4892,
|
| 138020 |
+
"step": 23400
|
| 138021 |
+
},
|
| 138022 |
+
{
|
| 138023 |
+
"epoch": 188.15,
|
| 138024 |
+
"learning_rate": 9.6381098546042e-06,
|
| 138025 |
+
"loss": 0.4829,
|
| 138026 |
+
"step": 23410
|
| 138027 |
+
},
|
| 138028 |
+
{
|
| 138029 |
+
"epoch": 188.23,
|
| 138030 |
+
"learning_rate": 9.63794830371567e-06,
|
| 138031 |
+
"loss": 1.0797,
|
| 138032 |
+
"step": 23420
|
| 138033 |
+
},
|
| 138034 |
+
{
|
| 138035 |
+
"epoch": 188.31,
|
| 138036 |
+
"learning_rate": 9.637786752827142e-06,
|
| 138037 |
+
"loss": 0.4272,
|
| 138038 |
+
"step": 23430
|
| 138039 |
+
},
|
| 138040 |
+
{
|
| 138041 |
+
"epoch": 188.39,
|
| 138042 |
+
"learning_rate": 9.637625201938612e-06,
|
| 138043 |
+
"loss": 0.9337,
|
| 138044 |
+
"step": 23440
|
| 138045 |
+
},
|
| 138046 |
+
{
|
| 138047 |
+
"epoch": 188.47,
|
| 138048 |
+
"learning_rate": 9.637463651050082e-06,
|
| 138049 |
+
"loss": 0.6514,
|
| 138050 |
+
"step": 23450
|
| 138051 |
+
},
|
| 138052 |
+
{
|
| 138053 |
+
"epoch": 188.55,
|
| 138054 |
+
"learning_rate": 9.637302100161552e-06,
|
| 138055 |
+
"loss": 0.516,
|
| 138056 |
+
"step": 23460
|
| 138057 |
+
},
|
| 138058 |
+
{
|
| 138059 |
+
"epoch": 188.63,
|
| 138060 |
+
"learning_rate": 9.637140549273022e-06,
|
| 138061 |
+
"loss": 1.0524,
|
| 138062 |
+
"step": 23470
|
| 138063 |
+
},
|
| 138064 |
+
{
|
| 138065 |
+
"epoch": 188.71,
|
| 138066 |
+
"learning_rate": 9.636978998384492e-06,
|
| 138067 |
+
"loss": 0.5051,
|
| 138068 |
+
"step": 23480
|
| 138069 |
+
},
|
| 138070 |
+
{
|
| 138071 |
+
"epoch": 188.8,
|
| 138072 |
+
"learning_rate": 9.636817447495962e-06,
|
| 138073 |
+
"loss": 0.8574,
|
| 138074 |
+
"step": 23490
|
| 138075 |
+
},
|
| 138076 |
+
{
|
| 138077 |
+
"epoch": 188.88,
|
| 138078 |
+
"learning_rate": 9.636655896607432e-06,
|
| 138079 |
+
"loss": 0.6547,
|
| 138080 |
+
"step": 23500
|
| 138081 |
+
},
|
| 138082 |
+
{
|
| 138083 |
+
"epoch": 188.96,
|
| 138084 |
+
"learning_rate": 9.636494345718902e-06,
|
| 138085 |
+
"loss": 0.5694,
|
| 138086 |
+
"step": 23510
|
| 138087 |
+
},
|
| 138088 |
+
{
|
| 138089 |
+
"epoch": 189.0,
|
| 138090 |
+
"eval_loss": 0.536078691482544,
|
| 138091 |
+
"eval_runtime": 41.4114,
|
| 138092 |
+
"eval_samples_per_second": 20.188,
|
| 138093 |
+
"eval_steps_per_second": 0.652,
|
| 138094 |
+
"eval_wer": 0.23328228688106176,
|
| 138095 |
+
"step": 23515
|
| 138096 |
+
},
|
| 138097 |
+
{
|
| 138098 |
+
"epoch": 188.04,
|
| 138099 |
+
"learning_rate": 9.636332794830372e-06,
|
| 138100 |
+
"loss": 0.4769,
|
| 138101 |
+
"step": 23520
|
| 138102 |
+
},
|
| 138103 |
+
{
|
| 138104 |
+
"epoch": 188.12,
|
| 138105 |
+
"learning_rate": 9.636171243941841e-06,
|
| 138106 |
+
"loss": 0.4583,
|
| 138107 |
+
"step": 23530
|
| 138108 |
+
},
|
| 138109 |
+
{
|
| 138110 |
+
"epoch": 188.2,
|
| 138111 |
+
"learning_rate": 9.636009693053313e-06,
|
| 138112 |
+
"loss": 1.056,
|
| 138113 |
+
"step": 23540
|
| 138114 |
+
},
|
| 138115 |
+
{
|
| 138116 |
+
"epoch": 188.28,
|
| 138117 |
+
"learning_rate": 9.635848142164783e-06,
|
| 138118 |
+
"loss": 0.4627,
|
| 138119 |
+
"step": 23550
|
| 138120 |
+
},
|
| 138121 |
+
{
|
| 138122 |
+
"epoch": 188.36,
|
| 138123 |
+
"learning_rate": 9.635686591276253e-06,
|
| 138124 |
+
"loss": 0.5362,
|
| 138125 |
+
"step": 23560
|
| 138126 |
+
},
|
| 138127 |
+
{
|
| 138128 |
+
"epoch": 188.44,
|
| 138129 |
+
"learning_rate": 9.635525040387723e-06,
|
| 138130 |
+
"loss": 0.9567,
|
| 138131 |
+
"step": 23570
|
| 138132 |
+
},
|
| 138133 |
+
{
|
| 138134 |
+
"epoch": 188.52,
|
| 138135 |
+
"learning_rate": 9.635363489499193e-06,
|
| 138136 |
+
"loss": 0.4269,
|
| 138137 |
+
"step": 23580
|
| 138138 |
+
},
|
| 138139 |
+
{
|
| 138140 |
+
"epoch": 188.6,
|
| 138141 |
+
"learning_rate": 9.635201938610663e-06,
|
| 138142 |
+
"loss": 1.0836,
|
| 138143 |
+
"step": 23590
|
| 138144 |
+
},
|
| 138145 |
+
{
|
| 138146 |
+
"epoch": 188.68,
|
| 138147 |
+
"learning_rate": 9.635040387722133e-06,
|
| 138148 |
+
"loss": 0.4315,
|
| 138149 |
+
"step": 23600
|
| 138150 |
+
},
|
| 138151 |
+
{
|
| 138152 |
+
"epoch": 188.76,
|
| 138153 |
+
"learning_rate": 9.634878836833603e-06,
|
| 138154 |
+
"loss": 0.6082,
|
| 138155 |
+
"step": 23610
|
| 138156 |
+
},
|
| 138157 |
+
{
|
| 138158 |
+
"epoch": 188.84,
|
| 138159 |
+
"learning_rate": 9.634717285945073e-06,
|
| 138160 |
+
"loss": 0.9336,
|
| 138161 |
+
"step": 23620
|
| 138162 |
+
},
|
| 138163 |
+
{
|
| 138164 |
+
"epoch": 188.92,
|
| 138165 |
+
"learning_rate": 9.634555735056543e-06,
|
| 138166 |
+
"loss": 0.4082,
|
| 138167 |
+
"step": 23630
|
| 138168 |
+
},
|
| 138169 |
+
{
|
| 138170 |
+
"epoch": 189.0,
|
| 138171 |
+
"learning_rate": 9.634394184168013e-06,
|
| 138172 |
+
"loss": 1.0443,
|
| 138173 |
+
"step": 23640
|
| 138174 |
+
},
|
| 138175 |
+
{
|
| 138176 |
+
"epoch": 189.0,
|
| 138177 |
+
"eval_loss": 0.5065667033195496,
|
| 138178 |
+
"eval_runtime": 42.0844,
|
| 138179 |
+
"eval_samples_per_second": 19.865,
|
| 138180 |
+
"eval_steps_per_second": 0.642,
|
| 138181 |
+
"eval_wer": 0.22739455494427988,
|
| 138182 |
+
"step": 23640
|
| 138183 |
+
},
|
| 138184 |
+
{
|
| 138185 |
+
"epoch": 189.08,
|
| 138186 |
+
"learning_rate": 9.634232633279483e-06,
|
| 138187 |
+
"loss": 0.4957,
|
| 138188 |
+
"step": 23650
|
| 138189 |
+
},
|
| 138190 |
+
{
|
| 138191 |
+
"epoch": 189.16,
|
| 138192 |
+
"learning_rate": 9.634071082390955e-06,
|
| 138193 |
+
"loss": 0.5665,
|
| 138194 |
+
"step": 23660
|
| 138195 |
+
},
|
| 138196 |
+
{
|
| 138197 |
+
"epoch": 189.24,
|
| 138198 |
+
"learning_rate": 9.633909531502425e-06,
|
| 138199 |
+
"loss": 1.1195,
|
| 138200 |
+
"step": 23670
|
| 138201 |
+
},
|
| 138202 |
+
{
|
| 138203 |
+
"epoch": 189.32,
|
| 138204 |
+
"learning_rate": 9.633747980613895e-06,
|
| 138205 |
+
"loss": 0.4325,
|
| 138206 |
+
"step": 23680
|
| 138207 |
+
},
|
| 138208 |
+
{
|
| 138209 |
+
"epoch": 189.4,
|
| 138210 |
+
"learning_rate": 9.633586429725364e-06,
|
| 138211 |
+
"loss": 1.0041,
|
| 138212 |
+
"step": 23690
|
| 138213 |
+
},
|
| 138214 |
+
{
|
| 138215 |
+
"epoch": 189.48,
|
| 138216 |
+
"learning_rate": 9.633424878836834e-06,
|
| 138217 |
+
"loss": 0.4172,
|
| 138218 |
+
"step": 23700
|
| 138219 |
+
},
|
| 138220 |
+
{
|
| 138221 |
+
"epoch": 189.56,
|
| 138222 |
+
"learning_rate": 9.633263327948304e-06,
|
| 138223 |
+
"loss": 0.5875,
|
| 138224 |
+
"step": 23710
|
| 138225 |
+
},
|
| 138226 |
+
{
|
| 138227 |
+
"epoch": 189.64,
|
| 138228 |
+
"learning_rate": 9.633101777059774e-06,
|
| 138229 |
+
"loss": 1.0255,
|
| 138230 |
+
"step": 23720
|
| 138231 |
+
},
|
| 138232 |
+
{
|
| 138233 |
+
"epoch": 189.72,
|
| 138234 |
+
"learning_rate": 9.632940226171244e-06,
|
| 138235 |
+
"loss": 0.415,
|
| 138236 |
+
"step": 23730
|
| 138237 |
+
},
|
| 138238 |
+
{
|
| 138239 |
+
"epoch": 189.8,
|
| 138240 |
+
"learning_rate": 9.632778675282714e-06,
|
| 138241 |
+
"loss": 1.01,
|
| 138242 |
+
"step": 23740
|
| 138243 |
+
},
|
| 138244 |
+
{
|
| 138245 |
+
"epoch": 189.88,
|
| 138246 |
+
"learning_rate": 9.632617124394184e-06,
|
| 138247 |
+
"loss": 0.4168,
|
| 138248 |
+
"step": 23750
|
| 138249 |
+
},
|
| 138250 |
+
{
|
| 138251 |
+
"epoch": 189.96,
|
| 138252 |
+
"learning_rate": 9.632455573505654e-06,
|
| 138253 |
+
"loss": 0.6321,
|
| 138254 |
+
"step": 23760
|
| 138255 |
+
},
|
| 138256 |
+
{
|
| 138257 |
+
"epoch": 190.0,
|
| 138258 |
+
"eval_loss": 0.67093425989151,
|
| 138259 |
+
"eval_runtime": 39.8635,
|
| 138260 |
+
"eval_samples_per_second": 20.972,
|
| 138261 |
+
"eval_steps_per_second": 0.677,
|
| 138262 |
+
"eval_wer": 0.24058212688546957,
|
| 138263 |
+
"step": 23765
|
| 138264 |
}
|
| 138265 |
],
|
| 138266 |
+
"max_steps": 625000,
|
| 138267 |
"num_train_epochs": 5000,
|
| 138268 |
+
"total_flos": 6.687085418220264e+19,
|
| 138269 |
"trial_name": null,
|
| 138270 |
"trial_params": null
|
| 138271 |
}
|
model-bin/finetune/base/{checkpoint-22893 → checkpoint-23765}/training_args.bin
RENAMED
|
File without changes
|
model-bin/finetune/base/{checkpoint-23266 → checkpoint-23890}/config.json
RENAMED
|
File without changes
|
model-bin/finetune/base/{checkpoint-23266 → checkpoint-23890}/optimizer.pt
RENAMED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 722165009
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:af2e3e6483177d469e78fda0bf8e474a560df0f8e29464802e5c49941615878b
|
| 3 |
size 722165009
|
model-bin/finetune/base/{checkpoint-23266 → checkpoint-23890}/preprocessor_config.json
RENAMED
|
File without changes
|
model-bin/finetune/base/{checkpoint-22893 → checkpoint-23890}/pytorch_model.bin
RENAMED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 377909911
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bf1dcf846e092936112d10588c82b38993a4406053b079856cdc96cc106504bf
|
| 3 |
size 377909911
|
model-bin/finetune/base/{checkpoint-23266 → checkpoint-23890}/rng_state.pth
RENAMED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14567
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e15223aa8a4e54f653e957040110510a699f2a203b15b4b80e5f163da185bb3b
|
| 3 |
size 14567
|
model-bin/finetune/base/{checkpoint-22893 → checkpoint-23890}/scaler.pt
RENAMED
|
@@ -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 sha256:296863b77db81b06d752c374760ece89edb8e64abd8c4f713f25b4043b63a048
|
| 3 |
size 559
|
model-bin/finetune/base/{checkpoint-23266 → checkpoint-23890}/scheduler.pt
RENAMED
|
@@ -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:e6bf76a43bba2c56d2a189c74a71692c5186f7b00ca77dbc1061e14fc8c9cdf6
|
| 3 |
size 623
|
model-bin/finetune/base/{checkpoint-22893 → checkpoint-23890}/trainer_state.json
RENAMED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 0.
|
| 3 |
-
"best_model_checkpoint": "./model-bin/finetune/base/checkpoint-
|
| 4 |
-
"epoch":
|
| 5 |
-
"global_step":
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
@@ -137676,11 +137676,683 @@
|
|
| 137676 |
"eval_steps_per_second": 0.634,
|
| 137677 |
"eval_wer": 0.22373344847438112,
|
| 137678 |
"step": 22893
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 137679 |
}
|
| 137680 |
],
|
| 137681 |
"max_steps": 625000,
|
| 137682 |
"num_train_epochs": 5000,
|
| 137683 |
-
"total_flos": 6.
|
| 137684 |
"trial_name": null,
|
| 137685 |
"trial_params": null
|
| 137686 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.2172567645365573,
|
| 3 |
+
"best_model_checkpoint": "./model-bin/finetune/base/checkpoint-23890",
|
| 4 |
+
"epoch": 191.0,
|
| 5 |
+
"global_step": 23890,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
|
|
| 137676 |
"eval_steps_per_second": 0.634,
|
| 137677 |
"eval_wer": 0.22373344847438112,
|
| 137678 |
"step": 22893
|
| 137679 |
+
},
|
| 137680 |
+
{
|
| 137681 |
+
"epoch": 184.06,
|
| 137682 |
+
"learning_rate": 9.646348949919225e-06,
|
| 137683 |
+
"loss": 0.4663,
|
| 137684 |
+
"step": 22900
|
| 137685 |
+
},
|
| 137686 |
+
{
|
| 137687 |
+
"epoch": 184.14,
|
| 137688 |
+
"learning_rate": 9.646187399030695e-06,
|
| 137689 |
+
"loss": 0.4929,
|
| 137690 |
+
"step": 22910
|
| 137691 |
+
},
|
| 137692 |
+
{
|
| 137693 |
+
"epoch": 184.22,
|
| 137694 |
+
"learning_rate": 9.646025848142165e-06,
|
| 137695 |
+
"loss": 1.0552,
|
| 137696 |
+
"step": 22920
|
| 137697 |
+
},
|
| 137698 |
+
{
|
| 137699 |
+
"epoch": 184.3,
|
| 137700 |
+
"learning_rate": 9.645864297253636e-06,
|
| 137701 |
+
"loss": 0.4567,
|
| 137702 |
+
"step": 22930
|
| 137703 |
+
},
|
| 137704 |
+
{
|
| 137705 |
+
"epoch": 184.38,
|
| 137706 |
+
"learning_rate": 9.645702746365106e-06,
|
| 137707 |
+
"loss": 0.6976,
|
| 137708 |
+
"step": 22940
|
| 137709 |
+
},
|
| 137710 |
+
{
|
| 137711 |
+
"epoch": 184.46,
|
| 137712 |
+
"learning_rate": 9.645541195476576e-06,
|
| 137713 |
+
"loss": 0.9129,
|
| 137714 |
+
"step": 22950
|
| 137715 |
+
},
|
| 137716 |
+
{
|
| 137717 |
+
"epoch": 184.54,
|
| 137718 |
+
"learning_rate": 9.645379644588046e-06,
|
| 137719 |
+
"loss": 0.4552,
|
| 137720 |
+
"step": 22960
|
| 137721 |
+
},
|
| 137722 |
+
{
|
| 137723 |
+
"epoch": 184.62,
|
| 137724 |
+
"learning_rate": 9.645218093699516e-06,
|
| 137725 |
+
"loss": 1.0201,
|
| 137726 |
+
"step": 22970
|
| 137727 |
+
},
|
| 137728 |
+
{
|
| 137729 |
+
"epoch": 184.7,
|
| 137730 |
+
"learning_rate": 9.645056542810986e-06,
|
| 137731 |
+
"loss": 0.4497,
|
| 137732 |
+
"step": 22980
|
| 137733 |
+
},
|
| 137734 |
+
{
|
| 137735 |
+
"epoch": 184.78,
|
| 137736 |
+
"learning_rate": 9.644894991922456e-06,
|
| 137737 |
+
"loss": 0.6841,
|
| 137738 |
+
"step": 22990
|
| 137739 |
+
},
|
| 137740 |
+
{
|
| 137741 |
+
"epoch": 184.86,
|
| 137742 |
+
"learning_rate": 9.644733441033926e-06,
|
| 137743 |
+
"loss": 0.861,
|
| 137744 |
+
"step": 23000
|
| 137745 |
+
},
|
| 137746 |
+
{
|
| 137747 |
+
"epoch": 184.94,
|
| 137748 |
+
"learning_rate": 9.644571890145396e-06,
|
| 137749 |
+
"loss": 0.4432,
|
| 137750 |
+
"step": 23010
|
| 137751 |
+
},
|
| 137752 |
+
{
|
| 137753 |
+
"epoch": 185.0,
|
| 137754 |
+
"eval_loss": 0.4946533739566803,
|
| 137755 |
+
"eval_runtime": 40.0956,
|
| 137756 |
+
"eval_samples_per_second": 20.85,
|
| 137757 |
+
"eval_steps_per_second": 0.673,
|
| 137758 |
+
"eval_wer": 0.2353116834639791,
|
| 137759 |
+
"step": 23017
|
| 137760 |
+
},
|
| 137761 |
+
{
|
| 137762 |
+
"epoch": 184.02,
|
| 137763 |
+
"learning_rate": 9.644410339256866e-06,
|
| 137764 |
+
"loss": 0.4684,
|
| 137765 |
+
"step": 23020
|
| 137766 |
+
},
|
| 137767 |
+
{
|
| 137768 |
+
"epoch": 184.1,
|
| 137769 |
+
"learning_rate": 9.644248788368336e-06,
|
| 137770 |
+
"loss": 0.4757,
|
| 137771 |
+
"step": 23030
|
| 137772 |
+
},
|
| 137773 |
+
{
|
| 137774 |
+
"epoch": 184.18,
|
| 137775 |
+
"learning_rate": 9.644087237479806e-06,
|
| 137776 |
+
"loss": 0.6576,
|
| 137777 |
+
"step": 23040
|
| 137778 |
+
},
|
| 137779 |
+
{
|
| 137780 |
+
"epoch": 184.26,
|
| 137781 |
+
"learning_rate": 9.643925686591276e-06,
|
| 137782 |
+
"loss": 0.756,
|
| 137783 |
+
"step": 23050
|
| 137784 |
+
},
|
| 137785 |
+
{
|
| 137786 |
+
"epoch": 184.34,
|
| 137787 |
+
"learning_rate": 9.643764135702746e-06,
|
| 137788 |
+
"loss": 0.5006,
|
| 137789 |
+
"step": 23060
|
| 137790 |
+
},
|
| 137791 |
+
{
|
| 137792 |
+
"epoch": 184.42,
|
| 137793 |
+
"learning_rate": 9.643602584814218e-06,
|
| 137794 |
+
"loss": 1.0807,
|
| 137795 |
+
"step": 23070
|
| 137796 |
+
},
|
| 137797 |
+
{
|
| 137798 |
+
"epoch": 184.5,
|
| 137799 |
+
"learning_rate": 9.643441033925688e-06,
|
| 137800 |
+
"loss": 0.4353,
|
| 137801 |
+
"step": 23080
|
| 137802 |
+
},
|
| 137803 |
+
{
|
| 137804 |
+
"epoch": 184.58,
|
| 137805 |
+
"learning_rate": 9.643279483037158e-06,
|
| 137806 |
+
"loss": 0.7112,
|
| 137807 |
+
"step": 23090
|
| 137808 |
+
},
|
| 137809 |
+
{
|
| 137810 |
+
"epoch": 184.66,
|
| 137811 |
+
"learning_rate": 9.643117932148627e-06,
|
| 137812 |
+
"loss": 0.9139,
|
| 137813 |
+
"step": 23100
|
| 137814 |
+
},
|
| 137815 |
+
{
|
| 137816 |
+
"epoch": 184.74,
|
| 137817 |
+
"learning_rate": 9.642956381260097e-06,
|
| 137818 |
+
"loss": 0.4894,
|
| 137819 |
+
"step": 23110
|
| 137820 |
+
},
|
| 137821 |
+
{
|
| 137822 |
+
"epoch": 184.82,
|
| 137823 |
+
"learning_rate": 9.642794830371567e-06,
|
| 137824 |
+
"loss": 1.0287,
|
| 137825 |
+
"step": 23120
|
| 137826 |
+
},
|
| 137827 |
+
{
|
| 137828 |
+
"epoch": 184.9,
|
| 137829 |
+
"learning_rate": 9.642633279483037e-06,
|
| 137830 |
+
"loss": 0.5134,
|
| 137831 |
+
"step": 23130
|
| 137832 |
+
},
|
| 137833 |
+
{
|
| 137834 |
+
"epoch": 184.98,
|
| 137835 |
+
"learning_rate": 9.642471728594507e-06,
|
| 137836 |
+
"loss": 0.8674,
|
| 137837 |
+
"step": 23140
|
| 137838 |
+
},
|
| 137839 |
+
{
|
| 137840 |
+
"epoch": 185.0,
|
| 137841 |
+
"eval_loss": 0.5111840963363647,
|
| 137842 |
+
"eval_runtime": 40.5764,
|
| 137843 |
+
"eval_samples_per_second": 20.628,
|
| 137844 |
+
"eval_steps_per_second": 0.665,
|
| 137845 |
+
"eval_wer": 0.23337041156840935,
|
| 137846 |
+
"step": 23142
|
| 137847 |
+
},
|
| 137848 |
+
{
|
| 137849 |
+
"epoch": 186.06,
|
| 137850 |
+
"learning_rate": 9.642310177705977e-06,
|
| 137851 |
+
"loss": 0.4571,
|
| 137852 |
+
"step": 23150
|
| 137853 |
+
},
|
| 137854 |
+
{
|
| 137855 |
+
"epoch": 186.14,
|
| 137856 |
+
"learning_rate": 9.642148626817447e-06,
|
| 137857 |
+
"loss": 0.5447,
|
| 137858 |
+
"step": 23160
|
| 137859 |
+
},
|
| 137860 |
+
{
|
| 137861 |
+
"epoch": 186.22,
|
| 137862 |
+
"learning_rate": 9.641987075928917e-06,
|
| 137863 |
+
"loss": 1.021,
|
| 137864 |
+
"step": 23170
|
| 137865 |
+
},
|
| 137866 |
+
{
|
| 137867 |
+
"epoch": 186.31,
|
| 137868 |
+
"learning_rate": 9.641825525040387e-06,
|
| 137869 |
+
"loss": 0.4516,
|
| 137870 |
+
"step": 23180
|
| 137871 |
+
},
|
| 137872 |
+
{
|
| 137873 |
+
"epoch": 186.39,
|
| 137874 |
+
"learning_rate": 9.641663974151859e-06,
|
| 137875 |
+
"loss": 0.8244,
|
| 137876 |
+
"step": 23190
|
| 137877 |
+
},
|
| 137878 |
+
{
|
| 137879 |
+
"epoch": 186.47,
|
| 137880 |
+
"learning_rate": 9.641502423263329e-06,
|
| 137881 |
+
"loss": 0.7353,
|
| 137882 |
+
"step": 23200
|
| 137883 |
+
},
|
| 137884 |
+
{
|
| 137885 |
+
"epoch": 186.55,
|
| 137886 |
+
"learning_rate": 9.641340872374799e-06,
|
| 137887 |
+
"loss": 0.4783,
|
| 137888 |
+
"step": 23210
|
| 137889 |
+
},
|
| 137890 |
+
{
|
| 137891 |
+
"epoch": 186.63,
|
| 137892 |
+
"learning_rate": 9.641179321486269e-06,
|
| 137893 |
+
"loss": 1.0272,
|
| 137894 |
+
"step": 23220
|
| 137895 |
+
},
|
| 137896 |
+
{
|
| 137897 |
+
"epoch": 186.71,
|
| 137898 |
+
"learning_rate": 9.641017770597739e-06,
|
| 137899 |
+
"loss": 0.4518,
|
| 137900 |
+
"step": 23230
|
| 137901 |
+
},
|
| 137902 |
+
{
|
| 137903 |
+
"epoch": 186.79,
|
| 137904 |
+
"learning_rate": 9.640856219709209e-06,
|
| 137905 |
+
"loss": 0.7568,
|
| 137906 |
+
"step": 23240
|
| 137907 |
+
},
|
| 137908 |
+
{
|
| 137909 |
+
"epoch": 186.87,
|
| 137910 |
+
"learning_rate": 9.640694668820679e-06,
|
| 137911 |
+
"loss": 0.7686,
|
| 137912 |
+
"step": 23250
|
| 137913 |
+
},
|
| 137914 |
+
{
|
| 137915 |
+
"epoch": 186.95,
|
| 137916 |
+
"learning_rate": 9.640533117932149e-06,
|
| 137917 |
+
"loss": 0.5597,
|
| 137918 |
+
"step": 23260
|
| 137919 |
+
},
|
| 137920 |
+
{
|
| 137921 |
+
"epoch": 187.0,
|
| 137922 |
+
"eval_loss": 0.5327870845794678,
|
| 137923 |
+
"eval_runtime": 41.0516,
|
| 137924 |
+
"eval_samples_per_second": 20.389,
|
| 137925 |
+
"eval_steps_per_second": 0.658,
|
| 137926 |
+
"eval_wer": 0.2345039771874531,
|
| 137927 |
+
"step": 23266
|
| 137928 |
+
},
|
| 137929 |
+
{
|
| 137930 |
+
"epoch": 186.03,
|
| 137931 |
+
"learning_rate": 9.640371567043619e-06,
|
| 137932 |
+
"loss": 0.439,
|
| 137933 |
+
"step": 23270
|
| 137934 |
+
},
|
| 137935 |
+
{
|
| 137936 |
+
"epoch": 186.11,
|
| 137937 |
+
"learning_rate": 9.640210016155089e-06,
|
| 137938 |
+
"loss": 0.461,
|
| 137939 |
+
"step": 23280
|
| 137940 |
+
},
|
| 137941 |
+
{
|
| 137942 |
+
"epoch": 186.19,
|
| 137943 |
+
"learning_rate": 9.640048465266559e-06,
|
| 137944 |
+
"loss": 0.8283,
|
| 137945 |
+
"step": 23290
|
| 137946 |
+
},
|
| 137947 |
+
{
|
| 137948 |
+
"epoch": 186.27,
|
| 137949 |
+
"learning_rate": 9.639886914378029e-06,
|
| 137950 |
+
"loss": 0.6584,
|
| 137951 |
+
"step": 23300
|
| 137952 |
+
},
|
| 137953 |
+
{
|
| 137954 |
+
"epoch": 186.35,
|
| 137955 |
+
"learning_rate": 9.6397253634895e-06,
|
| 137956 |
+
"loss": 0.542,
|
| 137957 |
+
"step": 23310
|
| 137958 |
+
},
|
| 137959 |
+
{
|
| 137960 |
+
"epoch": 186.43,
|
| 137961 |
+
"learning_rate": 9.63956381260097e-06,
|
| 137962 |
+
"loss": 0.955,
|
| 137963 |
+
"step": 23320
|
| 137964 |
+
},
|
| 137965 |
+
{
|
| 137966 |
+
"epoch": 186.51,
|
| 137967 |
+
"learning_rate": 9.63940226171244e-06,
|
| 137968 |
+
"loss": 0.4646,
|
| 137969 |
+
"step": 23330
|
| 137970 |
+
},
|
| 137971 |
+
{
|
| 137972 |
+
"epoch": 186.59,
|
| 137973 |
+
"learning_rate": 9.63924071082391e-06,
|
| 137974 |
+
"loss": 0.7872,
|
| 137975 |
+
"step": 23340
|
| 137976 |
+
},
|
| 137977 |
+
{
|
| 137978 |
+
"epoch": 186.67,
|
| 137979 |
+
"learning_rate": 9.63907915993538e-06,
|
| 137980 |
+
"loss": 0.9723,
|
| 137981 |
+
"step": 23350
|
| 137982 |
+
},
|
| 137983 |
+
{
|
| 137984 |
+
"epoch": 186.75,
|
| 137985 |
+
"learning_rate": 9.63891760904685e-06,
|
| 137986 |
+
"loss": 0.5465,
|
| 137987 |
+
"step": 23360
|
| 137988 |
+
},
|
| 137989 |
+
{
|
| 137990 |
+
"epoch": 186.83,
|
| 137991 |
+
"learning_rate": 9.63875605815832e-06,
|
| 137992 |
+
"loss": 1.1675,
|
| 137993 |
+
"step": 23370
|
| 137994 |
+
},
|
| 137995 |
+
{
|
| 137996 |
+
"epoch": 186.91,
|
| 137997 |
+
"learning_rate": 9.63859450726979e-06,
|
| 137998 |
+
"loss": 0.4183,
|
| 137999 |
+
"step": 23380
|
| 138000 |
+
},
|
| 138001 |
+
{
|
| 138002 |
+
"epoch": 186.99,
|
| 138003 |
+
"learning_rate": 9.63843295638126e-06,
|
| 138004 |
+
"loss": 0.7856,
|
| 138005 |
+
"step": 23390
|
| 138006 |
+
},
|
| 138007 |
+
{
|
| 138008 |
+
"epoch": 187.0,
|
| 138009 |
+
"eval_loss": 0.549532413482666,
|
| 138010 |
+
"eval_runtime": 41.1758,
|
| 138011 |
+
"eval_samples_per_second": 20.303,
|
| 138012 |
+
"eval_steps_per_second": 0.656,
|
| 138013 |
+
"eval_wer": 0.2319283686394409,
|
| 138014 |
+
"step": 23391
|
| 138015 |
+
},
|
| 138016 |
+
{
|
| 138017 |
+
"epoch": 188.07,
|
| 138018 |
+
"learning_rate": 9.63827140549273e-06,
|
| 138019 |
+
"loss": 0.4892,
|
| 138020 |
+
"step": 23400
|
| 138021 |
+
},
|
| 138022 |
+
{
|
| 138023 |
+
"epoch": 188.15,
|
| 138024 |
+
"learning_rate": 9.6381098546042e-06,
|
| 138025 |
+
"loss": 0.4829,
|
| 138026 |
+
"step": 23410
|
| 138027 |
+
},
|
| 138028 |
+
{
|
| 138029 |
+
"epoch": 188.23,
|
| 138030 |
+
"learning_rate": 9.63794830371567e-06,
|
| 138031 |
+
"loss": 1.0797,
|
| 138032 |
+
"step": 23420
|
| 138033 |
+
},
|
| 138034 |
+
{
|
| 138035 |
+
"epoch": 188.31,
|
| 138036 |
+
"learning_rate": 9.637786752827142e-06,
|
| 138037 |
+
"loss": 0.4272,
|
| 138038 |
+
"step": 23430
|
| 138039 |
+
},
|
| 138040 |
+
{
|
| 138041 |
+
"epoch": 188.39,
|
| 138042 |
+
"learning_rate": 9.637625201938612e-06,
|
| 138043 |
+
"loss": 0.9337,
|
| 138044 |
+
"step": 23440
|
| 138045 |
+
},
|
| 138046 |
+
{
|
| 138047 |
+
"epoch": 188.47,
|
| 138048 |
+
"learning_rate": 9.637463651050082e-06,
|
| 138049 |
+
"loss": 0.6514,
|
| 138050 |
+
"step": 23450
|
| 138051 |
+
},
|
| 138052 |
+
{
|
| 138053 |
+
"epoch": 188.55,
|
| 138054 |
+
"learning_rate": 9.637302100161552e-06,
|
| 138055 |
+
"loss": 0.516,
|
| 138056 |
+
"step": 23460
|
| 138057 |
+
},
|
| 138058 |
+
{
|
| 138059 |
+
"epoch": 188.63,
|
| 138060 |
+
"learning_rate": 9.637140549273022e-06,
|
| 138061 |
+
"loss": 1.0524,
|
| 138062 |
+
"step": 23470
|
| 138063 |
+
},
|
| 138064 |
+
{
|
| 138065 |
+
"epoch": 188.71,
|
| 138066 |
+
"learning_rate": 9.636978998384492e-06,
|
| 138067 |
+
"loss": 0.5051,
|
| 138068 |
+
"step": 23480
|
| 138069 |
+
},
|
| 138070 |
+
{
|
| 138071 |
+
"epoch": 188.8,
|
| 138072 |
+
"learning_rate": 9.636817447495962e-06,
|
| 138073 |
+
"loss": 0.8574,
|
| 138074 |
+
"step": 23490
|
| 138075 |
+
},
|
| 138076 |
+
{
|
| 138077 |
+
"epoch": 188.88,
|
| 138078 |
+
"learning_rate": 9.636655896607432e-06,
|
| 138079 |
+
"loss": 0.6547,
|
| 138080 |
+
"step": 23500
|
| 138081 |
+
},
|
| 138082 |
+
{
|
| 138083 |
+
"epoch": 188.96,
|
| 138084 |
+
"learning_rate": 9.636494345718902e-06,
|
| 138085 |
+
"loss": 0.5694,
|
| 138086 |
+
"step": 23510
|
| 138087 |
+
},
|
| 138088 |
+
{
|
| 138089 |
+
"epoch": 189.0,
|
| 138090 |
+
"eval_loss": 0.536078691482544,
|
| 138091 |
+
"eval_runtime": 41.4114,
|
| 138092 |
+
"eval_samples_per_second": 20.188,
|
| 138093 |
+
"eval_steps_per_second": 0.652,
|
| 138094 |
+
"eval_wer": 0.23328228688106176,
|
| 138095 |
+
"step": 23515
|
| 138096 |
+
},
|
| 138097 |
+
{
|
| 138098 |
+
"epoch": 188.04,
|
| 138099 |
+
"learning_rate": 9.636332794830372e-06,
|
| 138100 |
+
"loss": 0.4769,
|
| 138101 |
+
"step": 23520
|
| 138102 |
+
},
|
| 138103 |
+
{
|
| 138104 |
+
"epoch": 188.12,
|
| 138105 |
+
"learning_rate": 9.636171243941841e-06,
|
| 138106 |
+
"loss": 0.4583,
|
| 138107 |
+
"step": 23530
|
| 138108 |
+
},
|
| 138109 |
+
{
|
| 138110 |
+
"epoch": 188.2,
|
| 138111 |
+
"learning_rate": 9.636009693053313e-06,
|
| 138112 |
+
"loss": 1.056,
|
| 138113 |
+
"step": 23540
|
| 138114 |
+
},
|
| 138115 |
+
{
|
| 138116 |
+
"epoch": 188.28,
|
| 138117 |
+
"learning_rate": 9.635848142164783e-06,
|
| 138118 |
+
"loss": 0.4627,
|
| 138119 |
+
"step": 23550
|
| 138120 |
+
},
|
| 138121 |
+
{
|
| 138122 |
+
"epoch": 188.36,
|
| 138123 |
+
"learning_rate": 9.635686591276253e-06,
|
| 138124 |
+
"loss": 0.5362,
|
| 138125 |
+
"step": 23560
|
| 138126 |
+
},
|
| 138127 |
+
{
|
| 138128 |
+
"epoch": 188.44,
|
| 138129 |
+
"learning_rate": 9.635525040387723e-06,
|
| 138130 |
+
"loss": 0.9567,
|
| 138131 |
+
"step": 23570
|
| 138132 |
+
},
|
| 138133 |
+
{
|
| 138134 |
+
"epoch": 188.52,
|
| 138135 |
+
"learning_rate": 9.635363489499193e-06,
|
| 138136 |
+
"loss": 0.4269,
|
| 138137 |
+
"step": 23580
|
| 138138 |
+
},
|
| 138139 |
+
{
|
| 138140 |
+
"epoch": 188.6,
|
| 138141 |
+
"learning_rate": 9.635201938610663e-06,
|
| 138142 |
+
"loss": 1.0836,
|
| 138143 |
+
"step": 23590
|
| 138144 |
+
},
|
| 138145 |
+
{
|
| 138146 |
+
"epoch": 188.68,
|
| 138147 |
+
"learning_rate": 9.635040387722133e-06,
|
| 138148 |
+
"loss": 0.4315,
|
| 138149 |
+
"step": 23600
|
| 138150 |
+
},
|
| 138151 |
+
{
|
| 138152 |
+
"epoch": 188.76,
|
| 138153 |
+
"learning_rate": 9.634878836833603e-06,
|
| 138154 |
+
"loss": 0.6082,
|
| 138155 |
+
"step": 23610
|
| 138156 |
+
},
|
| 138157 |
+
{
|
| 138158 |
+
"epoch": 188.84,
|
| 138159 |
+
"learning_rate": 9.634717285945073e-06,
|
| 138160 |
+
"loss": 0.9336,
|
| 138161 |
+
"step": 23620
|
| 138162 |
+
},
|
| 138163 |
+
{
|
| 138164 |
+
"epoch": 188.92,
|
| 138165 |
+
"learning_rate": 9.634555735056543e-06,
|
| 138166 |
+
"loss": 0.4082,
|
| 138167 |
+
"step": 23630
|
| 138168 |
+
},
|
| 138169 |
+
{
|
| 138170 |
+
"epoch": 189.0,
|
| 138171 |
+
"learning_rate": 9.634394184168013e-06,
|
| 138172 |
+
"loss": 1.0443,
|
| 138173 |
+
"step": 23640
|
| 138174 |
+
},
|
| 138175 |
+
{
|
| 138176 |
+
"epoch": 189.0,
|
| 138177 |
+
"eval_loss": 0.5065667033195496,
|
| 138178 |
+
"eval_runtime": 42.0844,
|
| 138179 |
+
"eval_samples_per_second": 19.865,
|
| 138180 |
+
"eval_steps_per_second": 0.642,
|
| 138181 |
+
"eval_wer": 0.22739455494427988,
|
| 138182 |
+
"step": 23640
|
| 138183 |
+
},
|
| 138184 |
+
{
|
| 138185 |
+
"epoch": 189.08,
|
| 138186 |
+
"learning_rate": 9.634232633279483e-06,
|
| 138187 |
+
"loss": 0.4957,
|
| 138188 |
+
"step": 23650
|
| 138189 |
+
},
|
| 138190 |
+
{
|
| 138191 |
+
"epoch": 189.16,
|
| 138192 |
+
"learning_rate": 9.634071082390955e-06,
|
| 138193 |
+
"loss": 0.5665,
|
| 138194 |
+
"step": 23660
|
| 138195 |
+
},
|
| 138196 |
+
{
|
| 138197 |
+
"epoch": 189.24,
|
| 138198 |
+
"learning_rate": 9.633909531502425e-06,
|
| 138199 |
+
"loss": 1.1195,
|
| 138200 |
+
"step": 23670
|
| 138201 |
+
},
|
| 138202 |
+
{
|
| 138203 |
+
"epoch": 189.32,
|
| 138204 |
+
"learning_rate": 9.633747980613895e-06,
|
| 138205 |
+
"loss": 0.4325,
|
| 138206 |
+
"step": 23680
|
| 138207 |
+
},
|
| 138208 |
+
{
|
| 138209 |
+
"epoch": 189.4,
|
| 138210 |
+
"learning_rate": 9.633586429725364e-06,
|
| 138211 |
+
"loss": 1.0041,
|
| 138212 |
+
"step": 23690
|
| 138213 |
+
},
|
| 138214 |
+
{
|
| 138215 |
+
"epoch": 189.48,
|
| 138216 |
+
"learning_rate": 9.633424878836834e-06,
|
| 138217 |
+
"loss": 0.4172,
|
| 138218 |
+
"step": 23700
|
| 138219 |
+
},
|
| 138220 |
+
{
|
| 138221 |
+
"epoch": 189.56,
|
| 138222 |
+
"learning_rate": 9.633263327948304e-06,
|
| 138223 |
+
"loss": 0.5875,
|
| 138224 |
+
"step": 23710
|
| 138225 |
+
},
|
| 138226 |
+
{
|
| 138227 |
+
"epoch": 189.64,
|
| 138228 |
+
"learning_rate": 9.633101777059774e-06,
|
| 138229 |
+
"loss": 1.0255,
|
| 138230 |
+
"step": 23720
|
| 138231 |
+
},
|
| 138232 |
+
{
|
| 138233 |
+
"epoch": 189.72,
|
| 138234 |
+
"learning_rate": 9.632940226171244e-06,
|
| 138235 |
+
"loss": 0.415,
|
| 138236 |
+
"step": 23730
|
| 138237 |
+
},
|
| 138238 |
+
{
|
| 138239 |
+
"epoch": 189.8,
|
| 138240 |
+
"learning_rate": 9.632778675282714e-06,
|
| 138241 |
+
"loss": 1.01,
|
| 138242 |
+
"step": 23740
|
| 138243 |
+
},
|
| 138244 |
+
{
|
| 138245 |
+
"epoch": 189.88,
|
| 138246 |
+
"learning_rate": 9.632617124394184e-06,
|
| 138247 |
+
"loss": 0.4168,
|
| 138248 |
+
"step": 23750
|
| 138249 |
+
},
|
| 138250 |
+
{
|
| 138251 |
+
"epoch": 189.96,
|
| 138252 |
+
"learning_rate": 9.632455573505654e-06,
|
| 138253 |
+
"loss": 0.6321,
|
| 138254 |
+
"step": 23760
|
| 138255 |
+
},
|
| 138256 |
+
{
|
| 138257 |
+
"epoch": 190.0,
|
| 138258 |
+
"eval_loss": 0.67093425989151,
|
| 138259 |
+
"eval_runtime": 39.8635,
|
| 138260 |
+
"eval_samples_per_second": 20.972,
|
| 138261 |
+
"eval_steps_per_second": 0.677,
|
| 138262 |
+
"eval_wer": 0.24058212688546957,
|
| 138263 |
+
"step": 23765
|
| 138264 |
+
},
|
| 138265 |
+
{
|
| 138266 |
+
"epoch": 190.04,
|
| 138267 |
+
"learning_rate": 9.632294022617124e-06,
|
| 138268 |
+
"loss": 0.5074,
|
| 138269 |
+
"step": 23770
|
| 138270 |
+
},
|
| 138271 |
+
{
|
| 138272 |
+
"epoch": 190.12,
|
| 138273 |
+
"learning_rate": 9.632132471728596e-06,
|
| 138274 |
+
"loss": 0.4812,
|
| 138275 |
+
"step": 23780
|
| 138276 |
+
},
|
| 138277 |
+
{
|
| 138278 |
+
"epoch": 190.2,
|
| 138279 |
+
"learning_rate": 9.631970920840066e-06,
|
| 138280 |
+
"loss": 1.0191,
|
| 138281 |
+
"step": 23790
|
| 138282 |
+
},
|
| 138283 |
+
{
|
| 138284 |
+
"epoch": 190.28,
|
| 138285 |
+
"learning_rate": 9.631809369951536e-06,
|
| 138286 |
+
"loss": 0.5023,
|
| 138287 |
+
"step": 23800
|
| 138288 |
+
},
|
| 138289 |
+
{
|
| 138290 |
+
"epoch": 190.36,
|
| 138291 |
+
"learning_rate": 9.631647819063006e-06,
|
| 138292 |
+
"loss": 0.6277,
|
| 138293 |
+
"step": 23810
|
| 138294 |
+
},
|
| 138295 |
+
{
|
| 138296 |
+
"epoch": 190.44,
|
| 138297 |
+
"learning_rate": 9.631486268174476e-06,
|
| 138298 |
+
"loss": 0.9313,
|
| 138299 |
+
"step": 23820
|
| 138300 |
+
},
|
| 138301 |
+
{
|
| 138302 |
+
"epoch": 190.52,
|
| 138303 |
+
"learning_rate": 9.631324717285946e-06,
|
| 138304 |
+
"loss": 0.5032,
|
| 138305 |
+
"step": 23830
|
| 138306 |
+
},
|
| 138307 |
+
{
|
| 138308 |
+
"epoch": 190.6,
|
| 138309 |
+
"learning_rate": 9.631163166397416e-06,
|
| 138310 |
+
"loss": 1.0566,
|
| 138311 |
+
"step": 23840
|
| 138312 |
+
},
|
| 138313 |
+
{
|
| 138314 |
+
"epoch": 190.68,
|
| 138315 |
+
"learning_rate": 9.631001615508886e-06,
|
| 138316 |
+
"loss": 0.4492,
|
| 138317 |
+
"step": 23850
|
| 138318 |
+
},
|
| 138319 |
+
{
|
| 138320 |
+
"epoch": 190.76,
|
| 138321 |
+
"learning_rate": 9.630840064620356e-06,
|
| 138322 |
+
"loss": 0.5329,
|
| 138323 |
+
"step": 23860
|
| 138324 |
+
},
|
| 138325 |
+
{
|
| 138326 |
+
"epoch": 190.84,
|
| 138327 |
+
"learning_rate": 9.630678513731826e-06,
|
| 138328 |
+
"loss": 0.9454,
|
| 138329 |
+
"step": 23870
|
| 138330 |
+
},
|
| 138331 |
+
{
|
| 138332 |
+
"epoch": 190.92,
|
| 138333 |
+
"learning_rate": 9.630516962843296e-06,
|
| 138334 |
+
"loss": 0.4499,
|
| 138335 |
+
"step": 23880
|
| 138336 |
+
},
|
| 138337 |
+
{
|
| 138338 |
+
"epoch": 191.0,
|
| 138339 |
+
"learning_rate": 9.630355411954767e-06,
|
| 138340 |
+
"loss": 0.9996,
|
| 138341 |
+
"step": 23890
|
| 138342 |
+
},
|
| 138343 |
+
{
|
| 138344 |
+
"epoch": 191.0,
|
| 138345 |
+
"eval_loss": 0.5291967988014221,
|
| 138346 |
+
"eval_runtime": 41.96,
|
| 138347 |
+
"eval_samples_per_second": 19.924,
|
| 138348 |
+
"eval_steps_per_second": 0.643,
|
| 138349 |
+
"eval_wer": 0.2172567645365573,
|
| 138350 |
+
"step": 23890
|
| 138351 |
}
|
| 138352 |
],
|
| 138353 |
"max_steps": 625000,
|
| 138354 |
"num_train_epochs": 5000,
|
| 138355 |
+
"total_flos": 6.722296405038744e+19,
|
| 138356 |
"trial_name": null,
|
| 138357 |
"trial_params": null
|
| 138358 |
}
|
model-bin/finetune/base/{checkpoint-23266 → checkpoint-23890}/training_args.bin
RENAMED
|
File without changes
|
model-bin/finetune/base/log/1629594380.404467/events.out.tfevents.1629594380.91f414e9573a.903.11
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:de89ce13f179d7a9ddb4b7e7256977ab5d644f2dd81027f16ec1b5b890cd322a
|
| 3 |
+
size 4194
|
model-bin/finetune/base/log/1629595044.6201167/events.out.tfevents.1629595044.91f414e9573a.903.13
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:643026b904e24d36b797293c98d20505865bda7a1a59a7610ff5786e3e4a7384
|
| 3 |
+
size 4194
|
model-bin/finetune/base/log/1629595706.141513/events.out.tfevents.1629595706.91f414e9573a.903.15
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:549ea490c09ca91bb0fde16cfd6b627e2fc23db262c463526fb7e1c3d0002dca
|
| 3 |
+
size 4194
|
model-bin/finetune/base/log/1629596366.4482682/events.out.tfevents.1629596366.91f414e9573a.903.17
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bde349df8015f68410c92f7ccd3b219e44ad6054dcd0be3fbbb836317bda7b2f
|
| 3 |
+
size 4194
|
model-bin/finetune/base/log/1629597034.2743096/events.out.tfevents.1629597034.91f414e9573a.903.19
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:25e408e89c2e57907e023ed0703847c9f132cbe13adf7a6dfca27fc4b3d34609
|
| 3 |
+
size 4194
|
model-bin/finetune/base/log/events.out.tfevents.1629594380.91f414e9573a.903.10
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:af305ab147cd6d8001e953a60b625e94acd31b2ca3bb245c010611a42d66f43a
|
| 3 |
+
size 6703
|
model-bin/finetune/base/log/events.out.tfevents.1629595044.91f414e9573a.903.12
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:09c443e3a5a4632c8c25da14170a69e3a97183496c32d19f82b81d529c5f4e10
|
| 3 |
+
size 6543
|
model-bin/finetune/base/log/events.out.tfevents.1629595706.91f414e9573a.903.14
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0282a3ebd9a63e6e22d65509a041f587c4dcf53eaba8b928264a5dd1abae671f
|
| 3 |
+
size 6703
|
model-bin/finetune/base/log/events.out.tfevents.1629596366.91f414e9573a.903.16
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:13ea71bcfa633e9e936eeee16e495baabfd08d1c1538cb42db716e5fafab8324
|
| 3 |
+
size 6543
|
model-bin/finetune/base/log/events.out.tfevents.1629597034.91f414e9573a.903.18
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:61260ece09aca2402a8609e234c013524b94cc4161cd77a09de3f47e811b1edf
|
| 3 |
+
size 6703
|