"auto-commit"
Browse files- model-bin/finetune/base/{checkpoint-27620 → checkpoint-28240}/config.json +0 -0
- model-bin/finetune/base/{checkpoint-27620 → checkpoint-28240}/optimizer.pt +1 -1
- model-bin/finetune/base/{checkpoint-27620 → checkpoint-28240}/preprocessor_config.json +0 -0
- model-bin/finetune/base/{checkpoint-27620 → checkpoint-28240}/pytorch_model.bin +1 -1
- model-bin/finetune/base/{checkpoint-27620 → checkpoint-28240}/rng_state.pth +1 -1
- model-bin/finetune/base/{checkpoint-27620 → checkpoint-28240}/scaler.pt +1 -1
- model-bin/finetune/base/{checkpoint-27620 → checkpoint-28240}/scheduler.pt +1 -1
- model-bin/finetune/base/{checkpoint-27620 → checkpoint-28240}/trainer_state.json +420 -3
- model-bin/finetune/base/{checkpoint-27620 → checkpoint-28240}/training_args.bin +0 -0
- model-bin/finetune/base/log/1629618133.3065822/events.out.tfevents.1629618133.91f414e9573a.903.81 +3 -0
- model-bin/finetune/base/log/1629618796.0461793/events.out.tfevents.1629618796.91f414e9573a.903.83 +3 -0
- model-bin/finetune/base/log/1629619449.2236981/events.out.tfevents.1629619449.91f414e9573a.903.85 +3 -0
- model-bin/finetune/base/log/1629620107.8568785/events.out.tfevents.1629620107.91f414e9573a.903.87 +3 -0
- model-bin/finetune/base/log/1629620762.8681884/events.out.tfevents.1629620762.91f414e9573a.903.89 +3 -0
- model-bin/finetune/base/log/events.out.tfevents.1629618133.91f414e9573a.903.80 +3 -0
- model-bin/finetune/base/log/events.out.tfevents.1629618796.91f414e9573a.903.82 +3 -0
- model-bin/finetune/base/log/events.out.tfevents.1629619449.91f414e9573a.903.84 +3 -0
- model-bin/finetune/base/log/events.out.tfevents.1629620107.91f414e9573a.903.86 +3 -0
- model-bin/finetune/base/log/events.out.tfevents.1629620762.91f414e9573a.903.88 +3 -0
model-bin/finetune/base/{checkpoint-27620 → checkpoint-28240}/config.json
RENAMED
|
File without changes
|
model-bin/finetune/base/{checkpoint-27620 → checkpoint-28240}/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 sha256:23f205af0c85a79486671d7c2a46c01ad1c7ebc6c5a16791bf64853c549761a3
|
| 3 |
size 722165009
|
model-bin/finetune/base/{checkpoint-27620 → checkpoint-28240}/preprocessor_config.json
RENAMED
|
File without changes
|
model-bin/finetune/base/{checkpoint-27620 → checkpoint-28240}/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:c7274b2ad653556bac7a5326097f63ea934d37a657539721834f325d4411cb65
|
| 3 |
size 377909911
|
model-bin/finetune/base/{checkpoint-27620 → checkpoint-28240}/rng_state.pth
RENAMED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14503
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1f15081e891ea3f60ad40eb059ef2508f92dd6c3c2ee7847672edf1b10a39f2c
|
| 3 |
size 14503
|
model-bin/finetune/base/{checkpoint-27620 → checkpoint-28240}/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 sha256:2eb41d2fcb75c4cc78032c67119816584c6a8663c3a914dea3564e262841e64f
|
| 3 |
size 559
|
model-bin/finetune/base/{checkpoint-27620 → checkpoint-28240}/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 sha256:85fcca6898af77ab8a07c443dc170899439b330f6994ffe1a7c0eee0c29e7859
|
| 3 |
size 623
|
model-bin/finetune/base/{checkpoint-27620 → checkpoint-28240}/trainer_state.json
RENAMED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": 0.2158154859967051,
|
| 3 |
"best_model_checkpoint": "./model-bin/finetune/base/checkpoint-25631",
|
| 4 |
-
"epoch":
|
| 5 |
-
"global_step":
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
@@ -140856,11 +140856,428 @@
|
|
| 140856 |
"eval_steps_per_second": 0.66,
|
| 140857 |
"eval_wer": 0.22432529686937747,
|
| 140858 |
"step": 27620
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 140859 |
}
|
| 140860 |
],
|
| 140861 |
"max_steps": 620000,
|
| 140862 |
"num_train_epochs": 5000,
|
| 140863 |
-
"total_flos": 7.
|
| 140864 |
"trial_name": null,
|
| 140865 |
"trial_params": null
|
| 140866 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": 0.2158154859967051,
|
| 3 |
"best_model_checkpoint": "./model-bin/finetune/base/checkpoint-25631",
|
| 4 |
+
"epoch": 226.99598393574297,
|
| 5 |
+
"global_step": 28240,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
|
|
| 140856 |
"eval_steps_per_second": 0.66,
|
| 140857 |
"eval_wer": 0.22432529686937747,
|
| 140858 |
"step": 27620
|
| 140859 |
+
},
|
| 140860 |
+
{
|
| 140861 |
+
"epoch": 222.08,
|
| 140862 |
+
"learning_rate": 9.569951534733442e-06,
|
| 140863 |
+
"loss": 0.3857,
|
| 140864 |
+
"step": 27630
|
| 140865 |
+
},
|
| 140866 |
+
{
|
| 140867 |
+
"epoch": 222.16,
|
| 140868 |
+
"learning_rate": 9.569789983844912e-06,
|
| 140869 |
+
"loss": 0.492,
|
| 140870 |
+
"step": 27640
|
| 140871 |
+
},
|
| 140872 |
+
{
|
| 140873 |
+
"epoch": 222.24,
|
| 140874 |
+
"learning_rate": 9.569628432956382e-06,
|
| 140875 |
+
"loss": 0.9099,
|
| 140876 |
+
"step": 27650
|
| 140877 |
+
},
|
| 140878 |
+
{
|
| 140879 |
+
"epoch": 222.32,
|
| 140880 |
+
"learning_rate": 9.569466882067852e-06,
|
| 140881 |
+
"loss": 0.4436,
|
| 140882 |
+
"step": 27660
|
| 140883 |
+
},
|
| 140884 |
+
{
|
| 140885 |
+
"epoch": 222.4,
|
| 140886 |
+
"learning_rate": 9.569305331179322e-06,
|
| 140887 |
+
"loss": 1.0201,
|
| 140888 |
+
"step": 27670
|
| 140889 |
+
},
|
| 140890 |
+
{
|
| 140891 |
+
"epoch": 222.48,
|
| 140892 |
+
"learning_rate": 9.569143780290792e-06,
|
| 140893 |
+
"loss": 0.3894,
|
| 140894 |
+
"step": 27680
|
| 140895 |
+
},
|
| 140896 |
+
{
|
| 140897 |
+
"epoch": 222.56,
|
| 140898 |
+
"learning_rate": 9.568982229402264e-06,
|
| 140899 |
+
"loss": 0.5294,
|
| 140900 |
+
"step": 27690
|
| 140901 |
+
},
|
| 140902 |
+
{
|
| 140903 |
+
"epoch": 222.64,
|
| 140904 |
+
"learning_rate": 9.568820678513734e-06,
|
| 140905 |
+
"loss": 0.9159,
|
| 140906 |
+
"step": 27700
|
| 140907 |
+
},
|
| 140908 |
+
{
|
| 140909 |
+
"epoch": 222.72,
|
| 140910 |
+
"learning_rate": 9.568659127625204e-06,
|
| 140911 |
+
"loss": 0.6417,
|
| 140912 |
+
"step": 27710
|
| 140913 |
+
},
|
| 140914 |
+
{
|
| 140915 |
+
"epoch": 222.8,
|
| 140916 |
+
"learning_rate": 9.568497576736674e-06,
|
| 140917 |
+
"loss": 0.933,
|
| 140918 |
+
"step": 27720
|
| 140919 |
+
},
|
| 140920 |
+
{
|
| 140921 |
+
"epoch": 222.88,
|
| 140922 |
+
"learning_rate": 9.568336025848143e-06,
|
| 140923 |
+
"loss": 0.4265,
|
| 140924 |
+
"step": 27730
|
| 140925 |
+
},
|
| 140926 |
+
{
|
| 140927 |
+
"epoch": 222.96,
|
| 140928 |
+
"learning_rate": 9.568174474959613e-06,
|
| 140929 |
+
"loss": 0.5025,
|
| 140930 |
+
"step": 27740
|
| 140931 |
+
},
|
| 140932 |
+
{
|
| 140933 |
+
"epoch": 223.0,
|
| 140934 |
+
"eval_loss": 0.48019468784332275,
|
| 140935 |
+
"eval_runtime": 41.3313,
|
| 140936 |
+
"eval_samples_per_second": 20.324,
|
| 140937 |
+
"eval_steps_per_second": 0.653,
|
| 140938 |
+
"eval_wer": 0.22058281077093322,
|
| 140939 |
+
"step": 27744
|
| 140940 |
+
},
|
| 140941 |
+
{
|
| 140942 |
+
"epoch": 223.05,
|
| 140943 |
+
"learning_rate": 9.568012924071083e-06,
|
| 140944 |
+
"loss": 0.402,
|
| 140945 |
+
"step": 27750
|
| 140946 |
+
},
|
| 140947 |
+
{
|
| 140948 |
+
"epoch": 223.13,
|
| 140949 |
+
"learning_rate": 9.567851373182553e-06,
|
| 140950 |
+
"loss": 0.4301,
|
| 140951 |
+
"step": 27760
|
| 140952 |
+
},
|
| 140953 |
+
{
|
| 140954 |
+
"epoch": 223.21,
|
| 140955 |
+
"learning_rate": 9.567689822294023e-06,
|
| 140956 |
+
"loss": 1.0105,
|
| 140957 |
+
"step": 27770
|
| 140958 |
+
},
|
| 140959 |
+
{
|
| 140960 |
+
"epoch": 223.29,
|
| 140961 |
+
"learning_rate": 9.567528271405493e-06,
|
| 140962 |
+
"loss": 0.3728,
|
| 140963 |
+
"step": 27780
|
| 140964 |
+
},
|
| 140965 |
+
{
|
| 140966 |
+
"epoch": 223.37,
|
| 140967 |
+
"learning_rate": 9.567366720516963e-06,
|
| 140968 |
+
"loss": 0.6167,
|
| 140969 |
+
"step": 27790
|
| 140970 |
+
},
|
| 140971 |
+
{
|
| 140972 |
+
"epoch": 223.45,
|
| 140973 |
+
"learning_rate": 9.567205169628433e-06,
|
| 140974 |
+
"loss": 0.8874,
|
| 140975 |
+
"step": 27800
|
| 140976 |
+
},
|
| 140977 |
+
{
|
| 140978 |
+
"epoch": 223.53,
|
| 140979 |
+
"learning_rate": 9.567043618739903e-06,
|
| 140980 |
+
"loss": 0.5227,
|
| 140981 |
+
"step": 27810
|
| 140982 |
+
},
|
| 140983 |
+
{
|
| 140984 |
+
"epoch": 223.61,
|
| 140985 |
+
"learning_rate": 9.566882067851373e-06,
|
| 140986 |
+
"loss": 0.9741,
|
| 140987 |
+
"step": 27820
|
| 140988 |
+
},
|
| 140989 |
+
{
|
| 140990 |
+
"epoch": 223.69,
|
| 140991 |
+
"learning_rate": 9.566720516962845e-06,
|
| 140992 |
+
"loss": 0.4572,
|
| 140993 |
+
"step": 27830
|
| 140994 |
+
},
|
| 140995 |
+
{
|
| 140996 |
+
"epoch": 223.77,
|
| 140997 |
+
"learning_rate": 9.566558966074315e-06,
|
| 140998 |
+
"loss": 0.5684,
|
| 140999 |
+
"step": 27840
|
| 141000 |
+
},
|
| 141001 |
+
{
|
| 141002 |
+
"epoch": 223.85,
|
| 141003 |
+
"learning_rate": 9.566397415185785e-06,
|
| 141004 |
+
"loss": 0.9094,
|
| 141005 |
+
"step": 27850
|
| 141006 |
+
},
|
| 141007 |
+
{
|
| 141008 |
+
"epoch": 223.93,
|
| 141009 |
+
"learning_rate": 9.566235864297255e-06,
|
| 141010 |
+
"loss": 0.456,
|
| 141011 |
+
"step": 27860
|
| 141012 |
+
},
|
| 141013 |
+
{
|
| 141014 |
+
"epoch": 224.0,
|
| 141015 |
+
"eval_loss": 0.5359866619110107,
|
| 141016 |
+
"eval_runtime": 41.052,
|
| 141017 |
+
"eval_samples_per_second": 20.462,
|
| 141018 |
+
"eval_steps_per_second": 0.658,
|
| 141019 |
+
"eval_wer": 0.23175047928034212,
|
| 141020 |
+
"step": 27868
|
| 141021 |
+
},
|
| 141022 |
+
{
|
| 141023 |
+
"epoch": 224.02,
|
| 141024 |
+
"learning_rate": 9.566074313408725e-06,
|
| 141025 |
+
"loss": 0.5022,
|
| 141026 |
+
"step": 27870
|
| 141027 |
+
},
|
| 141028 |
+
{
|
| 141029 |
+
"epoch": 224.1,
|
| 141030 |
+
"learning_rate": 9.565912762520195e-06,
|
| 141031 |
+
"loss": 0.4177,
|
| 141032 |
+
"step": 27880
|
| 141033 |
+
},
|
| 141034 |
+
{
|
| 141035 |
+
"epoch": 224.18,
|
| 141036 |
+
"learning_rate": 9.565751211631665e-06,
|
| 141037 |
+
"loss": 0.6748,
|
| 141038 |
+
"step": 27890
|
| 141039 |
+
},
|
| 141040 |
+
{
|
| 141041 |
+
"epoch": 224.26,
|
| 141042 |
+
"learning_rate": 9.565589660743135e-06,
|
| 141043 |
+
"loss": 0.8692,
|
| 141044 |
+
"step": 27900
|
| 141045 |
+
},
|
| 141046 |
+
{
|
| 141047 |
+
"epoch": 224.34,
|
| 141048 |
+
"learning_rate": 9.565428109854605e-06,
|
| 141049 |
+
"loss": 0.4144,
|
| 141050 |
+
"step": 27910
|
| 141051 |
+
},
|
| 141052 |
+
{
|
| 141053 |
+
"epoch": 224.42,
|
| 141054 |
+
"learning_rate": 9.565266558966075e-06,
|
| 141055 |
+
"loss": 1.0509,
|
| 141056 |
+
"step": 27920
|
| 141057 |
+
},
|
| 141058 |
+
{
|
| 141059 |
+
"epoch": 224.5,
|
| 141060 |
+
"learning_rate": 9.565105008077545e-06,
|
| 141061 |
+
"loss": 0.3883,
|
| 141062 |
+
"step": 27930
|
| 141063 |
+
},
|
| 141064 |
+
{
|
| 141065 |
+
"epoch": 224.58,
|
| 141066 |
+
"learning_rate": 9.564943457189015e-06,
|
| 141067 |
+
"loss": 0.6538,
|
| 141068 |
+
"step": 27940
|
| 141069 |
+
},
|
| 141070 |
+
{
|
| 141071 |
+
"epoch": 224.66,
|
| 141072 |
+
"learning_rate": 9.564781906300485e-06,
|
| 141073 |
+
"loss": 0.7542,
|
| 141074 |
+
"step": 27950
|
| 141075 |
+
},
|
| 141076 |
+
{
|
| 141077 |
+
"epoch": 224.74,
|
| 141078 |
+
"learning_rate": 9.564620355411955e-06,
|
| 141079 |
+
"loss": 0.4809,
|
| 141080 |
+
"step": 27960
|
| 141081 |
+
},
|
| 141082 |
+
{
|
| 141083 |
+
"epoch": 224.82,
|
| 141084 |
+
"learning_rate": 9.564458804523426e-06,
|
| 141085 |
+
"loss": 1.0094,
|
| 141086 |
+
"step": 27970
|
| 141087 |
+
},
|
| 141088 |
+
{
|
| 141089 |
+
"epoch": 224.9,
|
| 141090 |
+
"learning_rate": 9.564297253634896e-06,
|
| 141091 |
+
"loss": 0.4012,
|
| 141092 |
+
"step": 27980
|
| 141093 |
+
},
|
| 141094 |
+
{
|
| 141095 |
+
"epoch": 224.98,
|
| 141096 |
+
"learning_rate": 9.564135702746366e-06,
|
| 141097 |
+
"loss": 0.6751,
|
| 141098 |
+
"step": 27990
|
| 141099 |
+
},
|
| 141100 |
+
{
|
| 141101 |
+
"epoch": 225.0,
|
| 141102 |
+
"eval_loss": 0.47236883640289307,
|
| 141103 |
+
"eval_runtime": 40.7547,
|
| 141104 |
+
"eval_samples_per_second": 20.611,
|
| 141105 |
+
"eval_steps_per_second": 0.663,
|
| 141106 |
+
"eval_wer": 0.22793042969891844,
|
| 141107 |
+
"step": 27992
|
| 141108 |
+
},
|
| 141109 |
+
{
|
| 141110 |
+
"epoch": 225.06,
|
| 141111 |
+
"learning_rate": 9.563974151857836e-06,
|
| 141112 |
+
"loss": 0.4728,
|
| 141113 |
+
"step": 28000
|
| 141114 |
+
},
|
| 141115 |
+
{
|
| 141116 |
+
"epoch": 225.15,
|
| 141117 |
+
"learning_rate": 9.563812600969306e-06,
|
| 141118 |
+
"loss": 0.4188,
|
| 141119 |
+
"step": 28010
|
| 141120 |
+
},
|
| 141121 |
+
{
|
| 141122 |
+
"epoch": 225.23,
|
| 141123 |
+
"learning_rate": 9.563651050080776e-06,
|
| 141124 |
+
"loss": 1.0539,
|
| 141125 |
+
"step": 28020
|
| 141126 |
+
},
|
| 141127 |
+
{
|
| 141128 |
+
"epoch": 225.31,
|
| 141129 |
+
"learning_rate": 9.563489499192246e-06,
|
| 141130 |
+
"loss": 0.4914,
|
| 141131 |
+
"step": 28030
|
| 141132 |
+
},
|
| 141133 |
+
{
|
| 141134 |
+
"epoch": 225.39,
|
| 141135 |
+
"learning_rate": 9.563327948303716e-06,
|
| 141136 |
+
"loss": 0.6993,
|
| 141137 |
+
"step": 28040
|
| 141138 |
+
},
|
| 141139 |
+
{
|
| 141140 |
+
"epoch": 225.47,
|
| 141141 |
+
"learning_rate": 9.563166397415186e-06,
|
| 141142 |
+
"loss": 0.7079,
|
| 141143 |
+
"step": 28050
|
| 141144 |
+
},
|
| 141145 |
+
{
|
| 141146 |
+
"epoch": 225.55,
|
| 141147 |
+
"learning_rate": 9.563004846526656e-06,
|
| 141148 |
+
"loss": 0.5766,
|
| 141149 |
+
"step": 28060
|
| 141150 |
+
},
|
| 141151 |
+
{
|
| 141152 |
+
"epoch": 225.63,
|
| 141153 |
+
"learning_rate": 9.562843295638126e-06,
|
| 141154 |
+
"loss": 0.9263,
|
| 141155 |
+
"step": 28070
|
| 141156 |
+
},
|
| 141157 |
+
{
|
| 141158 |
+
"epoch": 225.71,
|
| 141159 |
+
"learning_rate": 9.562681744749596e-06,
|
| 141160 |
+
"loss": 0.4226,
|
| 141161 |
+
"step": 28080
|
| 141162 |
+
},
|
| 141163 |
+
{
|
| 141164 |
+
"epoch": 225.79,
|
| 141165 |
+
"learning_rate": 9.562520193861066e-06,
|
| 141166 |
+
"loss": 0.6607,
|
| 141167 |
+
"step": 28090
|
| 141168 |
+
},
|
| 141169 |
+
{
|
| 141170 |
+
"epoch": 225.87,
|
| 141171 |
+
"learning_rate": 9.562358642972538e-06,
|
| 141172 |
+
"loss": 0.7028,
|
| 141173 |
+
"step": 28100
|
| 141174 |
+
},
|
| 141175 |
+
{
|
| 141176 |
+
"epoch": 225.95,
|
| 141177 |
+
"learning_rate": 9.562197092084008e-06,
|
| 141178 |
+
"loss": 0.5085,
|
| 141179 |
+
"step": 28110
|
| 141180 |
+
},
|
| 141181 |
+
{
|
| 141182 |
+
"epoch": 226.0,
|
| 141183 |
+
"eval_loss": 0.5034955739974976,
|
| 141184 |
+
"eval_runtime": 40.3248,
|
| 141185 |
+
"eval_samples_per_second": 20.856,
|
| 141186 |
+
"eval_steps_per_second": 0.67,
|
| 141187 |
+
"eval_wer": 0.22137010544945063,
|
| 141188 |
+
"step": 28116
|
| 141189 |
+
},
|
| 141190 |
+
{
|
| 141191 |
+
"epoch": 226.03,
|
| 141192 |
+
"learning_rate": 9.562035541195478e-06,
|
| 141193 |
+
"loss": 0.3976,
|
| 141194 |
+
"step": 28120
|
| 141195 |
+
},
|
| 141196 |
+
{
|
| 141197 |
+
"epoch": 226.11,
|
| 141198 |
+
"learning_rate": 9.561873990306948e-06,
|
| 141199 |
+
"loss": 0.4276,
|
| 141200 |
+
"step": 28130
|
| 141201 |
+
},
|
| 141202 |
+
{
|
| 141203 |
+
"epoch": 226.19,
|
| 141204 |
+
"learning_rate": 9.561712439418418e-06,
|
| 141205 |
+
"loss": 0.8649,
|
| 141206 |
+
"step": 28140
|
| 141207 |
+
},
|
| 141208 |
+
{
|
| 141209 |
+
"epoch": 226.27,
|
| 141210 |
+
"learning_rate": 9.561550888529888e-06,
|
| 141211 |
+
"loss": 0.704,
|
| 141212 |
+
"step": 28150
|
| 141213 |
+
},
|
| 141214 |
+
{
|
| 141215 |
+
"epoch": 226.35,
|
| 141216 |
+
"learning_rate": 9.561389337641357e-06,
|
| 141217 |
+
"loss": 0.4863,
|
| 141218 |
+
"step": 28160
|
| 141219 |
+
},
|
| 141220 |
+
{
|
| 141221 |
+
"epoch": 226.43,
|
| 141222 |
+
"learning_rate": 9.561227786752827e-06,
|
| 141223 |
+
"loss": 0.9448,
|
| 141224 |
+
"step": 28170
|
| 141225 |
+
},
|
| 141226 |
+
{
|
| 141227 |
+
"epoch": 226.51,
|
| 141228 |
+
"learning_rate": 9.561066235864297e-06,
|
| 141229 |
+
"loss": 0.4127,
|
| 141230 |
+
"step": 28180
|
| 141231 |
+
},
|
| 141232 |
+
{
|
| 141233 |
+
"epoch": 226.59,
|
| 141234 |
+
"learning_rate": 9.560904684975767e-06,
|
| 141235 |
+
"loss": 0.8289,
|
| 141236 |
+
"step": 28190
|
| 141237 |
+
},
|
| 141238 |
+
{
|
| 141239 |
+
"epoch": 226.67,
|
| 141240 |
+
"learning_rate": 9.560743134087237e-06,
|
| 141241 |
+
"loss": 0.7084,
|
| 141242 |
+
"step": 28200
|
| 141243 |
+
},
|
| 141244 |
+
{
|
| 141245 |
+
"epoch": 226.76,
|
| 141246 |
+
"learning_rate": 9.560581583198707e-06,
|
| 141247 |
+
"loss": 0.4398,
|
| 141248 |
+
"step": 28210
|
| 141249 |
+
},
|
| 141250 |
+
{
|
| 141251 |
+
"epoch": 226.84,
|
| 141252 |
+
"learning_rate": 9.560420032310177e-06,
|
| 141253 |
+
"loss": 1.0172,
|
| 141254 |
+
"step": 28220
|
| 141255 |
+
},
|
| 141256 |
+
{
|
| 141257 |
+
"epoch": 226.92,
|
| 141258 |
+
"learning_rate": 9.560258481421647e-06,
|
| 141259 |
+
"loss": 0.3978,
|
| 141260 |
+
"step": 28230
|
| 141261 |
+
},
|
| 141262 |
+
{
|
| 141263 |
+
"epoch": 227.0,
|
| 141264 |
+
"learning_rate": 9.560096930533119e-06,
|
| 141265 |
+
"loss": 0.9928,
|
| 141266 |
+
"step": 28240
|
| 141267 |
+
},
|
| 141268 |
+
{
|
| 141269 |
+
"epoch": 227.0,
|
| 141270 |
+
"eval_loss": 0.529734194278717,
|
| 141271 |
+
"eval_runtime": 40.5351,
|
| 141272 |
+
"eval_samples_per_second": 20.747,
|
| 141273 |
+
"eval_steps_per_second": 0.666,
|
| 141274 |
+
"eval_wer": 0.2228188906870678,
|
| 141275 |
+
"step": 28240
|
| 141276 |
}
|
| 141277 |
],
|
| 141278 |
"max_steps": 620000,
|
| 141279 |
"num_train_epochs": 5000,
|
| 141280 |
+
"total_flos": 7.946287777944314e+19,
|
| 141281 |
"trial_name": null,
|
| 141282 |
"trial_params": null
|
| 141283 |
}
|
model-bin/finetune/base/{checkpoint-27620 → checkpoint-28240}/training_args.bin
RENAMED
|
File without changes
|
model-bin/finetune/base/log/1629618133.3065822/events.out.tfevents.1629618133.91f414e9573a.903.81
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:762dfae89a03b197661d04ddfb2846b924e95ad24055f4f9395b9312f44321dd
|
| 3 |
+
size 4194
|
model-bin/finetune/base/log/1629618796.0461793/events.out.tfevents.1629618796.91f414e9573a.903.83
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:49b31b4359c95979bffe15dba90f110b4f94f0475c9994e1148fa846d16bd5fe
|
| 3 |
+
size 4194
|
model-bin/finetune/base/log/1629619449.2236981/events.out.tfevents.1629619449.91f414e9573a.903.85
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d75265816ccdaebec8d304620181107cab77c56d8e221e05df843999d62380bd
|
| 3 |
+
size 4194
|
model-bin/finetune/base/log/1629620107.8568785/events.out.tfevents.1629620107.91f414e9573a.903.87
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7798c1e772f8d029b448515261f82ec202106d2a955e07f21fae7f1849bccd8e
|
| 3 |
+
size 4194
|
model-bin/finetune/base/log/1629620762.8681884/events.out.tfevents.1629620762.91f414e9573a.903.89
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d1c12d35c9aa9ffaf906b49d385c85feec520ea0db88dc146b221a649925c71d
|
| 3 |
+
size 4194
|
model-bin/finetune/base/log/events.out.tfevents.1629618133.91f414e9573a.903.80
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a226d3be78e35166d025745692ca7237f98a79eeccb49b37555b7a99ce9d890b
|
| 3 |
+
size 6543
|
model-bin/finetune/base/log/events.out.tfevents.1629618796.91f414e9573a.903.82
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fd0ea28ccc11f10daa08aa351660fe9cbfe331df15318f2edf1d0b17da4282ad
|
| 3 |
+
size 6543
|
model-bin/finetune/base/log/events.out.tfevents.1629619449.91f414e9573a.903.84
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:97713ffcb1df4433842b142aa2dbbf7f174de5f6e82b803ea8715bb0ac32cae8
|
| 3 |
+
size 6703
|
model-bin/finetune/base/log/events.out.tfevents.1629620107.91f414e9573a.903.86
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9359044a2ed43ccff4cfe70aa92088842f004e7002ce3bff7386c4abb6955ce8
|
| 3 |
+
size 6543
|
model-bin/finetune/base/log/events.out.tfevents.1629620762.91f414e9573a.903.88
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ae421e31c0f45e24b2c9c8e949924f6c5c772f2aef6e571b673ffd85b23994d6
|
| 3 |
+
size 6703
|