"auto-commit"
Browse files- model-bin/finetune/base/{checkpoint-30356 → checkpoint-31228}/config.json +0 -0
- model-bin/finetune/base/{checkpoint-30356 → checkpoint-31228}/optimizer.pt +1 -1
- model-bin/finetune/base/{checkpoint-30356 → checkpoint-31228}/preprocessor_config.json +0 -0
- model-bin/finetune/base/{checkpoint-30729 → checkpoint-31228}/pytorch_model.bin +1 -1
- model-bin/finetune/base/{checkpoint-30729 → checkpoint-31228}/rng_state.pth +1 -1
- model-bin/finetune/base/{checkpoint-30729 → checkpoint-31228}/scaler.pt +1 -1
- model-bin/finetune/base/{checkpoint-30356 → checkpoint-31228}/scheduler.pt +1 -1
- model-bin/finetune/base/{checkpoint-30729 → checkpoint-31228}/trainer_state.json +340 -4
- model-bin/finetune/base/{checkpoint-30356 → checkpoint-31228}/training_args.bin +0 -0
- model-bin/finetune/base/{checkpoint-30729 → checkpoint-31352}/config.json +0 -0
- model-bin/finetune/base/{checkpoint-30729 → checkpoint-31352}/optimizer.pt +1 -1
- model-bin/finetune/base/{checkpoint-30729 → checkpoint-31352}/preprocessor_config.json +0 -0
- model-bin/finetune/base/{checkpoint-30356 → checkpoint-31352}/pytorch_model.bin +1 -1
- model-bin/finetune/base/{checkpoint-30356 → checkpoint-31352}/rng_state.pth +1 -1
- model-bin/finetune/base/{checkpoint-30356 → checkpoint-31352}/scaler.pt +1 -1
- model-bin/finetune/base/{checkpoint-30729 → checkpoint-31352}/scheduler.pt +1 -1
- model-bin/finetune/base/{checkpoint-30356 → checkpoint-31352}/trainer_state.json +678 -6
- model-bin/finetune/base/{checkpoint-30729 → checkpoint-31352}/training_args.bin +0 -0
- model-bin/finetune/base/log/1629634923.047115/events.out.tfevents.1629634923.91f414e9573a.903.131 +3 -0
- model-bin/finetune/base/log/1629635595.6999147/events.out.tfevents.1629635595.91f414e9573a.903.133 +3 -0
- model-bin/finetune/base/log/1629636245.2886124/events.out.tfevents.1629636245.91f414e9573a.903.135 +3 -0
- model-bin/finetune/base/log/1629636904.1195304/events.out.tfevents.1629636904.91f414e9573a.903.137 +3 -0
- model-bin/finetune/base/log/1629637560.6401086/events.out.tfevents.1629637560.91f414e9573a.903.139 +3 -0
- model-bin/finetune/base/log/events.out.tfevents.1629634923.91f414e9573a.903.130 +3 -0
- model-bin/finetune/base/log/events.out.tfevents.1629635595.91f414e9573a.903.132 +3 -0
- model-bin/finetune/base/log/events.out.tfevents.1629636245.91f414e9573a.903.134 +3 -0
- model-bin/finetune/base/log/events.out.tfevents.1629636904.91f414e9573a.903.136 +3 -0
- model-bin/finetune/base/log/events.out.tfevents.1629637560.91f414e9573a.903.138 +3 -0
model-bin/finetune/base/{checkpoint-30356 → checkpoint-31228}/config.json
RENAMED
|
File without changes
|
model-bin/finetune/base/{checkpoint-30356 → checkpoint-31228}/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 sha256:7d0982a2ba7bca16a75e802f8ba69bb240a79dfd8e82382fd7bdf32399221094
|
| 3 |
size 722165009
|
model-bin/finetune/base/{checkpoint-30356 → checkpoint-31228}/preprocessor_config.json
RENAMED
|
File without changes
|
model-bin/finetune/base/{checkpoint-30729 → checkpoint-31228}/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 sha256:3105e926ecf3aa529c00dcda74bfbe4efdb358da1fc0a09b5b7eb2316ac0df76
|
| 3 |
size 377909911
|
model-bin/finetune/base/{checkpoint-30729 → checkpoint-31228}/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 sha256:15fdb4765d4574f83054e847d4ca5f259da39c89c2c1b2e11dc34c0b2588ad3f
|
| 3 |
size 14503
|
model-bin/finetune/base/{checkpoint-30729 → checkpoint-31228}/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 sha256:18dc14d92ea307c10d2b1a653f8b317e82919bd98bf258c6d52b555dde004551
|
| 3 |
size 559
|
model-bin/finetune/base/{checkpoint-30356 → checkpoint-31228}/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:f003797122843def81c84db1eac41ec7a5af3f7903b822ae76d3d182f2ef323c
|
| 3 |
size 623
|
model-bin/finetune/base/{checkpoint-30729 → checkpoint-31228}/trainer_state.json
RENAMED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": 0.20691915513474143,
|
| 3 |
"best_model_checkpoint": "./model-bin/finetune/base/checkpoint-30356",
|
| 4 |
-
"epoch":
|
| 5 |
-
"global_step":
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
@@ -142941,11 +142941,347 @@
|
|
| 142941 |
"eval_steps_per_second": 0.642,
|
| 142942 |
"eval_wer": 0.2156060495360561,
|
| 142943 |
"step": 30729
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 142944 |
}
|
| 142945 |
],
|
| 142946 |
-
"max_steps":
|
| 142947 |
"num_train_epochs": 5000,
|
| 142948 |
-
"total_flos": 8.
|
| 142949 |
"trial_name": null,
|
| 142950 |
"trial_params": null
|
| 142951 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": 0.20691915513474143,
|
| 3 |
"best_model_checkpoint": "./model-bin/finetune/base/checkpoint-30356",
|
| 4 |
+
"epoch": 249.0,
|
| 5 |
+
"global_step": 31228,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
|
|
| 142941 |
"eval_steps_per_second": 0.642,
|
| 142942 |
"eval_wer": 0.2156060495360561,
|
| 142943 |
"step": 30729
|
| 142944 |
+
},
|
| 142945 |
+
{
|
| 142946 |
+
"epoch": 247.01,
|
| 142947 |
+
"learning_rate": 9.51988691437803e-06,
|
| 142948 |
+
"loss": 0.5436,
|
| 142949 |
+
"step": 30730
|
| 142950 |
+
},
|
| 142951 |
+
{
|
| 142952 |
+
"epoch": 247.09,
|
| 142953 |
+
"learning_rate": 9.5197253634895e-06,
|
| 142954 |
+
"loss": 0.3896,
|
| 142955 |
+
"step": 30740
|
| 142956 |
+
},
|
| 142957 |
+
{
|
| 142958 |
+
"epoch": 247.17,
|
| 142959 |
+
"learning_rate": 9.51956381260097e-06,
|
| 142960 |
+
"loss": 0.5227,
|
| 142961 |
+
"step": 30750
|
| 142962 |
+
},
|
| 142963 |
+
{
|
| 142964 |
+
"epoch": 247.25,
|
| 142965 |
+
"learning_rate": 9.51940226171244e-06,
|
| 142966 |
+
"loss": 0.779,
|
| 142967 |
+
"step": 30760
|
| 142968 |
+
},
|
| 142969 |
+
{
|
| 142970 |
+
"epoch": 247.33,
|
| 142971 |
+
"learning_rate": 9.51924071082391e-06,
|
| 142972 |
+
"loss": 0.4329,
|
| 142973 |
+
"step": 30770
|
| 142974 |
+
},
|
| 142975 |
+
{
|
| 142976 |
+
"epoch": 247.41,
|
| 142977 |
+
"learning_rate": 9.51907915993538e-06,
|
| 142978 |
+
"loss": 1.1671,
|
| 142979 |
+
"step": 30780
|
| 142980 |
+
},
|
| 142981 |
+
{
|
| 142982 |
+
"epoch": 247.49,
|
| 142983 |
+
"learning_rate": 9.51891760904685e-06,
|
| 142984 |
+
"loss": 0.4234,
|
| 142985 |
+
"step": 30790
|
| 142986 |
+
},
|
| 142987 |
+
{
|
| 142988 |
+
"epoch": 247.57,
|
| 142989 |
+
"learning_rate": 9.51875605815832e-06,
|
| 142990 |
+
"loss": 0.5782,
|
| 142991 |
+
"step": 30800
|
| 142992 |
+
},
|
| 142993 |
+
{
|
| 142994 |
+
"epoch": 247.65,
|
| 142995 |
+
"learning_rate": 9.518594507269791e-06,
|
| 142996 |
+
"loss": 0.83,
|
| 142997 |
+
"step": 30810
|
| 142998 |
+
},
|
| 142999 |
+
{
|
| 143000 |
+
"epoch": 247.73,
|
| 143001 |
+
"learning_rate": 9.518432956381261e-06,
|
| 143002 |
+
"loss": 0.4059,
|
| 143003 |
+
"step": 30820
|
| 143004 |
+
},
|
| 143005 |
+
{
|
| 143006 |
+
"epoch": 247.81,
|
| 143007 |
+
"learning_rate": 9.518271405492731e-06,
|
| 143008 |
+
"loss": 1.1213,
|
| 143009 |
+
"step": 30830
|
| 143010 |
+
},
|
| 143011 |
+
{
|
| 143012 |
+
"epoch": 247.89,
|
| 143013 |
+
"learning_rate": 9.518109854604201e-06,
|
| 143014 |
+
"loss": 0.4175,
|
| 143015 |
+
"step": 30840
|
| 143016 |
+
},
|
| 143017 |
+
{
|
| 143018 |
+
"epoch": 247.97,
|
| 143019 |
+
"learning_rate": 9.517948303715671e-06,
|
| 143020 |
+
"loss": 0.5727,
|
| 143021 |
+
"step": 30850
|
| 143022 |
+
},
|
| 143023 |
+
{
|
| 143024 |
+
"epoch": 248.0,
|
| 143025 |
+
"eval_loss": 0.4734344184398651,
|
| 143026 |
+
"eval_runtime": 41.7653,
|
| 143027 |
+
"eval_samples_per_second": 19.897,
|
| 143028 |
+
"eval_steps_per_second": 0.623,
|
| 143029 |
+
"eval_wer": 0.21280238183848157,
|
| 143030 |
+
"step": 30853
|
| 143031 |
+
},
|
| 143032 |
+
{
|
| 143033 |
+
"epoch": 246.06,
|
| 143034 |
+
"learning_rate": 9.517786752827141e-06,
|
| 143035 |
+
"loss": 0.3736,
|
| 143036 |
+
"step": 30860
|
| 143037 |
+
},
|
| 143038 |
+
{
|
| 143039 |
+
"epoch": 246.14,
|
| 143040 |
+
"learning_rate": 9.517625201938611e-06,
|
| 143041 |
+
"loss": 0.4175,
|
| 143042 |
+
"step": 30870
|
| 143043 |
+
},
|
| 143044 |
+
{
|
| 143045 |
+
"epoch": 246.22,
|
| 143046 |
+
"learning_rate": 9.517463651050081e-06,
|
| 143047 |
+
"loss": 0.9235,
|
| 143048 |
+
"step": 30880
|
| 143049 |
+
},
|
| 143050 |
+
{
|
| 143051 |
+
"epoch": 246.3,
|
| 143052 |
+
"learning_rate": 9.517302100161551e-06,
|
| 143053 |
+
"loss": 0.4543,
|
| 143054 |
+
"step": 30890
|
| 143055 |
+
},
|
| 143056 |
+
{
|
| 143057 |
+
"epoch": 246.38,
|
| 143058 |
+
"learning_rate": 9.517140549273021e-06,
|
| 143059 |
+
"loss": 0.6469,
|
| 143060 |
+
"step": 30900
|
| 143061 |
+
},
|
| 143062 |
+
{
|
| 143063 |
+
"epoch": 246.46,
|
| 143064 |
+
"learning_rate": 9.516978998384491e-06,
|
| 143065 |
+
"loss": 0.7732,
|
| 143066 |
+
"step": 30910
|
| 143067 |
+
},
|
| 143068 |
+
{
|
| 143069 |
+
"epoch": 246.54,
|
| 143070 |
+
"learning_rate": 9.516817447495961e-06,
|
| 143071 |
+
"loss": 0.4104,
|
| 143072 |
+
"step": 30920
|
| 143073 |
+
},
|
| 143074 |
+
{
|
| 143075 |
+
"epoch": 246.62,
|
| 143076 |
+
"learning_rate": 9.516655896607431e-06,
|
| 143077 |
+
"loss": 1.0242,
|
| 143078 |
+
"step": 30930
|
| 143079 |
+
},
|
| 143080 |
+
{
|
| 143081 |
+
"epoch": 246.7,
|
| 143082 |
+
"learning_rate": 9.516494345718903e-06,
|
| 143083 |
+
"loss": 0.4617,
|
| 143084 |
+
"step": 30940
|
| 143085 |
+
},
|
| 143086 |
+
{
|
| 143087 |
+
"epoch": 246.78,
|
| 143088 |
+
"learning_rate": 9.516332794830373e-06,
|
| 143089 |
+
"loss": 0.6495,
|
| 143090 |
+
"step": 30950
|
| 143091 |
+
},
|
| 143092 |
+
{
|
| 143093 |
+
"epoch": 246.86,
|
| 143094 |
+
"learning_rate": 9.516171243941843e-06,
|
| 143095 |
+
"loss": 0.7783,
|
| 143096 |
+
"step": 30960
|
| 143097 |
+
},
|
| 143098 |
+
{
|
| 143099 |
+
"epoch": 246.94,
|
| 143100 |
+
"learning_rate": 9.516009693053313e-06,
|
| 143101 |
+
"loss": 0.3745,
|
| 143102 |
+
"step": 30970
|
| 143103 |
+
},
|
| 143104 |
+
{
|
| 143105 |
+
"epoch": 247.0,
|
| 143106 |
+
"eval_loss": 0.4507042467594147,
|
| 143107 |
+
"eval_runtime": 39.3618,
|
| 143108 |
+
"eval_samples_per_second": 21.112,
|
| 143109 |
+
"eval_steps_per_second": 0.661,
|
| 143110 |
+
"eval_wer": 0.21471927162367224,
|
| 143111 |
+
"step": 30978
|
| 143112 |
+
},
|
| 143113 |
+
{
|
| 143114 |
+
"epoch": 247.02,
|
| 143115 |
+
"learning_rate": 9.515848142164783e-06,
|
| 143116 |
+
"loss": 0.4894,
|
| 143117 |
+
"step": 30980
|
| 143118 |
+
},
|
| 143119 |
+
{
|
| 143120 |
+
"epoch": 247.1,
|
| 143121 |
+
"learning_rate": 9.515686591276253e-06,
|
| 143122 |
+
"loss": 0.3954,
|
| 143123 |
+
"step": 30990
|
| 143124 |
+
},
|
| 143125 |
+
{
|
| 143126 |
+
"epoch": 247.18,
|
| 143127 |
+
"learning_rate": 9.515525040387723e-06,
|
| 143128 |
+
"loss": 0.6174,
|
| 143129 |
+
"step": 31000
|
| 143130 |
+
},
|
| 143131 |
+
{
|
| 143132 |
+
"epoch": 247.26,
|
| 143133 |
+
"learning_rate": 9.515363489499193e-06,
|
| 143134 |
+
"loss": 0.7535,
|
| 143135 |
+
"step": 31010
|
| 143136 |
+
},
|
| 143137 |
+
{
|
| 143138 |
+
"epoch": 247.34,
|
| 143139 |
+
"learning_rate": 9.515201938610662e-06,
|
| 143140 |
+
"loss": 0.4249,
|
| 143141 |
+
"step": 31020
|
| 143142 |
+
},
|
| 143143 |
+
{
|
| 143144 |
+
"epoch": 247.42,
|
| 143145 |
+
"learning_rate": 9.515040387722132e-06,
|
| 143146 |
+
"loss": 0.8701,
|
| 143147 |
+
"step": 31030
|
| 143148 |
+
},
|
| 143149 |
+
{
|
| 143150 |
+
"epoch": 247.5,
|
| 143151 |
+
"learning_rate": 9.514878836833602e-06,
|
| 143152 |
+
"loss": 0.4086,
|
| 143153 |
+
"step": 31040
|
| 143154 |
+
},
|
| 143155 |
+
{
|
| 143156 |
+
"epoch": 247.58,
|
| 143157 |
+
"learning_rate": 9.514717285945072e-06,
|
| 143158 |
+
"loss": 0.7135,
|
| 143159 |
+
"step": 31050
|
| 143160 |
+
},
|
| 143161 |
+
{
|
| 143162 |
+
"epoch": 247.66,
|
| 143163 |
+
"learning_rate": 9.514555735056542e-06,
|
| 143164 |
+
"loss": 0.8156,
|
| 143165 |
+
"step": 31060
|
| 143166 |
+
},
|
| 143167 |
+
{
|
| 143168 |
+
"epoch": 247.74,
|
| 143169 |
+
"learning_rate": 9.514394184168012e-06,
|
| 143170 |
+
"loss": 0.4138,
|
| 143171 |
+
"step": 31070
|
| 143172 |
+
},
|
| 143173 |
+
{
|
| 143174 |
+
"epoch": 247.82,
|
| 143175 |
+
"learning_rate": 9.514232633279484e-06,
|
| 143176 |
+
"loss": 1.0434,
|
| 143177 |
+
"step": 31080
|
| 143178 |
+
},
|
| 143179 |
+
{
|
| 143180 |
+
"epoch": 247.9,
|
| 143181 |
+
"learning_rate": 9.514071082390954e-06,
|
| 143182 |
+
"loss": 0.3624,
|
| 143183 |
+
"step": 31090
|
| 143184 |
+
},
|
| 143185 |
+
{
|
| 143186 |
+
"epoch": 247.98,
|
| 143187 |
+
"learning_rate": 9.513909531502424e-06,
|
| 143188 |
+
"loss": 0.6142,
|
| 143189 |
+
"step": 31100
|
| 143190 |
+
},
|
| 143191 |
+
{
|
| 143192 |
+
"epoch": 248.0,
|
| 143193 |
+
"eval_loss": 0.49309414625167847,
|
| 143194 |
+
"eval_runtime": 40.2195,
|
| 143195 |
+
"eval_samples_per_second": 20.687,
|
| 143196 |
+
"eval_steps_per_second": 0.646,
|
| 143197 |
+
"eval_wer": 0.21877075186305614,
|
| 143198 |
+
"step": 31103
|
| 143199 |
+
},
|
| 143200 |
+
{
|
| 143201 |
+
"epoch": 248.06,
|
| 143202 |
+
"learning_rate": 9.513747980613894e-06,
|
| 143203 |
+
"loss": 0.3996,
|
| 143204 |
+
"step": 31110
|
| 143205 |
+
},
|
| 143206 |
+
{
|
| 143207 |
+
"epoch": 248.14,
|
| 143208 |
+
"learning_rate": 9.513586429725364e-06,
|
| 143209 |
+
"loss": 0.4235,
|
| 143210 |
+
"step": 31120
|
| 143211 |
+
},
|
| 143212 |
+
{
|
| 143213 |
+
"epoch": 248.22,
|
| 143214 |
+
"learning_rate": 9.513424878836834e-06,
|
| 143215 |
+
"loss": 1.0097,
|
| 143216 |
+
"step": 31130
|
| 143217 |
+
},
|
| 143218 |
+
{
|
| 143219 |
+
"epoch": 248.3,
|
| 143220 |
+
"learning_rate": 9.513263327948304e-06,
|
| 143221 |
+
"loss": 0.4184,
|
| 143222 |
+
"step": 31140
|
| 143223 |
+
},
|
| 143224 |
+
{
|
| 143225 |
+
"epoch": 248.38,
|
| 143226 |
+
"learning_rate": 9.513101777059774e-06,
|
| 143227 |
+
"loss": 0.6077,
|
| 143228 |
+
"step": 31150
|
| 143229 |
+
},
|
| 143230 |
+
{
|
| 143231 |
+
"epoch": 248.46,
|
| 143232 |
+
"learning_rate": 9.512940226171244e-06,
|
| 143233 |
+
"loss": 0.8381,
|
| 143234 |
+
"step": 31160
|
| 143235 |
+
},
|
| 143236 |
+
{
|
| 143237 |
+
"epoch": 248.54,
|
| 143238 |
+
"learning_rate": 9.512778675282714e-06,
|
| 143239 |
+
"loss": 0.3861,
|
| 143240 |
+
"step": 31170
|
| 143241 |
+
},
|
| 143242 |
+
{
|
| 143243 |
+
"epoch": 248.62,
|
| 143244 |
+
"learning_rate": 9.512617124394184e-06,
|
| 143245 |
+
"loss": 0.9667,
|
| 143246 |
+
"step": 31180
|
| 143247 |
+
},
|
| 143248 |
+
{
|
| 143249 |
+
"epoch": 248.7,
|
| 143250 |
+
"learning_rate": 9.512455573505654e-06,
|
| 143251 |
+
"loss": 0.4098,
|
| 143252 |
+
"step": 31190
|
| 143253 |
+
},
|
| 143254 |
+
{
|
| 143255 |
+
"epoch": 248.78,
|
| 143256 |
+
"learning_rate": 9.512294022617125e-06,
|
| 143257 |
+
"loss": 0.6285,
|
| 143258 |
+
"step": 31200
|
| 143259 |
+
},
|
| 143260 |
+
{
|
| 143261 |
+
"epoch": 248.86,
|
| 143262 |
+
"learning_rate": 9.512132471728595e-06,
|
| 143263 |
+
"loss": 0.8214,
|
| 143264 |
+
"step": 31210
|
| 143265 |
+
},
|
| 143266 |
+
{
|
| 143267 |
+
"epoch": 248.94,
|
| 143268 |
+
"learning_rate": 9.511970920840065e-06,
|
| 143269 |
+
"loss": 0.3999,
|
| 143270 |
+
"step": 31220
|
| 143271 |
+
},
|
| 143272 |
+
{
|
| 143273 |
+
"epoch": 249.0,
|
| 143274 |
+
"eval_loss": 0.5187040567398071,
|
| 143275 |
+
"eval_runtime": 39.6923,
|
| 143276 |
+
"eval_samples_per_second": 20.961,
|
| 143277 |
+
"eval_steps_per_second": 0.655,
|
| 143278 |
+
"eval_wer": 0.22114444695089858,
|
| 143279 |
+
"step": 31228
|
| 143280 |
}
|
| 143281 |
],
|
| 143282 |
+
"max_steps": 625000,
|
| 143283 |
"num_train_epochs": 5000,
|
| 143284 |
+
"total_flos": 8.787204578449628e+19,
|
| 143285 |
"trial_name": null,
|
| 143286 |
"trial_params": null
|
| 143287 |
}
|
model-bin/finetune/base/{checkpoint-30356 → checkpoint-31228}/training_args.bin
RENAMED
|
File without changes
|
model-bin/finetune/base/{checkpoint-30729 → checkpoint-31352}/config.json
RENAMED
|
File without changes
|
model-bin/finetune/base/{checkpoint-30729 → checkpoint-31352}/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:be5e9949a1d9f960275fde6e40863dac1d0a28cfc23f7e4fe42e74f6cd73acbb
|
| 3 |
size 722165009
|
model-bin/finetune/base/{checkpoint-30729 → checkpoint-31352}/preprocessor_config.json
RENAMED
|
File without changes
|
model-bin/finetune/base/{checkpoint-30356 → checkpoint-31352}/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 sha256:3055d9048e5c475fba56f8d269a75782dadecc8525b1b347c380e9e240c5c114
|
| 3 |
size 377909911
|
model-bin/finetune/base/{checkpoint-30356 → checkpoint-31352}/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 sha256:198d5d69a85a5b4f68a4e9fa1a50e094226298b8a1f0ddc9e017722cf3804b6b
|
| 3 |
size 14503
|
model-bin/finetune/base/{checkpoint-30356 → checkpoint-31352}/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 sha256:022820e74e7f521c77ec87ebd5b0cb35a1f104c0face2a764d35ec3b9d917f83
|
| 3 |
size 559
|
model-bin/finetune/base/{checkpoint-30729 → checkpoint-31352}/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 sha256:73650a78a269555c41d333e2bf2bf8a1f37ae1b96412098df96490854ded2e96
|
| 3 |
size 623
|
model-bin/finetune/base/{checkpoint-30356 → checkpoint-31352}/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,
|
|
@@ -142692,11 +142692,683 @@
|
|
| 142692 |
"eval_steps_per_second": 0.643,
|
| 142693 |
"eval_wer": 0.20691915513474143,
|
| 142694 |
"step": 30356
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 142695 |
}
|
| 142696 |
],
|
| 142697 |
-
"max_steps":
|
| 142698 |
"num_train_epochs": 5000,
|
| 142699 |
-
"total_flos": 8.
|
| 142700 |
"trial_name": null,
|
| 142701 |
"trial_params": null
|
| 142702 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.20553532410779315,
|
| 3 |
+
"best_model_checkpoint": "./model-bin/finetune/base/checkpoint-31352",
|
| 4 |
+
"epoch": 251.99598393574297,
|
| 5 |
+
"global_step": 31352,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
|
|
| 142692 |
"eval_steps_per_second": 0.643,
|
| 142693 |
"eval_wer": 0.20691915513474143,
|
| 142694 |
"step": 30356
|
| 142695 |
+
},
|
| 142696 |
+
{
|
| 142697 |
+
"epoch": 242.03,
|
| 142698 |
+
"learning_rate": 9.525864297253636e-06,
|
| 142699 |
+
"loss": 0.4269,
|
| 142700 |
+
"step": 30360
|
| 142701 |
+
},
|
| 142702 |
+
{
|
| 142703 |
+
"epoch": 242.11,
|
| 142704 |
+
"learning_rate": 9.525702746365106e-06,
|
| 142705 |
+
"loss": 0.5977,
|
| 142706 |
+
"step": 30370
|
| 142707 |
+
},
|
| 142708 |
+
{
|
| 142709 |
+
"epoch": 242.19,
|
| 142710 |
+
"learning_rate": 9.525541195476576e-06,
|
| 142711 |
+
"loss": 0.8203,
|
| 142712 |
+
"step": 30380
|
| 142713 |
+
},
|
| 142714 |
+
{
|
| 142715 |
+
"epoch": 242.27,
|
| 142716 |
+
"learning_rate": 9.525379644588046e-06,
|
| 142717 |
+
"loss": 0.5911,
|
| 142718 |
+
"step": 30390
|
| 142719 |
+
},
|
| 142720 |
+
{
|
| 142721 |
+
"epoch": 242.35,
|
| 142722 |
+
"learning_rate": 9.525218093699517e-06,
|
| 142723 |
+
"loss": 0.476,
|
| 142724 |
+
"step": 30400
|
| 142725 |
+
},
|
| 142726 |
+
{
|
| 142727 |
+
"epoch": 242.43,
|
| 142728 |
+
"learning_rate": 9.525056542810987e-06,
|
| 142729 |
+
"loss": 0.9584,
|
| 142730 |
+
"step": 30410
|
| 142731 |
+
},
|
| 142732 |
+
{
|
| 142733 |
+
"epoch": 242.51,
|
| 142734 |
+
"learning_rate": 9.524894991922457e-06,
|
| 142735 |
+
"loss": 0.4033,
|
| 142736 |
+
"step": 30420
|
| 142737 |
+
},
|
| 142738 |
+
{
|
| 142739 |
+
"epoch": 242.59,
|
| 142740 |
+
"learning_rate": 9.524733441033927e-06,
|
| 142741 |
+
"loss": 0.8297,
|
| 142742 |
+
"step": 30430
|
| 142743 |
+
},
|
| 142744 |
+
{
|
| 142745 |
+
"epoch": 242.67,
|
| 142746 |
+
"learning_rate": 9.524571890145397e-06,
|
| 142747 |
+
"loss": 0.5949,
|
| 142748 |
+
"step": 30440
|
| 142749 |
+
},
|
| 142750 |
+
{
|
| 142751 |
+
"epoch": 242.75,
|
| 142752 |
+
"learning_rate": 9.524410339256867e-06,
|
| 142753 |
+
"loss": 0.4561,
|
| 142754 |
+
"step": 30450
|
| 142755 |
+
},
|
| 142756 |
+
{
|
| 142757 |
+
"epoch": 242.83,
|
| 142758 |
+
"learning_rate": 9.524248788368337e-06,
|
| 142759 |
+
"loss": 1.0078,
|
| 142760 |
+
"step": 30460
|
| 142761 |
+
},
|
| 142762 |
+
{
|
| 142763 |
+
"epoch": 242.91,
|
| 142764 |
+
"learning_rate": 9.524087237479807e-06,
|
| 142765 |
+
"loss": 0.459,
|
| 142766 |
+
"step": 30470
|
| 142767 |
+
},
|
| 142768 |
+
{
|
| 142769 |
+
"epoch": 242.99,
|
| 142770 |
+
"learning_rate": 9.523925686591277e-06,
|
| 142771 |
+
"loss": 0.8402,
|
| 142772 |
+
"step": 30480
|
| 142773 |
+
},
|
| 142774 |
+
{
|
| 142775 |
+
"epoch": 243.0,
|
| 142776 |
+
"eval_loss": 0.5306538939476013,
|
| 142777 |
+
"eval_runtime": 40.484,
|
| 142778 |
+
"eval_samples_per_second": 20.551,
|
| 142779 |
+
"eval_steps_per_second": 0.642,
|
| 142780 |
+
"eval_wer": 0.22069377990430622,
|
| 142781 |
+
"step": 30481
|
| 142782 |
+
},
|
| 142783 |
+
{
|
| 142784 |
+
"epoch": 245.07,
|
| 142785 |
+
"learning_rate": 9.523764135702747e-06,
|
| 142786 |
+
"loss": 0.4849,
|
| 142787 |
+
"step": 30490
|
| 142788 |
+
},
|
| 142789 |
+
{
|
| 142790 |
+
"epoch": 245.15,
|
| 142791 |
+
"learning_rate": 9.523602584814217e-06,
|
| 142792 |
+
"loss": 0.4615,
|
| 142793 |
+
"step": 30500
|
| 142794 |
+
},
|
| 142795 |
+
{
|
| 142796 |
+
"epoch": 245.23,
|
| 142797 |
+
"learning_rate": 9.523441033925687e-06,
|
| 142798 |
+
"loss": 0.9455,
|
| 142799 |
+
"step": 30510
|
| 142800 |
+
},
|
| 142801 |
+
{
|
| 142802 |
+
"epoch": 245.31,
|
| 142803 |
+
"learning_rate": 9.523279483037157e-06,
|
| 142804 |
+
"loss": 0.3454,
|
| 142805 |
+
"step": 30520
|
| 142806 |
+
},
|
| 142807 |
+
{
|
| 142808 |
+
"epoch": 245.39,
|
| 142809 |
+
"learning_rate": 9.523117932148629e-06,
|
| 142810 |
+
"loss": 0.8176,
|
| 142811 |
+
"step": 30530
|
| 142812 |
+
},
|
| 142813 |
+
{
|
| 142814 |
+
"epoch": 245.47,
|
| 142815 |
+
"learning_rate": 9.522956381260099e-06,
|
| 142816 |
+
"loss": 0.6493,
|
| 142817 |
+
"step": 30540
|
| 142818 |
+
},
|
| 142819 |
+
{
|
| 142820 |
+
"epoch": 245.55,
|
| 142821 |
+
"learning_rate": 9.522794830371569e-06,
|
| 142822 |
+
"loss": 0.5102,
|
| 142823 |
+
"step": 30550
|
| 142824 |
+
},
|
| 142825 |
+
{
|
| 142826 |
+
"epoch": 245.63,
|
| 142827 |
+
"learning_rate": 9.522633279483039e-06,
|
| 142828 |
+
"loss": 0.9747,
|
| 142829 |
+
"step": 30560
|
| 142830 |
+
},
|
| 142831 |
+
{
|
| 142832 |
+
"epoch": 245.71,
|
| 142833 |
+
"learning_rate": 9.522471728594509e-06,
|
| 142834 |
+
"loss": 0.4284,
|
| 142835 |
+
"step": 30570
|
| 142836 |
+
},
|
| 142837 |
+
{
|
| 142838 |
+
"epoch": 245.8,
|
| 142839 |
+
"learning_rate": 9.522310177705979e-06,
|
| 142840 |
+
"loss": 0.8277,
|
| 142841 |
+
"step": 30580
|
| 142842 |
+
},
|
| 142843 |
+
{
|
| 142844 |
+
"epoch": 245.88,
|
| 142845 |
+
"learning_rate": 9.522148626817448e-06,
|
| 142846 |
+
"loss": 0.606,
|
| 142847 |
+
"step": 30590
|
| 142848 |
+
},
|
| 142849 |
+
{
|
| 142850 |
+
"epoch": 245.96,
|
| 142851 |
+
"learning_rate": 9.521987075928918e-06,
|
| 142852 |
+
"loss": 0.5187,
|
| 142853 |
+
"step": 30600
|
| 142854 |
+
},
|
| 142855 |
+
{
|
| 142856 |
+
"epoch": 246.0,
|
| 142857 |
+
"eval_loss": 0.541337251663208,
|
| 142858 |
+
"eval_runtime": 40.6426,
|
| 142859 |
+
"eval_samples_per_second": 20.471,
|
| 142860 |
+
"eval_steps_per_second": 0.64,
|
| 142861 |
+
"eval_wer": 0.2235569879871081,
|
| 142862 |
+
"step": 30605
|
| 142863 |
+
},
|
| 142864 |
+
{
|
| 142865 |
+
"epoch": 246.04,
|
| 142866 |
+
"learning_rate": 9.521825525040388e-06,
|
| 142867 |
+
"loss": 0.4377,
|
| 142868 |
+
"step": 30610
|
| 142869 |
+
},
|
| 142870 |
+
{
|
| 142871 |
+
"epoch": 246.12,
|
| 142872 |
+
"learning_rate": 9.521663974151858e-06,
|
| 142873 |
+
"loss": 0.4489,
|
| 142874 |
+
"step": 30620
|
| 142875 |
+
},
|
| 142876 |
+
{
|
| 142877 |
+
"epoch": 246.2,
|
| 142878 |
+
"learning_rate": 9.521502423263328e-06,
|
| 142879 |
+
"loss": 1.0363,
|
| 142880 |
+
"step": 30630
|
| 142881 |
+
},
|
| 142882 |
+
{
|
| 142883 |
+
"epoch": 246.28,
|
| 142884 |
+
"learning_rate": 9.521340872374798e-06,
|
| 142885 |
+
"loss": 0.3974,
|
| 142886 |
+
"step": 30640
|
| 142887 |
+
},
|
| 142888 |
+
{
|
| 142889 |
+
"epoch": 246.36,
|
| 142890 |
+
"learning_rate": 9.521179321486268e-06,
|
| 142891 |
+
"loss": 0.4576,
|
| 142892 |
+
"step": 30650
|
| 142893 |
+
},
|
| 142894 |
+
{
|
| 142895 |
+
"epoch": 246.44,
|
| 142896 |
+
"learning_rate": 9.521017770597738e-06,
|
| 142897 |
+
"loss": 0.9549,
|
| 142898 |
+
"step": 30660
|
| 142899 |
+
},
|
| 142900 |
+
{
|
| 142901 |
+
"epoch": 246.52,
|
| 142902 |
+
"learning_rate": 9.52085621970921e-06,
|
| 142903 |
+
"loss": 0.3576,
|
| 142904 |
+
"step": 30670
|
| 142905 |
+
},
|
| 142906 |
+
{
|
| 142907 |
+
"epoch": 246.6,
|
| 142908 |
+
"learning_rate": 9.52069466882068e-06,
|
| 142909 |
+
"loss": 1.095,
|
| 142910 |
+
"step": 30680
|
| 142911 |
+
},
|
| 142912 |
+
{
|
| 142913 |
+
"epoch": 246.69,
|
| 142914 |
+
"learning_rate": 9.52053311793215e-06,
|
| 142915 |
+
"loss": 0.4144,
|
| 142916 |
+
"step": 30690
|
| 142917 |
+
},
|
| 142918 |
+
{
|
| 142919 |
+
"epoch": 246.77,
|
| 142920 |
+
"learning_rate": 9.52037156704362e-06,
|
| 142921 |
+
"loss": 0.5052,
|
| 142922 |
+
"step": 30700
|
| 142923 |
+
},
|
| 142924 |
+
{
|
| 142925 |
+
"epoch": 246.85,
|
| 142926 |
+
"learning_rate": 9.52021001615509e-06,
|
| 142927 |
+
"loss": 0.9081,
|
| 142928 |
+
"step": 30710
|
| 142929 |
+
},
|
| 142930 |
+
{
|
| 142931 |
+
"epoch": 246.93,
|
| 142932 |
+
"learning_rate": 9.52004846526656e-06,
|
| 142933 |
+
"loss": 0.3901,
|
| 142934 |
+
"step": 30720
|
| 142935 |
+
},
|
| 142936 |
+
{
|
| 142937 |
+
"epoch": 247.0,
|
| 142938 |
+
"eval_loss": 0.43034788966178894,
|
| 142939 |
+
"eval_runtime": 40.4735,
|
| 142940 |
+
"eval_samples_per_second": 20.557,
|
| 142941 |
+
"eval_steps_per_second": 0.642,
|
| 142942 |
+
"eval_wer": 0.2156060495360561,
|
| 142943 |
+
"step": 30729
|
| 142944 |
+
},
|
| 142945 |
+
{
|
| 142946 |
+
"epoch": 247.01,
|
| 142947 |
+
"learning_rate": 9.51988691437803e-06,
|
| 142948 |
+
"loss": 0.5436,
|
| 142949 |
+
"step": 30730
|
| 142950 |
+
},
|
| 142951 |
+
{
|
| 142952 |
+
"epoch": 247.09,
|
| 142953 |
+
"learning_rate": 9.5197253634895e-06,
|
| 142954 |
+
"loss": 0.3896,
|
| 142955 |
+
"step": 30740
|
| 142956 |
+
},
|
| 142957 |
+
{
|
| 142958 |
+
"epoch": 247.17,
|
| 142959 |
+
"learning_rate": 9.51956381260097e-06,
|
| 142960 |
+
"loss": 0.5227,
|
| 142961 |
+
"step": 30750
|
| 142962 |
+
},
|
| 142963 |
+
{
|
| 142964 |
+
"epoch": 247.25,
|
| 142965 |
+
"learning_rate": 9.51940226171244e-06,
|
| 142966 |
+
"loss": 0.779,
|
| 142967 |
+
"step": 30760
|
| 142968 |
+
},
|
| 142969 |
+
{
|
| 142970 |
+
"epoch": 247.33,
|
| 142971 |
+
"learning_rate": 9.51924071082391e-06,
|
| 142972 |
+
"loss": 0.4329,
|
| 142973 |
+
"step": 30770
|
| 142974 |
+
},
|
| 142975 |
+
{
|
| 142976 |
+
"epoch": 247.41,
|
| 142977 |
+
"learning_rate": 9.51907915993538e-06,
|
| 142978 |
+
"loss": 1.1671,
|
| 142979 |
+
"step": 30780
|
| 142980 |
+
},
|
| 142981 |
+
{
|
| 142982 |
+
"epoch": 247.49,
|
| 142983 |
+
"learning_rate": 9.51891760904685e-06,
|
| 142984 |
+
"loss": 0.4234,
|
| 142985 |
+
"step": 30790
|
| 142986 |
+
},
|
| 142987 |
+
{
|
| 142988 |
+
"epoch": 247.57,
|
| 142989 |
+
"learning_rate": 9.51875605815832e-06,
|
| 142990 |
+
"loss": 0.5782,
|
| 142991 |
+
"step": 30800
|
| 142992 |
+
},
|
| 142993 |
+
{
|
| 142994 |
+
"epoch": 247.65,
|
| 142995 |
+
"learning_rate": 9.518594507269791e-06,
|
| 142996 |
+
"loss": 0.83,
|
| 142997 |
+
"step": 30810
|
| 142998 |
+
},
|
| 142999 |
+
{
|
| 143000 |
+
"epoch": 247.73,
|
| 143001 |
+
"learning_rate": 9.518432956381261e-06,
|
| 143002 |
+
"loss": 0.4059,
|
| 143003 |
+
"step": 30820
|
| 143004 |
+
},
|
| 143005 |
+
{
|
| 143006 |
+
"epoch": 247.81,
|
| 143007 |
+
"learning_rate": 9.518271405492731e-06,
|
| 143008 |
+
"loss": 1.1213,
|
| 143009 |
+
"step": 30830
|
| 143010 |
+
},
|
| 143011 |
+
{
|
| 143012 |
+
"epoch": 247.89,
|
| 143013 |
+
"learning_rate": 9.518109854604201e-06,
|
| 143014 |
+
"loss": 0.4175,
|
| 143015 |
+
"step": 30840
|
| 143016 |
+
},
|
| 143017 |
+
{
|
| 143018 |
+
"epoch": 247.97,
|
| 143019 |
+
"learning_rate": 9.517948303715671e-06,
|
| 143020 |
+
"loss": 0.5727,
|
| 143021 |
+
"step": 30850
|
| 143022 |
+
},
|
| 143023 |
+
{
|
| 143024 |
+
"epoch": 248.0,
|
| 143025 |
+
"eval_loss": 0.4734344184398651,
|
| 143026 |
+
"eval_runtime": 41.7653,
|
| 143027 |
+
"eval_samples_per_second": 19.897,
|
| 143028 |
+
"eval_steps_per_second": 0.623,
|
| 143029 |
+
"eval_wer": 0.21280238183848157,
|
| 143030 |
+
"step": 30853
|
| 143031 |
+
},
|
| 143032 |
+
{
|
| 143033 |
+
"epoch": 246.06,
|
| 143034 |
+
"learning_rate": 9.517786752827141e-06,
|
| 143035 |
+
"loss": 0.3736,
|
| 143036 |
+
"step": 30860
|
| 143037 |
+
},
|
| 143038 |
+
{
|
| 143039 |
+
"epoch": 246.14,
|
| 143040 |
+
"learning_rate": 9.517625201938611e-06,
|
| 143041 |
+
"loss": 0.4175,
|
| 143042 |
+
"step": 30870
|
| 143043 |
+
},
|
| 143044 |
+
{
|
| 143045 |
+
"epoch": 246.22,
|
| 143046 |
+
"learning_rate": 9.517463651050081e-06,
|
| 143047 |
+
"loss": 0.9235,
|
| 143048 |
+
"step": 30880
|
| 143049 |
+
},
|
| 143050 |
+
{
|
| 143051 |
+
"epoch": 246.3,
|
| 143052 |
+
"learning_rate": 9.517302100161551e-06,
|
| 143053 |
+
"loss": 0.4543,
|
| 143054 |
+
"step": 30890
|
| 143055 |
+
},
|
| 143056 |
+
{
|
| 143057 |
+
"epoch": 246.38,
|
| 143058 |
+
"learning_rate": 9.517140549273021e-06,
|
| 143059 |
+
"loss": 0.6469,
|
| 143060 |
+
"step": 30900
|
| 143061 |
+
},
|
| 143062 |
+
{
|
| 143063 |
+
"epoch": 246.46,
|
| 143064 |
+
"learning_rate": 9.516978998384491e-06,
|
| 143065 |
+
"loss": 0.7732,
|
| 143066 |
+
"step": 30910
|
| 143067 |
+
},
|
| 143068 |
+
{
|
| 143069 |
+
"epoch": 246.54,
|
| 143070 |
+
"learning_rate": 9.516817447495961e-06,
|
| 143071 |
+
"loss": 0.4104,
|
| 143072 |
+
"step": 30920
|
| 143073 |
+
},
|
| 143074 |
+
{
|
| 143075 |
+
"epoch": 246.62,
|
| 143076 |
+
"learning_rate": 9.516655896607431e-06,
|
| 143077 |
+
"loss": 1.0242,
|
| 143078 |
+
"step": 30930
|
| 143079 |
+
},
|
| 143080 |
+
{
|
| 143081 |
+
"epoch": 246.7,
|
| 143082 |
+
"learning_rate": 9.516494345718903e-06,
|
| 143083 |
+
"loss": 0.4617,
|
| 143084 |
+
"step": 30940
|
| 143085 |
+
},
|
| 143086 |
+
{
|
| 143087 |
+
"epoch": 246.78,
|
| 143088 |
+
"learning_rate": 9.516332794830373e-06,
|
| 143089 |
+
"loss": 0.6495,
|
| 143090 |
+
"step": 30950
|
| 143091 |
+
},
|
| 143092 |
+
{
|
| 143093 |
+
"epoch": 246.86,
|
| 143094 |
+
"learning_rate": 9.516171243941843e-06,
|
| 143095 |
+
"loss": 0.7783,
|
| 143096 |
+
"step": 30960
|
| 143097 |
+
},
|
| 143098 |
+
{
|
| 143099 |
+
"epoch": 246.94,
|
| 143100 |
+
"learning_rate": 9.516009693053313e-06,
|
| 143101 |
+
"loss": 0.3745,
|
| 143102 |
+
"step": 30970
|
| 143103 |
+
},
|
| 143104 |
+
{
|
| 143105 |
+
"epoch": 247.0,
|
| 143106 |
+
"eval_loss": 0.4507042467594147,
|
| 143107 |
+
"eval_runtime": 39.3618,
|
| 143108 |
+
"eval_samples_per_second": 21.112,
|
| 143109 |
+
"eval_steps_per_second": 0.661,
|
| 143110 |
+
"eval_wer": 0.21471927162367224,
|
| 143111 |
+
"step": 30978
|
| 143112 |
+
},
|
| 143113 |
+
{
|
| 143114 |
+
"epoch": 247.02,
|
| 143115 |
+
"learning_rate": 9.515848142164783e-06,
|
| 143116 |
+
"loss": 0.4894,
|
| 143117 |
+
"step": 30980
|
| 143118 |
+
},
|
| 143119 |
+
{
|
| 143120 |
+
"epoch": 247.1,
|
| 143121 |
+
"learning_rate": 9.515686591276253e-06,
|
| 143122 |
+
"loss": 0.3954,
|
| 143123 |
+
"step": 30990
|
| 143124 |
+
},
|
| 143125 |
+
{
|
| 143126 |
+
"epoch": 247.18,
|
| 143127 |
+
"learning_rate": 9.515525040387723e-06,
|
| 143128 |
+
"loss": 0.6174,
|
| 143129 |
+
"step": 31000
|
| 143130 |
+
},
|
| 143131 |
+
{
|
| 143132 |
+
"epoch": 247.26,
|
| 143133 |
+
"learning_rate": 9.515363489499193e-06,
|
| 143134 |
+
"loss": 0.7535,
|
| 143135 |
+
"step": 31010
|
| 143136 |
+
},
|
| 143137 |
+
{
|
| 143138 |
+
"epoch": 247.34,
|
| 143139 |
+
"learning_rate": 9.515201938610662e-06,
|
| 143140 |
+
"loss": 0.4249,
|
| 143141 |
+
"step": 31020
|
| 143142 |
+
},
|
| 143143 |
+
{
|
| 143144 |
+
"epoch": 247.42,
|
| 143145 |
+
"learning_rate": 9.515040387722132e-06,
|
| 143146 |
+
"loss": 0.8701,
|
| 143147 |
+
"step": 31030
|
| 143148 |
+
},
|
| 143149 |
+
{
|
| 143150 |
+
"epoch": 247.5,
|
| 143151 |
+
"learning_rate": 9.514878836833602e-06,
|
| 143152 |
+
"loss": 0.4086,
|
| 143153 |
+
"step": 31040
|
| 143154 |
+
},
|
| 143155 |
+
{
|
| 143156 |
+
"epoch": 247.58,
|
| 143157 |
+
"learning_rate": 9.514717285945072e-06,
|
| 143158 |
+
"loss": 0.7135,
|
| 143159 |
+
"step": 31050
|
| 143160 |
+
},
|
| 143161 |
+
{
|
| 143162 |
+
"epoch": 247.66,
|
| 143163 |
+
"learning_rate": 9.514555735056542e-06,
|
| 143164 |
+
"loss": 0.8156,
|
| 143165 |
+
"step": 31060
|
| 143166 |
+
},
|
| 143167 |
+
{
|
| 143168 |
+
"epoch": 247.74,
|
| 143169 |
+
"learning_rate": 9.514394184168012e-06,
|
| 143170 |
+
"loss": 0.4138,
|
| 143171 |
+
"step": 31070
|
| 143172 |
+
},
|
| 143173 |
+
{
|
| 143174 |
+
"epoch": 247.82,
|
| 143175 |
+
"learning_rate": 9.514232633279484e-06,
|
| 143176 |
+
"loss": 1.0434,
|
| 143177 |
+
"step": 31080
|
| 143178 |
+
},
|
| 143179 |
+
{
|
| 143180 |
+
"epoch": 247.9,
|
| 143181 |
+
"learning_rate": 9.514071082390954e-06,
|
| 143182 |
+
"loss": 0.3624,
|
| 143183 |
+
"step": 31090
|
| 143184 |
+
},
|
| 143185 |
+
{
|
| 143186 |
+
"epoch": 247.98,
|
| 143187 |
+
"learning_rate": 9.513909531502424e-06,
|
| 143188 |
+
"loss": 0.6142,
|
| 143189 |
+
"step": 31100
|
| 143190 |
+
},
|
| 143191 |
+
{
|
| 143192 |
+
"epoch": 248.0,
|
| 143193 |
+
"eval_loss": 0.49309414625167847,
|
| 143194 |
+
"eval_runtime": 40.2195,
|
| 143195 |
+
"eval_samples_per_second": 20.687,
|
| 143196 |
+
"eval_steps_per_second": 0.646,
|
| 143197 |
+
"eval_wer": 0.21877075186305614,
|
| 143198 |
+
"step": 31103
|
| 143199 |
+
},
|
| 143200 |
+
{
|
| 143201 |
+
"epoch": 248.06,
|
| 143202 |
+
"learning_rate": 9.513747980613894e-06,
|
| 143203 |
+
"loss": 0.3996,
|
| 143204 |
+
"step": 31110
|
| 143205 |
+
},
|
| 143206 |
+
{
|
| 143207 |
+
"epoch": 248.14,
|
| 143208 |
+
"learning_rate": 9.513586429725364e-06,
|
| 143209 |
+
"loss": 0.4235,
|
| 143210 |
+
"step": 31120
|
| 143211 |
+
},
|
| 143212 |
+
{
|
| 143213 |
+
"epoch": 248.22,
|
| 143214 |
+
"learning_rate": 9.513424878836834e-06,
|
| 143215 |
+
"loss": 1.0097,
|
| 143216 |
+
"step": 31130
|
| 143217 |
+
},
|
| 143218 |
+
{
|
| 143219 |
+
"epoch": 248.3,
|
| 143220 |
+
"learning_rate": 9.513263327948304e-06,
|
| 143221 |
+
"loss": 0.4184,
|
| 143222 |
+
"step": 31140
|
| 143223 |
+
},
|
| 143224 |
+
{
|
| 143225 |
+
"epoch": 248.38,
|
| 143226 |
+
"learning_rate": 9.513101777059774e-06,
|
| 143227 |
+
"loss": 0.6077,
|
| 143228 |
+
"step": 31150
|
| 143229 |
+
},
|
| 143230 |
+
{
|
| 143231 |
+
"epoch": 248.46,
|
| 143232 |
+
"learning_rate": 9.512940226171244e-06,
|
| 143233 |
+
"loss": 0.8381,
|
| 143234 |
+
"step": 31160
|
| 143235 |
+
},
|
| 143236 |
+
{
|
| 143237 |
+
"epoch": 248.54,
|
| 143238 |
+
"learning_rate": 9.512778675282714e-06,
|
| 143239 |
+
"loss": 0.3861,
|
| 143240 |
+
"step": 31170
|
| 143241 |
+
},
|
| 143242 |
+
{
|
| 143243 |
+
"epoch": 248.62,
|
| 143244 |
+
"learning_rate": 9.512617124394184e-06,
|
| 143245 |
+
"loss": 0.9667,
|
| 143246 |
+
"step": 31180
|
| 143247 |
+
},
|
| 143248 |
+
{
|
| 143249 |
+
"epoch": 248.7,
|
| 143250 |
+
"learning_rate": 9.512455573505654e-06,
|
| 143251 |
+
"loss": 0.4098,
|
| 143252 |
+
"step": 31190
|
| 143253 |
+
},
|
| 143254 |
+
{
|
| 143255 |
+
"epoch": 248.78,
|
| 143256 |
+
"learning_rate": 9.512294022617125e-06,
|
| 143257 |
+
"loss": 0.6285,
|
| 143258 |
+
"step": 31200
|
| 143259 |
+
},
|
| 143260 |
+
{
|
| 143261 |
+
"epoch": 248.86,
|
| 143262 |
+
"learning_rate": 9.512132471728595e-06,
|
| 143263 |
+
"loss": 0.8214,
|
| 143264 |
+
"step": 31210
|
| 143265 |
+
},
|
| 143266 |
+
{
|
| 143267 |
+
"epoch": 248.94,
|
| 143268 |
+
"learning_rate": 9.511970920840065e-06,
|
| 143269 |
+
"loss": 0.3999,
|
| 143270 |
+
"step": 31220
|
| 143271 |
+
},
|
| 143272 |
+
{
|
| 143273 |
+
"epoch": 249.0,
|
| 143274 |
+
"eval_loss": 0.5187040567398071,
|
| 143275 |
+
"eval_runtime": 39.6923,
|
| 143276 |
+
"eval_samples_per_second": 20.961,
|
| 143277 |
+
"eval_steps_per_second": 0.655,
|
| 143278 |
+
"eval_wer": 0.22114444695089858,
|
| 143279 |
+
"step": 31228
|
| 143280 |
+
},
|
| 143281 |
+
{
|
| 143282 |
+
"epoch": 251.02,
|
| 143283 |
+
"learning_rate": 9.511809369951535e-06,
|
| 143284 |
+
"loss": 0.3917,
|
| 143285 |
+
"step": 31230
|
| 143286 |
+
},
|
| 143287 |
+
{
|
| 143288 |
+
"epoch": 251.1,
|
| 143289 |
+
"learning_rate": 9.511647819063005e-06,
|
| 143290 |
+
"loss": 0.4211,
|
| 143291 |
+
"step": 31240
|
| 143292 |
+
},
|
| 143293 |
+
{
|
| 143294 |
+
"epoch": 251.18,
|
| 143295 |
+
"learning_rate": 9.511486268174475e-06,
|
| 143296 |
+
"loss": 0.5998,
|
| 143297 |
+
"step": 31250
|
| 143298 |
+
},
|
| 143299 |
+
{
|
| 143300 |
+
"epoch": 251.26,
|
| 143301 |
+
"learning_rate": 9.511324717285945e-06,
|
| 143302 |
+
"loss": 0.7724,
|
| 143303 |
+
"step": 31260
|
| 143304 |
+
},
|
| 143305 |
+
{
|
| 143306 |
+
"epoch": 251.34,
|
| 143307 |
+
"learning_rate": 9.511163166397415e-06,
|
| 143308 |
+
"loss": 0.4741,
|
| 143309 |
+
"step": 31270
|
| 143310 |
+
},
|
| 143311 |
+
{
|
| 143312 |
+
"epoch": 251.42,
|
| 143313 |
+
"learning_rate": 9.511001615508885e-06,
|
| 143314 |
+
"loss": 0.911,
|
| 143315 |
+
"step": 31280
|
| 143316 |
+
},
|
| 143317 |
+
{
|
| 143318 |
+
"epoch": 251.5,
|
| 143319 |
+
"learning_rate": 9.510840064620355e-06,
|
| 143320 |
+
"loss": 0.367,
|
| 143321 |
+
"step": 31290
|
| 143322 |
+
},
|
| 143323 |
+
{
|
| 143324 |
+
"epoch": 251.58,
|
| 143325 |
+
"learning_rate": 9.510678513731825e-06,
|
| 143326 |
+
"loss": 0.6541,
|
| 143327 |
+
"step": 31300
|
| 143328 |
+
},
|
| 143329 |
+
{
|
| 143330 |
+
"epoch": 251.66,
|
| 143331 |
+
"learning_rate": 9.510516962843297e-06,
|
| 143332 |
+
"loss": 0.7644,
|
| 143333 |
+
"step": 31310
|
| 143334 |
+
},
|
| 143335 |
+
{
|
| 143336 |
+
"epoch": 251.74,
|
| 143337 |
+
"learning_rate": 9.510355411954767e-06,
|
| 143338 |
+
"loss": 0.4301,
|
| 143339 |
+
"step": 31320
|
| 143340 |
+
},
|
| 143341 |
+
{
|
| 143342 |
+
"epoch": 251.82,
|
| 143343 |
+
"learning_rate": 9.510193861066237e-06,
|
| 143344 |
+
"loss": 1.1003,
|
| 143345 |
+
"step": 31330
|
| 143346 |
+
},
|
| 143347 |
+
{
|
| 143348 |
+
"epoch": 251.9,
|
| 143349 |
+
"learning_rate": 9.510032310177707e-06,
|
| 143350 |
+
"loss": 0.4245,
|
| 143351 |
+
"step": 31340
|
| 143352 |
+
},
|
| 143353 |
+
{
|
| 143354 |
+
"epoch": 251.98,
|
| 143355 |
+
"learning_rate": 9.509870759289177e-06,
|
| 143356 |
+
"loss": 0.743,
|
| 143357 |
+
"step": 31350
|
| 143358 |
+
},
|
| 143359 |
+
{
|
| 143360 |
+
"epoch": 252.0,
|
| 143361 |
+
"eval_loss": 0.4088016152381897,
|
| 143362 |
+
"eval_runtime": 40.379,
|
| 143363 |
+
"eval_samples_per_second": 20.605,
|
| 143364 |
+
"eval_steps_per_second": 0.644,
|
| 143365 |
+
"eval_wer": 0.20553532410779315,
|
| 143366 |
+
"step": 31352
|
| 143367 |
}
|
| 143368 |
],
|
| 143369 |
+
"max_steps": 620000,
|
| 143370 |
"num_train_epochs": 5000,
|
| 143371 |
+
"total_flos": 8.821981503951631e+19,
|
| 143372 |
"trial_name": null,
|
| 143373 |
"trial_params": null
|
| 143374 |
}
|
model-bin/finetune/base/{checkpoint-30729 → checkpoint-31352}/training_args.bin
RENAMED
|
File without changes
|
model-bin/finetune/base/log/1629634923.047115/events.out.tfevents.1629634923.91f414e9573a.903.131
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e471ade11996e71f440acf8847beb59ba85617abd10eaa2f07b9e6c4067f66f3
|
| 3 |
+
size 4194
|
model-bin/finetune/base/log/1629635595.6999147/events.out.tfevents.1629635595.91f414e9573a.903.133
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1557f194f0c4eba6159de8c0b9156c42acb54246ad71a4c5f7568c0ac9438019
|
| 3 |
+
size 4194
|
model-bin/finetune/base/log/1629636245.2886124/events.out.tfevents.1629636245.91f414e9573a.903.135
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ce22f73a63f1b058f7d515fdba84e2d2769c89e4a42e8ad80c0ccb8b5bc1fc9f
|
| 3 |
+
size 4194
|
model-bin/finetune/base/log/1629636904.1195304/events.out.tfevents.1629636904.91f414e9573a.903.137
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8daa6c42dc2dd39c9df597c47a8b10f7920adfd774e5395878bce1012d0e95e7
|
| 3 |
+
size 4194
|
model-bin/finetune/base/log/1629637560.6401086/events.out.tfevents.1629637560.91f414e9573a.903.139
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:64b272e07c2b4633d81c7849bb9d3839a3865eda917b95a4a03ff58249b13ba9
|
| 3 |
+
size 4194
|
model-bin/finetune/base/log/events.out.tfevents.1629634923.91f414e9573a.903.130
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:458b0593920d8f1bb3b1fcb24885082bb3a289e070d4d59ec2dcc4d5811ba554
|
| 3 |
+
size 6703
|
model-bin/finetune/base/log/events.out.tfevents.1629635595.91f414e9573a.903.132
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:02d2d128aff42220bb83ce5da55f27ab6c93863d9741b5a1298acc4772ea0dab
|
| 3 |
+
size 6543
|
model-bin/finetune/base/log/events.out.tfevents.1629636245.91f414e9573a.903.134
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6368f6bb2705b75f15f8955e4a578bf78bf200eddd1381387b33394536501b4e
|
| 3 |
+
size 6703
|
model-bin/finetune/base/log/events.out.tfevents.1629636904.91f414e9573a.903.136
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d6aa5d0f2f60c80991441dd0226d13b5572423362997827e75e275a4c13e044f
|
| 3 |
+
size 6543
|
model-bin/finetune/base/log/events.out.tfevents.1629637560.91f414e9573a.903.138
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:97535379d22a71dba3efd6b42a0aee5e4acef2e9544e89f60a9fbc6fd172c005
|
| 3 |
+
size 6703
|