stefania-radu
commited on
Commit
•
7a4de87
1
Parent(s):
aa9de5a
Training in progress, step 400000
Browse files
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 893441530
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1d612139c711185e81ead4721c4ade182b8281e1479ae688f56802b6c4e9ba79
|
3 |
size 893441530
|
last-checkpoint/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 454197066
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4fa7a23bc8b764ecbc33e951ce5db5a8164946993424ddee93b25c094c7c5323
|
3 |
size 454197066
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14244
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5d031f87a51288ac205183f504513071ae4228fb022abef477b54b6727749f44
|
3 |
size 14244
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1064
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3802b6d325bea1bd6ad9279691926311340a3a4209ab5b2d2bcf1374ce2a9b10
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch": 0.
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -2892,11 +2892,85 @@
|
|
2892 |
"eval_samples_per_second": 105.762,
|
2893 |
"eval_steps_per_second": 13.22,
|
2894 |
"step": 390000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2895 |
}
|
2896 |
],
|
2897 |
"max_steps": 1000000,
|
2898 |
"num_train_epochs": 9223372036854775807,
|
2899 |
-
"total_flos": 3.
|
2900 |
"trial_name": null,
|
2901 |
"trial_params": null
|
2902 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.4,
|
5 |
+
"global_step": 400000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
2892 |
"eval_samples_per_second": 105.762,
|
2893 |
"eval_steps_per_second": 13.22,
|
2894 |
"step": 390000
|
2895 |
+
},
|
2896 |
+
{
|
2897 |
+
"epoch": 0.39,
|
2898 |
+
"learning_rate": 1.625086510311916e-05,
|
2899 |
+
"loss": 0.3443,
|
2900 |
+
"step": 391000
|
2901 |
+
},
|
2902 |
+
{
|
2903 |
+
"epoch": 0.39,
|
2904 |
+
"learning_rate": 1.623778440059719e-05,
|
2905 |
+
"loss": 0.3439,
|
2906 |
+
"step": 392000
|
2907 |
+
},
|
2908 |
+
{
|
2909 |
+
"epoch": 0.39,
|
2910 |
+
"learning_rate": 1.622468332696346e-05,
|
2911 |
+
"loss": 0.3444,
|
2912 |
+
"step": 393000
|
2913 |
+
},
|
2914 |
+
{
|
2915 |
+
"epoch": 0.39,
|
2916 |
+
"learning_rate": 1.6211562025489212e-05,
|
2917 |
+
"loss": 0.3426,
|
2918 |
+
"step": 394000
|
2919 |
+
},
|
2920 |
+
{
|
2921 |
+
"epoch": 0.4,
|
2922 |
+
"learning_rate": 1.6198420639666893e-05,
|
2923 |
+
"loss": 0.3395,
|
2924 |
+
"step": 395000
|
2925 |
+
},
|
2926 |
+
{
|
2927 |
+
"epoch": 0.4,
|
2928 |
+
"eval_runtime": 3116.6643,
|
2929 |
+
"eval_samples_per_second": 108.979,
|
2930 |
+
"eval_steps_per_second": 13.623,
|
2931 |
+
"step": 395000
|
2932 |
+
},
|
2933 |
+
{
|
2934 |
+
"epoch": 0.4,
|
2935 |
+
"learning_rate": 1.61852593132086e-05,
|
2936 |
+
"loss": 0.3363,
|
2937 |
+
"step": 396000
|
2938 |
+
},
|
2939 |
+
{
|
2940 |
+
"epoch": 0.4,
|
2941 |
+
"learning_rate": 1.6172078190044487e-05,
|
2942 |
+
"loss": 0.3362,
|
2943 |
+
"step": 397000
|
2944 |
+
},
|
2945 |
+
{
|
2946 |
+
"epoch": 0.4,
|
2947 |
+
"learning_rate": 1.61588774143212e-05,
|
2948 |
+
"loss": 0.3414,
|
2949 |
+
"step": 398000
|
2950 |
+
},
|
2951 |
+
{
|
2952 |
+
"epoch": 0.4,
|
2953 |
+
"learning_rate": 1.614565713040032e-05,
|
2954 |
+
"loss": 0.3447,
|
2955 |
+
"step": 399000
|
2956 |
+
},
|
2957 |
+
{
|
2958 |
+
"epoch": 0.4,
|
2959 |
+
"learning_rate": 1.613241748285674e-05,
|
2960 |
+
"loss": 0.3438,
|
2961 |
+
"step": 400000
|
2962 |
+
},
|
2963 |
+
{
|
2964 |
+
"epoch": 0.4,
|
2965 |
+
"eval_runtime": 3111.8012,
|
2966 |
+
"eval_samples_per_second": 109.15,
|
2967 |
+
"eval_steps_per_second": 13.644,
|
2968 |
+
"step": 400000
|
2969 |
}
|
2970 |
],
|
2971 |
"max_steps": 1000000,
|
2972 |
"num_train_epochs": 9223372036854775807,
|
2973 |
+
"total_flos": 3.5418440692924416e+21,
|
2974 |
"trial_name": null,
|
2975 |
"trial_params": null
|
2976 |
}
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 454197066
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4fa7a23bc8b764ecbc33e951ce5db5a8164946993424ddee93b25c094c7c5323
|
3 |
size 454197066
|