Training in progress, step 255000
Browse files- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/pytorch_model.bin +1 -1
- last-checkpoint/rng_state_0.pth +1 -1
- last-checkpoint/rng_state_1.pth +1 -1
- last-checkpoint/rng_state_2.pth +1 -1
- last-checkpoint/rng_state_3.pth +1 -1
- last-checkpoint/scaler.pt +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +62 -2
- pytorch_model.bin +1 -1
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 402588883
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dd1d4f86d82b48e89d3abcab7d780d7695618e705e6c9c79ecfbd7ee84a92e67
|
3 |
size 402588883
|
last-checkpoint/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 201355195
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b1420ef536f29364736b64e6b013986d649ee5c16564b6e00d08c0b954558aad
|
3 |
size 201355195
|
last-checkpoint/rng_state_0.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14503
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a175dd1c8aa9d5617f0dc8e1111adf90e9b1c58122b9eca28db5a37b67aa289e
|
3 |
size 14503
|
last-checkpoint/rng_state_1.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14503
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a4fcea8bf8cc9391883e8d9ed5e0d2e4ffd00e37100d644258fd71293220272b
|
3 |
size 14503
|
last-checkpoint/rng_state_2.pth
CHANGED
@@ -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 sha256:6e6e528c3ebab005da051410d7d07fe4168cd7f3a6e69b2c74ff79d751fba610
|
3 |
size 14503
|
last-checkpoint/rng_state_3.pth
CHANGED
@@ -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 sha256:7974e7a6ef61d10c08aa96d97058c352f2bbc357367cfe464f7d2f1cdb881f4d
|
3 |
size 14503
|
last-checkpoint/scaler.pt
CHANGED
@@ -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:e7f57d9c56c938fd3746c186b53e5608019678734f0d7c744e50439d1392426a
|
3 |
size 559
|
last-checkpoint/scheduler.pt
CHANGED
@@ -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:d6edba8b1b4ae2b4db3c2c3b6fbdd3a7dae94a68c6987b8d2adb48a7acd2e0b8
|
3 |
size 623
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch": 4.
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -3006,6 +3006,66 @@
|
|
3006 |
"learning_rate": 8.004266282559454e-05,
|
3007 |
"loss": 0.3291,
|
3008 |
"step": 250000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
3009 |
}
|
3010 |
],
|
3011 |
"max_steps": 500000,
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 4.340425531914893,
|
5 |
+
"global_step": 255000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
3006 |
"learning_rate": 8.004266282559454e-05,
|
3007 |
"loss": 0.3291,
|
3008 |
"step": 250000
|
3009 |
+
},
|
3010 |
+
{
|
3011 |
+
"epoch": 4.26,
|
3012 |
+
"learning_rate": 7.982275153189381e-05,
|
3013 |
+
"loss": 0.329,
|
3014 |
+
"step": 250500
|
3015 |
+
},
|
3016 |
+
{
|
3017 |
+
"epoch": 4.27,
|
3018 |
+
"learning_rate": 7.960284198756389e-05,
|
3019 |
+
"loss": 0.3289,
|
3020 |
+
"step": 251000
|
3021 |
+
},
|
3022 |
+
{
|
3023 |
+
"epoch": 4.28,
|
3024 |
+
"learning_rate": 7.938293636302323e-05,
|
3025 |
+
"loss": 0.3291,
|
3026 |
+
"step": 251500
|
3027 |
+
},
|
3028 |
+
{
|
3029 |
+
"epoch": 4.29,
|
3030 |
+
"learning_rate": 7.916303682865151e-05,
|
3031 |
+
"loss": 0.3288,
|
3032 |
+
"step": 252000
|
3033 |
+
},
|
3034 |
+
{
|
3035 |
+
"epoch": 4.3,
|
3036 |
+
"learning_rate": 7.894358532762969e-05,
|
3037 |
+
"loss": 0.3283,
|
3038 |
+
"step": 252500
|
3039 |
+
},
|
3040 |
+
{
|
3041 |
+
"epoch": 4.31,
|
3042 |
+
"learning_rate": 7.872414421133043e-05,
|
3043 |
+
"loss": 0.3287,
|
3044 |
+
"step": 253000
|
3045 |
+
},
|
3046 |
+
{
|
3047 |
+
"epoch": 4.31,
|
3048 |
+
"learning_rate": 7.85042759143097e-05,
|
3049 |
+
"loss": 0.3285,
|
3050 |
+
"step": 253500
|
3051 |
+
},
|
3052 |
+
{
|
3053 |
+
"epoch": 4.32,
|
3054 |
+
"learning_rate": 7.828442237948187e-05,
|
3055 |
+
"loss": 0.3286,
|
3056 |
+
"step": 254000
|
3057 |
+
},
|
3058 |
+
{
|
3059 |
+
"epoch": 4.33,
|
3060 |
+
"learning_rate": 7.806458577671251e-05,
|
3061 |
+
"loss": 0.3284,
|
3062 |
+
"step": 254500
|
3063 |
+
},
|
3064 |
+
{
|
3065 |
+
"epoch": 4.34,
|
3066 |
+
"learning_rate": 7.784476827570019e-05,
|
3067 |
+
"loss": 0.3282,
|
3068 |
+
"step": 255000
|
3069 |
}
|
3070 |
],
|
3071 |
"max_steps": 500000,
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 201355195
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b1420ef536f29364736b64e6b013986d649ee5c16564b6e00d08c0b954558aad
|
3 |
size 201355195
|