Training in progress, step 606000
Browse files- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/pytorch_model.bin +1 -1
- last-checkpoint/rng_state.pth +1 -1
- last-checkpoint/scaler.pt +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +39 -3
- last-checkpoint/training_args.bin +1 -1
- pytorch_model.bin +1 -1
- runs/Jun02_06-43-44_462ae3634d0f/1685689892.9804766/events.out.tfevents.1685689892.462ae3634d0f.537.1 +3 -0
- runs/Jun02_06-43-44_462ae3634d0f/events.out.tfevents.1685689892.462ae3634d0f.537.0 +3 -0
- training_args.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 3871544599
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a2d13d3a12cef582c6306a6caa2fcae2d260daa2ce07ccac6ed48930f9cb6fdb
|
3 |
size 3871544599
|
last-checkpoint/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1944201353
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ad629b28773c7d820cfd6cde21a45838352b203d77f81ab45ec65bbf2a2e4793
|
3 |
size 1944201353
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14575
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:161e17574a92f1e0eeb7c285fb40aa9725819ba6b13e4b03c177fbed941b28b1
|
3 |
size 14575
|
last-checkpoint/scaler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 557
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ea47bb5de10b32c753f83940ad7300fc4ab1482efe55c583eab8fc11abb582dd
|
3 |
size 557
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 627
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f0f5062102497ed59689dc2acf1b55f8405676119f0a4dbdf1ab2c4539860273
|
3 |
size 627
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch": 15.
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -7242,11 +7242,47 @@
|
|
7242 |
"learning_rate": 5.244509613783047e-07,
|
7243 |
"loss": 1.0278,
|
7244 |
"step": 603000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
7245 |
}
|
7246 |
],
|
7247 |
"max_steps": 762960,
|
7248 |
"num_train_epochs": 20,
|
7249 |
-
"total_flos": 7.
|
7250 |
"trial_name": null,
|
7251 |
"trial_params": null
|
7252 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 15.885489299682293,
|
5 |
+
"global_step": 606000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
7242 |
"learning_rate": 5.244509613783047e-07,
|
7243 |
"loss": 1.0278,
|
7244 |
"step": 603000
|
7245 |
+
},
|
7246 |
+
{
|
7247 |
+
"epoch": 15.82,
|
7248 |
+
"learning_rate": 5.213009179600098e-07,
|
7249 |
+
"loss": 1.0296,
|
7250 |
+
"step": 603500
|
7251 |
+
},
|
7252 |
+
{
|
7253 |
+
"epoch": 15.83,
|
7254 |
+
"learning_rate": 5.181592617188188e-07,
|
7255 |
+
"loss": 1.0337,
|
7256 |
+
"step": 604000
|
7257 |
+
},
|
7258 |
+
{
|
7259 |
+
"epoch": 15.85,
|
7260 |
+
"learning_rate": 5.15026005971374e-07,
|
7261 |
+
"loss": 1.0203,
|
7262 |
+
"step": 604500
|
7263 |
+
},
|
7264 |
+
{
|
7265 |
+
"epoch": 15.86,
|
7266 |
+
"learning_rate": 5.11901163998709e-07,
|
7267 |
+
"loss": 1.0221,
|
7268 |
+
"step": 605000
|
7269 |
+
},
|
7270 |
+
{
|
7271 |
+
"epoch": 15.87,
|
7272 |
+
"learning_rate": 5.087847490461962e-07,
|
7273 |
+
"loss": 1.0322,
|
7274 |
+
"step": 605500
|
7275 |
+
},
|
7276 |
+
{
|
7277 |
+
"epoch": 15.89,
|
7278 |
+
"learning_rate": 5.056767743234853e-07,
|
7279 |
+
"loss": 1.0341,
|
7280 |
+
"step": 606000
|
7281 |
}
|
7282 |
],
|
7283 |
"max_steps": 762960,
|
7284 |
"num_train_epochs": 20,
|
7285 |
+
"total_flos": 7.235421273337283e+17,
|
7286 |
"trial_name": null,
|
7287 |
"trial_params": null
|
7288 |
}
|
last-checkpoint/training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 3771
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b5a7858cb286d248a8d1b95c7338f74eac69d03a9b32f71567312088ea225a92
|
3 |
size 3771
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1944201353
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ad629b28773c7d820cfd6cde21a45838352b203d77f81ab45ec65bbf2a2e4793
|
3 |
size 1944201353
|
runs/Jun02_06-43-44_462ae3634d0f/1685689892.9804766/events.out.tfevents.1685689892.462ae3634d0f.537.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:09bed91ee67bc7e04fb9ae37b1ee1b02ac0900ba87ba0f4ca826410e0e0424cd
|
3 |
+
size 6184
|
runs/Jun02_06-43-44_462ae3634d0f/events.out.tfevents.1685689892.462ae3634d0f.537.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7dac55232b8f02f23a2984eba211d762b5bd404b554b36751e4f3a41f8135caf
|
3 |
+
size 5421
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 3771
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b5a7858cb286d248a8d1b95c7338f74eac69d03a9b32f71567312088ea225a92
|
3 |
size 3771
|