Training in progress, step 6500
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 +24 -5
- 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 484083951
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0df1e40f0a3e4aa6b7e5637575d0bf27826a7fb14b9622d96fff945e88792b6b
|
3 |
size 484083951
|
last-checkpoint/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 242031355
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9b622799c58cde8037bef34ba3162410fda8a345b825478083acc7068d8dac30
|
3 |
size 242031355
|
last-checkpoint/rng_state.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 sha256:59d837eb699b59ff5031bafdda4db4633d2a8b99a6ffa74717cabd5435d47538
|
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 sha256:2a2f43181016c74e374587ce9bda86ea94787b02b5dde0828a297741caa5f1dc
|
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 sha256:3a0515fb0c60a948d2994b5716e10d7ae64ebf63a3cec8321d099ceeda82556d
|
3 |
size 623
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
-
"best_metric": 0.
|
3 |
-
"best_model_checkpoint": "/home2/s5431786/jb-internship/results/t5-small-CodeXGLUE-CONCODE-faster/checkpoint-
|
4 |
-
"epoch":
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -234,11 +234,30 @@
|
|
234 |
"eval_samples_per_second": 55.668,
|
235 |
"eval_steps_per_second": 1.754,
|
236 |
"step": 6000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
237 |
}
|
238 |
],
|
239 |
"max_steps": 62500,
|
240 |
"num_train_epochs": 20,
|
241 |
-
"total_flos": 2.
|
242 |
"trial_name": null,
|
243 |
"trial_params": null
|
244 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.7727072834968567,
|
3 |
+
"best_model_checkpoint": "/home2/s5431786/jb-internship/results/t5-small-CodeXGLUE-CONCODE-faster/checkpoint-6500",
|
4 |
+
"epoch": 2.08,
|
5 |
+
"global_step": 6500,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
234 |
"eval_samples_per_second": 55.668,
|
235 |
"eval_steps_per_second": 1.754,
|
236 |
"step": 6000
|
237 |
+
},
|
238 |
+
{
|
239 |
+
"epoch": 2.08,
|
240 |
+
"learning_rate": 0.0004716042105263158,
|
241 |
+
"loss": 0.6778,
|
242 |
+
"step": 6500
|
243 |
+
},
|
244 |
+
{
|
245 |
+
"epoch": 2.08,
|
246 |
+
"eval_bleu": 0.06526774731233032,
|
247 |
+
"eval_exact_match": 0.097,
|
248 |
+
"eval_loss": 0.7727072834968567,
|
249 |
+
"eval_rouge1": 0.5015386585306862,
|
250 |
+
"eval_rouge2": 0.3327019592611423,
|
251 |
+
"eval_rougeL": 0.4858921391142662,
|
252 |
+
"eval_runtime": 36.8788,
|
253 |
+
"eval_samples_per_second": 54.232,
|
254 |
+
"eval_steps_per_second": 1.708,
|
255 |
+
"step": 6500
|
256 |
}
|
257 |
],
|
258 |
"max_steps": 62500,
|
259 |
"num_train_epochs": 20,
|
260 |
+
"total_flos": 2.723088888024269e+16,
|
261 |
"trial_name": null,
|
262 |
"trial_params": null
|
263 |
}
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 242031355
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9b622799c58cde8037bef34ba3162410fda8a345b825478083acc7068d8dac30
|
3 |
size 242031355
|