Training in progress, step 4000
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 sha256:3d9bb0c4572aa048453edc5b3e528fb13b78d4939175b9071dbcb82dd18de2b0
|
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:f06bd89414679587b23c8c150a916f737df0a8f483147e1d1d3532b3fe84b925
|
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 sha256:76522e532213df53c6933f87fbd2a0bc1a5e885cf404fa37f65916dd977640df
|
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 sha256:3f5d4dee40cfdc437b23430962db3ffac5d9e7825456eeafc215d73e6521854a
|
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 sha256:0eca0ffdbfafa504a95809f9d2787e96fed3e21281bcfcdf852530a76db7c720
|
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": 1.
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -139,11 +139,30 @@
|
|
139 |
"eval_samples_per_second": 55.587,
|
140 |
"eval_steps_per_second": 1.751,
|
141 |
"step": 3500
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
142 |
}
|
143 |
],
|
144 |
"max_steps": 62500,
|
145 |
"num_train_epochs": 20,
|
146 |
-
"total_flos": 1.
|
147 |
"trial_name": null,
|
148 |
"trial_params": null
|
149 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.8577723503112793,
|
3 |
+
"best_model_checkpoint": "/home2/s5431786/jb-internship/results/t5-small-CodeXGLUE-CONCODE-faster/checkpoint-4000",
|
4 |
+
"epoch": 1.28,
|
5 |
+
"global_step": 4000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
139 |
"eval_samples_per_second": 55.587,
|
140 |
"eval_steps_per_second": 1.751,
|
141 |
"step": 3500
|
142 |
+
},
|
143 |
+
{
|
144 |
+
"epoch": 1.28,
|
145 |
+
"learning_rate": 0.0004926568421052632,
|
146 |
+
"loss": 0.8077,
|
147 |
+
"step": 4000
|
148 |
+
},
|
149 |
+
{
|
150 |
+
"epoch": 1.28,
|
151 |
+
"eval_bleu": 0.060850014141887766,
|
152 |
+
"eval_exact_match": 0.088,
|
153 |
+
"eval_loss": 0.8577723503112793,
|
154 |
+
"eval_rouge1": 0.4857568042531289,
|
155 |
+
"eval_rouge2": 0.3123549789085296,
|
156 |
+
"eval_rougeL": 0.47152130323710484,
|
157 |
+
"eval_runtime": 35.0315,
|
158 |
+
"eval_samples_per_second": 57.091,
|
159 |
+
"eval_steps_per_second": 1.798,
|
160 |
+
"step": 4000
|
161 |
}
|
162 |
],
|
163 |
"max_steps": 62500,
|
164 |
"num_train_epochs": 20,
|
165 |
+
"total_flos": 1.6762623479513088e+16,
|
166 |
"trial_name": null,
|
167 |
"trial_params": null
|
168 |
}
|
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:f06bd89414679587b23c8c150a916f737df0a8f483147e1d1d3532b3fe84b925
|
3 |
size 242031355
|