Training in progress, step 4500
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 sha256:3f75ac877806bdda46d65566d3957dddcc9415756173fa9fc7fe1d031896944b
|
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:c13bf842e372f6ee30baca222d735de2443a391bef6b56c9b7d392fc1bfa1f61
|
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:ccbe618bcc7ec2550fc77b5e673c6ace2a4616a6776e76079284186e6c26c77d
|
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 sha256:09b9cf6dcc5edbdfa3f0b240eb508579ceebfa52734c1be448b8d8706adc5830
|
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 sha256:4626d25eb8afc03ffccf06f99844eda74479e90df1b9c48999b8df023fed3c4a
|
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,
|
@@ -158,11 +158,30 @@
|
|
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.
|
166 |
"trial_name": null,
|
167 |
"trial_params": null
|
168 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.8396906852722168,
|
3 |
+
"best_model_checkpoint": "/home2/s5431786/jb-internship/results/t5-small-CodeXGLUE-CONCODE-faster/checkpoint-4500",
|
4 |
+
"epoch": 1.44,
|
5 |
+
"global_step": 4500,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
158 |
"eval_samples_per_second": 57.091,
|
159 |
"eval_steps_per_second": 1.798,
|
160 |
"step": 4000
|
161 |
+
},
|
162 |
+
{
|
163 |
+
"epoch": 1.44,
|
164 |
+
"learning_rate": 0.0004884463157894737,
|
165 |
+
"loss": 0.7742,
|
166 |
+
"step": 4500
|
167 |
+
},
|
168 |
+
{
|
169 |
+
"epoch": 1.44,
|
170 |
+
"eval_bleu": 0.060679509741740224,
|
171 |
+
"eval_exact_match": 0.091,
|
172 |
+
"eval_loss": 0.8396906852722168,
|
173 |
+
"eval_rouge1": 0.48584317956376577,
|
174 |
+
"eval_rouge2": 0.31707363805938765,
|
175 |
+
"eval_rougeL": 0.47246293765798464,
|
176 |
+
"eval_runtime": 35.6286,
|
177 |
+
"eval_samples_per_second": 56.135,
|
178 |
+
"eval_steps_per_second": 1.768,
|
179 |
+
"step": 4500
|
180 |
}
|
181 |
],
|
182 |
"max_steps": 62500,
|
183 |
"num_train_epochs": 20,
|
184 |
+
"total_flos": 1.8861842491244544e+16,
|
185 |
"trial_name": null,
|
186 |
"trial_params": null
|
187 |
}
|
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:c13bf842e372f6ee30baca222d735de2443a391bef6b56c9b7d392fc1bfa1f61
|
3 |
size 242031355
|