Training in progress, step 6000
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 +21 -3
- 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 484079855
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d0ce376bb4663e22bb24032c497df139213155fd38ac787511a8d6de77f9b0e3
|
3 |
size 484079855
|
last-checkpoint/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 242029307
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:964c436b5e8fe2f922420894007a8b020447707a82e3a5d089242a95d125ac24
|
3 |
size 242029307
|
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 sha256:4a56645fe7a8c3cb584f676124d1e5983c030565c5653fefe439165b4b96882e
|
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 sha256:44982b6f8c2a6554bfd4edbc526e12d694da46eef7fe13cebfe72952cb5552d2
|
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 sha256:06c999c90bc9661947c1fcbb4229037965a547bc08095288b0e683aeeabdf8cc
|
3 |
size 623
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"best_metric": 1.5166430473327637,
|
3 |
"best_model_checkpoint": "/home2/s5431786/jb-internship-repr/results/Salesforce-codet5-small-java-small-selected/checkpoint-2000",
|
4 |
-
"epoch": 0.
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -42,11 +42,29 @@
|
|
42 |
"eval_samples_per_second": 146.665,
|
43 |
"eval_steps_per_second": 1.532,
|
44 |
"step": 4000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
45 |
}
|
46 |
],
|
47 |
"max_steps": 72090,
|
48 |
"num_train_epochs": 10,
|
49 |
-
"total_flos":
|
50 |
"trial_name": null,
|
51 |
"trial_params": null
|
52 |
}
|
|
|
1 |
{
|
2 |
"best_metric": 1.5166430473327637,
|
3 |
"best_model_checkpoint": "/home2/s5431786/jb-internship-repr/results/Salesforce-codet5-small-java-small-selected/checkpoint-2000",
|
4 |
+
"epoch": 0.8322929671244278,
|
5 |
+
"global_step": 6000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
42 |
"eval_samples_per_second": 146.665,
|
43 |
"eval_steps_per_second": 1.532,
|
44 |
"step": 4000
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.83,
|
48 |
+
"learning_rate": 9.651018471198073e-05,
|
49 |
+
"loss": 1.2334,
|
50 |
+
"step": 6000
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 0.83,
|
54 |
+
"eval_exact_match": 0.3253648716658279,
|
55 |
+
"eval_loss": 1.5264997482299805,
|
56 |
+
"eval_rouge1": 0.531867219960122,
|
57 |
+
"eval_rouge2": 0.25865030861885435,
|
58 |
+
"eval_rougeL": 0.5313541147701524,
|
59 |
+
"eval_runtime": 167.7297,
|
60 |
+
"eval_samples_per_second": 142.157,
|
61 |
+
"eval_steps_per_second": 1.485,
|
62 |
+
"step": 6000
|
63 |
}
|
64 |
],
|
65 |
"max_steps": 72090,
|
66 |
"num_train_epochs": 10,
|
67 |
+
"total_flos": 7.7956877647872e+16,
|
68 |
"trial_name": null,
|
69 |
"trial_params": null
|
70 |
}
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 242029307
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:964c436b5e8fe2f922420894007a8b020447707a82e3a5d089242a95d125ac24
|
3 |
size 242029307
|