Training in progress, step 8000
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 484059375
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:15d783de33996b26c84656c603b415b9054533f27c99dbac69fec1ace56b4aa5
|
3 |
size 484059375
|
last-checkpoint/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 242019067
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ca3baffeb398f1ac10a744d6085595df6f612e2d89c8fc0d14130375d0b5703d
|
3 |
size 242019067
|
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 sha256:74337421f4b5deb1fbf3656c17edbeea4392fd1faacddd4865ca0c1f1ab5aa2b
|
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 sha256:71e4ed352775c3fc23aad60491c42f0b0b2708e2318db50a0c3bf3cdb2897ce5
|
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 sha256:3849f378935585d785bef6e2600507ce25ea95df3ee403e380f0e75ea74999f2
|
3 |
size 623
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"best_metric": 1.528552770614624,
|
3 |
"best_model_checkpoint": "/home2/s5431786/jb-internship-repr/results/Salesforce-codet5-small-java-small-selected-wo-tokens/checkpoint-2000",
|
4 |
-
"epoch":
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -60,11 +60,29 @@
|
|
60 |
"eval_samples_per_second": 145.441,
|
61 |
"eval_steps_per_second": 1.519,
|
62 |
"step": 6000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
63 |
}
|
64 |
],
|
65 |
"max_steps": 36045,
|
66 |
"num_train_epochs": 5,
|
67 |
-
"total_flos":
|
68 |
"trial_name": null,
|
69 |
"trial_params": null
|
70 |
}
|
|
|
1 |
{
|
2 |
"best_metric": 1.528552770614624,
|
3 |
"best_model_checkpoint": "/home2/s5431786/jb-internship-repr/results/Salesforce-codet5-small-java-small-selected-wo-tokens/checkpoint-2000",
|
4 |
+
"epoch": 1.1097239561659038,
|
5 |
+
"global_step": 8000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
60 |
"eval_samples_per_second": 145.441,
|
61 |
"eval_steps_per_second": 1.519,
|
62 |
"step": 6000
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 1.11,
|
66 |
+
"learning_rate": 8.191402371356814e-05,
|
67 |
+
"loss": 1.1145,
|
68 |
+
"step": 8000
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 1.11,
|
72 |
+
"eval_exact_match": 0.31735447072638817,
|
73 |
+
"eval_loss": 1.572016954421997,
|
74 |
+
"eval_rouge1": 0.5094747473558878,
|
75 |
+
"eval_rouge2": 0.2465356707776194,
|
76 |
+
"eval_rougeL": 0.5091592701411148,
|
77 |
+
"eval_runtime": 163.415,
|
78 |
+
"eval_samples_per_second": 145.911,
|
79 |
+
"eval_steps_per_second": 1.524,
|
80 |
+
"step": 8000
|
81 |
}
|
82 |
],
|
83 |
"max_steps": 36045,
|
84 |
"num_train_epochs": 5,
|
85 |
+
"total_flos": 1.0393032276836352e+17,
|
86 |
"trial_name": null,
|
87 |
"trial_params": null
|
88 |
}
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 242019067
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ca3baffeb398f1ac10a744d6085595df6f612e2d89c8fc0d14130375d0b5703d
|
3 |
size 242019067
|