Training in progress, step 2500
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 +25 -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 838981
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3fc08dc99be75f1c94b73b8852ff9a8fc5842a49f19be7d629b458a9fb1850e0
|
3 |
size 838981
|
last-checkpoint/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 242014297
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2ff97ccc944d3a7d113d83dc77a6803bfb2b346243a2c583fcfd6299ec6b2dee
|
3 |
size 242014297
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14575
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6270ad342856a44bfc69ae067667c0aa9e39cf62a7ef48fd011fa5833882d18c
|
3 |
size 14575
|
last-checkpoint/scaler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 557
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0edb03ffaa7f1e13c55584177e3099b63577282f5098a3638681257f2d51ed39
|
3 |
size 557
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 627
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f379486ceb3fb849525dba52ed4ad9a3e41cbb661ec1dc05803f28a51cde0e8e
|
3 |
size 627
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
-
"best_metric": 0.
|
3 |
-
"best_model_checkpoint": "results/checkpoint-
|
4 |
-
"epoch": 0.
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -86,11 +86,31 @@
|
|
86 |
"eval_samples_per_second": 35.012,
|
87 |
"eval_steps_per_second": 1.751,
|
88 |
"step": 2000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
89 |
}
|
90 |
],
|
91 |
"max_steps": 15000,
|
92 |
"num_train_epochs": 3,
|
93 |
-
"total_flos":
|
94 |
"trial_name": null,
|
95 |
"trial_params": null
|
96 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.5561456362247019,
|
3 |
+
"best_model_checkpoint": "results/checkpoint-2500",
|
4 |
+
"epoch": 0.5,
|
5 |
+
"global_step": 2500,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
86 |
"eval_samples_per_second": 35.012,
|
87 |
"eval_steps_per_second": 1.751,
|
88 |
"step": 2000
|
89 |
+
},
|
90 |
+
{
|
91 |
+
"epoch": 0.5,
|
92 |
+
"learning_rate": 8.77543859649123e-05,
|
93 |
+
"loss": 0.7462,
|
94 |
+
"step": 2500
|
95 |
+
},
|
96 |
+
{
|
97 |
+
"epoch": 0.5,
|
98 |
+
"eval_bleu": 0.12237729595577906,
|
99 |
+
"eval_exact_match": 0.1455,
|
100 |
+
"eval_loss": 0.8430227637290955,
|
101 |
+
"eval_rouge1": 0.5561456362247019,
|
102 |
+
"eval_rouge2": 0.37889989269496904,
|
103 |
+
"eval_rougeL": 0.5365796163245027,
|
104 |
+
"eval_rougeLsum": 0.544772047797109,
|
105 |
+
"eval_runtime": 55.5277,
|
106 |
+
"eval_samples_per_second": 36.018,
|
107 |
+
"eval_steps_per_second": 1.801,
|
108 |
+
"step": 2500
|
109 |
}
|
110 |
],
|
111 |
"max_steps": 15000,
|
112 |
"num_train_epochs": 3,
|
113 |
+
"total_flos": 6418569074442240.0,
|
114 |
"trial_name": null,
|
115 |
"trial_params": null
|
116 |
}
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 242014297
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2ff97ccc944d3a7d113d83dc77a6803bfb2b346243a2c583fcfd6299ec6b2dee
|
3 |
size 242014297
|