Training in progress, step 2000
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 484015877
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ac9be1851d65c933b7df18eb2598af95761916b0452ddb06e81bc6019ee4aaa3
|
3 |
size 484015877
|
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 sha256:8a2e10ed5cdaff6f3b984879342cc4b4ed1ec68389e993b3b2415fd84410e5bd
|
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 sha256:1515038a3750a082fe43582d81ae01e0e929d02a90dbd2b2a2db82ae50b60938
|
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 sha256:30c5bbe7039a98199ba21ef040f9c1afa7247704578d4073dec2220319914364
|
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:f380f7c1d04e6f53aaea8030db0857aeddd02fa8a9eb1ce68514bd4a8b17ea4c
|
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,
|
@@ -66,11 +66,31 @@
|
|
66 |
"eval_samples_per_second": 36.226,
|
67 |
"eval_steps_per_second": 1.811,
|
68 |
"step": 1500
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
69 |
}
|
70 |
],
|
71 |
"max_steps": 15000,
|
72 |
"num_train_epochs": 3,
|
73 |
-
"total_flos":
|
74 |
"trial_name": null,
|
75 |
"trial_params": null
|
76 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.5495869647995661,
|
3 |
+
"best_model_checkpoint": "results/checkpoint-2000",
|
4 |
+
"epoch": 0.4,
|
5 |
+
"global_step": 2000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
66 |
"eval_samples_per_second": 36.226,
|
67 |
"eval_steps_per_second": 1.811,
|
68 |
"step": 1500
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 0.4,
|
72 |
+
"learning_rate": 9.126315789473685e-05,
|
73 |
+
"loss": 0.7745,
|
74 |
+
"step": 2000
|
75 |
+
},
|
76 |
+
{
|
77 |
+
"epoch": 0.4,
|
78 |
+
"eval_bleu": 0.11999069408174769,
|
79 |
+
"eval_exact_match": 0.152,
|
80 |
+
"eval_loss": 0.8501775860786438,
|
81 |
+
"eval_rouge1": 0.5495869647995661,
|
82 |
+
"eval_rouge2": 0.37385624817390106,
|
83 |
+
"eval_rougeL": 0.5307934771920211,
|
84 |
+
"eval_rougeLsum": 0.5391651788581161,
|
85 |
+
"eval_runtime": 56.8684,
|
86 |
+
"eval_samples_per_second": 35.169,
|
87 |
+
"eval_steps_per_second": 1.758,
|
88 |
+
"step": 2000
|
89 |
}
|
90 |
],
|
91 |
"max_steps": 15000,
|
92 |
"num_train_epochs": 3,
|
93 |
+
"total_flos": 5140995336437760.0,
|
94 |
"trial_name": null,
|
95 |
"trial_params": null
|
96 |
}
|
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 sha256:8a2e10ed5cdaff6f3b984879342cc4b4ed1ec68389e993b3b2415fd84410e5bd
|
3 |
size 242014297
|