Commit
•
de2b622
1
Parent(s):
bcb5c90
Training in progress, step 4000
Browse files- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/pytorch_model.bin +1 -1
- last-checkpoint/rng_state.pth +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +23 -3
- pytorch_model.bin +1 -1
- runs/Mar24_13-56-57_9891ffea5fdc/events.out.tfevents.1679666221.9891ffea5fdc.675.0 +2 -2
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 2847145157
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:62ebe265f64586ab183a0f3ded81debf7b2736596b5d3ed604eee5b45197aefd
|
3 |
size 2847145157
|
last-checkpoint/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1524261149
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:39ff2671ea9bc83fd28c5f7f82e369e3bfff0febf85fca50e35fe4a7bbec491f
|
3 |
size 1524261149
|
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 sha256:355721a0bbb5143f756b62c87bd4f1ecc862046d0b4ebd17b9aaaae29ad770aa
|
3 |
size 14575
|
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:af5ffbb60bcf2bcde1e6a5b036c754d8f1b8aa1c57c83e30f0d7246ed6db381b
|
3 |
size 627
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch":
|
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": 15.676,
|
67 |
"eval_steps_per_second": 2.614,
|
68 |
"step": 3000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
69 |
}
|
70 |
],
|
71 |
"max_steps": 9995,
|
72 |
"num_train_epochs": 5,
|
73 |
-
"total_flos":
|
74 |
"trial_name": null,
|
75 |
"trial_params": null
|
76 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 2.001000500250125,
|
5 |
+
"global_step": 4000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
66 |
"eval_samples_per_second": 15.676,
|
67 |
"eval_steps_per_second": 2.614,
|
68 |
"step": 3000
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 1.75,
|
72 |
+
"learning_rate": 1.2996498249124563e-05,
|
73 |
+
"loss": 3.0252,
|
74 |
+
"step": 3500
|
75 |
+
},
|
76 |
+
{
|
77 |
+
"epoch": 2.0,
|
78 |
+
"learning_rate": 1.19959979989995e-05,
|
79 |
+
"loss": 3.0156,
|
80 |
+
"step": 4000
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 2.0,
|
84 |
+
"eval_loss": 3.0884268283843994,
|
85 |
+
"eval_runtime": 135.2307,
|
86 |
+
"eval_samples_per_second": 15.655,
|
87 |
+
"eval_steps_per_second": 2.61,
|
88 |
+
"step": 4000
|
89 |
}
|
90 |
],
|
91 |
"max_steps": 9995,
|
92 |
"num_train_epochs": 5,
|
93 |
+
"total_flos": 1.131853971456e+16,
|
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 1524261149
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:39ff2671ea9bc83fd28c5f7f82e369e3bfff0febf85fca50e35fe4a7bbec491f
|
3 |
size 1524261149
|
runs/Mar24_13-56-57_9891ffea5fdc/events.out.tfevents.1679666221.9891ffea5fdc.675.0
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bacf641203e79ee4bdfa0d2056acf0d7791edff24ea26aeac7a8a7ab58a77b1c
|
3 |
+
size 6495
|