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 +51 -3
- pytorch_model.bin +1 -1
- runs/Jun16_09-47-04_1a3b54f65ca2/events.out.tfevents.1686908851.1a3b54f65ca2.10028.0 +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 3871543575
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:96559e121960210b371c3fcc350fdad69dc4bebab11e0e85ac5587d763377e3f
|
3 |
size 3871543575
|
last-checkpoint/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1944201353
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:57c726760f8cdd1ac918cb7b580cc42cc2847406cb9b68f2a0b2c79df0062d1b
|
3 |
size 1944201353
|
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:ea2fc25e8860dfffb4f2ed8f3fbd28f04f1afe41b93499531ba6c38f0c37deb4
|
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 sha256:3d79de33a1dadebecdc6710fbbebc54394b36ff40dc16ce7c4b9cd325b8d41b2
|
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:f8b7f7dd47f8776cb11bf81d14503503a8691f27074ccc97afc806b0f50fc73d
|
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": 0.
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -54,11 +54,59 @@
|
|
54 |
"learning_rate": 4.8657157740444606e-05,
|
55 |
"loss": 1.4518,
|
56 |
"step": 4000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
57 |
}
|
58 |
],
|
59 |
"max_steps": 38148,
|
60 |
"num_train_epochs": 1,
|
61 |
-
"total_flos":
|
62 |
"trial_name": null,
|
63 |
"trial_params": null
|
64 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.20970735338834656,
|
5 |
+
"global_step": 8000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
54 |
"learning_rate": 4.8657157740444606e-05,
|
55 |
"loss": 1.4518,
|
56 |
"step": 4000
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 0.12,
|
60 |
+
"learning_rate": 4.830436051991575e-05,
|
61 |
+
"loss": 1.471,
|
62 |
+
"step": 4500
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 0.13,
|
66 |
+
"learning_rate": 4.791205648303775e-05,
|
67 |
+
"loss": 1.4848,
|
68 |
+
"step": 5000
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 0.14,
|
72 |
+
"learning_rate": 4.7480910684898666e-05,
|
73 |
+
"loss": 1.4828,
|
74 |
+
"step": 5500
|
75 |
+
},
|
76 |
+
{
|
77 |
+
"epoch": 0.16,
|
78 |
+
"learning_rate": 4.7011654027247644e-05,
|
79 |
+
"loss": 1.4773,
|
80 |
+
"step": 6000
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 0.17,
|
84 |
+
"learning_rate": 4.650508201943061e-05,
|
85 |
+
"loss": 1.4821,
|
86 |
+
"step": 6500
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.18,
|
90 |
+
"learning_rate": 4.5962053429799665e-05,
|
91 |
+
"loss": 1.5051,
|
92 |
+
"step": 7000
|
93 |
+
},
|
94 |
+
{
|
95 |
+
"epoch": 0.2,
|
96 |
+
"learning_rate": 4.5383488829882384e-05,
|
97 |
+
"loss": 1.4952,
|
98 |
+
"step": 7500
|
99 |
+
},
|
100 |
+
{
|
101 |
+
"epoch": 0.21,
|
102 |
+
"learning_rate": 4.477036903377901e-05,
|
103 |
+
"loss": 1.4986,
|
104 |
+
"step": 8000
|
105 |
}
|
106 |
],
|
107 |
"max_steps": 38148,
|
108 |
"num_train_epochs": 1,
|
109 |
+
"total_flos": 8864585817513984.0,
|
110 |
"trial_name": null,
|
111 |
"trial_params": null
|
112 |
}
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1944201353
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:57c726760f8cdd1ac918cb7b580cc42cc2847406cb9b68f2a0b2c79df0062d1b
|
3 |
size 1944201353
|
runs/Jun16_09-47-04_1a3b54f65ca2/events.out.tfevents.1686908851.1a3b54f65ca2.10028.0
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 sha256:99a357266e63efac109efc4f27c9701e51837c5f584c4f5ea21dfd3f62d8d36f
|
3 |
+
size 6974
|