Training in progress, step 250, checkpoint
Browse files
last-checkpoint/adapter_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 109098378
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d34c8a9ca283ae7e0e8084e1fced24b888d6df8ef82671f5afbeb990470308ed
|
3 |
size 109098378
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 218182458
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8a1a95a044de08d70ea794b0233eced1293718590dfa14bbc2d68daf6f58b771
|
3 |
size 218182458
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14244
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e75328e6be212481706506b053c5861a3db0b31645c20ab87d116a258a9a5452
|
3 |
size 14244
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1064
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6088f970b1f0429ad85e576795204ef9269ce142d6ce9c2595b5649efde833b6
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch": 1.
|
5 |
"eval_steps": 500,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -55,13 +55,25 @@
|
|
55 |
"learning_rate": 2.03365443542764e-05,
|
56 |
"loss": 0.5387,
|
57 |
"step": 200
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
58 |
}
|
59 |
],
|
60 |
"logging_steps": 25,
|
61 |
"max_steps": 250,
|
62 |
"num_train_epochs": 2,
|
63 |
"save_steps": 50,
|
64 |
-
"total_flos": 1.
|
65 |
"trial_name": null,
|
66 |
"trial_params": null
|
67 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.3020833333333333,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 250,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
55 |
"learning_rate": 2.03365443542764e-05,
|
56 |
"loss": 0.5387,
|
57 |
"step": 200
|
58 |
+
},
|
59 |
+
{
|
60 |
+
"epoch": 1.17,
|
61 |
+
"learning_rate": 5.22039891260262e-06,
|
62 |
+
"loss": 0.5375,
|
63 |
+
"step": 225
|
64 |
+
},
|
65 |
+
{
|
66 |
+
"epoch": 1.3,
|
67 |
+
"learning_rate": 0.0,
|
68 |
+
"loss": 0.4968,
|
69 |
+
"step": 250
|
70 |
}
|
71 |
],
|
72 |
"logging_steps": 25,
|
73 |
"max_steps": 250,
|
74 |
"num_train_epochs": 2,
|
75 |
"save_steps": 50,
|
76 |
+
"total_flos": 1.37971841206272e+16,
|
77 |
"trial_name": null,
|
78 |
"trial_params": null
|
79 |
}
|