Training in progress, step 1500, checkpoint
Browse files
last-checkpoint/model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 241984552
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:782341ed4d6165e7fd8d209d7ad03cc24ce52fb33f692e3081a749d4315a7e85
|
3 |
size 241984552
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 121457978
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:afd1f4d76a2addd80e3181d89997df1a58f9ffb4b1c52e20f08010d329c6795b
|
3 |
size 121457978
|
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:ee6cda819c1a2323b565772a3d94d91eb65d9dab5b45edbec9696014f83fdabe
|
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 sha256:71b08411cb0eb53e0a8c7df5f16ee6389613ee5ab9806db0b3a1d1ceeab83e1e
|
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": 0.
|
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,
|
@@ -21,6 +21,13 @@
|
|
21 |
"learning_rate": 9.543691535477983e-05,
|
22 |
"loss": 0.9848,
|
23 |
"step": 1000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
24 |
}
|
25 |
],
|
26 |
"logging_steps": 500,
|
@@ -28,7 +35,7 @@
|
|
28 |
"num_input_tokens_seen": 0,
|
29 |
"num_train_epochs": 5,
|
30 |
"save_steps": 500,
|
31 |
-
"total_flos":
|
32 |
"train_batch_size": 12,
|
33 |
"trial_name": null,
|
34 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.34223134839151265,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 1500,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
21 |
"learning_rate": 9.543691535477983e-05,
|
22 |
"loss": 0.9848,
|
23 |
"step": 1000
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.34223134839151265,
|
27 |
+
"grad_norm": 1.83408522605896,
|
28 |
+
"learning_rate": 9.315537303216974e-05,
|
29 |
+
"loss": 0.9081,
|
30 |
+
"step": 1500
|
31 |
}
|
32 |
],
|
33 |
"logging_steps": 500,
|
|
|
35 |
"num_input_tokens_seen": 0,
|
36 |
"num_train_epochs": 5,
|
37 |
"save_steps": 500,
|
38 |
+
"total_flos": 2436152426496000.0,
|
39 |
"train_batch_size": 12,
|
40 |
"trial_name": null,
|
41 |
"trial_params": null
|