Upload folder using huggingface_hub
Browse files- model.safetensors +1 -1
- optimizer.pt +1 -1
- rng_state.pth +1 -1
- scheduler.pt +1 -1
- tokenizer.json +6 -1
- trainer_state.json +11 -11
- training_args.bin +1 -1
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 497789648
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6383ee5fbfb64d0b4cf03a4a9f2bc7be2c4e4f7323fe11e965da64f58f8899d1
|
3 |
size 497789648
|
optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 995673413
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7cf5857a72daa729e108302467f15291195ea115fb9fb143e3ccc7a0178553dd
|
3 |
size 995673413
|
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:b047f1373b87ecaa30f436b1ffebb9f5272b1851a2b56ec4eeff538120122c56
|
3 |
size 14575
|
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 sha256:25691735045c5749946dfe06471e1c5eb87438b273847d8c5a01062be5dc2158
|
3 |
size 627
|
tokenizer.json
CHANGED
@@ -1,6 +1,11 @@
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
-
"truncation":
|
|
|
|
|
|
|
|
|
|
|
4 |
"padding": null,
|
5 |
"added_tokens": [
|
6 |
{
|
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
+
"truncation": {
|
4 |
+
"direction": "Right",
|
5 |
+
"max_length": 1024,
|
6 |
+
"strategy": "LongestFirst",
|
7 |
+
"stride": 0
|
8 |
+
},
|
9 |
"padding": null,
|
10 |
"added_tokens": [
|
11 |
{
|
trainer_state.json
CHANGED
@@ -1,29 +1,29 @@
|
|
1 |
{
|
2 |
-
"best_metric": 1.
|
3 |
-
"best_model_checkpoint": "sean_test_out/checkpoint-
|
4 |
"epoch": 1.0,
|
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,
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 1.0,
|
13 |
-
"eval_accuracy": 0.
|
14 |
-
"eval_loss": 1.
|
15 |
-
"eval_runtime":
|
16 |
-
"eval_samples_per_second":
|
17 |
-
"eval_steps_per_second": 7.
|
18 |
-
"step":
|
19 |
}
|
20 |
],
|
21 |
"logging_steps": 500,
|
22 |
-
"max_steps":
|
23 |
"num_input_tokens_seen": 0,
|
24 |
"num_train_epochs": 1,
|
25 |
"save_steps": 500,
|
26 |
-
"total_flos":
|
27 |
"train_batch_size": 24,
|
28 |
"trial_name": null,
|
29 |
"trial_params": null
|
|
|
1 |
{
|
2 |
+
"best_metric": 1.2284976243972778,
|
3 |
+
"best_model_checkpoint": "sean_test_out/checkpoint-84",
|
4 |
"epoch": 1.0,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 84,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 1.0,
|
13 |
+
"eval_accuracy": 0.4164,
|
14 |
+
"eval_loss": 1.2284976243972778,
|
15 |
+
"eval_runtime": 59.5617,
|
16 |
+
"eval_samples_per_second": 167.893,
|
17 |
+
"eval_steps_per_second": 7.001,
|
18 |
+
"step": 84
|
19 |
}
|
20 |
],
|
21 |
"logging_steps": 500,
|
22 |
+
"max_steps": 84,
|
23 |
"num_input_tokens_seen": 0,
|
24 |
"num_train_epochs": 1,
|
25 |
"save_steps": 500,
|
26 |
+
"total_flos": 587868288122880.0,
|
27 |
"train_batch_size": 24,
|
28 |
"trial_name": null,
|
29 |
"trial_params": null
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4539
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:eca38542fb4cef217e46a666e97fb1e666bd8e14927f43bc96719a9823b82b38
|
3 |
size 4539
|