nielsbantilan
commited on
Commit
•
9b82947
1
Parent(s):
aa80b7d
Upload folder using huggingface_hub
Browse files- debug-cli.root.log +0 -0
- generation_config.json +6 -0
- pytorch_model.bin +2 -2
- special_tokens_map.json +6 -0
- tokenizer.json +6 -1
- trainer_state.json +31 -0
- training_args.bin +3 -0
- version.txt +1 -0
debug-cli.root.log
ADDED
File without changes
|
generation_config.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 0,
|
4 |
+
"eos_token_id": 0,
|
5 |
+
"transformers_version": "4.29.2"
|
6 |
+
}
|
pytorch_model.bin
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 sha256:247c2c8d4e70d963e87cfcd9c5ff7c32aac07fc279083a9c02af4c141ad296fc
|
3 |
+
size 2090751965
|
special_tokens_map.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<|endoftext|>",
|
3 |
+
"eos_token": "<|endoftext|>",
|
4 |
+
"pad_token": "[PAD]",
|
5 |
+
"unk_token": "<|endoftext|>"
|
6 |
+
}
|
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": 512,
|
6 |
+
"strategy": "LongestFirst",
|
7 |
+
"stride": 0
|
8 |
+
},
|
9 |
"padding": null,
|
10 |
"added_tokens": [
|
11 |
{
|
trainer_state.json
ADDED
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 3.3333333333333335,
|
5 |
+
"global_step": 10,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 3.33,
|
12 |
+
"learning_rate": 2e-05,
|
13 |
+
"loss": 2.1837,
|
14 |
+
"step": 10
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 3.33,
|
18 |
+
"step": 10,
|
19 |
+
"total_flos": 835002040320.0,
|
20 |
+
"train_loss": 2.1836517333984373,
|
21 |
+
"train_runtime": 74.2827,
|
22 |
+
"train_samples_per_second": 8.616,
|
23 |
+
"train_steps_per_second": 0.135
|
24 |
+
}
|
25 |
+
],
|
26 |
+
"max_steps": 10,
|
27 |
+
"num_train_epochs": 4,
|
28 |
+
"total_flos": 835002040320.0,
|
29 |
+
"trial_name": null,
|
30 |
+
"trial_params": null
|
31 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dccd10791eeca2765d0dab04a01995f27d811561179ad9f79d8ca91bbc1bae49
|
3 |
+
size 5499
|
version.txt
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
1
|