srsawant34
commited on
Commit
·
2a95641
1
Parent(s):
d4e7c7a
Upload folder using huggingface_hub
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- 1_Pooling/config.json +7 -0
- README.md +107 -0
- checkpoint-1148/model.safetensors +3 -0
- checkpoint-1148/optimizer.pt +3 -0
- checkpoint-1148/rng_state.pth +3 -0
- checkpoint-1148/scheduler.pt +3 -0
- checkpoint-1148/trainer_state.json +45 -0
- checkpoint-1148/training_args.bin +3 -0
- checkpoint-1435/model.safetensors +3 -0
- checkpoint-1435/optimizer.pt +3 -0
- checkpoint-1435/rng_state.pth +3 -0
- checkpoint-1435/scheduler.pt +3 -0
- checkpoint-1435/trainer_state.json +51 -0
- checkpoint-1435/training_args.bin +3 -0
- checkpoint-1722/model.safetensors +3 -0
- checkpoint-1722/optimizer.pt +3 -0
- checkpoint-1722/rng_state.pth +3 -0
- checkpoint-1722/scheduler.pt +3 -0
- checkpoint-1722/trainer_state.json +57 -0
- checkpoint-1722/training_args.bin +3 -0
- checkpoint-2009/model.safetensors +3 -0
- checkpoint-2009/optimizer.pt +3 -0
- checkpoint-2009/rng_state.pth +3 -0
- checkpoint-2009/scheduler.pt +3 -0
- checkpoint-2009/trainer_state.json +63 -0
- checkpoint-2009/training_args.bin +3 -0
- checkpoint-2296/model.safetensors +3 -0
- checkpoint-2296/optimizer.pt +3 -0
- checkpoint-2296/rng_state.pth +3 -0
- checkpoint-2296/scheduler.pt +3 -0
- checkpoint-2296/trainer_state.json +69 -0
- checkpoint-2296/training_args.bin +3 -0
- checkpoint-287/model.safetensors +3 -0
- checkpoint-287/optimizer.pt +3 -0
- checkpoint-287/rng_state.pth +3 -0
- checkpoint-287/scheduler.pt +3 -0
- checkpoint-287/trainer_state.json +27 -0
- checkpoint-287/training_args.bin +3 -0
- checkpoint-574/model.safetensors +3 -0
- checkpoint-574/optimizer.pt +3 -0
- checkpoint-574/rng_state.pth +3 -0
- checkpoint-574/scheduler.pt +3 -0
- checkpoint-574/trainer_state.json +33 -0
- checkpoint-574/training_args.bin +3 -0
- checkpoint-8323/model.safetensors +3 -0
- checkpoint-8323/optimizer.pt +3 -0
- checkpoint-8323/rng_state.pth +3 -0
- checkpoint-8323/scheduler.pt +3 -0
- checkpoint-8323/trainer_state.json +195 -0
- checkpoint-8323/training_args.bin +3 -0
1_Pooling/config.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"word_embedding_dimension": 384,
|
3 |
+
"pooling_mode_cls_token": false,
|
4 |
+
"pooling_mode_mean_tokens": true,
|
5 |
+
"pooling_mode_max_tokens": false,
|
6 |
+
"pooling_mode_mean_sqrt_len_tokens": false
|
7 |
+
}
|
README.md
ADDED
@@ -0,0 +1,107 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
pipeline_tag: sentence-similarity
|
3 |
+
license: apache-2.0
|
4 |
+
tags:
|
5 |
+
- sentence-transformers
|
6 |
+
- feature-extraction
|
7 |
+
- sentence-similarity
|
8 |
+
- transformers
|
9 |
+
---
|
10 |
+
|
11 |
+
# sentence-transformers/paraphrase-MiniLM-L6-v2
|
12 |
+
|
13 |
+
This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 384 dimensional dense vector space and can be used for tasks like clustering or semantic search.
|
14 |
+
|
15 |
+
|
16 |
+
|
17 |
+
## Usage (Sentence-Transformers)
|
18 |
+
|
19 |
+
Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed:
|
20 |
+
|
21 |
+
```
|
22 |
+
pip install -U sentence-transformers
|
23 |
+
```
|
24 |
+
|
25 |
+
Then you can use the model like this:
|
26 |
+
|
27 |
+
```python
|
28 |
+
from sentence_transformers import SentenceTransformer
|
29 |
+
sentences = ["This is an example sentence", "Each sentence is converted"]
|
30 |
+
|
31 |
+
model = SentenceTransformer('sentence-transformers/paraphrase-MiniLM-L6-v2')
|
32 |
+
embeddings = model.encode(sentences)
|
33 |
+
print(embeddings)
|
34 |
+
```
|
35 |
+
|
36 |
+
|
37 |
+
|
38 |
+
## Usage (HuggingFace Transformers)
|
39 |
+
Without [sentence-transformers](https://www.SBERT.net), you can use the model like this: First, you pass your input through the transformer model, then you have to apply the right pooling-operation on-top of the contextualized word embeddings.
|
40 |
+
|
41 |
+
```python
|
42 |
+
from transformers import AutoTokenizer, AutoModel
|
43 |
+
import torch
|
44 |
+
|
45 |
+
|
46 |
+
#Mean Pooling - Take attention mask into account for correct averaging
|
47 |
+
def mean_pooling(model_output, attention_mask):
|
48 |
+
token_embeddings = model_output[0] #First element of model_output contains all token embeddings
|
49 |
+
input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float()
|
50 |
+
return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9)
|
51 |
+
|
52 |
+
|
53 |
+
# Sentences we want sentence embeddings for
|
54 |
+
sentences = ['This is an example sentence', 'Each sentence is converted']
|
55 |
+
|
56 |
+
# Load model from HuggingFace Hub
|
57 |
+
tokenizer = AutoTokenizer.from_pretrained('sentence-transformers/paraphrase-MiniLM-L6-v2')
|
58 |
+
model = AutoModel.from_pretrained('sentence-transformers/paraphrase-MiniLM-L6-v2')
|
59 |
+
|
60 |
+
# Tokenize sentences
|
61 |
+
encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')
|
62 |
+
|
63 |
+
# Compute token embeddings
|
64 |
+
with torch.no_grad():
|
65 |
+
model_output = model(**encoded_input)
|
66 |
+
|
67 |
+
# Perform pooling. In this case, max pooling.
|
68 |
+
sentence_embeddings = mean_pooling(model_output, encoded_input['attention_mask'])
|
69 |
+
|
70 |
+
print("Sentence embeddings:")
|
71 |
+
print(sentence_embeddings)
|
72 |
+
```
|
73 |
+
|
74 |
+
|
75 |
+
|
76 |
+
## Evaluation Results
|
77 |
+
|
78 |
+
|
79 |
+
|
80 |
+
For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name=sentence-transformers/paraphrase-MiniLM-L6-v2)
|
81 |
+
|
82 |
+
|
83 |
+
|
84 |
+
## Full Model Architecture
|
85 |
+
```
|
86 |
+
SentenceTransformer(
|
87 |
+
(0): Transformer({'max_seq_length': 128, 'do_lower_case': False}) with Transformer model: BertModel
|
88 |
+
(1): Pooling({'word_embedding_dimension': 384, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False})
|
89 |
+
)
|
90 |
+
```
|
91 |
+
|
92 |
+
## Citing & Authors
|
93 |
+
|
94 |
+
This model was trained by [sentence-transformers](https://www.sbert.net/).
|
95 |
+
|
96 |
+
If you find this model helpful, feel free to cite our publication [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://arxiv.org/abs/1908.10084):
|
97 |
+
```bibtex
|
98 |
+
@inproceedings{reimers-2019-sentence-bert,
|
99 |
+
title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
|
100 |
+
author = "Reimers, Nils and Gurevych, Iryna",
|
101 |
+
booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
|
102 |
+
month = "11",
|
103 |
+
year = "2019",
|
104 |
+
publisher = "Association for Computational Linguistics",
|
105 |
+
url = "http://arxiv.org/abs/1908.10084",
|
106 |
+
}
|
107 |
+
```
|
checkpoint-1148/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0b2098e96fe45a5f982c95e9326eeb8656a11a99113e82ae00dda07104972886
|
3 |
+
size 90866120
|
checkpoint-1148/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3179416f106ae2f73588f990002ac14e2c2d259eaba15ca06fb8f9e8e63d390e
|
3 |
+
size 180607738
|
checkpoint-1148/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:87082ae80ddb9d34dbe1ab1348f8126541868839519795215c9dcc059ab63fc6
|
3 |
+
size 14244
|
checkpoint-1148/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5c37d10e949e0aa0b73992efa2d5c4e60e9e1eb519cda5feb64f0ab41724e9f3
|
3 |
+
size 1064
|
checkpoint-1148/trainer_state.json
ADDED
@@ -0,0 +1,45 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 4.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 1148,
|
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 |
+
"learning_rate": 0.0004375,
|
14 |
+
"loss": 2.2956,
|
15 |
+
"step": 287
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"epoch": 2.0,
|
19 |
+
"learning_rate": 0.000375,
|
20 |
+
"loss": 2.2508,
|
21 |
+
"step": 574
|
22 |
+
},
|
23 |
+
{
|
24 |
+
"epoch": 3.0,
|
25 |
+
"learning_rate": 0.0003125,
|
26 |
+
"loss": 2.223,
|
27 |
+
"step": 861
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"epoch": 4.0,
|
31 |
+
"learning_rate": 0.00025,
|
32 |
+
"loss": 2.1849,
|
33 |
+
"step": 1148
|
34 |
+
}
|
35 |
+
],
|
36 |
+
"logging_steps": 500,
|
37 |
+
"max_steps": 2296,
|
38 |
+
"num_input_tokens_seen": 0,
|
39 |
+
"num_train_epochs": 8,
|
40 |
+
"save_steps": 500,
|
41 |
+
"total_flos": 0.0,
|
42 |
+
"train_batch_size": 64,
|
43 |
+
"trial_name": null,
|
44 |
+
"trial_params": null
|
45 |
+
}
|
checkpoint-1148/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:59691d62067580cb96432d7835b9a22fa0cdbf9d683d1ce4d96a99344613e85b
|
3 |
+
size 4792
|
checkpoint-1435/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dc8c4d32a407aaa87a88f0e6bbd1ac189f2a27e026dd588466a5f8b37576ff9b
|
3 |
+
size 90866120
|
checkpoint-1435/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d10bd4efa881893777d05d306a2a6cabf7b54b6127e45e93eb4bb7d740c6cdb3
|
3 |
+
size 180607738
|
checkpoint-1435/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:50e824cfb48c98373f53fa9ca5548f2cb8c492dbb792ffd913076a907a3be071
|
3 |
+
size 14244
|
checkpoint-1435/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c3b5c008aeab85448dc93b26ef48ef1b1487424fcaa42a2b4edbcc01433b9da0
|
3 |
+
size 1064
|
checkpoint-1435/trainer_state.json
ADDED
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 5.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 1435,
|
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 |
+
"learning_rate": 0.0004375,
|
14 |
+
"loss": 2.2956,
|
15 |
+
"step": 287
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"epoch": 2.0,
|
19 |
+
"learning_rate": 0.000375,
|
20 |
+
"loss": 2.2508,
|
21 |
+
"step": 574
|
22 |
+
},
|
23 |
+
{
|
24 |
+
"epoch": 3.0,
|
25 |
+
"learning_rate": 0.0003125,
|
26 |
+
"loss": 2.223,
|
27 |
+
"step": 861
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"epoch": 4.0,
|
31 |
+
"learning_rate": 0.00025,
|
32 |
+
"loss": 2.1849,
|
33 |
+
"step": 1148
|
34 |
+
},
|
35 |
+
{
|
36 |
+
"epoch": 5.0,
|
37 |
+
"learning_rate": 0.0001875,
|
38 |
+
"loss": 2.129,
|
39 |
+
"step": 1435
|
40 |
+
}
|
41 |
+
],
|
42 |
+
"logging_steps": 500,
|
43 |
+
"max_steps": 2296,
|
44 |
+
"num_input_tokens_seen": 0,
|
45 |
+
"num_train_epochs": 8,
|
46 |
+
"save_steps": 500,
|
47 |
+
"total_flos": 0.0,
|
48 |
+
"train_batch_size": 64,
|
49 |
+
"trial_name": null,
|
50 |
+
"trial_params": null
|
51 |
+
}
|
checkpoint-1435/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:59691d62067580cb96432d7835b9a22fa0cdbf9d683d1ce4d96a99344613e85b
|
3 |
+
size 4792
|
checkpoint-1722/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8c8f67022add8bdf2b50f0f9728abf4878d9769cf37b6c527772b38f276f87ba
|
3 |
+
size 90866120
|
checkpoint-1722/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ab2d2ef97ecad6c8c0dbd0832adfc3310b8ac297d3d71519d4812ce989d7d08a
|
3 |
+
size 180607738
|
checkpoint-1722/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6410d8133abaf4a88621d2bcb3b13abb0ad5ba2fb8420e82b82efbc22b99f0a5
|
3 |
+
size 14244
|
checkpoint-1722/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ade3fcc8dc579752118cf26ed7f71bb709b1db10d0dc00e45e62e34e19de1862
|
3 |
+
size 1064
|
checkpoint-1722/trainer_state.json
ADDED
@@ -0,0 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 6.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 1722,
|
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 |
+
"learning_rate": 0.0004375,
|
14 |
+
"loss": 2.2956,
|
15 |
+
"step": 287
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"epoch": 2.0,
|
19 |
+
"learning_rate": 0.000375,
|
20 |
+
"loss": 2.2508,
|
21 |
+
"step": 574
|
22 |
+
},
|
23 |
+
{
|
24 |
+
"epoch": 3.0,
|
25 |
+
"learning_rate": 0.0003125,
|
26 |
+
"loss": 2.223,
|
27 |
+
"step": 861
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"epoch": 4.0,
|
31 |
+
"learning_rate": 0.00025,
|
32 |
+
"loss": 2.1849,
|
33 |
+
"step": 1148
|
34 |
+
},
|
35 |
+
{
|
36 |
+
"epoch": 5.0,
|
37 |
+
"learning_rate": 0.0001875,
|
38 |
+
"loss": 2.129,
|
39 |
+
"step": 1435
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 6.0,
|
43 |
+
"learning_rate": 0.000125,
|
44 |
+
"loss": 2.0923,
|
45 |
+
"step": 1722
|
46 |
+
}
|
47 |
+
],
|
48 |
+
"logging_steps": 500,
|
49 |
+
"max_steps": 2296,
|
50 |
+
"num_input_tokens_seen": 0,
|
51 |
+
"num_train_epochs": 8,
|
52 |
+
"save_steps": 500,
|
53 |
+
"total_flos": 0.0,
|
54 |
+
"train_batch_size": 64,
|
55 |
+
"trial_name": null,
|
56 |
+
"trial_params": null
|
57 |
+
}
|
checkpoint-1722/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:59691d62067580cb96432d7835b9a22fa0cdbf9d683d1ce4d96a99344613e85b
|
3 |
+
size 4792
|
checkpoint-2009/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:404ec8daad9aaa3bbf36ac0b5ae66ebc740e09b008b59e7b546f4d65846cf0c8
|
3 |
+
size 90866120
|
checkpoint-2009/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7155b933ef2854d6e51dc2007a87d953256098b5a55202a2f7b38594c7c1489c
|
3 |
+
size 180607738
|
checkpoint-2009/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8e5a38071360faecf02821c8f4fbb614f6435fe31e87d746da0bc03e552b342c
|
3 |
+
size 14244
|
checkpoint-2009/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4cee79f61c3bb2fb8a9032e1977574f64f859c6dd73869c3b327fbffa6589172
|
3 |
+
size 1064
|
checkpoint-2009/trainer_state.json
ADDED
@@ -0,0 +1,63 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 7.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 2009,
|
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 |
+
"learning_rate": 0.0004375,
|
14 |
+
"loss": 2.2956,
|
15 |
+
"step": 287
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"epoch": 2.0,
|
19 |
+
"learning_rate": 0.000375,
|
20 |
+
"loss": 2.2508,
|
21 |
+
"step": 574
|
22 |
+
},
|
23 |
+
{
|
24 |
+
"epoch": 3.0,
|
25 |
+
"learning_rate": 0.0003125,
|
26 |
+
"loss": 2.223,
|
27 |
+
"step": 861
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"epoch": 4.0,
|
31 |
+
"learning_rate": 0.00025,
|
32 |
+
"loss": 2.1849,
|
33 |
+
"step": 1148
|
34 |
+
},
|
35 |
+
{
|
36 |
+
"epoch": 5.0,
|
37 |
+
"learning_rate": 0.0001875,
|
38 |
+
"loss": 2.129,
|
39 |
+
"step": 1435
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 6.0,
|
43 |
+
"learning_rate": 0.000125,
|
44 |
+
"loss": 2.0923,
|
45 |
+
"step": 1722
|
46 |
+
},
|
47 |
+
{
|
48 |
+
"epoch": 7.0,
|
49 |
+
"learning_rate": 6.25e-05,
|
50 |
+
"loss": 2.0515,
|
51 |
+
"step": 2009
|
52 |
+
}
|
53 |
+
],
|
54 |
+
"logging_steps": 500,
|
55 |
+
"max_steps": 2296,
|
56 |
+
"num_input_tokens_seen": 0,
|
57 |
+
"num_train_epochs": 8,
|
58 |
+
"save_steps": 500,
|
59 |
+
"total_flos": 0.0,
|
60 |
+
"train_batch_size": 64,
|
61 |
+
"trial_name": null,
|
62 |
+
"trial_params": null
|
63 |
+
}
|
checkpoint-2009/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:59691d62067580cb96432d7835b9a22fa0cdbf9d683d1ce4d96a99344613e85b
|
3 |
+
size 4792
|
checkpoint-2296/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e26c278c82dfef249a456ec36e221a988b6d68d362fee2cb8d267663be9a8839
|
3 |
+
size 90866120
|
checkpoint-2296/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:321acd24548f9e1e302833e2279fa7442bf21c987d8e771bd5c094247b334456
|
3 |
+
size 180607738
|
checkpoint-2296/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6089dac575b53bd88bb39a67970f95bf63a880871d9872b7a41372a647ff1653
|
3 |
+
size 14244
|
checkpoint-2296/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d1d06d8c680538100d481f36453ab9a97fc9432e250541c38cdeebf478aa981f
|
3 |
+
size 1064
|
checkpoint-2296/trainer_state.json
ADDED
@@ -0,0 +1,69 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 8.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 2296,
|
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 |
+
"learning_rate": 0.0004375,
|
14 |
+
"loss": 2.2956,
|
15 |
+
"step": 287
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"epoch": 2.0,
|
19 |
+
"learning_rate": 0.000375,
|
20 |
+
"loss": 2.2508,
|
21 |
+
"step": 574
|
22 |
+
},
|
23 |
+
{
|
24 |
+
"epoch": 3.0,
|
25 |
+
"learning_rate": 0.0003125,
|
26 |
+
"loss": 2.223,
|
27 |
+
"step": 861
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"epoch": 4.0,
|
31 |
+
"learning_rate": 0.00025,
|
32 |
+
"loss": 2.1849,
|
33 |
+
"step": 1148
|
34 |
+
},
|
35 |
+
{
|
36 |
+
"epoch": 5.0,
|
37 |
+
"learning_rate": 0.0001875,
|
38 |
+
"loss": 2.129,
|
39 |
+
"step": 1435
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 6.0,
|
43 |
+
"learning_rate": 0.000125,
|
44 |
+
"loss": 2.0923,
|
45 |
+
"step": 1722
|
46 |
+
},
|
47 |
+
{
|
48 |
+
"epoch": 7.0,
|
49 |
+
"learning_rate": 6.25e-05,
|
50 |
+
"loss": 2.0515,
|
51 |
+
"step": 2009
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 8.0,
|
55 |
+
"learning_rate": 0.0,
|
56 |
+
"loss": 2.027,
|
57 |
+
"step": 2296
|
58 |
+
}
|
59 |
+
],
|
60 |
+
"logging_steps": 500,
|
61 |
+
"max_steps": 2296,
|
62 |
+
"num_input_tokens_seen": 0,
|
63 |
+
"num_train_epochs": 8,
|
64 |
+
"save_steps": 500,
|
65 |
+
"total_flos": 0.0,
|
66 |
+
"train_batch_size": 64,
|
67 |
+
"trial_name": null,
|
68 |
+
"trial_params": null
|
69 |
+
}
|
checkpoint-2296/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:59691d62067580cb96432d7835b9a22fa0cdbf9d683d1ce4d96a99344613e85b
|
3 |
+
size 4792
|
checkpoint-287/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:39da78be7e3a484ab8795fb515ec18f0be4754c5cab212996559e1a53ee32de6
|
3 |
+
size 90866120
|
checkpoint-287/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8c0a5b06cb0024bd0156188d29444929a1dc946adcc7c294a6fd797e1254b8e5
|
3 |
+
size 180607738
|
checkpoint-287/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d95ef98f5cd4b6c4540739b122435f8121ce1d964466889af8f8484ca6504e2c
|
3 |
+
size 14244
|
checkpoint-287/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ddfeeb2c40d442d9cf6870b8d5c753e579d58c73dd822f86ccebebc7298add3a
|
3 |
+
size 1064
|
checkpoint-287/trainer_state.json
ADDED
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 287,
|
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 |
+
"learning_rate": 0.0004375,
|
14 |
+
"loss": 2.2956,
|
15 |
+
"step": 287
|
16 |
+
}
|
17 |
+
],
|
18 |
+
"logging_steps": 500,
|
19 |
+
"max_steps": 2296,
|
20 |
+
"num_input_tokens_seen": 0,
|
21 |
+
"num_train_epochs": 8,
|
22 |
+
"save_steps": 500,
|
23 |
+
"total_flos": 0.0,
|
24 |
+
"train_batch_size": 64,
|
25 |
+
"trial_name": null,
|
26 |
+
"trial_params": null
|
27 |
+
}
|
checkpoint-287/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:59691d62067580cb96432d7835b9a22fa0cdbf9d683d1ce4d96a99344613e85b
|
3 |
+
size 4792
|
checkpoint-574/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:349a2c2e0c215111818507eb78aa0b183262faa7649367608bc67e77ea5d2218
|
3 |
+
size 90866120
|
checkpoint-574/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e5c92b4b4b84841ca6f94381ed19e37081521ad086f7346a6344212e73439111
|
3 |
+
size 180607738
|
checkpoint-574/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b8a4c4c8306949aa90fda7de408dd3be7bad8cfdb6a96376be8e42b698c0dcec
|
3 |
+
size 14244
|
checkpoint-574/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2053df1c10f5c000fa932bfa8f8a1e64f92dd69d5c946f45ddb7e721b17ac683
|
3 |
+
size 1064
|
checkpoint-574/trainer_state.json
ADDED
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 2.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 574,
|
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 |
+
"learning_rate": 0.0004375,
|
14 |
+
"loss": 2.2956,
|
15 |
+
"step": 287
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"epoch": 2.0,
|
19 |
+
"learning_rate": 0.000375,
|
20 |
+
"loss": 2.2508,
|
21 |
+
"step": 574
|
22 |
+
}
|
23 |
+
],
|
24 |
+
"logging_steps": 500,
|
25 |
+
"max_steps": 2296,
|
26 |
+
"num_input_tokens_seen": 0,
|
27 |
+
"num_train_epochs": 8,
|
28 |
+
"save_steps": 500,
|
29 |
+
"total_flos": 0.0,
|
30 |
+
"train_batch_size": 64,
|
31 |
+
"trial_name": null,
|
32 |
+
"trial_params": null
|
33 |
+
}
|
checkpoint-574/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:59691d62067580cb96432d7835b9a22fa0cdbf9d683d1ce4d96a99344613e85b
|
3 |
+
size 4792
|
checkpoint-8323/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8eb2a5db42fe1825e43b69b178c42992e7d87576776e33758f75592acf8c1f89
|
3 |
+
size 90866120
|
checkpoint-8323/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2b94a49c3e5c9b3b80c1f296a41d62252434fdc86628b024267ec35270194497
|
3 |
+
size 180607738
|
checkpoint-8323/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:113c7031f546d1e57f4645de606e8624d51751acbde70de8fdcf580b016726fa
|
3 |
+
size 14244
|
checkpoint-8323/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:003133324f971f67e818819da368b5822c56b1e11457a78920cf74596a8a62a2
|
3 |
+
size 1064
|
checkpoint-8323/trainer_state.json
ADDED
@@ -0,0 +1,195 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 29.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 8323,
|
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 |
+
"learning_rate": 0.000484375,
|
14 |
+
"loss": 3.0823,
|
15 |
+
"step": 287
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"epoch": 2.0,
|
19 |
+
"learning_rate": 0.00046875,
|
20 |
+
"loss": 2.7242,
|
21 |
+
"step": 574
|
22 |
+
},
|
23 |
+
{
|
24 |
+
"epoch": 3.0,
|
25 |
+
"learning_rate": 0.000453125,
|
26 |
+
"loss": 2.5348,
|
27 |
+
"step": 861
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"epoch": 4.0,
|
31 |
+
"learning_rate": 0.0004375,
|
32 |
+
"loss": 2.4455,
|
33 |
+
"step": 1148
|
34 |
+
},
|
35 |
+
{
|
36 |
+
"epoch": 5.0,
|
37 |
+
"learning_rate": 0.000421875,
|
38 |
+
"loss": 2.3794,
|
39 |
+
"step": 1435
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 6.0,
|
43 |
+
"learning_rate": 0.00040625000000000004,
|
44 |
+
"loss": 2.3375,
|
45 |
+
"step": 1722
|
46 |
+
},
|
47 |
+
{
|
48 |
+
"epoch": 7.0,
|
49 |
+
"learning_rate": 0.000390625,
|
50 |
+
"loss": 2.3262,
|
51 |
+
"step": 2009
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 8.0,
|
55 |
+
"learning_rate": 0.000375,
|
56 |
+
"loss": 2.3114,
|
57 |
+
"step": 2296
|
58 |
+
},
|
59 |
+
{
|
60 |
+
"epoch": 9.0,
|
61 |
+
"learning_rate": 0.000359375,
|
62 |
+
"loss": 2.2921,
|
63 |
+
"step": 2583
|
64 |
+
},
|
65 |
+
{
|
66 |
+
"epoch": 10.0,
|
67 |
+
"learning_rate": 0.00034375,
|
68 |
+
"loss": 2.2918,
|
69 |
+
"step": 2870
|
70 |
+
},
|
71 |
+
{
|
72 |
+
"epoch": 11.0,
|
73 |
+
"learning_rate": 0.000328125,
|
74 |
+
"loss": 2.2578,
|
75 |
+
"step": 3157
|
76 |
+
},
|
77 |
+
{
|
78 |
+
"epoch": 12.0,
|
79 |
+
"learning_rate": 0.0003125,
|
80 |
+
"loss": 2.2693,
|
81 |
+
"step": 3444
|
82 |
+
},
|
83 |
+
{
|
84 |
+
"epoch": 13.0,
|
85 |
+
"learning_rate": 0.000296875,
|
86 |
+
"loss": 2.2594,
|
87 |
+
"step": 3731
|
88 |
+
},
|
89 |
+
{
|
90 |
+
"epoch": 14.0,
|
91 |
+
"learning_rate": 0.00028125000000000003,
|
92 |
+
"loss": 2.2555,
|
93 |
+
"step": 4018
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 15.0,
|
97 |
+
"learning_rate": 0.000265625,
|
98 |
+
"loss": 2.2481,
|
99 |
+
"step": 4305
|
100 |
+
},
|
101 |
+
{
|
102 |
+
"epoch": 16.0,
|
103 |
+
"learning_rate": 0.00025,
|
104 |
+
"loss": 2.2468,
|
105 |
+
"step": 4592
|
106 |
+
},
|
107 |
+
{
|
108 |
+
"epoch": 17.0,
|
109 |
+
"learning_rate": 0.000234375,
|
110 |
+
"loss": 2.248,
|
111 |
+
"step": 4879
|
112 |
+
},
|
113 |
+
{
|
114 |
+
"epoch": 18.0,
|
115 |
+
"learning_rate": 0.00021875,
|
116 |
+
"loss": 2.2435,
|
117 |
+
"step": 5166
|
118 |
+
},
|
119 |
+
{
|
120 |
+
"epoch": 19.0,
|
121 |
+
"learning_rate": 0.00020312500000000002,
|
122 |
+
"loss": 2.2319,
|
123 |
+
"step": 5453
|
124 |
+
},
|
125 |
+
{
|
126 |
+
"epoch": 20.0,
|
127 |
+
"learning_rate": 0.0001875,
|
128 |
+
"loss": 2.2303,
|
129 |
+
"step": 5740
|
130 |
+
},
|
131 |
+
{
|
132 |
+
"epoch": 21.0,
|
133 |
+
"learning_rate": 0.000171875,
|
134 |
+
"loss": 2.2215,
|
135 |
+
"step": 6027
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 22.0,
|
139 |
+
"learning_rate": 0.00015625,
|
140 |
+
"loss": 2.2256,
|
141 |
+
"step": 6314
|
142 |
+
},
|
143 |
+
{
|
144 |
+
"epoch": 23.0,
|
145 |
+
"learning_rate": 0.00014062500000000002,
|
146 |
+
"loss": 2.2257,
|
147 |
+
"step": 6601
|
148 |
+
},
|
149 |
+
{
|
150 |
+
"epoch": 24.0,
|
151 |
+
"learning_rate": 0.000125,
|
152 |
+
"loss": 2.2275,
|
153 |
+
"step": 6888
|
154 |
+
},
|
155 |
+
{
|
156 |
+
"epoch": 25.0,
|
157 |
+
"learning_rate": 0.000109375,
|
158 |
+
"loss": 2.2225,
|
159 |
+
"step": 7175
|
160 |
+
},
|
161 |
+
{
|
162 |
+
"epoch": 26.0,
|
163 |
+
"learning_rate": 9.375e-05,
|
164 |
+
"loss": 2.2166,
|
165 |
+
"step": 7462
|
166 |
+
},
|
167 |
+
{
|
168 |
+
"epoch": 27.0,
|
169 |
+
"learning_rate": 7.8125e-05,
|
170 |
+
"loss": 2.2174,
|
171 |
+
"step": 7749
|
172 |
+
},
|
173 |
+
{
|
174 |
+
"epoch": 28.0,
|
175 |
+
"learning_rate": 6.25e-05,
|
176 |
+
"loss": 2.2188,
|
177 |
+
"step": 8036
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 29.0,
|
181 |
+
"learning_rate": 4.6875e-05,
|
182 |
+
"loss": 2.2143,
|
183 |
+
"step": 8323
|
184 |
+
}
|
185 |
+
],
|
186 |
+
"logging_steps": 500,
|
187 |
+
"max_steps": 9184,
|
188 |
+
"num_input_tokens_seen": 0,
|
189 |
+
"num_train_epochs": 32,
|
190 |
+
"save_steps": 500,
|
191 |
+
"total_flos": 0.0,
|
192 |
+
"train_batch_size": 64,
|
193 |
+
"trial_name": null,
|
194 |
+
"trial_params": null
|
195 |
+
}
|
checkpoint-8323/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1e68121a9357c4f016eb6bc0f031c8d8d3f664e26a8b5ed965be82c62d99c0bf
|
3 |
+
size 4792
|