Commit
•
493deb9
1
Parent(s):
4f1cb39
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-6027/model.safetensors +3 -0
- checkpoint-6027/optimizer.pt +3 -0
- checkpoint-6027/rng_state.pth +3 -0
- checkpoint-6027/scheduler.pt +3 -0
- checkpoint-6027/trainer_state.json +147 -0
- checkpoint-6027/training_args.bin +3 -0
- checkpoint-6314/model.safetensors +3 -0
- checkpoint-6314/optimizer.pt +3 -0
- checkpoint-6314/rng_state.pth +3 -0
- checkpoint-6314/scheduler.pt +3 -0
- checkpoint-6314/trainer_state.json +153 -0
- checkpoint-6314/training_args.bin +3 -0
- checkpoint-6601/model.safetensors +3 -0
- checkpoint-6601/optimizer.pt +3 -0
- checkpoint-6601/rng_state.pth +3 -0
- checkpoint-6601/scheduler.pt +3 -0
- checkpoint-6601/trainer_state.json +159 -0
- checkpoint-6601/training_args.bin +3 -0
- checkpoint-6888/model.safetensors +3 -0
- checkpoint-6888/optimizer.pt +3 -0
- checkpoint-6888/rng_state.pth +3 -0
- checkpoint-6888/scheduler.pt +3 -0
- checkpoint-6888/trainer_state.json +165 -0
- checkpoint-6888/training_args.bin +3 -0
- checkpoint-7175/model.safetensors +3 -0
- checkpoint-7175/optimizer.pt +3 -0
- checkpoint-7175/rng_state.pth +3 -0
- checkpoint-7175/scheduler.pt +3 -0
- checkpoint-7175/trainer_state.json +171 -0
- checkpoint-7175/training_args.bin +3 -0
- checkpoint-7462/model.safetensors +3 -0
- checkpoint-7462/optimizer.pt +3 -0
- checkpoint-7462/rng_state.pth +3 -0
- checkpoint-7462/scheduler.pt +3 -0
- checkpoint-7462/trainer_state.json +177 -0
- checkpoint-7462/training_args.bin +3 -0
- checkpoint-7749/model.safetensors +3 -0
- checkpoint-7749/optimizer.pt +3 -0
- checkpoint-7749/rng_state.pth +3 -0
- checkpoint-7749/scheduler.pt +3 -0
- checkpoint-7749/trainer_state.json +183 -0
- checkpoint-7749/training_args.bin +3 -0
- checkpoint-8036/model.safetensors +3 -0
- checkpoint-8036/optimizer.pt +3 -0
- checkpoint-8036/rng_state.pth +3 -0
- checkpoint-8036/scheduler.pt +3 -0
- checkpoint-8036/trainer_state.json +189 -0
- checkpoint-8036/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-6027/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4733fd7d4f13b14f19647c36ba4fa4454d7f3de192d83b1afb82511a84823e23
|
| 3 |
+
size 90866120
|
checkpoint-6027/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c886a67f3900eef2655cca574218b61d5a1cd40487a321e085fec5a326ae7540
|
| 3 |
+
size 180607738
|
checkpoint-6027/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8c8132ebefa53f250b44c875ba8e0ff411e4d800e0e9e5925eb8ae5a49fcd489
|
| 3 |
+
size 14244
|
checkpoint-6027/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d3fbd046324521587b4e80e111a51723c0f196dd3ff18ee5a2239809294d16ec
|
| 3 |
+
size 1064
|
checkpoint-6027/trainer_state.json
ADDED
|
@@ -0,0 +1,147 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 21.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 6027,
|
| 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 |
+
"logging_steps": 500,
|
| 139 |
+
"max_steps": 9184,
|
| 140 |
+
"num_input_tokens_seen": 0,
|
| 141 |
+
"num_train_epochs": 32,
|
| 142 |
+
"save_steps": 500,
|
| 143 |
+
"total_flos": 0.0,
|
| 144 |
+
"train_batch_size": 64,
|
| 145 |
+
"trial_name": null,
|
| 146 |
+
"trial_params": null
|
| 147 |
+
}
|
checkpoint-6027/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b2d8d559a9f0f171908c0a1db0384f658c1e31689653c8277d9ca4a2848e36c6
|
| 3 |
+
size 4792
|
checkpoint-6314/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ffb9d234ce16eb62bfaa4221636dafbdd629621a3d5d6c5fd9ab84b3b0b1b1a6
|
| 3 |
+
size 90866120
|
checkpoint-6314/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9a87cfb151fe8553d7bf1bc304afb20d87b6535e8731fa1a235ed08ffc7a2fe6
|
| 3 |
+
size 180607738
|
checkpoint-6314/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:19e881a8dd55719ee21e204acb99a2911d67016f769fb6b3b7466fafbaf0f9cd
|
| 3 |
+
size 14244
|
checkpoint-6314/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:287908aafda9b69a00a1a7fc70dab854c95a31d48d4802f418545e885ada59a2
|
| 3 |
+
size 1064
|
checkpoint-6314/trainer_state.json
ADDED
|
@@ -0,0 +1,153 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 22.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 6314,
|
| 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 |
+
"logging_steps": 500,
|
| 145 |
+
"max_steps": 9184,
|
| 146 |
+
"num_input_tokens_seen": 0,
|
| 147 |
+
"num_train_epochs": 32,
|
| 148 |
+
"save_steps": 500,
|
| 149 |
+
"total_flos": 0.0,
|
| 150 |
+
"train_batch_size": 64,
|
| 151 |
+
"trial_name": null,
|
| 152 |
+
"trial_params": null
|
| 153 |
+
}
|
checkpoint-6314/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b2d8d559a9f0f171908c0a1db0384f658c1e31689653c8277d9ca4a2848e36c6
|
| 3 |
+
size 4792
|
checkpoint-6601/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f34e4e0514126e422d0077461ee3fdf8da8668c43e97aaf363dc673364948c6f
|
| 3 |
+
size 90866120
|
checkpoint-6601/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:63e359bde6424914d379e217b4ba17a6f2d39e97e20cd4836b7d77b4ca84d62a
|
| 3 |
+
size 180607738
|
checkpoint-6601/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d798f414d39bf019c39269ef4f56532a529aab04afb3a417a5ff16b7ed0ad786
|
| 3 |
+
size 14244
|
checkpoint-6601/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b8c1c73cd10d4c6ed97f6679e38fdc6b436e706a28ba69046af4b534c81c02ec
|
| 3 |
+
size 1064
|
checkpoint-6601/trainer_state.json
ADDED
|
@@ -0,0 +1,159 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 23.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 6601,
|
| 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 |
+
"logging_steps": 500,
|
| 151 |
+
"max_steps": 9184,
|
| 152 |
+
"num_input_tokens_seen": 0,
|
| 153 |
+
"num_train_epochs": 32,
|
| 154 |
+
"save_steps": 500,
|
| 155 |
+
"total_flos": 0.0,
|
| 156 |
+
"train_batch_size": 64,
|
| 157 |
+
"trial_name": null,
|
| 158 |
+
"trial_params": null
|
| 159 |
+
}
|
checkpoint-6601/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b2d8d559a9f0f171908c0a1db0384f658c1e31689653c8277d9ca4a2848e36c6
|
| 3 |
+
size 4792
|
checkpoint-6888/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4ed9000929251e2f6f2419aac4b88167e4e0264b576d3bc6a2d1bb026eac5bd0
|
| 3 |
+
size 90866120
|
checkpoint-6888/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:49e950c4c4252d5d35e86d5eb4237b5d9fe84e76c44f29148682318bcc0019b4
|
| 3 |
+
size 180607738
|
checkpoint-6888/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:02dd0d13161623f5c7e3f1f8f092881967f367c62ffd2bdebb58fb8c30515275
|
| 3 |
+
size 14244
|
checkpoint-6888/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:94d772f8d585712dde96e99df002ebca4da45da1695bb55aa70e11a188f02c98
|
| 3 |
+
size 1064
|
checkpoint-6888/trainer_state.json
ADDED
|
@@ -0,0 +1,165 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 24.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 6888,
|
| 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 |
+
"logging_steps": 500,
|
| 157 |
+
"max_steps": 9184,
|
| 158 |
+
"num_input_tokens_seen": 0,
|
| 159 |
+
"num_train_epochs": 32,
|
| 160 |
+
"save_steps": 500,
|
| 161 |
+
"total_flos": 0.0,
|
| 162 |
+
"train_batch_size": 64,
|
| 163 |
+
"trial_name": null,
|
| 164 |
+
"trial_params": null
|
| 165 |
+
}
|
checkpoint-6888/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b2d8d559a9f0f171908c0a1db0384f658c1e31689653c8277d9ca4a2848e36c6
|
| 3 |
+
size 4792
|
checkpoint-7175/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:70399412ee3a628d0f3b4610a75eb6d34bbbfd5af078a54428cf923428ede87c
|
| 3 |
+
size 90866120
|
checkpoint-7175/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:35df210873e2c02a975d32ef197ce30b942c815e6ae93698e6ed9111688677e9
|
| 3 |
+
size 180607738
|
checkpoint-7175/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bfad4aa84c0d92f9d5ccb73464e7c346e61b36684ece175fbbc2d6232d4d2ec1
|
| 3 |
+
size 14244
|
checkpoint-7175/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8b28adf85aa6d40a127d685592ca8e5c171fb4571c03ae04230db692a8f1ffa7
|
| 3 |
+
size 1064
|
checkpoint-7175/trainer_state.json
ADDED
|
@@ -0,0 +1,171 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 25.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 7175,
|
| 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 |
+
"logging_steps": 500,
|
| 163 |
+
"max_steps": 9184,
|
| 164 |
+
"num_input_tokens_seen": 0,
|
| 165 |
+
"num_train_epochs": 32,
|
| 166 |
+
"save_steps": 500,
|
| 167 |
+
"total_flos": 0.0,
|
| 168 |
+
"train_batch_size": 64,
|
| 169 |
+
"trial_name": null,
|
| 170 |
+
"trial_params": null
|
| 171 |
+
}
|
checkpoint-7175/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b2d8d559a9f0f171908c0a1db0384f658c1e31689653c8277d9ca4a2848e36c6
|
| 3 |
+
size 4792
|
checkpoint-7462/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:93de1f250f3d2b213443d49f9a6bc58b9bc6136b5360cd3981314985ac99869e
|
| 3 |
+
size 90866120
|
checkpoint-7462/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:95db1db9cba8df01031b08118df90149273beaa66c8a2f4420b573054b006036
|
| 3 |
+
size 180607738
|
checkpoint-7462/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:989c0e225ca35a25d7e972b25c493513a6c249b1701d9a4935578c8df15b4a84
|
| 3 |
+
size 14244
|
checkpoint-7462/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0535cd984cd25c62d05ba741b59307e6d473370910220c9493fb6f0fb158f2c7
|
| 3 |
+
size 1064
|
checkpoint-7462/trainer_state.json
ADDED
|
@@ -0,0 +1,177 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 26.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 7462,
|
| 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 |
+
"logging_steps": 500,
|
| 169 |
+
"max_steps": 9184,
|
| 170 |
+
"num_input_tokens_seen": 0,
|
| 171 |
+
"num_train_epochs": 32,
|
| 172 |
+
"save_steps": 500,
|
| 173 |
+
"total_flos": 0.0,
|
| 174 |
+
"train_batch_size": 64,
|
| 175 |
+
"trial_name": null,
|
| 176 |
+
"trial_params": null
|
| 177 |
+
}
|
checkpoint-7462/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b2d8d559a9f0f171908c0a1db0384f658c1e31689653c8277d9ca4a2848e36c6
|
| 3 |
+
size 4792
|
checkpoint-7749/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:21ce4eca180873fb16cdb6d9bff483078203550177dabd4ed16bf462c7493af4
|
| 3 |
+
size 90866120
|
checkpoint-7749/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:254e2ba1d029861e2f7e1b7d917e6ab876636c3c0af898b8979e9336459deaeb
|
| 3 |
+
size 180607738
|
checkpoint-7749/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:eeca4e1dc911e6617de8c0b5c3b6ee333073453ada941b2b075b2c148e12374d
|
| 3 |
+
size 14244
|
checkpoint-7749/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c4097bc439462cd2d9ca9794414c1789ad4482313b2479440f57e54bfa023df2
|
| 3 |
+
size 1064
|
checkpoint-7749/trainer_state.json
ADDED
|
@@ -0,0 +1,183 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 27.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 7749,
|
| 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 |
+
"logging_steps": 500,
|
| 175 |
+
"max_steps": 9184,
|
| 176 |
+
"num_input_tokens_seen": 0,
|
| 177 |
+
"num_train_epochs": 32,
|
| 178 |
+
"save_steps": 500,
|
| 179 |
+
"total_flos": 0.0,
|
| 180 |
+
"train_batch_size": 64,
|
| 181 |
+
"trial_name": null,
|
| 182 |
+
"trial_params": null
|
| 183 |
+
}
|
checkpoint-7749/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b2d8d559a9f0f171908c0a1db0384f658c1e31689653c8277d9ca4a2848e36c6
|
| 3 |
+
size 4792
|
checkpoint-8036/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:094692f052bc3c1da865dd330ea4d8868877c2c651aa4728271543cff9649ebf
|
| 3 |
+
size 90866120
|
checkpoint-8036/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:efd5c0d40f596b5cc141af43a5a42a15ea6711ede357930782af5e5cdd103831
|
| 3 |
+
size 180607738
|
checkpoint-8036/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:55ad740d18cd84d3d6ab714ade3167df9b6d81cc8473d8c6af14b20d61391900
|
| 3 |
+
size 14244
|
checkpoint-8036/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:edce3f06ab8ae28b57207a6ce227dcbc4fb37cdbf3e247d385951ac8ed165923
|
| 3 |
+
size 1064
|
checkpoint-8036/trainer_state.json
ADDED
|
@@ -0,0 +1,189 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 28.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 8036,
|
| 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 |
+
"logging_steps": 500,
|
| 181 |
+
"max_steps": 9184,
|
| 182 |
+
"num_input_tokens_seen": 0,
|
| 183 |
+
"num_train_epochs": 32,
|
| 184 |
+
"save_steps": 500,
|
| 185 |
+
"total_flos": 0.0,
|
| 186 |
+
"train_batch_size": 64,
|
| 187 |
+
"trial_name": null,
|
| 188 |
+
"trial_params": null
|
| 189 |
+
}
|
checkpoint-8036/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b2d8d559a9f0f171908c0a1db0384f658c1e31689653c8277d9ca4a2848e36c6
|
| 3 |
+
size 4792
|