Upload folder using huggingface_hub
Browse files- README.md +38 -3
- config.json +32 -0
- generation_config.json +5 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- requirements.txt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +37 -0
- tokenizer.json +0 -0
- tokenizer_config.json +53 -0
- trainer_state.json +1122 -0
- training_args.bin +3 -0
README.md
CHANGED
|
@@ -1,3 +1,38 @@
|
|
| 1 |
-
|
| 2 |
-
|
| 3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# BerTELEO
|
| 2 |
+
|
| 3 |
+
A bert model pre-trained on short DNA sequence the teleo marker from zhihan1996/DNABERT-2-117M
|
| 4 |
+
use this model for teleo sequence emmebdding
|
| 5 |
+
|
| 6 |
+
Paper not already release.
|
| 7 |
+
|
| 8 |
+
How use :
|
| 9 |
+
|
| 10 |
+
|
| 11 |
+
```python
|
| 12 |
+
|
| 13 |
+
from transformers import AutoTokenizer, AutoModel, AutoModelForMaskedLM
|
| 14 |
+
import torch
|
| 15 |
+
|
| 16 |
+
model_id = "gustoudu81/BerTeleo"
|
| 17 |
+
|
| 18 |
+
tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)
|
| 19 |
+
model = AutoModelForMaskedLM.from_pretrained(model_id, trust_remote_code=True)
|
| 20 |
+
|
| 21 |
+
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
|
| 22 |
+
model = model.to(device).eval()
|
| 23 |
+
|
| 24 |
+
inputs = tokenizer("ACGTACGTACGT", return_tensors="pt")
|
| 25 |
+
inputs = {k: v.to(device) for k, v in inputs.items()}
|
| 26 |
+
|
| 27 |
+
with torch.no_grad():
|
| 28 |
+
hidden_states = model(**inputs)[0]
|
| 29 |
+
|
| 30 |
+
|
| 31 |
+
# embedding with mean pooling
|
| 32 |
+
embedding_mean = torch.mean(hidden_states[0], dim=0)
|
| 33 |
+
print(embedding_mean.shape) # expect to be 768
|
| 34 |
+
|
| 35 |
+
# embedding with max pooling
|
| 36 |
+
embedding_max = torch.max(hidden_states[0], dim=0)[0]
|
| 37 |
+
print(embedding_max.shape) # expect to be 768
|
| 38 |
+
```
|
config.json
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alibi_starting_size": 512,
|
| 3 |
+
"architectures": [
|
| 4 |
+
"BertForMaskedLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.0,
|
| 7 |
+
"auto_map": {
|
| 8 |
+
"AutoConfig": "gustoudu81/DNABERT-2-117M-tritonfix--configuration_bert.BertConfig",
|
| 9 |
+
"AutoModel": "gustoudu81/DNABERT-2-117M-tritonfix--bert_layers.BertModel",
|
| 10 |
+
"AutoModelForMaskedLM": "gustoudu81/DNABERT-2-117M-tritonfix-2-117M--bert_layers.BertForMaskedLM",
|
| 11 |
+
"AutoModelForSequenceClassification": "gustoudu81/DNABERT-2-117M-tritonfix--bert_layers.BertForSequenceClassification"
|
| 12 |
+
},
|
| 13 |
+
"classifier_dropout": null,
|
| 14 |
+
"gradient_checkpointing": false,
|
| 15 |
+
"hidden_act": "gelu",
|
| 16 |
+
"hidden_dropout_prob": 0.1,
|
| 17 |
+
"hidden_size": 768,
|
| 18 |
+
"initializer_range": 0.02,
|
| 19 |
+
"intermediate_size": 3072,
|
| 20 |
+
"layer_norm_eps": 1e-12,
|
| 21 |
+
"max_position_embeddings": 512,
|
| 22 |
+
"model_type": "bert",
|
| 23 |
+
"num_attention_heads": 12,
|
| 24 |
+
"num_hidden_layers": 12,
|
| 25 |
+
"pad_token_id": 0,
|
| 26 |
+
"position_embedding_type": "absolute",
|
| 27 |
+
"torch_dtype": "float32",
|
| 28 |
+
"transformers_version": "4.51.3",
|
| 29 |
+
"type_vocab_size": 2,
|
| 30 |
+
"use_cache": true,
|
| 31 |
+
"vocab_size": 4096
|
| 32 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"pad_token_id": 0,
|
| 4 |
+
"transformers_version": "4.51.3"
|
| 5 |
+
}
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:021362bcea4fcb6ffd4d39a71b75cc6e7a0b2b8c9f9a3e592a1155cd27f3effc
|
| 3 |
+
size 936711947
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a8556c570222ca9bfb38ddcfacd463dc6f7e7e6920228ad95c5de80e366a2f54
|
| 3 |
+
size 468345303
|
requirements.txt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
torch
|
| 2 |
+
transformers
|
| 3 |
+
einops
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c974aa6e6f13f300b7ec93fe25ab0069903d684b1fb3bbb8a54b0173af962d2d
|
| 3 |
+
size 14645
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:88ae2ad01e8731312f091eddfc4ec4e31d4cd78d95e717f33bff72c55a9c1dd0
|
| 3 |
+
size 1465
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": {
|
| 3 |
+
"content": "[CLS]",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"mask_token": {
|
| 10 |
+
"content": "[MASK]",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "[PAD]",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"sep_token": {
|
| 24 |
+
"content": "[SEP]",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"unk_token": {
|
| 31 |
+
"content": "[UNK]",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
}
|
| 37 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,53 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "[UNK]",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "[CLS]",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "[SEP]",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"3": {
|
| 28 |
+
"content": "[PAD]",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"4": {
|
| 36 |
+
"content": "[MASK]",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"clean_up_tokenization_spaces": false,
|
| 45 |
+
"cls_token": "[CLS]",
|
| 46 |
+
"extra_special_tokens": {},
|
| 47 |
+
"mask_token": "[MASK]",
|
| 48 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 49 |
+
"pad_token": "[PAD]",
|
| 50 |
+
"sep_token": "[SEP]",
|
| 51 |
+
"tokenizer_class": "PreTrainedTokenizer",
|
| 52 |
+
"unk_token": "[UNK]"
|
| 53 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1122 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": 67000,
|
| 3 |
+
"best_metric": 1.3910651206970215,
|
| 4 |
+
"best_model_checkpoint": "/home/auguste/Desktop/eDNA/TeleoClassification/scripts/DNABert2/experiments/masking_training/outputs/masking_teleo/checkpoints/checkpoint-67000",
|
| 5 |
+
"epoch": 108.06451612903226,
|
| 6 |
+
"eval_steps": 1000,
|
| 7 |
+
"global_step": 67000,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.0016129032258064516,
|
| 14 |
+
"grad_norm": 107.56168365478516,
|
| 15 |
+
"learning_rate": 2e-05,
|
| 16 |
+
"loss": 7.9233,
|
| 17 |
+
"step": 1
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 1.6129032258064515,
|
| 21 |
+
"grad_norm": 16.32627296447754,
|
| 22 |
+
"learning_rate": 1.9785161290322584e-05,
|
| 23 |
+
"loss": 3.0779,
|
| 24 |
+
"step": 1000
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 1.6129032258064515,
|
| 28 |
+
"eval_loss": 2.738837718963623,
|
| 29 |
+
"eval_model_preparation_time": 0.0012,
|
| 30 |
+
"eval_runtime": 0.2955,
|
| 31 |
+
"eval_samples_per_second": 1766.611,
|
| 32 |
+
"eval_steps_per_second": 111.682,
|
| 33 |
+
"step": 1000
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 3.225806451612903,
|
| 37 |
+
"grad_norm": 12.881124496459961,
|
| 38 |
+
"learning_rate": 1.9570107526881724e-05,
|
| 39 |
+
"loss": 2.506,
|
| 40 |
+
"step": 2000
|
| 41 |
+
},
|
| 42 |
+
{
|
| 43 |
+
"epoch": 3.225806451612903,
|
| 44 |
+
"eval_loss": 2.4902684688568115,
|
| 45 |
+
"eval_model_preparation_time": 0.0012,
|
| 46 |
+
"eval_runtime": 0.2968,
|
| 47 |
+
"eval_samples_per_second": 1758.892,
|
| 48 |
+
"eval_steps_per_second": 111.194,
|
| 49 |
+
"step": 2000
|
| 50 |
+
},
|
| 51 |
+
{
|
| 52 |
+
"epoch": 4.838709677419355,
|
| 53 |
+
"grad_norm": 12.914713859558105,
|
| 54 |
+
"learning_rate": 1.935505376344086e-05,
|
| 55 |
+
"loss": 2.734,
|
| 56 |
+
"step": 3000
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 4.838709677419355,
|
| 60 |
+
"eval_loss": 2.305058479309082,
|
| 61 |
+
"eval_model_preparation_time": 0.0012,
|
| 62 |
+
"eval_runtime": 0.3006,
|
| 63 |
+
"eval_samples_per_second": 1736.761,
|
| 64 |
+
"eval_steps_per_second": 109.795,
|
| 65 |
+
"step": 3000
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 6.451612903225806,
|
| 69 |
+
"grad_norm": 13.617836952209473,
|
| 70 |
+
"learning_rate": 1.914e-05,
|
| 71 |
+
"loss": 2.2267,
|
| 72 |
+
"step": 4000
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 6.451612903225806,
|
| 76 |
+
"eval_loss": 2.3899621963500977,
|
| 77 |
+
"eval_model_preparation_time": 0.0012,
|
| 78 |
+
"eval_runtime": 0.3004,
|
| 79 |
+
"eval_samples_per_second": 1737.628,
|
| 80 |
+
"eval_steps_per_second": 109.85,
|
| 81 |
+
"step": 4000
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 8.064516129032258,
|
| 85 |
+
"grad_norm": 11.493875503540039,
|
| 86 |
+
"learning_rate": 1.892494623655914e-05,
|
| 87 |
+
"loss": 2.1095,
|
| 88 |
+
"step": 5000
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 8.064516129032258,
|
| 92 |
+
"eval_loss": 2.1791865825653076,
|
| 93 |
+
"eval_model_preparation_time": 0.0012,
|
| 94 |
+
"eval_runtime": 0.2998,
|
| 95 |
+
"eval_samples_per_second": 1740.976,
|
| 96 |
+
"eval_steps_per_second": 110.062,
|
| 97 |
+
"step": 5000
|
| 98 |
+
},
|
| 99 |
+
{
|
| 100 |
+
"epoch": 9.67741935483871,
|
| 101 |
+
"grad_norm": 16.104379653930664,
|
| 102 |
+
"learning_rate": 1.870989247311828e-05,
|
| 103 |
+
"loss": 1.9622,
|
| 104 |
+
"step": 6000
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 9.67741935483871,
|
| 108 |
+
"eval_loss": 2.0534751415252686,
|
| 109 |
+
"eval_model_preparation_time": 0.0012,
|
| 110 |
+
"eval_runtime": 0.3144,
|
| 111 |
+
"eval_samples_per_second": 1660.314,
|
| 112 |
+
"eval_steps_per_second": 104.962,
|
| 113 |
+
"step": 6000
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 11.290322580645162,
|
| 117 |
+
"grad_norm": 15.933501243591309,
|
| 118 |
+
"learning_rate": 1.8494838709677422e-05,
|
| 119 |
+
"loss": 1.8713,
|
| 120 |
+
"step": 7000
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 11.290322580645162,
|
| 124 |
+
"eval_loss": 2.1255111694335938,
|
| 125 |
+
"eval_model_preparation_time": 0.0012,
|
| 126 |
+
"eval_runtime": 0.31,
|
| 127 |
+
"eval_samples_per_second": 1684.034,
|
| 128 |
+
"eval_steps_per_second": 106.462,
|
| 129 |
+
"step": 7000
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 12.903225806451612,
|
| 133 |
+
"grad_norm": 9.397466659545898,
|
| 134 |
+
"learning_rate": 1.8279784946236562e-05,
|
| 135 |
+
"loss": 1.7906,
|
| 136 |
+
"step": 8000
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 12.903225806451612,
|
| 140 |
+
"eval_loss": 1.9397249221801758,
|
| 141 |
+
"eval_model_preparation_time": 0.0012,
|
| 142 |
+
"eval_runtime": 0.3026,
|
| 143 |
+
"eval_samples_per_second": 1724.803,
|
| 144 |
+
"eval_steps_per_second": 109.039,
|
| 145 |
+
"step": 8000
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 14.516129032258064,
|
| 149 |
+
"grad_norm": 14.291478157043457,
|
| 150 |
+
"learning_rate": 1.8064731182795702e-05,
|
| 151 |
+
"loss": 1.7149,
|
| 152 |
+
"step": 9000
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 14.516129032258064,
|
| 156 |
+
"eval_loss": 1.8910889625549316,
|
| 157 |
+
"eval_model_preparation_time": 0.0012,
|
| 158 |
+
"eval_runtime": 0.3013,
|
| 159 |
+
"eval_samples_per_second": 1732.385,
|
| 160 |
+
"eval_steps_per_second": 109.519,
|
| 161 |
+
"step": 9000
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 16.129032258064516,
|
| 165 |
+
"grad_norm": 15.776030540466309,
|
| 166 |
+
"learning_rate": 1.784967741935484e-05,
|
| 167 |
+
"loss": 1.634,
|
| 168 |
+
"step": 10000
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 16.129032258064516,
|
| 172 |
+
"eval_loss": 1.893878698348999,
|
| 173 |
+
"eval_model_preparation_time": 0.0012,
|
| 174 |
+
"eval_runtime": 0.3023,
|
| 175 |
+
"eval_samples_per_second": 1726.506,
|
| 176 |
+
"eval_steps_per_second": 109.147,
|
| 177 |
+
"step": 10000
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 17.741935483870968,
|
| 181 |
+
"grad_norm": 12.53177547454834,
|
| 182 |
+
"learning_rate": 1.763462365591398e-05,
|
| 183 |
+
"loss": 1.5991,
|
| 184 |
+
"step": 11000
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 17.741935483870968,
|
| 188 |
+
"eval_loss": 1.8701565265655518,
|
| 189 |
+
"eval_model_preparation_time": 0.0012,
|
| 190 |
+
"eval_runtime": 0.3035,
|
| 191 |
+
"eval_samples_per_second": 1720.089,
|
| 192 |
+
"eval_steps_per_second": 108.741,
|
| 193 |
+
"step": 11000
|
| 194 |
+
},
|
| 195 |
+
{
|
| 196 |
+
"epoch": 19.35483870967742,
|
| 197 |
+
"grad_norm": 13.62909984588623,
|
| 198 |
+
"learning_rate": 1.741956989247312e-05,
|
| 199 |
+
"loss": 1.5008,
|
| 200 |
+
"step": 12000
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 19.35483870967742,
|
| 204 |
+
"eval_loss": 1.7572582960128784,
|
| 205 |
+
"eval_model_preparation_time": 0.0012,
|
| 206 |
+
"eval_runtime": 0.3051,
|
| 207 |
+
"eval_samples_per_second": 1710.701,
|
| 208 |
+
"eval_steps_per_second": 108.148,
|
| 209 |
+
"step": 12000
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 20.967741935483872,
|
| 213 |
+
"grad_norm": 13.886764526367188,
|
| 214 |
+
"learning_rate": 1.720451612903226e-05,
|
| 215 |
+
"loss": 1.4469,
|
| 216 |
+
"step": 13000
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 20.967741935483872,
|
| 220 |
+
"eval_loss": 1.7456613779067993,
|
| 221 |
+
"eval_model_preparation_time": 0.0012,
|
| 222 |
+
"eval_runtime": 0.3048,
|
| 223 |
+
"eval_samples_per_second": 1712.389,
|
| 224 |
+
"eval_steps_per_second": 108.254,
|
| 225 |
+
"step": 13000
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 22.580645161290324,
|
| 229 |
+
"grad_norm": 16.04749870300293,
|
| 230 |
+
"learning_rate": 1.6989462365591397e-05,
|
| 231 |
+
"loss": 1.404,
|
| 232 |
+
"step": 14000
|
| 233 |
+
},
|
| 234 |
+
{
|
| 235 |
+
"epoch": 22.580645161290324,
|
| 236 |
+
"eval_loss": 1.7826714515686035,
|
| 237 |
+
"eval_model_preparation_time": 0.0012,
|
| 238 |
+
"eval_runtime": 0.3034,
|
| 239 |
+
"eval_samples_per_second": 1720.509,
|
| 240 |
+
"eval_steps_per_second": 108.768,
|
| 241 |
+
"step": 14000
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 24.193548387096776,
|
| 245 |
+
"grad_norm": 14.932185173034668,
|
| 246 |
+
"learning_rate": 1.6774408602150537e-05,
|
| 247 |
+
"loss": 1.3552,
|
| 248 |
+
"step": 15000
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 24.193548387096776,
|
| 252 |
+
"eval_loss": 1.7234201431274414,
|
| 253 |
+
"eval_model_preparation_time": 0.0012,
|
| 254 |
+
"eval_runtime": 0.3061,
|
| 255 |
+
"eval_samples_per_second": 1705.173,
|
| 256 |
+
"eval_steps_per_second": 107.798,
|
| 257 |
+
"step": 15000
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 25.806451612903224,
|
| 261 |
+
"grad_norm": 8.178566932678223,
|
| 262 |
+
"learning_rate": 1.6559354838709676e-05,
|
| 263 |
+
"loss": 1.313,
|
| 264 |
+
"step": 16000
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 25.806451612903224,
|
| 268 |
+
"eval_loss": 1.8201613426208496,
|
| 269 |
+
"eval_model_preparation_time": 0.0012,
|
| 270 |
+
"eval_runtime": 0.3194,
|
| 271 |
+
"eval_samples_per_second": 1634.314,
|
| 272 |
+
"eval_steps_per_second": 103.319,
|
| 273 |
+
"step": 16000
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 27.419354838709676,
|
| 277 |
+
"grad_norm": 16.086894989013672,
|
| 278 |
+
"learning_rate": 1.634430107526882e-05,
|
| 279 |
+
"loss": 1.2751,
|
| 280 |
+
"step": 17000
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 27.419354838709676,
|
| 284 |
+
"eval_loss": 1.6344752311706543,
|
| 285 |
+
"eval_model_preparation_time": 0.0012,
|
| 286 |
+
"eval_runtime": 0.3053,
|
| 287 |
+
"eval_samples_per_second": 1709.792,
|
| 288 |
+
"eval_steps_per_second": 108.09,
|
| 289 |
+
"step": 17000
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 29.032258064516128,
|
| 293 |
+
"grad_norm": 9.854013442993164,
|
| 294 |
+
"learning_rate": 1.612924731182796e-05,
|
| 295 |
+
"loss": 1.2377,
|
| 296 |
+
"step": 18000
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 29.032258064516128,
|
| 300 |
+
"eval_loss": 1.6381661891937256,
|
| 301 |
+
"eval_model_preparation_time": 0.0012,
|
| 302 |
+
"eval_runtime": 0.343,
|
| 303 |
+
"eval_samples_per_second": 1521.702,
|
| 304 |
+
"eval_steps_per_second": 96.2,
|
| 305 |
+
"step": 18000
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"epoch": 30.64516129032258,
|
| 309 |
+
"grad_norm": 13.270648956298828,
|
| 310 |
+
"learning_rate": 1.59141935483871e-05,
|
| 311 |
+
"loss": 1.1772,
|
| 312 |
+
"step": 19000
|
| 313 |
+
},
|
| 314 |
+
{
|
| 315 |
+
"epoch": 30.64516129032258,
|
| 316 |
+
"eval_loss": 1.6601710319519043,
|
| 317 |
+
"eval_model_preparation_time": 0.0012,
|
| 318 |
+
"eval_runtime": 0.3037,
|
| 319 |
+
"eval_samples_per_second": 1718.661,
|
| 320 |
+
"eval_steps_per_second": 108.651,
|
| 321 |
+
"step": 19000
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 32.25806451612903,
|
| 325 |
+
"grad_norm": 20.389537811279297,
|
| 326 |
+
"learning_rate": 1.569913978494624e-05,
|
| 327 |
+
"loss": 1.176,
|
| 328 |
+
"step": 20000
|
| 329 |
+
},
|
| 330 |
+
{
|
| 331 |
+
"epoch": 32.25806451612903,
|
| 332 |
+
"eval_loss": 1.6632287502288818,
|
| 333 |
+
"eval_model_preparation_time": 0.0012,
|
| 334 |
+
"eval_runtime": 0.3045,
|
| 335 |
+
"eval_samples_per_second": 1714.128,
|
| 336 |
+
"eval_steps_per_second": 108.364,
|
| 337 |
+
"step": 20000
|
| 338 |
+
},
|
| 339 |
+
{
|
| 340 |
+
"epoch": 33.87096774193548,
|
| 341 |
+
"grad_norm": 11.229137420654297,
|
| 342 |
+
"learning_rate": 1.548408602150538e-05,
|
| 343 |
+
"loss": 1.1184,
|
| 344 |
+
"step": 21000
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 33.87096774193548,
|
| 348 |
+
"eval_loss": 1.7555991411209106,
|
| 349 |
+
"eval_model_preparation_time": 0.0012,
|
| 350 |
+
"eval_runtime": 0.3043,
|
| 351 |
+
"eval_samples_per_second": 1715.561,
|
| 352 |
+
"eval_steps_per_second": 108.455,
|
| 353 |
+
"step": 21000
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 35.483870967741936,
|
| 357 |
+
"grad_norm": 10.823155403137207,
|
| 358 |
+
"learning_rate": 1.5269032258064518e-05,
|
| 359 |
+
"loss": 1.0793,
|
| 360 |
+
"step": 22000
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 35.483870967741936,
|
| 364 |
+
"eval_loss": 1.6087384223937988,
|
| 365 |
+
"eval_model_preparation_time": 0.0012,
|
| 366 |
+
"eval_runtime": 0.3059,
|
| 367 |
+
"eval_samples_per_second": 1706.414,
|
| 368 |
+
"eval_steps_per_second": 107.877,
|
| 369 |
+
"step": 22000
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 37.096774193548384,
|
| 373 |
+
"grad_norm": 6.54916524887085,
|
| 374 |
+
"learning_rate": 1.5053978494623658e-05,
|
| 375 |
+
"loss": 1.0632,
|
| 376 |
+
"step": 23000
|
| 377 |
+
},
|
| 378 |
+
{
|
| 379 |
+
"epoch": 37.096774193548384,
|
| 380 |
+
"eval_loss": 1.6815119981765747,
|
| 381 |
+
"eval_model_preparation_time": 0.0012,
|
| 382 |
+
"eval_runtime": 0.3044,
|
| 383 |
+
"eval_samples_per_second": 1714.683,
|
| 384 |
+
"eval_steps_per_second": 108.399,
|
| 385 |
+
"step": 23000
|
| 386 |
+
},
|
| 387 |
+
{
|
| 388 |
+
"epoch": 38.70967741935484,
|
| 389 |
+
"grad_norm": 14.550293922424316,
|
| 390 |
+
"learning_rate": 1.4838924731182798e-05,
|
| 391 |
+
"loss": 1.0185,
|
| 392 |
+
"step": 24000
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 38.70967741935484,
|
| 396 |
+
"eval_loss": 1.6611889600753784,
|
| 397 |
+
"eval_model_preparation_time": 0.0012,
|
| 398 |
+
"eval_runtime": 0.3028,
|
| 399 |
+
"eval_samples_per_second": 1724.12,
|
| 400 |
+
"eval_steps_per_second": 108.996,
|
| 401 |
+
"step": 24000
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 40.32258064516129,
|
| 405 |
+
"grad_norm": 14.825828552246094,
|
| 406 |
+
"learning_rate": 1.4623870967741937e-05,
|
| 407 |
+
"loss": 1.0148,
|
| 408 |
+
"step": 25000
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 40.32258064516129,
|
| 412 |
+
"eval_loss": 1.5314302444458008,
|
| 413 |
+
"eval_model_preparation_time": 0.0012,
|
| 414 |
+
"eval_runtime": 0.3061,
|
| 415 |
+
"eval_samples_per_second": 1705.416,
|
| 416 |
+
"eval_steps_per_second": 107.814,
|
| 417 |
+
"step": 25000
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 41.935483870967744,
|
| 421 |
+
"grad_norm": 15.808582305908203,
|
| 422 |
+
"learning_rate": 1.4408817204301075e-05,
|
| 423 |
+
"loss": 0.9492,
|
| 424 |
+
"step": 26000
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"epoch": 41.935483870967744,
|
| 428 |
+
"eval_loss": 1.717032790184021,
|
| 429 |
+
"eval_model_preparation_time": 0.0012,
|
| 430 |
+
"eval_runtime": 0.3131,
|
| 431 |
+
"eval_samples_per_second": 1667.386,
|
| 432 |
+
"eval_steps_per_second": 105.409,
|
| 433 |
+
"step": 26000
|
| 434 |
+
},
|
| 435 |
+
{
|
| 436 |
+
"epoch": 43.54838709677419,
|
| 437 |
+
"grad_norm": 13.56778621673584,
|
| 438 |
+
"learning_rate": 1.4193763440860215e-05,
|
| 439 |
+
"loss": 0.9352,
|
| 440 |
+
"step": 27000
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 43.54838709677419,
|
| 444 |
+
"eval_loss": 1.631635069847107,
|
| 445 |
+
"eval_model_preparation_time": 0.0012,
|
| 446 |
+
"eval_runtime": 0.3065,
|
| 447 |
+
"eval_samples_per_second": 1703.186,
|
| 448 |
+
"eval_steps_per_second": 107.673,
|
| 449 |
+
"step": 27000
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 45.16129032258065,
|
| 453 |
+
"grad_norm": 14.375411987304688,
|
| 454 |
+
"learning_rate": 1.3978709677419355e-05,
|
| 455 |
+
"loss": 0.9287,
|
| 456 |
+
"step": 28000
|
| 457 |
+
},
|
| 458 |
+
{
|
| 459 |
+
"epoch": 45.16129032258065,
|
| 460 |
+
"eval_loss": 1.643862247467041,
|
| 461 |
+
"eval_model_preparation_time": 0.0012,
|
| 462 |
+
"eval_runtime": 0.3075,
|
| 463 |
+
"eval_samples_per_second": 1697.381,
|
| 464 |
+
"eval_steps_per_second": 107.306,
|
| 465 |
+
"step": 28000
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 46.774193548387096,
|
| 469 |
+
"grad_norm": 12.451338768005371,
|
| 470 |
+
"learning_rate": 1.3763655913978495e-05,
|
| 471 |
+
"loss": 0.9052,
|
| 472 |
+
"step": 29000
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 46.774193548387096,
|
| 476 |
+
"eval_loss": 1.4976590871810913,
|
| 477 |
+
"eval_model_preparation_time": 0.0012,
|
| 478 |
+
"eval_runtime": 0.3151,
|
| 479 |
+
"eval_samples_per_second": 1656.651,
|
| 480 |
+
"eval_steps_per_second": 104.731,
|
| 481 |
+
"step": 29000
|
| 482 |
+
},
|
| 483 |
+
{
|
| 484 |
+
"epoch": 48.38709677419355,
|
| 485 |
+
"grad_norm": 15.790621757507324,
|
| 486 |
+
"learning_rate": 1.3548602150537636e-05,
|
| 487 |
+
"loss": 0.8897,
|
| 488 |
+
"step": 30000
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 48.38709677419355,
|
| 492 |
+
"eval_loss": 1.544758915901184,
|
| 493 |
+
"eval_model_preparation_time": 0.0012,
|
| 494 |
+
"eval_runtime": 0.3045,
|
| 495 |
+
"eval_samples_per_second": 1714.222,
|
| 496 |
+
"eval_steps_per_second": 108.37,
|
| 497 |
+
"step": 30000
|
| 498 |
+
},
|
| 499 |
+
{
|
| 500 |
+
"epoch": 50.0,
|
| 501 |
+
"grad_norm": 15.337139129638672,
|
| 502 |
+
"learning_rate": 1.3333548387096776e-05,
|
| 503 |
+
"loss": 0.9353,
|
| 504 |
+
"step": 31000
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 50.0,
|
| 508 |
+
"eval_loss": 1.7019206285476685,
|
| 509 |
+
"eval_model_preparation_time": 0.0012,
|
| 510 |
+
"eval_runtime": 0.3181,
|
| 511 |
+
"eval_samples_per_second": 1640.743,
|
| 512 |
+
"eval_steps_per_second": 103.725,
|
| 513 |
+
"step": 31000
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 51.61290322580645,
|
| 517 |
+
"grad_norm": 17.48087501525879,
|
| 518 |
+
"learning_rate": 1.3118494623655916e-05,
|
| 519 |
+
"loss": 0.8976,
|
| 520 |
+
"step": 32000
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 51.61290322580645,
|
| 524 |
+
"eval_loss": 1.6256884336471558,
|
| 525 |
+
"eval_model_preparation_time": 0.0012,
|
| 526 |
+
"eval_runtime": 0.3131,
|
| 527 |
+
"eval_samples_per_second": 1667.367,
|
| 528 |
+
"eval_steps_per_second": 105.408,
|
| 529 |
+
"step": 32000
|
| 530 |
+
},
|
| 531 |
+
{
|
| 532 |
+
"epoch": 53.225806451612904,
|
| 533 |
+
"grad_norm": 15.387638092041016,
|
| 534 |
+
"learning_rate": 1.2903440860215055e-05,
|
| 535 |
+
"loss": 0.8414,
|
| 536 |
+
"step": 33000
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 53.225806451612904,
|
| 540 |
+
"eval_loss": 1.5139249563217163,
|
| 541 |
+
"eval_model_preparation_time": 0.0012,
|
| 542 |
+
"eval_runtime": 0.3191,
|
| 543 |
+
"eval_samples_per_second": 1635.972,
|
| 544 |
+
"eval_steps_per_second": 103.424,
|
| 545 |
+
"step": 33000
|
| 546 |
+
},
|
| 547 |
+
{
|
| 548 |
+
"epoch": 54.83870967741935,
|
| 549 |
+
"grad_norm": 15.2994384765625,
|
| 550 |
+
"learning_rate": 1.2688387096774195e-05,
|
| 551 |
+
"loss": 0.7897,
|
| 552 |
+
"step": 34000
|
| 553 |
+
},
|
| 554 |
+
{
|
| 555 |
+
"epoch": 54.83870967741935,
|
| 556 |
+
"eval_loss": 1.7013849020004272,
|
| 557 |
+
"eval_model_preparation_time": 0.0012,
|
| 558 |
+
"eval_runtime": 0.3268,
|
| 559 |
+
"eval_samples_per_second": 1597.145,
|
| 560 |
+
"eval_steps_per_second": 100.969,
|
| 561 |
+
"step": 34000
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 56.45161290322581,
|
| 565 |
+
"grad_norm": 14.40909481048584,
|
| 566 |
+
"learning_rate": 1.2473333333333335e-05,
|
| 567 |
+
"loss": 0.8627,
|
| 568 |
+
"step": 35000
|
| 569 |
+
},
|
| 570 |
+
{
|
| 571 |
+
"epoch": 56.45161290322581,
|
| 572 |
+
"eval_loss": 1.7141073942184448,
|
| 573 |
+
"eval_model_preparation_time": 0.0012,
|
| 574 |
+
"eval_runtime": 0.3089,
|
| 575 |
+
"eval_samples_per_second": 1689.899,
|
| 576 |
+
"eval_steps_per_second": 106.833,
|
| 577 |
+
"step": 35000
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 58.064516129032256,
|
| 581 |
+
"grad_norm": 19.243818283081055,
|
| 582 |
+
"learning_rate": 1.2258279569892474e-05,
|
| 583 |
+
"loss": 0.9135,
|
| 584 |
+
"step": 36000
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 58.064516129032256,
|
| 588 |
+
"eval_loss": 1.678747296333313,
|
| 589 |
+
"eval_model_preparation_time": 0.0012,
|
| 590 |
+
"eval_runtime": 0.3278,
|
| 591 |
+
"eval_samples_per_second": 1592.41,
|
| 592 |
+
"eval_steps_per_second": 100.67,
|
| 593 |
+
"step": 36000
|
| 594 |
+
},
|
| 595 |
+
{
|
| 596 |
+
"epoch": 59.67741935483871,
|
| 597 |
+
"grad_norm": 14.35431957244873,
|
| 598 |
+
"learning_rate": 1.2043225806451614e-05,
|
| 599 |
+
"loss": 0.9226,
|
| 600 |
+
"step": 37000
|
| 601 |
+
},
|
| 602 |
+
{
|
| 603 |
+
"epoch": 59.67741935483871,
|
| 604 |
+
"eval_loss": 1.9941015243530273,
|
| 605 |
+
"eval_model_preparation_time": 0.0012,
|
| 606 |
+
"eval_runtime": 0.3066,
|
| 607 |
+
"eval_samples_per_second": 1702.667,
|
| 608 |
+
"eval_steps_per_second": 107.64,
|
| 609 |
+
"step": 37000
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 61.29032258064516,
|
| 613 |
+
"grad_norm": 16.02369499206543,
|
| 614 |
+
"learning_rate": 1.1828172043010752e-05,
|
| 615 |
+
"loss": 0.8849,
|
| 616 |
+
"step": 38000
|
| 617 |
+
},
|
| 618 |
+
{
|
| 619 |
+
"epoch": 61.29032258064516,
|
| 620 |
+
"eval_loss": 1.5911988019943237,
|
| 621 |
+
"eval_model_preparation_time": 0.0012,
|
| 622 |
+
"eval_runtime": 0.3059,
|
| 623 |
+
"eval_samples_per_second": 1706.321,
|
| 624 |
+
"eval_steps_per_second": 107.871,
|
| 625 |
+
"step": 38000
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 62.903225806451616,
|
| 629 |
+
"grad_norm": 24.164094924926758,
|
| 630 |
+
"learning_rate": 1.1613118279569892e-05,
|
| 631 |
+
"loss": 0.7974,
|
| 632 |
+
"step": 39000
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 62.903225806451616,
|
| 636 |
+
"eval_loss": 1.5700287818908691,
|
| 637 |
+
"eval_model_preparation_time": 0.0012,
|
| 638 |
+
"eval_runtime": 0.3059,
|
| 639 |
+
"eval_samples_per_second": 1706.437,
|
| 640 |
+
"eval_steps_per_second": 107.878,
|
| 641 |
+
"step": 39000
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 64.51612903225806,
|
| 645 |
+
"grad_norm": 10.7676420211792,
|
| 646 |
+
"learning_rate": 1.1398064516129033e-05,
|
| 647 |
+
"loss": 0.7892,
|
| 648 |
+
"step": 40000
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 64.51612903225806,
|
| 652 |
+
"eval_loss": 1.6208666563034058,
|
| 653 |
+
"eval_model_preparation_time": 0.0012,
|
| 654 |
+
"eval_runtime": 0.3135,
|
| 655 |
+
"eval_samples_per_second": 1665.325,
|
| 656 |
+
"eval_steps_per_second": 105.279,
|
| 657 |
+
"step": 40000
|
| 658 |
+
},
|
| 659 |
+
{
|
| 660 |
+
"epoch": 66.12903225806451,
|
| 661 |
+
"grad_norm": 8.90040111541748,
|
| 662 |
+
"learning_rate": 1.1183010752688173e-05,
|
| 663 |
+
"loss": 0.7728,
|
| 664 |
+
"step": 41000
|
| 665 |
+
},
|
| 666 |
+
{
|
| 667 |
+
"epoch": 66.12903225806451,
|
| 668 |
+
"eval_loss": 1.5275108814239502,
|
| 669 |
+
"eval_model_preparation_time": 0.0012,
|
| 670 |
+
"eval_runtime": 0.3064,
|
| 671 |
+
"eval_samples_per_second": 1703.395,
|
| 672 |
+
"eval_steps_per_second": 107.686,
|
| 673 |
+
"step": 41000
|
| 674 |
+
},
|
| 675 |
+
{
|
| 676 |
+
"epoch": 67.74193548387096,
|
| 677 |
+
"grad_norm": 16.836742401123047,
|
| 678 |
+
"learning_rate": 1.0967956989247313e-05,
|
| 679 |
+
"loss": 0.7309,
|
| 680 |
+
"step": 42000
|
| 681 |
+
},
|
| 682 |
+
{
|
| 683 |
+
"epoch": 67.74193548387096,
|
| 684 |
+
"eval_loss": 1.6568617820739746,
|
| 685 |
+
"eval_model_preparation_time": 0.0012,
|
| 686 |
+
"eval_runtime": 0.3052,
|
| 687 |
+
"eval_samples_per_second": 1710.328,
|
| 688 |
+
"eval_steps_per_second": 108.124,
|
| 689 |
+
"step": 42000
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 69.35483870967742,
|
| 693 |
+
"grad_norm": 16.19956398010254,
|
| 694 |
+
"learning_rate": 1.0752903225806453e-05,
|
| 695 |
+
"loss": 0.6891,
|
| 696 |
+
"step": 43000
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 69.35483870967742,
|
| 700 |
+
"eval_loss": 1.4376003742218018,
|
| 701 |
+
"eval_model_preparation_time": 0.0012,
|
| 702 |
+
"eval_runtime": 0.3272,
|
| 703 |
+
"eval_samples_per_second": 1595.464,
|
| 704 |
+
"eval_steps_per_second": 100.863,
|
| 705 |
+
"step": 43000
|
| 706 |
+
},
|
| 707 |
+
{
|
| 708 |
+
"epoch": 70.96774193548387,
|
| 709 |
+
"grad_norm": 19.571664810180664,
|
| 710 |
+
"learning_rate": 1.0537849462365592e-05,
|
| 711 |
+
"loss": 0.6732,
|
| 712 |
+
"step": 44000
|
| 713 |
+
},
|
| 714 |
+
{
|
| 715 |
+
"epoch": 70.96774193548387,
|
| 716 |
+
"eval_loss": 1.6094655990600586,
|
| 717 |
+
"eval_model_preparation_time": 0.0012,
|
| 718 |
+
"eval_runtime": 0.3144,
|
| 719 |
+
"eval_samples_per_second": 1660.491,
|
| 720 |
+
"eval_steps_per_second": 104.974,
|
| 721 |
+
"step": 44000
|
| 722 |
+
},
|
| 723 |
+
{
|
| 724 |
+
"epoch": 72.58064516129032,
|
| 725 |
+
"grad_norm": 11.60450267791748,
|
| 726 |
+
"learning_rate": 1.0322795698924732e-05,
|
| 727 |
+
"loss": 0.6475,
|
| 728 |
+
"step": 45000
|
| 729 |
+
},
|
| 730 |
+
{
|
| 731 |
+
"epoch": 72.58064516129032,
|
| 732 |
+
"eval_loss": 1.569161295890808,
|
| 733 |
+
"eval_model_preparation_time": 0.0012,
|
| 734 |
+
"eval_runtime": 0.3241,
|
| 735 |
+
"eval_samples_per_second": 1610.77,
|
| 736 |
+
"eval_steps_per_second": 101.83,
|
| 737 |
+
"step": 45000
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 74.19354838709677,
|
| 741 |
+
"grad_norm": 14.973388671875,
|
| 742 |
+
"learning_rate": 1.0107741935483872e-05,
|
| 743 |
+
"loss": 0.674,
|
| 744 |
+
"step": 46000
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 74.19354838709677,
|
| 748 |
+
"eval_loss": 1.4532381296157837,
|
| 749 |
+
"eval_model_preparation_time": 0.0012,
|
| 750 |
+
"eval_runtime": 0.3117,
|
| 751 |
+
"eval_samples_per_second": 1674.469,
|
| 752 |
+
"eval_steps_per_second": 105.857,
|
| 753 |
+
"step": 46000
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 75.80645161290323,
|
| 757 |
+
"grad_norm": 19.416486740112305,
|
| 758 |
+
"learning_rate": 9.892688172043012e-06,
|
| 759 |
+
"loss": 0.6339,
|
| 760 |
+
"step": 47000
|
| 761 |
+
},
|
| 762 |
+
{
|
| 763 |
+
"epoch": 75.80645161290323,
|
| 764 |
+
"eval_loss": 1.5601801872253418,
|
| 765 |
+
"eval_model_preparation_time": 0.0012,
|
| 766 |
+
"eval_runtime": 0.3055,
|
| 767 |
+
"eval_samples_per_second": 1708.783,
|
| 768 |
+
"eval_steps_per_second": 108.027,
|
| 769 |
+
"step": 47000
|
| 770 |
+
},
|
| 771 |
+
{
|
| 772 |
+
"epoch": 77.41935483870968,
|
| 773 |
+
"grad_norm": 12.237533569335938,
|
| 774 |
+
"learning_rate": 9.677634408602151e-06,
|
| 775 |
+
"loss": 0.628,
|
| 776 |
+
"step": 48000
|
| 777 |
+
},
|
| 778 |
+
{
|
| 779 |
+
"epoch": 77.41935483870968,
|
| 780 |
+
"eval_loss": 1.5352447032928467,
|
| 781 |
+
"eval_model_preparation_time": 0.0012,
|
| 782 |
+
"eval_runtime": 0.3243,
|
| 783 |
+
"eval_samples_per_second": 1609.448,
|
| 784 |
+
"eval_steps_per_second": 101.747,
|
| 785 |
+
"step": 48000
|
| 786 |
+
},
|
| 787 |
+
{
|
| 788 |
+
"epoch": 79.03225806451613,
|
| 789 |
+
"grad_norm": 8.90131664276123,
|
| 790 |
+
"learning_rate": 9.462580645161291e-06,
|
| 791 |
+
"loss": 0.6123,
|
| 792 |
+
"step": 49000
|
| 793 |
+
},
|
| 794 |
+
{
|
| 795 |
+
"epoch": 79.03225806451613,
|
| 796 |
+
"eval_loss": 1.6023005247116089,
|
| 797 |
+
"eval_model_preparation_time": 0.0012,
|
| 798 |
+
"eval_runtime": 0.3064,
|
| 799 |
+
"eval_samples_per_second": 1703.925,
|
| 800 |
+
"eval_steps_per_second": 107.719,
|
| 801 |
+
"step": 49000
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 80.64516129032258,
|
| 805 |
+
"grad_norm": 19.542125701904297,
|
| 806 |
+
"learning_rate": 9.24752688172043e-06,
|
| 807 |
+
"loss": 0.5913,
|
| 808 |
+
"step": 50000
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 80.64516129032258,
|
| 812 |
+
"eval_loss": 1.4985138177871704,
|
| 813 |
+
"eval_model_preparation_time": 0.0012,
|
| 814 |
+
"eval_runtime": 0.3143,
|
| 815 |
+
"eval_samples_per_second": 1660.843,
|
| 816 |
+
"eval_steps_per_second": 104.996,
|
| 817 |
+
"step": 50000
|
| 818 |
+
},
|
| 819 |
+
{
|
| 820 |
+
"epoch": 82.25806451612904,
|
| 821 |
+
"grad_norm": 15.9403715133667,
|
| 822 |
+
"learning_rate": 9.03247311827957e-06,
|
| 823 |
+
"loss": 0.5919,
|
| 824 |
+
"step": 51000
|
| 825 |
+
},
|
| 826 |
+
{
|
| 827 |
+
"epoch": 82.25806451612904,
|
| 828 |
+
"eval_loss": 1.557279109954834,
|
| 829 |
+
"eval_model_preparation_time": 0.0012,
|
| 830 |
+
"eval_runtime": 0.3138,
|
| 831 |
+
"eval_samples_per_second": 1663.684,
|
| 832 |
+
"eval_steps_per_second": 105.175,
|
| 833 |
+
"step": 51000
|
| 834 |
+
},
|
| 835 |
+
{
|
| 836 |
+
"epoch": 83.87096774193549,
|
| 837 |
+
"grad_norm": 16.341463088989258,
|
| 838 |
+
"learning_rate": 8.81741935483871e-06,
|
| 839 |
+
"loss": 0.5849,
|
| 840 |
+
"step": 52000
|
| 841 |
+
},
|
| 842 |
+
{
|
| 843 |
+
"epoch": 83.87096774193549,
|
| 844 |
+
"eval_loss": 1.744088888168335,
|
| 845 |
+
"eval_model_preparation_time": 0.0012,
|
| 846 |
+
"eval_runtime": 0.3074,
|
| 847 |
+
"eval_samples_per_second": 1698.241,
|
| 848 |
+
"eval_steps_per_second": 107.36,
|
| 849 |
+
"step": 52000
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 85.48387096774194,
|
| 853 |
+
"grad_norm": 17.496572494506836,
|
| 854 |
+
"learning_rate": 8.60236559139785e-06,
|
| 855 |
+
"loss": 0.5798,
|
| 856 |
+
"step": 53000
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 85.48387096774194,
|
| 860 |
+
"eval_loss": 1.5605759620666504,
|
| 861 |
+
"eval_model_preparation_time": 0.0012,
|
| 862 |
+
"eval_runtime": 0.3312,
|
| 863 |
+
"eval_samples_per_second": 1576.078,
|
| 864 |
+
"eval_steps_per_second": 99.637,
|
| 865 |
+
"step": 53000
|
| 866 |
+
},
|
| 867 |
+
{
|
| 868 |
+
"epoch": 87.09677419354838,
|
| 869 |
+
"grad_norm": 22.154132843017578,
|
| 870 |
+
"learning_rate": 8.38731182795699e-06,
|
| 871 |
+
"loss": 0.5627,
|
| 872 |
+
"step": 54000
|
| 873 |
+
},
|
| 874 |
+
{
|
| 875 |
+
"epoch": 87.09677419354838,
|
| 876 |
+
"eval_loss": 1.486401081085205,
|
| 877 |
+
"eval_model_preparation_time": 0.0012,
|
| 878 |
+
"eval_runtime": 0.3046,
|
| 879 |
+
"eval_samples_per_second": 1713.463,
|
| 880 |
+
"eval_steps_per_second": 108.322,
|
| 881 |
+
"step": 54000
|
| 882 |
+
},
|
| 883 |
+
{
|
| 884 |
+
"epoch": 88.70967741935483,
|
| 885 |
+
"grad_norm": 12.007641792297363,
|
| 886 |
+
"learning_rate": 8.17225806451613e-06,
|
| 887 |
+
"loss": 0.5926,
|
| 888 |
+
"step": 55000
|
| 889 |
+
},
|
| 890 |
+
{
|
| 891 |
+
"epoch": 88.70967741935483,
|
| 892 |
+
"eval_loss": 1.533622145652771,
|
| 893 |
+
"eval_model_preparation_time": 0.0012,
|
| 894 |
+
"eval_runtime": 0.3189,
|
| 895 |
+
"eval_samples_per_second": 1636.753,
|
| 896 |
+
"eval_steps_per_second": 103.473,
|
| 897 |
+
"step": 55000
|
| 898 |
+
},
|
| 899 |
+
{
|
| 900 |
+
"epoch": 90.3225806451613,
|
| 901 |
+
"grad_norm": 16.921255111694336,
|
| 902 |
+
"learning_rate": 7.957204301075269e-06,
|
| 903 |
+
"loss": 0.5737,
|
| 904 |
+
"step": 56000
|
| 905 |
+
},
|
| 906 |
+
{
|
| 907 |
+
"epoch": 90.3225806451613,
|
| 908 |
+
"eval_loss": 1.595588207244873,
|
| 909 |
+
"eval_model_preparation_time": 0.0012,
|
| 910 |
+
"eval_runtime": 0.3248,
|
| 911 |
+
"eval_samples_per_second": 1607.001,
|
| 912 |
+
"eval_steps_per_second": 101.592,
|
| 913 |
+
"step": 56000
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 91.93548387096774,
|
| 917 |
+
"grad_norm": 14.567840576171875,
|
| 918 |
+
"learning_rate": 7.74215053763441e-06,
|
| 919 |
+
"loss": 0.5521,
|
| 920 |
+
"step": 57000
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 91.93548387096774,
|
| 924 |
+
"eval_loss": 1.6286988258361816,
|
| 925 |
+
"eval_model_preparation_time": 0.0012,
|
| 926 |
+
"eval_runtime": 0.308,
|
| 927 |
+
"eval_samples_per_second": 1694.658,
|
| 928 |
+
"eval_steps_per_second": 107.134,
|
| 929 |
+
"step": 57000
|
| 930 |
+
},
|
| 931 |
+
{
|
| 932 |
+
"epoch": 93.54838709677419,
|
| 933 |
+
"grad_norm": 7.83158016204834,
|
| 934 |
+
"learning_rate": 7.5270967741935486e-06,
|
| 935 |
+
"loss": 0.5672,
|
| 936 |
+
"step": 58000
|
| 937 |
+
},
|
| 938 |
+
{
|
| 939 |
+
"epoch": 93.54838709677419,
|
| 940 |
+
"eval_loss": 1.6612709760665894,
|
| 941 |
+
"eval_model_preparation_time": 0.0012,
|
| 942 |
+
"eval_runtime": 0.3047,
|
| 943 |
+
"eval_samples_per_second": 1713.282,
|
| 944 |
+
"eval_steps_per_second": 108.311,
|
| 945 |
+
"step": 58000
|
| 946 |
+
},
|
| 947 |
+
{
|
| 948 |
+
"epoch": 95.16129032258064,
|
| 949 |
+
"grad_norm": 20.766202926635742,
|
| 950 |
+
"learning_rate": 7.312043010752688e-06,
|
| 951 |
+
"loss": 0.5685,
|
| 952 |
+
"step": 59000
|
| 953 |
+
},
|
| 954 |
+
{
|
| 955 |
+
"epoch": 95.16129032258064,
|
| 956 |
+
"eval_loss": 1.5319266319274902,
|
| 957 |
+
"eval_model_preparation_time": 0.0012,
|
| 958 |
+
"eval_runtime": 0.3061,
|
| 959 |
+
"eval_samples_per_second": 1705.367,
|
| 960 |
+
"eval_steps_per_second": 107.811,
|
| 961 |
+
"step": 59000
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 96.7741935483871,
|
| 965 |
+
"grad_norm": 13.834534645080566,
|
| 966 |
+
"learning_rate": 7.096989247311829e-06,
|
| 967 |
+
"loss": 0.5394,
|
| 968 |
+
"step": 60000
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 96.7741935483871,
|
| 972 |
+
"eval_loss": 1.5068557262420654,
|
| 973 |
+
"eval_model_preparation_time": 0.0012,
|
| 974 |
+
"eval_runtime": 0.3061,
|
| 975 |
+
"eval_samples_per_second": 1705.255,
|
| 976 |
+
"eval_steps_per_second": 107.803,
|
| 977 |
+
"step": 60000
|
| 978 |
+
},
|
| 979 |
+
{
|
| 980 |
+
"epoch": 98.38709677419355,
|
| 981 |
+
"grad_norm": 9.130626678466797,
|
| 982 |
+
"learning_rate": 6.881935483870969e-06,
|
| 983 |
+
"loss": 0.5095,
|
| 984 |
+
"step": 61000
|
| 985 |
+
},
|
| 986 |
+
{
|
| 987 |
+
"epoch": 98.38709677419355,
|
| 988 |
+
"eval_loss": 1.4926313161849976,
|
| 989 |
+
"eval_model_preparation_time": 0.0012,
|
| 990 |
+
"eval_runtime": 0.3074,
|
| 991 |
+
"eval_samples_per_second": 1698.19,
|
| 992 |
+
"eval_steps_per_second": 107.357,
|
| 993 |
+
"step": 61000
|
| 994 |
+
},
|
| 995 |
+
{
|
| 996 |
+
"epoch": 100.0,
|
| 997 |
+
"grad_norm": 18.79903793334961,
|
| 998 |
+
"learning_rate": 6.666881720430108e-06,
|
| 999 |
+
"loss": 0.5327,
|
| 1000 |
+
"step": 62000
|
| 1001 |
+
},
|
| 1002 |
+
{
|
| 1003 |
+
"epoch": 100.0,
|
| 1004 |
+
"eval_loss": 1.4378135204315186,
|
| 1005 |
+
"eval_model_preparation_time": 0.0012,
|
| 1006 |
+
"eval_runtime": 0.3146,
|
| 1007 |
+
"eval_samples_per_second": 1659.02,
|
| 1008 |
+
"eval_steps_per_second": 104.881,
|
| 1009 |
+
"step": 62000
|
| 1010 |
+
},
|
| 1011 |
+
{
|
| 1012 |
+
"epoch": 101.61290322580645,
|
| 1013 |
+
"grad_norm": 17.528038024902344,
|
| 1014 |
+
"learning_rate": 6.451827956989248e-06,
|
| 1015 |
+
"loss": 0.5108,
|
| 1016 |
+
"step": 63000
|
| 1017 |
+
},
|
| 1018 |
+
{
|
| 1019 |
+
"epoch": 101.61290322580645,
|
| 1020 |
+
"eval_loss": 1.4716895818710327,
|
| 1021 |
+
"eval_model_preparation_time": 0.0012,
|
| 1022 |
+
"eval_runtime": 0.3118,
|
| 1023 |
+
"eval_samples_per_second": 1673.899,
|
| 1024 |
+
"eval_steps_per_second": 105.821,
|
| 1025 |
+
"step": 63000
|
| 1026 |
+
},
|
| 1027 |
+
{
|
| 1028 |
+
"epoch": 103.2258064516129,
|
| 1029 |
+
"grad_norm": 9.862174034118652,
|
| 1030 |
+
"learning_rate": 6.236774193548387e-06,
|
| 1031 |
+
"loss": 0.4874,
|
| 1032 |
+
"step": 64000
|
| 1033 |
+
},
|
| 1034 |
+
{
|
| 1035 |
+
"epoch": 103.2258064516129,
|
| 1036 |
+
"eval_loss": 1.519917368888855,
|
| 1037 |
+
"eval_model_preparation_time": 0.0012,
|
| 1038 |
+
"eval_runtime": 0.3105,
|
| 1039 |
+
"eval_samples_per_second": 1681.31,
|
| 1040 |
+
"eval_steps_per_second": 106.29,
|
| 1041 |
+
"step": 64000
|
| 1042 |
+
},
|
| 1043 |
+
{
|
| 1044 |
+
"epoch": 104.83870967741936,
|
| 1045 |
+
"grad_norm": 11.85350513458252,
|
| 1046 |
+
"learning_rate": 6.0217204301075275e-06,
|
| 1047 |
+
"loss": 0.4856,
|
| 1048 |
+
"step": 65000
|
| 1049 |
+
},
|
| 1050 |
+
{
|
| 1051 |
+
"epoch": 104.83870967741936,
|
| 1052 |
+
"eval_loss": 1.5175796747207642,
|
| 1053 |
+
"eval_model_preparation_time": 0.0012,
|
| 1054 |
+
"eval_runtime": 0.3143,
|
| 1055 |
+
"eval_samples_per_second": 1661.035,
|
| 1056 |
+
"eval_steps_per_second": 105.008,
|
| 1057 |
+
"step": 65000
|
| 1058 |
+
},
|
| 1059 |
+
{
|
| 1060 |
+
"epoch": 106.45161290322581,
|
| 1061 |
+
"grad_norm": 21.145742416381836,
|
| 1062 |
+
"learning_rate": 5.806666666666667e-06,
|
| 1063 |
+
"loss": 0.4665,
|
| 1064 |
+
"step": 66000
|
| 1065 |
+
},
|
| 1066 |
+
{
|
| 1067 |
+
"epoch": 106.45161290322581,
|
| 1068 |
+
"eval_loss": 1.5837030410766602,
|
| 1069 |
+
"eval_model_preparation_time": 0.0012,
|
| 1070 |
+
"eval_runtime": 0.3108,
|
| 1071 |
+
"eval_samples_per_second": 1679.611,
|
| 1072 |
+
"eval_steps_per_second": 106.182,
|
| 1073 |
+
"step": 66000
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 108.06451612903226,
|
| 1077 |
+
"grad_norm": 8.358002662658691,
|
| 1078 |
+
"learning_rate": 5.591612903225807e-06,
|
| 1079 |
+
"loss": 0.4846,
|
| 1080 |
+
"step": 67000
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"epoch": 108.06451612903226,
|
| 1084 |
+
"eval_loss": 1.3910651206970215,
|
| 1085 |
+
"eval_model_preparation_time": 0.0012,
|
| 1086 |
+
"eval_runtime": 0.3115,
|
| 1087 |
+
"eval_samples_per_second": 1676.029,
|
| 1088 |
+
"eval_steps_per_second": 105.956,
|
| 1089 |
+
"step": 67000
|
| 1090 |
+
}
|
| 1091 |
+
],
|
| 1092 |
+
"logging_steps": 1000,
|
| 1093 |
+
"max_steps": 93000,
|
| 1094 |
+
"num_input_tokens_seen": 0,
|
| 1095 |
+
"num_train_epochs": 150,
|
| 1096 |
+
"save_steps": 1000,
|
| 1097 |
+
"stateful_callbacks": {
|
| 1098 |
+
"EarlyStoppingCallback": {
|
| 1099 |
+
"args": {
|
| 1100 |
+
"early_stopping_patience": 80,
|
| 1101 |
+
"early_stopping_threshold": 0.0
|
| 1102 |
+
},
|
| 1103 |
+
"attributes": {
|
| 1104 |
+
"early_stopping_patience_counter": 0
|
| 1105 |
+
}
|
| 1106 |
+
},
|
| 1107 |
+
"TrainerControl": {
|
| 1108 |
+
"args": {
|
| 1109 |
+
"should_epoch_stop": false,
|
| 1110 |
+
"should_evaluate": false,
|
| 1111 |
+
"should_log": false,
|
| 1112 |
+
"should_save": true,
|
| 1113 |
+
"should_training_stop": false
|
| 1114 |
+
},
|
| 1115 |
+
"attributes": {}
|
| 1116 |
+
}
|
| 1117 |
+
},
|
| 1118 |
+
"total_flos": 1.1978332035428352e+16,
|
| 1119 |
+
"train_batch_size": 16,
|
| 1120 |
+
"trial_name": null,
|
| 1121 |
+
"trial_params": null
|
| 1122 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:015f7697b0ed907e67af5984ad66287dbd7e699787c9cb3398b8db4208a469cb
|
| 3 |
+
size 5905
|