Md Mushfiqur Rahman
commited on
Commit
•
cd31e4f
1
Parent(s):
b087a37
Upload with huggingface_hub
Browse files- README.md +15 -0
- all_results.json +26 -0
- config.json +51 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +1 -0
- test_predictions.txt +0 -0
- tokenizer_config.json +1 -0
- trainer_state.json +1105 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- canine
|
| 5 |
+
- pretrained-on-english-language
|
| 6 |
+
---
|
| 7 |
+
|
| 8 |
+
### How to use
|
| 9 |
+
|
| 10 |
+
Here is how to use this model:
|
| 11 |
+
|
| 12 |
+
```python
|
| 13 |
+
from transformers import CanineModel
|
| 14 |
+
model = CanineModel.from_pretrained('mushfiqur11/<repo name>')
|
| 15 |
+
```
|
all_results.json
ADDED
|
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 34.17,
|
| 3 |
+
"eval_accuracy_score": 0.9847692967744451,
|
| 4 |
+
"eval_f1": 0.9102957175353575,
|
| 5 |
+
"eval_loss": 0.1090984046459198,
|
| 6 |
+
"eval_precision": 0.9018224573780129,
|
| 7 |
+
"eval_recall": 0.9189297124600639,
|
| 8 |
+
"eval_runtime": 25.3996,
|
| 9 |
+
"eval_samples": 3250,
|
| 10 |
+
"eval_samples_per_second": 127.955,
|
| 11 |
+
"eval_steps_per_second": 16.024,
|
| 12 |
+
"test_accuracy_score": 0.9745238043876868,
|
| 13 |
+
"test_f1": 0.8645980253878702,
|
| 14 |
+
"test_loss": 0.23659789562225342,
|
| 15 |
+
"test_precision": 0.8587152291374824,
|
| 16 |
+
"test_recall": 0.8705619801176709,
|
| 17 |
+
"test_runtime": 27.0108,
|
| 18 |
+
"test_samples": 3453,
|
| 19 |
+
"test_samples_per_second": 127.838,
|
| 20 |
+
"test_steps_per_second": 15.994,
|
| 21 |
+
"train_loss": 0.023325540216763814,
|
| 22 |
+
"train_runtime": 9228.2252,
|
| 23 |
+
"train_samples": 14042,
|
| 24 |
+
"train_samples_per_second": 52.014,
|
| 25 |
+
"train_steps_per_second": 1.625
|
| 26 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "google/canine-c",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"CanineForTokenClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"bos_token_id": 57344,
|
| 8 |
+
"downsampling_rate": 4,
|
| 9 |
+
"eos_token_id": 57345,
|
| 10 |
+
"hidden_act": "gelu",
|
| 11 |
+
"hidden_dropout_prob": 0.1,
|
| 12 |
+
"hidden_size": 768,
|
| 13 |
+
"id2label": {
|
| 14 |
+
"0": "O",
|
| 15 |
+
"1": "B-DATE",
|
| 16 |
+
"2": "I-DATE",
|
| 17 |
+
"3": "B-PER",
|
| 18 |
+
"4": "I-PER",
|
| 19 |
+
"5": "B-ORG",
|
| 20 |
+
"6": "I-ORG",
|
| 21 |
+
"7": "B-LOC",
|
| 22 |
+
"8": "I-LOC"
|
| 23 |
+
},
|
| 24 |
+
"initializer_range": 0.02,
|
| 25 |
+
"intermediate_size": 3072,
|
| 26 |
+
"label2id": {
|
| 27 |
+
"B-DATE": 1,
|
| 28 |
+
"B-LOC": 7,
|
| 29 |
+
"B-ORG": 5,
|
| 30 |
+
"B-PER": 3,
|
| 31 |
+
"I-DATE": 2,
|
| 32 |
+
"I-LOC": 8,
|
| 33 |
+
"I-ORG": 6,
|
| 34 |
+
"I-PER": 4,
|
| 35 |
+
"O": 0
|
| 36 |
+
},
|
| 37 |
+
"layer_norm_eps": 1e-12,
|
| 38 |
+
"local_transformer_stride": 128,
|
| 39 |
+
"max_position_embeddings": 16384,
|
| 40 |
+
"model_type": "canine",
|
| 41 |
+
"num_attention_heads": 12,
|
| 42 |
+
"num_hash_buckets": 16384,
|
| 43 |
+
"num_hash_functions": 8,
|
| 44 |
+
"num_hidden_layers": 12,
|
| 45 |
+
"pad_token_id": 0,
|
| 46 |
+
"torch_dtype": "float32",
|
| 47 |
+
"transformers_version": "4.17.0",
|
| 48 |
+
"type_vocab_size": 16,
|
| 49 |
+
"upsampling_kernel_size": 4,
|
| 50 |
+
"use_cache": true
|
| 51 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a7cea9afa4e336f759061fa22f1ba20a2e95733d88cfb6f00e8cd43d4b578b92
|
| 3 |
+
size 528594737
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"bos_token": {"content": "", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "eos_token": {"content": "", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "sep_token": {"content": "", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "pad_token": {"content": "\u0000", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "cls_token": {"content": "", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "mask_token": {"content": "", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}}
|
test_predictions.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"bos_token": {"content": "", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "sep_token": {"content": "", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "cls_token": {"content": "", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "pad_token": {"content": "\u0000", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "mask_token": {"content": "", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_prefix_space": false, "model_max_length": 2048, "special_tokens_map_file": "/home/mrahma45/.cache/huggingface/transformers/f8be97736b4765e3e8d559b4e7d4f1f531b1621150e5344b600684a27bc84e38.ab71f530366fe02e2834427e7b90198bfd0d573bc4279bfafdb2b95fe2b46dde", "name_or_path": "google/canine-c", "tokenizer_class": "CanineTokenizer"}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1105 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.9102957175353575,
|
| 3 |
+
"best_model_checkpoint": "/scratch/mrahma45/pixel/finetuned_models/canine/canine-base-finetuned-masakhaner-conll_2003_en/checkpoint-15000",
|
| 4 |
+
"epoch": 34.16856492027335,
|
| 5 |
+
"global_step": 15000,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.46,
|
| 12 |
+
"eval_accuracy_score": 0.905671048012793,
|
| 13 |
+
"eval_f1": 0.4031678791785615,
|
| 14 |
+
"eval_loss": 0.3176519572734833,
|
| 15 |
+
"eval_precision": 0.37412408135361475,
|
| 16 |
+
"eval_recall": 0.4371006389776358,
|
| 17 |
+
"eval_runtime": 25.4824,
|
| 18 |
+
"eval_samples_per_second": 127.539,
|
| 19 |
+
"eval_steps_per_second": 15.972,
|
| 20 |
+
"step": 200
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.91,
|
| 24 |
+
"eval_accuracy_score": 0.9367760053044191,
|
| 25 |
+
"eval_f1": 0.600400266844563,
|
| 26 |
+
"eval_loss": 0.20133168995380402,
|
| 27 |
+
"eval_precision": 0.5742935278030994,
|
| 28 |
+
"eval_recall": 0.6289936102236422,
|
| 29 |
+
"eval_runtime": 25.4664,
|
| 30 |
+
"eval_samples_per_second": 127.619,
|
| 31 |
+
"eval_steps_per_second": 15.982,
|
| 32 |
+
"step": 400
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 1.14,
|
| 36 |
+
"learning_rate": 4.865771812080537e-05,
|
| 37 |
+
"loss": 0.3604,
|
| 38 |
+
"step": 500
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 1.37,
|
| 42 |
+
"eval_accuracy_score": 0.9617379773002067,
|
| 43 |
+
"eval_f1": 0.766023166023166,
|
| 44 |
+
"eval_loss": 0.1343105286359787,
|
| 45 |
+
"eval_precision": 0.7414050822122571,
|
| 46 |
+
"eval_recall": 0.792332268370607,
|
| 47 |
+
"eval_runtime": 25.4735,
|
| 48 |
+
"eval_samples_per_second": 127.584,
|
| 49 |
+
"eval_steps_per_second": 15.977,
|
| 50 |
+
"step": 600
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 1.82,
|
| 54 |
+
"eval_accuracy_score": 0.9683294980303444,
|
| 55 |
+
"eval_f1": 0.7997698504027618,
|
| 56 |
+
"eval_loss": 0.11298365145921707,
|
| 57 |
+
"eval_precision": 0.7693726937269373,
|
| 58 |
+
"eval_recall": 0.832667731629393,
|
| 59 |
+
"eval_runtime": 25.4403,
|
| 60 |
+
"eval_samples_per_second": 127.75,
|
| 61 |
+
"eval_steps_per_second": 15.998,
|
| 62 |
+
"step": 800
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 2.28,
|
| 66 |
+
"learning_rate": 4.697986577181208e-05,
|
| 67 |
+
"loss": 0.1118,
|
| 68 |
+
"step": 1000
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 2.28,
|
| 72 |
+
"eval_accuracy_score": 0.9734389016732322,
|
| 73 |
+
"eval_f1": 0.8381742738589212,
|
| 74 |
+
"eval_loss": 0.09904822707176208,
|
| 75 |
+
"eval_precision": 0.8110177404295051,
|
| 76 |
+
"eval_recall": 0.8672124600638977,
|
| 77 |
+
"eval_runtime": 25.4063,
|
| 78 |
+
"eval_samples_per_second": 127.921,
|
| 79 |
+
"eval_steps_per_second": 16.02,
|
| 80 |
+
"step": 1000
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 2.73,
|
| 84 |
+
"eval_accuracy_score": 0.9739654432700183,
|
| 85 |
+
"eval_f1": 0.8414692624916082,
|
| 86 |
+
"eval_loss": 0.09652349352836609,
|
| 87 |
+
"eval_precision": 0.8095589592175678,
|
| 88 |
+
"eval_recall": 0.8759984025559105,
|
| 89 |
+
"eval_runtime": 25.4049,
|
| 90 |
+
"eval_samples_per_second": 127.928,
|
| 91 |
+
"eval_steps_per_second": 16.021,
|
| 92 |
+
"step": 1200
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 3.19,
|
| 96 |
+
"eval_accuracy_score": 0.9777682436912516,
|
| 97 |
+
"eval_f1": 0.8652216748768473,
|
| 98 |
+
"eval_loss": 0.09149660170078278,
|
| 99 |
+
"eval_precision": 0.853947880202256,
|
| 100 |
+
"eval_recall": 0.876797124600639,
|
| 101 |
+
"eval_runtime": 25.4531,
|
| 102 |
+
"eval_samples_per_second": 127.686,
|
| 103 |
+
"eval_steps_per_second": 15.99,
|
| 104 |
+
"step": 1400
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 3.42,
|
| 108 |
+
"learning_rate": 4.530201342281879e-05,
|
| 109 |
+
"loss": 0.0611,
|
| 110 |
+
"step": 1500
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 3.64,
|
| 114 |
+
"eval_accuracy_score": 0.9783922929911463,
|
| 115 |
+
"eval_f1": 0.8685501275259958,
|
| 116 |
+
"eval_loss": 0.08810298144817352,
|
| 117 |
+
"eval_precision": 0.8536444273042808,
|
| 118 |
+
"eval_recall": 0.8839856230031949,
|
| 119 |
+
"eval_runtime": 25.471,
|
| 120 |
+
"eval_samples_per_second": 127.596,
|
| 121 |
+
"eval_steps_per_second": 15.979,
|
| 122 |
+
"step": 1600
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 4.1,
|
| 126 |
+
"eval_accuracy_score": 0.9792113576972581,
|
| 127 |
+
"eval_f1": 0.8704247406537483,
|
| 128 |
+
"eval_loss": 0.08606501668691635,
|
| 129 |
+
"eval_precision": 0.8535508637236084,
|
| 130 |
+
"eval_recall": 0.887979233226837,
|
| 131 |
+
"eval_runtime": 25.4698,
|
| 132 |
+
"eval_samples_per_second": 127.602,
|
| 133 |
+
"eval_steps_per_second": 15.98,
|
| 134 |
+
"step": 1800
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 4.56,
|
| 138 |
+
"learning_rate": 4.36241610738255e-05,
|
| 139 |
+
"loss": 0.0382,
|
| 140 |
+
"step": 2000
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 4.56,
|
| 144 |
+
"eval_accuracy_score": 0.9797574008346659,
|
| 145 |
+
"eval_f1": 0.875222816399287,
|
| 146 |
+
"eval_loss": 0.08422768861055374,
|
| 147 |
+
"eval_precision": 0.8681728880157171,
|
| 148 |
+
"eval_recall": 0.882388178913738,
|
| 149 |
+
"eval_runtime": 25.4807,
|
| 150 |
+
"eval_samples_per_second": 127.547,
|
| 151 |
+
"eval_steps_per_second": 15.973,
|
| 152 |
+
"step": 2000
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 5.01,
|
| 156 |
+
"eval_accuracy_score": 0.9801084285658567,
|
| 157 |
+
"eval_f1": 0.8783047826517477,
|
| 158 |
+
"eval_loss": 0.08461492508649826,
|
| 159 |
+
"eval_precision": 0.8711451581221764,
|
| 160 |
+
"eval_recall": 0.8855830670926518,
|
| 161 |
+
"eval_runtime": 25.4915,
|
| 162 |
+
"eval_samples_per_second": 127.494,
|
| 163 |
+
"eval_steps_per_second": 15.966,
|
| 164 |
+
"step": 2200
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 5.47,
|
| 168 |
+
"eval_accuracy_score": 0.9802839424314521,
|
| 169 |
+
"eval_f1": 0.8772208436724566,
|
| 170 |
+
"eval_loss": 0.0915483608841896,
|
| 171 |
+
"eval_precision": 0.872113676731794,
|
| 172 |
+
"eval_recall": 0.882388178913738,
|
| 173 |
+
"eval_runtime": 25.5288,
|
| 174 |
+
"eval_samples_per_second": 127.307,
|
| 175 |
+
"eval_steps_per_second": 15.943,
|
| 176 |
+
"step": 2400
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 5.69,
|
| 180 |
+
"learning_rate": 4.194630872483222e-05,
|
| 181 |
+
"loss": 0.0269,
|
| 182 |
+
"step": 2500
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 5.92,
|
| 186 |
+
"eval_accuracy_score": 0.9790358438316628,
|
| 187 |
+
"eval_f1": 0.8738092899931258,
|
| 188 |
+
"eval_loss": 0.08523886650800705,
|
| 189 |
+
"eval_precision": 0.8597101449275363,
|
| 190 |
+
"eval_recall": 0.8883785942492013,
|
| 191 |
+
"eval_runtime": 25.4488,
|
| 192 |
+
"eval_samples_per_second": 127.707,
|
| 193 |
+
"eval_steps_per_second": 15.993,
|
| 194 |
+
"step": 2600
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 6.38,
|
| 198 |
+
"eval_accuracy_score": 0.980556964000156,
|
| 199 |
+
"eval_f1": 0.8805166846071044,
|
| 200 |
+
"eval_loss": 0.0843101516366005,
|
| 201 |
+
"eval_precision": 0.8633659566302053,
|
| 202 |
+
"eval_recall": 0.8983626198083067,
|
| 203 |
+
"eval_runtime": 25.4351,
|
| 204 |
+
"eval_samples_per_second": 127.776,
|
| 205 |
+
"eval_steps_per_second": 16.002,
|
| 206 |
+
"step": 2800
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 6.83,
|
| 210 |
+
"learning_rate": 4.026845637583892e-05,
|
| 211 |
+
"loss": 0.0195,
|
| 212 |
+
"step": 3000
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 6.83,
|
| 216 |
+
"eval_accuracy_score": 0.9802449393502086,
|
| 217 |
+
"eval_f1": 0.8802047445614726,
|
| 218 |
+
"eval_loss": 0.09137295186519623,
|
| 219 |
+
"eval_precision": 0.8679867986798679,
|
| 220 |
+
"eval_recall": 0.8927715654952076,
|
| 221 |
+
"eval_runtime": 25.4199,
|
| 222 |
+
"eval_samples_per_second": 127.853,
|
| 223 |
+
"eval_steps_per_second": 16.011,
|
| 224 |
+
"step": 3000
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 7.29,
|
| 228 |
+
"eval_accuracy_score": 0.9824096103592184,
|
| 229 |
+
"eval_f1": 0.8886048569462195,
|
| 230 |
+
"eval_loss": 0.08367849141359329,
|
| 231 |
+
"eval_precision": 0.8752663180321518,
|
| 232 |
+
"eval_recall": 0.9023562300319489,
|
| 233 |
+
"eval_runtime": 25.6211,
|
| 234 |
+
"eval_samples_per_second": 126.849,
|
| 235 |
+
"eval_steps_per_second": 15.885,
|
| 236 |
+
"step": 3200
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 7.74,
|
| 240 |
+
"eval_accuracy_score": 0.9814540348687546,
|
| 241 |
+
"eval_f1": 0.886024025783768,
|
| 242 |
+
"eval_loss": 0.08719700574874878,
|
| 243 |
+
"eval_precision": 0.8671382144905372,
|
| 244 |
+
"eval_recall": 0.9057507987220448,
|
| 245 |
+
"eval_runtime": 25.3936,
|
| 246 |
+
"eval_samples_per_second": 127.985,
|
| 247 |
+
"eval_steps_per_second": 16.028,
|
| 248 |
+
"step": 3400
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 7.97,
|
| 252 |
+
"learning_rate": 3.859060402684564e-05,
|
| 253 |
+
"loss": 0.0136,
|
| 254 |
+
"step": 3500
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 8.2,
|
| 258 |
+
"eval_accuracy_score": 0.9823316041967315,
|
| 259 |
+
"eval_f1": 0.8920094936708859,
|
| 260 |
+
"eval_loss": 0.0911451056599617,
|
| 261 |
+
"eval_precision": 0.8836206896551724,
|
| 262 |
+
"eval_recall": 0.9005591054313099,
|
| 263 |
+
"eval_runtime": 25.4627,
|
| 264 |
+
"eval_samples_per_second": 127.638,
|
| 265 |
+
"eval_steps_per_second": 15.984,
|
| 266 |
+
"step": 3600
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 8.66,
|
| 270 |
+
"eval_accuracy_score": 0.9830921642809782,
|
| 271 |
+
"eval_f1": 0.8962131837307153,
|
| 272 |
+
"eval_loss": 0.08473534882068634,
|
| 273 |
+
"eval_precision": 0.8992762364294331,
|
| 274 |
+
"eval_recall": 0.8931709265175719,
|
| 275 |
+
"eval_runtime": 25.4742,
|
| 276 |
+
"eval_samples_per_second": 127.58,
|
| 277 |
+
"eval_steps_per_second": 15.977,
|
| 278 |
+
"step": 3800
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 9.11,
|
| 282 |
+
"learning_rate": 3.6912751677852356e-05,
|
| 283 |
+
"loss": 0.011,
|
| 284 |
+
"step": 4000
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 9.11,
|
| 288 |
+
"eval_accuracy_score": 0.9824096103592184,
|
| 289 |
+
"eval_f1": 0.8943864878291108,
|
| 290 |
+
"eval_loss": 0.08603190630674362,
|
| 291 |
+
"eval_precision": 0.8900533913387384,
|
| 292 |
+
"eval_recall": 0.8987619808306709,
|
| 293 |
+
"eval_runtime": 25.451,
|
| 294 |
+
"eval_samples_per_second": 127.696,
|
| 295 |
+
"eval_steps_per_second": 15.991,
|
| 296 |
+
"step": 4000
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 9.57,
|
| 300 |
+
"eval_accuracy_score": 0.9822535980342447,
|
| 301 |
+
"eval_f1": 0.8913835548990644,
|
| 302 |
+
"eval_loss": 0.09200570732355118,
|
| 303 |
+
"eval_precision": 0.8793471925393433,
|
| 304 |
+
"eval_recall": 0.9037539936102237,
|
| 305 |
+
"eval_runtime": 25.5623,
|
| 306 |
+
"eval_samples_per_second": 127.141,
|
| 307 |
+
"eval_steps_per_second": 15.922,
|
| 308 |
+
"step": 4200
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 10.02,
|
| 312 |
+
"eval_accuracy_score": 0.9827801396310308,
|
| 313 |
+
"eval_f1": 0.8969183814118342,
|
| 314 |
+
"eval_loss": 0.08794757723808289,
|
| 315 |
+
"eval_precision": 0.8846377937463585,
|
| 316 |
+
"eval_recall": 0.9095447284345048,
|
| 317 |
+
"eval_runtime": 25.5902,
|
| 318 |
+
"eval_samples_per_second": 127.002,
|
| 319 |
+
"eval_steps_per_second": 15.905,
|
| 320 |
+
"step": 4400
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 10.25,
|
| 324 |
+
"learning_rate": 3.523489932885906e-05,
|
| 325 |
+
"loss": 0.0085,
|
| 326 |
+
"step": 4500
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 10.48,
|
| 330 |
+
"eval_accuracy_score": 0.9820000780061625,
|
| 331 |
+
"eval_f1": 0.890210067380103,
|
| 332 |
+
"eval_loss": 0.09557678550481796,
|
| 333 |
+
"eval_precision": 0.8835562549173879,
|
| 334 |
+
"eval_recall": 0.896964856230032,
|
| 335 |
+
"eval_runtime": 25.5311,
|
| 336 |
+
"eval_samples_per_second": 127.296,
|
| 337 |
+
"eval_steps_per_second": 15.941,
|
| 338 |
+
"step": 4600
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 10.93,
|
| 342 |
+
"eval_accuracy_score": 0.9825266196029486,
|
| 343 |
+
"eval_f1": 0.8952569169960475,
|
| 344 |
+
"eval_loss": 0.0915537029504776,
|
| 345 |
+
"eval_precision": 0.886150234741784,
|
| 346 |
+
"eval_recall": 0.9045527156549521,
|
| 347 |
+
"eval_runtime": 25.5326,
|
| 348 |
+
"eval_samples_per_second": 127.288,
|
| 349 |
+
"eval_steps_per_second": 15.94,
|
| 350 |
+
"step": 4800
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 11.39,
|
| 354 |
+
"learning_rate": 3.3557046979865775e-05,
|
| 355 |
+
"loss": 0.0077,
|
| 356 |
+
"step": 5000
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 11.39,
|
| 360 |
+
"eval_accuracy_score": 0.9818635672218106,
|
| 361 |
+
"eval_f1": 0.8888670917116234,
|
| 362 |
+
"eval_loss": 0.09687037765979767,
|
| 363 |
+
"eval_precision": 0.8735299787931367,
|
| 364 |
+
"eval_recall": 0.9047523961661342,
|
| 365 |
+
"eval_runtime": 25.5023,
|
| 366 |
+
"eval_samples_per_second": 127.44,
|
| 367 |
+
"eval_steps_per_second": 15.959,
|
| 368 |
+
"step": 5000
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 11.85,
|
| 372 |
+
"eval_accuracy_score": 0.9833846873903038,
|
| 373 |
+
"eval_f1": 0.9005432098765432,
|
| 374 |
+
"eval_loss": 0.08850205689668655,
|
| 375 |
+
"eval_precision": 0.8909517295290209,
|
| 376 |
+
"eval_recall": 0.9103434504792333,
|
| 377 |
+
"eval_runtime": 25.8091,
|
| 378 |
+
"eval_samples_per_second": 125.925,
|
| 379 |
+
"eval_steps_per_second": 15.77,
|
| 380 |
+
"step": 5200
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 12.3,
|
| 384 |
+
"eval_accuracy_score": 0.9832676781465736,
|
| 385 |
+
"eval_f1": 0.8994011976047904,
|
| 386 |
+
"eval_loss": 0.09829097986221313,
|
| 387 |
+
"eval_precision": 0.8990422984836393,
|
| 388 |
+
"eval_recall": 0.8997603833865815,
|
| 389 |
+
"eval_runtime": 25.5033,
|
| 390 |
+
"eval_samples_per_second": 127.434,
|
| 391 |
+
"eval_steps_per_second": 15.959,
|
| 392 |
+
"step": 5400
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 12.53,
|
| 396 |
+
"learning_rate": 3.1879194630872485e-05,
|
| 397 |
+
"loss": 0.0064,
|
| 398 |
+
"step": 5500
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 12.76,
|
| 402 |
+
"eval_accuracy_score": 0.9810054994344554,
|
| 403 |
+
"eval_f1": 0.8866424575522622,
|
| 404 |
+
"eval_loss": 0.1039794534444809,
|
| 405 |
+
"eval_precision": 0.8718394132406871,
|
| 406 |
+
"eval_recall": 0.9019568690095847,
|
| 407 |
+
"eval_runtime": 25.823,
|
| 408 |
+
"eval_samples_per_second": 125.857,
|
| 409 |
+
"eval_steps_per_second": 15.761,
|
| 410 |
+
"step": 5600
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 13.21,
|
| 414 |
+
"eval_accuracy_score": 0.9827606380904091,
|
| 415 |
+
"eval_f1": 0.8954599761051374,
|
| 416 |
+
"eval_loss": 0.09817508608102798,
|
| 417 |
+
"eval_precision": 0.8929706115965051,
|
| 418 |
+
"eval_recall": 0.8979632587859425,
|
| 419 |
+
"eval_runtime": 25.5457,
|
| 420 |
+
"eval_samples_per_second": 127.223,
|
| 421 |
+
"eval_steps_per_second": 15.932,
|
| 422 |
+
"step": 5800
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 13.67,
|
| 426 |
+
"learning_rate": 3.02013422818792e-05,
|
| 427 |
+
"loss": 0.0053,
|
| 428 |
+
"step": 6000
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 13.67,
|
| 432 |
+
"eval_accuracy_score": 0.9824291118998401,
|
| 433 |
+
"eval_f1": 0.8904041901373655,
|
| 434 |
+
"eval_loss": 0.10226656496524811,
|
| 435 |
+
"eval_precision": 0.8814322050479358,
|
| 436 |
+
"eval_recall": 0.8995607028753994,
|
| 437 |
+
"eval_runtime": 25.5455,
|
| 438 |
+
"eval_samples_per_second": 127.224,
|
| 439 |
+
"eval_steps_per_second": 15.932,
|
| 440 |
+
"step": 6000
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 14.12,
|
| 444 |
+
"eval_accuracy_score": 0.9825461211435703,
|
| 445 |
+
"eval_f1": 0.8980195093112622,
|
| 446 |
+
"eval_loss": 0.10106658190488815,
|
| 447 |
+
"eval_precision": 0.8864034234584711,
|
| 448 |
+
"eval_recall": 0.909944089456869,
|
| 449 |
+
"eval_runtime": 25.4581,
|
| 450 |
+
"eval_samples_per_second": 127.661,
|
| 451 |
+
"eval_steps_per_second": 15.987,
|
| 452 |
+
"step": 6200
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 14.58,
|
| 456 |
+
"eval_accuracy_score": 0.9829361519560045,
|
| 457 |
+
"eval_f1": 0.8955665024630541,
|
| 458 |
+
"eval_loss": 0.10531075298786163,
|
| 459 |
+
"eval_precision": 0.8838973162193698,
|
| 460 |
+
"eval_recall": 0.9075479233226837,
|
| 461 |
+
"eval_runtime": 25.4921,
|
| 462 |
+
"eval_samples_per_second": 127.491,
|
| 463 |
+
"eval_steps_per_second": 15.966,
|
| 464 |
+
"step": 6400
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 14.81,
|
| 468 |
+
"learning_rate": 2.8523489932885905e-05,
|
| 469 |
+
"loss": 0.0047,
|
| 470 |
+
"step": 6500
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 15.03,
|
| 474 |
+
"eval_accuracy_score": 0.9832091735247085,
|
| 475 |
+
"eval_f1": 0.9004636480220973,
|
| 476 |
+
"eval_loss": 0.0937289446592331,
|
| 477 |
+
"eval_precision": 0.8898420744784559,
|
| 478 |
+
"eval_recall": 0.9113418530351438,
|
| 479 |
+
"eval_runtime": 25.4989,
|
| 480 |
+
"eval_samples_per_second": 127.456,
|
| 481 |
+
"eval_steps_per_second": 15.961,
|
| 482 |
+
"step": 6600
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 15.49,
|
| 486 |
+
"eval_accuracy_score": 0.9830141581184914,
|
| 487 |
+
"eval_f1": 0.8983334976826743,
|
| 488 |
+
"eval_loss": 0.10006673634052277,
|
| 489 |
+
"eval_precision": 0.8873952854081434,
|
| 490 |
+
"eval_recall": 0.9095447284345048,
|
| 491 |
+
"eval_runtime": 25.5372,
|
| 492 |
+
"eval_samples_per_second": 127.265,
|
| 493 |
+
"eval_steps_per_second": 15.938,
|
| 494 |
+
"step": 6800
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 15.95,
|
| 498 |
+
"learning_rate": 2.6845637583892618e-05,
|
| 499 |
+
"loss": 0.0037,
|
| 500 |
+
"step": 7000
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 15.95,
|
| 504 |
+
"eval_accuracy_score": 0.9821170872498928,
|
| 505 |
+
"eval_f1": 0.8939078751857356,
|
| 506 |
+
"eval_loss": 0.10096853971481323,
|
| 507 |
+
"eval_precision": 0.886966778061726,
|
| 508 |
+
"eval_recall": 0.9009584664536742,
|
| 509 |
+
"eval_runtime": 25.5089,
|
| 510 |
+
"eval_samples_per_second": 127.406,
|
| 511 |
+
"eval_steps_per_second": 15.955,
|
| 512 |
+
"step": 7000
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 16.4,
|
| 516 |
+
"eval_accuracy_score": 0.9839112289870899,
|
| 517 |
+
"eval_f1": 0.9025406907502977,
|
| 518 |
+
"eval_loss": 0.09699645638465881,
|
| 519 |
+
"eval_precision": 0.8971981057616417,
|
| 520 |
+
"eval_recall": 0.9079472843450479,
|
| 521 |
+
"eval_runtime": 25.3546,
|
| 522 |
+
"eval_samples_per_second": 128.182,
|
| 523 |
+
"eval_steps_per_second": 16.052,
|
| 524 |
+
"step": 7200
|
| 525 |
+
},
|
| 526 |
+
{
|
| 527 |
+
"epoch": 16.86,
|
| 528 |
+
"eval_accuracy_score": 0.9833846873903038,
|
| 529 |
+
"eval_f1": 0.9011811023622048,
|
| 530 |
+
"eval_loss": 0.10188570618629456,
|
| 531 |
+
"eval_precision": 0.8885869565217391,
|
| 532 |
+
"eval_recall": 0.9141373801916933,
|
| 533 |
+
"eval_runtime": 25.3306,
|
| 534 |
+
"eval_samples_per_second": 128.303,
|
| 535 |
+
"eval_steps_per_second": 16.068,
|
| 536 |
+
"step": 7400
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 17.08,
|
| 540 |
+
"learning_rate": 2.516778523489933e-05,
|
| 541 |
+
"loss": 0.003,
|
| 542 |
+
"step": 7500
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 17.31,
|
| 546 |
+
"eval_accuracy_score": 0.9829556534966263,
|
| 547 |
+
"eval_f1": 0.9035664474995019,
|
| 548 |
+
"eval_loss": 0.11874072253704071,
|
| 549 |
+
"eval_precision": 0.9015904572564613,
|
| 550 |
+
"eval_recall": 0.9055511182108626,
|
| 551 |
+
"eval_runtime": 25.391,
|
| 552 |
+
"eval_samples_per_second": 127.998,
|
| 553 |
+
"eval_steps_per_second": 16.029,
|
| 554 |
+
"step": 7600
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 17.77,
|
| 558 |
+
"eval_accuracy_score": 0.9826241273060572,
|
| 559 |
+
"eval_f1": 0.8982106189498388,
|
| 560 |
+
"eval_loss": 0.10930322110652924,
|
| 561 |
+
"eval_precision": 0.880053650124545,
|
| 562 |
+
"eval_recall": 0.917132587859425,
|
| 563 |
+
"eval_runtime": 25.3359,
|
| 564 |
+
"eval_samples_per_second": 128.277,
|
| 565 |
+
"eval_steps_per_second": 16.064,
|
| 566 |
+
"step": 7800
|
| 567 |
+
},
|
| 568 |
+
{
|
| 569 |
+
"epoch": 18.22,
|
| 570 |
+
"learning_rate": 2.348993288590604e-05,
|
| 571 |
+
"loss": 0.0023,
|
| 572 |
+
"step": 8000
|
| 573 |
+
},
|
| 574 |
+
{
|
| 575 |
+
"epoch": 18.22,
|
| 576 |
+
"eval_accuracy_score": 0.9830141581184914,
|
| 577 |
+
"eval_f1": 0.8999901273570936,
|
| 578 |
+
"eval_loss": 0.10627970844507217,
|
| 579 |
+
"eval_precision": 0.8900605350517478,
|
| 580 |
+
"eval_recall": 0.9101437699680511,
|
| 581 |
+
"eval_runtime": 25.3382,
|
| 582 |
+
"eval_samples_per_second": 128.265,
|
| 583 |
+
"eval_steps_per_second": 16.063,
|
| 584 |
+
"step": 8000
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 18.68,
|
| 588 |
+
"eval_accuracy_score": 0.983774718202738,
|
| 589 |
+
"eval_f1": 0.9028480698620622,
|
| 590 |
+
"eval_loss": 0.09893312305212021,
|
| 591 |
+
"eval_precision": 0.8974156638390215,
|
| 592 |
+
"eval_recall": 0.9083466453674122,
|
| 593 |
+
"eval_runtime": 25.3736,
|
| 594 |
+
"eval_samples_per_second": 128.086,
|
| 595 |
+
"eval_steps_per_second": 16.04,
|
| 596 |
+
"step": 8200
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"epoch": 19.13,
|
| 600 |
+
"eval_accuracy_score": 0.9830921642809782,
|
| 601 |
+
"eval_f1": 0.9000591366055589,
|
| 602 |
+
"eval_loss": 0.11214980483055115,
|
| 603 |
+
"eval_precision": 0.8886726352666408,
|
| 604 |
+
"eval_recall": 0.911741214057508,
|
| 605 |
+
"eval_runtime": 25.4824,
|
| 606 |
+
"eval_samples_per_second": 127.539,
|
| 607 |
+
"eval_steps_per_second": 15.972,
|
| 608 |
+
"step": 8400
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 19.36,
|
| 612 |
+
"learning_rate": 2.181208053691275e-05,
|
| 613 |
+
"loss": 0.0022,
|
| 614 |
+
"step": 8500
|
| 615 |
+
},
|
| 616 |
+
{
|
| 617 |
+
"epoch": 19.59,
|
| 618 |
+
"eval_accuracy_score": 0.9835406997152775,
|
| 619 |
+
"eval_f1": 0.8996444093243776,
|
| 620 |
+
"eval_loss": 0.10627951472997665,
|
| 621 |
+
"eval_precision": 0.8901485535574668,
|
| 622 |
+
"eval_recall": 0.9093450479233227,
|
| 623 |
+
"eval_runtime": 25.3697,
|
| 624 |
+
"eval_samples_per_second": 128.105,
|
| 625 |
+
"eval_steps_per_second": 16.043,
|
| 626 |
+
"step": 8600
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 20.05,
|
| 630 |
+
"eval_accuracy_score": 0.9832676781465736,
|
| 631 |
+
"eval_f1": 0.9012602957229334,
|
| 632 |
+
"eval_loss": 0.1101519763469696,
|
| 633 |
+
"eval_precision": 0.8958374432826988,
|
| 634 |
+
"eval_recall": 0.9067492012779552,
|
| 635 |
+
"eval_runtime": 25.36,
|
| 636 |
+
"eval_samples_per_second": 128.154,
|
| 637 |
+
"eval_steps_per_second": 16.049,
|
| 638 |
+
"step": 8800
|
| 639 |
+
},
|
| 640 |
+
{
|
| 641 |
+
"epoch": 20.5,
|
| 642 |
+
"learning_rate": 2.013422818791946e-05,
|
| 643 |
+
"loss": 0.0023,
|
| 644 |
+
"step": 9000
|
| 645 |
+
},
|
| 646 |
+
{
|
| 647 |
+
"epoch": 20.5,
|
| 648 |
+
"eval_accuracy_score": 0.9834626935527907,
|
| 649 |
+
"eval_f1": 0.8975216365066876,
|
| 650 |
+
"eval_loss": 0.10789068043231964,
|
| 651 |
+
"eval_precision": 0.8843023255813953,
|
| 652 |
+
"eval_recall": 0.9111421725239617,
|
| 653 |
+
"eval_runtime": 25.3261,
|
| 654 |
+
"eval_samples_per_second": 128.326,
|
| 655 |
+
"eval_steps_per_second": 16.07,
|
| 656 |
+
"step": 9000
|
| 657 |
+
},
|
| 658 |
+
{
|
| 659 |
+
"epoch": 20.96,
|
| 660 |
+
"eval_accuracy_score": 0.9833456843090604,
|
| 661 |
+
"eval_f1": 0.900358708648864,
|
| 662 |
+
"eval_loss": 0.11746969074010849,
|
| 663 |
+
"eval_precision": 0.8985680190930787,
|
| 664 |
+
"eval_recall": 0.9021565495207667,
|
| 665 |
+
"eval_runtime": 25.4056,
|
| 666 |
+
"eval_samples_per_second": 127.924,
|
| 667 |
+
"eval_steps_per_second": 16.02,
|
| 668 |
+
"step": 9200
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 21.41,
|
| 672 |
+
"eval_accuracy_score": 0.9833651858496821,
|
| 673 |
+
"eval_f1": 0.8977183320220299,
|
| 674 |
+
"eval_loss": 0.1041969433426857,
|
| 675 |
+
"eval_precision": 0.8844961240310077,
|
| 676 |
+
"eval_recall": 0.9113418530351438,
|
| 677 |
+
"eval_runtime": 25.4178,
|
| 678 |
+
"eval_samples_per_second": 127.863,
|
| 679 |
+
"eval_steps_per_second": 16.012,
|
| 680 |
+
"step": 9400
|
| 681 |
+
},
|
| 682 |
+
{
|
| 683 |
+
"epoch": 21.64,
|
| 684 |
+
"learning_rate": 1.8456375838926178e-05,
|
| 685 |
+
"loss": 0.0022,
|
| 686 |
+
"step": 9500
|
| 687 |
+
},
|
| 688 |
+
{
|
| 689 |
+
"epoch": 21.87,
|
| 690 |
+
"eval_accuracy_score": 0.9844572721244979,
|
| 691 |
+
"eval_f1": 0.905930267209695,
|
| 692 |
+
"eval_loss": 0.10449470579624176,
|
| 693 |
+
"eval_precision": 0.901363905910259,
|
| 694 |
+
"eval_recall": 0.9105431309904153,
|
| 695 |
+
"eval_runtime": 25.3884,
|
| 696 |
+
"eval_samples_per_second": 128.011,
|
| 697 |
+
"eval_steps_per_second": 16.031,
|
| 698 |
+
"step": 9600
|
| 699 |
+
},
|
| 700 |
+
{
|
| 701 |
+
"epoch": 22.32,
|
| 702 |
+
"eval_accuracy_score": 0.9839502320683334,
|
| 703 |
+
"eval_f1": 0.9034056960764787,
|
| 704 |
+
"eval_loss": 0.10690420866012573,
|
| 705 |
+
"eval_precision": 0.901072705601907,
|
| 706 |
+
"eval_recall": 0.9057507987220448,
|
| 707 |
+
"eval_runtime": 25.4089,
|
| 708 |
+
"eval_samples_per_second": 127.908,
|
| 709 |
+
"eval_steps_per_second": 16.018,
|
| 710 |
+
"step": 9800
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 22.78,
|
| 714 |
+
"learning_rate": 1.6778523489932888e-05,
|
| 715 |
+
"loss": 0.0019,
|
| 716 |
+
"step": 10000
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 22.78,
|
| 720 |
+
"eval_accuracy_score": 0.9835992043371427,
|
| 721 |
+
"eval_f1": 0.9027144838517931,
|
| 722 |
+
"eval_loss": 0.10763387382030487,
|
| 723 |
+
"eval_precision": 0.8957923712151002,
|
| 724 |
+
"eval_recall": 0.9097444089456869,
|
| 725 |
+
"eval_runtime": 25.3298,
|
| 726 |
+
"eval_samples_per_second": 128.307,
|
| 727 |
+
"eval_steps_per_second": 16.068,
|
| 728 |
+
"step": 10000
|
| 729 |
+
},
|
| 730 |
+
{
|
| 731 |
+
"epoch": 23.23,
|
| 732 |
+
"eval_accuracy_score": 0.9846522875307149,
|
| 733 |
+
"eval_f1": 0.9070299294024062,
|
| 734 |
+
"eval_loss": 0.10220099985599518,
|
| 735 |
+
"eval_precision": 0.9033471974648445,
|
| 736 |
+
"eval_recall": 0.9107428115015974,
|
| 737 |
+
"eval_runtime": 25.3799,
|
| 738 |
+
"eval_samples_per_second": 128.054,
|
| 739 |
+
"eval_steps_per_second": 16.036,
|
| 740 |
+
"step": 10200
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 23.69,
|
| 744 |
+
"eval_accuracy_score": 0.9840282382308202,
|
| 745 |
+
"eval_f1": 0.9080059671805072,
|
| 746 |
+
"eval_loss": 0.11143822968006134,
|
| 747 |
+
"eval_precision": 0.9044977214186646,
|
| 748 |
+
"eval_recall": 0.9115415335463258,
|
| 749 |
+
"eval_runtime": 25.375,
|
| 750 |
+
"eval_samples_per_second": 128.079,
|
| 751 |
+
"eval_steps_per_second": 16.039,
|
| 752 |
+
"step": 10400
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 23.92,
|
| 756 |
+
"learning_rate": 1.51006711409396e-05,
|
| 757 |
+
"loss": 0.0013,
|
| 758 |
+
"step": 10500
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 24.15,
|
| 762 |
+
"eval_accuracy_score": 0.9839502320683334,
|
| 763 |
+
"eval_f1": 0.9035462401907223,
|
| 764 |
+
"eval_loss": 0.11336545646190643,
|
| 765 |
+
"eval_precision": 0.8989918956315477,
|
| 766 |
+
"eval_recall": 0.90814696485623,
|
| 767 |
+
"eval_runtime": 25.4002,
|
| 768 |
+
"eval_samples_per_second": 127.952,
|
| 769 |
+
"eval_steps_per_second": 16.024,
|
| 770 |
+
"step": 10600
|
| 771 |
+
},
|
| 772 |
+
{
|
| 773 |
+
"epoch": 24.6,
|
| 774 |
+
"eval_accuracy_score": 0.9843012597995242,
|
| 775 |
+
"eval_f1": 0.9057239057239057,
|
| 776 |
+
"eval_loss": 0.10835720598697662,
|
| 777 |
+
"eval_precision": 0.8984282907662082,
|
| 778 |
+
"eval_recall": 0.9131389776357828,
|
| 779 |
+
"eval_runtime": 25.3998,
|
| 780 |
+
"eval_samples_per_second": 127.954,
|
| 781 |
+
"eval_steps_per_second": 16.024,
|
| 782 |
+
"step": 10800
|
| 783 |
+
},
|
| 784 |
+
{
|
| 785 |
+
"epoch": 25.06,
|
| 786 |
+
"learning_rate": 1.3422818791946309e-05,
|
| 787 |
+
"loss": 0.0009,
|
| 788 |
+
"step": 11000
|
| 789 |
+
},
|
| 790 |
+
{
|
| 791 |
+
"epoch": 25.06,
|
| 792 |
+
"eval_accuracy_score": 0.984379265962011,
|
| 793 |
+
"eval_f1": 0.9084597837945055,
|
| 794 |
+
"eval_loss": 0.10998024046421051,
|
| 795 |
+
"eval_precision": 0.9024630541871921,
|
| 796 |
+
"eval_recall": 0.9145367412140575,
|
| 797 |
+
"eval_runtime": 25.3705,
|
| 798 |
+
"eval_samples_per_second": 128.102,
|
| 799 |
+
"eval_steps_per_second": 16.042,
|
| 800 |
+
"step": 11000
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 25.51,
|
| 804 |
+
"eval_accuracy_score": 0.9838137212839815,
|
| 805 |
+
"eval_f1": 0.9037773359840955,
|
| 806 |
+
"eval_loss": 0.11049986630678177,
|
| 807 |
+
"eval_precision": 0.8998416468725258,
|
| 808 |
+
"eval_recall": 0.9077476038338658,
|
| 809 |
+
"eval_runtime": 25.3707,
|
| 810 |
+
"eval_samples_per_second": 128.1,
|
| 811 |
+
"eval_steps_per_second": 16.042,
|
| 812 |
+
"step": 11200
|
| 813 |
+
},
|
| 814 |
+
{
|
| 815 |
+
"epoch": 25.97,
|
| 816 |
+
"eval_accuracy_score": 0.9844767736651195,
|
| 817 |
+
"eval_f1": 0.9064790964929661,
|
| 818 |
+
"eval_loss": 0.10651768743991852,
|
| 819 |
+
"eval_precision": 0.8995281163979552,
|
| 820 |
+
"eval_recall": 0.9135383386581469,
|
| 821 |
+
"eval_runtime": 25.4896,
|
| 822 |
+
"eval_samples_per_second": 127.503,
|
| 823 |
+
"eval_steps_per_second": 15.967,
|
| 824 |
+
"step": 11400
|
| 825 |
+
},
|
| 826 |
+
{
|
| 827 |
+
"epoch": 26.2,
|
| 828 |
+
"learning_rate": 1.174496644295302e-05,
|
| 829 |
+
"loss": 0.0012,
|
| 830 |
+
"step": 11500
|
| 831 |
+
},
|
| 832 |
+
{
|
| 833 |
+
"epoch": 26.42,
|
| 834 |
+
"eval_accuracy_score": 0.9842817582589024,
|
| 835 |
+
"eval_f1": 0.9092719848620655,
|
| 836 |
+
"eval_loss": 0.1079045906662941,
|
| 837 |
+
"eval_precision": 0.9070137095171865,
|
| 838 |
+
"eval_recall": 0.9115415335463258,
|
| 839 |
+
"eval_runtime": 25.3954,
|
| 840 |
+
"eval_samples_per_second": 127.976,
|
| 841 |
+
"eval_steps_per_second": 16.027,
|
| 842 |
+
"step": 11600
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 26.88,
|
| 846 |
+
"eval_accuracy_score": 0.984184250555794,
|
| 847 |
+
"eval_f1": 0.9041501976284585,
|
| 848 |
+
"eval_loss": 0.10910345613956451,
|
| 849 |
+
"eval_precision": 0.8949530516431925,
|
| 850 |
+
"eval_recall": 0.9135383386581469,
|
| 851 |
+
"eval_runtime": 25.3926,
|
| 852 |
+
"eval_samples_per_second": 127.99,
|
| 853 |
+
"eval_steps_per_second": 16.028,
|
| 854 |
+
"step": 11800
|
| 855 |
+
},
|
| 856 |
+
{
|
| 857 |
+
"epoch": 27.33,
|
| 858 |
+
"learning_rate": 1.006711409395973e-05,
|
| 859 |
+
"loss": 0.0007,
|
| 860 |
+
"step": 12000
|
| 861 |
+
},
|
| 862 |
+
{
|
| 863 |
+
"epoch": 27.33,
|
| 864 |
+
"eval_accuracy_score": 0.9837942197433597,
|
| 865 |
+
"eval_f1": 0.9048899512000796,
|
| 866 |
+
"eval_loss": 0.11004339158535004,
|
| 867 |
+
"eval_precision": 0.9026425591098748,
|
| 868 |
+
"eval_recall": 0.9071485623003195,
|
| 869 |
+
"eval_runtime": 25.4253,
|
| 870 |
+
"eval_samples_per_second": 127.826,
|
| 871 |
+
"eval_steps_per_second": 16.008,
|
| 872 |
+
"step": 12000
|
| 873 |
+
},
|
| 874 |
+
{
|
| 875 |
+
"epoch": 27.79,
|
| 876 |
+
"eval_accuracy_score": 0.9841452474745505,
|
| 877 |
+
"eval_f1": 0.9081166898194086,
|
| 878 |
+
"eval_loss": 0.10656478255987167,
|
| 879 |
+
"eval_precision": 0.9025641025641026,
|
| 880 |
+
"eval_recall": 0.9137380191693291,
|
| 881 |
+
"eval_runtime": 25.3771,
|
| 882 |
+
"eval_samples_per_second": 128.068,
|
| 883 |
+
"eval_steps_per_second": 16.038,
|
| 884 |
+
"step": 12200
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 28.25,
|
| 888 |
+
"eval_accuracy_score": 0.9843597644213893,
|
| 889 |
+
"eval_f1": 0.9104314038059181,
|
| 890 |
+
"eval_loss": 0.10543405264616013,
|
| 891 |
+
"eval_precision": 0.9085305229667926,
|
| 892 |
+
"eval_recall": 0.9123402555910544,
|
| 893 |
+
"eval_runtime": 25.302,
|
| 894 |
+
"eval_samples_per_second": 128.448,
|
| 895 |
+
"eval_steps_per_second": 16.086,
|
| 896 |
+
"step": 12400
|
| 897 |
+
},
|
| 898 |
+
{
|
| 899 |
+
"epoch": 28.47,
|
| 900 |
+
"learning_rate": 8.389261744966444e-06,
|
| 901 |
+
"loss": 0.0008,
|
| 902 |
+
"step": 12500
|
| 903 |
+
},
|
| 904 |
+
{
|
| 905 |
+
"epoch": 28.7,
|
| 906 |
+
"eval_accuracy_score": 0.9839892351495768,
|
| 907 |
+
"eval_f1": 0.9044737625235593,
|
| 908 |
+
"eval_loss": 0.10808327049016953,
|
| 909 |
+
"eval_precision": 0.8986792824758526,
|
| 910 |
+
"eval_recall": 0.9103434504792333,
|
| 911 |
+
"eval_runtime": 25.3718,
|
| 912 |
+
"eval_samples_per_second": 128.095,
|
| 913 |
+
"eval_steps_per_second": 16.041,
|
| 914 |
+
"step": 12600
|
| 915 |
+
},
|
| 916 |
+
{
|
| 917 |
+
"epoch": 29.16,
|
| 918 |
+
"eval_accuracy_score": 0.9845937829088498,
|
| 919 |
+
"eval_f1": 0.9098848749503771,
|
| 920 |
+
"eval_loss": 0.10423844307661057,
|
| 921 |
+
"eval_precision": 0.904498816101026,
|
| 922 |
+
"eval_recall": 0.9153354632587859,
|
| 923 |
+
"eval_runtime": 25.3457,
|
| 924 |
+
"eval_samples_per_second": 128.227,
|
| 925 |
+
"eval_steps_per_second": 16.058,
|
| 926 |
+
"step": 12800
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 29.61,
|
| 930 |
+
"learning_rate": 6.7114093959731546e-06,
|
| 931 |
+
"loss": 0.0007,
|
| 932 |
+
"step": 13000
|
| 933 |
+
},
|
| 934 |
+
{
|
| 935 |
+
"epoch": 29.61,
|
| 936 |
+
"eval_accuracy_score": 0.9845742813682281,
|
| 937 |
+
"eval_f1": 0.9097922848664688,
|
| 938 |
+
"eval_loss": 0.10766186565160751,
|
| 939 |
+
"eval_precision": 0.9014112112896904,
|
| 940 |
+
"eval_recall": 0.9183306709265175,
|
| 941 |
+
"eval_runtime": 25.3084,
|
| 942 |
+
"eval_samples_per_second": 128.416,
|
| 943 |
+
"eval_steps_per_second": 16.082,
|
| 944 |
+
"step": 13000
|
| 945 |
+
},
|
| 946 |
+
{
|
| 947 |
+
"epoch": 30.07,
|
| 948 |
+
"eval_accuracy_score": 0.9844962752057412,
|
| 949 |
+
"eval_f1": 0.9077182874739247,
|
| 950 |
+
"eval_loss": 0.10705368965864182,
|
| 951 |
+
"eval_precision": 0.9031429136192923,
|
| 952 |
+
"eval_recall": 0.9123402555910544,
|
| 953 |
+
"eval_runtime": 25.4717,
|
| 954 |
+
"eval_samples_per_second": 127.593,
|
| 955 |
+
"eval_steps_per_second": 15.979,
|
| 956 |
+
"step": 13200
|
| 957 |
+
},
|
| 958 |
+
{
|
| 959 |
+
"epoch": 30.52,
|
| 960 |
+
"eval_accuracy_score": 0.9840087366901985,
|
| 961 |
+
"eval_f1": 0.9052005943536403,
|
| 962 |
+
"eval_loss": 0.10472096502780914,
|
| 963 |
+
"eval_precision": 0.8981718104973462,
|
| 964 |
+
"eval_recall": 0.9123402555910544,
|
| 965 |
+
"eval_runtime": 25.4157,
|
| 966 |
+
"eval_samples_per_second": 127.874,
|
| 967 |
+
"eval_steps_per_second": 16.014,
|
| 968 |
+
"step": 13400
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 30.75,
|
| 972 |
+
"learning_rate": 5.033557046979865e-06,
|
| 973 |
+
"loss": 0.0006,
|
| 974 |
+
"step": 13500
|
| 975 |
+
},
|
| 976 |
+
{
|
| 977 |
+
"epoch": 30.98,
|
| 978 |
+
"eval_accuracy_score": 0.9845937829088498,
|
| 979 |
+
"eval_f1": 0.9085492999702115,
|
| 980 |
+
"eval_loss": 0.10349733382463455,
|
| 981 |
+
"eval_precision": 0.9036144578313253,
|
| 982 |
+
"eval_recall": 0.9135383386581469,
|
| 983 |
+
"eval_runtime": 25.5031,
|
| 984 |
+
"eval_samples_per_second": 127.435,
|
| 985 |
+
"eval_steps_per_second": 15.959,
|
| 986 |
+
"step": 13600
|
| 987 |
+
},
|
| 988 |
+
{
|
| 989 |
+
"epoch": 31.44,
|
| 990 |
+
"eval_accuracy_score": 0.9849058075587972,
|
| 991 |
+
"eval_f1": 0.908856746582128,
|
| 992 |
+
"eval_loss": 0.10392281413078308,
|
| 993 |
+
"eval_precision": 0.9018875344081794,
|
| 994 |
+
"eval_recall": 0.9159345047923323,
|
| 995 |
+
"eval_runtime": 25.3529,
|
| 996 |
+
"eval_samples_per_second": 128.191,
|
| 997 |
+
"eval_steps_per_second": 16.053,
|
| 998 |
+
"step": 13800
|
| 999 |
+
},
|
| 1000 |
+
{
|
| 1001 |
+
"epoch": 31.89,
|
| 1002 |
+
"learning_rate": 3.3557046979865773e-06,
|
| 1003 |
+
"loss": 0.0005,
|
| 1004 |
+
"step": 14000
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 31.89,
|
| 1008 |
+
"eval_accuracy_score": 0.9849253090994189,
|
| 1009 |
+
"eval_f1": 0.909863609408974,
|
| 1010 |
+
"eval_loss": 0.10778042674064636,
|
| 1011 |
+
"eval_precision": 0.9007827788649706,
|
| 1012 |
+
"eval_recall": 0.919129392971246,
|
| 1013 |
+
"eval_runtime": 25.3322,
|
| 1014 |
+
"eval_samples_per_second": 128.295,
|
| 1015 |
+
"eval_steps_per_second": 16.066,
|
| 1016 |
+
"step": 14000
|
| 1017 |
+
},
|
| 1018 |
+
{
|
| 1019 |
+
"epoch": 32.35,
|
| 1020 |
+
"eval_accuracy_score": 0.9845742813682281,
|
| 1021 |
+
"eval_f1": 0.9082278481012659,
|
| 1022 |
+
"eval_loss": 0.10826905816793442,
|
| 1023 |
+
"eval_precision": 0.8996865203761756,
|
| 1024 |
+
"eval_recall": 0.9169329073482428,
|
| 1025 |
+
"eval_runtime": 25.3345,
|
| 1026 |
+
"eval_samples_per_second": 128.283,
|
| 1027 |
+
"eval_steps_per_second": 16.065,
|
| 1028 |
+
"step": 14200
|
| 1029 |
+
},
|
| 1030 |
+
{
|
| 1031 |
+
"epoch": 32.8,
|
| 1032 |
+
"eval_accuracy_score": 0.9846522875307149,
|
| 1033 |
+
"eval_f1": 0.9092885375494072,
|
| 1034 |
+
"eval_loss": 0.10940501093864441,
|
| 1035 |
+
"eval_precision": 0.900039123630673,
|
| 1036 |
+
"eval_recall": 0.9187300319488818,
|
| 1037 |
+
"eval_runtime": 25.4019,
|
| 1038 |
+
"eval_samples_per_second": 127.943,
|
| 1039 |
+
"eval_steps_per_second": 16.022,
|
| 1040 |
+
"step": 14400
|
| 1041 |
+
},
|
| 1042 |
+
{
|
| 1043 |
+
"epoch": 33.03,
|
| 1044 |
+
"learning_rate": 1.6778523489932886e-06,
|
| 1045 |
+
"loss": 0.0003,
|
| 1046 |
+
"step": 14500
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 33.26,
|
| 1050 |
+
"eval_accuracy_score": 0.9846912906119584,
|
| 1051 |
+
"eval_f1": 0.9091268664095719,
|
| 1052 |
+
"eval_loss": 0.10913100093603134,
|
| 1053 |
+
"eval_precision": 0.9004897159647405,
|
| 1054 |
+
"eval_recall": 0.9179313099041534,
|
| 1055 |
+
"eval_runtime": 25.3619,
|
| 1056 |
+
"eval_samples_per_second": 128.145,
|
| 1057 |
+
"eval_steps_per_second": 16.048,
|
| 1058 |
+
"step": 14600
|
| 1059 |
+
},
|
| 1060 |
+
{
|
| 1061 |
+
"epoch": 33.71,
|
| 1062 |
+
"eval_accuracy_score": 0.9848278013963103,
|
| 1063 |
+
"eval_f1": 0.9108891306497873,
|
| 1064 |
+
"eval_loss": 0.10917215794324875,
|
| 1065 |
+
"eval_precision": 0.9024103468547913,
|
| 1066 |
+
"eval_recall": 0.9195287539936102,
|
| 1067 |
+
"eval_runtime": 25.4358,
|
| 1068 |
+
"eval_samples_per_second": 127.773,
|
| 1069 |
+
"eval_steps_per_second": 16.001,
|
| 1070 |
+
"step": 14800
|
| 1071 |
+
},
|
| 1072 |
+
{
|
| 1073 |
+
"epoch": 34.17,
|
| 1074 |
+
"learning_rate": 0.0,
|
| 1075 |
+
"loss": 0.0003,
|
| 1076 |
+
"step": 15000
|
| 1077 |
+
},
|
| 1078 |
+
{
|
| 1079 |
+
"epoch": 34.17,
|
| 1080 |
+
"eval_accuracy_score": 0.9847692967744451,
|
| 1081 |
+
"eval_f1": 0.9102957175353575,
|
| 1082 |
+
"eval_loss": 0.1090984046459198,
|
| 1083 |
+
"eval_precision": 0.9018224573780129,
|
| 1084 |
+
"eval_recall": 0.9189297124600639,
|
| 1085 |
+
"eval_runtime": 25.2915,
|
| 1086 |
+
"eval_samples_per_second": 128.501,
|
| 1087 |
+
"eval_steps_per_second": 16.092,
|
| 1088 |
+
"step": 15000
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 34.17,
|
| 1092 |
+
"step": 15000,
|
| 1093 |
+
"total_flos": 7.879039709550797e+16,
|
| 1094 |
+
"train_loss": 0.023325540216763814,
|
| 1095 |
+
"train_runtime": 9228.2252,
|
| 1096 |
+
"train_samples_per_second": 52.014,
|
| 1097 |
+
"train_steps_per_second": 1.625
|
| 1098 |
+
}
|
| 1099 |
+
],
|
| 1100 |
+
"max_steps": 15000,
|
| 1101 |
+
"num_train_epochs": 35,
|
| 1102 |
+
"total_flos": 7.879039709550797e+16,
|
| 1103 |
+
"trial_name": null,
|
| 1104 |
+
"trial_params": null
|
| 1105 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ada586e106b12fc69e74a85eb6ee84e29348f9f88bcfe348f8569f19300c36f5
|
| 3 |
+
size 3259
|