Upload folder using huggingface_hub
Browse filesThis view is limited to 50 files because it contains too many changes. See raw diff
- .gitattributes +2 -0
- Fsoft-AIC__videberta-base/tmp_checkpoints/checkpoint-40000/config.json +40 -0
- Fsoft-AIC__videberta-base/tmp_checkpoints/checkpoint-40000/model.safetensors +3 -0
- Fsoft-AIC__videberta-base/tmp_checkpoints/checkpoint-40000/optimizer.pt +3 -0
- Fsoft-AIC__videberta-base/tmp_checkpoints/checkpoint-40000/rng_state.pth +3 -0
- Fsoft-AIC__videberta-base/tmp_checkpoints/checkpoint-40000/scheduler.pt +3 -0
- Fsoft-AIC__videberta-base/tmp_checkpoints/checkpoint-40000/tokenizer.json +0 -0
- Fsoft-AIC__videberta-base/tmp_checkpoints/checkpoint-40000/tokenizer_config.json +20 -0
- Fsoft-AIC__videberta-base/tmp_checkpoints/checkpoint-40000/trainer_state.json +1243 -0
- Fsoft-AIC__videberta-base/tmp_checkpoints/checkpoint-40000/training_args.bin +3 -0
- Fsoft-AIC__videberta-base/tmp_checkpoints/checkpoint-40500/config.json +40 -0
- Fsoft-AIC__videberta-base/tmp_checkpoints/checkpoint-40500/model.safetensors +3 -0
- Fsoft-AIC__videberta-base/tmp_checkpoints/checkpoint-40500/optimizer.pt +3 -0
- Fsoft-AIC__videberta-base/tmp_checkpoints/checkpoint-40500/rng_state.pth +3 -0
- Fsoft-AIC__videberta-base/tmp_checkpoints/checkpoint-40500/scheduler.pt +3 -0
- Fsoft-AIC__videberta-base/tmp_checkpoints/checkpoint-40500/tokenizer.json +0 -0
- Fsoft-AIC__videberta-base/tmp_checkpoints/checkpoint-40500/tokenizer_config.json +20 -0
- Fsoft-AIC__videberta-base/tmp_checkpoints/checkpoint-40500/trainer_state.json +1258 -0
- Fsoft-AIC__videberta-base/tmp_checkpoints/checkpoint-40500/training_args.bin +3 -0
- MikeGreen2710__mlm_listing_checkpoint-32442/.ipynb_checkpoints/pretrain_metadata-checkpoint.json +10 -0
- MikeGreen2710__mlm_listing_checkpoint-32442/added_tokens.json +3 -0
- MikeGreen2710__mlm_listing_checkpoint-32442/bpe.codes +0 -0
- MikeGreen2710__mlm_listing_checkpoint-32442/config.json +31 -0
- MikeGreen2710__mlm_listing_checkpoint-32442/model.safetensors +3 -0
- MikeGreen2710__mlm_listing_checkpoint-32442/pretrain_metadata.json +10 -0
- MikeGreen2710__mlm_listing_checkpoint-32442/tokenizer_config.json +56 -0
- MikeGreen2710__mlm_listing_checkpoint-32442/training_args.bin +3 -0
- MikeGreen2710__mlm_listing_checkpoint-32442/vocab.txt +0 -0
- NlpHUST__electra-base-vn/config.json +33 -0
- NlpHUST__electra-base-vn/model.safetensors +3 -0
- NlpHUST__electra-base-vn/pretrain_metadata.json +10 -0
- NlpHUST__electra-base-vn/tokenizer.json +0 -0
- NlpHUST__electra-base-vn/tokenizer_config.json +15 -0
- NlpHUST__electra-base-vn/training_args.bin +3 -0
- _token_cache/Fsoft-AIC__videberta-base/eval_00000_of_00004.arrow +3 -0
- _token_cache/Fsoft-AIC__videberta-base/eval_00001_of_00004.arrow +3 -0
- _token_cache/Fsoft-AIC__videberta-base/eval_00002_of_00004.arrow +3 -0
- _token_cache/Fsoft-AIC__videberta-base/eval_00003_of_00004.arrow +3 -0
- _token_cache/Fsoft-AIC__videberta-base/train_00000_of_00004.arrow +3 -0
- _token_cache/Fsoft-AIC__videberta-base/train_00001_of_00004.arrow +3 -0
- _token_cache/Fsoft-AIC__videberta-base/train_00002_of_00004.arrow +3 -0
- _token_cache/Fsoft-AIC__videberta-base/train_00003_of_00004.arrow +3 -0
- _token_cache/MikeGreen2710__mlm_listing_checkpoint-32442/eval_00000_of_00004.arrow +3 -0
- _token_cache/MikeGreen2710__mlm_listing_checkpoint-32442/eval_00001_of_00004.arrow +3 -0
- _token_cache/MikeGreen2710__mlm_listing_checkpoint-32442/eval_00002_of_00004.arrow +3 -0
- _token_cache/MikeGreen2710__mlm_listing_checkpoint-32442/eval_00003_of_00004.arrow +3 -0
- _token_cache/MikeGreen2710__mlm_listing_checkpoint-32442/train_00000_of_00004.arrow +3 -0
- _token_cache/MikeGreen2710__mlm_listing_checkpoint-32442/train_00001_of_00004.arrow +3 -0
- _token_cache/MikeGreen2710__mlm_listing_checkpoint-32442/train_00002_of_00004.arrow +3 -0
- _token_cache/MikeGreen2710__mlm_listing_checkpoint-32442/train_00003_of_00004.arrow +3 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
google__rembert/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 37 |
+
microsoft__mdeberta-v3-base/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
Fsoft-AIC__videberta-base/tmp_checkpoints/checkpoint-40000/config.json
ADDED
|
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"DebertaV2ForMaskedLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_head_size": 64,
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"bos_token_id": null,
|
| 8 |
+
"dtype": "float32",
|
| 9 |
+
"eos_token_id": null,
|
| 10 |
+
"hidden_act": "gelu",
|
| 11 |
+
"hidden_dropout_prob": 0.1,
|
| 12 |
+
"hidden_size": 768,
|
| 13 |
+
"initializer_range": 0.02,
|
| 14 |
+
"intermediate_size": 3072,
|
| 15 |
+
"layer_norm_eps": 1e-07,
|
| 16 |
+
"legacy": true,
|
| 17 |
+
"max_position_embeddings": 512,
|
| 18 |
+
"max_relative_positions": -1,
|
| 19 |
+
"model_type": "deberta-v2",
|
| 20 |
+
"norm_rel_ebd": "layer_norm",
|
| 21 |
+
"num_attention_heads": 12,
|
| 22 |
+
"num_hidden_layers": 12,
|
| 23 |
+
"pad_token_id": 0,
|
| 24 |
+
"pooler_dropout": 0.0,
|
| 25 |
+
"pooler_hidden_act": "gelu",
|
| 26 |
+
"pooler_hidden_size": 768,
|
| 27 |
+
"pos_att_type": [
|
| 28 |
+
"p2c",
|
| 29 |
+
"c2p"
|
| 30 |
+
],
|
| 31 |
+
"position_biased_input": false,
|
| 32 |
+
"position_buckets": 256,
|
| 33 |
+
"relative_attention": true,
|
| 34 |
+
"share_att_key": true,
|
| 35 |
+
"tie_word_embeddings": true,
|
| 36 |
+
"transformers_version": "5.8.0",
|
| 37 |
+
"type_vocab_size": 0,
|
| 38 |
+
"use_cache": false,
|
| 39 |
+
"vocab_size": 128000
|
| 40 |
+
}
|
Fsoft-AIC__videberta-base/tmp_checkpoints/checkpoint-40000/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:070c9d7f3520493081364e54b85776f3d7d8fd7ac9583edbbeee4b025086bfad
|
| 3 |
+
size 737924256
|
Fsoft-AIC__videberta-base/tmp_checkpoints/checkpoint-40000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4e9ad0eebad48967268ce4b39fc82006ffa1527ed08d5c8cd3a01d9016f1f3b9
|
| 3 |
+
size 1475968826
|
Fsoft-AIC__videberta-base/tmp_checkpoints/checkpoint-40000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:721493c653967e8fc0da471342b9b45a6ce9f6c41020cb8b85b0ea842275517a
|
| 3 |
+
size 14244
|
Fsoft-AIC__videberta-base/tmp_checkpoints/checkpoint-40000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0cb0652c550c0be0b49edd64a3f0322b69604984347ddcb0305da463120b06b0
|
| 3 |
+
size 1064
|
Fsoft-AIC__videberta-base/tmp_checkpoints/checkpoint-40000/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
Fsoft-AIC__videberta-base/tmp_checkpoints/checkpoint-40000/tokenizer_config.json
ADDED
|
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": true,
|
| 3 |
+
"backend": "tokenizers",
|
| 4 |
+
"bos_token": "[CLS]",
|
| 5 |
+
"cls_token": "[CLS]",
|
| 6 |
+
"do_lower_case": false,
|
| 7 |
+
"eos_token": "[SEP]",
|
| 8 |
+
"is_local": false,
|
| 9 |
+
"local_files_only": false,
|
| 10 |
+
"mask_token": "[MASK]",
|
| 11 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 12 |
+
"pad_token": "[PAD]",
|
| 13 |
+
"sep_token": "[SEP]",
|
| 14 |
+
"sp_model_kwargs": {},
|
| 15 |
+
"split_by_punct": false,
|
| 16 |
+
"tokenizer_class": "DebertaV2Tokenizer",
|
| 17 |
+
"unk_id": 3,
|
| 18 |
+
"unk_token": "[UNK]",
|
| 19 |
+
"vocab_type": "spm"
|
| 20 |
+
}
|
Fsoft-AIC__videberta-base/tmp_checkpoints/checkpoint-40000/trainer_state.json
ADDED
|
@@ -0,0 +1,1243 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": 40000,
|
| 3 |
+
"best_metric": 1.487270712852478,
|
| 4 |
+
"best_model_checkpoint": "pretrained_checkpoints/Fsoft-AIC__videberta-base/tmp_checkpoints/checkpoint-40000",
|
| 5 |
+
"epoch": 0.08848970201092848,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 40000,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.001106121275136606,
|
| 14 |
+
"grad_norm": 9.475790977478027,
|
| 15 |
+
"learning_rate": 1.9960000000000002e-05,
|
| 16 |
+
"loss": 10.73539453125,
|
| 17 |
+
"step": 500
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.001106121275136606,
|
| 21 |
+
"eval_loss": 6.908179759979248,
|
| 22 |
+
"eval_runtime": 65.5198,
|
| 23 |
+
"eval_samples_per_second": 152.626,
|
| 24 |
+
"eval_steps_per_second": 9.539,
|
| 25 |
+
"step": 500
|
| 26 |
+
},
|
| 27 |
+
{
|
| 28 |
+
"epoch": 0.002212242550273212,
|
| 29 |
+
"grad_norm": 4.896268367767334,
|
| 30 |
+
"learning_rate": 1.9999950750763816e-05,
|
| 31 |
+
"loss": 6.3172548828125,
|
| 32 |
+
"step": 1000
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.002212242550273212,
|
| 36 |
+
"eval_loss": 5.584421634674072,
|
| 37 |
+
"eval_runtime": 65.633,
|
| 38 |
+
"eval_samples_per_second": 152.362,
|
| 39 |
+
"eval_steps_per_second": 9.523,
|
| 40 |
+
"step": 1000
|
| 41 |
+
},
|
| 42 |
+
{
|
| 43 |
+
"epoch": 0.003318363825409818,
|
| 44 |
+
"grad_norm": 5.7100324630737305,
|
| 45 |
+
"learning_rate": 1.999980260856137e-05,
|
| 46 |
+
"loss": 5.51156884765625,
|
| 47 |
+
"step": 1500
|
| 48 |
+
},
|
| 49 |
+
{
|
| 50 |
+
"epoch": 0.003318363825409818,
|
| 51 |
+
"eval_loss": 5.097376823425293,
|
| 52 |
+
"eval_runtime": 65.5025,
|
| 53 |
+
"eval_samples_per_second": 152.666,
|
| 54 |
+
"eval_steps_per_second": 9.542,
|
| 55 |
+
"step": 1500
|
| 56 |
+
},
|
| 57 |
+
{
|
| 58 |
+
"epoch": 0.004424485100546424,
|
| 59 |
+
"grad_norm": 5.015883922576904,
|
| 60 |
+
"learning_rate": 1.9999555574659926e-05,
|
| 61 |
+
"loss": 5.04186083984375,
|
| 62 |
+
"step": 2000
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.004424485100546424,
|
| 66 |
+
"eval_loss": 4.640530109405518,
|
| 67 |
+
"eval_runtime": 65.8074,
|
| 68 |
+
"eval_samples_per_second": 151.959,
|
| 69 |
+
"eval_steps_per_second": 9.497,
|
| 70 |
+
"step": 2000
|
| 71 |
+
},
|
| 72 |
+
{
|
| 73 |
+
"epoch": 0.00553060637568303,
|
| 74 |
+
"grad_norm": 5.8804450035095215,
|
| 75 |
+
"learning_rate": 1.9999209651502484e-05,
|
| 76 |
+
"loss": 4.6854267578125,
|
| 77 |
+
"step": 2500
|
| 78 |
+
},
|
| 79 |
+
{
|
| 80 |
+
"epoch": 0.00553060637568303,
|
| 81 |
+
"eval_loss": 4.30808162689209,
|
| 82 |
+
"eval_runtime": 65.7347,
|
| 83 |
+
"eval_samples_per_second": 152.127,
|
| 84 |
+
"eval_steps_per_second": 9.508,
|
| 85 |
+
"step": 2500
|
| 86 |
+
},
|
| 87 |
+
{
|
| 88 |
+
"epoch": 0.006636727650819636,
|
| 89 |
+
"grad_norm": 6.087777614593506,
|
| 90 |
+
"learning_rate": 1.999876484251e-05,
|
| 91 |
+
"loss": 4.3789228515625,
|
| 92 |
+
"step": 3000
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.006636727650819636,
|
| 96 |
+
"eval_loss": 4.010719299316406,
|
| 97 |
+
"eval_runtime": 65.6921,
|
| 98 |
+
"eval_samples_per_second": 152.225,
|
| 99 |
+
"eval_steps_per_second": 9.514,
|
| 100 |
+
"step": 3000
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.0077428489259562415,
|
| 104 |
+
"grad_norm": 5.5657639503479,
|
| 105 |
+
"learning_rate": 1.9998221152081356e-05,
|
| 106 |
+
"loss": 4.1345771484375,
|
| 107 |
+
"step": 3500
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.0077428489259562415,
|
| 111 |
+
"eval_loss": 3.785635232925415,
|
| 112 |
+
"eval_runtime": 66.3485,
|
| 113 |
+
"eval_samples_per_second": 150.719,
|
| 114 |
+
"eval_steps_per_second": 9.42,
|
| 115 |
+
"step": 3500
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.008848970201092848,
|
| 119 |
+
"grad_norm": 6.631436824798584,
|
| 120 |
+
"learning_rate": 1.999757858559331e-05,
|
| 121 |
+
"loss": 3.9143818359375,
|
| 122 |
+
"step": 4000
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.008848970201092848,
|
| 126 |
+
"eval_loss": 3.588374614715576,
|
| 127 |
+
"eval_runtime": 66.3332,
|
| 128 |
+
"eval_samples_per_second": 150.754,
|
| 129 |
+
"eval_steps_per_second": 9.422,
|
| 130 |
+
"step": 4000
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 0.009955091476229454,
|
| 134 |
+
"grad_norm": 5.396254062652588,
|
| 135 |
+
"learning_rate": 1.999683714940043e-05,
|
| 136 |
+
"loss": 3.759765869140625,
|
| 137 |
+
"step": 4500
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 0.009955091476229454,
|
| 141 |
+
"eval_loss": 3.429428815841675,
|
| 142 |
+
"eval_runtime": 65.5002,
|
| 143 |
+
"eval_samples_per_second": 152.671,
|
| 144 |
+
"eval_steps_per_second": 9.542,
|
| 145 |
+
"step": 4500
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 0.01106121275136606,
|
| 149 |
+
"grad_norm": 5.386684894561768,
|
| 150 |
+
"learning_rate": 1.999599685083505e-05,
|
| 151 |
+
"loss": 3.61756494140625,
|
| 152 |
+
"step": 5000
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 0.01106121275136606,
|
| 156 |
+
"eval_loss": 3.315566301345825,
|
| 157 |
+
"eval_runtime": 65.3359,
|
| 158 |
+
"eval_samples_per_second": 153.055,
|
| 159 |
+
"eval_steps_per_second": 9.566,
|
| 160 |
+
"step": 5000
|
| 161 |
+
},
|
| 162 |
+
{
|
| 163 |
+
"epoch": 0.012167334026502667,
|
| 164 |
+
"grad_norm": 6.260346412658691,
|
| 165 |
+
"learning_rate": 1.9995057698207195e-05,
|
| 166 |
+
"loss": 3.486438720703125,
|
| 167 |
+
"step": 5500
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 0.012167334026502667,
|
| 171 |
+
"eval_loss": 3.190394639968872,
|
| 172 |
+
"eval_runtime": 65.353,
|
| 173 |
+
"eval_samples_per_second": 153.015,
|
| 174 |
+
"eval_steps_per_second": 9.563,
|
| 175 |
+
"step": 5500
|
| 176 |
+
},
|
| 177 |
+
{
|
| 178 |
+
"epoch": 0.013273455301639273,
|
| 179 |
+
"grad_norm": 5.308413028717041,
|
| 180 |
+
"learning_rate": 1.9994019700804483e-05,
|
| 181 |
+
"loss": 3.372943115234375,
|
| 182 |
+
"step": 6000
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 0.013273455301639273,
|
| 186 |
+
"eval_loss": 3.07236647605896,
|
| 187 |
+
"eval_runtime": 65.1836,
|
| 188 |
+
"eval_samples_per_second": 153.413,
|
| 189 |
+
"eval_steps_per_second": 9.588,
|
| 190 |
+
"step": 6000
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"epoch": 0.014379576576775877,
|
| 194 |
+
"grad_norm": 5.559189796447754,
|
| 195 |
+
"learning_rate": 1.9992882868892052e-05,
|
| 196 |
+
"loss": 3.33723486328125,
|
| 197 |
+
"step": 6500
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 0.014379576576775877,
|
| 201 |
+
"eval_loss": 2.9914042949676514,
|
| 202 |
+
"eval_runtime": 65.1138,
|
| 203 |
+
"eval_samples_per_second": 153.577,
|
| 204 |
+
"eval_steps_per_second": 9.599,
|
| 205 |
+
"step": 6500
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.015485697851912483,
|
| 209 |
+
"grad_norm": 5.7293925285339355,
|
| 210 |
+
"learning_rate": 1.9991647213712446e-05,
|
| 211 |
+
"loss": 3.1835166015625,
|
| 212 |
+
"step": 7000
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.015485697851912483,
|
| 216 |
+
"eval_loss": 2.9056553840637207,
|
| 217 |
+
"eval_runtime": 66.6383,
|
| 218 |
+
"eval_samples_per_second": 150.064,
|
| 219 |
+
"eval_steps_per_second": 9.379,
|
| 220 |
+
"step": 7000
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.01659181912704909,
|
| 224 |
+
"grad_norm": 5.745417594909668,
|
| 225 |
+
"learning_rate": 1.999031274748551e-05,
|
| 226 |
+
"loss": 3.09816748046875,
|
| 227 |
+
"step": 7500
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.01659181912704909,
|
| 231 |
+
"eval_loss": 2.8260159492492676,
|
| 232 |
+
"eval_runtime": 65.6949,
|
| 233 |
+
"eval_samples_per_second": 152.219,
|
| 234 |
+
"eval_steps_per_second": 9.514,
|
| 235 |
+
"step": 7500
|
| 236 |
+
},
|
| 237 |
+
{
|
| 238 |
+
"epoch": 0.017697940402185697,
|
| 239 |
+
"grad_norm": 5.706750869750977,
|
| 240 |
+
"learning_rate": 1.9988879483408266e-05,
|
| 241 |
+
"loss": 3.02596435546875,
|
| 242 |
+
"step": 8000
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 0.017697940402185697,
|
| 246 |
+
"eval_loss": 2.7651631832122803,
|
| 247 |
+
"eval_runtime": 65.8495,
|
| 248 |
+
"eval_samples_per_second": 151.862,
|
| 249 |
+
"eval_steps_per_second": 9.491,
|
| 250 |
+
"step": 8000
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"epoch": 0.018804061677322303,
|
| 254 |
+
"grad_norm": 4.90167760848999,
|
| 255 |
+
"learning_rate": 1.998734743565479e-05,
|
| 256 |
+
"loss": 2.940542236328125,
|
| 257 |
+
"step": 8500
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 0.018804061677322303,
|
| 261 |
+
"eval_loss": 2.683983325958252,
|
| 262 |
+
"eval_runtime": 65.8236,
|
| 263 |
+
"eval_samples_per_second": 151.921,
|
| 264 |
+
"eval_steps_per_second": 9.495,
|
| 265 |
+
"step": 8500
|
| 266 |
+
},
|
| 267 |
+
{
|
| 268 |
+
"epoch": 0.01991018295245891,
|
| 269 |
+
"grad_norm": 6.079418182373047,
|
| 270 |
+
"learning_rate": 1.998571661937606e-05,
|
| 271 |
+
"loss": 2.8865009765625,
|
| 272 |
+
"step": 9000
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 0.01991018295245891,
|
| 276 |
+
"eval_loss": 2.624776840209961,
|
| 277 |
+
"eval_runtime": 65.9969,
|
| 278 |
+
"eval_samples_per_second": 151.522,
|
| 279 |
+
"eval_steps_per_second": 9.47,
|
| 280 |
+
"step": 9000
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 0.021016304227595515,
|
| 284 |
+
"grad_norm": 5.454369068145752,
|
| 285 |
+
"learning_rate": 1.9983987050699813e-05,
|
| 286 |
+
"loss": 2.817274169921875,
|
| 287 |
+
"step": 9500
|
| 288 |
+
},
|
| 289 |
+
{
|
| 290 |
+
"epoch": 0.021016304227595515,
|
| 291 |
+
"eval_loss": 2.580995559692383,
|
| 292 |
+
"eval_runtime": 65.6963,
|
| 293 |
+
"eval_samples_per_second": 152.216,
|
| 294 |
+
"eval_steps_per_second": 9.513,
|
| 295 |
+
"step": 9500
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 0.02212242550273212,
|
| 299 |
+
"grad_norm": 5.633095741271973,
|
| 300 |
+
"learning_rate": 1.9982158746730387e-05,
|
| 301 |
+
"loss": 2.784319091796875,
|
| 302 |
+
"step": 10000
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 0.02212242550273212,
|
| 306 |
+
"eval_loss": 2.502817153930664,
|
| 307 |
+
"eval_runtime": 65.4322,
|
| 308 |
+
"eval_samples_per_second": 152.83,
|
| 309 |
+
"eval_steps_per_second": 9.552,
|
| 310 |
+
"step": 10000
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.023228546777868727,
|
| 314 |
+
"grad_norm": 5.46868896484375,
|
| 315 |
+
"learning_rate": 1.9980231725548545e-05,
|
| 316 |
+
"loss": 2.702649658203125,
|
| 317 |
+
"step": 10500
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.023228546777868727,
|
| 321 |
+
"eval_loss": 2.465555191040039,
|
| 322 |
+
"eval_runtime": 65.0987,
|
| 323 |
+
"eval_samples_per_second": 153.613,
|
| 324 |
+
"eval_steps_per_second": 9.601,
|
| 325 |
+
"step": 10500
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.024334668053005333,
|
| 329 |
+
"grad_norm": 5.703943252563477,
|
| 330 |
+
"learning_rate": 1.9978206006211304e-05,
|
| 331 |
+
"loss": 2.6762646484375,
|
| 332 |
+
"step": 11000
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.024334668053005333,
|
| 336 |
+
"eval_loss": 2.410994529724121,
|
| 337 |
+
"eval_runtime": 65.8492,
|
| 338 |
+
"eval_samples_per_second": 151.862,
|
| 339 |
+
"eval_steps_per_second": 9.491,
|
| 340 |
+
"step": 11000
|
| 341 |
+
},
|
| 342 |
+
{
|
| 343 |
+
"epoch": 0.02544078932814194,
|
| 344 |
+
"grad_norm": 5.745393753051758,
|
| 345 |
+
"learning_rate": 1.9976081608751742e-05,
|
| 346 |
+
"loss": 2.61624267578125,
|
| 347 |
+
"step": 11500
|
| 348 |
+
},
|
| 349 |
+
{
|
| 350 |
+
"epoch": 0.02544078932814194,
|
| 351 |
+
"eval_loss": 2.377451181411743,
|
| 352 |
+
"eval_runtime": 65.697,
|
| 353 |
+
"eval_samples_per_second": 152.214,
|
| 354 |
+
"eval_steps_per_second": 9.513,
|
| 355 |
+
"step": 11500
|
| 356 |
+
},
|
| 357 |
+
{
|
| 358 |
+
"epoch": 0.026546910603278545,
|
| 359 |
+
"grad_norm": 5.889176845550537,
|
| 360 |
+
"learning_rate": 1.99738585541788e-05,
|
| 361 |
+
"loss": 2.5832724609375,
|
| 362 |
+
"step": 12000
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 0.026546910603278545,
|
| 366 |
+
"eval_loss": 2.334881544113159,
|
| 367 |
+
"eval_runtime": 65.862,
|
| 368 |
+
"eval_samples_per_second": 151.833,
|
| 369 |
+
"eval_steps_per_second": 9.49,
|
| 370 |
+
"step": 12000
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 0.027653031878415148,
|
| 374 |
+
"grad_norm": 5.409160614013672,
|
| 375 |
+
"learning_rate": 1.9971536864477078e-05,
|
| 376 |
+
"loss": 2.548913818359375,
|
| 377 |
+
"step": 12500
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 0.027653031878415148,
|
| 381 |
+
"eval_loss": 2.30452823638916,
|
| 382 |
+
"eval_runtime": 65.0769,
|
| 383 |
+
"eval_samples_per_second": 153.664,
|
| 384 |
+
"eval_steps_per_second": 9.604,
|
| 385 |
+
"step": 12500
|
| 386 |
+
},
|
| 387 |
+
{
|
| 388 |
+
"epoch": 0.028759153153551754,
|
| 389 |
+
"grad_norm": 5.37885046005249,
|
| 390 |
+
"learning_rate": 1.9969116562606614e-05,
|
| 391 |
+
"loss": 2.498342041015625,
|
| 392 |
+
"step": 13000
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 0.028759153153551754,
|
| 396 |
+
"eval_loss": 2.262269973754883,
|
| 397 |
+
"eval_runtime": 66.4547,
|
| 398 |
+
"eval_samples_per_second": 150.478,
|
| 399 |
+
"eval_steps_per_second": 9.405,
|
| 400 |
+
"step": 13000
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"epoch": 0.02986527442868836,
|
| 404 |
+
"grad_norm": 5.803339004516602,
|
| 405 |
+
"learning_rate": 1.9966597672502653e-05,
|
| 406 |
+
"loss": 2.449419921875,
|
| 407 |
+
"step": 13500
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 0.02986527442868836,
|
| 411 |
+
"eval_loss": 2.2417187690734863,
|
| 412 |
+
"eval_runtime": 65.9915,
|
| 413 |
+
"eval_samples_per_second": 151.535,
|
| 414 |
+
"eval_steps_per_second": 9.471,
|
| 415 |
+
"step": 13500
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.030971395703824966,
|
| 419 |
+
"grad_norm": 5.598288059234619,
|
| 420 |
+
"learning_rate": 1.9963980219075425e-05,
|
| 421 |
+
"loss": 2.43294775390625,
|
| 422 |
+
"step": 14000
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.030971395703824966,
|
| 426 |
+
"eval_loss": 2.1951167583465576,
|
| 427 |
+
"eval_runtime": 66.3059,
|
| 428 |
+
"eval_samples_per_second": 150.816,
|
| 429 |
+
"eval_steps_per_second": 9.426,
|
| 430 |
+
"step": 14000
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 0.03207751697896157,
|
| 434 |
+
"grad_norm": 5.400110244750977,
|
| 435 |
+
"learning_rate": 1.9961264228209876e-05,
|
| 436 |
+
"loss": 2.380520263671875,
|
| 437 |
+
"step": 14500
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 0.03207751697896157,
|
| 441 |
+
"eval_loss": 2.1698226928710938,
|
| 442 |
+
"eval_runtime": 65.841,
|
| 443 |
+
"eval_samples_per_second": 151.881,
|
| 444 |
+
"eval_steps_per_second": 9.493,
|
| 445 |
+
"step": 14500
|
| 446 |
+
},
|
| 447 |
+
{
|
| 448 |
+
"epoch": 0.03318363825409818,
|
| 449 |
+
"grad_norm": 5.006521224975586,
|
| 450 |
+
"learning_rate": 1.995844972676544e-05,
|
| 451 |
+
"loss": 2.36803515625,
|
| 452 |
+
"step": 15000
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 0.03318363825409818,
|
| 456 |
+
"eval_loss": 2.1508238315582275,
|
| 457 |
+
"eval_runtime": 65.8184,
|
| 458 |
+
"eval_samples_per_second": 151.933,
|
| 459 |
+
"eval_steps_per_second": 9.496,
|
| 460 |
+
"step": 15000
|
| 461 |
+
},
|
| 462 |
+
{
|
| 463 |
+
"epoch": 0.034289759529234784,
|
| 464 |
+
"grad_norm": 22.403335571289062,
|
| 465 |
+
"learning_rate": 1.9955536742575737e-05,
|
| 466 |
+
"loss": 2.337472900390625,
|
| 467 |
+
"step": 15500
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 0.034289759529234784,
|
| 471 |
+
"eval_loss": 2.131364345550537,
|
| 472 |
+
"eval_runtime": 65.3739,
|
| 473 |
+
"eval_samples_per_second": 152.966,
|
| 474 |
+
"eval_steps_per_second": 9.56,
|
| 475 |
+
"step": 15500
|
| 476 |
+
},
|
| 477 |
+
{
|
| 478 |
+
"epoch": 0.035395880804371394,
|
| 479 |
+
"grad_norm": 4.748437881469727,
|
| 480 |
+
"learning_rate": 1.995252530444834e-05,
|
| 481 |
+
"loss": 2.32045849609375,
|
| 482 |
+
"step": 16000
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 0.035395880804371394,
|
| 486 |
+
"eval_loss": 2.0844030380249023,
|
| 487 |
+
"eval_runtime": 65.3283,
|
| 488 |
+
"eval_samples_per_second": 153.073,
|
| 489 |
+
"eval_steps_per_second": 9.567,
|
| 490 |
+
"step": 16000
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"epoch": 0.036502002079507996,
|
| 494 |
+
"grad_norm": 4.933561325073242,
|
| 495 |
+
"learning_rate": 1.9949415442164463e-05,
|
| 496 |
+
"loss": 2.2753798828125,
|
| 497 |
+
"step": 16500
|
| 498 |
+
},
|
| 499 |
+
{
|
| 500 |
+
"epoch": 0.036502002079507996,
|
| 501 |
+
"eval_loss": 2.060131549835205,
|
| 502 |
+
"eval_runtime": 65.6122,
|
| 503 |
+
"eval_samples_per_second": 152.411,
|
| 504 |
+
"eval_steps_per_second": 9.526,
|
| 505 |
+
"step": 16500
|
| 506 |
+
},
|
| 507 |
+
{
|
| 508 |
+
"epoch": 0.037608123354644606,
|
| 509 |
+
"grad_norm": 5.674777507781982,
|
| 510 |
+
"learning_rate": 1.9946207186478655e-05,
|
| 511 |
+
"loss": 2.25116943359375,
|
| 512 |
+
"step": 17000
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 0.037608123354644606,
|
| 516 |
+
"eval_loss": 2.0405194759368896,
|
| 517 |
+
"eval_runtime": 65.3009,
|
| 518 |
+
"eval_samples_per_second": 153.137,
|
| 519 |
+
"eval_steps_per_second": 9.571,
|
| 520 |
+
"step": 17000
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 0.03871424462978121,
|
| 524 |
+
"grad_norm": 5.777343273162842,
|
| 525 |
+
"learning_rate": 1.9942900569118546e-05,
|
| 526 |
+
"loss": 2.23547802734375,
|
| 527 |
+
"step": 17500
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.03871424462978121,
|
| 531 |
+
"eval_loss": 2.0208609104156494,
|
| 532 |
+
"eval_runtime": 66.1739,
|
| 533 |
+
"eval_samples_per_second": 151.117,
|
| 534 |
+
"eval_steps_per_second": 9.445,
|
| 535 |
+
"step": 17500
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 0.03982036590491782,
|
| 539 |
+
"grad_norm": 5.607430458068848,
|
| 540 |
+
"learning_rate": 1.9939495622784472e-05,
|
| 541 |
+
"loss": 2.1993876953125,
|
| 542 |
+
"step": 18000
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 0.03982036590491782,
|
| 546 |
+
"eval_loss": 2.001434087753296,
|
| 547 |
+
"eval_runtime": 66.1661,
|
| 548 |
+
"eval_samples_per_second": 151.135,
|
| 549 |
+
"eval_steps_per_second": 9.446,
|
| 550 |
+
"step": 18000
|
| 551 |
+
},
|
| 552 |
+
{
|
| 553 |
+
"epoch": 0.04092648718005442,
|
| 554 |
+
"grad_norm": 5.273671627044678,
|
| 555 |
+
"learning_rate": 1.993599238114919e-05,
|
| 556 |
+
"loss": 2.180281982421875,
|
| 557 |
+
"step": 18500
|
| 558 |
+
},
|
| 559 |
+
{
|
| 560 |
+
"epoch": 0.04092648718005442,
|
| 561 |
+
"eval_loss": 1.983248233795166,
|
| 562 |
+
"eval_runtime": 65.6213,
|
| 563 |
+
"eval_samples_per_second": 152.39,
|
| 564 |
+
"eval_steps_per_second": 9.524,
|
| 565 |
+
"step": 18500
|
| 566 |
+
},
|
| 567 |
+
{
|
| 568 |
+
"epoch": 0.04203260845519103,
|
| 569 |
+
"grad_norm": 5.48894739151001,
|
| 570 |
+
"learning_rate": 1.993239087885754e-05,
|
| 571 |
+
"loss": 2.180351318359375,
|
| 572 |
+
"step": 19000
|
| 573 |
+
},
|
| 574 |
+
{
|
| 575 |
+
"epoch": 0.04203260845519103,
|
| 576 |
+
"eval_loss": 1.9536426067352295,
|
| 577 |
+
"eval_runtime": 65.1545,
|
| 578 |
+
"eval_samples_per_second": 153.481,
|
| 579 |
+
"eval_steps_per_second": 9.593,
|
| 580 |
+
"step": 19000
|
| 581 |
+
},
|
| 582 |
+
{
|
| 583 |
+
"epoch": 0.04313872973032763,
|
| 584 |
+
"grad_norm": 4.517572402954102,
|
| 585 |
+
"learning_rate": 1.992869115152609e-05,
|
| 586 |
+
"loss": 2.14364501953125,
|
| 587 |
+
"step": 19500
|
| 588 |
+
},
|
| 589 |
+
{
|
| 590 |
+
"epoch": 0.04313872973032763,
|
| 591 |
+
"eval_loss": 1.9281601905822754,
|
| 592 |
+
"eval_runtime": 65.6074,
|
| 593 |
+
"eval_samples_per_second": 152.422,
|
| 594 |
+
"eval_steps_per_second": 9.526,
|
| 595 |
+
"step": 19500
|
| 596 |
+
},
|
| 597 |
+
{
|
| 598 |
+
"epoch": 0.04424485100546424,
|
| 599 |
+
"grad_norm": 5.366357326507568,
|
| 600 |
+
"learning_rate": 1.9924893235742795e-05,
|
| 601 |
+
"loss": 2.124390380859375,
|
| 602 |
+
"step": 20000
|
| 603 |
+
},
|
| 604 |
+
{
|
| 605 |
+
"epoch": 0.04424485100546424,
|
| 606 |
+
"eval_loss": 1.9185084104537964,
|
| 607 |
+
"eval_runtime": 66.4777,
|
| 608 |
+
"eval_samples_per_second": 150.426,
|
| 609 |
+
"eval_steps_per_second": 9.402,
|
| 610 |
+
"step": 20000
|
| 611 |
+
},
|
| 612 |
+
{
|
| 613 |
+
"epoch": 0.045350972280600844,
|
| 614 |
+
"grad_norm": 5.40119743347168,
|
| 615 |
+
"learning_rate": 1.992099716906663e-05,
|
| 616 |
+
"loss": 2.11509521484375,
|
| 617 |
+
"step": 20500
|
| 618 |
+
},
|
| 619 |
+
{
|
| 620 |
+
"epoch": 0.045350972280600844,
|
| 621 |
+
"eval_loss": 1.8964039087295532,
|
| 622 |
+
"eval_runtime": 65.269,
|
| 623 |
+
"eval_samples_per_second": 153.212,
|
| 624 |
+
"eval_steps_per_second": 9.576,
|
| 625 |
+
"step": 20500
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.046457093555737454,
|
| 629 |
+
"grad_norm": 4.91980504989624,
|
| 630 |
+
"learning_rate": 1.9917002990027225e-05,
|
| 631 |
+
"loss": 2.080730224609375,
|
| 632 |
+
"step": 21000
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 0.046457093555737454,
|
| 636 |
+
"eval_loss": 1.8814513683319092,
|
| 637 |
+
"eval_runtime": 65.8396,
|
| 638 |
+
"eval_samples_per_second": 151.884,
|
| 639 |
+
"eval_steps_per_second": 9.493,
|
| 640 |
+
"step": 21000
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 0.04756321483087406,
|
| 644 |
+
"grad_norm": 5.756763458251953,
|
| 645 |
+
"learning_rate": 1.991291073812447e-05,
|
| 646 |
+
"loss": 2.062693359375,
|
| 647 |
+
"step": 21500
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 0.04756321483087406,
|
| 651 |
+
"eval_loss": 1.8653240203857422,
|
| 652 |
+
"eval_runtime": 65.2727,
|
| 653 |
+
"eval_samples_per_second": 153.203,
|
| 654 |
+
"eval_steps_per_second": 9.575,
|
| 655 |
+
"step": 21500
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"epoch": 0.048669336106010666,
|
| 659 |
+
"grad_norm": 4.964697360992432,
|
| 660 |
+
"learning_rate": 1.990872045382814e-05,
|
| 661 |
+
"loss": 2.0461234130859376,
|
| 662 |
+
"step": 22000
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 0.048669336106010666,
|
| 666 |
+
"eval_loss": 1.8559273481369019,
|
| 667 |
+
"eval_runtime": 65.7552,
|
| 668 |
+
"eval_samples_per_second": 152.079,
|
| 669 |
+
"eval_steps_per_second": 9.505,
|
| 670 |
+
"step": 22000
|
| 671 |
+
},
|
| 672 |
+
{
|
| 673 |
+
"epoch": 0.04977545738114727,
|
| 674 |
+
"grad_norm": 4.809401988983154,
|
| 675 |
+
"learning_rate": 1.990443217857749e-05,
|
| 676 |
+
"loss": 2.030472412109375,
|
| 677 |
+
"step": 22500
|
| 678 |
+
},
|
| 679 |
+
{
|
| 680 |
+
"epoch": 0.04977545738114727,
|
| 681 |
+
"eval_loss": 1.8380959033966064,
|
| 682 |
+
"eval_runtime": 65.6745,
|
| 683 |
+
"eval_samples_per_second": 152.266,
|
| 684 |
+
"eval_steps_per_second": 9.517,
|
| 685 |
+
"step": 22500
|
| 686 |
+
},
|
| 687 |
+
{
|
| 688 |
+
"epoch": 0.05088157865628388,
|
| 689 |
+
"grad_norm": 5.332137584686279,
|
| 690 |
+
"learning_rate": 1.9900045954780833e-05,
|
| 691 |
+
"loss": 2.019200439453125,
|
| 692 |
+
"step": 23000
|
| 693 |
+
},
|
| 694 |
+
{
|
| 695 |
+
"epoch": 0.05088157865628388,
|
| 696 |
+
"eval_loss": 1.8243741989135742,
|
| 697 |
+
"eval_runtime": 66.808,
|
| 698 |
+
"eval_samples_per_second": 149.683,
|
| 699 |
+
"eval_steps_per_second": 9.355,
|
| 700 |
+
"step": 23000
|
| 701 |
+
},
|
| 702 |
+
{
|
| 703 |
+
"epoch": 0.05198769993142048,
|
| 704 |
+
"grad_norm": 5.7028913497924805,
|
| 705 |
+
"learning_rate": 1.989556182581514e-05,
|
| 706 |
+
"loss": 1.9847816162109375,
|
| 707 |
+
"step": 23500
|
| 708 |
+
},
|
| 709 |
+
{
|
| 710 |
+
"epoch": 0.05198769993142048,
|
| 711 |
+
"eval_loss": 1.8052804470062256,
|
| 712 |
+
"eval_runtime": 65.2434,
|
| 713 |
+
"eval_samples_per_second": 153.272,
|
| 714 |
+
"eval_steps_per_second": 9.58,
|
| 715 |
+
"step": 23500
|
| 716 |
+
},
|
| 717 |
+
{
|
| 718 |
+
"epoch": 0.05309382120655709,
|
| 719 |
+
"grad_norm": 4.981122970581055,
|
| 720 |
+
"learning_rate": 1.98909798360256e-05,
|
| 721 |
+
"loss": 1.9902779541015625,
|
| 722 |
+
"step": 24000
|
| 723 |
+
},
|
| 724 |
+
{
|
| 725 |
+
"epoch": 0.05309382120655709,
|
| 726 |
+
"eval_loss": 1.7762919664382935,
|
| 727 |
+
"eval_runtime": 65.1802,
|
| 728 |
+
"eval_samples_per_second": 153.421,
|
| 729 |
+
"eval_steps_per_second": 9.589,
|
| 730 |
+
"step": 24000
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 0.05419994248169369,
|
| 734 |
+
"grad_norm": 4.917308807373047,
|
| 735 |
+
"learning_rate": 1.9886300030725185e-05,
|
| 736 |
+
"loss": 1.9727127685546875,
|
| 737 |
+
"step": 24500
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 0.05419994248169369,
|
| 741 |
+
"eval_loss": 1.7766869068145752,
|
| 742 |
+
"eval_runtime": 65.0747,
|
| 743 |
+
"eval_samples_per_second": 153.67,
|
| 744 |
+
"eval_steps_per_second": 9.604,
|
| 745 |
+
"step": 24500
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 0.055306063756830295,
|
| 749 |
+
"grad_norm": 4.780125141143799,
|
| 750 |
+
"learning_rate": 1.9881522456194194e-05,
|
| 751 |
+
"loss": 1.948054443359375,
|
| 752 |
+
"step": 25000
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 0.055306063756830295,
|
| 756 |
+
"eval_loss": 1.7642755508422852,
|
| 757 |
+
"eval_runtime": 65.8137,
|
| 758 |
+
"eval_samples_per_second": 151.944,
|
| 759 |
+
"eval_steps_per_second": 9.497,
|
| 760 |
+
"step": 25000
|
| 761 |
+
},
|
| 762 |
+
{
|
| 763 |
+
"epoch": 0.056412185031966905,
|
| 764 |
+
"grad_norm": 5.44115686416626,
|
| 765 |
+
"learning_rate": 1.9876647159679813e-05,
|
| 766 |
+
"loss": 1.9313668212890625,
|
| 767 |
+
"step": 25500
|
| 768 |
+
},
|
| 769 |
+
{
|
| 770 |
+
"epoch": 0.056412185031966905,
|
| 771 |
+
"eval_loss": 1.7497310638427734,
|
| 772 |
+
"eval_runtime": 65.536,
|
| 773 |
+
"eval_samples_per_second": 152.588,
|
| 774 |
+
"eval_steps_per_second": 9.537,
|
| 775 |
+
"step": 25500
|
| 776 |
+
},
|
| 777 |
+
{
|
| 778 |
+
"epoch": 0.05751830630710351,
|
| 779 |
+
"grad_norm": 4.406560897827148,
|
| 780 |
+
"learning_rate": 1.9871674189395622e-05,
|
| 781 |
+
"loss": 1.933572021484375,
|
| 782 |
+
"step": 26000
|
| 783 |
+
},
|
| 784 |
+
{
|
| 785 |
+
"epoch": 0.05751830630710351,
|
| 786 |
+
"eval_loss": 1.7356730699539185,
|
| 787 |
+
"eval_runtime": 66.4858,
|
| 788 |
+
"eval_samples_per_second": 150.408,
|
| 789 |
+
"eval_steps_per_second": 9.401,
|
| 790 |
+
"step": 26000
|
| 791 |
+
},
|
| 792 |
+
{
|
| 793 |
+
"epoch": 0.05862442758224012,
|
| 794 |
+
"grad_norm": 6.296497344970703,
|
| 795 |
+
"learning_rate": 1.9866603594521142e-05,
|
| 796 |
+
"loss": 1.91761669921875,
|
| 797 |
+
"step": 26500
|
| 798 |
+
},
|
| 799 |
+
{
|
| 800 |
+
"epoch": 0.05862442758224012,
|
| 801 |
+
"eval_loss": 1.7373892068862915,
|
| 802 |
+
"eval_runtime": 65.2531,
|
| 803 |
+
"eval_samples_per_second": 153.25,
|
| 804 |
+
"eval_steps_per_second": 9.578,
|
| 805 |
+
"step": 26500
|
| 806 |
+
},
|
| 807 |
+
{
|
| 808 |
+
"epoch": 0.05973054885737672,
|
| 809 |
+
"grad_norm": 5.007937908172607,
|
| 810 |
+
"learning_rate": 1.9861435425201336e-05,
|
| 811 |
+
"loss": 1.898394287109375,
|
| 812 |
+
"step": 27000
|
| 813 |
+
},
|
| 814 |
+
{
|
| 815 |
+
"epoch": 0.05973054885737672,
|
| 816 |
+
"eval_loss": 1.7208389043807983,
|
| 817 |
+
"eval_runtime": 65.1399,
|
| 818 |
+
"eval_samples_per_second": 153.516,
|
| 819 |
+
"eval_steps_per_second": 9.595,
|
| 820 |
+
"step": 27000
|
| 821 |
+
},
|
| 822 |
+
{
|
| 823 |
+
"epoch": 0.06083667013251333,
|
| 824 |
+
"grad_norm": 4.655943393707275,
|
| 825 |
+
"learning_rate": 1.985616973254612e-05,
|
| 826 |
+
"loss": 1.9006209716796876,
|
| 827 |
+
"step": 27500
|
| 828 |
+
},
|
| 829 |
+
{
|
| 830 |
+
"epoch": 0.06083667013251333,
|
| 831 |
+
"eval_loss": 1.7028509378433228,
|
| 832 |
+
"eval_runtime": 66.0059,
|
| 833 |
+
"eval_samples_per_second": 151.502,
|
| 834 |
+
"eval_steps_per_second": 9.469,
|
| 835 |
+
"step": 27500
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 0.06194279140764993,
|
| 839 |
+
"grad_norm": 5.251052379608154,
|
| 840 |
+
"learning_rate": 1.985080656862985e-05,
|
| 841 |
+
"loss": 1.88404931640625,
|
| 842 |
+
"step": 28000
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 0.06194279140764993,
|
| 846 |
+
"eval_loss": 1.7043781280517578,
|
| 847 |
+
"eval_runtime": 65.8348,
|
| 848 |
+
"eval_samples_per_second": 151.895,
|
| 849 |
+
"eval_steps_per_second": 9.493,
|
| 850 |
+
"step": 28000
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 0.06304891268278653,
|
| 854 |
+
"grad_norm": 5.259983539581299,
|
| 855 |
+
"learning_rate": 1.984534598649081e-05,
|
| 856 |
+
"loss": 1.875679931640625,
|
| 857 |
+
"step": 28500
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 0.06304891268278653,
|
| 861 |
+
"eval_loss": 1.6936031579971313,
|
| 862 |
+
"eval_runtime": 65.104,
|
| 863 |
+
"eval_samples_per_second": 153.6,
|
| 864 |
+
"eval_steps_per_second": 9.6,
|
| 865 |
+
"step": 28500
|
| 866 |
+
},
|
| 867 |
+
{
|
| 868 |
+
"epoch": 0.06415503395792314,
|
| 869 |
+
"grad_norm": 4.902404308319092,
|
| 870 |
+
"learning_rate": 1.9839788040130693e-05,
|
| 871 |
+
"loss": 1.8586162109375,
|
| 872 |
+
"step": 29000
|
| 873 |
+
},
|
| 874 |
+
{
|
| 875 |
+
"epoch": 0.06415503395792314,
|
| 876 |
+
"eval_loss": 1.6735634803771973,
|
| 877 |
+
"eval_runtime": 65.6048,
|
| 878 |
+
"eval_samples_per_second": 152.428,
|
| 879 |
+
"eval_steps_per_second": 9.527,
|
| 880 |
+
"step": 29000
|
| 881 |
+
},
|
| 882 |
+
{
|
| 883 |
+
"epoch": 0.06526115523305975,
|
| 884 |
+
"grad_norm": 5.073776721954346,
|
| 885 |
+
"learning_rate": 1.9834132784514063e-05,
|
| 886 |
+
"loss": 1.83912939453125,
|
| 887 |
+
"step": 29500
|
| 888 |
+
},
|
| 889 |
+
{
|
| 890 |
+
"epoch": 0.06526115523305975,
|
| 891 |
+
"eval_loss": 1.6621925830841064,
|
| 892 |
+
"eval_runtime": 65.5527,
|
| 893 |
+
"eval_samples_per_second": 152.549,
|
| 894 |
+
"eval_steps_per_second": 9.534,
|
| 895 |
+
"step": 29500
|
| 896 |
+
},
|
| 897 |
+
{
|
| 898 |
+
"epoch": 0.06636727650819636,
|
| 899 |
+
"grad_norm": 5.1272969245910645,
|
| 900 |
+
"learning_rate": 1.9828380275567797e-05,
|
| 901 |
+
"loss": 1.842152099609375,
|
| 902 |
+
"step": 30000
|
| 903 |
+
},
|
| 904 |
+
{
|
| 905 |
+
"epoch": 0.06636727650819636,
|
| 906 |
+
"eval_loss": 1.6653783321380615,
|
| 907 |
+
"eval_runtime": 66.132,
|
| 908 |
+
"eval_samples_per_second": 151.213,
|
| 909 |
+
"eval_steps_per_second": 9.451,
|
| 910 |
+
"step": 30000
|
| 911 |
+
},
|
| 912 |
+
{
|
| 913 |
+
"epoch": 0.06747339778333296,
|
| 914 |
+
"grad_norm": 5.014630317687988,
|
| 915 |
+
"learning_rate": 1.9822530570180568e-05,
|
| 916 |
+
"loss": 1.8277916259765625,
|
| 917 |
+
"step": 30500
|
| 918 |
+
},
|
| 919 |
+
{
|
| 920 |
+
"epoch": 0.06747339778333296,
|
| 921 |
+
"eval_loss": 1.6496976613998413,
|
| 922 |
+
"eval_runtime": 65.7954,
|
| 923 |
+
"eval_samples_per_second": 151.986,
|
| 924 |
+
"eval_steps_per_second": 9.499,
|
| 925 |
+
"step": 30500
|
| 926 |
+
},
|
| 927 |
+
{
|
| 928 |
+
"epoch": 0.06857951905846957,
|
| 929 |
+
"grad_norm": 4.427914619445801,
|
| 930 |
+
"learning_rate": 1.9816583726202243e-05,
|
| 931 |
+
"loss": 1.8151114501953125,
|
| 932 |
+
"step": 31000
|
| 933 |
+
},
|
| 934 |
+
{
|
| 935 |
+
"epoch": 0.06857951905846957,
|
| 936 |
+
"eval_loss": 1.6335314512252808,
|
| 937 |
+
"eval_runtime": 65.8023,
|
| 938 |
+
"eval_samples_per_second": 151.97,
|
| 939 |
+
"eval_steps_per_second": 9.498,
|
| 940 |
+
"step": 31000
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 0.06968564033360618,
|
| 944 |
+
"grad_norm": 5.199036598205566,
|
| 945 |
+
"learning_rate": 1.9810539802443333e-05,
|
| 946 |
+
"loss": 1.8143702392578125,
|
| 947 |
+
"step": 31500
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 0.06968564033360618,
|
| 951 |
+
"eval_loss": 1.623861312866211,
|
| 952 |
+
"eval_runtime": 66.1814,
|
| 953 |
+
"eval_samples_per_second": 151.1,
|
| 954 |
+
"eval_steps_per_second": 9.444,
|
| 955 |
+
"step": 31500
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 0.07079176160874279,
|
| 959 |
+
"grad_norm": 4.4861226081848145,
|
| 960 |
+
"learning_rate": 1.980439885867441e-05,
|
| 961 |
+
"loss": 1.785080078125,
|
| 962 |
+
"step": 32000
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 0.07079176160874279,
|
| 966 |
+
"eval_loss": 1.61989164352417,
|
| 967 |
+
"eval_runtime": 65.8909,
|
| 968 |
+
"eval_samples_per_second": 151.766,
|
| 969 |
+
"eval_steps_per_second": 9.485,
|
| 970 |
+
"step": 32000
|
| 971 |
+
},
|
| 972 |
+
{
|
| 973 |
+
"epoch": 0.07189788288387938,
|
| 974 |
+
"grad_norm": 5.459568023681641,
|
| 975 |
+
"learning_rate": 1.9798160955625502e-05,
|
| 976 |
+
"loss": 1.790661865234375,
|
| 977 |
+
"step": 32500
|
| 978 |
+
},
|
| 979 |
+
{
|
| 980 |
+
"epoch": 0.07189788288387938,
|
| 981 |
+
"eval_loss": 1.5985878705978394,
|
| 982 |
+
"eval_runtime": 66.8491,
|
| 983 |
+
"eval_samples_per_second": 149.591,
|
| 984 |
+
"eval_steps_per_second": 9.349,
|
| 985 |
+
"step": 32500
|
| 986 |
+
},
|
| 987 |
+
{
|
| 988 |
+
"epoch": 0.07300400415901599,
|
| 989 |
+
"grad_norm": 5.195436954498291,
|
| 990 |
+
"learning_rate": 1.9791826154985515e-05,
|
| 991 |
+
"loss": 1.770203369140625,
|
| 992 |
+
"step": 33000
|
| 993 |
+
},
|
| 994 |
+
{
|
| 995 |
+
"epoch": 0.07300400415901599,
|
| 996 |
+
"eval_loss": 1.5977914333343506,
|
| 997 |
+
"eval_runtime": 69.3781,
|
| 998 |
+
"eval_samples_per_second": 144.138,
|
| 999 |
+
"eval_steps_per_second": 9.009,
|
| 1000 |
+
"step": 33000
|
| 1001 |
+
},
|
| 1002 |
+
{
|
| 1003 |
+
"epoch": 0.0741101254341526,
|
| 1004 |
+
"grad_norm": 4.659327983856201,
|
| 1005 |
+
"learning_rate": 1.978539451940161e-05,
|
| 1006 |
+
"loss": 1.756498291015625,
|
| 1007 |
+
"step": 33500
|
| 1008 |
+
},
|
| 1009 |
+
{
|
| 1010 |
+
"epoch": 0.0741101254341526,
|
| 1011 |
+
"eval_loss": 1.5864726305007935,
|
| 1012 |
+
"eval_runtime": 68.1458,
|
| 1013 |
+
"eval_samples_per_second": 146.744,
|
| 1014 |
+
"eval_steps_per_second": 9.172,
|
| 1015 |
+
"step": 33500
|
| 1016 |
+
},
|
| 1017 |
+
{
|
| 1018 |
+
"epoch": 0.07521624670928921,
|
| 1019 |
+
"grad_norm": 4.486781120300293,
|
| 1020 |
+
"learning_rate": 1.977886611247857e-05,
|
| 1021 |
+
"loss": 1.7513958740234374,
|
| 1022 |
+
"step": 34000
|
| 1023 |
+
},
|
| 1024 |
+
{
|
| 1025 |
+
"epoch": 0.07521624670928921,
|
| 1026 |
+
"eval_loss": 1.5759690999984741,
|
| 1027 |
+
"eval_runtime": 66.295,
|
| 1028 |
+
"eval_samples_per_second": 150.841,
|
| 1029 |
+
"eval_steps_per_second": 9.428,
|
| 1030 |
+
"step": 34000
|
| 1031 |
+
},
|
| 1032 |
+
{
|
| 1033 |
+
"epoch": 0.0763223679844258,
|
| 1034 |
+
"grad_norm": 4.723703861236572,
|
| 1035 |
+
"learning_rate": 1.97722409987782e-05,
|
| 1036 |
+
"loss": 1.7431859130859375,
|
| 1037 |
+
"step": 34500
|
| 1038 |
+
},
|
| 1039 |
+
{
|
| 1040 |
+
"epoch": 0.0763223679844258,
|
| 1041 |
+
"eval_loss": 1.5756099224090576,
|
| 1042 |
+
"eval_runtime": 66.3119,
|
| 1043 |
+
"eval_samples_per_second": 150.803,
|
| 1044 |
+
"eval_steps_per_second": 9.425,
|
| 1045 |
+
"step": 34500
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 0.07742848925956242,
|
| 1049 |
+
"grad_norm": 4.389305114746094,
|
| 1050 |
+
"learning_rate": 1.9765519243818665e-05,
|
| 1051 |
+
"loss": 1.732319580078125,
|
| 1052 |
+
"step": 35000
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 0.07742848925956242,
|
| 1056 |
+
"eval_loss": 1.5581341981887817,
|
| 1057 |
+
"eval_runtime": 66.4353,
|
| 1058 |
+
"eval_samples_per_second": 150.522,
|
| 1059 |
+
"eval_steps_per_second": 9.408,
|
| 1060 |
+
"step": 35000
|
| 1061 |
+
},
|
| 1062 |
+
{
|
| 1063 |
+
"epoch": 0.07853461053469903,
|
| 1064 |
+
"grad_norm": 4.597053050994873,
|
| 1065 |
+
"learning_rate": 1.9758700914073858e-05,
|
| 1066 |
+
"loss": 1.7261806640625,
|
| 1067 |
+
"step": 35500
|
| 1068 |
+
},
|
| 1069 |
+
{
|
| 1070 |
+
"epoch": 0.07853461053469903,
|
| 1071 |
+
"eval_loss": 1.5474776029586792,
|
| 1072 |
+
"eval_runtime": 65.4425,
|
| 1073 |
+
"eval_samples_per_second": 152.806,
|
| 1074 |
+
"eval_steps_per_second": 9.55,
|
| 1075 |
+
"step": 35500
|
| 1076 |
+
},
|
| 1077 |
+
{
|
| 1078 |
+
"epoch": 0.07964073180983564,
|
| 1079 |
+
"grad_norm": 5.074342250823975,
|
| 1080 |
+
"learning_rate": 1.975178607697273e-05,
|
| 1081 |
+
"loss": 1.704677001953125,
|
| 1082 |
+
"step": 36000
|
| 1083 |
+
},
|
| 1084 |
+
{
|
| 1085 |
+
"epoch": 0.07964073180983564,
|
| 1086 |
+
"eval_loss": 1.5465320348739624,
|
| 1087 |
+
"eval_runtime": 67.0948,
|
| 1088 |
+
"eval_samples_per_second": 149.043,
|
| 1089 |
+
"eval_steps_per_second": 9.315,
|
| 1090 |
+
"step": 36000
|
| 1091 |
+
},
|
| 1092 |
+
{
|
| 1093 |
+
"epoch": 0.08074685308497223,
|
| 1094 |
+
"grad_norm": 4.983928680419922,
|
| 1095 |
+
"learning_rate": 1.974477480089863e-05,
|
| 1096 |
+
"loss": 1.7111588134765625,
|
| 1097 |
+
"step": 36500
|
| 1098 |
+
},
|
| 1099 |
+
{
|
| 1100 |
+
"epoch": 0.08074685308497223,
|
| 1101 |
+
"eval_loss": 1.5471775531768799,
|
| 1102 |
+
"eval_runtime": 66.0681,
|
| 1103 |
+
"eval_samples_per_second": 151.359,
|
| 1104 |
+
"eval_steps_per_second": 9.46,
|
| 1105 |
+
"step": 36500
|
| 1106 |
+
},
|
| 1107 |
+
{
|
| 1108 |
+
"epoch": 0.08185297436010884,
|
| 1109 |
+
"grad_norm": 4.309070587158203,
|
| 1110 |
+
"learning_rate": 1.9737667155188625e-05,
|
| 1111 |
+
"loss": 1.700852783203125,
|
| 1112 |
+
"step": 37000
|
| 1113 |
+
},
|
| 1114 |
+
{
|
| 1115 |
+
"epoch": 0.08185297436010884,
|
| 1116 |
+
"eval_loss": 1.5260053873062134,
|
| 1117 |
+
"eval_runtime": 65.5968,
|
| 1118 |
+
"eval_samples_per_second": 152.446,
|
| 1119 |
+
"eval_steps_per_second": 9.528,
|
| 1120 |
+
"step": 37000
|
| 1121 |
+
},
|
| 1122 |
+
{
|
| 1123 |
+
"epoch": 0.08295909563524545,
|
| 1124 |
+
"grad_norm": 5.114826679229736,
|
| 1125 |
+
"learning_rate": 1.9730463210132817e-05,
|
| 1126 |
+
"loss": 1.699755615234375,
|
| 1127 |
+
"step": 37500
|
| 1128 |
+
},
|
| 1129 |
+
{
|
| 1130 |
+
"epoch": 0.08295909563524545,
|
| 1131 |
+
"eval_loss": 1.5352414846420288,
|
| 1132 |
+
"eval_runtime": 65.7743,
|
| 1133 |
+
"eval_samples_per_second": 152.035,
|
| 1134 |
+
"eval_steps_per_second": 9.502,
|
| 1135 |
+
"step": 37500
|
| 1136 |
+
},
|
| 1137 |
+
{
|
| 1138 |
+
"epoch": 0.08406521691038206,
|
| 1139 |
+
"grad_norm": 4.944478988647461,
|
| 1140 |
+
"learning_rate": 1.9723163036973652e-05,
|
| 1141 |
+
"loss": 1.6774451904296874,
|
| 1142 |
+
"step": 38000
|
| 1143 |
+
},
|
| 1144 |
+
{
|
| 1145 |
+
"epoch": 0.08406521691038206,
|
| 1146 |
+
"eval_loss": 1.5184470415115356,
|
| 1147 |
+
"eval_runtime": 66.7501,
|
| 1148 |
+
"eval_samples_per_second": 149.813,
|
| 1149 |
+
"eval_steps_per_second": 9.363,
|
| 1150 |
+
"step": 38000
|
| 1151 |
+
},
|
| 1152 |
+
{
|
| 1153 |
+
"epoch": 0.08517133818551866,
|
| 1154 |
+
"grad_norm": 4.7983012199401855,
|
| 1155 |
+
"learning_rate": 1.971576670790521e-05,
|
| 1156 |
+
"loss": 1.6922623291015626,
|
| 1157 |
+
"step": 38500
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 0.08517133818551866,
|
| 1161 |
+
"eval_loss": 1.5099477767944336,
|
| 1162 |
+
"eval_runtime": 65.8114,
|
| 1163 |
+
"eval_samples_per_second": 151.949,
|
| 1164 |
+
"eval_steps_per_second": 9.497,
|
| 1165 |
+
"step": 38500
|
| 1166 |
+
},
|
| 1167 |
+
{
|
| 1168 |
+
"epoch": 0.08627745946065526,
|
| 1169 |
+
"grad_norm": 4.645780563354492,
|
| 1170 |
+
"learning_rate": 1.9708274296072487e-05,
|
| 1171 |
+
"loss": 1.6959698486328125,
|
| 1172 |
+
"step": 39000
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 0.08627745946065526,
|
| 1176 |
+
"eval_loss": 1.5127439498901367,
|
| 1177 |
+
"eval_runtime": 66.0848,
|
| 1178 |
+
"eval_samples_per_second": 151.321,
|
| 1179 |
+
"eval_steps_per_second": 9.458,
|
| 1180 |
+
"step": 39000
|
| 1181 |
+
},
|
| 1182 |
+
{
|
| 1183 |
+
"epoch": 0.08738358073579187,
|
| 1184 |
+
"grad_norm": 5.602351188659668,
|
| 1185 |
+
"learning_rate": 1.9700685875570678e-05,
|
| 1186 |
+
"loss": 1.668989501953125,
|
| 1187 |
+
"step": 39500
|
| 1188 |
+
},
|
| 1189 |
+
{
|
| 1190 |
+
"epoch": 0.08738358073579187,
|
| 1191 |
+
"eval_loss": 1.5060431957244873,
|
| 1192 |
+
"eval_runtime": 65.3814,
|
| 1193 |
+
"eval_samples_per_second": 152.949,
|
| 1194 |
+
"eval_steps_per_second": 9.559,
|
| 1195 |
+
"step": 39500
|
| 1196 |
+
},
|
| 1197 |
+
{
|
| 1198 |
+
"epoch": 0.08848970201092848,
|
| 1199 |
+
"grad_norm": 5.003055572509766,
|
| 1200 |
+
"learning_rate": 1.9693001521444445e-05,
|
| 1201 |
+
"loss": 1.657955810546875,
|
| 1202 |
+
"step": 40000
|
| 1203 |
+
},
|
| 1204 |
+
{
|
| 1205 |
+
"epoch": 0.08848970201092848,
|
| 1206 |
+
"eval_loss": 1.487270712852478,
|
| 1207 |
+
"eval_runtime": 65.5877,
|
| 1208 |
+
"eval_samples_per_second": 152.468,
|
| 1209 |
+
"eval_steps_per_second": 9.529,
|
| 1210 |
+
"step": 40000
|
| 1211 |
+
}
|
| 1212 |
+
],
|
| 1213 |
+
"logging_steps": 500,
|
| 1214 |
+
"max_steps": 500000,
|
| 1215 |
+
"num_input_tokens_seen": 0,
|
| 1216 |
+
"num_train_epochs": 2,
|
| 1217 |
+
"save_steps": 500,
|
| 1218 |
+
"stateful_callbacks": {
|
| 1219 |
+
"EarlyStoppingCallback": {
|
| 1220 |
+
"args": {
|
| 1221 |
+
"early_stopping_patience": 8,
|
| 1222 |
+
"early_stopping_threshold": 0.0
|
| 1223 |
+
},
|
| 1224 |
+
"attributes": {
|
| 1225 |
+
"early_stopping_patience_counter": 0
|
| 1226 |
+
}
|
| 1227 |
+
},
|
| 1228 |
+
"TrainerControl": {
|
| 1229 |
+
"args": {
|
| 1230 |
+
"should_epoch_stop": false,
|
| 1231 |
+
"should_evaluate": false,
|
| 1232 |
+
"should_log": false,
|
| 1233 |
+
"should_save": true,
|
| 1234 |
+
"should_training_stop": false
|
| 1235 |
+
},
|
| 1236 |
+
"attributes": {}
|
| 1237 |
+
}
|
| 1238 |
+
},
|
| 1239 |
+
"total_flos": 8.427905821534618e+16,
|
| 1240 |
+
"train_batch_size": 16,
|
| 1241 |
+
"trial_name": null,
|
| 1242 |
+
"trial_params": null
|
| 1243 |
+
}
|
Fsoft-AIC__videberta-base/tmp_checkpoints/checkpoint-40000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9389243dbf7fcc95a280d47b0331a96e11d3aead152fe1769d52dee590c11663
|
| 3 |
+
size 4856
|
Fsoft-AIC__videberta-base/tmp_checkpoints/checkpoint-40500/config.json
ADDED
|
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"DebertaV2ForMaskedLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_head_size": 64,
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"bos_token_id": null,
|
| 8 |
+
"dtype": "float32",
|
| 9 |
+
"eos_token_id": null,
|
| 10 |
+
"hidden_act": "gelu",
|
| 11 |
+
"hidden_dropout_prob": 0.1,
|
| 12 |
+
"hidden_size": 768,
|
| 13 |
+
"initializer_range": 0.02,
|
| 14 |
+
"intermediate_size": 3072,
|
| 15 |
+
"layer_norm_eps": 1e-07,
|
| 16 |
+
"legacy": true,
|
| 17 |
+
"max_position_embeddings": 512,
|
| 18 |
+
"max_relative_positions": -1,
|
| 19 |
+
"model_type": "deberta-v2",
|
| 20 |
+
"norm_rel_ebd": "layer_norm",
|
| 21 |
+
"num_attention_heads": 12,
|
| 22 |
+
"num_hidden_layers": 12,
|
| 23 |
+
"pad_token_id": 0,
|
| 24 |
+
"pooler_dropout": 0.0,
|
| 25 |
+
"pooler_hidden_act": "gelu",
|
| 26 |
+
"pooler_hidden_size": 768,
|
| 27 |
+
"pos_att_type": [
|
| 28 |
+
"p2c",
|
| 29 |
+
"c2p"
|
| 30 |
+
],
|
| 31 |
+
"position_biased_input": false,
|
| 32 |
+
"position_buckets": 256,
|
| 33 |
+
"relative_attention": true,
|
| 34 |
+
"share_att_key": true,
|
| 35 |
+
"tie_word_embeddings": true,
|
| 36 |
+
"transformers_version": "5.8.0",
|
| 37 |
+
"type_vocab_size": 0,
|
| 38 |
+
"use_cache": false,
|
| 39 |
+
"vocab_size": 128000
|
| 40 |
+
}
|
Fsoft-AIC__videberta-base/tmp_checkpoints/checkpoint-40500/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8eb2fc2e2e898e4a42afc350807290880f01c2b0419e9c2fe925d36a74ff8f4c
|
| 3 |
+
size 737924256
|
Fsoft-AIC__videberta-base/tmp_checkpoints/checkpoint-40500/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:78a1f7ae16bf601e00e41817747d0978f0547f51f226ae2d0b81f704425d2947
|
| 3 |
+
size 1475968826
|
Fsoft-AIC__videberta-base/tmp_checkpoints/checkpoint-40500/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e18608d76e6397648d03ad3b0131032df8eb868d101074c7d3933facf0a43f3f
|
| 3 |
+
size 14244
|
Fsoft-AIC__videberta-base/tmp_checkpoints/checkpoint-40500/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f340e6813a4405eaaf5974d413910f5327bdd12720dba397540c5fa202d5a632
|
| 3 |
+
size 1064
|
Fsoft-AIC__videberta-base/tmp_checkpoints/checkpoint-40500/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
Fsoft-AIC__videberta-base/tmp_checkpoints/checkpoint-40500/tokenizer_config.json
ADDED
|
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": true,
|
| 3 |
+
"backend": "tokenizers",
|
| 4 |
+
"bos_token": "[CLS]",
|
| 5 |
+
"cls_token": "[CLS]",
|
| 6 |
+
"do_lower_case": false,
|
| 7 |
+
"eos_token": "[SEP]",
|
| 8 |
+
"is_local": false,
|
| 9 |
+
"local_files_only": false,
|
| 10 |
+
"mask_token": "[MASK]",
|
| 11 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 12 |
+
"pad_token": "[PAD]",
|
| 13 |
+
"sep_token": "[SEP]",
|
| 14 |
+
"sp_model_kwargs": {},
|
| 15 |
+
"split_by_punct": false,
|
| 16 |
+
"tokenizer_class": "DebertaV2Tokenizer",
|
| 17 |
+
"unk_id": 3,
|
| 18 |
+
"unk_token": "[UNK]",
|
| 19 |
+
"vocab_type": "spm"
|
| 20 |
+
}
|
Fsoft-AIC__videberta-base/tmp_checkpoints/checkpoint-40500/trainer_state.json
ADDED
|
@@ -0,0 +1,1258 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": 40000,
|
| 3 |
+
"best_metric": 1.487270712852478,
|
| 4 |
+
"best_model_checkpoint": "pretrained_checkpoints/Fsoft-AIC__videberta-base/tmp_checkpoints/checkpoint-40000",
|
| 5 |
+
"epoch": 0.08959582328606508,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 40500,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.001106121275136606,
|
| 14 |
+
"grad_norm": 9.475790977478027,
|
| 15 |
+
"learning_rate": 1.9960000000000002e-05,
|
| 16 |
+
"loss": 10.73539453125,
|
| 17 |
+
"step": 500
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.001106121275136606,
|
| 21 |
+
"eval_loss": 6.908179759979248,
|
| 22 |
+
"eval_runtime": 65.5198,
|
| 23 |
+
"eval_samples_per_second": 152.626,
|
| 24 |
+
"eval_steps_per_second": 9.539,
|
| 25 |
+
"step": 500
|
| 26 |
+
},
|
| 27 |
+
{
|
| 28 |
+
"epoch": 0.002212242550273212,
|
| 29 |
+
"grad_norm": 4.896268367767334,
|
| 30 |
+
"learning_rate": 1.9999950750763816e-05,
|
| 31 |
+
"loss": 6.3172548828125,
|
| 32 |
+
"step": 1000
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.002212242550273212,
|
| 36 |
+
"eval_loss": 5.584421634674072,
|
| 37 |
+
"eval_runtime": 65.633,
|
| 38 |
+
"eval_samples_per_second": 152.362,
|
| 39 |
+
"eval_steps_per_second": 9.523,
|
| 40 |
+
"step": 1000
|
| 41 |
+
},
|
| 42 |
+
{
|
| 43 |
+
"epoch": 0.003318363825409818,
|
| 44 |
+
"grad_norm": 5.7100324630737305,
|
| 45 |
+
"learning_rate": 1.999980260856137e-05,
|
| 46 |
+
"loss": 5.51156884765625,
|
| 47 |
+
"step": 1500
|
| 48 |
+
},
|
| 49 |
+
{
|
| 50 |
+
"epoch": 0.003318363825409818,
|
| 51 |
+
"eval_loss": 5.097376823425293,
|
| 52 |
+
"eval_runtime": 65.5025,
|
| 53 |
+
"eval_samples_per_second": 152.666,
|
| 54 |
+
"eval_steps_per_second": 9.542,
|
| 55 |
+
"step": 1500
|
| 56 |
+
},
|
| 57 |
+
{
|
| 58 |
+
"epoch": 0.004424485100546424,
|
| 59 |
+
"grad_norm": 5.015883922576904,
|
| 60 |
+
"learning_rate": 1.9999555574659926e-05,
|
| 61 |
+
"loss": 5.04186083984375,
|
| 62 |
+
"step": 2000
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.004424485100546424,
|
| 66 |
+
"eval_loss": 4.640530109405518,
|
| 67 |
+
"eval_runtime": 65.8074,
|
| 68 |
+
"eval_samples_per_second": 151.959,
|
| 69 |
+
"eval_steps_per_second": 9.497,
|
| 70 |
+
"step": 2000
|
| 71 |
+
},
|
| 72 |
+
{
|
| 73 |
+
"epoch": 0.00553060637568303,
|
| 74 |
+
"grad_norm": 5.8804450035095215,
|
| 75 |
+
"learning_rate": 1.9999209651502484e-05,
|
| 76 |
+
"loss": 4.6854267578125,
|
| 77 |
+
"step": 2500
|
| 78 |
+
},
|
| 79 |
+
{
|
| 80 |
+
"epoch": 0.00553060637568303,
|
| 81 |
+
"eval_loss": 4.30808162689209,
|
| 82 |
+
"eval_runtime": 65.7347,
|
| 83 |
+
"eval_samples_per_second": 152.127,
|
| 84 |
+
"eval_steps_per_second": 9.508,
|
| 85 |
+
"step": 2500
|
| 86 |
+
},
|
| 87 |
+
{
|
| 88 |
+
"epoch": 0.006636727650819636,
|
| 89 |
+
"grad_norm": 6.087777614593506,
|
| 90 |
+
"learning_rate": 1.999876484251e-05,
|
| 91 |
+
"loss": 4.3789228515625,
|
| 92 |
+
"step": 3000
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.006636727650819636,
|
| 96 |
+
"eval_loss": 4.010719299316406,
|
| 97 |
+
"eval_runtime": 65.6921,
|
| 98 |
+
"eval_samples_per_second": 152.225,
|
| 99 |
+
"eval_steps_per_second": 9.514,
|
| 100 |
+
"step": 3000
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.0077428489259562415,
|
| 104 |
+
"grad_norm": 5.5657639503479,
|
| 105 |
+
"learning_rate": 1.9998221152081356e-05,
|
| 106 |
+
"loss": 4.1345771484375,
|
| 107 |
+
"step": 3500
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.0077428489259562415,
|
| 111 |
+
"eval_loss": 3.785635232925415,
|
| 112 |
+
"eval_runtime": 66.3485,
|
| 113 |
+
"eval_samples_per_second": 150.719,
|
| 114 |
+
"eval_steps_per_second": 9.42,
|
| 115 |
+
"step": 3500
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.008848970201092848,
|
| 119 |
+
"grad_norm": 6.631436824798584,
|
| 120 |
+
"learning_rate": 1.999757858559331e-05,
|
| 121 |
+
"loss": 3.9143818359375,
|
| 122 |
+
"step": 4000
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.008848970201092848,
|
| 126 |
+
"eval_loss": 3.588374614715576,
|
| 127 |
+
"eval_runtime": 66.3332,
|
| 128 |
+
"eval_samples_per_second": 150.754,
|
| 129 |
+
"eval_steps_per_second": 9.422,
|
| 130 |
+
"step": 4000
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 0.009955091476229454,
|
| 134 |
+
"grad_norm": 5.396254062652588,
|
| 135 |
+
"learning_rate": 1.999683714940043e-05,
|
| 136 |
+
"loss": 3.759765869140625,
|
| 137 |
+
"step": 4500
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 0.009955091476229454,
|
| 141 |
+
"eval_loss": 3.429428815841675,
|
| 142 |
+
"eval_runtime": 65.5002,
|
| 143 |
+
"eval_samples_per_second": 152.671,
|
| 144 |
+
"eval_steps_per_second": 9.542,
|
| 145 |
+
"step": 4500
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 0.01106121275136606,
|
| 149 |
+
"grad_norm": 5.386684894561768,
|
| 150 |
+
"learning_rate": 1.999599685083505e-05,
|
| 151 |
+
"loss": 3.61756494140625,
|
| 152 |
+
"step": 5000
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 0.01106121275136606,
|
| 156 |
+
"eval_loss": 3.315566301345825,
|
| 157 |
+
"eval_runtime": 65.3359,
|
| 158 |
+
"eval_samples_per_second": 153.055,
|
| 159 |
+
"eval_steps_per_second": 9.566,
|
| 160 |
+
"step": 5000
|
| 161 |
+
},
|
| 162 |
+
{
|
| 163 |
+
"epoch": 0.012167334026502667,
|
| 164 |
+
"grad_norm": 6.260346412658691,
|
| 165 |
+
"learning_rate": 1.9995057698207195e-05,
|
| 166 |
+
"loss": 3.486438720703125,
|
| 167 |
+
"step": 5500
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 0.012167334026502667,
|
| 171 |
+
"eval_loss": 3.190394639968872,
|
| 172 |
+
"eval_runtime": 65.353,
|
| 173 |
+
"eval_samples_per_second": 153.015,
|
| 174 |
+
"eval_steps_per_second": 9.563,
|
| 175 |
+
"step": 5500
|
| 176 |
+
},
|
| 177 |
+
{
|
| 178 |
+
"epoch": 0.013273455301639273,
|
| 179 |
+
"grad_norm": 5.308413028717041,
|
| 180 |
+
"learning_rate": 1.9994019700804483e-05,
|
| 181 |
+
"loss": 3.372943115234375,
|
| 182 |
+
"step": 6000
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 0.013273455301639273,
|
| 186 |
+
"eval_loss": 3.07236647605896,
|
| 187 |
+
"eval_runtime": 65.1836,
|
| 188 |
+
"eval_samples_per_second": 153.413,
|
| 189 |
+
"eval_steps_per_second": 9.588,
|
| 190 |
+
"step": 6000
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"epoch": 0.014379576576775877,
|
| 194 |
+
"grad_norm": 5.559189796447754,
|
| 195 |
+
"learning_rate": 1.9992882868892052e-05,
|
| 196 |
+
"loss": 3.33723486328125,
|
| 197 |
+
"step": 6500
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 0.014379576576775877,
|
| 201 |
+
"eval_loss": 2.9914042949676514,
|
| 202 |
+
"eval_runtime": 65.1138,
|
| 203 |
+
"eval_samples_per_second": 153.577,
|
| 204 |
+
"eval_steps_per_second": 9.599,
|
| 205 |
+
"step": 6500
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.015485697851912483,
|
| 209 |
+
"grad_norm": 5.7293925285339355,
|
| 210 |
+
"learning_rate": 1.9991647213712446e-05,
|
| 211 |
+
"loss": 3.1835166015625,
|
| 212 |
+
"step": 7000
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.015485697851912483,
|
| 216 |
+
"eval_loss": 2.9056553840637207,
|
| 217 |
+
"eval_runtime": 66.6383,
|
| 218 |
+
"eval_samples_per_second": 150.064,
|
| 219 |
+
"eval_steps_per_second": 9.379,
|
| 220 |
+
"step": 7000
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.01659181912704909,
|
| 224 |
+
"grad_norm": 5.745417594909668,
|
| 225 |
+
"learning_rate": 1.999031274748551e-05,
|
| 226 |
+
"loss": 3.09816748046875,
|
| 227 |
+
"step": 7500
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.01659181912704909,
|
| 231 |
+
"eval_loss": 2.8260159492492676,
|
| 232 |
+
"eval_runtime": 65.6949,
|
| 233 |
+
"eval_samples_per_second": 152.219,
|
| 234 |
+
"eval_steps_per_second": 9.514,
|
| 235 |
+
"step": 7500
|
| 236 |
+
},
|
| 237 |
+
{
|
| 238 |
+
"epoch": 0.017697940402185697,
|
| 239 |
+
"grad_norm": 5.706750869750977,
|
| 240 |
+
"learning_rate": 1.9988879483408266e-05,
|
| 241 |
+
"loss": 3.02596435546875,
|
| 242 |
+
"step": 8000
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 0.017697940402185697,
|
| 246 |
+
"eval_loss": 2.7651631832122803,
|
| 247 |
+
"eval_runtime": 65.8495,
|
| 248 |
+
"eval_samples_per_second": 151.862,
|
| 249 |
+
"eval_steps_per_second": 9.491,
|
| 250 |
+
"step": 8000
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"epoch": 0.018804061677322303,
|
| 254 |
+
"grad_norm": 4.90167760848999,
|
| 255 |
+
"learning_rate": 1.998734743565479e-05,
|
| 256 |
+
"loss": 2.940542236328125,
|
| 257 |
+
"step": 8500
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 0.018804061677322303,
|
| 261 |
+
"eval_loss": 2.683983325958252,
|
| 262 |
+
"eval_runtime": 65.8236,
|
| 263 |
+
"eval_samples_per_second": 151.921,
|
| 264 |
+
"eval_steps_per_second": 9.495,
|
| 265 |
+
"step": 8500
|
| 266 |
+
},
|
| 267 |
+
{
|
| 268 |
+
"epoch": 0.01991018295245891,
|
| 269 |
+
"grad_norm": 6.079418182373047,
|
| 270 |
+
"learning_rate": 1.998571661937606e-05,
|
| 271 |
+
"loss": 2.8865009765625,
|
| 272 |
+
"step": 9000
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 0.01991018295245891,
|
| 276 |
+
"eval_loss": 2.624776840209961,
|
| 277 |
+
"eval_runtime": 65.9969,
|
| 278 |
+
"eval_samples_per_second": 151.522,
|
| 279 |
+
"eval_steps_per_second": 9.47,
|
| 280 |
+
"step": 9000
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 0.021016304227595515,
|
| 284 |
+
"grad_norm": 5.454369068145752,
|
| 285 |
+
"learning_rate": 1.9983987050699813e-05,
|
| 286 |
+
"loss": 2.817274169921875,
|
| 287 |
+
"step": 9500
|
| 288 |
+
},
|
| 289 |
+
{
|
| 290 |
+
"epoch": 0.021016304227595515,
|
| 291 |
+
"eval_loss": 2.580995559692383,
|
| 292 |
+
"eval_runtime": 65.6963,
|
| 293 |
+
"eval_samples_per_second": 152.216,
|
| 294 |
+
"eval_steps_per_second": 9.513,
|
| 295 |
+
"step": 9500
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 0.02212242550273212,
|
| 299 |
+
"grad_norm": 5.633095741271973,
|
| 300 |
+
"learning_rate": 1.9982158746730387e-05,
|
| 301 |
+
"loss": 2.784319091796875,
|
| 302 |
+
"step": 10000
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 0.02212242550273212,
|
| 306 |
+
"eval_loss": 2.502817153930664,
|
| 307 |
+
"eval_runtime": 65.4322,
|
| 308 |
+
"eval_samples_per_second": 152.83,
|
| 309 |
+
"eval_steps_per_second": 9.552,
|
| 310 |
+
"step": 10000
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.023228546777868727,
|
| 314 |
+
"grad_norm": 5.46868896484375,
|
| 315 |
+
"learning_rate": 1.9980231725548545e-05,
|
| 316 |
+
"loss": 2.702649658203125,
|
| 317 |
+
"step": 10500
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.023228546777868727,
|
| 321 |
+
"eval_loss": 2.465555191040039,
|
| 322 |
+
"eval_runtime": 65.0987,
|
| 323 |
+
"eval_samples_per_second": 153.613,
|
| 324 |
+
"eval_steps_per_second": 9.601,
|
| 325 |
+
"step": 10500
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.024334668053005333,
|
| 329 |
+
"grad_norm": 5.703943252563477,
|
| 330 |
+
"learning_rate": 1.9978206006211304e-05,
|
| 331 |
+
"loss": 2.6762646484375,
|
| 332 |
+
"step": 11000
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.024334668053005333,
|
| 336 |
+
"eval_loss": 2.410994529724121,
|
| 337 |
+
"eval_runtime": 65.8492,
|
| 338 |
+
"eval_samples_per_second": 151.862,
|
| 339 |
+
"eval_steps_per_second": 9.491,
|
| 340 |
+
"step": 11000
|
| 341 |
+
},
|
| 342 |
+
{
|
| 343 |
+
"epoch": 0.02544078932814194,
|
| 344 |
+
"grad_norm": 5.745393753051758,
|
| 345 |
+
"learning_rate": 1.9976081608751742e-05,
|
| 346 |
+
"loss": 2.61624267578125,
|
| 347 |
+
"step": 11500
|
| 348 |
+
},
|
| 349 |
+
{
|
| 350 |
+
"epoch": 0.02544078932814194,
|
| 351 |
+
"eval_loss": 2.377451181411743,
|
| 352 |
+
"eval_runtime": 65.697,
|
| 353 |
+
"eval_samples_per_second": 152.214,
|
| 354 |
+
"eval_steps_per_second": 9.513,
|
| 355 |
+
"step": 11500
|
| 356 |
+
},
|
| 357 |
+
{
|
| 358 |
+
"epoch": 0.026546910603278545,
|
| 359 |
+
"grad_norm": 5.889176845550537,
|
| 360 |
+
"learning_rate": 1.99738585541788e-05,
|
| 361 |
+
"loss": 2.5832724609375,
|
| 362 |
+
"step": 12000
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 0.026546910603278545,
|
| 366 |
+
"eval_loss": 2.334881544113159,
|
| 367 |
+
"eval_runtime": 65.862,
|
| 368 |
+
"eval_samples_per_second": 151.833,
|
| 369 |
+
"eval_steps_per_second": 9.49,
|
| 370 |
+
"step": 12000
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 0.027653031878415148,
|
| 374 |
+
"grad_norm": 5.409160614013672,
|
| 375 |
+
"learning_rate": 1.9971536864477078e-05,
|
| 376 |
+
"loss": 2.548913818359375,
|
| 377 |
+
"step": 12500
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 0.027653031878415148,
|
| 381 |
+
"eval_loss": 2.30452823638916,
|
| 382 |
+
"eval_runtime": 65.0769,
|
| 383 |
+
"eval_samples_per_second": 153.664,
|
| 384 |
+
"eval_steps_per_second": 9.604,
|
| 385 |
+
"step": 12500
|
| 386 |
+
},
|
| 387 |
+
{
|
| 388 |
+
"epoch": 0.028759153153551754,
|
| 389 |
+
"grad_norm": 5.37885046005249,
|
| 390 |
+
"learning_rate": 1.9969116562606614e-05,
|
| 391 |
+
"loss": 2.498342041015625,
|
| 392 |
+
"step": 13000
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 0.028759153153551754,
|
| 396 |
+
"eval_loss": 2.262269973754883,
|
| 397 |
+
"eval_runtime": 66.4547,
|
| 398 |
+
"eval_samples_per_second": 150.478,
|
| 399 |
+
"eval_steps_per_second": 9.405,
|
| 400 |
+
"step": 13000
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"epoch": 0.02986527442868836,
|
| 404 |
+
"grad_norm": 5.803339004516602,
|
| 405 |
+
"learning_rate": 1.9966597672502653e-05,
|
| 406 |
+
"loss": 2.449419921875,
|
| 407 |
+
"step": 13500
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 0.02986527442868836,
|
| 411 |
+
"eval_loss": 2.2417187690734863,
|
| 412 |
+
"eval_runtime": 65.9915,
|
| 413 |
+
"eval_samples_per_second": 151.535,
|
| 414 |
+
"eval_steps_per_second": 9.471,
|
| 415 |
+
"step": 13500
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.030971395703824966,
|
| 419 |
+
"grad_norm": 5.598288059234619,
|
| 420 |
+
"learning_rate": 1.9963980219075425e-05,
|
| 421 |
+
"loss": 2.43294775390625,
|
| 422 |
+
"step": 14000
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.030971395703824966,
|
| 426 |
+
"eval_loss": 2.1951167583465576,
|
| 427 |
+
"eval_runtime": 66.3059,
|
| 428 |
+
"eval_samples_per_second": 150.816,
|
| 429 |
+
"eval_steps_per_second": 9.426,
|
| 430 |
+
"step": 14000
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 0.03207751697896157,
|
| 434 |
+
"grad_norm": 5.400110244750977,
|
| 435 |
+
"learning_rate": 1.9961264228209876e-05,
|
| 436 |
+
"loss": 2.380520263671875,
|
| 437 |
+
"step": 14500
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 0.03207751697896157,
|
| 441 |
+
"eval_loss": 2.1698226928710938,
|
| 442 |
+
"eval_runtime": 65.841,
|
| 443 |
+
"eval_samples_per_second": 151.881,
|
| 444 |
+
"eval_steps_per_second": 9.493,
|
| 445 |
+
"step": 14500
|
| 446 |
+
},
|
| 447 |
+
{
|
| 448 |
+
"epoch": 0.03318363825409818,
|
| 449 |
+
"grad_norm": 5.006521224975586,
|
| 450 |
+
"learning_rate": 1.995844972676544e-05,
|
| 451 |
+
"loss": 2.36803515625,
|
| 452 |
+
"step": 15000
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 0.03318363825409818,
|
| 456 |
+
"eval_loss": 2.1508238315582275,
|
| 457 |
+
"eval_runtime": 65.8184,
|
| 458 |
+
"eval_samples_per_second": 151.933,
|
| 459 |
+
"eval_steps_per_second": 9.496,
|
| 460 |
+
"step": 15000
|
| 461 |
+
},
|
| 462 |
+
{
|
| 463 |
+
"epoch": 0.034289759529234784,
|
| 464 |
+
"grad_norm": 22.403335571289062,
|
| 465 |
+
"learning_rate": 1.9955536742575737e-05,
|
| 466 |
+
"loss": 2.337472900390625,
|
| 467 |
+
"step": 15500
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 0.034289759529234784,
|
| 471 |
+
"eval_loss": 2.131364345550537,
|
| 472 |
+
"eval_runtime": 65.3739,
|
| 473 |
+
"eval_samples_per_second": 152.966,
|
| 474 |
+
"eval_steps_per_second": 9.56,
|
| 475 |
+
"step": 15500
|
| 476 |
+
},
|
| 477 |
+
{
|
| 478 |
+
"epoch": 0.035395880804371394,
|
| 479 |
+
"grad_norm": 4.748437881469727,
|
| 480 |
+
"learning_rate": 1.995252530444834e-05,
|
| 481 |
+
"loss": 2.32045849609375,
|
| 482 |
+
"step": 16000
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 0.035395880804371394,
|
| 486 |
+
"eval_loss": 2.0844030380249023,
|
| 487 |
+
"eval_runtime": 65.3283,
|
| 488 |
+
"eval_samples_per_second": 153.073,
|
| 489 |
+
"eval_steps_per_second": 9.567,
|
| 490 |
+
"step": 16000
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"epoch": 0.036502002079507996,
|
| 494 |
+
"grad_norm": 4.933561325073242,
|
| 495 |
+
"learning_rate": 1.9949415442164463e-05,
|
| 496 |
+
"loss": 2.2753798828125,
|
| 497 |
+
"step": 16500
|
| 498 |
+
},
|
| 499 |
+
{
|
| 500 |
+
"epoch": 0.036502002079507996,
|
| 501 |
+
"eval_loss": 2.060131549835205,
|
| 502 |
+
"eval_runtime": 65.6122,
|
| 503 |
+
"eval_samples_per_second": 152.411,
|
| 504 |
+
"eval_steps_per_second": 9.526,
|
| 505 |
+
"step": 16500
|
| 506 |
+
},
|
| 507 |
+
{
|
| 508 |
+
"epoch": 0.037608123354644606,
|
| 509 |
+
"grad_norm": 5.674777507781982,
|
| 510 |
+
"learning_rate": 1.9946207186478655e-05,
|
| 511 |
+
"loss": 2.25116943359375,
|
| 512 |
+
"step": 17000
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 0.037608123354644606,
|
| 516 |
+
"eval_loss": 2.0405194759368896,
|
| 517 |
+
"eval_runtime": 65.3009,
|
| 518 |
+
"eval_samples_per_second": 153.137,
|
| 519 |
+
"eval_steps_per_second": 9.571,
|
| 520 |
+
"step": 17000
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 0.03871424462978121,
|
| 524 |
+
"grad_norm": 5.777343273162842,
|
| 525 |
+
"learning_rate": 1.9942900569118546e-05,
|
| 526 |
+
"loss": 2.23547802734375,
|
| 527 |
+
"step": 17500
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.03871424462978121,
|
| 531 |
+
"eval_loss": 2.0208609104156494,
|
| 532 |
+
"eval_runtime": 66.1739,
|
| 533 |
+
"eval_samples_per_second": 151.117,
|
| 534 |
+
"eval_steps_per_second": 9.445,
|
| 535 |
+
"step": 17500
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 0.03982036590491782,
|
| 539 |
+
"grad_norm": 5.607430458068848,
|
| 540 |
+
"learning_rate": 1.9939495622784472e-05,
|
| 541 |
+
"loss": 2.1993876953125,
|
| 542 |
+
"step": 18000
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 0.03982036590491782,
|
| 546 |
+
"eval_loss": 2.001434087753296,
|
| 547 |
+
"eval_runtime": 66.1661,
|
| 548 |
+
"eval_samples_per_second": 151.135,
|
| 549 |
+
"eval_steps_per_second": 9.446,
|
| 550 |
+
"step": 18000
|
| 551 |
+
},
|
| 552 |
+
{
|
| 553 |
+
"epoch": 0.04092648718005442,
|
| 554 |
+
"grad_norm": 5.273671627044678,
|
| 555 |
+
"learning_rate": 1.993599238114919e-05,
|
| 556 |
+
"loss": 2.180281982421875,
|
| 557 |
+
"step": 18500
|
| 558 |
+
},
|
| 559 |
+
{
|
| 560 |
+
"epoch": 0.04092648718005442,
|
| 561 |
+
"eval_loss": 1.983248233795166,
|
| 562 |
+
"eval_runtime": 65.6213,
|
| 563 |
+
"eval_samples_per_second": 152.39,
|
| 564 |
+
"eval_steps_per_second": 9.524,
|
| 565 |
+
"step": 18500
|
| 566 |
+
},
|
| 567 |
+
{
|
| 568 |
+
"epoch": 0.04203260845519103,
|
| 569 |
+
"grad_norm": 5.48894739151001,
|
| 570 |
+
"learning_rate": 1.993239087885754e-05,
|
| 571 |
+
"loss": 2.180351318359375,
|
| 572 |
+
"step": 19000
|
| 573 |
+
},
|
| 574 |
+
{
|
| 575 |
+
"epoch": 0.04203260845519103,
|
| 576 |
+
"eval_loss": 1.9536426067352295,
|
| 577 |
+
"eval_runtime": 65.1545,
|
| 578 |
+
"eval_samples_per_second": 153.481,
|
| 579 |
+
"eval_steps_per_second": 9.593,
|
| 580 |
+
"step": 19000
|
| 581 |
+
},
|
| 582 |
+
{
|
| 583 |
+
"epoch": 0.04313872973032763,
|
| 584 |
+
"grad_norm": 4.517572402954102,
|
| 585 |
+
"learning_rate": 1.992869115152609e-05,
|
| 586 |
+
"loss": 2.14364501953125,
|
| 587 |
+
"step": 19500
|
| 588 |
+
},
|
| 589 |
+
{
|
| 590 |
+
"epoch": 0.04313872973032763,
|
| 591 |
+
"eval_loss": 1.9281601905822754,
|
| 592 |
+
"eval_runtime": 65.6074,
|
| 593 |
+
"eval_samples_per_second": 152.422,
|
| 594 |
+
"eval_steps_per_second": 9.526,
|
| 595 |
+
"step": 19500
|
| 596 |
+
},
|
| 597 |
+
{
|
| 598 |
+
"epoch": 0.04424485100546424,
|
| 599 |
+
"grad_norm": 5.366357326507568,
|
| 600 |
+
"learning_rate": 1.9924893235742795e-05,
|
| 601 |
+
"loss": 2.124390380859375,
|
| 602 |
+
"step": 20000
|
| 603 |
+
},
|
| 604 |
+
{
|
| 605 |
+
"epoch": 0.04424485100546424,
|
| 606 |
+
"eval_loss": 1.9185084104537964,
|
| 607 |
+
"eval_runtime": 66.4777,
|
| 608 |
+
"eval_samples_per_second": 150.426,
|
| 609 |
+
"eval_steps_per_second": 9.402,
|
| 610 |
+
"step": 20000
|
| 611 |
+
},
|
| 612 |
+
{
|
| 613 |
+
"epoch": 0.045350972280600844,
|
| 614 |
+
"grad_norm": 5.40119743347168,
|
| 615 |
+
"learning_rate": 1.992099716906663e-05,
|
| 616 |
+
"loss": 2.11509521484375,
|
| 617 |
+
"step": 20500
|
| 618 |
+
},
|
| 619 |
+
{
|
| 620 |
+
"epoch": 0.045350972280600844,
|
| 621 |
+
"eval_loss": 1.8964039087295532,
|
| 622 |
+
"eval_runtime": 65.269,
|
| 623 |
+
"eval_samples_per_second": 153.212,
|
| 624 |
+
"eval_steps_per_second": 9.576,
|
| 625 |
+
"step": 20500
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.046457093555737454,
|
| 629 |
+
"grad_norm": 4.91980504989624,
|
| 630 |
+
"learning_rate": 1.9917002990027225e-05,
|
| 631 |
+
"loss": 2.080730224609375,
|
| 632 |
+
"step": 21000
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 0.046457093555737454,
|
| 636 |
+
"eval_loss": 1.8814513683319092,
|
| 637 |
+
"eval_runtime": 65.8396,
|
| 638 |
+
"eval_samples_per_second": 151.884,
|
| 639 |
+
"eval_steps_per_second": 9.493,
|
| 640 |
+
"step": 21000
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 0.04756321483087406,
|
| 644 |
+
"grad_norm": 5.756763458251953,
|
| 645 |
+
"learning_rate": 1.991291073812447e-05,
|
| 646 |
+
"loss": 2.062693359375,
|
| 647 |
+
"step": 21500
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 0.04756321483087406,
|
| 651 |
+
"eval_loss": 1.8653240203857422,
|
| 652 |
+
"eval_runtime": 65.2727,
|
| 653 |
+
"eval_samples_per_second": 153.203,
|
| 654 |
+
"eval_steps_per_second": 9.575,
|
| 655 |
+
"step": 21500
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"epoch": 0.048669336106010666,
|
| 659 |
+
"grad_norm": 4.964697360992432,
|
| 660 |
+
"learning_rate": 1.990872045382814e-05,
|
| 661 |
+
"loss": 2.0461234130859376,
|
| 662 |
+
"step": 22000
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 0.048669336106010666,
|
| 666 |
+
"eval_loss": 1.8559273481369019,
|
| 667 |
+
"eval_runtime": 65.7552,
|
| 668 |
+
"eval_samples_per_second": 152.079,
|
| 669 |
+
"eval_steps_per_second": 9.505,
|
| 670 |
+
"step": 22000
|
| 671 |
+
},
|
| 672 |
+
{
|
| 673 |
+
"epoch": 0.04977545738114727,
|
| 674 |
+
"grad_norm": 4.809401988983154,
|
| 675 |
+
"learning_rate": 1.990443217857749e-05,
|
| 676 |
+
"loss": 2.030472412109375,
|
| 677 |
+
"step": 22500
|
| 678 |
+
},
|
| 679 |
+
{
|
| 680 |
+
"epoch": 0.04977545738114727,
|
| 681 |
+
"eval_loss": 1.8380959033966064,
|
| 682 |
+
"eval_runtime": 65.6745,
|
| 683 |
+
"eval_samples_per_second": 152.266,
|
| 684 |
+
"eval_steps_per_second": 9.517,
|
| 685 |
+
"step": 22500
|
| 686 |
+
},
|
| 687 |
+
{
|
| 688 |
+
"epoch": 0.05088157865628388,
|
| 689 |
+
"grad_norm": 5.332137584686279,
|
| 690 |
+
"learning_rate": 1.9900045954780833e-05,
|
| 691 |
+
"loss": 2.019200439453125,
|
| 692 |
+
"step": 23000
|
| 693 |
+
},
|
| 694 |
+
{
|
| 695 |
+
"epoch": 0.05088157865628388,
|
| 696 |
+
"eval_loss": 1.8243741989135742,
|
| 697 |
+
"eval_runtime": 66.808,
|
| 698 |
+
"eval_samples_per_second": 149.683,
|
| 699 |
+
"eval_steps_per_second": 9.355,
|
| 700 |
+
"step": 23000
|
| 701 |
+
},
|
| 702 |
+
{
|
| 703 |
+
"epoch": 0.05198769993142048,
|
| 704 |
+
"grad_norm": 5.7028913497924805,
|
| 705 |
+
"learning_rate": 1.989556182581514e-05,
|
| 706 |
+
"loss": 1.9847816162109375,
|
| 707 |
+
"step": 23500
|
| 708 |
+
},
|
| 709 |
+
{
|
| 710 |
+
"epoch": 0.05198769993142048,
|
| 711 |
+
"eval_loss": 1.8052804470062256,
|
| 712 |
+
"eval_runtime": 65.2434,
|
| 713 |
+
"eval_samples_per_second": 153.272,
|
| 714 |
+
"eval_steps_per_second": 9.58,
|
| 715 |
+
"step": 23500
|
| 716 |
+
},
|
| 717 |
+
{
|
| 718 |
+
"epoch": 0.05309382120655709,
|
| 719 |
+
"grad_norm": 4.981122970581055,
|
| 720 |
+
"learning_rate": 1.98909798360256e-05,
|
| 721 |
+
"loss": 1.9902779541015625,
|
| 722 |
+
"step": 24000
|
| 723 |
+
},
|
| 724 |
+
{
|
| 725 |
+
"epoch": 0.05309382120655709,
|
| 726 |
+
"eval_loss": 1.7762919664382935,
|
| 727 |
+
"eval_runtime": 65.1802,
|
| 728 |
+
"eval_samples_per_second": 153.421,
|
| 729 |
+
"eval_steps_per_second": 9.589,
|
| 730 |
+
"step": 24000
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 0.05419994248169369,
|
| 734 |
+
"grad_norm": 4.917308807373047,
|
| 735 |
+
"learning_rate": 1.9886300030725185e-05,
|
| 736 |
+
"loss": 1.9727127685546875,
|
| 737 |
+
"step": 24500
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 0.05419994248169369,
|
| 741 |
+
"eval_loss": 1.7766869068145752,
|
| 742 |
+
"eval_runtime": 65.0747,
|
| 743 |
+
"eval_samples_per_second": 153.67,
|
| 744 |
+
"eval_steps_per_second": 9.604,
|
| 745 |
+
"step": 24500
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 0.055306063756830295,
|
| 749 |
+
"grad_norm": 4.780125141143799,
|
| 750 |
+
"learning_rate": 1.9881522456194194e-05,
|
| 751 |
+
"loss": 1.948054443359375,
|
| 752 |
+
"step": 25000
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 0.055306063756830295,
|
| 756 |
+
"eval_loss": 1.7642755508422852,
|
| 757 |
+
"eval_runtime": 65.8137,
|
| 758 |
+
"eval_samples_per_second": 151.944,
|
| 759 |
+
"eval_steps_per_second": 9.497,
|
| 760 |
+
"step": 25000
|
| 761 |
+
},
|
| 762 |
+
{
|
| 763 |
+
"epoch": 0.056412185031966905,
|
| 764 |
+
"grad_norm": 5.44115686416626,
|
| 765 |
+
"learning_rate": 1.9876647159679813e-05,
|
| 766 |
+
"loss": 1.9313668212890625,
|
| 767 |
+
"step": 25500
|
| 768 |
+
},
|
| 769 |
+
{
|
| 770 |
+
"epoch": 0.056412185031966905,
|
| 771 |
+
"eval_loss": 1.7497310638427734,
|
| 772 |
+
"eval_runtime": 65.536,
|
| 773 |
+
"eval_samples_per_second": 152.588,
|
| 774 |
+
"eval_steps_per_second": 9.537,
|
| 775 |
+
"step": 25500
|
| 776 |
+
},
|
| 777 |
+
{
|
| 778 |
+
"epoch": 0.05751830630710351,
|
| 779 |
+
"grad_norm": 4.406560897827148,
|
| 780 |
+
"learning_rate": 1.9871674189395622e-05,
|
| 781 |
+
"loss": 1.933572021484375,
|
| 782 |
+
"step": 26000
|
| 783 |
+
},
|
| 784 |
+
{
|
| 785 |
+
"epoch": 0.05751830630710351,
|
| 786 |
+
"eval_loss": 1.7356730699539185,
|
| 787 |
+
"eval_runtime": 66.4858,
|
| 788 |
+
"eval_samples_per_second": 150.408,
|
| 789 |
+
"eval_steps_per_second": 9.401,
|
| 790 |
+
"step": 26000
|
| 791 |
+
},
|
| 792 |
+
{
|
| 793 |
+
"epoch": 0.05862442758224012,
|
| 794 |
+
"grad_norm": 6.296497344970703,
|
| 795 |
+
"learning_rate": 1.9866603594521142e-05,
|
| 796 |
+
"loss": 1.91761669921875,
|
| 797 |
+
"step": 26500
|
| 798 |
+
},
|
| 799 |
+
{
|
| 800 |
+
"epoch": 0.05862442758224012,
|
| 801 |
+
"eval_loss": 1.7373892068862915,
|
| 802 |
+
"eval_runtime": 65.2531,
|
| 803 |
+
"eval_samples_per_second": 153.25,
|
| 804 |
+
"eval_steps_per_second": 9.578,
|
| 805 |
+
"step": 26500
|
| 806 |
+
},
|
| 807 |
+
{
|
| 808 |
+
"epoch": 0.05973054885737672,
|
| 809 |
+
"grad_norm": 5.007937908172607,
|
| 810 |
+
"learning_rate": 1.9861435425201336e-05,
|
| 811 |
+
"loss": 1.898394287109375,
|
| 812 |
+
"step": 27000
|
| 813 |
+
},
|
| 814 |
+
{
|
| 815 |
+
"epoch": 0.05973054885737672,
|
| 816 |
+
"eval_loss": 1.7208389043807983,
|
| 817 |
+
"eval_runtime": 65.1399,
|
| 818 |
+
"eval_samples_per_second": 153.516,
|
| 819 |
+
"eval_steps_per_second": 9.595,
|
| 820 |
+
"step": 27000
|
| 821 |
+
},
|
| 822 |
+
{
|
| 823 |
+
"epoch": 0.06083667013251333,
|
| 824 |
+
"grad_norm": 4.655943393707275,
|
| 825 |
+
"learning_rate": 1.985616973254612e-05,
|
| 826 |
+
"loss": 1.9006209716796876,
|
| 827 |
+
"step": 27500
|
| 828 |
+
},
|
| 829 |
+
{
|
| 830 |
+
"epoch": 0.06083667013251333,
|
| 831 |
+
"eval_loss": 1.7028509378433228,
|
| 832 |
+
"eval_runtime": 66.0059,
|
| 833 |
+
"eval_samples_per_second": 151.502,
|
| 834 |
+
"eval_steps_per_second": 9.469,
|
| 835 |
+
"step": 27500
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 0.06194279140764993,
|
| 839 |
+
"grad_norm": 5.251052379608154,
|
| 840 |
+
"learning_rate": 1.985080656862985e-05,
|
| 841 |
+
"loss": 1.88404931640625,
|
| 842 |
+
"step": 28000
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 0.06194279140764993,
|
| 846 |
+
"eval_loss": 1.7043781280517578,
|
| 847 |
+
"eval_runtime": 65.8348,
|
| 848 |
+
"eval_samples_per_second": 151.895,
|
| 849 |
+
"eval_steps_per_second": 9.493,
|
| 850 |
+
"step": 28000
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 0.06304891268278653,
|
| 854 |
+
"grad_norm": 5.259983539581299,
|
| 855 |
+
"learning_rate": 1.984534598649081e-05,
|
| 856 |
+
"loss": 1.875679931640625,
|
| 857 |
+
"step": 28500
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 0.06304891268278653,
|
| 861 |
+
"eval_loss": 1.6936031579971313,
|
| 862 |
+
"eval_runtime": 65.104,
|
| 863 |
+
"eval_samples_per_second": 153.6,
|
| 864 |
+
"eval_steps_per_second": 9.6,
|
| 865 |
+
"step": 28500
|
| 866 |
+
},
|
| 867 |
+
{
|
| 868 |
+
"epoch": 0.06415503395792314,
|
| 869 |
+
"grad_norm": 4.902404308319092,
|
| 870 |
+
"learning_rate": 1.9839788040130693e-05,
|
| 871 |
+
"loss": 1.8586162109375,
|
| 872 |
+
"step": 29000
|
| 873 |
+
},
|
| 874 |
+
{
|
| 875 |
+
"epoch": 0.06415503395792314,
|
| 876 |
+
"eval_loss": 1.6735634803771973,
|
| 877 |
+
"eval_runtime": 65.6048,
|
| 878 |
+
"eval_samples_per_second": 152.428,
|
| 879 |
+
"eval_steps_per_second": 9.527,
|
| 880 |
+
"step": 29000
|
| 881 |
+
},
|
| 882 |
+
{
|
| 883 |
+
"epoch": 0.06526115523305975,
|
| 884 |
+
"grad_norm": 5.073776721954346,
|
| 885 |
+
"learning_rate": 1.9834132784514063e-05,
|
| 886 |
+
"loss": 1.83912939453125,
|
| 887 |
+
"step": 29500
|
| 888 |
+
},
|
| 889 |
+
{
|
| 890 |
+
"epoch": 0.06526115523305975,
|
| 891 |
+
"eval_loss": 1.6621925830841064,
|
| 892 |
+
"eval_runtime": 65.5527,
|
| 893 |
+
"eval_samples_per_second": 152.549,
|
| 894 |
+
"eval_steps_per_second": 9.534,
|
| 895 |
+
"step": 29500
|
| 896 |
+
},
|
| 897 |
+
{
|
| 898 |
+
"epoch": 0.06636727650819636,
|
| 899 |
+
"grad_norm": 5.1272969245910645,
|
| 900 |
+
"learning_rate": 1.9828380275567797e-05,
|
| 901 |
+
"loss": 1.842152099609375,
|
| 902 |
+
"step": 30000
|
| 903 |
+
},
|
| 904 |
+
{
|
| 905 |
+
"epoch": 0.06636727650819636,
|
| 906 |
+
"eval_loss": 1.6653783321380615,
|
| 907 |
+
"eval_runtime": 66.132,
|
| 908 |
+
"eval_samples_per_second": 151.213,
|
| 909 |
+
"eval_steps_per_second": 9.451,
|
| 910 |
+
"step": 30000
|
| 911 |
+
},
|
| 912 |
+
{
|
| 913 |
+
"epoch": 0.06747339778333296,
|
| 914 |
+
"grad_norm": 5.014630317687988,
|
| 915 |
+
"learning_rate": 1.9822530570180568e-05,
|
| 916 |
+
"loss": 1.8277916259765625,
|
| 917 |
+
"step": 30500
|
| 918 |
+
},
|
| 919 |
+
{
|
| 920 |
+
"epoch": 0.06747339778333296,
|
| 921 |
+
"eval_loss": 1.6496976613998413,
|
| 922 |
+
"eval_runtime": 65.7954,
|
| 923 |
+
"eval_samples_per_second": 151.986,
|
| 924 |
+
"eval_steps_per_second": 9.499,
|
| 925 |
+
"step": 30500
|
| 926 |
+
},
|
| 927 |
+
{
|
| 928 |
+
"epoch": 0.06857951905846957,
|
| 929 |
+
"grad_norm": 4.427914619445801,
|
| 930 |
+
"learning_rate": 1.9816583726202243e-05,
|
| 931 |
+
"loss": 1.8151114501953125,
|
| 932 |
+
"step": 31000
|
| 933 |
+
},
|
| 934 |
+
{
|
| 935 |
+
"epoch": 0.06857951905846957,
|
| 936 |
+
"eval_loss": 1.6335314512252808,
|
| 937 |
+
"eval_runtime": 65.8023,
|
| 938 |
+
"eval_samples_per_second": 151.97,
|
| 939 |
+
"eval_steps_per_second": 9.498,
|
| 940 |
+
"step": 31000
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 0.06968564033360618,
|
| 944 |
+
"grad_norm": 5.199036598205566,
|
| 945 |
+
"learning_rate": 1.9810539802443333e-05,
|
| 946 |
+
"loss": 1.8143702392578125,
|
| 947 |
+
"step": 31500
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 0.06968564033360618,
|
| 951 |
+
"eval_loss": 1.623861312866211,
|
| 952 |
+
"eval_runtime": 66.1814,
|
| 953 |
+
"eval_samples_per_second": 151.1,
|
| 954 |
+
"eval_steps_per_second": 9.444,
|
| 955 |
+
"step": 31500
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 0.07079176160874279,
|
| 959 |
+
"grad_norm": 4.4861226081848145,
|
| 960 |
+
"learning_rate": 1.980439885867441e-05,
|
| 961 |
+
"loss": 1.785080078125,
|
| 962 |
+
"step": 32000
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 0.07079176160874279,
|
| 966 |
+
"eval_loss": 1.61989164352417,
|
| 967 |
+
"eval_runtime": 65.8909,
|
| 968 |
+
"eval_samples_per_second": 151.766,
|
| 969 |
+
"eval_steps_per_second": 9.485,
|
| 970 |
+
"step": 32000
|
| 971 |
+
},
|
| 972 |
+
{
|
| 973 |
+
"epoch": 0.07189788288387938,
|
| 974 |
+
"grad_norm": 5.459568023681641,
|
| 975 |
+
"learning_rate": 1.9798160955625502e-05,
|
| 976 |
+
"loss": 1.790661865234375,
|
| 977 |
+
"step": 32500
|
| 978 |
+
},
|
| 979 |
+
{
|
| 980 |
+
"epoch": 0.07189788288387938,
|
| 981 |
+
"eval_loss": 1.5985878705978394,
|
| 982 |
+
"eval_runtime": 66.8491,
|
| 983 |
+
"eval_samples_per_second": 149.591,
|
| 984 |
+
"eval_steps_per_second": 9.349,
|
| 985 |
+
"step": 32500
|
| 986 |
+
},
|
| 987 |
+
{
|
| 988 |
+
"epoch": 0.07300400415901599,
|
| 989 |
+
"grad_norm": 5.195436954498291,
|
| 990 |
+
"learning_rate": 1.9791826154985515e-05,
|
| 991 |
+
"loss": 1.770203369140625,
|
| 992 |
+
"step": 33000
|
| 993 |
+
},
|
| 994 |
+
{
|
| 995 |
+
"epoch": 0.07300400415901599,
|
| 996 |
+
"eval_loss": 1.5977914333343506,
|
| 997 |
+
"eval_runtime": 69.3781,
|
| 998 |
+
"eval_samples_per_second": 144.138,
|
| 999 |
+
"eval_steps_per_second": 9.009,
|
| 1000 |
+
"step": 33000
|
| 1001 |
+
},
|
| 1002 |
+
{
|
| 1003 |
+
"epoch": 0.0741101254341526,
|
| 1004 |
+
"grad_norm": 4.659327983856201,
|
| 1005 |
+
"learning_rate": 1.978539451940161e-05,
|
| 1006 |
+
"loss": 1.756498291015625,
|
| 1007 |
+
"step": 33500
|
| 1008 |
+
},
|
| 1009 |
+
{
|
| 1010 |
+
"epoch": 0.0741101254341526,
|
| 1011 |
+
"eval_loss": 1.5864726305007935,
|
| 1012 |
+
"eval_runtime": 68.1458,
|
| 1013 |
+
"eval_samples_per_second": 146.744,
|
| 1014 |
+
"eval_steps_per_second": 9.172,
|
| 1015 |
+
"step": 33500
|
| 1016 |
+
},
|
| 1017 |
+
{
|
| 1018 |
+
"epoch": 0.07521624670928921,
|
| 1019 |
+
"grad_norm": 4.486781120300293,
|
| 1020 |
+
"learning_rate": 1.977886611247857e-05,
|
| 1021 |
+
"loss": 1.7513958740234374,
|
| 1022 |
+
"step": 34000
|
| 1023 |
+
},
|
| 1024 |
+
{
|
| 1025 |
+
"epoch": 0.07521624670928921,
|
| 1026 |
+
"eval_loss": 1.5759690999984741,
|
| 1027 |
+
"eval_runtime": 66.295,
|
| 1028 |
+
"eval_samples_per_second": 150.841,
|
| 1029 |
+
"eval_steps_per_second": 9.428,
|
| 1030 |
+
"step": 34000
|
| 1031 |
+
},
|
| 1032 |
+
{
|
| 1033 |
+
"epoch": 0.0763223679844258,
|
| 1034 |
+
"grad_norm": 4.723703861236572,
|
| 1035 |
+
"learning_rate": 1.97722409987782e-05,
|
| 1036 |
+
"loss": 1.7431859130859375,
|
| 1037 |
+
"step": 34500
|
| 1038 |
+
},
|
| 1039 |
+
{
|
| 1040 |
+
"epoch": 0.0763223679844258,
|
| 1041 |
+
"eval_loss": 1.5756099224090576,
|
| 1042 |
+
"eval_runtime": 66.3119,
|
| 1043 |
+
"eval_samples_per_second": 150.803,
|
| 1044 |
+
"eval_steps_per_second": 9.425,
|
| 1045 |
+
"step": 34500
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 0.07742848925956242,
|
| 1049 |
+
"grad_norm": 4.389305114746094,
|
| 1050 |
+
"learning_rate": 1.9765519243818665e-05,
|
| 1051 |
+
"loss": 1.732319580078125,
|
| 1052 |
+
"step": 35000
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 0.07742848925956242,
|
| 1056 |
+
"eval_loss": 1.5581341981887817,
|
| 1057 |
+
"eval_runtime": 66.4353,
|
| 1058 |
+
"eval_samples_per_second": 150.522,
|
| 1059 |
+
"eval_steps_per_second": 9.408,
|
| 1060 |
+
"step": 35000
|
| 1061 |
+
},
|
| 1062 |
+
{
|
| 1063 |
+
"epoch": 0.07853461053469903,
|
| 1064 |
+
"grad_norm": 4.597053050994873,
|
| 1065 |
+
"learning_rate": 1.9758700914073858e-05,
|
| 1066 |
+
"loss": 1.7261806640625,
|
| 1067 |
+
"step": 35500
|
| 1068 |
+
},
|
| 1069 |
+
{
|
| 1070 |
+
"epoch": 0.07853461053469903,
|
| 1071 |
+
"eval_loss": 1.5474776029586792,
|
| 1072 |
+
"eval_runtime": 65.4425,
|
| 1073 |
+
"eval_samples_per_second": 152.806,
|
| 1074 |
+
"eval_steps_per_second": 9.55,
|
| 1075 |
+
"step": 35500
|
| 1076 |
+
},
|
| 1077 |
+
{
|
| 1078 |
+
"epoch": 0.07964073180983564,
|
| 1079 |
+
"grad_norm": 5.074342250823975,
|
| 1080 |
+
"learning_rate": 1.975178607697273e-05,
|
| 1081 |
+
"loss": 1.704677001953125,
|
| 1082 |
+
"step": 36000
|
| 1083 |
+
},
|
| 1084 |
+
{
|
| 1085 |
+
"epoch": 0.07964073180983564,
|
| 1086 |
+
"eval_loss": 1.5465320348739624,
|
| 1087 |
+
"eval_runtime": 67.0948,
|
| 1088 |
+
"eval_samples_per_second": 149.043,
|
| 1089 |
+
"eval_steps_per_second": 9.315,
|
| 1090 |
+
"step": 36000
|
| 1091 |
+
},
|
| 1092 |
+
{
|
| 1093 |
+
"epoch": 0.08074685308497223,
|
| 1094 |
+
"grad_norm": 4.983928680419922,
|
| 1095 |
+
"learning_rate": 1.974477480089863e-05,
|
| 1096 |
+
"loss": 1.7111588134765625,
|
| 1097 |
+
"step": 36500
|
| 1098 |
+
},
|
| 1099 |
+
{
|
| 1100 |
+
"epoch": 0.08074685308497223,
|
| 1101 |
+
"eval_loss": 1.5471775531768799,
|
| 1102 |
+
"eval_runtime": 66.0681,
|
| 1103 |
+
"eval_samples_per_second": 151.359,
|
| 1104 |
+
"eval_steps_per_second": 9.46,
|
| 1105 |
+
"step": 36500
|
| 1106 |
+
},
|
| 1107 |
+
{
|
| 1108 |
+
"epoch": 0.08185297436010884,
|
| 1109 |
+
"grad_norm": 4.309070587158203,
|
| 1110 |
+
"learning_rate": 1.9737667155188625e-05,
|
| 1111 |
+
"loss": 1.700852783203125,
|
| 1112 |
+
"step": 37000
|
| 1113 |
+
},
|
| 1114 |
+
{
|
| 1115 |
+
"epoch": 0.08185297436010884,
|
| 1116 |
+
"eval_loss": 1.5260053873062134,
|
| 1117 |
+
"eval_runtime": 65.5968,
|
| 1118 |
+
"eval_samples_per_second": 152.446,
|
| 1119 |
+
"eval_steps_per_second": 9.528,
|
| 1120 |
+
"step": 37000
|
| 1121 |
+
},
|
| 1122 |
+
{
|
| 1123 |
+
"epoch": 0.08295909563524545,
|
| 1124 |
+
"grad_norm": 5.114826679229736,
|
| 1125 |
+
"learning_rate": 1.9730463210132817e-05,
|
| 1126 |
+
"loss": 1.699755615234375,
|
| 1127 |
+
"step": 37500
|
| 1128 |
+
},
|
| 1129 |
+
{
|
| 1130 |
+
"epoch": 0.08295909563524545,
|
| 1131 |
+
"eval_loss": 1.5352414846420288,
|
| 1132 |
+
"eval_runtime": 65.7743,
|
| 1133 |
+
"eval_samples_per_second": 152.035,
|
| 1134 |
+
"eval_steps_per_second": 9.502,
|
| 1135 |
+
"step": 37500
|
| 1136 |
+
},
|
| 1137 |
+
{
|
| 1138 |
+
"epoch": 0.08406521691038206,
|
| 1139 |
+
"grad_norm": 4.944478988647461,
|
| 1140 |
+
"learning_rate": 1.9723163036973652e-05,
|
| 1141 |
+
"loss": 1.6774451904296874,
|
| 1142 |
+
"step": 38000
|
| 1143 |
+
},
|
| 1144 |
+
{
|
| 1145 |
+
"epoch": 0.08406521691038206,
|
| 1146 |
+
"eval_loss": 1.5184470415115356,
|
| 1147 |
+
"eval_runtime": 66.7501,
|
| 1148 |
+
"eval_samples_per_second": 149.813,
|
| 1149 |
+
"eval_steps_per_second": 9.363,
|
| 1150 |
+
"step": 38000
|
| 1151 |
+
},
|
| 1152 |
+
{
|
| 1153 |
+
"epoch": 0.08517133818551866,
|
| 1154 |
+
"grad_norm": 4.7983012199401855,
|
| 1155 |
+
"learning_rate": 1.971576670790521e-05,
|
| 1156 |
+
"loss": 1.6922623291015626,
|
| 1157 |
+
"step": 38500
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 0.08517133818551866,
|
| 1161 |
+
"eval_loss": 1.5099477767944336,
|
| 1162 |
+
"eval_runtime": 65.8114,
|
| 1163 |
+
"eval_samples_per_second": 151.949,
|
| 1164 |
+
"eval_steps_per_second": 9.497,
|
| 1165 |
+
"step": 38500
|
| 1166 |
+
},
|
| 1167 |
+
{
|
| 1168 |
+
"epoch": 0.08627745946065526,
|
| 1169 |
+
"grad_norm": 4.645780563354492,
|
| 1170 |
+
"learning_rate": 1.9708274296072487e-05,
|
| 1171 |
+
"loss": 1.6959698486328125,
|
| 1172 |
+
"step": 39000
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 0.08627745946065526,
|
| 1176 |
+
"eval_loss": 1.5127439498901367,
|
| 1177 |
+
"eval_runtime": 66.0848,
|
| 1178 |
+
"eval_samples_per_second": 151.321,
|
| 1179 |
+
"eval_steps_per_second": 9.458,
|
| 1180 |
+
"step": 39000
|
| 1181 |
+
},
|
| 1182 |
+
{
|
| 1183 |
+
"epoch": 0.08738358073579187,
|
| 1184 |
+
"grad_norm": 5.602351188659668,
|
| 1185 |
+
"learning_rate": 1.9700685875570678e-05,
|
| 1186 |
+
"loss": 1.668989501953125,
|
| 1187 |
+
"step": 39500
|
| 1188 |
+
},
|
| 1189 |
+
{
|
| 1190 |
+
"epoch": 0.08738358073579187,
|
| 1191 |
+
"eval_loss": 1.5060431957244873,
|
| 1192 |
+
"eval_runtime": 65.3814,
|
| 1193 |
+
"eval_samples_per_second": 152.949,
|
| 1194 |
+
"eval_steps_per_second": 9.559,
|
| 1195 |
+
"step": 39500
|
| 1196 |
+
},
|
| 1197 |
+
{
|
| 1198 |
+
"epoch": 0.08848970201092848,
|
| 1199 |
+
"grad_norm": 5.003055572509766,
|
| 1200 |
+
"learning_rate": 1.9693001521444445e-05,
|
| 1201 |
+
"loss": 1.657955810546875,
|
| 1202 |
+
"step": 40000
|
| 1203 |
+
},
|
| 1204 |
+
{
|
| 1205 |
+
"epoch": 0.08848970201092848,
|
| 1206 |
+
"eval_loss": 1.487270712852478,
|
| 1207 |
+
"eval_runtime": 65.5877,
|
| 1208 |
+
"eval_samples_per_second": 152.468,
|
| 1209 |
+
"eval_steps_per_second": 9.529,
|
| 1210 |
+
"step": 40000
|
| 1211 |
+
},
|
| 1212 |
+
{
|
| 1213 |
+
"epoch": 0.08959582328606508,
|
| 1214 |
+
"grad_norm": 4.99888801574707,
|
| 1215 |
+
"learning_rate": 1.968522130968717e-05,
|
| 1216 |
+
"loss": 1.64573046875,
|
| 1217 |
+
"step": 40500
|
| 1218 |
+
},
|
| 1219 |
+
{
|
| 1220 |
+
"epoch": 0.08959582328606508,
|
| 1221 |
+
"eval_loss": 1.4930541515350342,
|
| 1222 |
+
"eval_runtime": 65.6676,
|
| 1223 |
+
"eval_samples_per_second": 152.282,
|
| 1224 |
+
"eval_steps_per_second": 9.518,
|
| 1225 |
+
"step": 40500
|
| 1226 |
+
}
|
| 1227 |
+
],
|
| 1228 |
+
"logging_steps": 500,
|
| 1229 |
+
"max_steps": 500000,
|
| 1230 |
+
"num_input_tokens_seen": 0,
|
| 1231 |
+
"num_train_epochs": 2,
|
| 1232 |
+
"save_steps": 500,
|
| 1233 |
+
"stateful_callbacks": {
|
| 1234 |
+
"EarlyStoppingCallback": {
|
| 1235 |
+
"args": {
|
| 1236 |
+
"early_stopping_patience": 8,
|
| 1237 |
+
"early_stopping_threshold": 0.0
|
| 1238 |
+
},
|
| 1239 |
+
"attributes": {
|
| 1240 |
+
"early_stopping_patience_counter": 1
|
| 1241 |
+
}
|
| 1242 |
+
},
|
| 1243 |
+
"TrainerControl": {
|
| 1244 |
+
"args": {
|
| 1245 |
+
"should_epoch_stop": false,
|
| 1246 |
+
"should_evaluate": false,
|
| 1247 |
+
"should_log": false,
|
| 1248 |
+
"should_save": true,
|
| 1249 |
+
"should_training_stop": false
|
| 1250 |
+
},
|
| 1251 |
+
"attributes": {}
|
| 1252 |
+
}
|
| 1253 |
+
},
|
| 1254 |
+
"total_flos": 8.533239420483994e+16,
|
| 1255 |
+
"train_batch_size": 16,
|
| 1256 |
+
"trial_name": null,
|
| 1257 |
+
"trial_params": null
|
| 1258 |
+
}
|
Fsoft-AIC__videberta-base/tmp_checkpoints/checkpoint-40500/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9389243dbf7fcc95a280d47b0331a96e11d3aead152fe1769d52dee590c11663
|
| 3 |
+
size 4856
|
MikeGreen2710__mlm_listing_checkpoint-32442/.ipynb_checkpoints/pretrain_metadata-checkpoint.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"model_name": "MikeGreen2710/mlm_listing_checkpoint-32442",
|
| 3 |
+
"perplexity": 1.9174,
|
| 4 |
+
"eval_loss": 0.650966,
|
| 5 |
+
"mlm_probability": 0.15,
|
| 6 |
+
"whole_word_masking": true,
|
| 7 |
+
"max_steps": 5000,
|
| 8 |
+
"learning_rate": 3e-05,
|
| 9 |
+
"pretrained_at": "2026-05-13 06:20:15"
|
| 10 |
+
}
|
MikeGreen2710__mlm_listing_checkpoint-32442/added_tokens.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<mask>": 64000
|
| 3 |
+
}
|
MikeGreen2710__mlm_listing_checkpoint-32442/bpe.codes
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
MikeGreen2710__mlm_listing_checkpoint-32442/config.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_cross_attention": false,
|
| 3 |
+
"architectures": [
|
| 4 |
+
"RobertaForMaskedLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"bos_token_id": 0,
|
| 8 |
+
"classifier_dropout": null,
|
| 9 |
+
"dtype": "float32",
|
| 10 |
+
"eos_token_id": 2,
|
| 11 |
+
"gradient_checkpointing": false,
|
| 12 |
+
"hidden_act": "gelu",
|
| 13 |
+
"hidden_dropout_prob": 0.1,
|
| 14 |
+
"hidden_size": 1024,
|
| 15 |
+
"initializer_range": 0.02,
|
| 16 |
+
"intermediate_size": 4096,
|
| 17 |
+
"is_decoder": false,
|
| 18 |
+
"layer_norm_eps": 1e-05,
|
| 19 |
+
"max_position_embeddings": 258,
|
| 20 |
+
"model_type": "roberta",
|
| 21 |
+
"num_attention_heads": 16,
|
| 22 |
+
"num_hidden_layers": 24,
|
| 23 |
+
"pad_token_id": 1,
|
| 24 |
+
"position_embedding_type": "absolute",
|
| 25 |
+
"tie_word_embeddings": true,
|
| 26 |
+
"tokenizer_class": "PhobertTokenizer",
|
| 27 |
+
"transformers_version": "5.8.0",
|
| 28 |
+
"type_vocab_size": 1,
|
| 29 |
+
"use_cache": false,
|
| 30 |
+
"vocab_size": 64001
|
| 31 |
+
}
|
MikeGreen2710__mlm_listing_checkpoint-32442/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:664d6c4a64e34c2e08d4b546c1be507f324cebea98898fa222e4e31366d46095
|
| 3 |
+
size 1476965596
|
MikeGreen2710__mlm_listing_checkpoint-32442/pretrain_metadata.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"model_name": "MikeGreen2710/mlm_listing_checkpoint-32442",
|
| 3 |
+
"perplexity": 2.0284,
|
| 4 |
+
"eval_loss": 0.707233,
|
| 5 |
+
"mlm_probability": 0.15,
|
| 6 |
+
"whole_word_masking": true,
|
| 7 |
+
"max_steps": 50000,
|
| 8 |
+
"learning_rate": 3e-05,
|
| 9 |
+
"pretrained_at": "2026-05-13 19:02:03"
|
| 10 |
+
}
|
MikeGreen2710__mlm_listing_checkpoint-32442/tokenizer_config.json
ADDED
|
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "<s>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "<pad>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "</s>",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"3": {
|
| 28 |
+
"content": "<unk>",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"64000": {
|
| 36 |
+
"content": "<mask>",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"backend": "custom",
|
| 45 |
+
"bos_token": "<s>",
|
| 46 |
+
"cls_token": "<s>",
|
| 47 |
+
"eos_token": "</s>",
|
| 48 |
+
"is_local": false,
|
| 49 |
+
"local_files_only": false,
|
| 50 |
+
"mask_token": "<mask>",
|
| 51 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 52 |
+
"pad_token": "<pad>",
|
| 53 |
+
"sep_token": "</s>",
|
| 54 |
+
"tokenizer_class": "PhobertTokenizer",
|
| 55 |
+
"unk_token": "<unk>"
|
| 56 |
+
}
|
MikeGreen2710__mlm_listing_checkpoint-32442/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6f9fa4324e5417e89ec813d9d9171a12eb8d25e3b665944e9730560f35c08884
|
| 3 |
+
size 4920
|
MikeGreen2710__mlm_listing_checkpoint-32442/vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
NlpHUST__electra-base-vn/config.json
ADDED
|
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_cross_attention": false,
|
| 3 |
+
"architectures": [
|
| 4 |
+
"ElectraForMaskedLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"bos_token_id": null,
|
| 8 |
+
"classifier_dropout": null,
|
| 9 |
+
"dtype": "float32",
|
| 10 |
+
"embedding_size": 768,
|
| 11 |
+
"eos_token_id": null,
|
| 12 |
+
"hidden_act": "gelu",
|
| 13 |
+
"hidden_dropout_prob": 0.1,
|
| 14 |
+
"hidden_size": 768,
|
| 15 |
+
"initializer_range": 0.02,
|
| 16 |
+
"intermediate_size": 3072,
|
| 17 |
+
"is_decoder": false,
|
| 18 |
+
"layer_norm_eps": 1e-12,
|
| 19 |
+
"max_position_embeddings": 512,
|
| 20 |
+
"model_type": "electra",
|
| 21 |
+
"num_attention_heads": 12,
|
| 22 |
+
"num_hidden_layers": 12,
|
| 23 |
+
"pad_token_id": 0,
|
| 24 |
+
"summary_activation": "gelu",
|
| 25 |
+
"summary_last_dropout": 0.1,
|
| 26 |
+
"summary_type": "first",
|
| 27 |
+
"summary_use_proj": true,
|
| 28 |
+
"tie_word_embeddings": true,
|
| 29 |
+
"transformers_version": "5.8.0",
|
| 30 |
+
"type_vocab_size": 2,
|
| 31 |
+
"use_cache": false,
|
| 32 |
+
"vocab_size": 62000
|
| 33 |
+
}
|
NlpHUST__electra-base-vn/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cdd00acb0b5670e7ee2ac7a97155f93cf7ce2df1325392910007381a2ec5267b
|
| 3 |
+
size 534907816
|
NlpHUST__electra-base-vn/pretrain_metadata.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"model_name": "NlpHUST/electra-base-vn",
|
| 3 |
+
"perplexity": 2.6595,
|
| 4 |
+
"eval_loss": 0.978123,
|
| 5 |
+
"mlm_probability": 0.15,
|
| 6 |
+
"whole_word_masking": false,
|
| 7 |
+
"max_steps": 10000,
|
| 8 |
+
"learning_rate": 3e-05,
|
| 9 |
+
"pretrained_at": "2026-05-13 09:15:05"
|
| 10 |
+
}
|
NlpHUST__electra-base-vn/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
NlpHUST__electra-base-vn/tokenizer_config.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"backend": "tokenizers",
|
| 3 |
+
"cls_token": "[CLS]",
|
| 4 |
+
"do_lower_case": false,
|
| 5 |
+
"is_local": false,
|
| 6 |
+
"local_files_only": false,
|
| 7 |
+
"mask_token": "[MASK]",
|
| 8 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 9 |
+
"pad_token": "[PAD]",
|
| 10 |
+
"sep_token": "[SEP]",
|
| 11 |
+
"strip_accents": null,
|
| 12 |
+
"tokenize_chinese_chars": true,
|
| 13 |
+
"tokenizer_class": "BertTokenizer",
|
| 14 |
+
"unk_token": "[UNK]"
|
| 15 |
+
}
|
NlpHUST__electra-base-vn/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b95480b17f3ee9440639b86b2c7a4160484820261a32594f42b92c7a9b31ffb5
|
| 3 |
+
size 4856
|
_token_cache/Fsoft-AIC__videberta-base/eval_00000_of_00004.arrow
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c5551e9a29f4d9be27a7183a8e27b70b77594bddf5c28f60550a966d28d7ee7b
|
| 3 |
+
size 3538072
|
_token_cache/Fsoft-AIC__videberta-base/eval_00001_of_00004.arrow
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5b35dea59161f0e52570d2cc8170494b34130d0ce80f3f00d2ed5e37d80d7bd6
|
| 3 |
+
size 3537112
|
_token_cache/Fsoft-AIC__videberta-base/eval_00002_of_00004.arrow
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2282074482bfbb965be84811b072218c19ddb03326b9d567ebb2c2253f9b0234
|
| 3 |
+
size 3564808
|
_token_cache/Fsoft-AIC__videberta-base/eval_00003_of_00004.arrow
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:540e11fec437057a753a24004f2ae85e314c0127e6a6f2560caf7f7bfde6896f
|
| 3 |
+
size 3534408
|
_token_cache/Fsoft-AIC__videberta-base/train_00000_of_00004.arrow
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:89e6c89958861d0b04471cd044947b047a7f50fd5150c90f6334ba5a308fc63e
|
| 3 |
+
size 2555708896
|
_token_cache/Fsoft-AIC__videberta-base/train_00001_of_00004.arrow
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0f245751553ddc10728b112d5fc4ec18adeceaf93138129321ce1af70f3768e4
|
| 3 |
+
size 2555645216
|
_token_cache/Fsoft-AIC__videberta-base/train_00002_of_00004.arrow
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a82d5ed6a860b5b80d8e7d761f13ee9b5753a1a9999c0e9b8d23f61bcfc05406
|
| 3 |
+
size 2555377912
|
_token_cache/Fsoft-AIC__videberta-base/train_00003_of_00004.arrow
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6838ada7d35c7a8520dd6ebc5cd8d4f5f465e59bb30478ced945d63768b887b9
|
| 3 |
+
size 2555366824
|
_token_cache/MikeGreen2710__mlm_listing_checkpoint-32442/eval_00000_of_00004.arrow
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8170f8d7867840ff774d8ff94ac2957b5347a85e01f35404627f86402c434801
|
| 3 |
+
size 3066304
|
_token_cache/MikeGreen2710__mlm_listing_checkpoint-32442/eval_00001_of_00004.arrow
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:45224462a27b10378e25bdadd83eae043404c1ba866cf2864cb337ef56d554ca
|
| 3 |
+
size 3060016
|
_token_cache/MikeGreen2710__mlm_listing_checkpoint-32442/eval_00002_of_00004.arrow
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3d1ac4b1cacdff6556e880e6ddfcd14215855c25e7fed753e968eb082f184bec
|
| 3 |
+
size 3083960
|
_token_cache/MikeGreen2710__mlm_listing_checkpoint-32442/eval_00003_of_00004.arrow
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fe9f6d27f59c19ddd343b4f9fab71c80035a657136623c74c97504ef14cc19a8
|
| 3 |
+
size 3065840
|
_token_cache/MikeGreen2710__mlm_listing_checkpoint-32442/train_00000_of_00004.arrow
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:720ba049e07e3134c7bd2932a3f28b6a64bde4a2d9697360d845750580d70f3f
|
| 3 |
+
size 2214489696
|
_token_cache/MikeGreen2710__mlm_listing_checkpoint-32442/train_00001_of_00004.arrow
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:247c6c4a97b7210fab17a54d01a7c02d64ab1aaf089ea604dc32e494af408c0c
|
| 3 |
+
size 2214392736
|
_token_cache/MikeGreen2710__mlm_listing_checkpoint-32442/train_00002_of_00004.arrow
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:64b6bca22e05d7e000bb24d43ee64e37cb0dbe57a2d74d396e1bcc7e038af557
|
| 3 |
+
size 2214139712
|
_token_cache/MikeGreen2710__mlm_listing_checkpoint-32442/train_00003_of_00004.arrow
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b5672caedbfd758c43a24b0c4befdfee8caee64f3e68e28d6aff7b0aae079c35
|
| 3 |
+
size 2214349480
|