Upload folder using huggingface_hub
Browse files- README.md +35 -0
- checkpoint-1372/config.json +61 -0
- checkpoint-1372/generation_config.json +16 -0
- checkpoint-1372/model.safetensors +3 -0
- checkpoint-1372/optimizer.pt +3 -0
- checkpoint-1372/rng_state.pth +3 -0
- checkpoint-1372/scheduler.pt +3 -0
- checkpoint-1372/source.spm +0 -0
- checkpoint-1372/special_tokens_map.json +23 -0
- checkpoint-1372/target.spm +0 -0
- checkpoint-1372/tokenizer_config.json +38 -0
- checkpoint-1372/trainer_state.json +1176 -0
- checkpoint-1372/training_args.bin +3 -0
- checkpoint-1372/vocab.json +0 -0
- config.json +61 -0
- generation_config.json +16 -0
- model.safetensors +3 -0
- runs/May13_07-56-46_r-lrj1981-ml-test-zx4ztum5-855f6-xnwlo/events.out.tfevents.1715587009.r-lrj1981-ml-test-zx4ztum5-855f6-xnwlo.67.0 +2 -2
- runs/May13_07-56-46_r-lrj1981-ml-test-zx4ztum5-855f6-xnwlo/events.out.tfevents.1715587442.r-lrj1981-ml-test-zx4ztum5-855f6-xnwlo.67.1 +3 -0
- source.spm +0 -0
- special_tokens_map.json +23 -0
- target.spm +0 -0
- tokenizer_config.json +38 -0
- training_args.bin +3 -0
- training_params.json +35 -0
- vocab.json +0 -0
README.md
ADDED
|
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
|
| 2 |
+
---
|
| 3 |
+
tags:
|
| 4 |
+
- autotrain
|
| 5 |
+
- text2text-generation
|
| 6 |
+
widget:
|
| 7 |
+
- text: "I love AutoTrain"
|
| 8 |
+
datasets:
|
| 9 |
+
- autotrain-9t83i-0umcp/autotrain-data
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
# Model Trained Using AutoTrain
|
| 13 |
+
|
| 14 |
+
- Problem type: Seq2Seq
|
| 15 |
+
|
| 16 |
+
## Validation Metrics
|
| 17 |
+
loss: 0.003461688058450818
|
| 18 |
+
|
| 19 |
+
rouge1: 99.738
|
| 20 |
+
|
| 21 |
+
rouge2: 99.6362
|
| 22 |
+
|
| 23 |
+
rougeL: 99.7372
|
| 24 |
+
|
| 25 |
+
rougeLsum: 99.739
|
| 26 |
+
|
| 27 |
+
gen_len: 127.7143
|
| 28 |
+
|
| 29 |
+
runtime: 37.8429
|
| 30 |
+
|
| 31 |
+
samples_per_second: 2.59
|
| 32 |
+
|
| 33 |
+
steps_per_second: 0.661
|
| 34 |
+
|
| 35 |
+
: 7.0
|
checkpoint-1372/config.json
ADDED
|
@@ -0,0 +1,61 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "LRJ1981/autotrain-redigeretData-version21",
|
| 3 |
+
"_num_labels": 3,
|
| 4 |
+
"activation_dropout": 0.0,
|
| 5 |
+
"activation_function": "swish",
|
| 6 |
+
"add_bias_logits": false,
|
| 7 |
+
"add_final_layer_norm": false,
|
| 8 |
+
"architectures": [
|
| 9 |
+
"MarianMTModel"
|
| 10 |
+
],
|
| 11 |
+
"attention_dropout": 0.0,
|
| 12 |
+
"bad_words_ids": [
|
| 13 |
+
[
|
| 14 |
+
58929
|
| 15 |
+
]
|
| 16 |
+
],
|
| 17 |
+
"bos_token_id": 0,
|
| 18 |
+
"classif_dropout": 0.0,
|
| 19 |
+
"classifier_dropout": 0.0,
|
| 20 |
+
"d_model": 512,
|
| 21 |
+
"decoder_attention_heads": 8,
|
| 22 |
+
"decoder_ffn_dim": 2048,
|
| 23 |
+
"decoder_layerdrop": 0.0,
|
| 24 |
+
"decoder_layers": 6,
|
| 25 |
+
"decoder_start_token_id": 58929,
|
| 26 |
+
"decoder_vocab_size": 58930,
|
| 27 |
+
"dropout": 0.1,
|
| 28 |
+
"encoder_attention_heads": 8,
|
| 29 |
+
"encoder_ffn_dim": 2048,
|
| 30 |
+
"encoder_layerdrop": 0.0,
|
| 31 |
+
"encoder_layers": 6,
|
| 32 |
+
"eos_token_id": 0,
|
| 33 |
+
"forced_eos_token_id": 0,
|
| 34 |
+
"id2label": {
|
| 35 |
+
"0": "LABEL_0",
|
| 36 |
+
"1": "LABEL_1",
|
| 37 |
+
"2": "LABEL_2"
|
| 38 |
+
},
|
| 39 |
+
"init_std": 0.02,
|
| 40 |
+
"is_encoder_decoder": true,
|
| 41 |
+
"label2id": {
|
| 42 |
+
"LABEL_0": 0,
|
| 43 |
+
"LABEL_1": 1,
|
| 44 |
+
"LABEL_2": 2
|
| 45 |
+
},
|
| 46 |
+
"max_length": 512,
|
| 47 |
+
"max_position_embeddings": 512,
|
| 48 |
+
"model_type": "marian",
|
| 49 |
+
"normalize_before": false,
|
| 50 |
+
"normalize_embedding": false,
|
| 51 |
+
"num_beams": 4,
|
| 52 |
+
"num_hidden_layers": 6,
|
| 53 |
+
"pad_token_id": 58929,
|
| 54 |
+
"scale_embedding": true,
|
| 55 |
+
"share_encoder_decoder_embeddings": true,
|
| 56 |
+
"static_position_embeddings": true,
|
| 57 |
+
"torch_dtype": "float32",
|
| 58 |
+
"transformers_version": "4.40.1",
|
| 59 |
+
"use_cache": false,
|
| 60 |
+
"vocab_size": 58930
|
| 61 |
+
}
|
checkpoint-1372/generation_config.json
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bad_words_ids": [
|
| 3 |
+
[
|
| 4 |
+
58929
|
| 5 |
+
]
|
| 6 |
+
],
|
| 7 |
+
"bos_token_id": 0,
|
| 8 |
+
"decoder_start_token_id": 58929,
|
| 9 |
+
"eos_token_id": 0,
|
| 10 |
+
"forced_eos_token_id": 0,
|
| 11 |
+
"max_length": 512,
|
| 12 |
+
"num_beams": 4,
|
| 13 |
+
"pad_token_id": 58929,
|
| 14 |
+
"renormalize_logits": true,
|
| 15 |
+
"transformers_version": "4.40.1"
|
| 16 |
+
}
|
checkpoint-1372/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cb6edaa6b942cd09ecbc8c1838ab6e7cc057269c1e71894f3f44fb3f78c9eec8
|
| 3 |
+
size 297507400
|
checkpoint-1372/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fb10c9a9b5167b78dac95cbfe336dae54d92f2d3da8e3b8f9857c14c9adddc37
|
| 3 |
+
size 594696826
|
checkpoint-1372/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b97cfda974ed4551da68d43de7543df2d4813418b1f877483613fe7c37f8af68
|
| 3 |
+
size 14244
|
checkpoint-1372/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:75a1cdce5c64aeeb00260bf92a8c01e23028565e5d997826a131a0a8a631b2f5
|
| 3 |
+
size 1064
|
checkpoint-1372/source.spm
ADDED
|
Binary file (820 kB). View file
|
|
|
checkpoint-1372/special_tokens_map.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"eos_token": {
|
| 3 |
+
"content": "</s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"pad_token": {
|
| 10 |
+
"content": "<pad>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"unk_token": {
|
| 17 |
+
"content": "<unk>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
}
|
| 23 |
+
}
|
checkpoint-1372/target.spm
ADDED
|
Binary file (788 kB). View file
|
|
|
checkpoint-1372/tokenizer_config.json
ADDED
|
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": "<unk>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"58929": {
|
| 20 |
+
"content": "<pad>",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
}
|
| 27 |
+
},
|
| 28 |
+
"clean_up_tokenization_spaces": true,
|
| 29 |
+
"eos_token": "</s>",
|
| 30 |
+
"model_max_length": 512,
|
| 31 |
+
"pad_token": "<pad>",
|
| 32 |
+
"separate_vocabs": false,
|
| 33 |
+
"source_lang": "da",
|
| 34 |
+
"sp_model_kwargs": {},
|
| 35 |
+
"target_lang": "en",
|
| 36 |
+
"tokenizer_class": "MarianTokenizer",
|
| 37 |
+
"unk_token": "<unk>"
|
| 38 |
+
}
|
checkpoint-1372/trainer_state.json
ADDED
|
@@ -0,0 +1,1176 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.003461688058450818,
|
| 3 |
+
"best_model_checkpoint": "autotrain-9t83i-0umcp/checkpoint-1372",
|
| 4 |
+
"epoch": 7.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 1372,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.04591836734693878,
|
| 13 |
+
"grad_norm": 2.446383237838745,
|
| 14 |
+
"learning_rate": 1.1479591836734695e-06,
|
| 15 |
+
"loss": 0.1983,
|
| 16 |
+
"step": 9
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.09183673469387756,
|
| 20 |
+
"grad_norm": 3.9726994037628174,
|
| 21 |
+
"learning_rate": 2.295918367346939e-06,
|
| 22 |
+
"loss": 0.2526,
|
| 23 |
+
"step": 18
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.1377551020408163,
|
| 27 |
+
"grad_norm": 4.180245399475098,
|
| 28 |
+
"learning_rate": 3.443877551020408e-06,
|
| 29 |
+
"loss": 0.1536,
|
| 30 |
+
"step": 27
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.1836734693877551,
|
| 34 |
+
"grad_norm": 3.1698622703552246,
|
| 35 |
+
"learning_rate": 4.591836734693878e-06,
|
| 36 |
+
"loss": 0.3117,
|
| 37 |
+
"step": 36
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.22959183673469388,
|
| 41 |
+
"grad_norm": 4.330101490020752,
|
| 42 |
+
"learning_rate": 5.7397959183673475e-06,
|
| 43 |
+
"loss": 0.2641,
|
| 44 |
+
"step": 45
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.2755102040816326,
|
| 48 |
+
"grad_norm": 2.323159694671631,
|
| 49 |
+
"learning_rate": 6.887755102040816e-06,
|
| 50 |
+
"loss": 0.4657,
|
| 51 |
+
"step": 54
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.32142857142857145,
|
| 55 |
+
"grad_norm": 5.427762508392334,
|
| 56 |
+
"learning_rate": 8.035714285714286e-06,
|
| 57 |
+
"loss": 0.3486,
|
| 58 |
+
"step": 63
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.3673469387755102,
|
| 62 |
+
"grad_norm": 4.673620223999023,
|
| 63 |
+
"learning_rate": 9.183673469387756e-06,
|
| 64 |
+
"loss": 0.3346,
|
| 65 |
+
"step": 72
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.413265306122449,
|
| 69 |
+
"grad_norm": 4.061607837677002,
|
| 70 |
+
"learning_rate": 1.0331632653061225e-05,
|
| 71 |
+
"loss": 0.1703,
|
| 72 |
+
"step": 81
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.45918367346938777,
|
| 76 |
+
"grad_norm": 2.6127052307128906,
|
| 77 |
+
"learning_rate": 1.1479591836734695e-05,
|
| 78 |
+
"loss": 0.4217,
|
| 79 |
+
"step": 90
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.5051020408163265,
|
| 83 |
+
"grad_norm": 4.84128475189209,
|
| 84 |
+
"learning_rate": 1.2627551020408163e-05,
|
| 85 |
+
"loss": 0.1865,
|
| 86 |
+
"step": 99
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.5510204081632653,
|
| 90 |
+
"grad_norm": 3.507438898086548,
|
| 91 |
+
"learning_rate": 1.3775510204081633e-05,
|
| 92 |
+
"loss": 0.3114,
|
| 93 |
+
"step": 108
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.5969387755102041,
|
| 97 |
+
"grad_norm": 1.1375735998153687,
|
| 98 |
+
"learning_rate": 1.4923469387755104e-05,
|
| 99 |
+
"loss": 0.3519,
|
| 100 |
+
"step": 117
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.6428571428571429,
|
| 104 |
+
"grad_norm": 3.5756773948669434,
|
| 105 |
+
"learning_rate": 1.6071428571428572e-05,
|
| 106 |
+
"loss": 0.2934,
|
| 107 |
+
"step": 126
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.6887755102040817,
|
| 111 |
+
"grad_norm": 3.714728593826294,
|
| 112 |
+
"learning_rate": 1.7219387755102043e-05,
|
| 113 |
+
"loss": 0.3112,
|
| 114 |
+
"step": 135
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.7346938775510204,
|
| 118 |
+
"grad_norm": 4.473227500915527,
|
| 119 |
+
"learning_rate": 1.836734693877551e-05,
|
| 120 |
+
"loss": 0.1897,
|
| 121 |
+
"step": 144
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.7806122448979592,
|
| 125 |
+
"grad_norm": 2.203939914703369,
|
| 126 |
+
"learning_rate": 1.9515306122448983e-05,
|
| 127 |
+
"loss": 0.2168,
|
| 128 |
+
"step": 153
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.826530612244898,
|
| 132 |
+
"grad_norm": 1.36044180393219,
|
| 133 |
+
"learning_rate": 2.066326530612245e-05,
|
| 134 |
+
"loss": 0.117,
|
| 135 |
+
"step": 162
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.8724489795918368,
|
| 139 |
+
"grad_norm": 1.2238707542419434,
|
| 140 |
+
"learning_rate": 2.181122448979592e-05,
|
| 141 |
+
"loss": 0.2936,
|
| 142 |
+
"step": 171
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.9183673469387755,
|
| 146 |
+
"grad_norm": 2.6794865131378174,
|
| 147 |
+
"learning_rate": 2.295918367346939e-05,
|
| 148 |
+
"loss": 0.1305,
|
| 149 |
+
"step": 180
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.9642857142857143,
|
| 153 |
+
"grad_norm": 3.089512825012207,
|
| 154 |
+
"learning_rate": 2.4107142857142858e-05,
|
| 155 |
+
"loss": 0.397,
|
| 156 |
+
"step": 189
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 1.0,
|
| 160 |
+
"eval_gen_len": 128.0,
|
| 161 |
+
"eval_loss": 0.18853867053985596,
|
| 162 |
+
"eval_rouge1": 89.2949,
|
| 163 |
+
"eval_rouge2": 83.057,
|
| 164 |
+
"eval_rougeL": 88.1848,
|
| 165 |
+
"eval_rougeLsum": 88.7391,
|
| 166 |
+
"eval_runtime": 38.0997,
|
| 167 |
+
"eval_samples_per_second": 2.572,
|
| 168 |
+
"eval_steps_per_second": 0.656,
|
| 169 |
+
"step": 196
|
| 170 |
+
},
|
| 171 |
+
{
|
| 172 |
+
"epoch": 1.010204081632653,
|
| 173 |
+
"grad_norm": 2.5835583209991455,
|
| 174 |
+
"learning_rate": 2.5255102040816326e-05,
|
| 175 |
+
"loss": 0.3554,
|
| 176 |
+
"step": 198
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 1.0561224489795917,
|
| 180 |
+
"grad_norm": 1.9029709100723267,
|
| 181 |
+
"learning_rate": 2.6403061224489794e-05,
|
| 182 |
+
"loss": 0.1324,
|
| 183 |
+
"step": 207
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 1.1020408163265305,
|
| 187 |
+
"grad_norm": 2.5668606758117676,
|
| 188 |
+
"learning_rate": 2.7551020408163265e-05,
|
| 189 |
+
"loss": 0.1243,
|
| 190 |
+
"step": 216
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"epoch": 1.1479591836734695,
|
| 194 |
+
"grad_norm": 2.5577433109283447,
|
| 195 |
+
"learning_rate": 2.869897959183674e-05,
|
| 196 |
+
"loss": 0.0995,
|
| 197 |
+
"step": 225
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 1.193877551020408,
|
| 201 |
+
"grad_norm": 4.285234451293945,
|
| 202 |
+
"learning_rate": 2.9846938775510208e-05,
|
| 203 |
+
"loss": 0.2354,
|
| 204 |
+
"step": 234
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 1.239795918367347,
|
| 208 |
+
"grad_norm": 3.811396598815918,
|
| 209 |
+
"learning_rate": 3.0994897959183676e-05,
|
| 210 |
+
"loss": 0.181,
|
| 211 |
+
"step": 243
|
| 212 |
+
},
|
| 213 |
+
{
|
| 214 |
+
"epoch": 1.2857142857142856,
|
| 215 |
+
"grad_norm": 0.5611918568611145,
|
| 216 |
+
"learning_rate": 3.2142857142857144e-05,
|
| 217 |
+
"loss": 0.0721,
|
| 218 |
+
"step": 252
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 1.3316326530612246,
|
| 222 |
+
"grad_norm": 4.734651565551758,
|
| 223 |
+
"learning_rate": 3.329081632653062e-05,
|
| 224 |
+
"loss": 0.1276,
|
| 225 |
+
"step": 261
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 1.3775510204081631,
|
| 229 |
+
"grad_norm": 2.2007200717926025,
|
| 230 |
+
"learning_rate": 3.443877551020409e-05,
|
| 231 |
+
"loss": 0.0872,
|
| 232 |
+
"step": 270
|
| 233 |
+
},
|
| 234 |
+
{
|
| 235 |
+
"epoch": 1.4234693877551021,
|
| 236 |
+
"grad_norm": 1.3555959463119507,
|
| 237 |
+
"learning_rate": 3.5586734693877555e-05,
|
| 238 |
+
"loss": 0.2188,
|
| 239 |
+
"step": 279
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 1.469387755102041,
|
| 243 |
+
"grad_norm": 2.6970372200012207,
|
| 244 |
+
"learning_rate": 3.673469387755102e-05,
|
| 245 |
+
"loss": 0.2266,
|
| 246 |
+
"step": 288
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 1.5153061224489797,
|
| 250 |
+
"grad_norm": 10.701809883117676,
|
| 251 |
+
"learning_rate": 3.788265306122449e-05,
|
| 252 |
+
"loss": 0.157,
|
| 253 |
+
"step": 297
|
| 254 |
+
},
|
| 255 |
+
{
|
| 256 |
+
"epoch": 1.5612244897959182,
|
| 257 |
+
"grad_norm": 1.6892890930175781,
|
| 258 |
+
"learning_rate": 3.9030612244897965e-05,
|
| 259 |
+
"loss": 0.0885,
|
| 260 |
+
"step": 306
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 1.6071428571428572,
|
| 264 |
+
"grad_norm": 1.5699105262756348,
|
| 265 |
+
"learning_rate": 4.017857142857143e-05,
|
| 266 |
+
"loss": 0.1323,
|
| 267 |
+
"step": 315
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 1.6530612244897958,
|
| 271 |
+
"grad_norm": 4.3087639808654785,
|
| 272 |
+
"learning_rate": 4.13265306122449e-05,
|
| 273 |
+
"loss": 0.1482,
|
| 274 |
+
"step": 324
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 1.6989795918367347,
|
| 278 |
+
"grad_norm": 0.6790181994438171,
|
| 279 |
+
"learning_rate": 4.247448979591837e-05,
|
| 280 |
+
"loss": 0.1814,
|
| 281 |
+
"step": 333
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 1.7448979591836735,
|
| 285 |
+
"grad_norm": 2.1411118507385254,
|
| 286 |
+
"learning_rate": 4.362244897959184e-05,
|
| 287 |
+
"loss": 0.0834,
|
| 288 |
+
"step": 342
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 1.7908163265306123,
|
| 292 |
+
"grad_norm": 1.8243377208709717,
|
| 293 |
+
"learning_rate": 4.477040816326531e-05,
|
| 294 |
+
"loss": 0.1124,
|
| 295 |
+
"step": 351
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 1.836734693877551,
|
| 299 |
+
"grad_norm": 1.9441792964935303,
|
| 300 |
+
"learning_rate": 4.591836734693878e-05,
|
| 301 |
+
"loss": 0.095,
|
| 302 |
+
"step": 360
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 1.8826530612244898,
|
| 306 |
+
"grad_norm": 3.742511034011841,
|
| 307 |
+
"learning_rate": 4.706632653061225e-05,
|
| 308 |
+
"loss": 0.0955,
|
| 309 |
+
"step": 369
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 1.9285714285714286,
|
| 313 |
+
"grad_norm": 1.4945087432861328,
|
| 314 |
+
"learning_rate": 4.8214285714285716e-05,
|
| 315 |
+
"loss": 0.0543,
|
| 316 |
+
"step": 378
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 1.9744897959183674,
|
| 320 |
+
"grad_norm": 1.0501391887664795,
|
| 321 |
+
"learning_rate": 4.9362244897959184e-05,
|
| 322 |
+
"loss": 0.0861,
|
| 323 |
+
"step": 387
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"epoch": 2.0,
|
| 327 |
+
"eval_gen_len": 128.0,
|
| 328 |
+
"eval_loss": 0.05252710357308388,
|
| 329 |
+
"eval_rouge1": 96.0027,
|
| 330 |
+
"eval_rouge2": 93.3236,
|
| 331 |
+
"eval_rougeL": 95.501,
|
| 332 |
+
"eval_rougeLsum": 95.7994,
|
| 333 |
+
"eval_runtime": 37.9097,
|
| 334 |
+
"eval_samples_per_second": 2.585,
|
| 335 |
+
"eval_steps_per_second": 0.659,
|
| 336 |
+
"step": 392
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"epoch": 2.020408163265306,
|
| 340 |
+
"grad_norm": 2.9681637287139893,
|
| 341 |
+
"learning_rate": 4.9943310657596374e-05,
|
| 342 |
+
"loss": 0.0559,
|
| 343 |
+
"step": 396
|
| 344 |
+
},
|
| 345 |
+
{
|
| 346 |
+
"epoch": 2.066326530612245,
|
| 347 |
+
"grad_norm": 0.807901918888092,
|
| 348 |
+
"learning_rate": 4.981575963718821e-05,
|
| 349 |
+
"loss": 0.0334,
|
| 350 |
+
"step": 405
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 2.1122448979591835,
|
| 354 |
+
"grad_norm": 5.0659918785095215,
|
| 355 |
+
"learning_rate": 4.968820861678005e-05,
|
| 356 |
+
"loss": 0.1104,
|
| 357 |
+
"step": 414
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 2.1581632653061225,
|
| 361 |
+
"grad_norm": 2.9605283737182617,
|
| 362 |
+
"learning_rate": 4.956065759637189e-05,
|
| 363 |
+
"loss": 0.0817,
|
| 364 |
+
"step": 423
|
| 365 |
+
},
|
| 366 |
+
{
|
| 367 |
+
"epoch": 2.204081632653061,
|
| 368 |
+
"grad_norm": 2.554128408432007,
|
| 369 |
+
"learning_rate": 4.9433106575963725e-05,
|
| 370 |
+
"loss": 0.0524,
|
| 371 |
+
"step": 432
|
| 372 |
+
},
|
| 373 |
+
{
|
| 374 |
+
"epoch": 2.25,
|
| 375 |
+
"grad_norm": 1.5891895294189453,
|
| 376 |
+
"learning_rate": 4.930555555555556e-05,
|
| 377 |
+
"loss": 0.0988,
|
| 378 |
+
"step": 441
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 2.295918367346939,
|
| 382 |
+
"grad_norm": 3.2821803092956543,
|
| 383 |
+
"learning_rate": 4.917800453514739e-05,
|
| 384 |
+
"loss": 0.08,
|
| 385 |
+
"step": 450
|
| 386 |
+
},
|
| 387 |
+
{
|
| 388 |
+
"epoch": 2.3418367346938775,
|
| 389 |
+
"grad_norm": 1.6306498050689697,
|
| 390 |
+
"learning_rate": 4.905045351473923e-05,
|
| 391 |
+
"loss": 0.0339,
|
| 392 |
+
"step": 459
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 2.387755102040816,
|
| 396 |
+
"grad_norm": 3.2567660808563232,
|
| 397 |
+
"learning_rate": 4.892290249433107e-05,
|
| 398 |
+
"loss": 0.0755,
|
| 399 |
+
"step": 468
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 2.433673469387755,
|
| 403 |
+
"grad_norm": 2.143312931060791,
|
| 404 |
+
"learning_rate": 4.8795351473922906e-05,
|
| 405 |
+
"loss": 0.0682,
|
| 406 |
+
"step": 477
|
| 407 |
+
},
|
| 408 |
+
{
|
| 409 |
+
"epoch": 2.479591836734694,
|
| 410 |
+
"grad_norm": 1.9906742572784424,
|
| 411 |
+
"learning_rate": 4.866780045351474e-05,
|
| 412 |
+
"loss": 0.0747,
|
| 413 |
+
"step": 486
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"epoch": 2.5255102040816326,
|
| 417 |
+
"grad_norm": 6.981854438781738,
|
| 418 |
+
"learning_rate": 4.8540249433106574e-05,
|
| 419 |
+
"loss": 0.0533,
|
| 420 |
+
"step": 495
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 2.571428571428571,
|
| 424 |
+
"grad_norm": 1.767125129699707,
|
| 425 |
+
"learning_rate": 4.841269841269841e-05,
|
| 426 |
+
"loss": 0.0537,
|
| 427 |
+
"step": 504
|
| 428 |
+
},
|
| 429 |
+
{
|
| 430 |
+
"epoch": 2.61734693877551,
|
| 431 |
+
"grad_norm": 1.545177698135376,
|
| 432 |
+
"learning_rate": 4.828514739229025e-05,
|
| 433 |
+
"loss": 0.0535,
|
| 434 |
+
"step": 513
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 2.663265306122449,
|
| 438 |
+
"grad_norm": 1.537906527519226,
|
| 439 |
+
"learning_rate": 4.8157596371882094e-05,
|
| 440 |
+
"loss": 0.0721,
|
| 441 |
+
"step": 522
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 2.7091836734693877,
|
| 445 |
+
"grad_norm": 1.4103052616119385,
|
| 446 |
+
"learning_rate": 4.8030045351473925e-05,
|
| 447 |
+
"loss": 0.0515,
|
| 448 |
+
"step": 531
|
| 449 |
+
},
|
| 450 |
+
{
|
| 451 |
+
"epoch": 2.7551020408163263,
|
| 452 |
+
"grad_norm": 1.9743316173553467,
|
| 453 |
+
"learning_rate": 4.790249433106576e-05,
|
| 454 |
+
"loss": 0.0606,
|
| 455 |
+
"step": 540
|
| 456 |
+
},
|
| 457 |
+
{
|
| 458 |
+
"epoch": 2.8010204081632653,
|
| 459 |
+
"grad_norm": 1.1865582466125488,
|
| 460 |
+
"learning_rate": 4.77749433106576e-05,
|
| 461 |
+
"loss": 0.0336,
|
| 462 |
+
"step": 549
|
| 463 |
+
},
|
| 464 |
+
{
|
| 465 |
+
"epoch": 2.8469387755102042,
|
| 466 |
+
"grad_norm": 1.7514479160308838,
|
| 467 |
+
"learning_rate": 4.764739229024944e-05,
|
| 468 |
+
"loss": 0.0357,
|
| 469 |
+
"step": 558
|
| 470 |
+
},
|
| 471 |
+
{
|
| 472 |
+
"epoch": 2.892857142857143,
|
| 473 |
+
"grad_norm": 3.3062944412231445,
|
| 474 |
+
"learning_rate": 4.751984126984127e-05,
|
| 475 |
+
"loss": 0.0613,
|
| 476 |
+
"step": 567
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 2.938775510204082,
|
| 480 |
+
"grad_norm": 0.8094915151596069,
|
| 481 |
+
"learning_rate": 4.7392290249433106e-05,
|
| 482 |
+
"loss": 0.0449,
|
| 483 |
+
"step": 576
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 2.9846938775510203,
|
| 487 |
+
"grad_norm": 2.2876973152160645,
|
| 488 |
+
"learning_rate": 4.7264739229024944e-05,
|
| 489 |
+
"loss": 0.06,
|
| 490 |
+
"step": 585
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"epoch": 3.0,
|
| 494 |
+
"eval_gen_len": 127.6939,
|
| 495 |
+
"eval_loss": 0.025030160322785378,
|
| 496 |
+
"eval_rouge1": 98.6655,
|
| 497 |
+
"eval_rouge2": 97.5818,
|
| 498 |
+
"eval_rougeL": 98.5529,
|
| 499 |
+
"eval_rougeLsum": 98.5395,
|
| 500 |
+
"eval_runtime": 37.9756,
|
| 501 |
+
"eval_samples_per_second": 2.581,
|
| 502 |
+
"eval_steps_per_second": 0.658,
|
| 503 |
+
"step": 588
|
| 504 |
+
},
|
| 505 |
+
{
|
| 506 |
+
"epoch": 3.0306122448979593,
|
| 507 |
+
"grad_norm": 1.7782725095748901,
|
| 508 |
+
"learning_rate": 4.713718820861678e-05,
|
| 509 |
+
"loss": 0.0219,
|
| 510 |
+
"step": 594
|
| 511 |
+
},
|
| 512 |
+
{
|
| 513 |
+
"epoch": 3.076530612244898,
|
| 514 |
+
"grad_norm": 0.317821741104126,
|
| 515 |
+
"learning_rate": 4.700963718820862e-05,
|
| 516 |
+
"loss": 0.037,
|
| 517 |
+
"step": 603
|
| 518 |
+
},
|
| 519 |
+
{
|
| 520 |
+
"epoch": 3.122448979591837,
|
| 521 |
+
"grad_norm": 0.8859459757804871,
|
| 522 |
+
"learning_rate": 4.688208616780046e-05,
|
| 523 |
+
"loss": 0.0531,
|
| 524 |
+
"step": 612
|
| 525 |
+
},
|
| 526 |
+
{
|
| 527 |
+
"epoch": 3.1683673469387754,
|
| 528 |
+
"grad_norm": 0.3588017225265503,
|
| 529 |
+
"learning_rate": 4.67687074829932e-05,
|
| 530 |
+
"loss": 0.0307,
|
| 531 |
+
"step": 621
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 3.2142857142857144,
|
| 535 |
+
"grad_norm": 2.5311052799224854,
|
| 536 |
+
"learning_rate": 4.664115646258503e-05,
|
| 537 |
+
"loss": 0.0218,
|
| 538 |
+
"step": 630
|
| 539 |
+
},
|
| 540 |
+
{
|
| 541 |
+
"epoch": 3.260204081632653,
|
| 542 |
+
"grad_norm": 0.19862987101078033,
|
| 543 |
+
"learning_rate": 4.651360544217687e-05,
|
| 544 |
+
"loss": 0.0367,
|
| 545 |
+
"step": 639
|
| 546 |
+
},
|
| 547 |
+
{
|
| 548 |
+
"epoch": 3.306122448979592,
|
| 549 |
+
"grad_norm": 0.6744495034217834,
|
| 550 |
+
"learning_rate": 4.638605442176871e-05,
|
| 551 |
+
"loss": 0.0369,
|
| 552 |
+
"step": 648
|
| 553 |
+
},
|
| 554 |
+
{
|
| 555 |
+
"epoch": 3.3520408163265305,
|
| 556 |
+
"grad_norm": 2.8351736068725586,
|
| 557 |
+
"learning_rate": 4.625850340136055e-05,
|
| 558 |
+
"loss": 0.0465,
|
| 559 |
+
"step": 657
|
| 560 |
+
},
|
| 561 |
+
{
|
| 562 |
+
"epoch": 3.3979591836734695,
|
| 563 |
+
"grad_norm": 3.43568754196167,
|
| 564 |
+
"learning_rate": 4.613095238095239e-05,
|
| 565 |
+
"loss": 0.0335,
|
| 566 |
+
"step": 666
|
| 567 |
+
},
|
| 568 |
+
{
|
| 569 |
+
"epoch": 3.443877551020408,
|
| 570 |
+
"grad_norm": 2.1830670833587646,
|
| 571 |
+
"learning_rate": 4.600340136054422e-05,
|
| 572 |
+
"loss": 0.0284,
|
| 573 |
+
"step": 675
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 3.489795918367347,
|
| 577 |
+
"grad_norm": 0.9732754826545715,
|
| 578 |
+
"learning_rate": 4.587585034013606e-05,
|
| 579 |
+
"loss": 0.0269,
|
| 580 |
+
"step": 684
|
| 581 |
+
},
|
| 582 |
+
{
|
| 583 |
+
"epoch": 3.5357142857142856,
|
| 584 |
+
"grad_norm": 2.1796019077301025,
|
| 585 |
+
"learning_rate": 4.5748299319727895e-05,
|
| 586 |
+
"loss": 0.0362,
|
| 587 |
+
"step": 693
|
| 588 |
+
},
|
| 589 |
+
{
|
| 590 |
+
"epoch": 3.5816326530612246,
|
| 591 |
+
"grad_norm": 1.1703124046325684,
|
| 592 |
+
"learning_rate": 4.562074829931973e-05,
|
| 593 |
+
"loss": 0.0229,
|
| 594 |
+
"step": 702
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 3.627551020408163,
|
| 598 |
+
"grad_norm": 2.6701223850250244,
|
| 599 |
+
"learning_rate": 4.549319727891156e-05,
|
| 600 |
+
"loss": 0.0471,
|
| 601 |
+
"step": 711
|
| 602 |
+
},
|
| 603 |
+
{
|
| 604 |
+
"epoch": 3.673469387755102,
|
| 605 |
+
"grad_norm": 1.3318531513214111,
|
| 606 |
+
"learning_rate": 4.53656462585034e-05,
|
| 607 |
+
"loss": 0.0327,
|
| 608 |
+
"step": 720
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 3.7193877551020407,
|
| 612 |
+
"grad_norm": 1.4701616764068604,
|
| 613 |
+
"learning_rate": 4.523809523809524e-05,
|
| 614 |
+
"loss": 0.0184,
|
| 615 |
+
"step": 729
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"epoch": 3.7653061224489797,
|
| 619 |
+
"grad_norm": 0.9515037536621094,
|
| 620 |
+
"learning_rate": 4.5110544217687076e-05,
|
| 621 |
+
"loss": 0.0308,
|
| 622 |
+
"step": 738
|
| 623 |
+
},
|
| 624 |
+
{
|
| 625 |
+
"epoch": 3.811224489795918,
|
| 626 |
+
"grad_norm": 3.164966583251953,
|
| 627 |
+
"learning_rate": 4.4982993197278914e-05,
|
| 628 |
+
"loss": 0.0262,
|
| 629 |
+
"step": 747
|
| 630 |
+
},
|
| 631 |
+
{
|
| 632 |
+
"epoch": 3.857142857142857,
|
| 633 |
+
"grad_norm": 0.8453909158706665,
|
| 634 |
+
"learning_rate": 4.485544217687075e-05,
|
| 635 |
+
"loss": 0.0327,
|
| 636 |
+
"step": 756
|
| 637 |
+
},
|
| 638 |
+
{
|
| 639 |
+
"epoch": 3.9030612244897958,
|
| 640 |
+
"grad_norm": 2.3475284576416016,
|
| 641 |
+
"learning_rate": 4.472789115646259e-05,
|
| 642 |
+
"loss": 0.0222,
|
| 643 |
+
"step": 765
|
| 644 |
+
},
|
| 645 |
+
{
|
| 646 |
+
"epoch": 3.9489795918367347,
|
| 647 |
+
"grad_norm": 0.677014946937561,
|
| 648 |
+
"learning_rate": 4.4600340136054427e-05,
|
| 649 |
+
"loss": 0.0244,
|
| 650 |
+
"step": 774
|
| 651 |
+
},
|
| 652 |
+
{
|
| 653 |
+
"epoch": 3.9948979591836737,
|
| 654 |
+
"grad_norm": 3.246267318725586,
|
| 655 |
+
"learning_rate": 4.4472789115646264e-05,
|
| 656 |
+
"loss": 0.0297,
|
| 657 |
+
"step": 783
|
| 658 |
+
},
|
| 659 |
+
{
|
| 660 |
+
"epoch": 4.0,
|
| 661 |
+
"eval_gen_len": 127.7143,
|
| 662 |
+
"eval_loss": 0.010969710536301136,
|
| 663 |
+
"eval_rouge1": 99.1634,
|
| 664 |
+
"eval_rouge2": 98.7404,
|
| 665 |
+
"eval_rougeL": 99.1194,
|
| 666 |
+
"eval_rougeLsum": 99.1779,
|
| 667 |
+
"eval_runtime": 37.9041,
|
| 668 |
+
"eval_samples_per_second": 2.585,
|
| 669 |
+
"eval_steps_per_second": 0.66,
|
| 670 |
+
"step": 784
|
| 671 |
+
},
|
| 672 |
+
{
|
| 673 |
+
"epoch": 4.040816326530612,
|
| 674 |
+
"grad_norm": 0.39469975233078003,
|
| 675 |
+
"learning_rate": 4.4345238095238095e-05,
|
| 676 |
+
"loss": 0.0244,
|
| 677 |
+
"step": 792
|
| 678 |
+
},
|
| 679 |
+
{
|
| 680 |
+
"epoch": 4.086734693877551,
|
| 681 |
+
"grad_norm": 2.384838581085205,
|
| 682 |
+
"learning_rate": 4.421768707482993e-05,
|
| 683 |
+
"loss": 0.0213,
|
| 684 |
+
"step": 801
|
| 685 |
+
},
|
| 686 |
+
{
|
| 687 |
+
"epoch": 4.13265306122449,
|
| 688 |
+
"grad_norm": 3.5253398418426514,
|
| 689 |
+
"learning_rate": 4.409013605442177e-05,
|
| 690 |
+
"loss": 0.0089,
|
| 691 |
+
"step": 810
|
| 692 |
+
},
|
| 693 |
+
{
|
| 694 |
+
"epoch": 4.178571428571429,
|
| 695 |
+
"grad_norm": 2.1386358737945557,
|
| 696 |
+
"learning_rate": 4.396258503401361e-05,
|
| 697 |
+
"loss": 0.036,
|
| 698 |
+
"step": 819
|
| 699 |
+
},
|
| 700 |
+
{
|
| 701 |
+
"epoch": 4.224489795918367,
|
| 702 |
+
"grad_norm": 0.44415947794914246,
|
| 703 |
+
"learning_rate": 4.383503401360544e-05,
|
| 704 |
+
"loss": 0.0147,
|
| 705 |
+
"step": 828
|
| 706 |
+
},
|
| 707 |
+
{
|
| 708 |
+
"epoch": 4.270408163265306,
|
| 709 |
+
"grad_norm": 2.4095001220703125,
|
| 710 |
+
"learning_rate": 4.3707482993197277e-05,
|
| 711 |
+
"loss": 0.0321,
|
| 712 |
+
"step": 837
|
| 713 |
+
},
|
| 714 |
+
{
|
| 715 |
+
"epoch": 4.316326530612245,
|
| 716 |
+
"grad_norm": 2.395909070968628,
|
| 717 |
+
"learning_rate": 4.357993197278912e-05,
|
| 718 |
+
"loss": 0.0296,
|
| 719 |
+
"step": 846
|
| 720 |
+
},
|
| 721 |
+
{
|
| 722 |
+
"epoch": 4.362244897959184,
|
| 723 |
+
"grad_norm": 4.824786186218262,
|
| 724 |
+
"learning_rate": 4.345238095238096e-05,
|
| 725 |
+
"loss": 0.0233,
|
| 726 |
+
"step": 855
|
| 727 |
+
},
|
| 728 |
+
{
|
| 729 |
+
"epoch": 4.408163265306122,
|
| 730 |
+
"grad_norm": 2.400609254837036,
|
| 731 |
+
"learning_rate": 4.3324829931972796e-05,
|
| 732 |
+
"loss": 0.0389,
|
| 733 |
+
"step": 864
|
| 734 |
+
},
|
| 735 |
+
{
|
| 736 |
+
"epoch": 4.454081632653061,
|
| 737 |
+
"grad_norm": 1.0374516248703003,
|
| 738 |
+
"learning_rate": 4.319727891156463e-05,
|
| 739 |
+
"loss": 0.0307,
|
| 740 |
+
"step": 873
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 4.5,
|
| 744 |
+
"grad_norm": 2.5744516849517822,
|
| 745 |
+
"learning_rate": 4.3069727891156465e-05,
|
| 746 |
+
"loss": 0.0234,
|
| 747 |
+
"step": 882
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 4.545918367346939,
|
| 751 |
+
"grad_norm": 0.4013276696205139,
|
| 752 |
+
"learning_rate": 4.29421768707483e-05,
|
| 753 |
+
"loss": 0.0171,
|
| 754 |
+
"step": 891
|
| 755 |
+
},
|
| 756 |
+
{
|
| 757 |
+
"epoch": 4.591836734693878,
|
| 758 |
+
"grad_norm": 1.4164782762527466,
|
| 759 |
+
"learning_rate": 4.281462585034014e-05,
|
| 760 |
+
"loss": 0.0217,
|
| 761 |
+
"step": 900
|
| 762 |
+
},
|
| 763 |
+
{
|
| 764 |
+
"epoch": 4.637755102040816,
|
| 765 |
+
"grad_norm": 0.2612836956977844,
|
| 766 |
+
"learning_rate": 4.268707482993197e-05,
|
| 767 |
+
"loss": 0.007,
|
| 768 |
+
"step": 909
|
| 769 |
+
},
|
| 770 |
+
{
|
| 771 |
+
"epoch": 4.683673469387755,
|
| 772 |
+
"grad_norm": 0.537272036075592,
|
| 773 |
+
"learning_rate": 4.255952380952381e-05,
|
| 774 |
+
"loss": 0.034,
|
| 775 |
+
"step": 918
|
| 776 |
+
},
|
| 777 |
+
{
|
| 778 |
+
"epoch": 4.729591836734694,
|
| 779 |
+
"grad_norm": 0.7186601758003235,
|
| 780 |
+
"learning_rate": 4.2431972789115646e-05,
|
| 781 |
+
"loss": 0.0173,
|
| 782 |
+
"step": 927
|
| 783 |
+
},
|
| 784 |
+
{
|
| 785 |
+
"epoch": 4.775510204081632,
|
| 786 |
+
"grad_norm": 0.5405403971672058,
|
| 787 |
+
"learning_rate": 4.2304421768707484e-05,
|
| 788 |
+
"loss": 0.0175,
|
| 789 |
+
"step": 936
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 4.821428571428571,
|
| 793 |
+
"grad_norm": 0.49115684628486633,
|
| 794 |
+
"learning_rate": 4.217687074829932e-05,
|
| 795 |
+
"loss": 0.0115,
|
| 796 |
+
"step": 945
|
| 797 |
+
},
|
| 798 |
+
{
|
| 799 |
+
"epoch": 4.86734693877551,
|
| 800 |
+
"grad_norm": 0.08387177437543869,
|
| 801 |
+
"learning_rate": 4.204931972789116e-05,
|
| 802 |
+
"loss": 0.0159,
|
| 803 |
+
"step": 954
|
| 804 |
+
},
|
| 805 |
+
{
|
| 806 |
+
"epoch": 4.913265306122449,
|
| 807 |
+
"grad_norm": 0.31179898977279663,
|
| 808 |
+
"learning_rate": 4.1921768707483e-05,
|
| 809 |
+
"loss": 0.0163,
|
| 810 |
+
"step": 963
|
| 811 |
+
},
|
| 812 |
+
{
|
| 813 |
+
"epoch": 4.959183673469388,
|
| 814 |
+
"grad_norm": 1.2666131258010864,
|
| 815 |
+
"learning_rate": 4.1794217687074834e-05,
|
| 816 |
+
"loss": 0.0221,
|
| 817 |
+
"step": 972
|
| 818 |
+
},
|
| 819 |
+
{
|
| 820 |
+
"epoch": 5.0,
|
| 821 |
+
"eval_gen_len": 127.7143,
|
| 822 |
+
"eval_loss": 0.00930405966937542,
|
| 823 |
+
"eval_rouge1": 99.2277,
|
| 824 |
+
"eval_rouge2": 98.8302,
|
| 825 |
+
"eval_rougeL": 99.2299,
|
| 826 |
+
"eval_rougeLsum": 99.2242,
|
| 827 |
+
"eval_runtime": 37.8008,
|
| 828 |
+
"eval_samples_per_second": 2.593,
|
| 829 |
+
"eval_steps_per_second": 0.661,
|
| 830 |
+
"step": 980
|
| 831 |
+
},
|
| 832 |
+
{
|
| 833 |
+
"epoch": 5.005102040816326,
|
| 834 |
+
"grad_norm": 1.5087450742721558,
|
| 835 |
+
"learning_rate": 4.166666666666667e-05,
|
| 836 |
+
"loss": 0.0229,
|
| 837 |
+
"step": 981
|
| 838 |
+
},
|
| 839 |
+
{
|
| 840 |
+
"epoch": 5.051020408163265,
|
| 841 |
+
"grad_norm": 0.1325344741344452,
|
| 842 |
+
"learning_rate": 4.15391156462585e-05,
|
| 843 |
+
"loss": 0.011,
|
| 844 |
+
"step": 990
|
| 845 |
+
},
|
| 846 |
+
{
|
| 847 |
+
"epoch": 5.096938775510204,
|
| 848 |
+
"grad_norm": 0.32866305112838745,
|
| 849 |
+
"learning_rate": 4.141156462585034e-05,
|
| 850 |
+
"loss": 0.0112,
|
| 851 |
+
"step": 999
|
| 852 |
+
},
|
| 853 |
+
{
|
| 854 |
+
"epoch": 5.142857142857143,
|
| 855 |
+
"grad_norm": 3.6175878047943115,
|
| 856 |
+
"learning_rate": 4.128401360544218e-05,
|
| 857 |
+
"loss": 0.0151,
|
| 858 |
+
"step": 1008
|
| 859 |
+
},
|
| 860 |
+
{
|
| 861 |
+
"epoch": 5.188775510204081,
|
| 862 |
+
"grad_norm": 1.1477692127227783,
|
| 863 |
+
"learning_rate": 4.1156462585034016e-05,
|
| 864 |
+
"loss": 0.0093,
|
| 865 |
+
"step": 1017
|
| 866 |
+
},
|
| 867 |
+
{
|
| 868 |
+
"epoch": 5.23469387755102,
|
| 869 |
+
"grad_norm": 0.1428331732749939,
|
| 870 |
+
"learning_rate": 4.1028911564625853e-05,
|
| 871 |
+
"loss": 0.0115,
|
| 872 |
+
"step": 1026
|
| 873 |
+
},
|
| 874 |
+
{
|
| 875 |
+
"epoch": 5.280612244897959,
|
| 876 |
+
"grad_norm": 0.1712471842765808,
|
| 877 |
+
"learning_rate": 4.0901360544217684e-05,
|
| 878 |
+
"loss": 0.0219,
|
| 879 |
+
"step": 1035
|
| 880 |
+
},
|
| 881 |
+
{
|
| 882 |
+
"epoch": 5.326530612244898,
|
| 883 |
+
"grad_norm": 0.21103200316429138,
|
| 884 |
+
"learning_rate": 4.077380952380952e-05,
|
| 885 |
+
"loss": 0.0121,
|
| 886 |
+
"step": 1044
|
| 887 |
+
},
|
| 888 |
+
{
|
| 889 |
+
"epoch": 5.372448979591836,
|
| 890 |
+
"grad_norm": 0.15935823321342468,
|
| 891 |
+
"learning_rate": 4.0646258503401366e-05,
|
| 892 |
+
"loss": 0.0074,
|
| 893 |
+
"step": 1053
|
| 894 |
+
},
|
| 895 |
+
{
|
| 896 |
+
"epoch": 5.418367346938775,
|
| 897 |
+
"grad_norm": 0.7716410756111145,
|
| 898 |
+
"learning_rate": 4.0518707482993204e-05,
|
| 899 |
+
"loss": 0.0314,
|
| 900 |
+
"step": 1062
|
| 901 |
+
},
|
| 902 |
+
{
|
| 903 |
+
"epoch": 5.464285714285714,
|
| 904 |
+
"grad_norm": 0.5172207951545715,
|
| 905 |
+
"learning_rate": 4.0391156462585035e-05,
|
| 906 |
+
"loss": 0.0101,
|
| 907 |
+
"step": 1071
|
| 908 |
+
},
|
| 909 |
+
{
|
| 910 |
+
"epoch": 5.510204081632653,
|
| 911 |
+
"grad_norm": 1.6434773206710815,
|
| 912 |
+
"learning_rate": 4.026360544217687e-05,
|
| 913 |
+
"loss": 0.0176,
|
| 914 |
+
"step": 1080
|
| 915 |
+
},
|
| 916 |
+
{
|
| 917 |
+
"epoch": 5.5561224489795915,
|
| 918 |
+
"grad_norm": 0.2688583731651306,
|
| 919 |
+
"learning_rate": 4.013605442176871e-05,
|
| 920 |
+
"loss": 0.0136,
|
| 921 |
+
"step": 1089
|
| 922 |
+
},
|
| 923 |
+
{
|
| 924 |
+
"epoch": 5.6020408163265305,
|
| 925 |
+
"grad_norm": 0.7320523858070374,
|
| 926 |
+
"learning_rate": 4.000850340136055e-05,
|
| 927 |
+
"loss": 0.0132,
|
| 928 |
+
"step": 1098
|
| 929 |
+
},
|
| 930 |
+
{
|
| 931 |
+
"epoch": 5.6479591836734695,
|
| 932 |
+
"grad_norm": 0.7341743111610413,
|
| 933 |
+
"learning_rate": 3.9880952380952386e-05,
|
| 934 |
+
"loss": 0.0064,
|
| 935 |
+
"step": 1107
|
| 936 |
+
},
|
| 937 |
+
{
|
| 938 |
+
"epoch": 5.6938775510204085,
|
| 939 |
+
"grad_norm": 1.0884281396865845,
|
| 940 |
+
"learning_rate": 3.9753401360544216e-05,
|
| 941 |
+
"loss": 0.0192,
|
| 942 |
+
"step": 1116
|
| 943 |
+
},
|
| 944 |
+
{
|
| 945 |
+
"epoch": 5.739795918367347,
|
| 946 |
+
"grad_norm": 0.36947500705718994,
|
| 947 |
+
"learning_rate": 3.9625850340136054e-05,
|
| 948 |
+
"loss": 0.0128,
|
| 949 |
+
"step": 1125
|
| 950 |
+
},
|
| 951 |
+
{
|
| 952 |
+
"epoch": 5.785714285714286,
|
| 953 |
+
"grad_norm": 0.5507375597953796,
|
| 954 |
+
"learning_rate": 3.949829931972789e-05,
|
| 955 |
+
"loss": 0.005,
|
| 956 |
+
"step": 1134
|
| 957 |
+
},
|
| 958 |
+
{
|
| 959 |
+
"epoch": 5.831632653061225,
|
| 960 |
+
"grad_norm": 2.703362226486206,
|
| 961 |
+
"learning_rate": 3.937074829931973e-05,
|
| 962 |
+
"loss": 0.0336,
|
| 963 |
+
"step": 1143
|
| 964 |
+
},
|
| 965 |
+
{
|
| 966 |
+
"epoch": 5.877551020408164,
|
| 967 |
+
"grad_norm": 0.28341037034988403,
|
| 968 |
+
"learning_rate": 3.924319727891157e-05,
|
| 969 |
+
"loss": 0.0085,
|
| 970 |
+
"step": 1152
|
| 971 |
+
},
|
| 972 |
+
{
|
| 973 |
+
"epoch": 5.923469387755102,
|
| 974 |
+
"grad_norm": 0.5502461194992065,
|
| 975 |
+
"learning_rate": 3.9115646258503405e-05,
|
| 976 |
+
"loss": 0.0197,
|
| 977 |
+
"step": 1161
|
| 978 |
+
},
|
| 979 |
+
{
|
| 980 |
+
"epoch": 5.969387755102041,
|
| 981 |
+
"grad_norm": 0.14302176237106323,
|
| 982 |
+
"learning_rate": 3.898809523809524e-05,
|
| 983 |
+
"loss": 0.0085,
|
| 984 |
+
"step": 1170
|
| 985 |
+
},
|
| 986 |
+
{
|
| 987 |
+
"epoch": 6.0,
|
| 988 |
+
"eval_gen_len": 127.0408,
|
| 989 |
+
"eval_loss": 0.005346208810806274,
|
| 990 |
+
"eval_rouge1": 99.1155,
|
| 991 |
+
"eval_rouge2": 98.9388,
|
| 992 |
+
"eval_rougeL": 99.0647,
|
| 993 |
+
"eval_rougeLsum": 99.1173,
|
| 994 |
+
"eval_runtime": 37.8929,
|
| 995 |
+
"eval_samples_per_second": 2.586,
|
| 996 |
+
"eval_steps_per_second": 0.66,
|
| 997 |
+
"step": 1176
|
| 998 |
+
},
|
| 999 |
+
{
|
| 1000 |
+
"epoch": 6.01530612244898,
|
| 1001 |
+
"grad_norm": 3.993354558944702,
|
| 1002 |
+
"learning_rate": 3.886054421768708e-05,
|
| 1003 |
+
"loss": 0.0131,
|
| 1004 |
+
"step": 1179
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 6.061224489795919,
|
| 1008 |
+
"grad_norm": 1.2994415760040283,
|
| 1009 |
+
"learning_rate": 3.873299319727892e-05,
|
| 1010 |
+
"loss": 0.0164,
|
| 1011 |
+
"step": 1188
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 6.107142857142857,
|
| 1015 |
+
"grad_norm": 1.7750136852264404,
|
| 1016 |
+
"learning_rate": 3.860544217687075e-05,
|
| 1017 |
+
"loss": 0.0049,
|
| 1018 |
+
"step": 1197
|
| 1019 |
+
},
|
| 1020 |
+
{
|
| 1021 |
+
"epoch": 6.153061224489796,
|
| 1022 |
+
"grad_norm": 1.9320180416107178,
|
| 1023 |
+
"learning_rate": 3.8477891156462586e-05,
|
| 1024 |
+
"loss": 0.0039,
|
| 1025 |
+
"step": 1206
|
| 1026 |
+
},
|
| 1027 |
+
{
|
| 1028 |
+
"epoch": 6.198979591836735,
|
| 1029 |
+
"grad_norm": 0.19184532761573792,
|
| 1030 |
+
"learning_rate": 3.8350340136054424e-05,
|
| 1031 |
+
"loss": 0.0045,
|
| 1032 |
+
"step": 1215
|
| 1033 |
+
},
|
| 1034 |
+
{
|
| 1035 |
+
"epoch": 6.244897959183674,
|
| 1036 |
+
"grad_norm": 0.7971787452697754,
|
| 1037 |
+
"learning_rate": 3.822278911564626e-05,
|
| 1038 |
+
"loss": 0.0063,
|
| 1039 |
+
"step": 1224
|
| 1040 |
+
},
|
| 1041 |
+
{
|
| 1042 |
+
"epoch": 6.290816326530612,
|
| 1043 |
+
"grad_norm": 0.3261989951133728,
|
| 1044 |
+
"learning_rate": 3.809523809523809e-05,
|
| 1045 |
+
"loss": 0.0166,
|
| 1046 |
+
"step": 1233
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 6.336734693877551,
|
| 1050 |
+
"grad_norm": 3.3873021602630615,
|
| 1051 |
+
"learning_rate": 3.796768707482993e-05,
|
| 1052 |
+
"loss": 0.0074,
|
| 1053 |
+
"step": 1242
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 6.38265306122449,
|
| 1057 |
+
"grad_norm": 2.5156352519989014,
|
| 1058 |
+
"learning_rate": 3.784013605442177e-05,
|
| 1059 |
+
"loss": 0.0132,
|
| 1060 |
+
"step": 1251
|
| 1061 |
+
},
|
| 1062 |
+
{
|
| 1063 |
+
"epoch": 6.428571428571429,
|
| 1064 |
+
"grad_norm": 4.740504264831543,
|
| 1065 |
+
"learning_rate": 3.771258503401361e-05,
|
| 1066 |
+
"loss": 0.0197,
|
| 1067 |
+
"step": 1260
|
| 1068 |
+
},
|
| 1069 |
+
{
|
| 1070 |
+
"epoch": 6.474489795918368,
|
| 1071 |
+
"grad_norm": 0.14355747401714325,
|
| 1072 |
+
"learning_rate": 3.758503401360544e-05,
|
| 1073 |
+
"loss": 0.005,
|
| 1074 |
+
"step": 1269
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 6.520408163265306,
|
| 1078 |
+
"grad_norm": 1.1807011365890503,
|
| 1079 |
+
"learning_rate": 3.745748299319728e-05,
|
| 1080 |
+
"loss": 0.0073,
|
| 1081 |
+
"step": 1278
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 6.566326530612245,
|
| 1085 |
+
"grad_norm": 0.22915400564670563,
|
| 1086 |
+
"learning_rate": 3.732993197278912e-05,
|
| 1087 |
+
"loss": 0.006,
|
| 1088 |
+
"step": 1287
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 6.612244897959184,
|
| 1092 |
+
"grad_norm": 0.3873462975025177,
|
| 1093 |
+
"learning_rate": 3.7202380952380956e-05,
|
| 1094 |
+
"loss": 0.0113,
|
| 1095 |
+
"step": 1296
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 6.658163265306122,
|
| 1099 |
+
"grad_norm": 1.502334475517273,
|
| 1100 |
+
"learning_rate": 3.707482993197279e-05,
|
| 1101 |
+
"loss": 0.0145,
|
| 1102 |
+
"step": 1305
|
| 1103 |
+
},
|
| 1104 |
+
{
|
| 1105 |
+
"epoch": 6.704081632653061,
|
| 1106 |
+
"grad_norm": 1.4580602645874023,
|
| 1107 |
+
"learning_rate": 3.6947278911564624e-05,
|
| 1108 |
+
"loss": 0.0115,
|
| 1109 |
+
"step": 1314
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 6.75,
|
| 1113 |
+
"grad_norm": 0.14768829941749573,
|
| 1114 |
+
"learning_rate": 3.681972789115646e-05,
|
| 1115 |
+
"loss": 0.0057,
|
| 1116 |
+
"step": 1323
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 6.795918367346939,
|
| 1120 |
+
"grad_norm": 0.10615669190883636,
|
| 1121 |
+
"learning_rate": 3.66921768707483e-05,
|
| 1122 |
+
"loss": 0.0113,
|
| 1123 |
+
"step": 1332
|
| 1124 |
+
},
|
| 1125 |
+
{
|
| 1126 |
+
"epoch": 6.841836734693878,
|
| 1127 |
+
"grad_norm": 0.17342956364154816,
|
| 1128 |
+
"learning_rate": 3.656462585034014e-05,
|
| 1129 |
+
"loss": 0.0077,
|
| 1130 |
+
"step": 1341
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 6.887755102040816,
|
| 1134 |
+
"grad_norm": 1.031613826751709,
|
| 1135 |
+
"learning_rate": 3.6437074829931975e-05,
|
| 1136 |
+
"loss": 0.0061,
|
| 1137 |
+
"step": 1350
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 6.933673469387755,
|
| 1141 |
+
"grad_norm": 0.5434854030609131,
|
| 1142 |
+
"learning_rate": 3.630952380952381e-05,
|
| 1143 |
+
"loss": 0.0046,
|
| 1144 |
+
"step": 1359
|
| 1145 |
+
},
|
| 1146 |
+
{
|
| 1147 |
+
"epoch": 6.979591836734694,
|
| 1148 |
+
"grad_norm": 2.6706666946411133,
|
| 1149 |
+
"learning_rate": 3.618197278911565e-05,
|
| 1150 |
+
"loss": 0.008,
|
| 1151 |
+
"step": 1368
|
| 1152 |
+
},
|
| 1153 |
+
{
|
| 1154 |
+
"epoch": 7.0,
|
| 1155 |
+
"eval_gen_len": 127.7143,
|
| 1156 |
+
"eval_loss": 0.003461688058450818,
|
| 1157 |
+
"eval_rouge1": 99.738,
|
| 1158 |
+
"eval_rouge2": 99.6362,
|
| 1159 |
+
"eval_rougeL": 99.7372,
|
| 1160 |
+
"eval_rougeLsum": 99.739,
|
| 1161 |
+
"eval_runtime": 37.7713,
|
| 1162 |
+
"eval_samples_per_second": 2.595,
|
| 1163 |
+
"eval_steps_per_second": 0.662,
|
| 1164 |
+
"step": 1372
|
| 1165 |
+
}
|
| 1166 |
+
],
|
| 1167 |
+
"logging_steps": 9,
|
| 1168 |
+
"max_steps": 3920,
|
| 1169 |
+
"num_input_tokens_seen": 0,
|
| 1170 |
+
"num_train_epochs": 20,
|
| 1171 |
+
"save_steps": 500,
|
| 1172 |
+
"total_flos": 93017113362432.0,
|
| 1173 |
+
"train_batch_size": 2,
|
| 1174 |
+
"trial_name": null,
|
| 1175 |
+
"trial_params": null
|
| 1176 |
+
}
|
checkpoint-1372/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e588d45705b34a78a08ec306fd6558ecc34f8b0346279eed034d165506fb2d86
|
| 3 |
+
size 5176
|
checkpoint-1372/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
config.json
ADDED
|
@@ -0,0 +1,61 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "LRJ1981/autotrain-redigeretData-version21",
|
| 3 |
+
"_num_labels": 3,
|
| 4 |
+
"activation_dropout": 0.0,
|
| 5 |
+
"activation_function": "swish",
|
| 6 |
+
"add_bias_logits": false,
|
| 7 |
+
"add_final_layer_norm": false,
|
| 8 |
+
"architectures": [
|
| 9 |
+
"MarianMTModel"
|
| 10 |
+
],
|
| 11 |
+
"attention_dropout": 0.0,
|
| 12 |
+
"bad_words_ids": [
|
| 13 |
+
[
|
| 14 |
+
58929
|
| 15 |
+
]
|
| 16 |
+
],
|
| 17 |
+
"bos_token_id": 0,
|
| 18 |
+
"classif_dropout": 0.0,
|
| 19 |
+
"classifier_dropout": 0.0,
|
| 20 |
+
"d_model": 512,
|
| 21 |
+
"decoder_attention_heads": 8,
|
| 22 |
+
"decoder_ffn_dim": 2048,
|
| 23 |
+
"decoder_layerdrop": 0.0,
|
| 24 |
+
"decoder_layers": 6,
|
| 25 |
+
"decoder_start_token_id": 58929,
|
| 26 |
+
"decoder_vocab_size": 58930,
|
| 27 |
+
"dropout": 0.1,
|
| 28 |
+
"encoder_attention_heads": 8,
|
| 29 |
+
"encoder_ffn_dim": 2048,
|
| 30 |
+
"encoder_layerdrop": 0.0,
|
| 31 |
+
"encoder_layers": 6,
|
| 32 |
+
"eos_token_id": 0,
|
| 33 |
+
"forced_eos_token_id": 0,
|
| 34 |
+
"id2label": {
|
| 35 |
+
"0": "LABEL_0",
|
| 36 |
+
"1": "LABEL_1",
|
| 37 |
+
"2": "LABEL_2"
|
| 38 |
+
},
|
| 39 |
+
"init_std": 0.02,
|
| 40 |
+
"is_encoder_decoder": true,
|
| 41 |
+
"label2id": {
|
| 42 |
+
"LABEL_0": 0,
|
| 43 |
+
"LABEL_1": 1,
|
| 44 |
+
"LABEL_2": 2
|
| 45 |
+
},
|
| 46 |
+
"max_length": 512,
|
| 47 |
+
"max_position_embeddings": 512,
|
| 48 |
+
"model_type": "marian",
|
| 49 |
+
"normalize_before": false,
|
| 50 |
+
"normalize_embedding": false,
|
| 51 |
+
"num_beams": 4,
|
| 52 |
+
"num_hidden_layers": 6,
|
| 53 |
+
"pad_token_id": 58929,
|
| 54 |
+
"scale_embedding": true,
|
| 55 |
+
"share_encoder_decoder_embeddings": true,
|
| 56 |
+
"static_position_embeddings": true,
|
| 57 |
+
"torch_dtype": "float32",
|
| 58 |
+
"transformers_version": "4.40.1",
|
| 59 |
+
"use_cache": true,
|
| 60 |
+
"vocab_size": 58930
|
| 61 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bad_words_ids": [
|
| 3 |
+
[
|
| 4 |
+
58929
|
| 5 |
+
]
|
| 6 |
+
],
|
| 7 |
+
"bos_token_id": 0,
|
| 8 |
+
"decoder_start_token_id": 58929,
|
| 9 |
+
"eos_token_id": 0,
|
| 10 |
+
"forced_eos_token_id": 0,
|
| 11 |
+
"max_length": 512,
|
| 12 |
+
"num_beams": 4,
|
| 13 |
+
"pad_token_id": 58929,
|
| 14 |
+
"renormalize_logits": true,
|
| 15 |
+
"transformers_version": "4.40.1"
|
| 16 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cb6edaa6b942cd09ecbc8c1838ab6e7cc057269c1e71894f3f44fb3f78c9eec8
|
| 3 |
+
size 297507400
|
runs/May13_07-56-46_r-lrj1981-ml-test-zx4ztum5-855f6-xnwlo/events.out.tfevents.1715587009.r-lrj1981-ml-test-zx4ztum5-855f6-xnwlo.67.0
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dbb592e7ee149e1de7aace8f5565ee1184f60dc53ccf5fb1e09e4f04cdbc9f91
|
| 3 |
+
size 41679
|
runs/May13_07-56-46_r-lrj1981-ml-test-zx4ztum5-855f6-xnwlo/events.out.tfevents.1715587442.r-lrj1981-ml-test-zx4ztum5-855f6-xnwlo.67.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:714d346ba481f4767de024ec8e8ac3e9aa262d52aa5a12ffa0b5bdd65e7eadbf
|
| 3 |
+
size 613
|
source.spm
ADDED
|
Binary file (820 kB). View file
|
|
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"eos_token": {
|
| 3 |
+
"content": "</s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"pad_token": {
|
| 10 |
+
"content": "<pad>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"unk_token": {
|
| 17 |
+
"content": "<unk>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
}
|
| 23 |
+
}
|
target.spm
ADDED
|
Binary file (788 kB). View file
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": "<unk>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"58929": {
|
| 20 |
+
"content": "<pad>",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
}
|
| 27 |
+
},
|
| 28 |
+
"clean_up_tokenization_spaces": true,
|
| 29 |
+
"eos_token": "</s>",
|
| 30 |
+
"model_max_length": 512,
|
| 31 |
+
"pad_token": "<pad>",
|
| 32 |
+
"separate_vocabs": false,
|
| 33 |
+
"source_lang": "da",
|
| 34 |
+
"sp_model_kwargs": {},
|
| 35 |
+
"target_lang": "en",
|
| 36 |
+
"tokenizer_class": "MarianTokenizer",
|
| 37 |
+
"unk_token": "<unk>"
|
| 38 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e588d45705b34a78a08ec306fd6558ecc34f8b0346279eed034d165506fb2d86
|
| 3 |
+
size 5176
|
training_params.json
ADDED
|
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"data_path": "autotrain-9t83i-0umcp/autotrain-data",
|
| 3 |
+
"model": "LRJ1981/autotrain-redigeretData-version21",
|
| 4 |
+
"username": "LRJ1981",
|
| 5 |
+
"seed": 42,
|
| 6 |
+
"train_split": "train",
|
| 7 |
+
"valid_split": "validation",
|
| 8 |
+
"project_name": "autotrain-9t83i-0umcp",
|
| 9 |
+
"push_to_hub": true,
|
| 10 |
+
"text_column": "autotrain_text",
|
| 11 |
+
"target_column": "autotrain_label",
|
| 12 |
+
"lr": 5e-05,
|
| 13 |
+
"epochs": 20,
|
| 14 |
+
"max_seq_length": 128,
|
| 15 |
+
"max_target_length": 128,
|
| 16 |
+
"batch_size": 2,
|
| 17 |
+
"warmup_ratio": 0.1,
|
| 18 |
+
"gradient_accumulation": 1,
|
| 19 |
+
"optimizer": "adamw_torch",
|
| 20 |
+
"scheduler": "linear",
|
| 21 |
+
"weight_decay": 0.0,
|
| 22 |
+
"max_grad_norm": 1.0,
|
| 23 |
+
"logging_steps": -1,
|
| 24 |
+
"evaluation_strategy": "epoch",
|
| 25 |
+
"auto_find_batch_size": false,
|
| 26 |
+
"mixed_precision": "fp16",
|
| 27 |
+
"save_total_limit": 1,
|
| 28 |
+
"peft": false,
|
| 29 |
+
"quantization": "int4",
|
| 30 |
+
"lora_r": 16,
|
| 31 |
+
"lora_alpha": 32,
|
| 32 |
+
"lora_dropout": 0.05,
|
| 33 |
+
"target_modules": "all-linear",
|
| 34 |
+
"log": "tensorboard"
|
| 35 |
+
}
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|