Upload folder using huggingface_hub
Browse files- checkpoint-22000/config.json +75 -0
- checkpoint-22000/generation_config.json +13 -0
- checkpoint-22000/merges.txt +0 -0
- checkpoint-22000/model.safetensors +3 -0
- checkpoint-22000/optimizer.pt +3 -0
- checkpoint-22000/rng_state.pth +3 -0
- checkpoint-22000/scheduler.pt +3 -0
- checkpoint-22000/special_tokens_map.json +15 -0
- checkpoint-22000/tokenizer.json +0 -0
- checkpoint-22000/tokenizer_config.json +57 -0
- checkpoint-22000/trainer_state.json +693 -0
- checkpoint-22000/training_args.bin +3 -0
- checkpoint-22000/vocab.json +0 -0
- config.json +75 -0
- generation_config.json +13 -0
- merges.txt +0 -0
- model.safetensors +3 -0
- special_tokens_map.json +15 -0
- test_results.csv +0 -0
- tokenizer.json +0 -0
- tokenizer_config.json +57 -0
- training_args.bin +3 -0
- vocab.json +0 -0
checkpoint-22000/config.json
ADDED
|
@@ -0,0 +1,75 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "facebook/bart-base",
|
| 3 |
+
"activation_dropout": 0.1,
|
| 4 |
+
"activation_function": "gelu",
|
| 5 |
+
"add_bias_logits": false,
|
| 6 |
+
"add_final_layer_norm": false,
|
| 7 |
+
"architectures": [
|
| 8 |
+
"BartForConditionalGeneration"
|
| 9 |
+
],
|
| 10 |
+
"attention_dropout": 0.1,
|
| 11 |
+
"bos_token_id": 0,
|
| 12 |
+
"classif_dropout": 0.1,
|
| 13 |
+
"classifier_dropout": 0.0,
|
| 14 |
+
"d_model": 768,
|
| 15 |
+
"decoder_attention_heads": 12,
|
| 16 |
+
"decoder_ffn_dim": 3072,
|
| 17 |
+
"decoder_layerdrop": 0.0,
|
| 18 |
+
"decoder_layers": 6,
|
| 19 |
+
"decoder_start_token_id": 2,
|
| 20 |
+
"dropout": 0.1,
|
| 21 |
+
"early_stopping": true,
|
| 22 |
+
"encoder_attention_heads": 12,
|
| 23 |
+
"encoder_ffn_dim": 3072,
|
| 24 |
+
"encoder_layerdrop": 0.0,
|
| 25 |
+
"encoder_layers": 6,
|
| 26 |
+
"eos_token_id": 2,
|
| 27 |
+
"forced_bos_token_id": 0,
|
| 28 |
+
"forced_eos_token_id": 2,
|
| 29 |
+
"gradient_checkpointing": false,
|
| 30 |
+
"id2label": {
|
| 31 |
+
"0": "LABEL_0",
|
| 32 |
+
"1": "LABEL_1",
|
| 33 |
+
"2": "LABEL_2"
|
| 34 |
+
},
|
| 35 |
+
"init_std": 0.02,
|
| 36 |
+
"is_encoder_decoder": true,
|
| 37 |
+
"label2id": {
|
| 38 |
+
"LABEL_0": 0,
|
| 39 |
+
"LABEL_1": 1,
|
| 40 |
+
"LABEL_2": 2
|
| 41 |
+
},
|
| 42 |
+
"max_position_embeddings": 1024,
|
| 43 |
+
"model_type": "bart",
|
| 44 |
+
"no_repeat_ngram_size": 3,
|
| 45 |
+
"normalize_before": false,
|
| 46 |
+
"normalize_embedding": true,
|
| 47 |
+
"num_beams": 4,
|
| 48 |
+
"num_hidden_layers": 6,
|
| 49 |
+
"pad_token_id": 1,
|
| 50 |
+
"scale_embedding": false,
|
| 51 |
+
"task_specific_params": {
|
| 52 |
+
"summarization": {
|
| 53 |
+
"length_penalty": 1.0,
|
| 54 |
+
"max_length": 128,
|
| 55 |
+
"min_length": 12,
|
| 56 |
+
"num_beams": 4
|
| 57 |
+
},
|
| 58 |
+
"summarization_cnn": {
|
| 59 |
+
"length_penalty": 2.0,
|
| 60 |
+
"max_length": 142,
|
| 61 |
+
"min_length": 56,
|
| 62 |
+
"num_beams": 4
|
| 63 |
+
},
|
| 64 |
+
"summarization_xsum": {
|
| 65 |
+
"length_penalty": 1.0,
|
| 66 |
+
"max_length": 62,
|
| 67 |
+
"min_length": 11,
|
| 68 |
+
"num_beams": 6
|
| 69 |
+
}
|
| 70 |
+
},
|
| 71 |
+
"torch_dtype": "float32",
|
| 72 |
+
"transformers_version": "4.44.1",
|
| 73 |
+
"use_cache": true,
|
| 74 |
+
"vocab_size": 50265
|
| 75 |
+
}
|
checkpoint-22000/generation_config.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 0,
|
| 4 |
+
"decoder_start_token_id": 2,
|
| 5 |
+
"early_stopping": true,
|
| 6 |
+
"eos_token_id": 2,
|
| 7 |
+
"forced_bos_token_id": 0,
|
| 8 |
+
"forced_eos_token_id": 2,
|
| 9 |
+
"no_repeat_ngram_size": 3,
|
| 10 |
+
"num_beams": 4,
|
| 11 |
+
"pad_token_id": 1,
|
| 12 |
+
"transformers_version": "4.44.1"
|
| 13 |
+
}
|
checkpoint-22000/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-22000/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:10e203555fb675c210bdc97d850733c2063293e738eb3a476f075b2e79939573
|
| 3 |
+
size 557912620
|
checkpoint-22000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:457c238407f2e0aedf9c939a11c3bbc7336bb9ccbbeaf9e860ade5ea8039e9c2
|
| 3 |
+
size 1115579898
|
checkpoint-22000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:724f47cca758f0552d09f68f0164a6f4a69e77e6efb6b71d601fe8998d1243d3
|
| 3 |
+
size 14244
|
checkpoint-22000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:277fd6a90ebb4d34fbc07d7e3771748297e3b84a3b919dfb30d50774436adb77
|
| 3 |
+
size 1064
|
checkpoint-22000/special_tokens_map.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<s>",
|
| 3 |
+
"cls_token": "<s>",
|
| 4 |
+
"eos_token": "</s>",
|
| 5 |
+
"mask_token": {
|
| 6 |
+
"content": "<mask>",
|
| 7 |
+
"lstrip": true,
|
| 8 |
+
"normalized": true,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false
|
| 11 |
+
},
|
| 12 |
+
"pad_token": "<pad>",
|
| 13 |
+
"sep_token": "</s>",
|
| 14 |
+
"unk_token": "<unk>"
|
| 15 |
+
}
|
checkpoint-22000/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-22000/tokenizer_config.json
ADDED
|
@@ -0,0 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"0": {
|
| 5 |
+
"content": "<s>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": true,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"1": {
|
| 13 |
+
"content": "<pad>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": true,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
},
|
| 20 |
+
"2": {
|
| 21 |
+
"content": "</s>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": true,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": true
|
| 27 |
+
},
|
| 28 |
+
"3": {
|
| 29 |
+
"content": "<unk>",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": true,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false,
|
| 34 |
+
"special": true
|
| 35 |
+
},
|
| 36 |
+
"50264": {
|
| 37 |
+
"content": "<mask>",
|
| 38 |
+
"lstrip": true,
|
| 39 |
+
"normalized": true,
|
| 40 |
+
"rstrip": false,
|
| 41 |
+
"single_word": false,
|
| 42 |
+
"special": true
|
| 43 |
+
}
|
| 44 |
+
},
|
| 45 |
+
"bos_token": "<s>",
|
| 46 |
+
"clean_up_tokenization_spaces": true,
|
| 47 |
+
"cls_token": "<s>",
|
| 48 |
+
"eos_token": "</s>",
|
| 49 |
+
"errors": "replace",
|
| 50 |
+
"mask_token": "<mask>",
|
| 51 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 52 |
+
"pad_token": "<pad>",
|
| 53 |
+
"sep_token": "</s>",
|
| 54 |
+
"tokenizer_class": "BartTokenizer",
|
| 55 |
+
"trim_offsets": true,
|
| 56 |
+
"unk_token": "<unk>"
|
| 57 |
+
}
|
checkpoint-22000/trainer_state.json
ADDED
|
@@ -0,0 +1,693 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.04673506319522858,
|
| 3 |
+
"best_model_checkpoint": "models/seniority_classification_v2/checkpoint-22000",
|
| 4 |
+
"epoch": 2.962962962962963,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 22000,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.06734006734006734,
|
| 13 |
+
"grad_norm": 4.000732421875,
|
| 14 |
+
"learning_rate": 4.443447037701975e-06,
|
| 15 |
+
"loss": 2.0078,
|
| 16 |
+
"step": 500
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.06734006734006734,
|
| 20 |
+
"eval_loss": 0.11451733857393265,
|
| 21 |
+
"eval_runtime": 16.4688,
|
| 22 |
+
"eval_samples_per_second": 759.376,
|
| 23 |
+
"eval_steps_per_second": 94.968,
|
| 24 |
+
"step": 500
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.13468013468013468,
|
| 28 |
+
"grad_norm": 3.557553291320801,
|
| 29 |
+
"learning_rate": 8.931777378815083e-06,
|
| 30 |
+
"loss": 0.1318,
|
| 31 |
+
"step": 1000
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.13468013468013468,
|
| 35 |
+
"eval_loss": 0.08117523789405823,
|
| 36 |
+
"eval_runtime": 16.1911,
|
| 37 |
+
"eval_samples_per_second": 772.401,
|
| 38 |
+
"eval_steps_per_second": 96.596,
|
| 39 |
+
"step": 1000
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.20202020202020202,
|
| 43 |
+
"grad_norm": 3.078228712081909,
|
| 44 |
+
"learning_rate": 1.3411131059245961e-05,
|
| 45 |
+
"loss": 0.1009,
|
| 46 |
+
"step": 1500
|
| 47 |
+
},
|
| 48 |
+
{
|
| 49 |
+
"epoch": 0.20202020202020202,
|
| 50 |
+
"eval_loss": 0.08063514530658722,
|
| 51 |
+
"eval_runtime": 16.5133,
|
| 52 |
+
"eval_samples_per_second": 757.327,
|
| 53 |
+
"eval_steps_per_second": 94.711,
|
| 54 |
+
"step": 1500
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 0.26936026936026936,
|
| 58 |
+
"grad_norm": 2.201984167098999,
|
| 59 |
+
"learning_rate": 1.7899461400359067e-05,
|
| 60 |
+
"loss": 0.0881,
|
| 61 |
+
"step": 2000
|
| 62 |
+
},
|
| 63 |
+
{
|
| 64 |
+
"epoch": 0.26936026936026936,
|
| 65 |
+
"eval_loss": 0.07039299607276917,
|
| 66 |
+
"eval_runtime": 16.8702,
|
| 67 |
+
"eval_samples_per_second": 741.305,
|
| 68 |
+
"eval_steps_per_second": 92.708,
|
| 69 |
+
"step": 2000
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.3367003367003367,
|
| 73 |
+
"grad_norm": 1.8311361074447632,
|
| 74 |
+
"learning_rate": 1.9734623634459023e-05,
|
| 75 |
+
"loss": 0.0782,
|
| 76 |
+
"step": 2500
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"epoch": 0.3367003367003367,
|
| 80 |
+
"eval_loss": 0.06892260909080505,
|
| 81 |
+
"eval_runtime": 16.6262,
|
| 82 |
+
"eval_samples_per_second": 752.185,
|
| 83 |
+
"eval_steps_per_second": 94.068,
|
| 84 |
+
"step": 2500
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 0.40404040404040403,
|
| 88 |
+
"grad_norm": 0.8982350826263428,
|
| 89 |
+
"learning_rate": 1.923579587968275e-05,
|
| 90 |
+
"loss": 0.0741,
|
| 91 |
+
"step": 3000
|
| 92 |
+
},
|
| 93 |
+
{
|
| 94 |
+
"epoch": 0.40404040404040403,
|
| 95 |
+
"eval_loss": 0.06992588192224503,
|
| 96 |
+
"eval_runtime": 17.2623,
|
| 97 |
+
"eval_samples_per_second": 724.468,
|
| 98 |
+
"eval_steps_per_second": 90.602,
|
| 99 |
+
"step": 3000
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.4713804713804714,
|
| 103 |
+
"grad_norm": 1.2489134073257446,
|
| 104 |
+
"learning_rate": 1.8736968124906473e-05,
|
| 105 |
+
"loss": 0.0733,
|
| 106 |
+
"step": 3500
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 0.4713804713804714,
|
| 110 |
+
"eval_loss": 0.06877408921718597,
|
| 111 |
+
"eval_runtime": 16.6808,
|
| 112 |
+
"eval_samples_per_second": 749.722,
|
| 113 |
+
"eval_steps_per_second": 93.76,
|
| 114 |
+
"step": 3500
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.5387205387205387,
|
| 118 |
+
"grad_norm": 0.49788302183151245,
|
| 119 |
+
"learning_rate": 1.8238140370130196e-05,
|
| 120 |
+
"loss": 0.0694,
|
| 121 |
+
"step": 4000
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.5387205387205387,
|
| 125 |
+
"eval_loss": 0.06228644400835037,
|
| 126 |
+
"eval_runtime": 16.6792,
|
| 127 |
+
"eval_samples_per_second": 749.796,
|
| 128 |
+
"eval_steps_per_second": 93.769,
|
| 129 |
+
"step": 4000
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.6060606060606061,
|
| 133 |
+
"grad_norm": 2.0687389373779297,
|
| 134 |
+
"learning_rate": 1.773931261535392e-05,
|
| 135 |
+
"loss": 0.0651,
|
| 136 |
+
"step": 4500
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.6060606060606061,
|
| 140 |
+
"eval_loss": 0.0640697330236435,
|
| 141 |
+
"eval_runtime": 16.2802,
|
| 142 |
+
"eval_samples_per_second": 768.174,
|
| 143 |
+
"eval_steps_per_second": 96.068,
|
| 144 |
+
"step": 4500
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 0.6734006734006734,
|
| 148 |
+
"grad_norm": 1.90867018699646,
|
| 149 |
+
"learning_rate": 1.7240484860577643e-05,
|
| 150 |
+
"loss": 0.0673,
|
| 151 |
+
"step": 5000
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 0.6734006734006734,
|
| 155 |
+
"eval_loss": 0.056220319122076035,
|
| 156 |
+
"eval_runtime": 16.3077,
|
| 157 |
+
"eval_samples_per_second": 766.879,
|
| 158 |
+
"eval_steps_per_second": 95.906,
|
| 159 |
+
"step": 5000
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.7407407407407407,
|
| 163 |
+
"grad_norm": 1.8701962232589722,
|
| 164 |
+
"learning_rate": 1.674165710580137e-05,
|
| 165 |
+
"loss": 0.065,
|
| 166 |
+
"step": 5500
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 0.7407407407407407,
|
| 170 |
+
"eval_loss": 0.055869247764348984,
|
| 171 |
+
"eval_runtime": 16.2985,
|
| 172 |
+
"eval_samples_per_second": 767.308,
|
| 173 |
+
"eval_steps_per_second": 95.96,
|
| 174 |
+
"step": 5500
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 0.8080808080808081,
|
| 178 |
+
"grad_norm": 0.8173530697822571,
|
| 179 |
+
"learning_rate": 1.6242829351025093e-05,
|
| 180 |
+
"loss": 0.0636,
|
| 181 |
+
"step": 6000
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 0.8080808080808081,
|
| 185 |
+
"eval_loss": 0.053115226328372955,
|
| 186 |
+
"eval_runtime": 16.6909,
|
| 187 |
+
"eval_samples_per_second": 749.271,
|
| 188 |
+
"eval_steps_per_second": 93.704,
|
| 189 |
+
"step": 6000
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 0.8754208754208754,
|
| 193 |
+
"grad_norm": 1.0414296388626099,
|
| 194 |
+
"learning_rate": 1.5744001596248816e-05,
|
| 195 |
+
"loss": 0.059,
|
| 196 |
+
"step": 6500
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 0.8754208754208754,
|
| 200 |
+
"eval_loss": 0.056747473776340485,
|
| 201 |
+
"eval_runtime": 16.8281,
|
| 202 |
+
"eval_samples_per_second": 743.16,
|
| 203 |
+
"eval_steps_per_second": 92.94,
|
| 204 |
+
"step": 6500
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 0.9427609427609428,
|
| 208 |
+
"grad_norm": 1.5116974115371704,
|
| 209 |
+
"learning_rate": 1.524517384147254e-05,
|
| 210 |
+
"loss": 0.0605,
|
| 211 |
+
"step": 7000
|
| 212 |
+
},
|
| 213 |
+
{
|
| 214 |
+
"epoch": 0.9427609427609428,
|
| 215 |
+
"eval_loss": 0.05442998558282852,
|
| 216 |
+
"eval_runtime": 16.7015,
|
| 217 |
+
"eval_samples_per_second": 748.794,
|
| 218 |
+
"eval_steps_per_second": 93.644,
|
| 219 |
+
"step": 7000
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 1.0101010101010102,
|
| 223 |
+
"grad_norm": 0.9356850981712341,
|
| 224 |
+
"learning_rate": 1.4747343742205818e-05,
|
| 225 |
+
"loss": 0.0599,
|
| 226 |
+
"step": 7500
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 1.0101010101010102,
|
| 230 |
+
"eval_loss": 0.05337799713015556,
|
| 231 |
+
"eval_runtime": 16.5326,
|
| 232 |
+
"eval_samples_per_second": 756.443,
|
| 233 |
+
"eval_steps_per_second": 94.601,
|
| 234 |
+
"step": 7500
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 1.0774410774410774,
|
| 238 |
+
"grad_norm": 0.9384571313858032,
|
| 239 |
+
"learning_rate": 1.4248515987429541e-05,
|
| 240 |
+
"loss": 0.0524,
|
| 241 |
+
"step": 8000
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 1.0774410774410774,
|
| 245 |
+
"eval_loss": 0.05485278367996216,
|
| 246 |
+
"eval_runtime": 16.5656,
|
| 247 |
+
"eval_samples_per_second": 754.939,
|
| 248 |
+
"eval_steps_per_second": 94.413,
|
| 249 |
+
"step": 8000
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 1.144781144781145,
|
| 253 |
+
"grad_norm": 0.44167083501815796,
|
| 254 |
+
"learning_rate": 1.3749688232653266e-05,
|
| 255 |
+
"loss": 0.0528,
|
| 256 |
+
"step": 8500
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 1.144781144781145,
|
| 260 |
+
"eval_loss": 0.053506139665842056,
|
| 261 |
+
"eval_runtime": 16.8486,
|
| 262 |
+
"eval_samples_per_second": 742.258,
|
| 263 |
+
"eval_steps_per_second": 92.827,
|
| 264 |
+
"step": 8500
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 1.2121212121212122,
|
| 268 |
+
"grad_norm": 0.8863353133201599,
|
| 269 |
+
"learning_rate": 1.325086047787699e-05,
|
| 270 |
+
"loss": 0.0523,
|
| 271 |
+
"step": 9000
|
| 272 |
+
},
|
| 273 |
+
{
|
| 274 |
+
"epoch": 1.2121212121212122,
|
| 275 |
+
"eval_loss": 0.05303048714995384,
|
| 276 |
+
"eval_runtime": 16.3723,
|
| 277 |
+
"eval_samples_per_second": 763.85,
|
| 278 |
+
"eval_steps_per_second": 95.527,
|
| 279 |
+
"step": 9000
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 1.2794612794612794,
|
| 283 |
+
"grad_norm": 1.013847827911377,
|
| 284 |
+
"learning_rate": 1.2752032723100714e-05,
|
| 285 |
+
"loss": 0.0522,
|
| 286 |
+
"step": 9500
|
| 287 |
+
},
|
| 288 |
+
{
|
| 289 |
+
"epoch": 1.2794612794612794,
|
| 290 |
+
"eval_loss": 0.05080660432577133,
|
| 291 |
+
"eval_runtime": 16.4509,
|
| 292 |
+
"eval_samples_per_second": 760.201,
|
| 293 |
+
"eval_steps_per_second": 95.071,
|
| 294 |
+
"step": 9500
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 1.3468013468013469,
|
| 298 |
+
"grad_norm": 0.994468092918396,
|
| 299 |
+
"learning_rate": 1.2253204968324439e-05,
|
| 300 |
+
"loss": 0.0553,
|
| 301 |
+
"step": 10000
|
| 302 |
+
},
|
| 303 |
+
{
|
| 304 |
+
"epoch": 1.3468013468013469,
|
| 305 |
+
"eval_loss": 0.0516626238822937,
|
| 306 |
+
"eval_runtime": 16.3067,
|
| 307 |
+
"eval_samples_per_second": 766.925,
|
| 308 |
+
"eval_steps_per_second": 95.912,
|
| 309 |
+
"step": 10000
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 1.4141414141414141,
|
| 313 |
+
"grad_norm": 1.3221837282180786,
|
| 314 |
+
"learning_rate": 1.1754377213548162e-05,
|
| 315 |
+
"loss": 0.0484,
|
| 316 |
+
"step": 10500
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 1.4141414141414141,
|
| 320 |
+
"eval_loss": 0.0554862879216671,
|
| 321 |
+
"eval_runtime": 16.7511,
|
| 322 |
+
"eval_samples_per_second": 746.576,
|
| 323 |
+
"eval_steps_per_second": 93.367,
|
| 324 |
+
"step": 10500
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 1.4814814814814814,
|
| 328 |
+
"grad_norm": 0.7883066534996033,
|
| 329 |
+
"learning_rate": 1.1255549458771886e-05,
|
| 330 |
+
"loss": 0.0538,
|
| 331 |
+
"step": 11000
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 1.4814814814814814,
|
| 335 |
+
"eval_loss": 0.05182446911931038,
|
| 336 |
+
"eval_runtime": 16.3438,
|
| 337 |
+
"eval_samples_per_second": 765.184,
|
| 338 |
+
"eval_steps_per_second": 95.694,
|
| 339 |
+
"step": 11000
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 1.5488215488215489,
|
| 343 |
+
"grad_norm": 1.4432556629180908,
|
| 344 |
+
"learning_rate": 1.0756721703995612e-05,
|
| 345 |
+
"loss": 0.051,
|
| 346 |
+
"step": 11500
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 1.5488215488215489,
|
| 350 |
+
"eval_loss": 0.04986888915300369,
|
| 351 |
+
"eval_runtime": 16.4001,
|
| 352 |
+
"eval_samples_per_second": 762.558,
|
| 353 |
+
"eval_steps_per_second": 95.365,
|
| 354 |
+
"step": 11500
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 1.6161616161616161,
|
| 358 |
+
"grad_norm": 0.5576290488243103,
|
| 359 |
+
"learning_rate": 1.0257893949219335e-05,
|
| 360 |
+
"loss": 0.0511,
|
| 361 |
+
"step": 12000
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 1.6161616161616161,
|
| 365 |
+
"eval_loss": 0.04941289499402046,
|
| 366 |
+
"eval_runtime": 16.3023,
|
| 367 |
+
"eval_samples_per_second": 767.132,
|
| 368 |
+
"eval_steps_per_second": 95.938,
|
| 369 |
+
"step": 12000
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 1.6835016835016834,
|
| 373 |
+
"grad_norm": 0.6536795496940613,
|
| 374 |
+
"learning_rate": 9.75906619444306e-06,
|
| 375 |
+
"loss": 0.0521,
|
| 376 |
+
"step": 12500
|
| 377 |
+
},
|
| 378 |
+
{
|
| 379 |
+
"epoch": 1.6835016835016834,
|
| 380 |
+
"eval_loss": 0.04754636064171791,
|
| 381 |
+
"eval_runtime": 16.0829,
|
| 382 |
+
"eval_samples_per_second": 777.594,
|
| 383 |
+
"eval_steps_per_second": 97.246,
|
| 384 |
+
"step": 12500
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 1.7508417508417509,
|
| 388 |
+
"grad_norm": 1.5757887363433838,
|
| 389 |
+
"learning_rate": 9.260238439666784e-06,
|
| 390 |
+
"loss": 0.0493,
|
| 391 |
+
"step": 13000
|
| 392 |
+
},
|
| 393 |
+
{
|
| 394 |
+
"epoch": 1.7508417508417509,
|
| 395 |
+
"eval_loss": 0.04865530878305435,
|
| 396 |
+
"eval_runtime": 16.6799,
|
| 397 |
+
"eval_samples_per_second": 749.764,
|
| 398 |
+
"eval_steps_per_second": 93.765,
|
| 399 |
+
"step": 13000
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 1.8181818181818183,
|
| 403 |
+
"grad_norm": 0.5477749109268188,
|
| 404 |
+
"learning_rate": 8.761410684890508e-06,
|
| 405 |
+
"loss": 0.0476,
|
| 406 |
+
"step": 13500
|
| 407 |
+
},
|
| 408 |
+
{
|
| 409 |
+
"epoch": 1.8181818181818183,
|
| 410 |
+
"eval_loss": 0.04944827780127525,
|
| 411 |
+
"eval_runtime": 16.5358,
|
| 412 |
+
"eval_samples_per_second": 756.299,
|
| 413 |
+
"eval_steps_per_second": 94.583,
|
| 414 |
+
"step": 13500
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 1.8855218855218854,
|
| 418 |
+
"grad_norm": 1.0127934217453003,
|
| 419 |
+
"learning_rate": 8.262582930114232e-06,
|
| 420 |
+
"loss": 0.0529,
|
| 421 |
+
"step": 14000
|
| 422 |
+
},
|
| 423 |
+
{
|
| 424 |
+
"epoch": 1.8855218855218854,
|
| 425 |
+
"eval_loss": 0.04990923032164574,
|
| 426 |
+
"eval_runtime": 16.8929,
|
| 427 |
+
"eval_samples_per_second": 740.312,
|
| 428 |
+
"eval_steps_per_second": 92.583,
|
| 429 |
+
"step": 14000
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 1.9528619528619529,
|
| 433 |
+
"grad_norm": 0.6945014595985413,
|
| 434 |
+
"learning_rate": 7.763755175337957e-06,
|
| 435 |
+
"loss": 0.0485,
|
| 436 |
+
"step": 14500
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 1.9528619528619529,
|
| 440 |
+
"eval_loss": 0.04856531694531441,
|
| 441 |
+
"eval_runtime": 16.4321,
|
| 442 |
+
"eval_samples_per_second": 761.069,
|
| 443 |
+
"eval_steps_per_second": 95.179,
|
| 444 |
+
"step": 14500
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 2.0202020202020203,
|
| 448 |
+
"grad_norm": 0.9249310493469238,
|
| 449 |
+
"learning_rate": 7.266922731580785e-06,
|
| 450 |
+
"loss": 0.0476,
|
| 451 |
+
"step": 15000
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 2.0202020202020203,
|
| 455 |
+
"eval_loss": 0.04919321462512016,
|
| 456 |
+
"eval_runtime": 16.2793,
|
| 457 |
+
"eval_samples_per_second": 768.215,
|
| 458 |
+
"eval_steps_per_second": 96.073,
|
| 459 |
+
"step": 15000
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 2.0875420875420874,
|
| 463 |
+
"grad_norm": 0.8430482745170593,
|
| 464 |
+
"learning_rate": 6.76809497680451e-06,
|
| 465 |
+
"loss": 0.0464,
|
| 466 |
+
"step": 15500
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 2.0875420875420874,
|
| 470 |
+
"eval_loss": 0.04808473214507103,
|
| 471 |
+
"eval_runtime": 16.0614,
|
| 472 |
+
"eval_samples_per_second": 778.638,
|
| 473 |
+
"eval_steps_per_second": 97.376,
|
| 474 |
+
"step": 15500
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 2.154882154882155,
|
| 478 |
+
"grad_norm": 0.6089836955070496,
|
| 479 |
+
"learning_rate": 6.269267222028234e-06,
|
| 480 |
+
"loss": 0.0438,
|
| 481 |
+
"step": 16000
|
| 482 |
+
},
|
| 483 |
+
{
|
| 484 |
+
"epoch": 2.154882154882155,
|
| 485 |
+
"eval_loss": 0.04803529381752014,
|
| 486 |
+
"eval_runtime": 16.3428,
|
| 487 |
+
"eval_samples_per_second": 765.229,
|
| 488 |
+
"eval_steps_per_second": 95.7,
|
| 489 |
+
"step": 16000
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 2.2222222222222223,
|
| 493 |
+
"grad_norm": 1.1016465425491333,
|
| 494 |
+
"learning_rate": 5.770439467251958e-06,
|
| 495 |
+
"loss": 0.0432,
|
| 496 |
+
"step": 16500
|
| 497 |
+
},
|
| 498 |
+
{
|
| 499 |
+
"epoch": 2.2222222222222223,
|
| 500 |
+
"eval_loss": 0.04978441074490547,
|
| 501 |
+
"eval_runtime": 16.1869,
|
| 502 |
+
"eval_samples_per_second": 772.6,
|
| 503 |
+
"eval_steps_per_second": 96.621,
|
| 504 |
+
"step": 16500
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 2.28956228956229,
|
| 508 |
+
"grad_norm": 0.7859874367713928,
|
| 509 |
+
"learning_rate": 5.2716117124756825e-06,
|
| 510 |
+
"loss": 0.0411,
|
| 511 |
+
"step": 17000
|
| 512 |
+
},
|
| 513 |
+
{
|
| 514 |
+
"epoch": 2.28956228956229,
|
| 515 |
+
"eval_loss": 0.04951639473438263,
|
| 516 |
+
"eval_runtime": 16.3651,
|
| 517 |
+
"eval_samples_per_second": 764.186,
|
| 518 |
+
"eval_steps_per_second": 95.569,
|
| 519 |
+
"step": 17000
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 2.356902356902357,
|
| 523 |
+
"grad_norm": 0.6224056482315063,
|
| 524 |
+
"learning_rate": 4.7727839576994065e-06,
|
| 525 |
+
"loss": 0.043,
|
| 526 |
+
"step": 17500
|
| 527 |
+
},
|
| 528 |
+
{
|
| 529 |
+
"epoch": 2.356902356902357,
|
| 530 |
+
"eval_loss": 0.04945288226008415,
|
| 531 |
+
"eval_runtime": 18.4689,
|
| 532 |
+
"eval_samples_per_second": 677.14,
|
| 533 |
+
"eval_steps_per_second": 84.683,
|
| 534 |
+
"step": 17500
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 2.4242424242424243,
|
| 538 |
+
"grad_norm": 1.5550422668457031,
|
| 539 |
+
"learning_rate": 4.273956202923131e-06,
|
| 540 |
+
"loss": 0.0441,
|
| 541 |
+
"step": 18000
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 2.4242424242424243,
|
| 545 |
+
"eval_loss": 0.047826144844293594,
|
| 546 |
+
"eval_runtime": 16.706,
|
| 547 |
+
"eval_samples_per_second": 748.595,
|
| 548 |
+
"eval_steps_per_second": 93.619,
|
| 549 |
+
"step": 18000
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 2.4915824915824913,
|
| 553 |
+
"grad_norm": 0.836184561252594,
|
| 554 |
+
"learning_rate": 3.776126103656408e-06,
|
| 555 |
+
"loss": 0.0423,
|
| 556 |
+
"step": 18500
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 2.4915824915824913,
|
| 560 |
+
"eval_loss": 0.04859430342912674,
|
| 561 |
+
"eval_runtime": 16.8726,
|
| 562 |
+
"eval_samples_per_second": 741.2,
|
| 563 |
+
"eval_steps_per_second": 92.694,
|
| 564 |
+
"step": 18500
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 2.558922558922559,
|
| 568 |
+
"grad_norm": 1.5994545221328735,
|
| 569 |
+
"learning_rate": 3.277298348880132e-06,
|
| 570 |
+
"loss": 0.0408,
|
| 571 |
+
"step": 19000
|
| 572 |
+
},
|
| 573 |
+
{
|
| 574 |
+
"epoch": 2.558922558922559,
|
| 575 |
+
"eval_loss": 0.048782531172037125,
|
| 576 |
+
"eval_runtime": 16.4855,
|
| 577 |
+
"eval_samples_per_second": 758.606,
|
| 578 |
+
"eval_steps_per_second": 94.871,
|
| 579 |
+
"step": 19000
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 2.6262626262626263,
|
| 583 |
+
"grad_norm": 1.1767594814300537,
|
| 584 |
+
"learning_rate": 2.778470594103856e-06,
|
| 585 |
+
"loss": 0.0396,
|
| 586 |
+
"step": 19500
|
| 587 |
+
},
|
| 588 |
+
{
|
| 589 |
+
"epoch": 2.6262626262626263,
|
| 590 |
+
"eval_loss": 0.04762514308094978,
|
| 591 |
+
"eval_runtime": 16.87,
|
| 592 |
+
"eval_samples_per_second": 741.315,
|
| 593 |
+
"eval_steps_per_second": 92.709,
|
| 594 |
+
"step": 19500
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 2.6936026936026938,
|
| 598 |
+
"grad_norm": 0.5949750542640686,
|
| 599 |
+
"learning_rate": 2.2796428393275805e-06,
|
| 600 |
+
"loss": 0.0424,
|
| 601 |
+
"step": 20000
|
| 602 |
+
},
|
| 603 |
+
{
|
| 604 |
+
"epoch": 2.6936026936026938,
|
| 605 |
+
"eval_loss": 0.04687490314245224,
|
| 606 |
+
"eval_runtime": 16.6716,
|
| 607 |
+
"eval_samples_per_second": 750.136,
|
| 608 |
+
"eval_steps_per_second": 93.812,
|
| 609 |
+
"step": 20000
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 2.760942760942761,
|
| 613 |
+
"grad_norm": 1.3800585269927979,
|
| 614 |
+
"learning_rate": 1.7808150845513046e-06,
|
| 615 |
+
"loss": 0.0401,
|
| 616 |
+
"step": 20500
|
| 617 |
+
},
|
| 618 |
+
{
|
| 619 |
+
"epoch": 2.760942760942761,
|
| 620 |
+
"eval_loss": 0.04696694761514664,
|
| 621 |
+
"eval_runtime": 16.9129,
|
| 622 |
+
"eval_samples_per_second": 739.438,
|
| 623 |
+
"eval_steps_per_second": 92.474,
|
| 624 |
+
"step": 20500
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"epoch": 2.8282828282828283,
|
| 628 |
+
"grad_norm": 0.3980063498020172,
|
| 629 |
+
"learning_rate": 1.2819873297750289e-06,
|
| 630 |
+
"loss": 0.0394,
|
| 631 |
+
"step": 21000
|
| 632 |
+
},
|
| 633 |
+
{
|
| 634 |
+
"epoch": 2.8282828282828283,
|
| 635 |
+
"eval_loss": 0.04716961458325386,
|
| 636 |
+
"eval_runtime": 16.3858,
|
| 637 |
+
"eval_samples_per_second": 763.221,
|
| 638 |
+
"eval_steps_per_second": 95.448,
|
| 639 |
+
"step": 21000
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 2.8956228956228958,
|
| 643 |
+
"grad_norm": 0.5946763753890991,
|
| 644 |
+
"learning_rate": 7.83159574998753e-07,
|
| 645 |
+
"loss": 0.0402,
|
| 646 |
+
"step": 21500
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 2.8956228956228958,
|
| 650 |
+
"eval_loss": 0.047023624181747437,
|
| 651 |
+
"eval_runtime": 16.6868,
|
| 652 |
+
"eval_samples_per_second": 749.457,
|
| 653 |
+
"eval_steps_per_second": 93.727,
|
| 654 |
+
"step": 21500
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 2.962962962962963,
|
| 658 |
+
"grad_norm": 0.1639704555273056,
|
| 659 |
+
"learning_rate": 2.843318202224772e-07,
|
| 660 |
+
"loss": 0.0404,
|
| 661 |
+
"step": 22000
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 2.962962962962963,
|
| 665 |
+
"eval_loss": 0.04673506319522858,
|
| 666 |
+
"eval_runtime": 16.8589,
|
| 667 |
+
"eval_samples_per_second": 741.804,
|
| 668 |
+
"eval_steps_per_second": 92.77,
|
| 669 |
+
"step": 22000
|
| 670 |
+
}
|
| 671 |
+
],
|
| 672 |
+
"logging_steps": 500,
|
| 673 |
+
"max_steps": 22275,
|
| 674 |
+
"num_input_tokens_seen": 0,
|
| 675 |
+
"num_train_epochs": 3,
|
| 676 |
+
"save_steps": 500,
|
| 677 |
+
"stateful_callbacks": {
|
| 678 |
+
"TrainerControl": {
|
| 679 |
+
"args": {
|
| 680 |
+
"should_epoch_stop": false,
|
| 681 |
+
"should_evaluate": false,
|
| 682 |
+
"should_log": false,
|
| 683 |
+
"should_save": true,
|
| 684 |
+
"should_training_stop": false
|
| 685 |
+
},
|
| 686 |
+
"attributes": {}
|
| 687 |
+
}
|
| 688 |
+
},
|
| 689 |
+
"total_flos": 2.910626095774925e+17,
|
| 690 |
+
"train_batch_size": 8,
|
| 691 |
+
"trial_name": null,
|
| 692 |
+
"trial_params": null
|
| 693 |
+
}
|
checkpoint-22000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:550c16ecf4d366c457abc0c5a07d6736a92a7b0602d6f987938f2b75b0b88ed4
|
| 3 |
+
size 5240
|
checkpoint-22000/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
config.json
ADDED
|
@@ -0,0 +1,75 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "facebook/bart-base",
|
| 3 |
+
"activation_dropout": 0.1,
|
| 4 |
+
"activation_function": "gelu",
|
| 5 |
+
"add_bias_logits": false,
|
| 6 |
+
"add_final_layer_norm": false,
|
| 7 |
+
"architectures": [
|
| 8 |
+
"BartForConditionalGeneration"
|
| 9 |
+
],
|
| 10 |
+
"attention_dropout": 0.1,
|
| 11 |
+
"bos_token_id": 0,
|
| 12 |
+
"classif_dropout": 0.1,
|
| 13 |
+
"classifier_dropout": 0.0,
|
| 14 |
+
"d_model": 768,
|
| 15 |
+
"decoder_attention_heads": 12,
|
| 16 |
+
"decoder_ffn_dim": 3072,
|
| 17 |
+
"decoder_layerdrop": 0.0,
|
| 18 |
+
"decoder_layers": 6,
|
| 19 |
+
"decoder_start_token_id": 2,
|
| 20 |
+
"dropout": 0.1,
|
| 21 |
+
"early_stopping": true,
|
| 22 |
+
"encoder_attention_heads": 12,
|
| 23 |
+
"encoder_ffn_dim": 3072,
|
| 24 |
+
"encoder_layerdrop": 0.0,
|
| 25 |
+
"encoder_layers": 6,
|
| 26 |
+
"eos_token_id": 2,
|
| 27 |
+
"forced_bos_token_id": 0,
|
| 28 |
+
"forced_eos_token_id": 2,
|
| 29 |
+
"gradient_checkpointing": false,
|
| 30 |
+
"id2label": {
|
| 31 |
+
"0": "LABEL_0",
|
| 32 |
+
"1": "LABEL_1",
|
| 33 |
+
"2": "LABEL_2"
|
| 34 |
+
},
|
| 35 |
+
"init_std": 0.02,
|
| 36 |
+
"is_encoder_decoder": true,
|
| 37 |
+
"label2id": {
|
| 38 |
+
"LABEL_0": 0,
|
| 39 |
+
"LABEL_1": 1,
|
| 40 |
+
"LABEL_2": 2
|
| 41 |
+
},
|
| 42 |
+
"max_position_embeddings": 1024,
|
| 43 |
+
"model_type": "bart",
|
| 44 |
+
"no_repeat_ngram_size": 3,
|
| 45 |
+
"normalize_before": false,
|
| 46 |
+
"normalize_embedding": true,
|
| 47 |
+
"num_beams": 4,
|
| 48 |
+
"num_hidden_layers": 6,
|
| 49 |
+
"pad_token_id": 1,
|
| 50 |
+
"scale_embedding": false,
|
| 51 |
+
"task_specific_params": {
|
| 52 |
+
"summarization": {
|
| 53 |
+
"length_penalty": 1.0,
|
| 54 |
+
"max_length": 128,
|
| 55 |
+
"min_length": 12,
|
| 56 |
+
"num_beams": 4
|
| 57 |
+
},
|
| 58 |
+
"summarization_cnn": {
|
| 59 |
+
"length_penalty": 2.0,
|
| 60 |
+
"max_length": 142,
|
| 61 |
+
"min_length": 56,
|
| 62 |
+
"num_beams": 4
|
| 63 |
+
},
|
| 64 |
+
"summarization_xsum": {
|
| 65 |
+
"length_penalty": 1.0,
|
| 66 |
+
"max_length": 62,
|
| 67 |
+
"min_length": 11,
|
| 68 |
+
"num_beams": 6
|
| 69 |
+
}
|
| 70 |
+
},
|
| 71 |
+
"torch_dtype": "float32",
|
| 72 |
+
"transformers_version": "4.44.1",
|
| 73 |
+
"use_cache": true,
|
| 74 |
+
"vocab_size": 50265
|
| 75 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 0,
|
| 4 |
+
"decoder_start_token_id": 2,
|
| 5 |
+
"early_stopping": true,
|
| 6 |
+
"eos_token_id": 2,
|
| 7 |
+
"forced_bos_token_id": 0,
|
| 8 |
+
"forced_eos_token_id": 2,
|
| 9 |
+
"no_repeat_ngram_size": 3,
|
| 10 |
+
"num_beams": 4,
|
| 11 |
+
"pad_token_id": 1,
|
| 12 |
+
"transformers_version": "4.44.1"
|
| 13 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:10e203555fb675c210bdc97d850733c2063293e738eb3a476f075b2e79939573
|
| 3 |
+
size 557912620
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<s>",
|
| 3 |
+
"cls_token": "<s>",
|
| 4 |
+
"eos_token": "</s>",
|
| 5 |
+
"mask_token": {
|
| 6 |
+
"content": "<mask>",
|
| 7 |
+
"lstrip": true,
|
| 8 |
+
"normalized": true,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false
|
| 11 |
+
},
|
| 12 |
+
"pad_token": "<pad>",
|
| 13 |
+
"sep_token": "</s>",
|
| 14 |
+
"unk_token": "<unk>"
|
| 15 |
+
}
|
test_results.csv
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"0": {
|
| 5 |
+
"content": "<s>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": true,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"1": {
|
| 13 |
+
"content": "<pad>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": true,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
},
|
| 20 |
+
"2": {
|
| 21 |
+
"content": "</s>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": true,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": true
|
| 27 |
+
},
|
| 28 |
+
"3": {
|
| 29 |
+
"content": "<unk>",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": true,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false,
|
| 34 |
+
"special": true
|
| 35 |
+
},
|
| 36 |
+
"50264": {
|
| 37 |
+
"content": "<mask>",
|
| 38 |
+
"lstrip": true,
|
| 39 |
+
"normalized": true,
|
| 40 |
+
"rstrip": false,
|
| 41 |
+
"single_word": false,
|
| 42 |
+
"special": true
|
| 43 |
+
}
|
| 44 |
+
},
|
| 45 |
+
"bos_token": "<s>",
|
| 46 |
+
"clean_up_tokenization_spaces": true,
|
| 47 |
+
"cls_token": "<s>",
|
| 48 |
+
"eos_token": "</s>",
|
| 49 |
+
"errors": "replace",
|
| 50 |
+
"mask_token": "<mask>",
|
| 51 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 52 |
+
"pad_token": "<pad>",
|
| 53 |
+
"sep_token": "</s>",
|
| 54 |
+
"tokenizer_class": "BartTokenizer",
|
| 55 |
+
"trim_offsets": true,
|
| 56 |
+
"unk_token": "<unk>"
|
| 57 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:550c16ecf4d366c457abc0c5a07d6736a92a7b0602d6f987938f2b75b0b88ed4
|
| 3 |
+
size 5240
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|