Training in progress, epoch 26, checkpoint
Browse files- checkpoint-2106/config.json +57 -0
- checkpoint-2106/merges.txt +0 -0
- checkpoint-2106/model.safetensors +3 -0
- checkpoint-2106/optimizer.pt +3 -0
- checkpoint-2106/rng_state.pth +3 -0
- checkpoint-2106/scheduler.pt +3 -0
- checkpoint-2106/special_tokens_map.json +15 -0
- checkpoint-2106/tokenizer.json +0 -0
- checkpoint-2106/tokenizer_config.json +57 -0
- checkpoint-2106/trainer_state.json +1219 -0
- checkpoint-2106/training_args.bin +3 -0
- checkpoint-2106/vocab.json +0 -0
checkpoint-2106/config.json
ADDED
|
@@ -0,0 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "allenai/longformer-base-4096",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"LongformerForTokenClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_mode": "longformer",
|
| 7 |
+
"attention_probs_dropout_prob": 0.1,
|
| 8 |
+
"attention_window": [
|
| 9 |
+
700,
|
| 10 |
+
700,
|
| 11 |
+
700,
|
| 12 |
+
700,
|
| 13 |
+
700,
|
| 14 |
+
700,
|
| 15 |
+
700,
|
| 16 |
+
700,
|
| 17 |
+
700,
|
| 18 |
+
700,
|
| 19 |
+
700,
|
| 20 |
+
700
|
| 21 |
+
],
|
| 22 |
+
"bos_token_id": 0,
|
| 23 |
+
"eos_token_id": 2,
|
| 24 |
+
"gradient_checkpointing": false,
|
| 25 |
+
"hidden_act": "gelu",
|
| 26 |
+
"hidden_dropout_prob": 0.1,
|
| 27 |
+
"hidden_size": 768,
|
| 28 |
+
"id2label": {
|
| 29 |
+
"0": "O",
|
| 30 |
+
"1": "X_placeholder_X",
|
| 31 |
+
"2": "MajorClaim",
|
| 32 |
+
"3": "Claim",
|
| 33 |
+
"4": "Premise"
|
| 34 |
+
},
|
| 35 |
+
"ignore_attention_mask": false,
|
| 36 |
+
"initializer_range": 0.02,
|
| 37 |
+
"intermediate_size": 3072,
|
| 38 |
+
"label2id": {
|
| 39 |
+
"Claim": 3,
|
| 40 |
+
"MajorClaim": 2,
|
| 41 |
+
"O": 0,
|
| 42 |
+
"Premise": 4,
|
| 43 |
+
"X_placeholder_X": 1
|
| 44 |
+
},
|
| 45 |
+
"layer_norm_eps": 1e-05,
|
| 46 |
+
"max_position_embeddings": 4098,
|
| 47 |
+
"model_type": "longformer",
|
| 48 |
+
"num_attention_heads": 12,
|
| 49 |
+
"num_hidden_layers": 12,
|
| 50 |
+
"onnx_export": false,
|
| 51 |
+
"pad_token_id": 1,
|
| 52 |
+
"sep_token_id": 2,
|
| 53 |
+
"torch_dtype": "float32",
|
| 54 |
+
"transformers_version": "4.38.2",
|
| 55 |
+
"type_vocab_size": 1,
|
| 56 |
+
"vocab_size": 50265
|
| 57 |
+
}
|
checkpoint-2106/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-2106/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a096e1cf3fb40b0ddae71dafc27d4a78583ef941b44607c02bf436000bfd7472
|
| 3 |
+
size 592324828
|
checkpoint-2106/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:80f4c5b45acd388b55e1e8e891e053a904bbf86a696388884e0f488b9bde534c
|
| 3 |
+
size 1014657786
|
checkpoint-2106/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:164e69b2c55b65211871f7f6a24d516925a9888b1d257795ff838d2a6eb1c882
|
| 3 |
+
size 14244
|
checkpoint-2106/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:262d54542665a80a932bf6af44de28766d1769b22664ebec77c9cf1959ca13ab
|
| 3 |
+
size 1064
|
checkpoint-2106/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": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false
|
| 11 |
+
},
|
| 12 |
+
"pad_token": "<pad>",
|
| 13 |
+
"sep_token": "</s>",
|
| 14 |
+
"unk_token": "<unk>"
|
| 15 |
+
}
|
checkpoint-2106/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-2106/tokenizer_config.json
ADDED
|
@@ -0,0 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": true,
|
| 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": false,
|
| 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": 4096,
|
| 52 |
+
"pad_token": "<pad>",
|
| 53 |
+
"sep_token": "</s>",
|
| 54 |
+
"tokenizer_class": "LongformerTokenizer",
|
| 55 |
+
"trim_offsets": true,
|
| 56 |
+
"unk_token": "<unk>"
|
| 57 |
+
}
|
checkpoint-2106/trainer_state.json
ADDED
|
@@ -0,0 +1,1219 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 26.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 2106,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 1.0,
|
| 13 |
+
"eval_Claim": {
|
| 14 |
+
"f1-score": 0.44734338904742493,
|
| 15 |
+
"precision": 0.5477537437603993,
|
| 16 |
+
"recall": 0.3780431786862655,
|
| 17 |
+
"support": 4354.0
|
| 18 |
+
},
|
| 19 |
+
"eval_MajorClaim": {
|
| 20 |
+
"f1-score": 0.6504965622612681,
|
| 21 |
+
"precision": 0.5898856944925528,
|
| 22 |
+
"recall": 0.7249893571732652,
|
| 23 |
+
"support": 2349.0
|
| 24 |
+
},
|
| 25 |
+
"eval_O": {
|
| 26 |
+
"f1-score": 0.8859784283513097,
|
| 27 |
+
"precision": 0.8689081979599547,
|
| 28 |
+
"recall": 0.9037328094302554,
|
| 29 |
+
"support": 10180.0
|
| 30 |
+
},
|
| 31 |
+
"eval_Premise": {
|
| 32 |
+
"f1-score": 0.8720120805863504,
|
| 33 |
+
"precision": 0.859258183929738,
|
| 34 |
+
"recall": 0.8851502916105877,
|
| 35 |
+
"support": 13374.0
|
| 36 |
+
},
|
| 37 |
+
"eval_accuracy": 0.8059953068711373,
|
| 38 |
+
"eval_loss": 0.47828415036201477,
|
| 39 |
+
"eval_macro avg": {
|
| 40 |
+
"f1-score": 0.7139576150615883,
|
| 41 |
+
"precision": 0.7164514550356611,
|
| 42 |
+
"recall": 0.7229789092250934,
|
| 43 |
+
"support": 30257.0
|
| 44 |
+
},
|
| 45 |
+
"eval_runtime": 4.8422,
|
| 46 |
+
"eval_samples_per_second": 16.728,
|
| 47 |
+
"eval_steps_per_second": 2.272,
|
| 48 |
+
"eval_weighted avg": {
|
| 49 |
+
"f1-score": 0.7984036588902531,
|
| 50 |
+
"precision": 0.7967665566250599,
|
| 51 |
+
"recall": 0.8059953068711373,
|
| 52 |
+
"support": 30257.0
|
| 53 |
+
},
|
| 54 |
+
"step": 81
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 2.0,
|
| 58 |
+
"eval_Claim": {
|
| 59 |
+
"f1-score": 0.5787561000934482,
|
| 60 |
+
"precision": 0.5281409891984082,
|
| 61 |
+
"recall": 0.6401010564997703,
|
| 62 |
+
"support": 4354.0
|
| 63 |
+
},
|
| 64 |
+
"eval_MajorClaim": {
|
| 65 |
+
"f1-score": 0.7702650787552824,
|
| 66 |
+
"precision": 0.7017850892544627,
|
| 67 |
+
"recall": 0.8535547041294168,
|
| 68 |
+
"support": 2349.0
|
| 69 |
+
},
|
| 70 |
+
"eval_O": {
|
| 71 |
+
"f1-score": 0.9095337508698677,
|
| 72 |
+
"precision": 0.9206077681626081,
|
| 73 |
+
"recall": 0.8987229862475442,
|
| 74 |
+
"support": 10180.0
|
| 75 |
+
},
|
| 76 |
+
"eval_Premise": {
|
| 77 |
+
"f1-score": 0.8736648538675224,
|
| 78 |
+
"precision": 0.9162905211325401,
|
| 79 |
+
"recall": 0.8348287722446538,
|
| 80 |
+
"support": 13374.0
|
| 81 |
+
},
|
| 82 |
+
"eval_accuracy": 0.8297584030141786,
|
| 83 |
+
"eval_loss": 0.4241589605808258,
|
| 84 |
+
"eval_macro avg": {
|
| 85 |
+
"f1-score": 0.7830549458965301,
|
| 86 |
+
"precision": 0.7667060919370048,
|
| 87 |
+
"recall": 0.8068018797803463,
|
| 88 |
+
"support": 30257.0
|
| 89 |
+
},
|
| 90 |
+
"eval_runtime": 4.8636,
|
| 91 |
+
"eval_samples_per_second": 16.654,
|
| 92 |
+
"eval_steps_per_second": 2.262,
|
| 93 |
+
"eval_weighted avg": {
|
| 94 |
+
"f1-score": 0.8352680063880269,
|
| 95 |
+
"precision": 0.8452350051608073,
|
| 96 |
+
"recall": 0.8297584030141786,
|
| 97 |
+
"support": 30257.0
|
| 98 |
+
},
|
| 99 |
+
"step": 162
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 3.0,
|
| 103 |
+
"eval_Claim": {
|
| 104 |
+
"f1-score": 0.5728465083303793,
|
| 105 |
+
"precision": 0.5899245558530056,
|
| 106 |
+
"recall": 0.5567294441892513,
|
| 107 |
+
"support": 4354.0
|
| 108 |
+
},
|
| 109 |
+
"eval_MajorClaim": {
|
| 110 |
+
"f1-score": 0.7862876979822088,
|
| 111 |
+
"precision": 0.8017699115044248,
|
| 112 |
+
"recall": 0.7713920817369093,
|
| 113 |
+
"support": 2349.0
|
| 114 |
+
},
|
| 115 |
+
"eval_O": {
|
| 116 |
+
"f1-score": 0.914532821534425,
|
| 117 |
+
"precision": 0.9048168445341794,
|
| 118 |
+
"recall": 0.9244597249508841,
|
| 119 |
+
"support": 10180.0
|
| 120 |
+
},
|
| 121 |
+
"eval_Premise": {
|
| 122 |
+
"f1-score": 0.8880533114924986,
|
| 123 |
+
"precision": 0.8843330614665975,
|
| 124 |
+
"recall": 0.8918049947659639,
|
| 125 |
+
"support": 13374.0
|
| 126 |
+
},
|
| 127 |
+
"eval_accuracy": 0.8452258981392735,
|
| 128 |
+
"eval_loss": 0.41067537665367126,
|
| 129 |
+
"eval_macro avg": {
|
| 130 |
+
"f1-score": 0.7904300848348779,
|
| 131 |
+
"precision": 0.7952110933395518,
|
| 132 |
+
"recall": 0.7860965614107521,
|
| 133 |
+
"support": 30257.0
|
| 134 |
+
},
|
| 135 |
+
"eval_runtime": 4.8684,
|
| 136 |
+
"eval_samples_per_second": 16.638,
|
| 137 |
+
"eval_steps_per_second": 2.259,
|
| 138 |
+
"eval_weighted avg": {
|
| 139 |
+
"f1-score": 0.8437033615676307,
|
| 140 |
+
"precision": 0.8424495118392472,
|
| 141 |
+
"recall": 0.8452258981392735,
|
| 142 |
+
"support": 30257.0
|
| 143 |
+
},
|
| 144 |
+
"step": 243
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 4.0,
|
| 148 |
+
"eval_Claim": {
|
| 149 |
+
"f1-score": 0.5865384615384616,
|
| 150 |
+
"precision": 0.5714596949891068,
|
| 151 |
+
"recall": 0.6024345429490124,
|
| 152 |
+
"support": 4354.0
|
| 153 |
+
},
|
| 154 |
+
"eval_MajorClaim": {
|
| 155 |
+
"f1-score": 0.7783630470016208,
|
| 156 |
+
"precision": 0.7425589485890993,
|
| 157 |
+
"recall": 0.8177948063005535,
|
| 158 |
+
"support": 2349.0
|
| 159 |
+
},
|
| 160 |
+
"eval_O": {
|
| 161 |
+
"f1-score": 0.9108591535529275,
|
| 162 |
+
"precision": 0.9063411787589963,
|
| 163 |
+
"recall": 0.9154223968565816,
|
| 164 |
+
"support": 10180.0
|
| 165 |
+
},
|
| 166 |
+
"eval_Premise": {
|
| 167 |
+
"f1-score": 0.8868256151612411,
|
| 168 |
+
"precision": 0.9067823097358962,
|
| 169 |
+
"recall": 0.8677284282937042,
|
| 170 |
+
"support": 13374.0
|
| 171 |
+
},
|
| 172 |
+
"eval_accuracy": 0.8417225765938461,
|
| 173 |
+
"eval_loss": 0.4545813202857971,
|
| 174 |
+
"eval_macro avg": {
|
| 175 |
+
"f1-score": 0.7906465693135627,
|
| 176 |
+
"precision": 0.7817855330182747,
|
| 177 |
+
"recall": 0.8008450435999629,
|
| 178 |
+
"support": 30257.0
|
| 179 |
+
},
|
| 180 |
+
"eval_runtime": 4.9112,
|
| 181 |
+
"eval_samples_per_second": 16.493,
|
| 182 |
+
"eval_steps_per_second": 2.24,
|
| 183 |
+
"eval_weighted avg": {
|
| 184 |
+
"f1-score": 0.8432797441676475,
|
| 185 |
+
"precision": 0.8456313015960876,
|
| 186 |
+
"recall": 0.8417225765938461,
|
| 187 |
+
"support": 30257.0
|
| 188 |
+
},
|
| 189 |
+
"step": 324
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 5.0,
|
| 193 |
+
"eval_Claim": {
|
| 194 |
+
"f1-score": 0.597399608790703,
|
| 195 |
+
"precision": 0.5985704403965875,
|
| 196 |
+
"recall": 0.5962333486449242,
|
| 197 |
+
"support": 4354.0
|
| 198 |
+
},
|
| 199 |
+
"eval_MajorClaim": {
|
| 200 |
+
"f1-score": 0.7933532168726033,
|
| 201 |
+
"precision": 0.7940298507462686,
|
| 202 |
+
"recall": 0.7926777352064709,
|
| 203 |
+
"support": 2349.0
|
| 204 |
+
},
|
| 205 |
+
"eval_O": {
|
| 206 |
+
"f1-score": 0.9101112629318758,
|
| 207 |
+
"precision": 0.9042862684251358,
|
| 208 |
+
"recall": 0.9160117878192534,
|
| 209 |
+
"support": 10180.0
|
| 210 |
+
},
|
| 211 |
+
"eval_Premise": {
|
| 212 |
+
"f1-score": 0.8923677591320345,
|
| 213 |
+
"precision": 0.8961019377214808,
|
| 214 |
+
"recall": 0.8886645730521908,
|
| 215 |
+
"support": 13374.0
|
| 216 |
+
},
|
| 217 |
+
"eval_accuracy": 0.848332617245596,
|
| 218 |
+
"eval_loss": 0.48704993724823,
|
| 219 |
+
"eval_macro avg": {
|
| 220 |
+
"f1-score": 0.7983079619318041,
|
| 221 |
+
"precision": 0.7982471243223681,
|
| 222 |
+
"recall": 0.7983968611807098,
|
| 223 |
+
"support": 30257.0
|
| 224 |
+
},
|
| 225 |
+
"eval_runtime": 4.8769,
|
| 226 |
+
"eval_samples_per_second": 16.609,
|
| 227 |
+
"eval_steps_per_second": 2.256,
|
| 228 |
+
"eval_weighted avg": {
|
| 229 |
+
"f1-score": 0.8482045037639816,
|
| 230 |
+
"precision": 0.8481162489521332,
|
| 231 |
+
"recall": 0.848332617245596,
|
| 232 |
+
"support": 30257.0
|
| 233 |
+
},
|
| 234 |
+
"step": 405
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 6.0,
|
| 238 |
+
"eval_Claim": {
|
| 239 |
+
"f1-score": 0.6060809300245921,
|
| 240 |
+
"precision": 0.5903745644599303,
|
| 241 |
+
"recall": 0.6226458429030777,
|
| 242 |
+
"support": 4354.0
|
| 243 |
+
},
|
| 244 |
+
"eval_MajorClaim": {
|
| 245 |
+
"f1-score": 0.7858529221479404,
|
| 246 |
+
"precision": 0.7963286713286714,
|
| 247 |
+
"recall": 0.7756492124308216,
|
| 248 |
+
"support": 2349.0
|
| 249 |
+
},
|
| 250 |
+
"eval_O": {
|
| 251 |
+
"f1-score": 0.9135615470059578,
|
| 252 |
+
"precision": 0.9398504051527115,
|
| 253 |
+
"recall": 0.8887033398821218,
|
| 254 |
+
"support": 10180.0
|
| 255 |
+
},
|
| 256 |
+
"eval_Premise": {
|
| 257 |
+
"f1-score": 0.895557603686636,
|
| 258 |
+
"precision": 0.88328121591157,
|
| 259 |
+
"recall": 0.908180050844923,
|
| 260 |
+
"support": 13374.0
|
| 261 |
+
},
|
| 262 |
+
"eval_accuracy": 0.8502495290346036,
|
| 263 |
+
"eval_loss": 0.5423789024353027,
|
| 264 |
+
"eval_macro avg": {
|
| 265 |
+
"f1-score": 0.8002632507162816,
|
| 266 |
+
"precision": 0.8024587142132208,
|
| 267 |
+
"recall": 0.7987946115152361,
|
| 268 |
+
"support": 30257.0
|
| 269 |
+
},
|
| 270 |
+
"eval_runtime": 4.867,
|
| 271 |
+
"eval_samples_per_second": 16.643,
|
| 272 |
+
"eval_steps_per_second": 2.26,
|
| 273 |
+
"eval_weighted avg": {
|
| 274 |
+
"f1-score": 0.8514422719925407,
|
| 275 |
+
"precision": 0.8534139871324166,
|
| 276 |
+
"recall": 0.8502495290346036,
|
| 277 |
+
"support": 30257.0
|
| 278 |
+
},
|
| 279 |
+
"step": 486
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 6.17,
|
| 283 |
+
"grad_norm": 4.494631767272949,
|
| 284 |
+
"learning_rate": 1.7530864197530865e-05,
|
| 285 |
+
"loss": 0.35,
|
| 286 |
+
"step": 500
|
| 287 |
+
},
|
| 288 |
+
{
|
| 289 |
+
"epoch": 7.0,
|
| 290 |
+
"eval_Claim": {
|
| 291 |
+
"f1-score": 0.6040515653775324,
|
| 292 |
+
"precision": 0.6054453161052146,
|
| 293 |
+
"recall": 0.6026642168121268,
|
| 294 |
+
"support": 4354.0
|
| 295 |
+
},
|
| 296 |
+
"eval_MajorClaim": {
|
| 297 |
+
"f1-score": 0.8052777186635455,
|
| 298 |
+
"precision": 0.8051063829787234,
|
| 299 |
+
"recall": 0.8054491272882077,
|
| 300 |
+
"support": 2349.0
|
| 301 |
+
},
|
| 302 |
+
"eval_O": {
|
| 303 |
+
"f1-score": 0.9184720354599332,
|
| 304 |
+
"precision": 0.9315082331548641,
|
| 305 |
+
"recall": 0.9057956777996071,
|
| 306 |
+
"support": 10180.0
|
| 307 |
+
},
|
| 308 |
+
"eval_Premise": {
|
| 309 |
+
"f1-score": 0.8908606921029282,
|
| 310 |
+
"precision": 0.8810881965774463,
|
| 311 |
+
"recall": 0.9008524001794527,
|
| 312 |
+
"support": 13374.0
|
| 313 |
+
},
|
| 314 |
+
"eval_accuracy": 0.8521994910268698,
|
| 315 |
+
"eval_loss": 0.5764245986938477,
|
| 316 |
+
"eval_macro avg": {
|
| 317 |
+
"f1-score": 0.8046655029009848,
|
| 318 |
+
"precision": 0.8057870322040621,
|
| 319 |
+
"recall": 0.8036903555198486,
|
| 320 |
+
"support": 30257.0
|
| 321 |
+
},
|
| 322 |
+
"eval_runtime": 4.8398,
|
| 323 |
+
"eval_samples_per_second": 16.736,
|
| 324 |
+
"eval_steps_per_second": 2.273,
|
| 325 |
+
"eval_weighted avg": {
|
| 326 |
+
"f1-score": 0.8522343290465387,
|
| 327 |
+
"precision": 0.8524880574571969,
|
| 328 |
+
"recall": 0.8521994910268698,
|
| 329 |
+
"support": 30257.0
|
| 330 |
+
},
|
| 331 |
+
"step": 567
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 8.0,
|
| 335 |
+
"eval_Claim": {
|
| 336 |
+
"f1-score": 0.597346719254213,
|
| 337 |
+
"precision": 0.6227261400448543,
|
| 338 |
+
"recall": 0.5739549839228296,
|
| 339 |
+
"support": 4354.0
|
| 340 |
+
},
|
| 341 |
+
"eval_MajorClaim": {
|
| 342 |
+
"f1-score": 0.8047001620745543,
|
| 343 |
+
"precision": 0.7676845767298028,
|
| 344 |
+
"recall": 0.8454661558109834,
|
| 345 |
+
"support": 2349.0
|
| 346 |
+
},
|
| 347 |
+
"eval_O": {
|
| 348 |
+
"f1-score": 0.9099175618286286,
|
| 349 |
+
"precision": 0.9258769700050838,
|
| 350 |
+
"recall": 0.8944990176817289,
|
| 351 |
+
"support": 10180.0
|
| 352 |
+
},
|
| 353 |
+
"eval_Premise": {
|
| 354 |
+
"f1-score": 0.8942491542873952,
|
| 355 |
+
"precision": 0.8797569092750688,
|
| 356 |
+
"recall": 0.9092268580828473,
|
| 357 |
+
"support": 13374.0
|
| 358 |
+
},
|
| 359 |
+
"eval_accuracy": 0.8510757841160723,
|
| 360 |
+
"eval_loss": 0.5954988598823547,
|
| 361 |
+
"eval_macro avg": {
|
| 362 |
+
"f1-score": 0.8015533993611977,
|
| 363 |
+
"precision": 0.7990111490137024,
|
| 364 |
+
"recall": 0.8057867538745973,
|
| 365 |
+
"support": 30257.0
|
| 366 |
+
},
|
| 367 |
+
"eval_runtime": 4.8609,
|
| 368 |
+
"eval_samples_per_second": 16.663,
|
| 369 |
+
"eval_steps_per_second": 2.263,
|
| 370 |
+
"eval_weighted avg": {
|
| 371 |
+
"f1-score": 0.8498442431569896,
|
| 372 |
+
"precision": 0.8495864475589161,
|
| 373 |
+
"recall": 0.8510757841160723,
|
| 374 |
+
"support": 30257.0
|
| 375 |
+
},
|
| 376 |
+
"step": 648
|
| 377 |
+
},
|
| 378 |
+
{
|
| 379 |
+
"epoch": 9.0,
|
| 380 |
+
"eval_Claim": {
|
| 381 |
+
"f1-score": 0.6049033474776048,
|
| 382 |
+
"precision": 0.6213075060532688,
|
| 383 |
+
"recall": 0.5893431327514929,
|
| 384 |
+
"support": 4354.0
|
| 385 |
+
},
|
| 386 |
+
"eval_MajorClaim": {
|
| 387 |
+
"f1-score": 0.823503227242377,
|
| 388 |
+
"precision": 0.8628731343283582,
|
| 389 |
+
"recall": 0.787569178373776,
|
| 390 |
+
"support": 2349.0
|
| 391 |
+
},
|
| 392 |
+
"eval_O": {
|
| 393 |
+
"f1-score": 0.9189658498938837,
|
| 394 |
+
"precision": 0.9027672479150872,
|
| 395 |
+
"recall": 0.9357563850687622,
|
| 396 |
+
"support": 10180.0
|
| 397 |
+
},
|
| 398 |
+
"eval_Premise": {
|
| 399 |
+
"f1-score": 0.8989367655288193,
|
| 400 |
+
"precision": 0.8970292606656243,
|
| 401 |
+
"recall": 0.9008524001794527,
|
| 402 |
+
"support": 13374.0
|
| 403 |
+
},
|
| 404 |
+
"eval_accuracy": 0.8589747826949136,
|
| 405 |
+
"eval_loss": 0.5689579844474792,
|
| 406 |
+
"eval_macro avg": {
|
| 407 |
+
"f1-score": 0.8115772975356712,
|
| 408 |
+
"precision": 0.8209942872405847,
|
| 409 |
+
"recall": 0.803380274093371,
|
| 410 |
+
"support": 30257.0
|
| 411 |
+
},
|
| 412 |
+
"eval_runtime": 4.8593,
|
| 413 |
+
"eval_samples_per_second": 16.669,
|
| 414 |
+
"eval_steps_per_second": 2.264,
|
| 415 |
+
"eval_weighted avg": {
|
| 416 |
+
"f1-score": 0.8575077142417292,
|
| 417 |
+
"precision": 0.8566315824374819,
|
| 418 |
+
"recall": 0.8589747826949136,
|
| 419 |
+
"support": 30257.0
|
| 420 |
+
},
|
| 421 |
+
"step": 729
|
| 422 |
+
},
|
| 423 |
+
{
|
| 424 |
+
"epoch": 10.0,
|
| 425 |
+
"eval_Claim": {
|
| 426 |
+
"f1-score": 0.60162224797219,
|
| 427 |
+
"precision": 0.6071094480823199,
|
| 428 |
+
"recall": 0.5962333486449242,
|
| 429 |
+
"support": 4354.0
|
| 430 |
+
},
|
| 431 |
+
"eval_MajorClaim": {
|
| 432 |
+
"f1-score": 0.8131676477000218,
|
| 433 |
+
"precision": 0.8333333333333334,
|
| 434 |
+
"recall": 0.7939548744146445,
|
| 435 |
+
"support": 2349.0
|
| 436 |
+
},
|
| 437 |
+
"eval_O": {
|
| 438 |
+
"f1-score": 0.9197247706422018,
|
| 439 |
+
"precision": 0.9338801134062373,
|
| 440 |
+
"recall": 0.905992141453831,
|
| 441 |
+
"support": 10180.0
|
| 442 |
+
},
|
| 443 |
+
"eval_Premise": {
|
| 444 |
+
"f1-score": 0.9008479864909512,
|
| 445 |
+
"precision": 0.884834499170693,
|
| 446 |
+
"recall": 0.9174517720951099,
|
| 447 |
+
"support": 13374.0
|
| 448 |
+
},
|
| 449 |
+
"eval_accuracy": 0.8577849753775986,
|
| 450 |
+
"eval_loss": 0.7088457942008972,
|
| 451 |
+
"eval_macro avg": {
|
| 452 |
+
"f1-score": 0.8088406632013413,
|
| 453 |
+
"precision": 0.8147893484981459,
|
| 454 |
+
"recall": 0.8034080341521274,
|
| 455 |
+
"support": 30257.0
|
| 456 |
+
},
|
| 457 |
+
"eval_runtime": 4.9043,
|
| 458 |
+
"eval_samples_per_second": 16.516,
|
| 459 |
+
"eval_steps_per_second": 2.243,
|
| 460 |
+
"eval_weighted avg": {
|
| 461 |
+
"f1-score": 0.8573332851434664,
|
| 462 |
+
"precision": 0.8573728619273148,
|
| 463 |
+
"recall": 0.8577849753775986,
|
| 464 |
+
"support": 30257.0
|
| 465 |
+
},
|
| 466 |
+
"step": 810
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 11.0,
|
| 470 |
+
"eval_Claim": {
|
| 471 |
+
"f1-score": 0.6253176253176252,
|
| 472 |
+
"precision": 0.6289498141263941,
|
| 473 |
+
"recall": 0.6217271474506201,
|
| 474 |
+
"support": 4354.0
|
| 475 |
+
},
|
| 476 |
+
"eval_MajorClaim": {
|
| 477 |
+
"f1-score": 0.7947071414672116,
|
| 478 |
+
"precision": 0.7318996415770609,
|
| 479 |
+
"recall": 0.8693060876968923,
|
| 480 |
+
"support": 2349.0
|
| 481 |
+
},
|
| 482 |
+
"eval_O": {
|
| 483 |
+
"f1-score": 0.9110249527786062,
|
| 484 |
+
"precision": 0.9221171261823304,
|
| 485 |
+
"recall": 0.900196463654224,
|
| 486 |
+
"support": 10180.0
|
| 487 |
+
},
|
| 488 |
+
"eval_Premise": {
|
| 489 |
+
"f1-score": 0.8996578818752584,
|
| 490 |
+
"precision": 0.9047258979206049,
|
| 491 |
+
"recall": 0.8946463286974727,
|
| 492 |
+
"support": 13374.0
|
| 493 |
+
},
|
| 494 |
+
"eval_accuracy": 0.8552731599299336,
|
| 495 |
+
"eval_loss": 0.7312190532684326,
|
| 496 |
+
"eval_macro avg": {
|
| 497 |
+
"f1-score": 0.8076769003596753,
|
| 498 |
+
"precision": 0.7969231199515976,
|
| 499 |
+
"recall": 0.8214690068748023,
|
| 500 |
+
"support": 30257.0
|
| 501 |
+
},
|
| 502 |
+
"eval_runtime": 4.9029,
|
| 503 |
+
"eval_samples_per_second": 16.521,
|
| 504 |
+
"eval_steps_per_second": 2.244,
|
| 505 |
+
"eval_weighted avg": {
|
| 506 |
+
"f1-score": 0.8558567785115953,
|
| 507 |
+
"precision": 0.857475501606145,
|
| 508 |
+
"recall": 0.8552731599299336,
|
| 509 |
+
"support": 30257.0
|
| 510 |
+
},
|
| 511 |
+
"step": 891
|
| 512 |
+
},
|
| 513 |
+
{
|
| 514 |
+
"epoch": 12.0,
|
| 515 |
+
"eval_Claim": {
|
| 516 |
+
"f1-score": 0.633677135241627,
|
| 517 |
+
"precision": 0.6395321637426901,
|
| 518 |
+
"recall": 0.6279283417547084,
|
| 519 |
+
"support": 4354.0
|
| 520 |
+
},
|
| 521 |
+
"eval_MajorClaim": {
|
| 522 |
+
"f1-score": 0.8290997764681975,
|
| 523 |
+
"precision": 0.7931570762052877,
|
| 524 |
+
"recall": 0.8684546615581098,
|
| 525 |
+
"support": 2349.0
|
| 526 |
+
},
|
| 527 |
+
"eval_O": {
|
| 528 |
+
"f1-score": 0.916678984971668,
|
| 529 |
+
"precision": 0.9196243203163619,
|
| 530 |
+
"recall": 0.9137524557956778,
|
| 531 |
+
"support": 10180.0
|
| 532 |
+
},
|
| 533 |
+
"eval_Premise": {
|
| 534 |
+
"f1-score": 0.9029209944129889,
|
| 535 |
+
"precision": 0.905603610379842,
|
| 536 |
+
"recall": 0.9002542246149244,
|
| 537 |
+
"support": 13374.0
|
| 538 |
+
},
|
| 539 |
+
"eval_accuracy": 0.8631391083055161,
|
| 540 |
+
"eval_loss": 0.7092207074165344,
|
| 541 |
+
"eval_macro avg": {
|
| 542 |
+
"f1-score": 0.8205942227736204,
|
| 543 |
+
"precision": 0.8144792926610454,
|
| 544 |
+
"recall": 0.8275974209308551,
|
| 545 |
+
"support": 30257.0
|
| 546 |
+
},
|
| 547 |
+
"eval_runtime": 4.8734,
|
| 548 |
+
"eval_samples_per_second": 16.621,
|
| 549 |
+
"eval_steps_per_second": 2.257,
|
| 550 |
+
"eval_weighted avg": {
|
| 551 |
+
"f1-score": 0.8630744313070275,
|
| 552 |
+
"precision": 0.8633032778855295,
|
| 553 |
+
"recall": 0.8631391083055161,
|
| 554 |
+
"support": 30257.0
|
| 555 |
+
},
|
| 556 |
+
"step": 972
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 12.35,
|
| 560 |
+
"grad_norm": 4.426708698272705,
|
| 561 |
+
"learning_rate": 1.506172839506173e-05,
|
| 562 |
+
"loss": 0.063,
|
| 563 |
+
"step": 1000
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 13.0,
|
| 567 |
+
"eval_Claim": {
|
| 568 |
+
"f1-score": 0.5936837143530521,
|
| 569 |
+
"precision": 0.6096321393998064,
|
| 570 |
+
"recall": 0.5785484611851172,
|
| 571 |
+
"support": 4354.0
|
| 572 |
+
},
|
| 573 |
+
"eval_MajorClaim": {
|
| 574 |
+
"f1-score": 0.8065005417118094,
|
| 575 |
+
"precision": 0.821270962047661,
|
| 576 |
+
"recall": 0.7922520221370796,
|
| 577 |
+
"support": 2349.0
|
| 578 |
+
},
|
| 579 |
+
"eval_O": {
|
| 580 |
+
"f1-score": 0.9133826964170352,
|
| 581 |
+
"precision": 0.9242683294780247,
|
| 582 |
+
"recall": 0.9027504911591355,
|
| 583 |
+
"support": 10180.0
|
| 584 |
+
},
|
| 585 |
+
"eval_Premise": {
|
| 586 |
+
"f1-score": 0.901282521069989,
|
| 587 |
+
"precision": 0.883730957171601,
|
| 588 |
+
"recall": 0.9195453865709585,
|
| 589 |
+
"support": 13374.0
|
| 590 |
+
},
|
| 591 |
+
"eval_accuracy": 0.854942657897346,
|
| 592 |
+
"eval_loss": 0.7807008624076843,
|
| 593 |
+
"eval_macro avg": {
|
| 594 |
+
"f1-score": 0.8037123683879714,
|
| 595 |
+
"precision": 0.8097255970242733,
|
| 596 |
+
"recall": 0.7982740902630727,
|
| 597 |
+
"support": 30257.0
|
| 598 |
+
},
|
| 599 |
+
"eval_runtime": 4.8517,
|
| 600 |
+
"eval_samples_per_second": 16.695,
|
| 601 |
+
"eval_steps_per_second": 2.267,
|
| 602 |
+
"eval_weighted avg": {
|
| 603 |
+
"f1-score": 0.8537315976828396,
|
| 604 |
+
"precision": 0.8530777420132861,
|
| 605 |
+
"recall": 0.854942657897346,
|
| 606 |
+
"support": 30257.0
|
| 607 |
+
},
|
| 608 |
+
"step": 1053
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 14.0,
|
| 612 |
+
"eval_Claim": {
|
| 613 |
+
"f1-score": 0.6335702820454024,
|
| 614 |
+
"precision": 0.632554945054945,
|
| 615 |
+
"recall": 0.6345888837850253,
|
| 616 |
+
"support": 4354.0
|
| 617 |
+
},
|
| 618 |
+
"eval_MajorClaim": {
|
| 619 |
+
"f1-score": 0.8183556405353729,
|
| 620 |
+
"precision": 0.816793893129771,
|
| 621 |
+
"recall": 0.8199233716475096,
|
| 622 |
+
"support": 2349.0
|
| 623 |
+
},
|
| 624 |
+
"eval_O": {
|
| 625 |
+
"f1-score": 0.9172396976347231,
|
| 626 |
+
"precision": 0.9107990314769976,
|
| 627 |
+
"recall": 0.9237721021611002,
|
| 628 |
+
"support": 10180.0
|
| 629 |
+
},
|
| 630 |
+
"eval_Premise": {
|
| 631 |
+
"f1-score": 0.8981941309255079,
|
| 632 |
+
"precision": 0.9039073148568832,
|
| 633 |
+
"recall": 0.8925527142216241,
|
| 634 |
+
"support": 13374.0
|
| 635 |
+
},
|
| 636 |
+
"eval_accuracy": 0.8602967908252636,
|
| 637 |
+
"eval_loss": 0.7879041433334351,
|
| 638 |
+
"eval_macro avg": {
|
| 639 |
+
"f1-score": 0.8168399377852517,
|
| 640 |
+
"precision": 0.8160137961296492,
|
| 641 |
+
"recall": 0.8177092679538147,
|
| 642 |
+
"support": 30257.0
|
| 643 |
+
},
|
| 644 |
+
"eval_runtime": 4.864,
|
| 645 |
+
"eval_samples_per_second": 16.653,
|
| 646 |
+
"eval_steps_per_second": 2.262,
|
| 647 |
+
"eval_weighted avg": {
|
| 648 |
+
"f1-score": 0.8603242501425289,
|
| 649 |
+
"precision": 0.8604152313535001,
|
| 650 |
+
"recall": 0.8602967908252636,
|
| 651 |
+
"support": 30257.0
|
| 652 |
+
},
|
| 653 |
+
"step": 1134
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 15.0,
|
| 657 |
+
"eval_Claim": {
|
| 658 |
+
"f1-score": 0.6212592513139547,
|
| 659 |
+
"precision": 0.5828134433487623,
|
| 660 |
+
"recall": 0.6651355075792375,
|
| 661 |
+
"support": 4354.0
|
| 662 |
+
},
|
| 663 |
+
"eval_MajorClaim": {
|
| 664 |
+
"f1-score": 0.7988422575976845,
|
| 665 |
+
"precision": 0.7765273311897106,
|
| 666 |
+
"recall": 0.822477650063857,
|
| 667 |
+
"support": 2349.0
|
| 668 |
+
},
|
| 669 |
+
"eval_O": {
|
| 670 |
+
"f1-score": 0.9143625765954267,
|
| 671 |
+
"precision": 0.9276255938542404,
|
| 672 |
+
"recall": 0.9014734774066797,
|
| 673 |
+
"support": 10180.0
|
| 674 |
+
},
|
| 675 |
+
"eval_Premise": {
|
| 676 |
+
"f1-score": 0.8928883984627678,
|
| 677 |
+
"precision": 0.9090416053304409,
|
| 678 |
+
"recall": 0.8772992373261552,
|
| 679 |
+
"support": 13374.0
|
| 680 |
+
},
|
| 681 |
+
"eval_accuracy": 0.8506461314737086,
|
| 682 |
+
"eval_loss": 0.8185116052627563,
|
| 683 |
+
"eval_macro avg": {
|
| 684 |
+
"f1-score": 0.8068381209924584,
|
| 685 |
+
"precision": 0.7990019934307886,
|
| 686 |
+
"recall": 0.8165964680939823,
|
| 687 |
+
"support": 30257.0
|
| 688 |
+
},
|
| 689 |
+
"eval_runtime": 4.8575,
|
| 690 |
+
"eval_samples_per_second": 16.675,
|
| 691 |
+
"eval_steps_per_second": 2.265,
|
| 692 |
+
"eval_weighted avg": {
|
| 693 |
+
"f1-score": 0.8537245501570023,
|
| 694 |
+
"precision": 0.8580620487302317,
|
| 695 |
+
"recall": 0.8506461314737086,
|
| 696 |
+
"support": 30257.0
|
| 697 |
+
},
|
| 698 |
+
"step": 1215
|
| 699 |
+
},
|
| 700 |
+
{
|
| 701 |
+
"epoch": 16.0,
|
| 702 |
+
"eval_Claim": {
|
| 703 |
+
"f1-score": 0.620457750298297,
|
| 704 |
+
"precision": 0.5878725590955807,
|
| 705 |
+
"recall": 0.6568672485071199,
|
| 706 |
+
"support": 4354.0
|
| 707 |
+
},
|
| 708 |
+
"eval_MajorClaim": {
|
| 709 |
+
"f1-score": 0.8217720482913852,
|
| 710 |
+
"precision": 0.7911741528762806,
|
| 711 |
+
"recall": 0.8548318433375904,
|
| 712 |
+
"support": 2349.0
|
| 713 |
+
},
|
| 714 |
+
"eval_O": {
|
| 715 |
+
"f1-score": 0.9171081176529942,
|
| 716 |
+
"precision": 0.9427445285758739,
|
| 717 |
+
"recall": 0.8928290766208251,
|
| 718 |
+
"support": 10180.0
|
| 719 |
+
},
|
| 720 |
+
"eval_Premise": {
|
| 721 |
+
"f1-score": 0.8952495580546884,
|
| 722 |
+
"precision": 0.900703852266707,
|
| 723 |
+
"recall": 0.8898609241812472,
|
| 724 |
+
"support": 13374.0
|
| 725 |
+
},
|
| 726 |
+
"eval_accuracy": 0.8546121558647586,
|
| 727 |
+
"eval_loss": 0.8933361768722534,
|
| 728 |
+
"eval_macro avg": {
|
| 729 |
+
"f1-score": 0.8136468685743412,
|
| 730 |
+
"precision": 0.8056237732036106,
|
| 731 |
+
"recall": 0.8235972731616956,
|
| 732 |
+
"support": 30257.0
|
| 733 |
+
},
|
| 734 |
+
"eval_runtime": 4.839,
|
| 735 |
+
"eval_samples_per_second": 16.739,
|
| 736 |
+
"eval_steps_per_second": 2.273,
|
| 737 |
+
"eval_weighted avg": {
|
| 738 |
+
"f1-score": 0.8573567707758909,
|
| 739 |
+
"precision": 0.8613285464033407,
|
| 740 |
+
"recall": 0.8546121558647586,
|
| 741 |
+
"support": 30257.0
|
| 742 |
+
},
|
| 743 |
+
"step": 1296
|
| 744 |
+
},
|
| 745 |
+
{
|
| 746 |
+
"epoch": 17.0,
|
| 747 |
+
"eval_Claim": {
|
| 748 |
+
"f1-score": 0.577664702731655,
|
| 749 |
+
"precision": 0.6926782273603083,
|
| 750 |
+
"recall": 0.49540652273771246,
|
| 751 |
+
"support": 4354.0
|
| 752 |
+
},
|
| 753 |
+
"eval_MajorClaim": {
|
| 754 |
+
"f1-score": 0.8222534645511148,
|
| 755 |
+
"precision": 0.7783269961977186,
|
| 756 |
+
"recall": 0.8714346530438485,
|
| 757 |
+
"support": 2349.0
|
| 758 |
+
},
|
| 759 |
+
"eval_O": {
|
| 760 |
+
"f1-score": 0.9173265135494024,
|
| 761 |
+
"precision": 0.9185462424899045,
|
| 762 |
+
"recall": 0.9161100196463654,
|
| 763 |
+
"support": 10180.0
|
| 764 |
+
},
|
| 765 |
+
"eval_Premise": {
|
| 766 |
+
"f1-score": 0.901492752578063,
|
| 767 |
+
"precision": 0.8705431754874652,
|
| 768 |
+
"recall": 0.9347240915208613,
|
| 769 |
+
"support": 13374.0
|
| 770 |
+
},
|
| 771 |
+
"eval_accuracy": 0.8603298410285223,
|
| 772 |
+
"eval_loss": 0.8753499984741211,
|
| 773 |
+
"eval_macro avg": {
|
| 774 |
+
"f1-score": 0.8046843583525589,
|
| 775 |
+
"precision": 0.8150236603838491,
|
| 776 |
+
"recall": 0.8044188217371968,
|
| 777 |
+
"support": 30257.0
|
| 778 |
+
},
|
| 779 |
+
"eval_runtime": 4.8417,
|
| 780 |
+
"eval_samples_per_second": 16.73,
|
| 781 |
+
"eval_steps_per_second": 2.272,
|
| 782 |
+
"eval_weighted avg": {
|
| 783 |
+
"f1-score": 0.8540692561997597,
|
| 784 |
+
"precision": 0.8539397922302876,
|
| 785 |
+
"recall": 0.8603298410285223,
|
| 786 |
+
"support": 30257.0
|
| 787 |
+
},
|
| 788 |
+
"step": 1377
|
| 789 |
+
},
|
| 790 |
+
{
|
| 791 |
+
"epoch": 18.0,
|
| 792 |
+
"eval_Claim": {
|
| 793 |
+
"f1-score": 0.6204532891100056,
|
| 794 |
+
"precision": 0.5981667021956939,
|
| 795 |
+
"recall": 0.6444648598989435,
|
| 796 |
+
"support": 4354.0
|
| 797 |
+
},
|
| 798 |
+
"eval_MajorClaim": {
|
| 799 |
+
"f1-score": 0.8362068965517241,
|
| 800 |
+
"precision": 0.807372175980975,
|
| 801 |
+
"recall": 0.8671775223499362,
|
| 802 |
+
"support": 2349.0
|
| 803 |
+
},
|
| 804 |
+
"eval_O": {
|
| 805 |
+
"f1-score": 0.9045747829039926,
|
| 806 |
+
"precision": 0.8936068244991853,
|
| 807 |
+
"recall": 0.9158153241650294,
|
| 808 |
+
"support": 10180.0
|
| 809 |
+
},
|
| 810 |
+
"eval_Premise": {
|
| 811 |
+
"f1-score": 0.8850831280788178,
|
| 812 |
+
"precision": 0.9118953211736717,
|
| 813 |
+
"recall": 0.8598026020637057,
|
| 814 |
+
"support": 13374.0
|
| 815 |
+
},
|
| 816 |
+
"eval_accuracy": 0.8482334666358198,
|
| 817 |
+
"eval_loss": 0.9685499668121338,
|
| 818 |
+
"eval_macro avg": {
|
| 819 |
+
"f1-score": 0.811579524161135,
|
| 820 |
+
"precision": 0.8027602559623814,
|
| 821 |
+
"recall": 0.8218150771194037,
|
| 822 |
+
"support": 30257.0
|
| 823 |
+
},
|
| 824 |
+
"eval_runtime": 4.8521,
|
| 825 |
+
"eval_samples_per_second": 16.694,
|
| 826 |
+
"eval_steps_per_second": 2.267,
|
| 827 |
+
"eval_weighted avg": {
|
| 828 |
+
"f1-score": 0.8497662248627994,
|
| 829 |
+
"precision": 0.8524817583209754,
|
| 830 |
+
"recall": 0.8482334666358198,
|
| 831 |
+
"support": 30257.0
|
| 832 |
+
},
|
| 833 |
+
"step": 1458
|
| 834 |
+
},
|
| 835 |
+
{
|
| 836 |
+
"epoch": 18.52,
|
| 837 |
+
"grad_norm": 0.44517388939857483,
|
| 838 |
+
"learning_rate": 1.2592592592592593e-05,
|
| 839 |
+
"loss": 0.0216,
|
| 840 |
+
"step": 1500
|
| 841 |
+
},
|
| 842 |
+
{
|
| 843 |
+
"epoch": 19.0,
|
| 844 |
+
"eval_Claim": {
|
| 845 |
+
"f1-score": 0.6178126034654013,
|
| 846 |
+
"precision": 0.5946462715105163,
|
| 847 |
+
"recall": 0.6428571428571429,
|
| 848 |
+
"support": 4354.0
|
| 849 |
+
},
|
| 850 |
+
"eval_MajorClaim": {
|
| 851 |
+
"f1-score": 0.8151062155782848,
|
| 852 |
+
"precision": 0.7575868372943327,
|
| 853 |
+
"recall": 0.8820774797786292,
|
| 854 |
+
"support": 2349.0
|
| 855 |
+
},
|
| 856 |
+
"eval_O": {
|
| 857 |
+
"f1-score": 0.9146588828971454,
|
| 858 |
+
"precision": 0.9213595136051032,
|
| 859 |
+
"recall": 0.9080550098231827,
|
| 860 |
+
"support": 10180.0
|
| 861 |
+
},
|
| 862 |
+
"eval_Premise": {
|
| 863 |
+
"f1-score": 0.8898914207065302,
|
| 864 |
+
"precision": 0.9104991394148021,
|
| 865 |
+
"recall": 0.870195902497383,
|
| 866 |
+
"support": 13374.0
|
| 867 |
+
},
|
| 868 |
+
"eval_accuracy": 0.8511418845225898,
|
| 869 |
+
"eval_loss": 0.9391252398490906,
|
| 870 |
+
"eval_macro avg": {
|
| 871 |
+
"f1-score": 0.8093672806618404,
|
| 872 |
+
"precision": 0.7960229404561886,
|
| 873 |
+
"recall": 0.8257963837390844,
|
| 874 |
+
"support": 30257.0
|
| 875 |
+
},
|
| 876 |
+
"eval_runtime": 4.8661,
|
| 877 |
+
"eval_samples_per_second": 16.646,
|
| 878 |
+
"eval_steps_per_second": 2.261,
|
| 879 |
+
"eval_weighted avg": {
|
| 880 |
+
"f1-score": 0.853266214902463,
|
| 881 |
+
"precision": 0.8568303759789367,
|
| 882 |
+
"recall": 0.8511418845225898,
|
| 883 |
+
"support": 30257.0
|
| 884 |
+
},
|
| 885 |
+
"step": 1539
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 20.0,
|
| 889 |
+
"eval_Claim": {
|
| 890 |
+
"f1-score": 0.6097087378640776,
|
| 891 |
+
"precision": 0.6064530788457169,
|
| 892 |
+
"recall": 0.6129995406522738,
|
| 893 |
+
"support": 4354.0
|
| 894 |
+
},
|
| 895 |
+
"eval_MajorClaim": {
|
| 896 |
+
"f1-score": 0.8268961376826096,
|
| 897 |
+
"precision": 0.7802114803625377,
|
| 898 |
+
"recall": 0.8795232013622818,
|
| 899 |
+
"support": 2349.0
|
| 900 |
+
},
|
| 901 |
+
"eval_O": {
|
| 902 |
+
"f1-score": 0.9215637325877477,
|
| 903 |
+
"precision": 0.9370494466443293,
|
| 904 |
+
"recall": 0.906581532416503,
|
| 905 |
+
"support": 10180.0
|
| 906 |
+
},
|
| 907 |
+
"eval_Premise": {
|
| 908 |
+
"f1-score": 0.896644596566042,
|
| 909 |
+
"precision": 0.8971479901190209,
|
| 910 |
+
"recall": 0.8961417676087932,
|
| 911 |
+
"support": 13374.0
|
| 912 |
+
},
|
| 913 |
+
"eval_accuracy": 0.8576197243613048,
|
| 914 |
+
"eval_loss": 0.8915661573410034,
|
| 915 |
+
"eval_macro avg": {
|
| 916 |
+
"f1-score": 0.8137033011751192,
|
| 917 |
+
"precision": 0.8052154989929012,
|
| 918 |
+
"recall": 0.8238115105099629,
|
| 919 |
+
"support": 30257.0
|
| 920 |
+
},
|
| 921 |
+
"eval_runtime": 4.864,
|
| 922 |
+
"eval_samples_per_second": 16.653,
|
| 923 |
+
"eval_steps_per_second": 2.261,
|
| 924 |
+
"eval_weighted avg": {
|
| 925 |
+
"f1-score": 0.8583235120565212,
|
| 926 |
+
"precision": 0.8596633525913644,
|
| 927 |
+
"recall": 0.8576197243613048,
|
| 928 |
+
"support": 30257.0
|
| 929 |
+
},
|
| 930 |
+
"step": 1620
|
| 931 |
+
},
|
| 932 |
+
{
|
| 933 |
+
"epoch": 21.0,
|
| 934 |
+
"eval_Claim": {
|
| 935 |
+
"f1-score": 0.6211416490486258,
|
| 936 |
+
"precision": 0.5754014884449667,
|
| 937 |
+
"recall": 0.6747818098300413,
|
| 938 |
+
"support": 4354.0
|
| 939 |
+
},
|
| 940 |
+
"eval_MajorClaim": {
|
| 941 |
+
"f1-score": 0.8162756902636495,
|
| 942 |
+
"precision": 0.7965964343598055,
|
| 943 |
+
"recall": 0.8369518944231588,
|
| 944 |
+
"support": 2349.0
|
| 945 |
+
},
|
| 946 |
+
"eval_O": {
|
| 947 |
+
"f1-score": 0.911611088790679,
|
| 948 |
+
"precision": 0.9325935059597205,
|
| 949 |
+
"recall": 0.8915520628683693,
|
| 950 |
+
"support": 10180.0
|
| 951 |
+
},
|
| 952 |
+
"eval_Premise": {
|
| 953 |
+
"f1-score": 0.8885090218423553,
|
| 954 |
+
"precision": 0.9030190718863408,
|
| 955 |
+
"recall": 0.8744579033946464,
|
| 956 |
+
"support": 13374.0
|
| 957 |
+
},
|
| 958 |
+
"eval_accuracy": 0.8485639686684073,
|
| 959 |
+
"eval_loss": 0.9740728735923767,
|
| 960 |
+
"eval_macro avg": {
|
| 961 |
+
"f1-score": 0.8093843624863275,
|
| 962 |
+
"precision": 0.8019026251627084,
|
| 963 |
+
"recall": 0.8194359176290539,
|
| 964 |
+
"support": 30257.0
|
| 965 |
+
},
|
| 966 |
+
"eval_runtime": 4.884,
|
| 967 |
+
"eval_samples_per_second": 16.585,
|
| 968 |
+
"eval_steps_per_second": 2.252,
|
| 969 |
+
"eval_weighted avg": {
|
| 970 |
+
"f1-score": 0.852199586158436,
|
| 971 |
+
"precision": 0.8575629461968616,
|
| 972 |
+
"recall": 0.8485639686684073,
|
| 973 |
+
"support": 30257.0
|
| 974 |
+
},
|
| 975 |
+
"step": 1701
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 22.0,
|
| 979 |
+
"eval_Claim": {
|
| 980 |
+
"f1-score": 0.6145704312577412,
|
| 981 |
+
"precision": 0.6028274795670422,
|
| 982 |
+
"recall": 0.6267799724391364,
|
| 983 |
+
"support": 4354.0
|
| 984 |
+
},
|
| 985 |
+
"eval_MajorClaim": {
|
| 986 |
+
"f1-score": 0.8148905706688483,
|
| 987 |
+
"precision": 0.784251968503937,
|
| 988 |
+
"recall": 0.8480204342273308,
|
| 989 |
+
"support": 2349.0
|
| 990 |
+
},
|
| 991 |
+
"eval_O": {
|
| 992 |
+
"f1-score": 0.9175837613108339,
|
| 993 |
+
"precision": 0.9137847053093034,
|
| 994 |
+
"recall": 0.9214145383104125,
|
| 995 |
+
"support": 10180.0
|
| 996 |
+
},
|
| 997 |
+
"eval_Premise": {
|
| 998 |
+
"f1-score": 0.8915167877105593,
|
| 999 |
+
"precision": 0.9070019342359767,
|
| 1000 |
+
"recall": 0.876551517870495,
|
| 1001 |
+
"support": 13374.0
|
| 1002 |
+
},
|
| 1003 |
+
"eval_accuracy": 0.853488448953961,
|
| 1004 |
+
"eval_loss": 0.9675940871238708,
|
| 1005 |
+
"eval_macro avg": {
|
| 1006 |
+
"f1-score": 0.8096403877369956,
|
| 1007 |
+
"precision": 0.8019665219040648,
|
| 1008 |
+
"recall": 0.8181916157118437,
|
| 1009 |
+
"support": 30257.0
|
| 1010 |
+
},
|
| 1011 |
+
"eval_runtime": 4.8521,
|
| 1012 |
+
"eval_samples_per_second": 16.694,
|
| 1013 |
+
"eval_steps_per_second": 2.267,
|
| 1014 |
+
"eval_weighted avg": {
|
| 1015 |
+
"f1-score": 0.8544854353433136,
|
| 1016 |
+
"precision": 0.8559834381654265,
|
| 1017 |
+
"recall": 0.853488448953961,
|
| 1018 |
+
"support": 30257.0
|
| 1019 |
+
},
|
| 1020 |
+
"step": 1782
|
| 1021 |
+
},
|
| 1022 |
+
{
|
| 1023 |
+
"epoch": 23.0,
|
| 1024 |
+
"eval_Claim": {
|
| 1025 |
+
"f1-score": 0.5983347015362965,
|
| 1026 |
+
"precision": 0.6113108075724898,
|
| 1027 |
+
"recall": 0.5858980248047773,
|
| 1028 |
+
"support": 4354.0
|
| 1029 |
+
},
|
| 1030 |
+
"eval_MajorClaim": {
|
| 1031 |
+
"f1-score": 0.8269188475918188,
|
| 1032 |
+
"precision": 0.8553230209281165,
|
| 1033 |
+
"recall": 0.800340570455513,
|
| 1034 |
+
"support": 2349.0
|
| 1035 |
+
},
|
| 1036 |
+
"eval_O": {
|
| 1037 |
+
"f1-score": 0.9219349129879069,
|
| 1038 |
+
"precision": 0.9227514268844715,
|
| 1039 |
+
"recall": 0.9211198428290767,
|
| 1040 |
+
"support": 10180.0
|
| 1041 |
+
},
|
| 1042 |
+
"eval_Premise": {
|
| 1043 |
+
"f1-score": 0.8949737988043397,
|
| 1044 |
+
"precision": 0.8835616438356164,
|
| 1045 |
+
"recall": 0.9066846119336025,
|
| 1046 |
+
"support": 13374.0
|
| 1047 |
+
},
|
| 1048 |
+
"eval_accuracy": 0.8571239713124236,
|
| 1049 |
+
"eval_loss": 0.9897539019584656,
|
| 1050 |
+
"eval_macro avg": {
|
| 1051 |
+
"f1-score": 0.8105405652300904,
|
| 1052 |
+
"precision": 0.8182367248051736,
|
| 1053 |
+
"recall": 0.8035107625057423,
|
| 1054 |
+
"support": 30257.0
|
| 1055 |
+
},
|
| 1056 |
+
"eval_runtime": 4.8416,
|
| 1057 |
+
"eval_samples_per_second": 16.73,
|
| 1058 |
+
"eval_steps_per_second": 2.272,
|
| 1059 |
+
"eval_weighted avg": {
|
| 1060 |
+
"f1-score": 0.8560749136698399,
|
| 1061 |
+
"precision": 0.8553777302003576,
|
| 1062 |
+
"recall": 0.8571239713124236,
|
| 1063 |
+
"support": 30257.0
|
| 1064 |
+
},
|
| 1065 |
+
"step": 1863
|
| 1066 |
+
},
|
| 1067 |
+
{
|
| 1068 |
+
"epoch": 24.0,
|
| 1069 |
+
"eval_Claim": {
|
| 1070 |
+
"f1-score": 0.6090506975161619,
|
| 1071 |
+
"precision": 0.6016132646202106,
|
| 1072 |
+
"recall": 0.6166743224621039,
|
| 1073 |
+
"support": 4354.0
|
| 1074 |
+
},
|
| 1075 |
+
"eval_MajorClaim": {
|
| 1076 |
+
"f1-score": 0.7960317460317461,
|
| 1077 |
+
"precision": 0.7454477889260498,
|
| 1078 |
+
"recall": 0.853980417198808,
|
| 1079 |
+
"support": 2349.0
|
| 1080 |
+
},
|
| 1081 |
+
"eval_O": {
|
| 1082 |
+
"f1-score": 0.9115434760806339,
|
| 1083 |
+
"precision": 0.9310592091784471,
|
| 1084 |
+
"recall": 0.8928290766208251,
|
| 1085 |
+
"support": 10180.0
|
| 1086 |
+
},
|
| 1087 |
+
"eval_Premise": {
|
| 1088 |
+
"f1-score": 0.8995695302264645,
|
| 1089 |
+
"precision": 0.9006821077880219,
|
| 1090 |
+
"recall": 0.89845969792134,
|
| 1091 |
+
"support": 13374.0
|
| 1092 |
+
},
|
| 1093 |
+
"eval_accuracy": 0.852563043262716,
|
| 1094 |
+
"eval_loss": 0.9720127582550049,
|
| 1095 |
+
"eval_macro avg": {
|
| 1096 |
+
"f1-score": 0.8040488624637516,
|
| 1097 |
+
"precision": 0.7947005926281823,
|
| 1098 |
+
"recall": 0.8154858785507693,
|
| 1099 |
+
"support": 30257.0
|
| 1100 |
+
},
|
| 1101 |
+
"eval_runtime": 4.8503,
|
| 1102 |
+
"eval_samples_per_second": 16.7,
|
| 1103 |
+
"eval_steps_per_second": 2.268,
|
| 1104 |
+
"eval_weighted avg": {
|
| 1105 |
+
"f1-score": 0.8537541987693271,
|
| 1106 |
+
"precision": 0.8558147294621835,
|
| 1107 |
+
"recall": 0.852563043262716,
|
| 1108 |
+
"support": 30257.0
|
| 1109 |
+
},
|
| 1110 |
+
"step": 1944
|
| 1111 |
+
},
|
| 1112 |
+
{
|
| 1113 |
+
"epoch": 24.69,
|
| 1114 |
+
"grad_norm": 3.446370840072632,
|
| 1115 |
+
"learning_rate": 1.0123456790123458e-05,
|
| 1116 |
+
"loss": 0.0116,
|
| 1117 |
+
"step": 2000
|
| 1118 |
+
},
|
| 1119 |
+
{
|
| 1120 |
+
"epoch": 25.0,
|
| 1121 |
+
"eval_Claim": {
|
| 1122 |
+
"f1-score": 0.6102259215219976,
|
| 1123 |
+
"precision": 0.6326429980276134,
|
| 1124 |
+
"recall": 0.5893431327514929,
|
| 1125 |
+
"support": 4354.0
|
| 1126 |
+
},
|
| 1127 |
+
"eval_MajorClaim": {
|
| 1128 |
+
"f1-score": 0.8064243448858834,
|
| 1129 |
+
"precision": 0.8006714225765842,
|
| 1130 |
+
"recall": 0.8122605363984674,
|
| 1131 |
+
"support": 2349.0
|
| 1132 |
+
},
|
| 1133 |
+
"eval_O": {
|
| 1134 |
+
"f1-score": 0.9169322709163347,
|
| 1135 |
+
"precision": 0.9298989898989899,
|
| 1136 |
+
"recall": 0.9043222003929273,
|
| 1137 |
+
"support": 10180.0
|
| 1138 |
+
},
|
| 1139 |
+
"eval_Premise": {
|
| 1140 |
+
"f1-score": 0.8993844349992672,
|
| 1141 |
+
"precision": 0.8818077309958328,
|
| 1142 |
+
"recall": 0.917676087931808,
|
| 1143 |
+
"support": 13374.0
|
| 1144 |
+
},
|
| 1145 |
+
"eval_accuracy": 0.8577519251743398,
|
| 1146 |
+
"eval_loss": 1.0132465362548828,
|
| 1147 |
+
"eval_macro avg": {
|
| 1148 |
+
"f1-score": 0.8082417430808707,
|
| 1149 |
+
"precision": 0.811255285374755,
|
| 1150 |
+
"recall": 0.8059004893686739,
|
| 1151 |
+
"support": 30257.0
|
| 1152 |
+
},
|
| 1153 |
+
"eval_runtime": 4.8662,
|
| 1154 |
+
"eval_samples_per_second": 16.645,
|
| 1155 |
+
"eval_steps_per_second": 2.26,
|
| 1156 |
+
"eval_weighted avg": {
|
| 1157 |
+
"f1-score": 0.8564613940592988,
|
| 1158 |
+
"precision": 0.8558341242209939,
|
| 1159 |
+
"recall": 0.8577519251743398,
|
| 1160 |
+
"support": 30257.0
|
| 1161 |
+
},
|
| 1162 |
+
"step": 2025
|
| 1163 |
+
},
|
| 1164 |
+
{
|
| 1165 |
+
"epoch": 26.0,
|
| 1166 |
+
"eval_Claim": {
|
| 1167 |
+
"f1-score": 0.6123184326089406,
|
| 1168 |
+
"precision": 0.6006185111552905,
|
| 1169 |
+
"recall": 0.6244832338079926,
|
| 1170 |
+
"support": 4354.0
|
| 1171 |
+
},
|
| 1172 |
+
"eval_MajorClaim": {
|
| 1173 |
+
"f1-score": 0.7939849624060151,
|
| 1174 |
+
"precision": 0.8013876843018214,
|
| 1175 |
+
"recall": 0.7867177522349936,
|
| 1176 |
+
"support": 2349.0
|
| 1177 |
+
},
|
| 1178 |
+
"eval_O": {
|
| 1179 |
+
"f1-score": 0.9205986178093769,
|
| 1180 |
+
"precision": 0.93204469948656,
|
| 1181 |
+
"recall": 0.9094302554027505,
|
| 1182 |
+
"support": 10180.0
|
| 1183 |
+
},
|
| 1184 |
+
"eval_Premise": {
|
| 1185 |
+
"f1-score": 0.8996091568955891,
|
| 1186 |
+
"precision": 0.8957082499444073,
|
| 1187 |
+
"recall": 0.9035441902198296,
|
| 1188 |
+
"support": 13374.0
|
| 1189 |
+
},
|
| 1190 |
+
"eval_accuracy": 0.8562977162309549,
|
| 1191 |
+
"eval_loss": 1.0289610624313354,
|
| 1192 |
+
"eval_macro avg": {
|
| 1193 |
+
"f1-score": 0.8066277924299805,
|
| 1194 |
+
"precision": 0.8074397862220198,
|
| 1195 |
+
"recall": 0.8060438579163915,
|
| 1196 |
+
"support": 30257.0
|
| 1197 |
+
},
|
| 1198 |
+
"eval_runtime": 4.8488,
|
| 1199 |
+
"eval_samples_per_second": 16.705,
|
| 1200 |
+
"eval_steps_per_second": 2.269,
|
| 1201 |
+
"eval_weighted avg": {
|
| 1202 |
+
"f1-score": 0.8571296534981037,
|
| 1203 |
+
"precision": 0.8581475309358099,
|
| 1204 |
+
"recall": 0.8562977162309549,
|
| 1205 |
+
"support": 30257.0
|
| 1206 |
+
},
|
| 1207 |
+
"step": 2106
|
| 1208 |
+
}
|
| 1209 |
+
],
|
| 1210 |
+
"logging_steps": 500,
|
| 1211 |
+
"max_steps": 4050,
|
| 1212 |
+
"num_input_tokens_seen": 0,
|
| 1213 |
+
"num_train_epochs": 50,
|
| 1214 |
+
"save_steps": 500,
|
| 1215 |
+
"total_flos": 3726896780552400.0,
|
| 1216 |
+
"train_batch_size": 4,
|
| 1217 |
+
"trial_name": null,
|
| 1218 |
+
"trial_params": null
|
| 1219 |
+
}
|
checkpoint-2106/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0ce83aa27c1a93c128c1dae6a1646206ab5d85d935efad925ac4e4beb0be29a0
|
| 3 |
+
size 4856
|
checkpoint-2106/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|