Upload folder using huggingface_hub
Browse files- added_tokens.json +5 -0
- gliner_config.json +221 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- special_tokens_map.json +51 -0
- spm.model +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +75 -0
- trainer_state.json +321 -0
added_tokens.json
ADDED
|
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<<ENT>>": 128001,
|
| 3 |
+
"<<SEP>>": 128002,
|
| 4 |
+
"[MASK]": 128000
|
| 5 |
+
}
|
gliner_config.json
ADDED
|
@@ -0,0 +1,221 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"class_token_index": 128001,
|
| 3 |
+
"dropout": 0.4,
|
| 4 |
+
"embed_ent_token": true,
|
| 5 |
+
"encoder_config": {
|
| 6 |
+
"_attn_implementation_autoset": false,
|
| 7 |
+
"_name_or_path": "microsoft/deberta-v3-base",
|
| 8 |
+
"add_cross_attention": false,
|
| 9 |
+
"architectures": null,
|
| 10 |
+
"attention_probs_dropout_prob": 0.1,
|
| 11 |
+
"bad_words_ids": null,
|
| 12 |
+
"begin_suppress_tokens": null,
|
| 13 |
+
"bos_token_id": null,
|
| 14 |
+
"chunk_size_feed_forward": 0,
|
| 15 |
+
"cross_attention_hidden_size": null,
|
| 16 |
+
"decoder_start_token_id": null,
|
| 17 |
+
"diversity_penalty": 0.0,
|
| 18 |
+
"do_sample": false,
|
| 19 |
+
"early_stopping": false,
|
| 20 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 21 |
+
"eos_token_id": null,
|
| 22 |
+
"exponential_decay_length_penalty": null,
|
| 23 |
+
"finetuning_task": null,
|
| 24 |
+
"forced_bos_token_id": null,
|
| 25 |
+
"forced_eos_token_id": null,
|
| 26 |
+
"hidden_act": "gelu",
|
| 27 |
+
"hidden_dropout_prob": 0.1,
|
| 28 |
+
"hidden_size": 768,
|
| 29 |
+
"id2label": {
|
| 30 |
+
"0": "LABEL_0",
|
| 31 |
+
"1": "LABEL_1"
|
| 32 |
+
},
|
| 33 |
+
"initializer_range": 0.02,
|
| 34 |
+
"intermediate_size": 3072,
|
| 35 |
+
"is_decoder": false,
|
| 36 |
+
"is_encoder_decoder": false,
|
| 37 |
+
"label2id": {
|
| 38 |
+
"LABEL_0": 0,
|
| 39 |
+
"LABEL_1": 1
|
| 40 |
+
},
|
| 41 |
+
"layer_norm_eps": 1e-07,
|
| 42 |
+
"legacy": true,
|
| 43 |
+
"length_penalty": 1.0,
|
| 44 |
+
"max_length": 20,
|
| 45 |
+
"max_position_embeddings": 512,
|
| 46 |
+
"max_relative_positions": -1,
|
| 47 |
+
"min_length": 0,
|
| 48 |
+
"model_type": "deberta-v2",
|
| 49 |
+
"no_repeat_ngram_size": 0,
|
| 50 |
+
"norm_rel_ebd": "layer_norm",
|
| 51 |
+
"num_attention_heads": 12,
|
| 52 |
+
"num_beam_groups": 1,
|
| 53 |
+
"num_beams": 1,
|
| 54 |
+
"num_hidden_layers": 12,
|
| 55 |
+
"num_return_sequences": 1,
|
| 56 |
+
"output_attentions": false,
|
| 57 |
+
"output_hidden_states": false,
|
| 58 |
+
"output_scores": false,
|
| 59 |
+
"pad_token_id": 0,
|
| 60 |
+
"pooler_dropout": 0,
|
| 61 |
+
"pooler_hidden_act": "gelu",
|
| 62 |
+
"pooler_hidden_size": 768,
|
| 63 |
+
"pos_att_type": [
|
| 64 |
+
"p2c",
|
| 65 |
+
"c2p"
|
| 66 |
+
],
|
| 67 |
+
"position_biased_input": false,
|
| 68 |
+
"position_buckets": 256,
|
| 69 |
+
"prefix": null,
|
| 70 |
+
"problem_type": null,
|
| 71 |
+
"pruned_heads": {},
|
| 72 |
+
"relative_attention": true,
|
| 73 |
+
"remove_invalid_values": false,
|
| 74 |
+
"repetition_penalty": 1.0,
|
| 75 |
+
"return_dict": true,
|
| 76 |
+
"return_dict_in_generate": false,
|
| 77 |
+
"sep_token_id": null,
|
| 78 |
+
"share_att_key": true,
|
| 79 |
+
"suppress_tokens": null,
|
| 80 |
+
"task_specific_params": null,
|
| 81 |
+
"temperature": 1.0,
|
| 82 |
+
"tf_legacy_loss": false,
|
| 83 |
+
"tie_encoder_decoder": false,
|
| 84 |
+
"tie_word_embeddings": true,
|
| 85 |
+
"tokenizer_class": null,
|
| 86 |
+
"top_k": 50,
|
| 87 |
+
"top_p": 1.0,
|
| 88 |
+
"torch_dtype": null,
|
| 89 |
+
"torchscript": false,
|
| 90 |
+
"type_vocab_size": 0,
|
| 91 |
+
"typical_p": 1.0,
|
| 92 |
+
"use_bfloat16": false,
|
| 93 |
+
"vocab_size": 128003
|
| 94 |
+
},
|
| 95 |
+
"ent_token": "<<ENT>>",
|
| 96 |
+
"eval_every": 25000,
|
| 97 |
+
"fine_tune": true,
|
| 98 |
+
"freeze_token_rep": false,
|
| 99 |
+
"fuse_layers": false,
|
| 100 |
+
"has_rnn": true,
|
| 101 |
+
"hidden_size": 768,
|
| 102 |
+
"label_smoothing": 0,
|
| 103 |
+
"labels_encoder": "BAAI/bge-small-en-v1.5",
|
| 104 |
+
"labels_encoder_config": {
|
| 105 |
+
"_attn_implementation_autoset": false,
|
| 106 |
+
"_name_or_path": "BAAI/bge-small-en-v1.5",
|
| 107 |
+
"add_cross_attention": false,
|
| 108 |
+
"architectures": [
|
| 109 |
+
"BertModel"
|
| 110 |
+
],
|
| 111 |
+
"attention_probs_dropout_prob": 0.1,
|
| 112 |
+
"bad_words_ids": null,
|
| 113 |
+
"begin_suppress_tokens": null,
|
| 114 |
+
"bos_token_id": null,
|
| 115 |
+
"chunk_size_feed_forward": 0,
|
| 116 |
+
"classifier_dropout": null,
|
| 117 |
+
"cross_attention_hidden_size": null,
|
| 118 |
+
"decoder_start_token_id": null,
|
| 119 |
+
"diversity_penalty": 0.0,
|
| 120 |
+
"do_sample": false,
|
| 121 |
+
"early_stopping": false,
|
| 122 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 123 |
+
"eos_token_id": null,
|
| 124 |
+
"exponential_decay_length_penalty": null,
|
| 125 |
+
"finetuning_task": null,
|
| 126 |
+
"forced_bos_token_id": null,
|
| 127 |
+
"forced_eos_token_id": null,
|
| 128 |
+
"hidden_act": "gelu",
|
| 129 |
+
"hidden_dropout_prob": 0.1,
|
| 130 |
+
"hidden_size": 384,
|
| 131 |
+
"id2label": {
|
| 132 |
+
"0": "LABEL_0"
|
| 133 |
+
},
|
| 134 |
+
"initializer_range": 0.02,
|
| 135 |
+
"intermediate_size": 1536,
|
| 136 |
+
"is_decoder": false,
|
| 137 |
+
"is_encoder_decoder": false,
|
| 138 |
+
"label2id": {
|
| 139 |
+
"LABEL_0": 0
|
| 140 |
+
},
|
| 141 |
+
"layer_norm_eps": 1e-12,
|
| 142 |
+
"length_penalty": 1.0,
|
| 143 |
+
"max_length": 20,
|
| 144 |
+
"max_position_embeddings": 512,
|
| 145 |
+
"min_length": 0,
|
| 146 |
+
"model_type": "bert",
|
| 147 |
+
"no_repeat_ngram_size": 0,
|
| 148 |
+
"num_attention_heads": 12,
|
| 149 |
+
"num_beam_groups": 1,
|
| 150 |
+
"num_beams": 1,
|
| 151 |
+
"num_hidden_layers": 12,
|
| 152 |
+
"num_return_sequences": 1,
|
| 153 |
+
"output_attentions": false,
|
| 154 |
+
"output_hidden_states": false,
|
| 155 |
+
"output_scores": false,
|
| 156 |
+
"pad_token_id": 0,
|
| 157 |
+
"position_embedding_type": "absolute",
|
| 158 |
+
"prefix": null,
|
| 159 |
+
"problem_type": null,
|
| 160 |
+
"pruned_heads": {},
|
| 161 |
+
"remove_invalid_values": false,
|
| 162 |
+
"repetition_penalty": 1.0,
|
| 163 |
+
"return_dict": true,
|
| 164 |
+
"return_dict_in_generate": false,
|
| 165 |
+
"sep_token_id": null,
|
| 166 |
+
"suppress_tokens": null,
|
| 167 |
+
"task_specific_params": null,
|
| 168 |
+
"temperature": 1.0,
|
| 169 |
+
"tf_legacy_loss": false,
|
| 170 |
+
"tie_encoder_decoder": false,
|
| 171 |
+
"tie_word_embeddings": true,
|
| 172 |
+
"tokenizer_class": null,
|
| 173 |
+
"top_k": 50,
|
| 174 |
+
"top_p": 1.0,
|
| 175 |
+
"torch_dtype": "float32",
|
| 176 |
+
"torchscript": false,
|
| 177 |
+
"type_vocab_size": 2,
|
| 178 |
+
"typical_p": 1.0,
|
| 179 |
+
"use_bfloat16": false,
|
| 180 |
+
"use_cache": true,
|
| 181 |
+
"vocab_size": 30522
|
| 182 |
+
},
|
| 183 |
+
"labels_fusion_schema": "pre-post",
|
| 184 |
+
"log_dir": "models/",
|
| 185 |
+
"loss_alpha": 0.75,
|
| 186 |
+
"loss_gamma": 2,
|
| 187 |
+
"loss_reduction": "sum",
|
| 188 |
+
"lr_encoder": "1e-5",
|
| 189 |
+
"lr_others": "5e-5",
|
| 190 |
+
"max_grad_norm": 10.0,
|
| 191 |
+
"max_len": 1024,
|
| 192 |
+
"max_neg_type_ratio": 1,
|
| 193 |
+
"max_types": 30,
|
| 194 |
+
"max_width": 12,
|
| 195 |
+
"model_name": "microsoft/deberta-v3-base",
|
| 196 |
+
"model_type": "gliner",
|
| 197 |
+
"name": "span level gliner",
|
| 198 |
+
"num_post_fusion_layers": 1,
|
| 199 |
+
"num_steps": 150000,
|
| 200 |
+
"post_fusion_schema": "",
|
| 201 |
+
"pre_fusion": true,
|
| 202 |
+
"prev_path": null,
|
| 203 |
+
"random_drop": true,
|
| 204 |
+
"root_dir": "gliner_logs",
|
| 205 |
+
"save_total_limit": 3,
|
| 206 |
+
"scheduler_type": "cosine",
|
| 207 |
+
"sep_token": "<<SEP>>",
|
| 208 |
+
"shuffle_types": true,
|
| 209 |
+
"size_sup": -1,
|
| 210 |
+
"span_mode": "markerV0",
|
| 211 |
+
"subtoken_pooling": "first",
|
| 212 |
+
"train_batch_size": 8,
|
| 213 |
+
"train_data": "data/nuner_full.json",
|
| 214 |
+
"transformers_version": "4.48.0.dev0",
|
| 215 |
+
"val_data_dir": "none",
|
| 216 |
+
"vocab_size": 128003,
|
| 217 |
+
"warmup_ratio": 0.1,
|
| 218 |
+
"weight_decay_encoder": 0.01,
|
| 219 |
+
"weight_decay_other": 0.01,
|
| 220 |
+
"words_splitter_type": "whitespace"
|
| 221 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:61b590298f97de9be8e3d902388c52cc7f78501919fb5ecea13b9f4f20ac510a
|
| 3 |
+
size 990237154
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a0797e46a3771478320394692fa0e616854e1186d917e68065ad8221eee4e32e
|
| 3 |
+
size 14244
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "[CLS]",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"cls_token": {
|
| 10 |
+
"content": "[CLS]",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"eos_token": {
|
| 17 |
+
"content": "[SEP]",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"mask_token": {
|
| 24 |
+
"content": "[MASK]",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"pad_token": {
|
| 31 |
+
"content": "[PAD]",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
},
|
| 37 |
+
"sep_token": {
|
| 38 |
+
"content": "[SEP]",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false
|
| 43 |
+
},
|
| 44 |
+
"unk_token": {
|
| 45 |
+
"content": "[UNK]",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": true,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false
|
| 50 |
+
}
|
| 51 |
+
}
|
spm.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
|
| 3 |
+
size 2464616
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,75 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "[PAD]",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "[CLS]",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "[SEP]",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"3": {
|
| 28 |
+
"content": "[UNK]",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": true,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"128000": {
|
| 36 |
+
"content": "[MASK]",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
},
|
| 43 |
+
"128001": {
|
| 44 |
+
"content": "<<ENT>>",
|
| 45 |
+
"lstrip": false,
|
| 46 |
+
"normalized": false,
|
| 47 |
+
"rstrip": false,
|
| 48 |
+
"single_word": false,
|
| 49 |
+
"special": true
|
| 50 |
+
},
|
| 51 |
+
"128002": {
|
| 52 |
+
"content": "<<SEP>>",
|
| 53 |
+
"lstrip": false,
|
| 54 |
+
"normalized": false,
|
| 55 |
+
"rstrip": false,
|
| 56 |
+
"single_word": false,
|
| 57 |
+
"special": true
|
| 58 |
+
}
|
| 59 |
+
},
|
| 60 |
+
"bos_token": "[CLS]",
|
| 61 |
+
"clean_up_tokenization_spaces": false,
|
| 62 |
+
"cls_token": "[CLS]",
|
| 63 |
+
"do_lower_case": false,
|
| 64 |
+
"eos_token": "[SEP]",
|
| 65 |
+
"extra_special_tokens": {},
|
| 66 |
+
"mask_token": "[MASK]",
|
| 67 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 68 |
+
"pad_token": "[PAD]",
|
| 69 |
+
"sep_token": "[SEP]",
|
| 70 |
+
"sp_model_kwargs": {},
|
| 71 |
+
"split_by_punct": false,
|
| 72 |
+
"tokenizer_class": "DebertaV2Tokenizer",
|
| 73 |
+
"unk_token": "[UNK]",
|
| 74 |
+
"vocab_type": "spm"
|
| 75 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,321 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.8021265092809515,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 20000,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.04505316273202379,
|
| 13 |
+
"grad_norm": 4495.31298828125,
|
| 14 |
+
"learning_rate": 1.25e-05,
|
| 15 |
+
"loss": 876.4691,
|
| 16 |
+
"step": 500
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.09010632546404758,
|
| 20 |
+
"grad_norm": 7690.41552734375,
|
| 21 |
+
"learning_rate": 2.5e-05,
|
| 22 |
+
"loss": 552.9783,
|
| 23 |
+
"step": 1000
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.13515948819607138,
|
| 27 |
+
"grad_norm": 3831.229736328125,
|
| 28 |
+
"learning_rate": 3.7500000000000003e-05,
|
| 29 |
+
"loss": 508.4013,
|
| 30 |
+
"step": 1500
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.18021265092809516,
|
| 34 |
+
"grad_norm": 2652.883056640625,
|
| 35 |
+
"learning_rate": 5e-05,
|
| 36 |
+
"loss": 493.1244,
|
| 37 |
+
"step": 2000
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.22526581366011894,
|
| 41 |
+
"grad_norm": 2329.73388671875,
|
| 42 |
+
"learning_rate": 4.990486745229364e-05,
|
| 43 |
+
"loss": 471.2945,
|
| 44 |
+
"step": 2500
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.27031897639214275,
|
| 48 |
+
"grad_norm": 2660.374267578125,
|
| 49 |
+
"learning_rate": 4.962019382530521e-05,
|
| 50 |
+
"loss": 462.8009,
|
| 51 |
+
"step": 3000
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.3153721391241665,
|
| 55 |
+
"grad_norm": 2498.203857421875,
|
| 56 |
+
"learning_rate": 4.914814565722671e-05,
|
| 57 |
+
"loss": 446.8442,
|
| 58 |
+
"step": 3500
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.3604253018561903,
|
| 62 |
+
"grad_norm": 3495.0498046875,
|
| 63 |
+
"learning_rate": 4.849231551964771e-05,
|
| 64 |
+
"loss": 449.2647,
|
| 65 |
+
"step": 4000
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.40547846458821407,
|
| 69 |
+
"grad_norm": 2064.2861328125,
|
| 70 |
+
"learning_rate": 4.765769467591625e-05,
|
| 71 |
+
"loss": 438.1682,
|
| 72 |
+
"step": 4500
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.4505316273202379,
|
| 76 |
+
"grad_norm": 2323.6640625,
|
| 77 |
+
"learning_rate": 4.665063509461097e-05,
|
| 78 |
+
"loss": 434.8857,
|
| 79 |
+
"step": 5000
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.4955847900522617,
|
| 83 |
+
"grad_norm": 3712.401611328125,
|
| 84 |
+
"learning_rate": 4.54788011072248e-05,
|
| 85 |
+
"loss": 426.7452,
|
| 86 |
+
"step": 5500
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.5406379527842855,
|
| 90 |
+
"grad_norm": 3010.898193359375,
|
| 91 |
+
"learning_rate": 4.415111107797445e-05,
|
| 92 |
+
"loss": 425.659,
|
| 93 |
+
"step": 6000
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.5856911155163093,
|
| 97 |
+
"grad_norm": 2957.86572265625,
|
| 98 |
+
"learning_rate": 4.267766952966369e-05,
|
| 99 |
+
"loss": 414.4347,
|
| 100 |
+
"step": 6500
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.630744278248333,
|
| 104 |
+
"grad_norm": 5558.51171875,
|
| 105 |
+
"learning_rate": 4.1069690242163484e-05,
|
| 106 |
+
"loss": 414.9519,
|
| 107 |
+
"step": 7000
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.6757974409803568,
|
| 111 |
+
"grad_norm": 2855.100341796875,
|
| 112 |
+
"learning_rate": 3.933941090877615e-05,
|
| 113 |
+
"loss": 400.0895,
|
| 114 |
+
"step": 7500
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.7208506037123806,
|
| 118 |
+
"grad_norm": 6043.2392578125,
|
| 119 |
+
"learning_rate": 3.7500000000000003e-05,
|
| 120 |
+
"loss": 406.6636,
|
| 121 |
+
"step": 8000
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.7659037664444044,
|
| 125 |
+
"grad_norm": 2479.6162109375,
|
| 126 |
+
"learning_rate": 3.556545654351749e-05,
|
| 127 |
+
"loss": 396.584,
|
| 128 |
+
"step": 8500
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.8109569291764281,
|
| 132 |
+
"grad_norm": 2344.032958984375,
|
| 133 |
+
"learning_rate": 3.355050358314172e-05,
|
| 134 |
+
"loss": 394.9724,
|
| 135 |
+
"step": 9000
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.856010091908452,
|
| 139 |
+
"grad_norm": 2779.349853515625,
|
| 140 |
+
"learning_rate": 3.147047612756302e-05,
|
| 141 |
+
"loss": 397.4112,
|
| 142 |
+
"step": 9500
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.9010632546404758,
|
| 146 |
+
"grad_norm": 2716.18994140625,
|
| 147 |
+
"learning_rate": 2.9341204441673266e-05,
|
| 148 |
+
"loss": 391.9731,
|
| 149 |
+
"step": 10000
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.9461164173724995,
|
| 153 |
+
"grad_norm": 2225.15673828125,
|
| 154 |
+
"learning_rate": 2.717889356869146e-05,
|
| 155 |
+
"loss": 393.7706,
|
| 156 |
+
"step": 10500
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.9911695801045234,
|
| 160 |
+
"grad_norm": 1508.1142578125,
|
| 161 |
+
"learning_rate": 2.5e-05,
|
| 162 |
+
"loss": 382.8044,
|
| 163 |
+
"step": 11000
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 1.0,
|
| 167 |
+
"eval_loss": 358.9232177734375,
|
| 168 |
+
"eval_runtime": 101.4193,
|
| 169 |
+
"eval_samples_per_second": 97.269,
|
| 170 |
+
"eval_steps_per_second": 12.167,
|
| 171 |
+
"step": 11098
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 1.0362227428365471,
|
| 175 |
+
"grad_norm": 2014.6854248046875,
|
| 176 |
+
"learning_rate": 2.2821106431308544e-05,
|
| 177 |
+
"loss": 367.5687,
|
| 178 |
+
"step": 11500
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 1.081275905568571,
|
| 182 |
+
"grad_norm": 3775.6591796875,
|
| 183 |
+
"learning_rate": 2.0658795558326743e-05,
|
| 184 |
+
"loss": 359.601,
|
| 185 |
+
"step": 12000
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 1.1263290683005946,
|
| 189 |
+
"grad_norm": 5092.62548828125,
|
| 190 |
+
"learning_rate": 1.852952387243698e-05,
|
| 191 |
+
"loss": 363.3713,
|
| 192 |
+
"step": 12500
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 1.1713822310326185,
|
| 196 |
+
"grad_norm": 2063.513671875,
|
| 197 |
+
"learning_rate": 1.6449496416858284e-05,
|
| 198 |
+
"loss": 359.5718,
|
| 199 |
+
"step": 13000
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 1.2164353937646424,
|
| 203 |
+
"grad_norm": 2899.44091796875,
|
| 204 |
+
"learning_rate": 1.443454345648252e-05,
|
| 205 |
+
"loss": 360.4644,
|
| 206 |
+
"step": 13500
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 1.261488556496666,
|
| 210 |
+
"grad_norm": 4710.76123046875,
|
| 211 |
+
"learning_rate": 1.2500000000000006e-05,
|
| 212 |
+
"loss": 361.0999,
|
| 213 |
+
"step": 14000
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 1.30654171922869,
|
| 217 |
+
"grad_norm": 2558.06005859375,
|
| 218 |
+
"learning_rate": 1.0660589091223855e-05,
|
| 219 |
+
"loss": 350.5707,
|
| 220 |
+
"step": 14500
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 1.3515948819607138,
|
| 224 |
+
"grad_norm": 3802.858642578125,
|
| 225 |
+
"learning_rate": 8.930309757836517e-06,
|
| 226 |
+
"loss": 357.1574,
|
| 227 |
+
"step": 15000
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 1.3966480446927374,
|
| 231 |
+
"grad_norm": 2361.53662109375,
|
| 232 |
+
"learning_rate": 7.3223304703363135e-06,
|
| 233 |
+
"loss": 347.2792,
|
| 234 |
+
"step": 15500
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 1.4417012074247613,
|
| 238 |
+
"grad_norm": 2280.421630859375,
|
| 239 |
+
"learning_rate": 5.848888922025553e-06,
|
| 240 |
+
"loss": 349.3208,
|
| 241 |
+
"step": 16000
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 1.4867543701567851,
|
| 245 |
+
"grad_norm": 2809.066650390625,
|
| 246 |
+
"learning_rate": 4.521198892775203e-06,
|
| 247 |
+
"loss": 353.3406,
|
| 248 |
+
"step": 16500
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 1.5318075328888088,
|
| 252 |
+
"grad_norm": 2266.29248046875,
|
| 253 |
+
"learning_rate": 3.3493649053890326e-06,
|
| 254 |
+
"loss": 349.8974,
|
| 255 |
+
"step": 17000
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 1.5768606956208324,
|
| 259 |
+
"grad_norm": 2905.138671875,
|
| 260 |
+
"learning_rate": 2.3423053240837515e-06,
|
| 261 |
+
"loss": 342.301,
|
| 262 |
+
"step": 17500
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 1.6219138583528565,
|
| 266 |
+
"grad_norm": 2068.38330078125,
|
| 267 |
+
"learning_rate": 1.5076844803522922e-06,
|
| 268 |
+
"loss": 347.1441,
|
| 269 |
+
"step": 18000
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 1.6669670210848802,
|
| 273 |
+
"grad_norm": 2976.573486328125,
|
| 274 |
+
"learning_rate": 8.51854342773295e-07,
|
| 275 |
+
"loss": 349.023,
|
| 276 |
+
"step": 18500
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 1.7120201838169038,
|
| 280 |
+
"grad_norm": 3883.230712890625,
|
| 281 |
+
"learning_rate": 3.7980617469479953e-07,
|
| 282 |
+
"loss": 356.191,
|
| 283 |
+
"step": 19000
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 1.7570733465489279,
|
| 287 |
+
"grad_norm": 1931.0743408203125,
|
| 288 |
+
"learning_rate": 9.513254770636137e-08,
|
| 289 |
+
"loss": 344.1293,
|
| 290 |
+
"step": 19500
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 1.8021265092809515,
|
| 294 |
+
"grad_norm": 2924.070556640625,
|
| 295 |
+
"learning_rate": 0.0,
|
| 296 |
+
"loss": 350.3576,
|
| 297 |
+
"step": 20000
|
| 298 |
+
}
|
| 299 |
+
],
|
| 300 |
+
"logging_steps": 500,
|
| 301 |
+
"max_steps": 20000,
|
| 302 |
+
"num_input_tokens_seen": 0,
|
| 303 |
+
"num_train_epochs": 2,
|
| 304 |
+
"save_steps": 5000,
|
| 305 |
+
"stateful_callbacks": {
|
| 306 |
+
"TrainerControl": {
|
| 307 |
+
"args": {
|
| 308 |
+
"should_epoch_stop": false,
|
| 309 |
+
"should_evaluate": false,
|
| 310 |
+
"should_log": false,
|
| 311 |
+
"should_save": true,
|
| 312 |
+
"should_training_stop": true
|
| 313 |
+
},
|
| 314 |
+
"attributes": {}
|
| 315 |
+
}
|
| 316 |
+
},
|
| 317 |
+
"total_flos": 0.0,
|
| 318 |
+
"train_batch_size": 8,
|
| 319 |
+
"trial_name": null,
|
| 320 |
+
"trial_params": null
|
| 321 |
+
}
|