Upload 17 files

README (1).md

@@ -0,0 +1,52 @@
+---
+license: apache-2.0
+base_model: google-bert/bert-large-cased
+tags:
+- generated_from_trainer
+model-index:
+- name: results_bert_xlarge
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# results_bert_xlarge
+
+This model is a fine-tuned version of [google-bert/bert-large-cased](https://huggingface.co/google-bert/bert-large-cased) on an unknown dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 2e-05
+- train_batch_size: 32
+- eval_batch_size: 8
+- seed: 8446
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 11.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.39.0.dev0
+- Pytorch 2.2.1+cu121
+- Datasets 2.18.0
+- Tokenizers 0.15.2

all_results (1).json

@@ -0,0 +1,8 @@
+{
+    "epoch": 11.0,
+    "train_loss": 0.0872608635859056,
+    "train_runtime": 5767.3328,
+    "train_samples": 7998,
+    "train_samples_per_second": 15.255,
+    "train_steps_per_second": 0.477
+}

checkpoint-1000.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:201e0fd7db166b72478343eabe0b992942bd150513b7a7a42c82b39c7070a763
+size 3586628165

checkpoint-1500.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0cc0e57d54a355115ef49c5fda89598c6370bffced54f4cebb9f08298956962
+size 3587360413

checkpoint-2000.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60ce485ce5aa8a7258d75426651cb7d8adeb0437adfe21fa10775c3e0613c6eb
+size 3587506007

checkpoint-2500.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34f96b2788c4ab0a194ebbf95b35cdc23a0d6d0404680afb1ca567c013d23dff
+size 3587389878

checkpoint-500.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7889fb323e49a45261fb14b3a588c41d7bd1777c788dbd5de67f81120e891e24
+size 3586145586

config (1).json

@@ -0,0 +1,42 @@
+{
+  "_name_or_path": "google-bert/bert-large-cased",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "finetuning_task": "text-classification",
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "0",
+    "1": "1"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "0": 0,
+    "1": 1
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 0,
+  "pooler_fc_size": 768,
+  "pooler_num_attention_heads": 12,
+  "pooler_num_fc_layers": 3,
+  "pooler_size_per_head": 128,
+  "pooler_type": "first_token_transform",
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.39.0.dev0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 28996
+}

model (1).safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bda00803d9c27bcb3e95da2a3f56f3c8adb5b1dce6074c463bb59293c3fcd79d
+size 1334372264

predict_results (1).txt

@@ -0,0 +1,1001 @@
+index	prediction
+0	0
+1	0
+2	0
+3	0
+4	0
+5	1
+6	0
+7	0
+8	0
+9	0
+10	0
+11	0
+12	0
+13	1
+14	1
+15	0
+16	0
+17	0
+18	0
+19	0
+20	0
+21	0
+22	0
+23	1
+24	0
+25	0
+26	0
+27	0
+28	0
+29	0
+30	0
+31	0
+32	0
+33	0
+34	0
+35	0
+36	0
+37	0
+38	1
+39	0
+40	0
+41	0
+42	0
+43	0
+44	1
+45	0
+46	0
+47	0
+48	1
+49	0
+50	0
+51	0
+52	0
+53	0
+54	0
+55	0
+56	0
+57	0
+58	0
+59	0
+60	0
+61	0
+62	0
+63	0
+64	0
+65	0
+66	0
+67	0
+68	0
+69	0
+70	1
+71	0
+72	0
+73	0
+74	0
+75	0
+76	0
+77	0
+78	0
+79	0
+80	0
+81	0
+82	1
+83	0
+84	0
+85	0
+86	0
+87	0
+88	0
+89	0
+90	0
+91	0
+92	0
+93	0
+94	0
+95	0
+96	0
+97	0
+98	0
+99	0
+100	0
+101	0
+102	0
+103	0
+104	0
+105	1
+106	0
+107	0
+108	0
+109	0
+110	0
+111	0
+112	0
+113	0
+114	0
+115	0
+116	0
+117	0
+118	0
+119	0
+120	0
+121	0
+122	0
+123	0
+124	1
+125	0
+126	0
+127	0
+128	0
+129	0
+130	0
+131	0
+132	0
+133	0
+134	0
+135	0
+136	0
+137	0
+138	0
+139	0
+140	0
+141	0
+142	0
+143	1
+144	0
+145	0
+146	0
+147	0
+148	0
+149	0
+150	0
+151	0
+152	0
+153	0
+154	0
+155	0
+156	0
+157	0
+158	0
+159	0
+160	0
+161	0
+162	0
+163	0
+164	1
+165	0
+166	0
+167	0
+168	0
+169	0
+170	0
+171	0
+172	0
+173	0
+174	0
+175	0
+176	1
+177	0
+178	0
+179	0
+180	0
+181	0
+182	0
+183	0
+184	0
+185	0
+186	0
+187	1
+188	0
+189	0
+190	0
+191	0
+192	0
+193	0
+194	0
+195	0
+196	0
+197	0
+198	0
+199	0
+200	0
+201	0
+202	0
+203	0
+204	0
+205	0
+206	0
+207	0
+208	0
+209	0
+210	0
+211	1
+212	1
+213	0
+214	0
+215	0
+216	0
+217	0
+218	0
+219	0
+220	0
+221	0
+222	0
+223	0
+224	0
+225	0
+226	0
+227	0
+228	0
+229	0
+230	0
+231	0
+232	0
+233	1
+234	0
+235	1
+236	0
+237	0
+238	0
+239	0
+240	0
+241	1
+242	0
+243	0
+244	0
+245	0
+246	0
+247	0
+248	0
+249	0
+250	0
+251	0
+252	0
+253	0
+254	0
+255	1
+256	0
+257	0
+258	0
+259	0
+260	0
+261	1
+262	0
+263	0
+264	0
+265	0
+266	0
+267	0
+268	1
+269	0
+270	0
+271	0
+272	0
+273	0
+274	0
+275	1
+276	1
+277	0
+278	0
+279	0
+280	0
+281	1
+282	0
+283	0
+284	0
+285	0
+286	0
+287	0
+288	1
+289	0
+290	0
+291	0
+292	0
+293	1
+294	0
+295	0
+296	0
+297	1
+298	0
+299	1
+300	0
+301	1
+302	0
+303	0
+304	0
+305	0
+306	0
+307	0
+308	1
+309	0
+310	0
+311	0
+312	0
+313	0
+314	0
+315	0
+316	0
+317	0
+318	0
+319	0
+320	0
+321	0
+322	0
+323	0
+324	0
+325	0
+326	0
+327	0
+328	0
+329	0
+330	1
+331	0
+332	0
+333	0
+334	1
+335	0
+336	0
+337	0
+338	0
+339	0
+340	0
+341	0
+342	0
+343	0
+344	1
+345	0
+346	1
+347	0
+348	0
+349	0
+350	0
+351	0
+352	1
+353	0
+354	0
+355	0
+356	0
+357	0
+358	0
+359	0
+360	0
+361	0
+362	0
+363	0
+364	0
+365	1
+366	0
+367	0
+368	1
+369	0
+370	0
+371	0
+372	0
+373	0
+374	0
+375	0
+376	0
+377	0
+378	0
+379	0
+380	0
+381	0
+382	0
+383	0
+384	0
+385	0
+386	0
+387	0
+388	0
+389	1
+390	0
+391	0
+392	0
+393	0
+394	0
+395	0
+396	1
+397	0
+398	0
+399	0
+400	0
+401	0
+402	0
+403	0
+404	0
+405	1
+406	0
+407	0
+408	0
+409	0
+410	0
+411	0
+412	0
+413	0
+414	0
+415	0
+416	0
+417	0
+418	0
+419	0
+420	0
+421	0
+422	0
+423	0
+424	0
+425	0
+426	0
+427	0
+428	0
+429	0
+430	0
+431	0
+432	0
+433	0
+434	0
+435	0
+436	0
+437	0
+438	0
+439	0
+440	0
+441	0
+442	0
+443	0
+444	0
+445	0
+446	0
+447	1
+448	0
+449	0
+450	0
+451	0
+452	0
+453	0
+454	0
+455	0
+456	0
+457	0
+458	0
+459	0
+460	1
+461	0
+462	0
+463	0
+464	1
+465	0
+466	0
+467	0
+468	0
+469	0
+470	0
+471	0
+472	0
+473	0
+474	0
+475	0
+476	0
+477	0
+478	0
+479	0
+480	0
+481	0
+482	0
+483	0
+484	0
+485	0
+486	0
+487	0
+488	0
+489	0
+490	0
+491	0
+492	1
+493	0
+494	0
+495	0
+496	0
+497	0
+498	0
+499	0
+500	1
+501	1
+502	1
+503	0
+504	1
+505	1
+506	1
+507	1
+508	1
+509	1
+510	1
+511	1
+512	0
+513	1
+514	1
+515	1
+516	1
+517	1
+518	0
+519	1
+520	1
+521	1
+522	1
+523	1
+524	1
+525	1
+526	1
+527	1
+528	1
+529	1
+530	1
+531	1
+532	1
+533	1
+534	1
+535	1
+536	1
+537	0
+538	1
+539	1
+540	1
+541	1
+542	0
+543	1
+544	1
+545	1
+546	1
+547	1
+548	1
+549	1
+550	1
+551	1
+552	1
+553	1
+554	1
+555	1
+556	1
+557	1
+558	1
+559	1
+560	1
+561	1
+562	1
+563	1
+564	1
+565	1
+566	1
+567	1
+568	1
+569	1
+570	1
+571	1
+572	0
+573	1
+574	1
+575	1
+576	1
+577	1
+578	1
+579	0
+580	1
+581	1
+582	1
+583	1
+584	1
+585	1
+586	0
+587	0
+588	0
+589	1
+590	1
+591	1
+592	1
+593	1
+594	1
+595	1
+596	1
+597	1
+598	1
+599	1
+600	1
+601	1
+602	1
+603	1
+604	1
+605	1
+606	1
+607	1
+608	1
+609	0
+610	1
+611	1
+612	1
+613	1
+614	1
+615	1
+616	0
+617	1
+618	1
+619	1
+620	1
+621	0
+622	1
+623	1
+624	0
+625	1
+626	1
+627	1
+628	1
+629	0
+630	1
+631	1
+632	1
+633	1
+634	1
+635	0
+636	0
+637	1
+638	1
+639	1
+640	1
+641	1
+642	1
+643	1
+644	1
+645	1
+646	1
+647	1
+648	1
+649	1
+650	1
+651	1
+652	1
+653	1
+654	1
+655	1
+656	1
+657	1
+658	1
+659	0
+660	1
+661	1
+662	1
+663	1
+664	0
+665	1
+666	1
+667	1
+668	1
+669	1
+670	1
+671	1
+672	0
+673	1
+674	1
+675	1
+676	1
+677	1
+678	1
+679	1
+680	1
+681	1
+682	1
+683	1
+684	1
+685	1
+686	1
+687	1
+688	1
+689	1
+690	1
+691	1
+692	1
+693	1
+694	1
+695	1
+696	1
+697	1
+698	1
+699	1
+700	1
+701	1
+702	0
+703	1
+704	1
+705	0
+706	1
+707	1
+708	1
+709	1
+710	1
+711	1
+712	1
+713	1
+714	0
+715	1
+716	0
+717	1
+718	1
+719	1
+720	1
+721	1
+722	1
+723	1
+724	1
+725	0
+726	1
+727	1
+728	1
+729	1
+730	1
+731	1
+732	1
+733	1
+734	1
+735	1
+736	1
+737	1
+738	1
+739	1
+740	1
+741	1
+742	1
+743	1
+744	1
+745	1
+746	1
+747	1
+748	1
+749	1
+750	1
+751	1
+752	1
+753	1
+754	1
+755	1
+756	1
+757	1
+758	1
+759	1
+760	1
+761	1
+762	0
+763	1
+764	1
+765	1
+766	1
+767	1
+768	1
+769	1
+770	1
+771	1
+772	1
+773	1
+774	1
+775	1
+776	1
+777	1
+778	1
+779	1
+780	0
+781	1
+782	1
+783	1
+784	1
+785	1
+786	1
+787	1
+788	1
+789	1
+790	1
+791	1
+792	1
+793	1
+794	1
+795	1
+796	1
+797	1
+798	1
+799	1
+800	1
+801	0
+802	1
+803	1
+804	1
+805	1
+806	1
+807	1
+808	1
+809	1
+810	1
+811	1
+812	1
+813	1
+814	1
+815	1
+816	1
+817	1
+818	1
+819	1
+820	1
+821	1
+822	1
+823	1
+824	1
+825	1
+826	1
+827	1
+828	1
+829	1
+830	1
+831	1
+832	1
+833	1
+834	1
+835	1
+836	1
+837	1
+838	1
+839	1
+840	1
+841	1
+842	0
+843	0
+844	1
+845	1
+846	1
+847	1
+848	0
+849	1
+850	1
+851	1
+852	1
+853	1
+854	1
+855	1
+856	1
+857	1
+858	1
+859	1
+860	1
+861	1
+862	1
+863	1
+864	1
+865	1
+866	1
+867	1
+868	1
+869	1
+870	1
+871	1
+872	1
+873	1
+874	1
+875	1
+876	0
+877	1
+878	1
+879	1
+880	1
+881	1
+882	1
+883	1
+884	1
+885	1
+886	0
+887	1
+888	1
+889	1
+890	1
+891	1
+892	1
+893	1
+894	1
+895	1
+896	1
+897	1
+898	1
+899	1
+900	0
+901	1
+902	1
+903	1
+904	1
+905	1
+906	1
+907	1
+908	1
+909	1
+910	1
+911	1
+912	1
+913	1
+914	1
+915	1
+916	0
+917	1
+918	1
+919	1
+920	0
+921	1
+922	1
+923	1
+924	1
+925	1
+926	1
+927	1
+928	1
+929	1
+930	1
+931	1
+932	1
+933	1
+934	1
+935	1
+936	1
+937	1
+938	1
+939	1
+940	1
+941	1
+942	1
+943	1
+944	1
+945	1
+946	1
+947	0
+948	1
+949	1
+950	1
+951	1
+952	0
+953	1
+954	0
+955	1
+956	0
+957	1
+958	1
+959	1
+960	0
+961	1
+962	1
+963	1
+964	1
+965	1
+966	1
+967	1
+968	1
+969	1
+970	1
+971	1
+972	1
+973	1
+974	1
+975	1
+976	1
+977	0
+978	1
+979	1
+980	1
+981	1
+982	1
+983	1
+984	1
+985	1
+986	1
+987	1
+988	1
+989	1
+990	1
+991	1
+992	0
+993	1
+994	1
+995	1
+996	1
+997	1
+998	1
+999	1

special_tokens_map (1).json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config (1).json

@@ -0,0 +1,55 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

train_results (1).json

@@ -0,0 +1,8 @@
+{
+    "epoch": 11.0,
+    "train_loss": 0.0872608635859056,
+    "train_runtime": 5767.3328,
+    "train_samples": 7998,
+    "train_samples_per_second": 15.255,
+    "train_steps_per_second": 0.477
+}

trainer_state (1).json

@@ -0,0 +1,65 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 11.0,
+  "eval_steps": 500,
+  "global_step": 2750,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 2.0,
+      "grad_norm": 8.074329376220703,
+      "learning_rate": 1.6363636363636366e-05,
+      "loss": 0.341,
+      "step": 500
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.7640824913978577,
+      "learning_rate": 1.2727272727272728e-05,
+      "loss": 0.0878,
+      "step": 1000
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 69.4479751586914,
+      "learning_rate": 9.090909090909091e-06,
+      "loss": 0.0308,
+      "step": 1500
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 61.59275817871094,
+      "learning_rate": 5.4545454545454545e-06,
+      "loss": 0.0136,
+      "step": 2000
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 0.014042490161955357,
+      "learning_rate": 1.8181818181818183e-06,
+      "loss": 0.0051,
+      "step": 2500
+    },
+    {
+      "epoch": 11.0,
+      "step": 2750,
+      "total_flos": 8.198945748287078e+16,
+      "train_loss": 0.0872608635859056,
+      "train_runtime": 5767.3328,
+      "train_samples_per_second": 15.255,
+      "train_steps_per_second": 0.477
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2750,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 11,
+  "save_steps": 500,
+  "total_flos": 8.198945748287078e+16,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

training_args (1).bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4e8412eb58689d6154e81d7d38dc817f724132fb7d0d9b47ec30f0baf67aa23
+size 4920