Add best model

README.md

@@ -0,0 +1,76 @@
+---
+language:
+- es
+license: cc-by-4.0
+tags:
+- generated_from_trainer
+datasets:
+- jorgeortizfuentes/toxicity_spanish_incivility_v3
+metrics:
+- f1
+model-index:
+- name: incivility-dv3-patana-chilean-spanish-bert-j63zilm4
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: jorgeortizfuentes/toxicity_spanish_incivility_v3
+      type: jorgeortizfuentes/toxicity_spanish_incivility_v3
+      config: null
+      split: validation
+    metrics:
+    - name: F1
+      type: f1
+      value: 0.9135014363230132
+---
+
+<!-- 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. -->
+
+# incivility-dv3-patana-chilean-spanish-bert-j63zilm4
+
+This model is a fine-tuned version of [dccuchile/patana-chilean-spanish-bert](https://huggingface.co/dccuchile/patana-chilean-spanish-bert) on the jorgeortizfuentes/toxicity_spanish_incivility_v3 dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.5672
+- F1: 0.9135
+
+## 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: 5e-05
+- train_batch_size: 128
+- eval_batch_size: 128
+- seed: 13
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 10
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | F1     |
+|:-------------:|:-----:|:----:|:---------------:|:------:|
+| 0.1351        | 5.0   | 455  | 0.4608          | 0.9119 |
+| 0.0114        | 10.0  | 910  | 0.5672          | 0.9135 |
+
+
+### Framework versions
+
+- Transformers 4.30.2
+- Pytorch 2.0.1+cu117
+- Datasets 2.13.1
+- Tokenizers 0.13.3

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 10.0,
+    "train_loss": 0.07324187100588621,
+    "train_runtime": 1328.6278,
+    "train_samples": 11532,
+    "train_samples_per_second": 86.796,
+    "train_steps_per_second": 0.685
+}

checkpoint-500/config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "dccuchile/patana-chilean-spanish-bert",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.30.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 31002
+}

checkpoint-500/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7a94a9dc9567bece3eb5bda1f6cefd37a8b7771530170bdc7c8bbf7f90da457
+size 439437392

checkpoint-500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60be5e28937c469a039569a1bfc30043ee9d65d333b76ae52dabca23b616fa46
+size 878937221

checkpoint-500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d4e6b040ff015bd9b06563b5be216f512e8eb05cf5c40a77247d802ab88208b
+size 14639

checkpoint-500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66d8a82960fdf7511b32f1ea1d794f4a920a406df03a48505d69f0524a4008a9
+size 627

checkpoint-500/special_tokens_map.json

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

checkpoint-500/tokenizer_config.json

@@ -0,0 +1,15 @@
+{
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": false,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": false,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

checkpoint-500/trainer_state.json

@@ -0,0 +1,31 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 5.4945054945054945,
+  "global_step": 500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 5.0,
+      "learning_rate": 2.5e-05,
+      "loss": 0.1351,
+      "step": 455
+    },
+    {
+      "epoch": 5.0,
+      "eval_f1": 0.9119336311423102,
+      "eval_loss": 0.46077126264572144,
+      "eval_runtime": 12.6487,
+      "eval_samples_per_second": 227.928,
+      "eval_steps_per_second": 1.818,
+      "step": 455
+    }
+  ],
+  "max_steps": 910,
+  "num_train_epochs": 10,
+  "total_flos": 1.66865031309312e+16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04d95d7b3cd606d84475d60127739194a155d83c8f25e04d615b47e74d0649f6
+size 4027

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "dccuchile/patana-chilean-spanish-bert",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.30.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 31002
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f13259ec4a476425b1b2634a412f5a80010b9f686dec362b3c1c9373dbe68ed1
+size 439437392

predict_results_incivility.txt

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

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1,15 @@
+{
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": false,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": false,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 10.0,
+    "train_loss": 0.07324187100588621,
+    "train_runtime": 1328.6278,
+    "train_samples": 11532,
+    "train_samples_per_second": 86.796,
+    "train_steps_per_second": 0.685
+}

trainer_state.json

@@ -0,0 +1,55 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 10.0,
+  "global_step": 910,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 5.0,
+      "learning_rate": 2.5e-05,
+      "loss": 0.1351,
+      "step": 455
+    },
+    {
+      "epoch": 5.0,
+      "eval_f1": 0.9119336311423102,
+      "eval_loss": 0.46077126264572144,
+      "eval_runtime": 12.6487,
+      "eval_samples_per_second": 227.928,
+      "eval_steps_per_second": 1.818,
+      "step": 455
+    },
+    {
+      "epoch": 10.0,
+      "learning_rate": 0.0,
+      "loss": 0.0114,
+      "step": 910
+    },
+    {
+      "epoch": 10.0,
+      "eval_f1": 0.9135014363230132,
+      "eval_loss": 0.567248523235321,
+      "eval_runtime": 12.6489,
+      "eval_samples_per_second": 227.925,
+      "eval_steps_per_second": 1.818,
+      "step": 910
+    },
+    {
+      "epoch": 10.0,
+      "step": 910,
+      "total_flos": 3.03419669041152e+16,
+      "train_loss": 0.07324187100588621,
+      "train_runtime": 1328.6278,
+      "train_samples_per_second": 86.796,
+      "train_steps_per_second": 0.685
+    }
+  ],
+  "max_steps": 910,
+  "num_train_epochs": 10,
+  "total_flos": 3.03419669041152e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04d95d7b3cd606d84475d60127739194a155d83c8f25e04d615b47e74d0649f6
+size 4027