Add best model

README.md

@@ -0,0 +1,76 @@
+---
+language:
+- es
+license: cc-by-4.0
+tags:
+- generated_from_trainer
+datasets:
+- jorgeortizfuentes/toxicity_spanish_hate_speech_v2
+metrics:
+- f1
+model-index:
+- name: hate_speech-dv2-patana-chilean-spanish-bert-8k0iqdv2
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: jorgeortizfuentes/toxicity_spanish_hate_speech_v2
+      type: jorgeortizfuentes/toxicity_spanish_hate_speech_v2
+      config: null
+      split: validation
+    metrics:
+    - name: F1
+      type: f1
+      value: 0.8160919540229885
+---
+
+<!-- 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. -->
+
+# hate_speech-dv2-patana-chilean-spanish-bert-8k0iqdv2
+
+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_hate_speech_v2 dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1628
+- F1: 0.8161
+
+## 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: 4e-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     |
+|:-------------:|:-----:|:----:|:---------------:|:------:|
+| 0.0528        | 5.0   | 430  | 0.1698          | 0.7376 |
+| 0.003         | 10.0  | 860  | 0.1628          | 0.8161 |
+
+
+### 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": 0.02791861295700073,
+    "train_runtime": 1253.6999,
+    "train_samples": 10892,
+    "train_samples_per_second": 86.879,
+    "train_steps_per_second": 0.686
+}

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 sha256:2f57e8823e33c33f434989923de54a95f04b81a615e652a5182bd0eea7c7ef1a
+size 439437392

checkpoint-500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30cf7c4b726a1bfee5f14681bbb4a13fa94e62f02873bceeb79a6352489f18f1
+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 sha256:6c9fc6b0c905660fa8c460753a9a9c807f4dbd7b8107893a7b6adabd9e9130ac
+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": 5.813953488372093,
+  "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": 2e-05,
+      "loss": 0.0528,
+      "step": 430
+    },
+    {
+      "epoch": 5.0,
+      "eval_f1": 0.7376237623762376,
+      "eval_loss": 0.1697508543729782,
+      "eval_runtime": 11.9306,
+      "eval_samples_per_second": 228.236,
+      "eval_steps_per_second": 1.844,
+      "step": 430
+    }
+  ],
+  "max_steps": 860,
+  "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 sha256:285887ee7fbb469bfaa4eb3d94b7655d5d9b9295c618ac1d0ddf4da4b61d80db
+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 sha256:9e0ecabdde1a6ed35d4fa5d6164b63cd9a2d7f35fb475a45c369d43b174781fe
+size 439437392

predict_results_hate_speech.txt

@@ -0,0 +1,801 @@
+index	prediction
+0	0
+1	0
+2	0
+3	0
+4	0
+5	0
+6	0
+7	0
+8	0
+9	0
+10	0
+11	0
+12	0
+13	0
+14	0
+15	0
+16	0
+17	0
+18	0
+19	0
+20	0
+21	0
+22	1
+23	0
+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	0
+39	0
+40	0
+41	0
+42	0
+43	0
+44	0
+45	0
+46	0
+47	0
+48	0
+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	0
+71	0
+72	0
+73	0
+74	0
+75	0
+76	0
+77	0
+78	0
+79	0
+80	0
+81	0
+82	0
+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	0
+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	0
+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	0
+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	0
+165	0
+166	0
+167	0
+168	0
+169	0
+170	0
+171	1
+172	0
+173	0
+174	0
+175	0
+176	0
+177	0
+178	0
+179	0
+180	0
+181	0
+182	0
+183	0
+184	0
+185	0
+186	0
+187	0
+188	0
+189	0
+190	0
+191	0
+192	0
+193	0
+194	0
+195	0
+196	0
+197	0
+198	0
+199	1
+200	0
+201	0
+202	0
+203	0
+204	0
+205	0
+206	0
+207	0
+208	0
+209	0
+210	0
+211	0
+212	0
+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	0
+234	0
+235	0
+236	0
+237	0
+238	0
+239	0
+240	0
+241	0
+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	0
+256	0
+257	0
+258	0
+259	0
+260	0
+261	0
+262	0
+263	0
+264	0
+265	0
+266	0
+267	1
+268	0
+269	0
+270	0
+271	0
+272	0
+273	0
+274	0
+275	0
+276	0
+277	0
+278	0
+279	0
+280	0
+281	0
+282	1
+283	0
+284	0
+285	0
+286	0
+287	0
+288	0
+289	0
+290	0
+291	0
+292	0
+293	0
+294	0
+295	0
+296	0
+297	0
+298	0
+299	0
+300	0
+301	0
+302	0
+303	0
+304	0
+305	0
+306	0
+307	0
+308	0
+309	0
+310	0
+311	0
+312	0
+313	0
+314	0
+315	0
+316	1
+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	0
+331	0
+332	0
+333	0
+334	0
+335	0
+336	0
+337	0
+338	0
+339	0
+340	0
+341	0
+342	0
+343	0
+344	0
+345	0
+346	0
+347	0
+348	0
+349	0
+350	0
+351	0
+352	0
+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	0
+366	0
+367	0
+368	0
+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	0
+390	0
+391	0
+392	0
+393	0
+394	0
+395	0
+396	0
+397	0
+398	0
+399	0
+400	0
+401	0
+402	0
+403	0
+404	0
+405	0
+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	0
+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	0
+461	0
+462	0
+463	0
+464	0
+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	0
+493	0
+494	0
+495	0
+496	0
+497	0
+498	0
+499	0
+500	0
+501	0
+502	0
+503	0
+504	0
+505	0
+506	1
+507	0
+508	0
+509	0
+510	0
+511	1
+512	0
+513	0
+514	0
+515	0
+516	0
+517	0
+518	0
+519	0
+520	0
+521	0
+522	0
+523	0
+524	0
+525	0
+526	0
+527	0
+528	0
+529	0
+530	0
+531	0
+532	0
+533	0
+534	0
+535	0
+536	0
+537	0
+538	0
+539	0
+540	0
+541	1
+542	0
+543	0
+544	0
+545	0
+546	0
+547	0
+548	0
+549	0
+550	0
+551	0
+552	0
+553	0
+554	0
+555	0
+556	0
+557	0
+558	0
+559	0
+560	0
+561	0
+562	0
+563	0
+564	0
+565	0
+566	0
+567	0
+568	0
+569	0
+570	0
+571	0
+572	0
+573	0
+574	0
+575	0
+576	0
+577	0
+578	0
+579	0
+580	0
+581	0
+582	0
+583	0
+584	0
+585	0
+586	0
+587	0
+588	0
+589	0
+590	1
+591	0
+592	0
+593	0
+594	0
+595	0
+596	0
+597	0
+598	0
+599	0
+600	0
+601	0
+602	0
+603	0
+604	0
+605	0
+606	0
+607	0
+608	0
+609	0
+610	0
+611	0
+612	0
+613	0
+614	0
+615	0
+616	0
+617	0
+618	0
+619	0
+620	0
+621	0
+622	0
+623	0
+624	0
+625	0
+626	0
+627	0
+628	0
+629	0
+630	0
+631	0
+632	0
+633	0
+634	0
+635	0
+636	0
+637	0
+638	0
+639	0
+640	1
+641	0
+642	0
+643	0
+644	0
+645	0
+646	0
+647	0
+648	0
+649	0
+650	0
+651	0
+652	0
+653	0
+654	0
+655	0
+656	0
+657	0
+658	0
+659	0
+660	0
+661	0
+662	0
+663	0
+664	0
+665	0
+666	0
+667	0
+668	0
+669	0
+670	0
+671	0
+672	0
+673	0
+674	0
+675	0
+676	0
+677	0
+678	0
+679	0
+680	0
+681	0
+682	0
+683	0
+684	0
+685	1
+686	0
+687	0
+688	0
+689	0
+690	0
+691	0
+692	0
+693	0
+694	0
+695	0
+696	0
+697	0
+698	0
+699	0
+700	0
+701	0
+702	0
+703	0
+704	0
+705	0
+706	0
+707	1
+708	0
+709	0
+710	0
+711	0
+712	0
+713	0
+714	0
+715	0
+716	0
+717	0
+718	0
+719	0
+720	0
+721	0
+722	0
+723	0
+724	0
+725	0
+726	0
+727	0
+728	0
+729	0
+730	0
+731	0
+732	0
+733	0
+734	0
+735	0
+736	0
+737	0
+738	0
+739	0
+740	0
+741	0
+742	0
+743	0
+744	0
+745	0
+746	0
+747	0
+748	0
+749	0
+750	0
+751	0
+752	0
+753	0
+754	0
+755	0
+756	0
+757	0
+758	0
+759	0
+760	0
+761	0
+762	0
+763	0
+764	0
+765	1
+766	0
+767	0
+768	0
+769	0
+770	0
+771	0
+772	0
+773	0
+774	0
+775	0
+776	0
+777	0
+778	0
+779	0
+780	0
+781	0
+782	0
+783	0
+784	0
+785	0
+786	0
+787	0
+788	0
+789	0
+790	0
+791	0
+792	0
+793	0
+794	0
+795	0
+796	0
+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": 0.02791861295700073,
+    "train_runtime": 1253.6999,
+    "train_samples": 10892,
+    "train_samples_per_second": 86.879,
+    "train_steps_per_second": 0.686
+}

trainer_state.json

@@ -0,0 +1,55 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 10.0,
+  "global_step": 860,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 5.0,
+      "learning_rate": 2e-05,
+      "loss": 0.0528,
+      "step": 430
+    },
+    {
+      "epoch": 5.0,
+      "eval_f1": 0.7376237623762376,
+      "eval_loss": 0.1697508543729782,
+      "eval_runtime": 11.9306,
+      "eval_samples_per_second": 228.236,
+      "eval_steps_per_second": 1.844,
+      "step": 430
+    },
+    {
+      "epoch": 10.0,
+      "learning_rate": 0.0,
+      "loss": 0.003,
+      "step": 860
+    },
+    {
+      "epoch": 10.0,
+      "eval_f1": 0.8160919540229885,
+      "eval_loss": 0.16279307007789612,
+      "eval_runtime": 11.9395,
+      "eval_samples_per_second": 228.067,
+      "eval_steps_per_second": 1.843,
+      "step": 860
+    },
+    {
+      "epoch": 10.0,
+      "step": 860,
+      "total_flos": 2.86580561498112e+16,
+      "train_loss": 0.02791861295700073,
+      "train_runtime": 1253.6999,
+      "train_samples_per_second": 86.879,
+      "train_steps_per_second": 0.686
+    }
+  ],
+  "max_steps": 860,
+  "num_train_epochs": 10,
+  "total_flos": 2.86580561498112e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:285887ee7fbb469bfaa4eb3d94b7655d5d9b9295c618ac1d0ddf4da4b61d80db
+size 4027