Upload 11 files

config.json

@@ -0,0 +1,40 @@
+{
+  "_name_or_path": "airesearch/wangchanberta-base-att-spm-uncased",
+  "architectures": [
+    "CamembertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "negative",
+    "1": "positive",
+    "2": "neutral"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "negative": 0,
+    "neutral": 2,
+    "positive": 1
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "camembert",
+  "num_attention_head": 12,
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 25005
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ebe5fa9b3cfbe1e9248596a60b502c2f9b3ec1e16a8c1dd10a3b5ecdbc091b7b
+size 421011004

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:035bb3eb0535bd42613169511224092bc3d29ec337b67f6470223646a28dd799
+size 842141882

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe14677fe1d08d2475dedba85708d39112206eafc6ad8dffcbe3b1a3af3df3d1
+size 14308

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b64b0d62503196bd681918360b8deb09d34d823b82c38bef3770241d9fb059df
+size 1064

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49c4ba4e495ddf31eb2fdba7fc6aef3c233091d25d35bc9d24694ccf48ae114c
+size 904693

special_tokens_map.json

@@ -0,0 +1,20 @@
+{
+  "additional_special_tokens": [
+    "<s>NOTUSED",
+    "</s>NOTUSED",
+    "<_>"
+  ],
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,84 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>NOTUSED",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>NOTUSED",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "8": {
+      "content": "<_>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "25004": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<s>NOTUSED",
+    "</s>NOTUSED",
+    "<_>"
+  ],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "CamembertTokenizer",
+  "unk_token": "<unk>"
+}

trainer_state.json

@@ -0,0 +1,120 @@
+{
+  "best_metric": 0.7792592592592592,
+  "best_model_checkpoint": "sentiment-analysis-pp/checkpoint-4728",
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 4728,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.42,
+      "grad_norm": 163.66278076171875,
+      "learning_rate": 2.7461928934010155e-05,
+      "loss": 0.9585,
+      "step": 500
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 7.153451919555664,
+      "learning_rate": 2.4923857868020305e-05,
+      "loss": 0.8643,
+      "step": 1000
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.6766666666666666,
+      "eval_loss": 0.7678444981575012,
+      "eval_runtime": 42.3243,
+      "eval_samples_per_second": 63.793,
+      "eval_steps_per_second": 3.993,
+      "step": 1182
+    },
+    {
+      "epoch": 1.27,
+      "grad_norm": 6.358371257781982,
+      "learning_rate": 2.238578680203046e-05,
+      "loss": 0.7115,
+      "step": 1500
+    },
+    {
+      "epoch": 1.69,
+      "grad_norm": 6.753957748413086,
+      "learning_rate": 1.9847715736040607e-05,
+      "loss": 0.6343,
+      "step": 2000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7188888888888889,
+      "eval_loss": 0.6581271290779114,
+      "eval_runtime": 42.3763,
+      "eval_samples_per_second": 63.715,
+      "eval_steps_per_second": 3.988,
+      "step": 2364
+    },
+    {
+      "epoch": 2.12,
+      "grad_norm": 12.652050971984863,
+      "learning_rate": 1.730964467005076e-05,
+      "loss": 0.5684,
+      "step": 2500
+    },
+    {
+      "epoch": 2.54,
+      "grad_norm": 22.428882598876953,
+      "learning_rate": 1.4771573604060913e-05,
+      "loss": 0.4881,
+      "step": 3000
+    },
+    {
+      "epoch": 2.96,
+      "grad_norm": 7.206263542175293,
+      "learning_rate": 1.2233502538071067e-05,
+      "loss": 0.4631,
+      "step": 3500
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7648148148148148,
+      "eval_loss": 0.6259744763374329,
+      "eval_runtime": 42.4889,
+      "eval_samples_per_second": 63.546,
+      "eval_steps_per_second": 3.978,
+      "step": 3546
+    },
+    {
+      "epoch": 3.38,
+      "grad_norm": 7.703592300415039,
+      "learning_rate": 9.695431472081218e-06,
+      "loss": 0.3736,
+      "step": 4000
+    },
+    {
+      "epoch": 3.81,
+      "grad_norm": 11.456498146057129,
+      "learning_rate": 7.15736040609137e-06,
+      "loss": 0.3553,
+      "step": 4500
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.7792592592592592,
+      "eval_loss": 0.623358964920044,
+      "eval_runtime": 42.3946,
+      "eval_samples_per_second": 63.687,
+      "eval_steps_per_second": 3.986,
+      "step": 4728
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 5910,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 1.60063403215968e+16,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec6411f5ede3019f238e193492baa1896d6851aade6b57e4a4b6cd66bf7646f7
+size 4920