upload model

all_results.json

@@ -0,0 +1,19 @@
+{
+    "epoch": 10.0,
+    "eval_accuracy": 0.8090737462043762,
+    "eval_loss": 1.4761372804641724,
+    "eval_runtime": 15.9645,
+    "eval_samples": 2117,
+    "eval_samples_per_second": 132.544,
+    "eval_steps_per_second": 4.197,
+    "predict_accuracy": 0.7912139892578125,
+    "predict_loss": 1.6161744594573975,
+    "predict_runtime": 16.0928,
+    "predict_samples_per_second": 131.55,
+    "predict_steps_per_second": 4.163,
+    "train_loss": 0.1654055107068024,
+    "train_runtime": 5360.0658,
+    "train_samples": 16930,
+    "train_samples_per_second": 31.585,
+    "train_steps_per_second": 0.987
+}

config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "BSC-TeMU/roberta-base-ca",
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "finetuning_task": "textual-entailment",
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "ENTAILMENT",
+    "1": "NEUTRAL",
+    "2": "CONTRADICTION"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "ENTAILMENT": 0,
+    "NEUTRAL": 1,
+    "CONTRADICTION": 2
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "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": "4.9.1",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 52000
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 10.0,
+    "eval_accuracy": 0.8090737462043762,
+    "eval_loss": 1.4761372804641724,
+    "eval_runtime": 15.9645,
+    "eval_samples": 2116,
+    "eval_samples_per_second": 132.544,
+    "eval_steps_per_second": 4.197
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d56f1dcd9072d54c03b8571a6ef27332b68c6999985ac26e2bda02e09466d01
+size 504010159

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1 @@
+{"unk_token": {"content": "<unk>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_prefix_space": true, "errors": "replace", "sep_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "cls_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "pad_token": {"content": "<pad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "max_len": 512, "special_tokens_map_file": null, "name_or_path": "BSC-TeMU/roberta-base-ca", "tokenizer_class": "RobertaTokenizer"}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 10.0,
+    "train_loss": 0.1654055107068024,
+    "train_runtime": 5360.0658,
+    "train_samples": 16930,
+    "train_samples_per_second": 31.585,
+    "train_steps_per_second": 0.987
+}

trainer_state.json

@@ -0,0 +1,175 @@
+{
+  "best_metric": 0.8090737462043762,
+  "best_model_checkpoint": "/home/ccasimiro/ccasimiro/berta/src/finetuning/te/roberta-base-ca-cased-te/checkpoint-5290",
+  "epoch": 9.999055712936732,
+  "global_step": 5290,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.94,
+      "learning_rate": 4.527410207939509e-05,
+      "loss": 0.7295,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7693761587142944,
+      "eval_loss": 0.5496639013290405,
+      "eval_runtime": 15.769,
+      "eval_samples_per_second": 134.188,
+      "eval_steps_per_second": 4.249,
+      "step": 529
+    },
+    {
+      "epoch": 1.89,
+      "learning_rate": 4.054820415879017e-05,
+      "loss": 0.4162,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.782136082649231,
+      "eval_loss": 0.5493781566619873,
+      "eval_runtime": 15.7381,
+      "eval_samples_per_second": 134.45,
+      "eval_steps_per_second": 4.257,
+      "step": 1058
+    },
+    {
+      "epoch": 2.83,
+      "learning_rate": 3.582230623818525e-05,
+      "loss": 0.237,
+      "step": 1500
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7948960065841675,
+      "eval_loss": 0.6657664179801941,
+      "eval_runtime": 15.8042,
+      "eval_samples_per_second": 133.888,
+      "eval_steps_per_second": 4.239,
+      "step": 1587
+    },
+    {
+      "epoch": 3.78,
+      "learning_rate": 3.1096408317580344e-05,
+      "loss": 0.1316,
+      "step": 2000
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.79347825050354,
+      "eval_loss": 0.910639226436615,
+      "eval_runtime": 15.913,
+      "eval_samples_per_second": 132.973,
+      "eval_steps_per_second": 4.21,
+      "step": 2116
+    },
+    {
+      "epoch": 4.73,
+      "learning_rate": 2.637051039697543e-05,
+      "loss": 0.0853,
+      "step": 2500
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.8057655692100525,
+      "eval_loss": 1.0349944829940796,
+      "eval_runtime": 15.8236,
+      "eval_samples_per_second": 133.724,
+      "eval_steps_per_second": 4.234,
+      "step": 2645
+    },
+    {
+      "epoch": 5.67,
+      "learning_rate": 2.1644612476370512e-05,
+      "loss": 0.0593,
+      "step": 3000
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.8010396957397461,
+      "eval_loss": 1.2216821908950806,
+      "eval_runtime": 15.8613,
+      "eval_samples_per_second": 133.407,
+      "eval_steps_per_second": 4.224,
+      "step": 3174
+    },
+    {
+      "epoch": 6.62,
+      "learning_rate": 1.6918714555765597e-05,
+      "loss": 0.0384,
+      "step": 3500
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.8010396957397461,
+      "eval_loss": 1.3548704385757446,
+      "eval_runtime": 15.9719,
+      "eval_samples_per_second": 132.483,
+      "eval_steps_per_second": 4.195,
+      "step": 3703
+    },
+    {
+      "epoch": 7.56,
+      "learning_rate": 1.2192816635160681e-05,
+      "loss": 0.0231,
+      "step": 4000
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.8024574518203735,
+      "eval_loss": 1.385912537574768,
+      "eval_runtime": 15.9537,
+      "eval_samples_per_second": 132.633,
+      "eval_steps_per_second": 4.2,
+      "step": 4232
+    },
+    {
+      "epoch": 8.51,
+      "learning_rate": 7.466918714555767e-06,
+      "loss": 0.0142,
+      "step": 4500
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.8062381744384766,
+      "eval_loss": 1.4750466346740723,
+      "eval_runtime": 15.969,
+      "eval_samples_per_second": 132.507,
+      "eval_steps_per_second": 4.196,
+      "step": 4761
+    },
+    {
+      "epoch": 9.45,
+      "learning_rate": 2.741020793950851e-06,
+      "loss": 0.0118,
+      "step": 5000
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.8090737462043762,
+      "eval_loss": 1.4761372804641724,
+      "eval_runtime": 15.9022,
+      "eval_samples_per_second": 133.064,
+      "eval_steps_per_second": 4.213,
+      "step": 5290
+    },
+    {
+      "epoch": 10.0,
+      "step": 5290,
+      "total_flos": 1.1136143848628736e+16,
+      "train_loss": 0.1654055107068024,
+      "train_runtime": 5360.0658,
+      "train_samples_per_second": 31.585,
+      "train_steps_per_second": 0.987
+    }
+  ],
+  "max_steps": 5290,
+  "num_train_epochs": 10,
+  "total_flos": 1.1136143848628736e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:767fab7545b0cbbfae578348bab15195548649b2efccfd04a94d1b1bdabf1723
+size 49074176