adding model finetuned on PAWS-X

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 0.8949999809265137,
+    "eval_loss": 0.28261637687683105,
+    "eval_runtime": 0.88,
+    "eval_samples": 2000,
+    "eval_samples_per_second": 2272.75,
+    "eval_steps_per_second": 36.364,
+    "train_loss": 0.14005086088427607,
+    "train_runtime": 226.3922,
+    "train_samples": 49401,
+    "train_samples_per_second": 654.629,
+    "train_steps_per_second": 10.23
+}

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "PlanTL-GOB-ES/roberta-base-bne",
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "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": "4.15.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50262
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 0.8949999809265137,
+    "eval_loss": 0.28261637687683105,
+    "eval_runtime": 0.88,
+    "eval_samples": 2000,
+    "eval_samples_per_second": 2272.75,
+    "eval_steps_per_second": 36.364
+}

events.out.tfevents.1653496254.nodeGPU01.1745454.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97056fc0710b7102dc0d6a879cd1f5b9615ef32063ef52643e47adb510c18019
+size 6715

events.out.tfevents.1653496482.nodeGPU01.1745454.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:198ece4cf965bba889c8da53d8c1b589a574e75a7a3b42de6cf3c1b1f21fba83
+size 363

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:013e383fc52a5356ecdf502ebd3e963acf421e41c3cb4784ac0a3efb4adbae58
+size 498664877

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": false, "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"}, "trim_offsets": true, "max_len": 512, "special_tokens_map_file": null, "name_or_path": "PlanTL-GOB-ES/roberta-base-bne", "tokenizer_class": "RobertaTokenizer"}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "train_loss": 0.14005086088427607,
+    "train_runtime": 226.3922,
+    "train_samples": 49401,
+    "train_samples_per_second": 654.629,
+    "train_steps_per_second": 10.23
+}

trainer_state.json

@@ -0,0 +1,112 @@
+{
+  "best_metric": 0.28261637687683105,
+  "best_model_checkpoint": "/home/fbravo/data/all_results/pawsx/roberta_base_bne/epochs_3_bs_64_lr_3e-5/checkpoint-900",
+  "epoch": 3.0,
+  "global_step": 2316,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.39,
+      "eval_accuracy": 0.8794999718666077,
+      "eval_loss": 0.30226433277130127,
+      "eval_runtime": 0.8479,
+      "eval_samples_per_second": 2358.837,
+      "eval_steps_per_second": 37.741,
+      "step": 300
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 2.3523316062176165e-05,
+      "loss": 0.318,
+      "step": 500
+    },
+    {
+      "epoch": 0.78,
+      "eval_accuracy": 0.8740000128746033,
+      "eval_loss": 0.33601614832878113,
+      "eval_runtime": 0.8536,
+      "eval_samples_per_second": 2343.133,
+      "eval_steps_per_second": 37.49,
+      "step": 600
+    },
+    {
+      "epoch": 1.17,
+      "eval_accuracy": 0.8949999809265137,
+      "eval_loss": 0.28261637687683105,
+      "eval_runtime": 0.8516,
+      "eval_samples_per_second": 2348.387,
+      "eval_steps_per_second": 37.574,
+      "step": 900
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 1.705958549222798e-05,
+      "loss": 0.1498,
+      "step": 1000
+    },
+    {
+      "epoch": 1.55,
+      "eval_accuracy": 0.8949999809265137,
+      "eval_loss": 0.3580223321914673,
+      "eval_runtime": 0.8515,
+      "eval_samples_per_second": 2348.84,
+      "eval_steps_per_second": 37.581,
+      "step": 1200
+    },
+    {
+      "epoch": 1.94,
+      "learning_rate": 1.0582901554404146e-05,
+      "loss": 0.101,
+      "step": 1500
+    },
+    {
+      "epoch": 1.94,
+      "eval_accuracy": 0.8899999856948853,
+      "eval_loss": 0.33210474252700806,
+      "eval_runtime": 0.8482,
+      "eval_samples_per_second": 2357.924,
+      "eval_steps_per_second": 37.727,
+      "step": 1500
+    },
+    {
+      "epoch": 2.33,
+      "eval_accuracy": 0.8939999938011169,
+      "eval_loss": 0.4253285527229309,
+      "eval_runtime": 0.8518,
+      "eval_samples_per_second": 2347.886,
+      "eval_steps_per_second": 37.566,
+      "step": 1800
+    },
+    {
+      "epoch": 2.59,
+      "learning_rate": 4.106217616580311e-06,
+      "loss": 0.0505,
+      "step": 2000
+    },
+    {
+      "epoch": 2.72,
+      "eval_accuracy": 0.8985000252723694,
+      "eval_loss": 0.39427509903907776,
+      "eval_runtime": 0.8509,
+      "eval_samples_per_second": 2350.514,
+      "eval_steps_per_second": 37.608,
+      "step": 2100
+    },
+    {
+      "epoch": 3.0,
+      "step": 2316,
+      "total_flos": 8004352140640256.0,
+      "train_loss": 0.14005086088427607,
+      "train_runtime": 226.3922,
+      "train_samples_per_second": 654.629,
+      "train_steps_per_second": 10.23
+    }
+  ],
+  "max_steps": 2316,
+  "num_train_epochs": 3,
+  "total_flos": 8004352140640256.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0063434af20f6b4bc1126d42e63deaef19180c4c01c916368d1fec317942fa98
+size 3055