adding model finetuned on PAWS-X

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 2.0,
+    "eval_accuracy": 0.890999972820282,
+    "eval_loss": 0.276936411857605,
+    "eval_runtime": 2.0572,
+    "eval_samples": 2000,
+    "eval_samples_per_second": 972.216,
+    "eval_steps_per_second": 30.625,
+    "train_loss": 0.17663975268447954,
+    "train_runtime": 500.8558,
+    "train_samples": 49401,
+    "train_samples_per_second": 197.266,
+    "train_steps_per_second": 6.165
+}

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "PlanTL-GOB-ES/roberta-large-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": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "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": 2.0,
+    "eval_accuracy": 0.890999972820282,
+    "eval_loss": 0.276936411857605,
+    "eval_runtime": 2.0572,
+    "eval_samples": 2000,
+    "eval_samples_per_second": 972.216,
+    "eval_steps_per_second": 30.625
+}

events.out.tfevents.1653522238.nodeGPU01.2119856.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5cb1805824cda2749a5eb39820478d77d7cc5358eb3ce5f572186b5283b9559a
+size 8003

events.out.tfevents.1653522744.nodeGPU01.2119856.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be75ce57c008c948c09bc70cd0ef19293af77cd6684bb8ade81e5c47fb7c8c46
+size 363

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d92ee65a42a8e0cdb5c092412539a1bd865b6acca706c98abccaf65736d5ba0
+size 1421599021

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

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.0,
+    "train_loss": 0.17663975268447954,
+    "train_runtime": 500.8558,
+    "train_samples": 49401,
+    "train_samples_per_second": 197.266,
+    "train_steps_per_second": 6.165
+}

trainer_state.json

@@ -0,0 +1,151 @@
+{
+  "best_metric": 0.276936411857605,
+  "best_model_checkpoint": "/home/fbravo/data/all_results/pawsx/roberta_large_bne/epochs_2_bs_32_lr_1e-5/checkpoint-1200",
+  "epoch": 2.0,
+  "global_step": 3088,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.19,
+      "eval_accuracy": 0.859499990940094,
+      "eval_loss": 0.36283692717552185,
+      "eval_runtime": 2.0197,
+      "eval_samples_per_second": 990.267,
+      "eval_steps_per_second": 31.193,
+      "step": 300
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 8.380829015544043e-06,
+      "loss": 0.3845,
+      "step": 500
+    },
+    {
+      "epoch": 0.39,
+      "eval_accuracy": 0.871999979019165,
+      "eval_loss": 0.3212876617908478,
+      "eval_runtime": 2.0153,
+      "eval_samples_per_second": 992.393,
+      "eval_steps_per_second": 31.26,
+      "step": 600
+    },
+    {
+      "epoch": 0.58,
+      "eval_accuracy": 0.890999972820282,
+      "eval_loss": 0.281432181596756,
+      "eval_runtime": 2.0204,
+      "eval_samples_per_second": 989.885,
+      "eval_steps_per_second": 31.181,
+      "step": 900
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 6.764896373056995e-06,
+      "loss": 0.2115,
+      "step": 1000
+    },
+    {
+      "epoch": 0.78,
+      "eval_accuracy": 0.890999972820282,
+      "eval_loss": 0.276936411857605,
+      "eval_runtime": 2.0133,
+      "eval_samples_per_second": 993.395,
+      "eval_steps_per_second": 31.292,
+      "step": 1200
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 5.1457253886010375e-06,
+      "loss": 0.1843,
+      "step": 1500
+    },
+    {
+      "epoch": 0.97,
+      "eval_accuracy": 0.8934999704360962,
+      "eval_loss": 0.2994357943534851,
+      "eval_runtime": 2.0148,
+      "eval_samples_per_second": 992.653,
+      "eval_steps_per_second": 31.269,
+      "step": 1500
+    },
+    {
+      "epoch": 1.17,
+      "eval_accuracy": 0.9010000228881836,
+      "eval_loss": 0.3649846911430359,
+      "eval_runtime": 2.0177,
+      "eval_samples_per_second": 991.23,
+      "eval_steps_per_second": 31.224,
+      "step": 1800
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 3.5265544041450777e-06,
+      "loss": 0.1041,
+      "step": 2000
+    },
+    {
+      "epoch": 1.36,
+      "eval_accuracy": 0.902999997138977,
+      "eval_loss": 0.3713494837284088,
+      "eval_runtime": 2.0175,
+      "eval_samples_per_second": 991.324,
+      "eval_steps_per_second": 31.227,
+      "step": 2100
+    },
+    {
+      "epoch": 1.55,
+      "eval_accuracy": 0.8995000123977661,
+      "eval_loss": 0.380949467420578,
+      "eval_runtime": 2.0124,
+      "eval_samples_per_second": 993.836,
+      "eval_steps_per_second": 31.306,
+      "step": 2400
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 1.9073834196891196e-06,
+      "loss": 0.0994,
+      "step": 2500
+    },
+    {
+      "epoch": 1.75,
+      "eval_accuracy": 0.8974999785423279,
+      "eval_loss": 0.34086307883262634,
+      "eval_runtime": 2.0134,
+      "eval_samples_per_second": 993.346,
+      "eval_steps_per_second": 31.29,
+      "step": 2700
+    },
+    {
+      "epoch": 1.94,
+      "learning_rate": 2.9145077720207257e-07,
+      "loss": 0.09,
+      "step": 3000
+    },
+    {
+      "epoch": 1.94,
+      "eval_accuracy": 0.902999997138977,
+      "eval_loss": 0.3528608977794647,
+      "eval_runtime": 2.0143,
+      "eval_samples_per_second": 992.921,
+      "eval_steps_per_second": 31.277,
+      "step": 3000
+    },
+    {
+      "epoch": 2.0,
+      "step": 3088,
+      "total_flos": 1.7847300994891776e+16,
+      "train_loss": 0.17663975268447954,
+      "train_runtime": 500.8558,
+      "train_samples_per_second": 197.266,
+      "train_steps_per_second": 6.165
+    }
+  ],
+  "max_steps": 3088,
+  "num_train_epochs": 2,
+  "total_flos": 1.7847300994891776e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e745315485c3f5b70da391745ad3568b72c9a0a381a9e9ff1174ef109211ab21
+size 3055