adding model finetuned on PAWS-X

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 4.0,
+    "eval_accuracy": 0.8709999918937683,
+    "eval_loss": 0.3038647472858429,
+    "eval_runtime": 0.9597,
+    "eval_samples": 2000,
+    "eval_samples_per_second": 2084.017,
+    "eval_steps_per_second": 65.647,
+    "train_loss": 0.12696161927954522,
+    "train_runtime": 470.6783,
+    "train_samples": 49401,
+    "train_samples_per_second": 419.828,
+    "train_steps_per_second": 13.121
+}

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "bertin-project/bertin-roberta-base-spanish",
+  "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": 4.0,
+    "eval_accuracy": 0.8709999918937683,
+    "eval_loss": 0.3038647472858429,
+    "eval_runtime": 0.9597,
+    "eval_samples": 2000,
+    "eval_samples_per_second": 2084.017,
+    "eval_steps_per_second": 65.647
+}

events.out.tfevents.1658152153.nodeGPU01.2524808.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:971e7f6ec3be2fd7fc4993016df9e9cefd0aa0512795e44ac2bd3bc1959ddd9b
+size 12191

events.out.tfevents.1658152626.nodeGPU01.2524808.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c784a01561344fb5a69df626e54bd3fd401f0cefd0681f39c194dd10608150b8
+size 363

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75ba5b81f3cc948737094b7418718e1a17c9494305b5d3ec7fdb0d380c6506ab
+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": "bertin-project/bertin-roberta-base-spanish", "tokenizer_class": "RobertaTokenizer"}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 4.0,
+    "train_loss": 0.12696161927954522,
+    "train_runtime": 470.6783,
+    "train_samples": 49401,
+    "train_samples_per_second": 419.828,
+    "train_steps_per_second": 13.121
+}

trainer_state.json

@@ -0,0 +1,277 @@
+{
+  "best_metric": 0.3038647472858429,
+  "best_model_checkpoint": "/home/fbravo/data/all_results/pawsx/bertin_roberta_base/epochs_4_bs_32_lr_1e-5/checkpoint-1500",
+  "epoch": 4.0,
+  "global_step": 6176,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.19,
+      "eval_accuracy": 0.7979999780654907,
+      "eval_loss": 0.4853031635284424,
+      "eval_runtime": 0.9414,
+      "eval_samples_per_second": 2124.606,
+      "eval_steps_per_second": 66.925,
+      "step": 300
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 9.193652849740934e-06,
+      "loss": 0.4315,
+      "step": 500
+    },
+    {
+      "epoch": 0.39,
+      "eval_accuracy": 0.8364999890327454,
+      "eval_loss": 0.3721293807029724,
+      "eval_runtime": 0.9441,
+      "eval_samples_per_second": 2118.529,
+      "eval_steps_per_second": 66.734,
+      "step": 600
+    },
+    {
+      "epoch": 0.58,
+      "eval_accuracy": 0.8544999957084656,
+      "eval_loss": 0.3503261208534241,
+      "eval_runtime": 0.9463,
+      "eval_samples_per_second": 2113.472,
+      "eval_steps_per_second": 66.574,
+      "step": 900
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 8.384067357512954e-06,
+      "loss": 0.25,
+      "step": 1000
+    },
+    {
+      "epoch": 0.78,
+      "eval_accuracy": 0.8709999918937683,
+      "eval_loss": 0.31852295994758606,
+      "eval_runtime": 0.9416,
+      "eval_samples_per_second": 2123.951,
+      "eval_steps_per_second": 66.904,
+      "step": 1200
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 7.574481865284975e-06,
+      "loss": 0.2072,
+      "step": 1500
+    },
+    {
+      "epoch": 0.97,
+      "eval_accuracy": 0.8709999918937683,
+      "eval_loss": 0.3038647472858429,
+      "eval_runtime": 0.9413,
+      "eval_samples_per_second": 2124.819,
+      "eval_steps_per_second": 66.932,
+      "step": 1500
+    },
+    {
+      "epoch": 1.17,
+      "eval_accuracy": 0.8684999942779541,
+      "eval_loss": 0.41912218928337097,
+      "eval_runtime": 0.9381,
+      "eval_samples_per_second": 2132.007,
+      "eval_steps_per_second": 67.158,
+      "step": 1800
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 6.766515544041451e-06,
+      "loss": 0.1311,
+      "step": 2000
+    },
+    {
+      "epoch": 1.36,
+      "eval_accuracy": 0.8600000143051147,
+      "eval_loss": 0.4942796230316162,
+      "eval_runtime": 0.9429,
+      "eval_samples_per_second": 2121.101,
+      "eval_steps_per_second": 66.815,
+      "step": 2100
+    },
+    {
+      "epoch": 1.55,
+      "eval_accuracy": 0.8654999732971191,
+      "eval_loss": 0.4631992280483246,
+      "eval_runtime": 0.9996,
+      "eval_samples_per_second": 2000.899,
+      "eval_steps_per_second": 63.028,
+      "step": 2400
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 5.956930051813472e-06,
+      "loss": 0.1229,
+      "step": 2500
+    },
+    {
+      "epoch": 1.75,
+      "eval_accuracy": 0.8569999933242798,
+      "eval_loss": 0.48928430676460266,
+      "eval_runtime": 0.9369,
+      "eval_samples_per_second": 2134.751,
+      "eval_steps_per_second": 67.245,
+      "step": 2700
+    },
+    {
+      "epoch": 1.94,
+      "learning_rate": 5.147344559585493e-06,
+      "loss": 0.1193,
+      "step": 3000
+    },
+    {
+      "epoch": 1.94,
+      "eval_accuracy": 0.8640000224113464,
+      "eval_loss": 0.538551390171051,
+      "eval_runtime": 0.9376,
+      "eval_samples_per_second": 2133.008,
+      "eval_steps_per_second": 67.19,
+      "step": 3000
+    },
+    {
+      "epoch": 2.14,
+      "eval_accuracy": 0.8650000095367432,
+      "eval_loss": 0.5807957649230957,
+      "eval_runtime": 0.9434,
+      "eval_samples_per_second": 2119.923,
+      "eval_steps_per_second": 66.778,
+      "step": 3300
+    },
+    {
+      "epoch": 2.27,
+      "learning_rate": 4.337759067357513e-06,
+      "loss": 0.0718,
+      "step": 3500
+    },
+    {
+      "epoch": 2.33,
+      "eval_accuracy": 0.8730000257492065,
+      "eval_loss": 0.5360826253890991,
+      "eval_runtime": 0.9423,
+      "eval_samples_per_second": 2122.415,
+      "eval_steps_per_second": 66.856,
+      "step": 3600
+    },
+    {
+      "epoch": 2.53,
+      "eval_accuracy": 0.8684999942779541,
+      "eval_loss": 0.6216676235198975,
+      "eval_runtime": 0.946,
+      "eval_samples_per_second": 2114.204,
+      "eval_steps_per_second": 66.597,
+      "step": 3900
+    },
+    {
+      "epoch": 2.59,
+      "learning_rate": 3.5281735751295337e-06,
+      "loss": 0.0637,
+      "step": 4000
+    },
+    {
+      "epoch": 2.72,
+      "eval_accuracy": 0.8659999966621399,
+      "eval_loss": 0.6211779713630676,
+      "eval_runtime": 0.9442,
+      "eval_samples_per_second": 2118.136,
+      "eval_steps_per_second": 66.721,
+      "step": 4200
+    },
+    {
+      "epoch": 2.91,
+      "learning_rate": 2.7202072538860106e-06,
+      "loss": 0.0629,
+      "step": 4500
+    },
+    {
+      "epoch": 2.91,
+      "eval_accuracy": 0.871999979019165,
+      "eval_loss": 0.5773542523384094,
+      "eval_runtime": 0.9435,
+      "eval_samples_per_second": 2119.687,
+      "eval_steps_per_second": 66.77,
+      "step": 4500
+    },
+    {
+      "epoch": 3.11,
+      "eval_accuracy": 0.8669999837875366,
+      "eval_loss": 0.614871084690094,
+      "eval_runtime": 0.942,
+      "eval_samples_per_second": 2123.196,
+      "eval_steps_per_second": 66.881,
+      "step": 4800
+    },
+    {
+      "epoch": 3.24,
+      "learning_rate": 1.9106217616580315e-06,
+      "loss": 0.0385,
+      "step": 5000
+    },
+    {
+      "epoch": 3.3,
+      "eval_accuracy": 0.8679999709129333,
+      "eval_loss": 0.6947777271270752,
+      "eval_runtime": 0.937,
+      "eval_samples_per_second": 2134.496,
+      "eval_steps_per_second": 67.237,
+      "step": 5100
+    },
+    {
+      "epoch": 3.5,
+      "eval_accuracy": 0.8705000281333923,
+      "eval_loss": 0.7105850577354431,
+      "eval_runtime": 0.9421,
+      "eval_samples_per_second": 2122.995,
+      "eval_steps_per_second": 66.874,
+      "step": 5400
+    },
+    {
+      "epoch": 3.56,
+      "learning_rate": 1.1010362694300518e-06,
+      "loss": 0.0308,
+      "step": 5500
+    },
+    {
+      "epoch": 3.69,
+      "eval_accuracy": 0.8679999709129333,
+      "eval_loss": 0.7033668756484985,
+      "eval_runtime": 0.9383,
+      "eval_samples_per_second": 2131.574,
+      "eval_steps_per_second": 67.145,
+      "step": 5700
+    },
+    {
+      "epoch": 3.89,
+      "learning_rate": 2.9145077720207257e-07,
+      "loss": 0.0291,
+      "step": 6000
+    },
+    {
+      "epoch": 3.89,
+      "eval_accuracy": 0.8700000047683716,
+      "eval_loss": 0.7085065841674805,
+      "eval_runtime": 0.9424,
+      "eval_samples_per_second": 2122.247,
+      "eval_steps_per_second": 66.851,
+      "step": 6000
+    },
+    {
+      "epoch": 4.0,
+      "step": 6176,
+      "total_flos": 1.0169542344966144e+16,
+      "train_loss": 0.12696161927954522,
+      "train_runtime": 470.6783,
+      "train_samples_per_second": 419.828,
+      "train_steps_per_second": 13.121
+    }
+  ],
+  "max_steps": 6176,
+  "num_train_epochs": 4,
+  "total_flos": 1.0169542344966144e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03fd6c994d02e6de523373de08b1dea94edc6188150b5aba9e98ef84f9801d05
+size 3055