adding model finetuned on MLDoc

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 4.0,
+    "eval_accuracy": 0.9739999771118164,
+    "eval_loss": 0.12496982514858246,
+    "eval_runtime": 52.2788,
+    "eval_samples": 1000,
+    "eval_samples_per_second": 19.128,
+    "eval_steps_per_second": 2.391,
+    "train_loss": 0.06767434234748233,
+    "train_runtime": 11146.6816,
+    "train_samples": 9458,
+    "train_samples_per_second": 3.394,
+    "train_steps_per_second": 0.212
+}

config.json

@@ -0,0 +1,47 @@
+{
+  "_name_or_path": "CenIA/albert_xxlarge_spanish",
+  "architectures": [
+    "AlbertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0,
+  "bos_token_id": 2,
+  "classifier_dropout_prob": 0.1,
+  "down_scale_factor": 1,
+  "embedding_size": 128,
+  "eos_token_id": 3,
+  "gap_size": 0,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0,
+  "hidden_size": 4096,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3"
+  },
+  "initializer_range": 0.01,
+  "inner_group_num": 1,
+  "intermediate_size": 16384,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3
+  },
+  "layer_norm_eps": 1e-12,
+  "layers_to_keep": [],
+  "max_position_embeddings": 512,
+  "model_type": "albert",
+  "net_structure_type": 0,
+  "num_attention_heads": 64,
+  "num_hidden_groups": 1,
+  "num_hidden_layers": 12,
+  "num_memory_blocks": 0,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.15.0",
+  "type_vocab_size": 2,
+  "vocab_size": 31000
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 4.0,
+    "eval_accuracy": 0.9739999771118164,
+    "eval_loss": 0.12496982514858246,
+    "eval_runtime": 52.2788,
+    "eval_samples": 1000,
+    "eval_samples_per_second": 19.128,
+    "eval_steps_per_second": 2.391
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8cdc557df9ea23c791c1b31f84557b093c93e4ea1cda07227059320af0db957
+size 890974929

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "[CLS]", "eos_token": "[SEP]", "unk_token": "<unk>", "sep_token": "[SEP]", "pad_token": "<pad>", "cls_token": "[CLS]", "mask_token": "[MASK]"}

tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": true, "remove_space": true, "keep_accents": true, "bos_token": "[CLS]", "eos_token": "[SEP]", "unk_token": "<unk>", "sep_token": "[SEP]", "pad_token": "<pad>", "cls_token": "[CLS]", "mask_token": {"content": "[MASK]", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "CenIA/albert_xxlarge_spanish", "tokenizer_class": "AlbertTokenizer"}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 4.0,
+    "train_loss": 0.06767434234748233,
+    "train_runtime": 11146.6816,
+    "train_samples": 9458,
+    "train_samples_per_second": 3.394,
+    "train_steps_per_second": 0.212
+}

trainer_state.json

@@ -0,0 +1,256 @@
+{
+  "best_metric": 0.12496982514858246,
+  "best_model_checkpoint": "/data/jcanete/all_results/mldoc/albeto_xxlarge/epochs_4_bs_16_lr_5e-6/checkpoint-900",
+  "epoch": 3.9991546914623837,
+  "global_step": 2364,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.17,
+      "eval_accuracy": 0.6899999976158142,
+      "eval_loss": 0.9207698702812195,
+      "eval_runtime": 53.4599,
+      "eval_samples_per_second": 18.706,
+      "eval_steps_per_second": 2.338,
+      "step": 100
+    },
+    {
+      "epoch": 0.34,
+      "eval_accuracy": 0.8460000157356262,
+      "eval_loss": 0.4446202516555786,
+      "eval_runtime": 53.5207,
+      "eval_samples_per_second": 18.684,
+      "eval_steps_per_second": 2.336,
+      "step": 200
+    },
+    {
+      "epoch": 0.51,
+      "eval_accuracy": 0.9229999780654907,
+      "eval_loss": 0.31312161684036255,
+      "eval_runtime": 52.7206,
+      "eval_samples_per_second": 18.968,
+      "eval_steps_per_second": 2.371,
+      "step": 300
+    },
+    {
+      "epoch": 0.68,
+      "eval_accuracy": 0.9449999928474426,
+      "eval_loss": 0.29927751421928406,
+      "eval_runtime": 53.4208,
+      "eval_samples_per_second": 18.719,
+      "eval_steps_per_second": 2.34,
+      "step": 400
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 3.95093062605753e-06,
+      "loss": 0.1599,
+      "step": 500
+    },
+    {
+      "epoch": 0.85,
+      "eval_accuracy": 0.953000009059906,
+      "eval_loss": 0.22006945312023163,
+      "eval_runtime": 52.7047,
+      "eval_samples_per_second": 18.974,
+      "eval_steps_per_second": 2.372,
+      "step": 500
+    },
+    {
+      "epoch": 1.02,
+      "eval_accuracy": 0.9279999732971191,
+      "eval_loss": 0.3698674440383911,
+      "eval_runtime": 52.7048,
+      "eval_samples_per_second": 18.974,
+      "eval_steps_per_second": 2.372,
+      "step": 600
+    },
+    {
+      "epoch": 1.18,
+      "eval_accuracy": 0.9580000042915344,
+      "eval_loss": 0.23167340457439423,
+      "eval_runtime": 52.7049,
+      "eval_samples_per_second": 18.974,
+      "eval_steps_per_second": 2.372,
+      "step": 700
+    },
+    {
+      "epoch": 1.35,
+      "eval_accuracy": 0.9639999866485596,
+      "eval_loss": 0.16574066877365112,
+      "eval_runtime": 53.2433,
+      "eval_samples_per_second": 18.782,
+      "eval_steps_per_second": 2.348,
+      "step": 800
+    },
+    {
+      "epoch": 1.52,
+      "eval_accuracy": 0.9739999771118164,
+      "eval_loss": 0.12496982514858246,
+      "eval_runtime": 52.7138,
+      "eval_samples_per_second": 18.97,
+      "eval_steps_per_second": 2.371,
+      "step": 900
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 2.8934010152284262e-06,
+      "loss": 0.0708,
+      "step": 1000
+    },
+    {
+      "epoch": 1.69,
+      "eval_accuracy": 0.9549999833106995,
+      "eval_loss": 0.23840972781181335,
+      "eval_runtime": 52.6578,
+      "eval_samples_per_second": 18.991,
+      "eval_steps_per_second": 2.374,
+      "step": 1000
+    },
+    {
+      "epoch": 1.86,
+      "eval_accuracy": 0.9700000286102295,
+      "eval_loss": 0.1677614450454712,
+      "eval_runtime": 52.6824,
+      "eval_samples_per_second": 18.982,
+      "eval_steps_per_second": 2.373,
+      "step": 1100
+    },
+    {
+      "epoch": 2.03,
+      "eval_accuracy": 0.9710000157356262,
+      "eval_loss": 0.1557045578956604,
+      "eval_runtime": 53.1989,
+      "eval_samples_per_second": 18.797,
+      "eval_steps_per_second": 2.35,
+      "step": 1200
+    },
+    {
+      "epoch": 2.2,
+      "eval_accuracy": 0.9629999995231628,
+      "eval_loss": 0.22913765907287598,
+      "eval_runtime": 52.6879,
+      "eval_samples_per_second": 18.98,
+      "eval_steps_per_second": 2.372,
+      "step": 1300
+    },
+    {
+      "epoch": 2.37,
+      "eval_accuracy": 0.9670000076293945,
+      "eval_loss": 0.17893917858600616,
+      "eval_runtime": 52.8001,
+      "eval_samples_per_second": 18.939,
+      "eval_steps_per_second": 2.367,
+      "step": 1400
+    },
+    {
+      "epoch": 2.54,
+      "learning_rate": 1.8358714043993234e-06,
+      "loss": 0.0453,
+      "step": 1500
+    },
+    {
+      "epoch": 2.54,
+      "eval_accuracy": 0.9710000157356262,
+      "eval_loss": 0.16048669815063477,
+      "eval_runtime": 52.6463,
+      "eval_samples_per_second": 18.995,
+      "eval_steps_per_second": 2.374,
+      "step": 1500
+    },
+    {
+      "epoch": 2.71,
+      "eval_accuracy": 0.9520000219345093,
+      "eval_loss": 0.2762700319290161,
+      "eval_runtime": 52.6922,
+      "eval_samples_per_second": 18.978,
+      "eval_steps_per_second": 2.372,
+      "step": 1600
+    },
+    {
+      "epoch": 2.88,
+      "eval_accuracy": 0.9649999737739563,
+      "eval_loss": 0.18934407830238342,
+      "eval_runtime": 52.6384,
+      "eval_samples_per_second": 18.998,
+      "eval_steps_per_second": 2.375,
+      "step": 1700
+    },
+    {
+      "epoch": 3.05,
+      "eval_accuracy": 0.9739999771118164,
+      "eval_loss": 0.16606220602989197,
+      "eval_runtime": 52.7133,
+      "eval_samples_per_second": 18.971,
+      "eval_steps_per_second": 2.371,
+      "step": 1800
+    },
+    {
+      "epoch": 3.21,
+      "eval_accuracy": 0.9660000205039978,
+      "eval_loss": 0.222770556807518,
+      "eval_runtime": 53.295,
+      "eval_samples_per_second": 18.763,
+      "eval_steps_per_second": 2.345,
+      "step": 1900
+    },
+    {
+      "epoch": 3.38,
+      "learning_rate": 7.7834179357022e-07,
+      "loss": 0.0294,
+      "step": 2000
+    },
+    {
+      "epoch": 3.38,
+      "eval_accuracy": 0.9639999866485596,
+      "eval_loss": 0.20788319408893585,
+      "eval_runtime": 52.7008,
+      "eval_samples_per_second": 18.975,
+      "eval_steps_per_second": 2.372,
+      "step": 2000
+    },
+    {
+      "epoch": 3.55,
+      "eval_accuracy": 0.9660000205039978,
+      "eval_loss": 0.18167437613010406,
+      "eval_runtime": 52.7113,
+      "eval_samples_per_second": 18.971,
+      "eval_steps_per_second": 2.371,
+      "step": 2100
+    },
+    {
+      "epoch": 3.72,
+      "eval_accuracy": 0.9620000123977661,
+      "eval_loss": 0.20487231016159058,
+      "eval_runtime": 52.7823,
+      "eval_samples_per_second": 18.946,
+      "eval_steps_per_second": 2.368,
+      "step": 2200
+    },
+    {
+      "epoch": 3.89,
+      "eval_accuracy": 0.9670000076293945,
+      "eval_loss": 0.19099852442741394,
+      "eval_runtime": 53.0072,
+      "eval_samples_per_second": 18.865,
+      "eval_steps_per_second": 2.358,
+      "step": 2300
+    },
+    {
+      "epoch": 4.0,
+      "step": 2364,
+      "total_flos": 1.796922868289472e+16,
+      "train_loss": 0.06767434234748233,
+      "train_runtime": 11146.6816,
+      "train_samples_per_second": 3.394,
+      "train_steps_per_second": 0.212
+    }
+  ],
+  "max_steps": 2364,
+  "num_train_epochs": 4,
+  "total_flos": 1.796922868289472e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48532441e49fcfa32383c324a073e4ba394ae35c58bc1f469ff2fbe452196356
+size 2991