first commit

README.md

@@ -0,0 +1,51 @@
+---
+license: apache-2.0
+tags:
+- generated_from_trainer
+model-index:
+- name: gpt2-wl-base-es
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# gpt2-wl-base-es
+
+This model is a fine-tuned version of [PlanTL-GOB-ES/gpt2-base-bne](https://huggingface.co/PlanTL-GOB-ES/gpt2-base-bne) on an unknown dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-05
+- train_batch_size: 32
+- eval_batch_size: 16
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 3.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.21.0.dev0
+- Pytorch 1.11.0+cu113
+- Datasets 2.3.3.dev0
+- Tokenizers 0.12.1

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<|endoftext|>": 50262
+}

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "train_loss": 1.076262406198602,
+    "train_runtime": 7529.011,
+    "train_samples": 303974,
+    "train_samples_per_second": 121.121,
+    "train_steps_per_second": 3.785
+}

config.json

@@ -0,0 +1,41 @@
+{
+  "_name_or_path": "PlanTL-GOB-ES/gpt2-base-bne",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.0,
+  "bos_token_id": 2,
+  "embd_pdrop": 0.0,
+  "eos_token_id": 2,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-06,
+  "model_type": "gpt2",
+  "n_ctx": 512,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 512,
+  "pad_token_id": 1,
+  "prefix": "</s>",
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.0,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.0,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 50
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.21.0.dev0",
+  "use_cache": true,
+  "vocab_size": 50263
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca6383ad0b3e5f3524e4b17ff08ade0e4214522a9db940c4241a9efaf7e0e0c8
+size 499404905

special_tokens_map.json

@@ -0,0 +1,5 @@
+{
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
+}

tokenizer_config.json

@@ -0,0 +1,9 @@
+{
+  "add_prefix_space": false,
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "name_or_path": "PlanTL-GOB-ES/gpt2-base-bne",
+  "special_tokens_map_file": null,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "train_loss": 1.076262406198602,
+    "train_runtime": 7529.011,
+    "train_samples": 303974,
+    "train_samples_per_second": 121.121,
+    "train_steps_per_second": 3.785
+}

trainer_state.json

@@ -0,0 +1,367 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "global_step": 28500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.05,
+      "learning_rate": 4.912280701754386e-05,
+      "loss": 2.1706,
+      "step": 500
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 4.824561403508772e-05,
+      "loss": 1.4815,
+      "step": 1000
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 4.736842105263158e-05,
+      "loss": 1.3855,
+      "step": 1500
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 4.649122807017544e-05,
+      "loss": 1.3281,
+      "step": 2000
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 4.56140350877193e-05,
+      "loss": 1.289,
+      "step": 2500
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 4.473684210526316e-05,
+      "loss": 1.2496,
+      "step": 3000
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 4.3859649122807014e-05,
+      "loss": 1.2333,
+      "step": 3500
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 4.298245614035088e-05,
+      "loss": 1.2021,
+      "step": 4000
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 4.210526315789474e-05,
+      "loss": 1.1839,
+      "step": 4500
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 4.12280701754386e-05,
+      "loss": 1.1753,
+      "step": 5000
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 4.0350877192982455e-05,
+      "loss": 1.1603,
+      "step": 5500
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 3.9473684210526316e-05,
+      "loss": 1.1491,
+      "step": 6000
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 3.859649122807018e-05,
+      "loss": 1.1346,
+      "step": 6500
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 3.771929824561404e-05,
+      "loss": 1.1201,
+      "step": 7000
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 3.6842105263157895e-05,
+      "loss": 1.1135,
+      "step": 7500
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 3.5964912280701756e-05,
+      "loss": 1.1096,
+      "step": 8000
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 3.508771929824561e-05,
+      "loss": 1.0949,
+      "step": 8500
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 3.421052631578947e-05,
+      "loss": 1.0927,
+      "step": 9000
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 3.3333333333333335e-05,
+      "loss": 1.0762,
+      "step": 9500
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 3.24561403508772e-05,
+      "loss": 1.0578,
+      "step": 10000
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 3.157894736842105e-05,
+      "loss": 1.045,
+      "step": 10500
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 3.0701754385964913e-05,
+      "loss": 1.0412,
+      "step": 11000
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 2.9824561403508772e-05,
+      "loss": 1.0424,
+      "step": 11500
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 2.8947368421052634e-05,
+      "loss": 1.0348,
+      "step": 12000
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 2.8070175438596492e-05,
+      "loss": 1.0283,
+      "step": 12500
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 2.7192982456140354e-05,
+      "loss": 1.0286,
+      "step": 13000
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 2.6315789473684212e-05,
+      "loss": 1.0263,
+      "step": 13500
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 2.5438596491228074e-05,
+      "loss": 1.025,
+      "step": 14000
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 2.456140350877193e-05,
+      "loss": 1.019,
+      "step": 14500
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 2.368421052631579e-05,
+      "loss": 1.0152,
+      "step": 15000
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 2.280701754385965e-05,
+      "loss": 1.0116,
+      "step": 15500
+    },
+    {
+      "epoch": 1.68,
+      "learning_rate": 2.1929824561403507e-05,
+      "loss": 1.0123,
+      "step": 16000
+    },
+    {
+      "epoch": 1.74,
+      "learning_rate": 2.105263157894737e-05,
+      "loss": 1.0018,
+      "step": 16500
+    },
+    {
+      "epoch": 1.79,
+      "learning_rate": 2.0175438596491227e-05,
+      "loss": 1.0069,
+      "step": 17000
+    },
+    {
+      "epoch": 1.84,
+      "learning_rate": 1.929824561403509e-05,
+      "loss": 0.9927,
+      "step": 17500
+    },
+    {
+      "epoch": 1.89,
+      "learning_rate": 1.8421052631578947e-05,
+      "loss": 0.9961,
+      "step": 18000
+    },
+    {
+      "epoch": 1.95,
+      "learning_rate": 1.7543859649122806e-05,
+      "loss": 0.9895,
+      "step": 18500
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 1.6666666666666667e-05,
+      "loss": 0.9959,
+      "step": 19000
+    },
+    {
+      "epoch": 2.05,
+      "learning_rate": 1.5789473684210526e-05,
+      "loss": 0.9769,
+      "step": 19500
+    },
+    {
+      "epoch": 2.11,
+      "learning_rate": 1.4912280701754386e-05,
+      "loss": 0.9681,
+      "step": 20000
+    },
+    {
+      "epoch": 2.16,
+      "learning_rate": 1.4035087719298246e-05,
+      "loss": 0.973,
+      "step": 20500
+    },
+    {
+      "epoch": 2.21,
+      "learning_rate": 1.3157894736842106e-05,
+      "loss": 0.9714,
+      "step": 21000
+    },
+    {
+      "epoch": 2.26,
+      "learning_rate": 1.2280701754385964e-05,
+      "loss": 0.9678,
+      "step": 21500
+    },
+    {
+      "epoch": 2.32,
+      "learning_rate": 1.1403508771929824e-05,
+      "loss": 0.9586,
+      "step": 22000
+    },
+    {
+      "epoch": 2.37,
+      "learning_rate": 1.0526315789473684e-05,
+      "loss": 0.9594,
+      "step": 22500
+    },
+    {
+      "epoch": 2.42,
+      "learning_rate": 9.649122807017545e-06,
+      "loss": 0.9624,
+      "step": 23000
+    },
+    {
+      "epoch": 2.47,
+      "learning_rate": 8.771929824561403e-06,
+      "loss": 0.9592,
+      "step": 23500
+    },
+    {
+      "epoch": 2.53,
+      "learning_rate": 7.894736842105263e-06,
+      "loss": 0.9573,
+      "step": 24000
+    },
+    {
+      "epoch": 2.58,
+      "learning_rate": 7.017543859649123e-06,
+      "loss": 0.9614,
+      "step": 24500
+    },
+    {
+      "epoch": 2.63,
+      "learning_rate": 6.140350877192982e-06,
+      "loss": 0.9534,
+      "step": 25000
+    },
+    {
+      "epoch": 2.68,
+      "learning_rate": 5.263157894736842e-06,
+      "loss": 0.9518,
+      "step": 25500
+    },
+    {
+      "epoch": 2.74,
+      "learning_rate": 4.3859649122807014e-06,
+      "loss": 0.9523,
+      "step": 26000
+    },
+    {
+      "epoch": 2.79,
+      "learning_rate": 3.5087719298245615e-06,
+      "loss": 0.9492,
+      "step": 26500
+    },
+    {
+      "epoch": 2.84,
+      "learning_rate": 2.631578947368421e-06,
+      "loss": 0.9512,
+      "step": 27000
+    },
+    {
+      "epoch": 2.89,
+      "learning_rate": 1.7543859649122807e-06,
+      "loss": 0.952,
+      "step": 27500
+    },
+    {
+      "epoch": 2.95,
+      "learning_rate": 8.771929824561404e-07,
+      "loss": 0.9526,
+      "step": 28000
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 0.0,
+      "loss": 0.9482,
+      "step": 28500
+    },
+    {
+      "epoch": 3.0,
+      "step": 28500,
+      "total_flos": 2.38277952405504e+17,
+      "train_loss": 1.076262406198602,
+      "train_runtime": 7529.011,
+      "train_samples_per_second": 121.121,
+      "train_steps_per_second": 3.785
+    }
+  ],
+  "max_steps": 28500,
+  "num_train_epochs": 3,
+  "total_flos": 2.38277952405504e+17,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:278c9d8d24ff673d8331a3d0d1f8645140fa00923fbc52bb765e2d311a1bf6fa
+size 3247