Training in progress, step 500

.gitignore

@@ -0,0 +1 @@
+checkpoint-*/

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "bert-fromscratch-galician-large",
+  "architectures": [
+    "RobertaForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.25.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

events.out.tfevents.1674219058.turing.535864.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:945dc67bd2cd32d657520fe05ea3bc2c283cd8d97573cebd8848603c65e23248
+size 40

last-checkpoint/config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "bert-fromscratch-galician-large",
+  "architectures": [
+    "RobertaForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.25.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

last-checkpoint/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:baa56fc354bab9722a82d8f85c69a770342e80cba7ebb98840a157908da2ca3e
+size 1270901637

last-checkpoint/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6224ac56335a66abd35ac70f16cc5cf9f099c1b47c77a2b3bfa666e0fb25f5a6
+size 635440313

last-checkpoint/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02f2bb7ce981ff1e3541eb338207fdec5835069386155674aff24b7a0342a2fb
+size 14575

last-checkpoint/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3f196a54202bb4ba1220e8c59f42f9cda0702d68ea83147d814c2fb2f36b8f2
+size 557

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f1b26120718f1fc7514dbf4a2e75f903adca9179906a60978c2e35f5f1bfb14
+size 627

last-checkpoint/trainer_state.json

@@ -0,0 +1,30 @@
+{
+  "best_metric": 7.173837184906006,
+  "best_model_checkpoint": "/home/pcjf/CESGA/works/lmodels/models/large/checkpoint-500",
+  "epoch": 0.4516201874223778,
+  "global_step": 500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.45,
+      "learning_rate": 9.698885877747666e-05,
+      "loss": 7.2539,
+      "step": 500
+    },
+    {
+      "epoch": 0.45,
+      "eval_loss": 7.173837184906006,
+      "eval_runtime": 53.1876,
+      "eval_samples_per_second": 216.065,
+      "eval_steps_per_second": 27.018,
+      "step": 500
+    }
+  ],
+  "max_steps": 16605,
+  "num_train_epochs": 15,
+  "total_flos": 2.352130715179123e+16,
+  "trial_name": null,
+  "trial_params": null
+}

last-checkpoint/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4996bd364fd243c3cfe1cd3d164ea77995538c4e1b23bef6d87942bffa66e6d
+size 3515

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6224ac56335a66abd35ac70f16cc5cf9f099c1b47c77a2b3bfa666e0fb25f5a6
+size 635440313

runs/Jan20_13-50-58_turing/1674219065.6657515/events.out.tfevents.1674219065.turing.535864.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07808dc97e7bb690acdab9d1f9c3f313b49c3c4824da3ce223a0acb87c1d1f4f
+size 5621

runs/Jan20_13-50-58_turing/events.out.tfevents.1674219065.turing.535864.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a3e6c5ef07181261ea7ae6adbf4e7cd6906420acd9bd3e47987302b825d4d62
+size 4305

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4996bd364fd243c3cfe1cd3d164ea77995538c4e1b23bef6d87942bffa66e6d
+size 3515