Model save

last-checkpoint/config.json

@@ -1,27 +0,0 @@
-{
-  "_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,
-  "hidden_act": "gelu",
-  "hidden_dropout_prob": 0.1,
-  "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",
-  "torch_dtype": "float32",
-  "transformers_version": "4.24.0",
-  "type_vocab_size": 1,
-  "use_cache": true,
-  "vocab_size": 50265
-}

last-checkpoint/optimizer.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:7eeb4233aad5f1a1fa9853dd8052be96ee296aaab975eaf8ab53cfb58608efe8
-size 997747845

last-checkpoint/pytorch_model.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:b5634cfe2312a8039ab3967c518a6f32869c348d83ffc800c525176f4c98438d
-size 498863417

last-checkpoint/rng_state.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:0181d7e1e30a5f22b9769be65342eba1c1e28b01fe477b02a9bb3ec5d0ad3dc0
-size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:5709c81ed6119207bfafe582322092d4688aeb99f981a15d0a832211c0b354a5
-size 627

last-checkpoint/special_tokens_map.json

@@ -1,15 +0,0 @@
-{
-  "bos_token": "<s>",
-  "cls_token": "<s>",
-  "eos_token": "</s>",
-  "mask_token": {
-    "content": "<mask>",
-    "lstrip": true,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "pad_token": "<pad>",
-  "sep_token": "</s>",
-  "unk_token": "<unk>"
-}

last-checkpoint/tokenizer_config.json

@@ -1,17 +0,0 @@
-{
-  "add_prefix_space": false,
-  "bos_token": "<s>",
-  "cls_token": "<s>",
-  "eos_token": "</s>",
-  "errors": "replace",
-  "mask_token": "<mask>",
-  "max_len": 512,
-  "model_max_length": 512,
-  "name_or_path": "/home/pcjf/CESGA/works/lmodels/models/large",
-  "pad_token": "<pad>",
-  "sep_token": "</s>",
-  "special_tokens_map_file": null,
-  "tokenizer_class": "RobertaTokenizer",
-  "trim_offsets": true,
-  "unk_token": "<unk>"
-}

last-checkpoint/trainer_state.json

@@ -1,72 +0,0 @@
-{
-  "best_metric": 5.888911247253418,
-  "best_model_checkpoint": "/home/pcjf/CESGA/works/lmodels/models/large/checkpoint-6000",
-  "epoch": 0.86385703166126,
-  "global_step": 6000,
-  "is_hyper_param_search": false,
-  "is_local_process_zero": true,
-  "is_world_process_zero": true,
-  "log_history": [
-    {
-      "epoch": 0.22,
-      "learning_rate": 7.840172786177106e-06,
-      "loss": 6.8838,
-      "step": 1500
-    },
-    {
-      "epoch": 0.22,
-      "eval_loss": 6.199821949005127,
-      "eval_runtime": 80.1923,
-      "eval_samples_per_second": 226.281,
-      "eval_steps_per_second": 28.294,
-      "step": 1500
-    },
-    {
-      "epoch": 0.43,
-      "learning_rate": 5.6803455723542124e-06,
-      "loss": 6.1582,
-      "step": 3000
-    },
-    {
-      "epoch": 0.43,
-      "eval_loss": 6.045103549957275,
-      "eval_runtime": 79.8804,
-      "eval_samples_per_second": 227.165,
-      "eval_steps_per_second": 28.405,
-      "step": 3000
-    },
-    {
-      "epoch": 0.65,
-      "learning_rate": 3.520518358531318e-06,
-      "loss": 6.0547,
-      "step": 4500
-    },
-    {
-      "epoch": 0.65,
-      "eval_loss": 5.95121955871582,
-      "eval_runtime": 80.1607,
-      "eval_samples_per_second": 226.37,
-      "eval_steps_per_second": 28.306,
-      "step": 4500
-    },
-    {
-      "epoch": 0.86,
-      "learning_rate": 1.3606911447084234e-06,
-      "loss": 5.9863,
-      "step": 6000
-    },
-    {
-      "epoch": 0.86,
-      "eval_loss": 5.888911247253418,
-      "eval_runtime": 81.0425,
-      "eval_samples_per_second": 223.907,
-      "eval_steps_per_second": 27.998,
-      "step": 6000
-    }
-  ],
-  "max_steps": 6945,
-  "num_train_epochs": 1,
-  "total_flos": 8.995108319836056e+16,
-  "trial_name": null,
-  "trial_params": null
-}

last-checkpoint/training_args.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:8ac315fb6f01a713c35d8bb0bc140e603ae3fc1ed639b8dd43fdc17fa5a664b6
-size 3451

runs/Feb05_19-18-25_turing/events.out.tfevents.1675621116.turing.942264.1

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a1e2eae149ace5293869a67cee48dac9e8167880b670712581ba7b9253fefc83
-size 5552
+oid sha256:9563588a96edafe7a32ad5535c6314e4e32abb835a745b033d3084b31f3773d8
+size 5906