italian finetuning

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 1.0,
+    "init_mem_cpu_alloc_delta": 346966,
+    "init_mem_cpu_peaked_delta": 18306,
+    "init_mem_gpu_alloc_delta": 1109893120,
+    "init_mem_gpu_peaked_delta": 0,
+    "train_mem_cpu_alloc_delta": 458891,
+    "train_mem_cpu_peaked_delta": 216825,
+    "train_mem_gpu_alloc_delta": 3344808960,
+    "train_mem_gpu_peaked_delta": 3576805376,
+    "train_runtime": 45.8048,
+    "train_samples": 898,
+    "train_samples_per_second": 2.467
+}

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "/home/cloud-user/gpt2_colab/models/xlm_e1_CHpart_adapt_",
+  "architectures": [
+    "XLMRobertaForQuestionAnswering"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "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": "xlm-roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "transformers_version": "4.4.0.dev0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69906d439f2afa58ad399508656167e68f1bd7aaaeeb4b00e6ced975c5395dab
+size 1109906126

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
+size 5069051

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "sep_token": "</s>", "cls_token": "<s>", "unk_token": "<unk>", "pad_token": "<pad>", "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": "/home/cloud-user/gpt2_colab/models/xlm_e1_CHpart_adapt_"}

train_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 1.0,
+    "init_mem_cpu_alloc_delta": 346966,
+    "init_mem_cpu_peaked_delta": 18306,
+    "init_mem_gpu_alloc_delta": 1109893120,
+    "init_mem_gpu_peaked_delta": 0,
+    "train_mem_cpu_alloc_delta": 458891,
+    "train_mem_cpu_peaked_delta": 216825,
+    "train_mem_gpu_alloc_delta": 3344808960,
+    "train_mem_gpu_peaked_delta": 3576805376,
+    "train_runtime": 45.8048,
+    "train_samples": 898,
+    "train_samples_per_second": 2.467
+}

trainer_state.json

@@ -0,0 +1,23 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "global_step": 113,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "step": 113,
+      "total_flos": 574051335349248.0,
+      "train_runtime": 45.8048,
+      "train_samples_per_second": 2.467
+    }
+  ],
+  "max_steps": 113,
+  "num_train_epochs": 1,
+  "total_flos": 574051335349248.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e7a0ae8e029201305c62418f615d78922c0ed7745f32794d5e2fb49c9237163
+size 2351