german finetuning

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 1.0,
+    "init_mem_cpu_alloc_delta": 346890,
+    "init_mem_cpu_peaked_delta": 18306,
+    "init_mem_gpu_alloc_delta": 497524736,
+    "init_mem_gpu_peaked_delta": 0,
+    "train_mem_cpu_alloc_delta": 587733,
+    "train_mem_cpu_peaked_delta": 221105,
+    "train_mem_gpu_alloc_delta": 1509221376,
+    "train_mem_gpu_peaked_delta": 3575343104,
+    "train_runtime": 41.401,
+    "train_samples": 818,
+    "train_samples_per_second": 2.488
+}

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "/home/cloud-user/gpt2_colab/models/roberta_e1_CHpart_adapt_",
+  "architectures": [
+    "RobertaForQuestionAnswering"
+  ],
+  "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": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "transformers_version": "4.4.0.dev0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c02ffd4e04248e24a1498b724938940fe18c842e8866cd0ca0bbfa9cdc3aff50
+size 496314063

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 @@
+{"unk_token": {"content": "<unk>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_prefix_space": false, "errors": "replace", "sep_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "cls_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "pad_token": {"content": "<pad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "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/roberta_e1_CHpart_adapt_"}

train_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 1.0,
+    "init_mem_cpu_alloc_delta": 346890,
+    "init_mem_cpu_peaked_delta": 18306,
+    "init_mem_gpu_alloc_delta": 497524736,
+    "init_mem_gpu_peaked_delta": 0,
+    "train_mem_cpu_alloc_delta": 587733,
+    "train_mem_cpu_peaked_delta": 221105,
+    "train_mem_gpu_alloc_delta": 1509221376,
+    "train_mem_gpu_peaked_delta": 3575343104,
+    "train_runtime": 41.401,
+    "train_samples": 818,
+    "train_samples_per_second": 2.488
+}

trainer_state.json

@@ -0,0 +1,23 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "global_step": 103,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "step": 103,
+      "total_flos": 233805958972416.0,
+      "train_runtime": 41.401,
+      "train_samples_per_second": 2.488
+    }
+  ],
+  "max_steps": 103,
+  "num_train_epochs": 1,
+  "total_flos": 233805958972416.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:594c840f0c5a7a6ffb6e859fb111ee38506bba85a977cec952e7414688f1bd2b
+size 2351