italian finetuning

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 1.0,
+    "init_mem_cpu_alloc_delta": 336807,
+    "init_mem_cpu_peaked_delta": 18306,
+    "init_mem_gpu_alloc_delta": 511148032,
+    "init_mem_gpu_peaked_delta": 0,
+    "train_mem_cpu_alloc_delta": 488444,
+    "train_mem_cpu_peaked_delta": 195767,
+    "train_mem_gpu_alloc_delta": 1501967872,
+    "train_mem_gpu_peaked_delta": 3374894592,
+    "train_runtime": 34.4014,
+    "train_samples": 128,
+    "train_samples_per_second": 3.721
+}

config.json

@@ -0,0 +1,36 @@
+{
+  "_name_or_path": "/home/cloud-user/gpt2_colab/models/gpt_e1_CHpart_adapt__adapt_",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "gradient_checkpointing": false,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "resid_pdrop": 0.1,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 50
+    }
+  },
+  "transformers_version": "4.4.0.dev0",
+  "use_cache": true,
+  "vocab_size": 50257
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa186a3c6e9167c9fd021f230833045eb399db6cd1ca27342d8a14a8081401de
+size 510406560

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1 @@
+{"unk_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_prefix_space": false, "model_max_length": 1024, "special_tokens_map_file": null, "name_or_path": "/home/cloud-user/gpt2_colab/models/gpt_e1_CHpart_adapt__adapt_", "errors": "replace"}

train_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 1.0,
+    "init_mem_cpu_alloc_delta": 336807,
+    "init_mem_cpu_peaked_delta": 18306,
+    "init_mem_gpu_alloc_delta": 511148032,
+    "init_mem_gpu_peaked_delta": 0,
+    "train_mem_cpu_alloc_delta": 488444,
+    "train_mem_cpu_peaked_delta": 195767,
+    "train_mem_gpu_alloc_delta": 1501967872,
+    "train_mem_gpu_peaked_delta": 3374894592,
+    "train_runtime": 34.4014,
+    "train_samples": 128,
+    "train_samples_per_second": 3.721
+}

trainer_state.json

@@ -0,0 +1,23 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "global_step": 128,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "step": 128,
+      "total_flos": 97863447085056.0,
+      "train_runtime": 34.4014,
+      "train_samples_per_second": 3.721
+    }
+  ],
+  "max_steps": 128,
+  "num_train_epochs": 1,
+  "total_flos": 97863447085056.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48979f4a10ff234c9ccd7049f08e5e7ba589377e98bb119123ba4179a29937e2
+size 2351