Initial commit

all_results.json

@@ -0,0 +1,23 @@
+{
+    "epoch": 25.0,
+    "eval_loss": 1.7208493947982788,
+    "eval_mem_cpu_alloc_delta": 104295,
+    "eval_mem_cpu_peaked_delta": 513049,
+    "eval_mem_gpu_alloc_delta": 0,
+    "eval_mem_gpu_peaked_delta": 5843399680,
+    "eval_runtime": 2.9265,
+    "eval_samples": 20,
+    "eval_samples_per_second": 6.834,
+    "init_mem_cpu_alloc_delta": 336056,
+    "init_mem_cpu_peaked_delta": 18306,
+    "init_mem_gpu_alloc_delta": 509558784,
+    "init_mem_gpu_peaked_delta": 0,
+    "perplexity": 5.58927394881408,
+    "train_mem_cpu_alloc_delta": 846748,
+    "train_mem_cpu_peaked_delta": 752929,
+    "train_mem_gpu_alloc_delta": 1501306368,
+    "train_mem_gpu_peaked_delta": 3372484096,
+    "train_runtime": 1074.2277,
+    "train_samples": 184,
+    "train_samples_per_second": 4.282
+}

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "/content/drive/MyDrive/gpt2/finetuned",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 0,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 2,
+  "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,
+  "transformers_version": "4.4.2",
+  "use_cache": true,
+  "vocab_size": 50000
+}

eval_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 25.0,
+    "eval_loss": 1.7208493947982788,
+    "eval_mem_cpu_alloc_delta": 104295,
+    "eval_mem_cpu_peaked_delta": 513049,
+    "eval_mem_gpu_alloc_delta": 0,
+    "eval_mem_gpu_peaked_delta": 5843399680,
+    "eval_runtime": 2.9265,
+    "eval_samples": 20,
+    "eval_samples_per_second": 6.834,
+    "perplexity": 5.58927394881408
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d010aed8fecf2bb774f1fb809f4b77039c4d78b708c9ec20741e87054965a47
+size 509618811

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "mask_token": "<mask>"}

tf_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f6dc4ce5d994738a0b5ac09e67066a7c31dec4b2980c3911b49cce91823c1ec
+size 497144144

tokenizer_config.json

@@ -0,0 +1 @@
+{"errors": "replace", "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, "special_tokens_map_file": null, "name_or_path": "/content/drive/MyDrive/gpt2/finetuned", "tokenizer_file": null}

train_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 25.0,
+    "init_mem_cpu_alloc_delta": 336056,
+    "init_mem_cpu_peaked_delta": 18306,
+    "init_mem_gpu_alloc_delta": 509558784,
+    "init_mem_gpu_peaked_delta": 0,
+    "train_mem_cpu_alloc_delta": 846748,
+    "train_mem_cpu_peaked_delta": 752929,
+    "train_mem_gpu_alloc_delta": 1501306368,
+    "train_mem_gpu_peaked_delta": 3372484096,
+    "train_runtime": 1074.2277,
+    "train_samples": 184,
+    "train_samples_per_second": 4.282
+}

trainer_state.json

@@ -0,0 +1,77 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 25.0,
+  "global_step": 4600,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 2.72,
+      "learning_rate": 4.456521739130435e-05,
+      "loss": 2.6463,
+      "step": 500
+    },
+    {
+      "epoch": 5.43,
+      "learning_rate": 3.91304347826087e-05,
+      "loss": 1.5589,
+      "step": 1000
+    },
+    {
+      "epoch": 8.15,
+      "learning_rate": 3.369565217391305e-05,
+      "loss": 1.107,
+      "step": 1500
+    },
+    {
+      "epoch": 10.87,
+      "learning_rate": 2.826086956521739e-05,
+      "loss": 0.8178,
+      "step": 2000
+    },
+    {
+      "epoch": 13.59,
+      "learning_rate": 2.282608695652174e-05,
+      "loss": 0.6328,
+      "step": 2500
+    },
+    {
+      "epoch": 16.3,
+      "learning_rate": 1.739130434782609e-05,
+      "loss": 0.515,
+      "step": 3000
+    },
+    {
+      "epoch": 19.02,
+      "learning_rate": 1.1956521739130435e-05,
+      "loss": 0.4357,
+      "step": 3500
+    },
+    {
+      "epoch": 21.74,
+      "learning_rate": 6.521739130434783e-06,
+      "loss": 0.3796,
+      "step": 4000
+    },
+    {
+      "epoch": 24.46,
+      "learning_rate": 1.0869565217391306e-06,
+      "loss": 0.3478,
+      "step": 4500
+    },
+    {
+      "epoch": 25.0,
+      "step": 4600,
+      "total_flos": 3511389310156800.0,
+      "train_runtime": 1074.2277,
+      "train_samples_per_second": 4.282
+    }
+  ],
+  "max_steps": 4600,
+  "num_train_epochs": 25,
+  "total_flos": 3511389310156800.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98e28a6df1626a16a0a69053e61921133f6c89a402aaf1f0c97b9703214bbb28
+size 2287