Model save

.gitignore

@@ -0,0 +1 @@
+checkpoint-*/

all_results.json

@@ -0,0 +1,9 @@
+{
+    "eval_accuracy": 0.042991682974559686,
+    "eval_loss": 5.509965419769287,
+    "eval_runtime": 2.8095,
+    "eval_samples": 64,
+    "eval_samples_per_second": 22.78,
+    "eval_steps_per_second": 0.356,
+    "perplexity": 247.1425806723978
+}

config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "EleutherAI/pythia-1b-deduped",
+  "architectures": [
+    "GPTNeoXForCausalLM"
+  ],
+  "bos_token_id": 0,
+  "eos_token_id": 0,
+  "hidden_act": "gelu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 2048,
+  "model_type": "gpt_neox",
+  "num_attention_heads": 8,
+  "num_hidden_layers": 16,
+  "rotary_emb_base": 10000,
+  "rotary_pct": 0.25,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.28.1",
+  "use_cache": true,
+  "use_parallel_residual": true,
+  "vocab_size": 50304
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "eval_accuracy": 0.042991682974559686,
+    "eval_loss": 5.509965419769287,
+    "eval_runtime": 2.8095,
+    "eval_samples": 64,
+    "eval_samples_per_second": 22.78,
+    "eval_steps_per_second": 0.356,
+    "perplexity": 247.1425806723978
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 0,
+  "transformers_version": "4.28.1"
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e94f058251caf36400c08b26954937d097ba23a4027b8586e229ce48e729d95d
+size 4114319645

special_tokens_map.json

@@ -0,0 +1,5 @@
+{
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
+}

tokenizer_config.json

@@ -0,0 +1,9 @@
+{
+  "add_prefix_space": false,
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1000000000000000019884624838656,
+  "tokenizer_class": "GPTNeoXTokenizer",
+  "unk_token": "<|endoftext|>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4cf45744bd1cb2af1a656f2fd0a3e71490f8dd8d0bb3e40ddaaf805e2eb9ece6
+size 3771