OutEffHop-opt-1.3b

all_results.json

@@ -0,0 +1 @@
+{"perplexity": 2064.929987881927}

checkpoints/checkpoint_30000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a8e55d185f442bfc970a3ba7b85ef68b7e77d8e3ba8d73de4b587e2ecd8bc21
+size 5009879832

checkpoints/checkpoint_30000/optimizer.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:718cf4431c747bb7087f774a95cf01cd275da389a797af85a8250fb33f337c85
+size 10020009668

checkpoints/checkpoint_30000/random_states_0.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ef10532396f3b0f1f1740dba50dd55592ac9a5bc43aeed33aafe02e81838b59
+size 15060

checkpoints/checkpoint_30000/random_states_1.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f41999dbfff6846a0593223c2a00ac6dabac1695307037ddb6b2b10542cb9e3c
+size 15060

checkpoints/checkpoint_30000/random_states_2.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83d94ef78e8fceaf273719f416adb34665a06847bd47a892ed3d3f3b80f82739
+size 15060

checkpoints/checkpoint_30000/random_states_3.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5b4a26bcb1dbb1da24223dfda94efedb8c702fa836e5e9c4d49d15c88fa2617
+size 15060

checkpoints/checkpoint_30000/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:996e482d7113d1552c854585970963491dff89aace5a33b5bc82a19f32014cec
+size 988

checkpoints/checkpoint_30000/scheduler.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c22814f4f2f0e27c9bd4bdae5fefceacdb002df622f962fdfdc09783a7d25527
+size 1064

config.json

@@ -0,0 +1,28 @@
+{
+  "_remove_final_layer_norm": false,
+  "activation_function": "relu",
+  "architectures": [
+    "OPTForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 2,
+  "do_layer_norm_before": true,
+  "dropout": 0.1,
+  "enable_bias": true,
+  "eos_token_id": 2,
+  "ffn_dim": 8192,
+  "hidden_size": 2048,
+  "init_std": 0.006,
+  "layer_norm_elementwise_affine": true,
+  "layerdrop": 0.0,
+  "max_position_embeddings": 1024,
+  "model_type": "opt",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 24,
+  "pad_token_id": 1,
+  "torch_dtype": "float32",
+  "transformers_version": "4.31.0",
+  "use_cache": true,
+  "vocab_size": 50272,
+  "word_embed_proj_dim": 768
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 2,
+  "eos_token_id": 2,
+  "pad_token_id": 1,
+  "transformers_version": "4.31.0"
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b48801ba48de045ede663ee262bc374eec9679bf1228916ab77504b919feef95
+size 5009967394

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,40 @@
+{
+  "add_bos_token": true,
+  "add_prefix_space": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": true,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "errors": "replace",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": {
+    "__type": "AddedToken",
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}