Upload 10 files

added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "<unk>": 0,
+  "<|endoftext|>": 2,
+  "<|startoftext|>": 1
+}

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "train_loss": 0.3784581153609504,
+    "train_runtime": 122473.9577,
+    "train_samples": 93204,
+    "train_samples_per_second": 2.24,
+    "train_steps_per_second": 0.224
+}

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "/data/llm/models/Pretrained/yi-6B/01ai/Yi-6B",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 4096,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 4,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 5000000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.34.0",
+  "use_cache": true,
+  "vocab_size": 64000
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 0,
+  "transformers_version": "4.34.0"
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf4392114988bdfa71d68ef881441fa64bbd87b64e90fd2b10c89a48d3c96bd8
+size 12122111662

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:386c49cf943d71aa110361135338c50e38beeff0a66593480421f37b319e1a39
+size 1033105

tokenizer_config.json

@@ -0,0 +1,13 @@
+{
+  "add_bos_token": false,
+  "add_eos_token": false,
+  "model_max_length": 4096,
+  "unk_token": "<unk>",
+  "bos_token": "<|startoftext|>",
+  "eos_token": "<|endoftext|>",
+  "pad_token": "<unk>",
+  "sp_model_kwargs": {},
+  "clean_up_tokenization_spaces": false,
+  "legacy": true,
+  "tokenizer_class": "LlamaTokenizer"
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "train_loss": 0.3784581153609504,
+    "train_runtime": 122473.9577,
+    "train_samples": 93204,
+    "train_samples_per_second": 2.24,
+    "train_steps_per_second": 0.224
+}