Snaphsot zero

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "configs/llama_1b_el.json",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "bos_token_id": 0,
+  "eos_token_id": 1,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 5461,
+  "max_position_embeddings": 2048,
+  "max_sequence_length": 1024,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 32,
+  "pad_token_id": -1,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.31.0",
+  "use_cache": true,
+  "vocab_size": 22000
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 1,
+  "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 sha256:77cbf57033130bda092530405d71fbc3d2f37e7eb58fa3c7adb0501a31004315
+size 2596329174

training_state.json

@@ -0,0 +1,7 @@
+{
+    "global_step": 4000,
+    "update_step": 500,
+    "tokens_seen": 95632015,
+    "tokens_seen_before": 95441505,
+    "update_time": 63.00493049621582
+}