Upload folder using huggingface_hub

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "[PAD]": 32016
+}

all_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 2.0,
+    "train_loss": 0.4584712987964593,
+    "train_runtime": 26272.8035,
+    "train_samples_per_second": 16.064,
+    "train_steps_per_second": 0.063
+}

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "/group/30172/kaitongyang/open_models/CodeLlama-13b-hf",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 13824,
+  "max_position_embeddings": 16384,
+  "model_type": "llama",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 40,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.33.3",
+  "use_cache": false,
+  "vocab_size": 32017
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.33.3"
+}

pytorch_model-00001-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5524124ff054182ffaf089b2e7a0588da9771e537457e51ffedb0d7390dacf6d
+size 9948893513

pytorch_model-00002-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:efeae2b6d1185fa774c1292513f9819a66aee4c5c1ff858639f00a6de6d81999
+size 9904155408

pytorch_model-00003-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a71eec4fad986403cb91e9f990399d2093151c69cd5941cb131ad6afd1acb3e6
+size 6179152287

pytorch_model.bin.index.json

@@ -0,0 +1,370 @@
+{
+  "metadata": {
+    "total_size": 26032076800
+  },
+  "weight_map": {
+    "lm_head.weight": "pytorch_model-00003-of-00003.bin",
+    "model.embed_tokens.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.10.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.10.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.11.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.11.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.11.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.12.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.12.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.12.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.13.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.13.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.13.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.14.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.14.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.14.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.15.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.15.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.15.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.16.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.16.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.16.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.17.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.17.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.17.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.18.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.18.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.18.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.19.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.19.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.19.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.20.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.20.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.20.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.21.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.21.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.21.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.22.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.22.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.22.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.23.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.23.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.23.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.24.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.24.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.24.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.25.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.25.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.25.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.26.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.26.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.26.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.27.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.27.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.27.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.28.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.28.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.28.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.29.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.29.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.29.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.30.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.30.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.30.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.31.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.31.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.31.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.32.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.32.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.32.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.32.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.32.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.32.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.32.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.32.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.32.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.33.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.33.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.33.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.33.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.33.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.33.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.33.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.33.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.33.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.34.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.34.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.34.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.34.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.34.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.34.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.34.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.34.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.34.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.35.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.35.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.35.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.35.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.35.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.35.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.35.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.35.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.35.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.36.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.36.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.36.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.36.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.36.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.36.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.36.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.36.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.36.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.37.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.37.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.37.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.37.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.37.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.37.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.37.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.37.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.37.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.38.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.38.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.38.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.38.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.38.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.38.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.38.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.38.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.38.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.39.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.39.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.39.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.39.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.39.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.39.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.39.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.39.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.39.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.8.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.9.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.9.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.norm.weight": "pytorch_model-00003-of-00003.bin"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "additional_special_tokens": [
+    "▁<PRE>",
+    "▁<MID>",
+    "▁<SUF>",
+    "▁<EOT>"
+  ],
+  "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": "[PAD]",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45ccb9c8b6b561889acea59191d66986d314e7cbd6a78abc6e49b139ca91c1e6
+size 500058

tokenizer_config.json

@@ -0,0 +1,48 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "additional_special_tokens": [
+    "▁<PRE>",
+    "▁<MID>",
+    "▁<SUF>",
+    "▁<EOT>"
+  ],
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": false,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eot_token": "▁<EOT>",
+  "fill_token": "<FILL_ME>",
+  "legacy": null,
+  "middle_token": "▁<MID>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "padding_side": "left",
+  "prefix_token": "▁<PRE>",
+  "sp_model_kwargs": {},
+  "suffix_first": false,
+  "suffix_token": "▁<SUF>",
+  "tokenizer_class": "CodeLlamaTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "use_default_system_prompt": false
+}

train_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 2.0,
+    "train_loss": 0.4584712987964593,
+    "train_runtime": 26272.8035,
+    "train_samples_per_second": 16.064,
+    "train_steps_per_second": 0.063
+}

trainer_state.json

@@ -0,0 +1,1012 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.9987871437234688,
+  "eval_steps": 500,
+  "global_step": 1648,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.9998183053318547e-05,
+      "loss": 0.6602,
+      "step": 10
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.9992732873533223e-05,
+      "loss": 0.5998,
+      "step": 20
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.9983651441181253e-05,
+      "loss": 0.5727,
+      "step": 30
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.997094205635831e-05,
+      "loss": 0.5677,
+      "step": 40
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.99546093375193e-05,
+      "loss": 0.545,
+      "step": 50
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.99346592198001e-05,
+      "loss": 0.5564,
+      "step": 60
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.9911098952860726e-05,
+      "loss": 0.5393,
+      "step": 70
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.9883937098250962e-05,
+      "loss": 0.52,
+      "step": 80
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.985318352629912e-05,
+      "loss": 0.5319,
+      "step": 90
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.9818849412525294e-05,
+      "loss": 0.5382,
+      "step": 100
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.978094723358031e-05,
+      "loss": 0.5302,
+      "step": 110
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.9739490762711812e-05,
+      "loss": 0.5377,
+      "step": 120
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.969449506475924e-05,
+      "loss": 0.5253,
+      "step": 130
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.9645976490679402e-05,
+      "loss": 0.5364,
+      "step": 140
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.9593952671604737e-05,
+      "loss": 0.5277,
+      "step": 150
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.953844251243633e-05,
+      "loss": 0.5193,
+      "step": 160
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.947946618497407e-05,
+      "loss": 0.5161,
+      "step": 170
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.941704512058646e-05,
+      "loss": 0.5225,
+      "step": 180
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.9351202002422654e-05,
+      "loss": 0.5313,
+      "step": 190
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.928196075716966e-05,
+      "loss": 0.5152,
+      "step": 200
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.920934654635764e-05,
+      "loss": 0.5242,
+      "step": 210
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.9133385757216458e-05,
+      "loss": 0.5219,
+      "step": 220
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.905410599308687e-05,
+      "loss": 0.5212,
+      "step": 230
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.8971536063389745e-05,
+      "loss": 0.5083,
+      "step": 240
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.888570597315703e-05,
+      "loss": 0.509,
+      "step": 250
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.8796646912128247e-05,
+      "loss": 0.513,
+      "step": 260
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.8704391243416478e-05,
+      "loss": 0.5027,
+      "step": 270
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.8608972491747946e-05,
+      "loss": 0.5167,
+      "step": 280
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 1.8510425331279488e-05,
+      "loss": 0.5147,
+      "step": 290
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.8408785572998335e-05,
+      "loss": 0.5045,
+      "step": 300
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.8304090151708797e-05,
+      "loss": 0.5076,
+      "step": 310
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.8196377112610524e-05,
+      "loss": 0.5066,
+      "step": 320
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.808568559747331e-05,
+      "loss": 0.5125,
+      "step": 330
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.7972055830413372e-05,
+      "loss": 0.5079,
+      "step": 340
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.7855529103276337e-05,
+      "loss": 0.5085,
+      "step": 350
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.773614776063225e-05,
+      "loss": 0.4952,
+      "step": 360
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.761395518438797e-05,
+      "loss": 0.5107,
+      "step": 370
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.7488995778022687e-05,
+      "loss": 0.4863,
+      "step": 380
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.7361314950452137e-05,
+      "loss": 0.5035,
+      "step": 390
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.7230959099527512e-05,
+      "loss": 0.514,
+      "step": 400
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.709797559517496e-05,
+      "loss": 0.498,
+      "step": 410
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1.6962412762181867e-05,
+      "loss": 0.5048,
+      "step": 420
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 1.6824319862636137e-05,
+      "loss": 0.5145,
+      "step": 430
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 1.6683747078024887e-05,
+      "loss": 0.4913,
+      "step": 440
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 1.654074549099901e-05,
+      "loss": 0.5129,
+      "step": 450
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 1.6395367066810312e-05,
+      "loss": 0.5024,
+      "step": 460
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 1.6247664634427866e-05,
+      "loss": 0.5127,
+      "step": 470
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 1.6097691867340547e-05,
+      "loss": 0.4951,
+      "step": 480
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 1.5945503264052638e-05,
+      "loss": 0.5059,
+      "step": 490
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 1.5791154128279694e-05,
+      "loss": 0.4891,
+      "step": 500
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 1.5634700548851713e-05,
+      "loss": 0.4874,
+      "step": 510
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 1.547619937933108e-05,
+      "loss": 0.5008,
+      "step": 520
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 1.53157082173526e-05,
+      "loss": 0.5038,
+      "step": 530
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 1.5153285383693091e-05,
+      "loss": 0.5154,
+      "step": 540
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 1.4988989901078286e-05,
+      "loss": 0.4846,
+      "step": 550
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 1.4822881472734563e-05,
+      "loss": 0.5016,
+      "step": 560
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 1.4655020460693452e-05,
+      "loss": 0.514,
+      "step": 570
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 1.4485467863856704e-05,
+      "loss": 0.4998,
+      "step": 580
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 1.4314285295829957e-05,
+      "loss": 0.4985,
+      "step": 590
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 1.4141534962532986e-05,
+      "loss": 0.4833,
+      "step": 600
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 1.3967279639594753e-05,
+      "loss": 0.5018,
+      "step": 610
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 1.3791582649541404e-05,
+      "loss": 0.487,
+      "step": 620
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 1.3614507838785547e-05,
+      "loss": 0.509,
+      "step": 630
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 1.3436119554425133e-05,
+      "loss": 0.4856,
+      "step": 640
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 1.3256482620860415e-05,
+      "loss": 0.5007,
+      "step": 650
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 1.3075662316237466e-05,
+      "loss": 0.4985,
+      "step": 660
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1.2893724348726757e-05,
+      "loss": 0.4868,
+      "step": 670
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.2710734832645557e-05,
+      "loss": 0.4888,
+      "step": 680
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.2526760264432658e-05,
+      "loss": 0.4963,
+      "step": 690
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.2341867498484303e-05,
+      "loss": 0.4898,
+      "step": 700
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 1.2156123722859989e-05,
+      "loss": 0.4968,
+      "step": 710
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 1.1969596434867063e-05,
+      "loss": 0.4901,
+      "step": 720
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 1.1782353416532908e-05,
+      "loss": 0.5002,
+      "step": 730
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 1.1594462709973684e-05,
+      "loss": 0.4862,
+      "step": 740
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 1.140599259266854e-05,
+      "loss": 0.4839,
+      "step": 750
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 1.1217011552648316e-05,
+      "loss": 0.4923,
+      "step": 760
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 1.102758826360772e-05,
+      "loss": 0.4957,
+      "step": 770
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.0837791559950029e-05,
+      "loss": 0.4864,
+      "step": 780
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 1.0647690411773415e-05,
+      "loss": 0.4843,
+      "step": 790
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 1.0457353899807947e-05,
+      "loss": 0.5063,
+      "step": 800
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 1.0266851190312375e-05,
+      "loss": 0.4786,
+      "step": 810
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 1.0076251509939867e-05,
+      "loss": 0.4892,
+      "step": 820
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 9.885624120581772e-06,
+      "loss": 0.4588,
+      "step": 830
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 9.695038294198588e-06,
+      "loss": 0.4106,
+      "step": 840
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 9.504563287647265e-06,
+      "loss": 0.4155,
+      "step": 850
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 9.314268317514023e-06,
+      "loss": 0.4123,
+      "step": 860
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 9.12422253496175e-06,
+      "loss": 0.4064,
+      "step": 870
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 8.934495000601241e-06,
+      "loss": 0.4115,
+      "step": 880
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 8.745154659395273e-06,
+      "loss": 0.4155,
+      "step": 890
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 8.556270315604779e-06,
+      "loss": 0.404,
+      "step": 900
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 8.36791060778608e-06,
+      "loss": 0.4002,
+      "step": 910
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 8.180143983848388e-06,
+      "loss": 0.4042,
+      "step": 920
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 7.993038676180546e-06,
+      "loss": 0.402,
+      "step": 930
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 7.806662676856134e-06,
+      "loss": 0.4041,
+      "step": 940
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 7.62108371292584e-06,
+      "loss": 0.4162,
+      "step": 950
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 7.436369221806201e-06,
+      "loss": 0.4206,
+      "step": 960
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 7.2525863267735405e-06,
+      "loss": 0.4022,
+      "step": 970
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 7.069801812572117e-06,
+      "loss": 0.3994,
+      "step": 980
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 6.888082101145222e-06,
+      "loss": 0.4124,
+      "step": 990
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 6.707493227498187e-06,
+      "loss": 0.4182,
+      "step": 1000
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 6.5281008157019425e-06,
+      "loss": 0.4079,
+      "step": 1010
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 6.3499700550459554e-06,
+      "loss": 0.4118,
+      "step": 1020
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 6.173165676349103e-06,
+      "loss": 0.4144,
+      "step": 1030
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 5.99775192843722e-06,
+      "loss": 0.4101,
+      "step": 1040
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 5.823792554795738e-06,
+      "loss": 0.4041,
+      "step": 1050
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 5.6513507704059835e-06,
+      "loss": 0.413,
+      "step": 1060
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 5.480489238773536e-06,
+      "loss": 0.3996,
+      "step": 1070
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 5.311270049156967e-06,
+      "loss": 0.4124,
+      "step": 1080
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 5.14375469400529e-06,
+      "loss": 0.4026,
+      "step": 1090
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 4.978004046612224e-06,
+      "loss": 0.4067,
+      "step": 1100
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 4.814078338995516e-06,
+      "loss": 0.3976,
+      "step": 1110
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 4.652037140009259e-06,
+      "loss": 0.3902,
+      "step": 1120
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 4.491939333697205e-06,
+      "loss": 0.403,
+      "step": 1130
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 4.333843097894932e-06,
+      "loss": 0.4138,
+      "step": 1140
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 4.177805883088641e-06,
+      "loss": 0.4199,
+      "step": 1150
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 4.023884391538244e-06,
+      "loss": 0.4104,
+      "step": 1160
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 3.8721345566724156e-06,
+      "loss": 0.4091,
+      "step": 1170
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 3.722611522762917e-06,
+      "loss": 0.4069,
+      "step": 1180
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 3.575369624885803e-06,
+      "loss": 0.4105,
+      "step": 1190
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 3.4304623691766193e-06,
+      "loss": 0.399,
+      "step": 1200
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 3.287942413386841e-06,
+      "loss": 0.4018,
+      "step": 1210
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 3.147861547748612e-06,
+      "loss": 0.4119,
+      "step": 1220
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 3.0102706761547264e-06,
+      "loss": 0.3934,
+      "step": 1230
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 2.875219797660681e-06,
+      "loss": 0.3954,
+      "step": 1240
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 2.7427579883155895e-06,
+      "loss": 0.4046,
+      "step": 1250
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 2.612933383328432e-06,
+      "loss": 0.4042,
+      "step": 1260
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 2.4857931595762406e-06,
+      "loss": 0.4089,
+      "step": 1270
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 2.3613835184605527e-06,
+      "loss": 0.4,
+      "step": 1280
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 2.239749669118272e-06,
+      "loss": 0.4033,
+      "step": 1290
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 2.1209358119931845e-06,
+      "loss": 0.4108,
+      "step": 1300
+    },
+    {
+      "epoch": 1.59,
+      "learning_rate": 2.0049851227739746e-06,
+      "loss": 0.4039,
+      "step": 1310
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 1.891939736704641e-06,
+      "loss": 0.4134,
+      "step": 1320
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 1.7818407332729914e-06,
+      "loss": 0.4096,
+      "step": 1330
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 1.6747281212828193e-06,
+      "loss": 0.4128,
+      "step": 1340
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 1.570640824315095e-06,
+      "loss": 0.4065,
+      "step": 1350
+    },
+    {
+      "epoch": 1.65,
+      "learning_rate": 1.4696166665835853e-06,
+      "loss": 0.4054,
+      "step": 1360
+    },
+    {
+      "epoch": 1.66,
+      "learning_rate": 1.3716923591899167e-06,
+      "loss": 0.408,
+      "step": 1370
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 1.2769034867831588e-06,
+      "loss": 0.4029,
+      "step": 1380
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 1.1852844946287434e-06,
+      "loss": 0.4044,
+      "step": 1390
+    },
+    {
+      "epoch": 1.7,
+      "learning_rate": 1.0968686760914248e-06,
+      "loss": 0.4138,
+      "step": 1400
+    },
+    {
+      "epoch": 1.71,
+      "learning_rate": 1.0116881605368112e-06,
+      "loss": 0.4042,
+      "step": 1410
+    },
+    {
+      "epoch": 1.72,
+      "learning_rate": 9.297739016559226e-07,
+      "loss": 0.3991,
+      "step": 1420
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 8.511556662169218e-07,
+      "loss": 0.4039,
+      "step": 1430
+    },
+    {
+      "epoch": 1.75,
+      "learning_rate": 7.758620232482083e-07,
+      "loss": 0.3994,
+      "step": 1440
+    },
+    {
+      "epoch": 1.76,
+      "learning_rate": 7.039203336567247e-07,
+      "loss": 0.4016,
+      "step": 1450
+    },
+    {
+      "epoch": 1.77,
+      "learning_rate": 6.353567402853056e-07,
+      "loss": 0.3923,
+      "step": 1460
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 5.701961584126392e-07,
+      "loss": 0.4143,
+      "step": 1470
+    },
+    {
+      "epoch": 1.8,
+      "learning_rate": 5.084622666993244e-07,
+      "loss": 0.3955,
+      "step": 1480
+    },
+    {
+      "epoch": 1.81,
+      "learning_rate": 4.501774985832974e-07,
+      "loss": 0.4004,
+      "step": 1490
+    },
+    {
+      "epoch": 1.82,
+      "learning_rate": 3.953630341277603e-07,
+      "loss": 0.4099,
+      "step": 1500
+    },
+    {
+      "epoch": 1.83,
+      "learning_rate": 3.440387923245714e-07,
+      "loss": 0.4063,
+      "step": 1510
+    },
+    {
+      "epoch": 1.84,
+      "learning_rate": 2.9622342385589256e-07,
+      "loss": 0.3992,
+      "step": 1520
+    },
+    {
+      "epoch": 1.86,
+      "learning_rate": 2.519343043167399e-07,
+      "loss": 0.4101,
+      "step": 1530
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 2.111875279008657e-07,
+      "loss": 0.3898,
+      "step": 1540
+    },
+    {
+      "epoch": 1.88,
+      "learning_rate": 1.7399790155230633e-07,
+      "loss": 0.412,
+      "step": 1550
+    },
+    {
+      "epoch": 1.89,
+      "learning_rate": 1.4037893958469994e-07,
+      "loss": 0.4033,
+      "step": 1560
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 1.1034285877032147e-07,
+      "loss": 0.3981,
+      "step": 1570
+    },
+    {
+      "epoch": 1.92,
+      "learning_rate": 8.390057390064266e-08,
+      "loss": 0.4058,
+      "step": 1580
+    },
+    {
+      "epoch": 1.93,
+      "learning_rate": 6.10616938200137e-08,
+      "loss": 0.3935,
+      "step": 1590
+    },
+    {
+      "epoch": 1.94,
+      "learning_rate": 4.183451793390747e-08,
+      "loss": 0.4147,
+      "step": 1600
+    },
+    {
+      "epoch": 1.95,
+      "learning_rate": 2.6226033193007538e-08,
+      "loss": 0.4007,
+      "step": 1610
+    },
+    {
+      "epoch": 1.96,
+      "learning_rate": 1.424191155422583e-08,
+      "loss": 0.4087,
+      "step": 1620
+    },
+    {
+      "epoch": 1.98,
+      "learning_rate": 5.886507919570239e-09,
+      "loss": 0.4052,
+      "step": 1630
+    },
+    {
+      "epoch": 1.99,
+      "learning_rate": 1.1628585536216374e-09,
+      "loss": 0.4062,
+      "step": 1640
+    },
+    {
+      "epoch": 2.0,
+      "step": 1648,
+      "total_flos": 1323567688974336.0,
+      "train_loss": 0.4584712987964593,
+      "train_runtime": 26272.8035,
+      "train_samples_per_second": 16.064,
+      "train_steps_per_second": 0.063
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1648,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "total_flos": 1323567688974336.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f52cb03ce2e1a8f81e2586dcc378c4a144af7ed39485c0472828d5eb7f71cdb
+size 6075