Checkpoint first release.

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "[PAD]": 32000
+}

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "reward_model_llama_new_scgeme/checkpoint-5400",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "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": 32,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.28.1",
+  "use_cache": true,
+  "vocab_size": 32001
+}

generation_config.json

@@ -0,0 +1,10 @@
+{
+  "bos_token_id": 1,
+  "do_sample": true,
+  "eos_token_id": 2,
+  "max_length": 4096,
+  "pad_token_id": 0,
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.28.1"
+}

pytorch_model-00001-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef8f2e4fa1fd976b711e48fd3d3af9fab9fa19d8a6259af3caf1b5bd16234c6c
+size 9878005970

pytorch_model-00002-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a9b6c535430b6cff55fb323f4b289beeb32f3f0cf7b650fd2899f15454e35b1
+size 9894801014

pytorch_model-00003-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce66101de944ddcd48ed9cac10280cf0861ba4a4f68ff820ac89454eed56abc8
+size 7181007033

pytorch_model.bin.index.json

@@ -0,0 +1,330 @@
+{
+  "metadata": {
+    "total_size": 26953703424
+  },
+  "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.rotary_emb.inv_freq": "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.rotary_emb.inv_freq": "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.rotary_emb.inv_freq": "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-00002-of-00003.bin",
+    "model.layers.11.mlp.down_proj.weight": "pytorch_model-00002-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-00002-of-00003.bin",
+    "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00002-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.rotary_emb.inv_freq": "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-00002-of-00003.bin",
+    "model.layers.12.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.12.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.12.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.13.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.13.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.13.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.13.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.14.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.14.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.14.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.14.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00002-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-00002-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-00002-of-00003.bin",
+    "model.layers.15.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-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.rotary_emb.inv_freq": "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.rotary_emb.inv_freq": "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.rotary_emb.inv_freq": "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.rotary_emb.inv_freq": "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.rotary_emb.inv_freq": "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.rotary_emb.inv_freq": "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.rotary_emb.inv_freq": "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.rotary_emb.inv_freq": "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-00003-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-00003-of-00003.bin",
+    "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00003-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.rotary_emb.inv_freq": "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-00003-of-00003.bin",
+    "model.layers.24.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.24.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.24.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
+    "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.25.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.25.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.25.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.25.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
+    "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.26.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.26.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.26.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.26.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
+    "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.27.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.27.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.27.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.27.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
+    "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.28.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.28.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.28.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.28.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
+    "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.29.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.29.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.29.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.29.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
+    "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00003-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.rotary_emb.inv_freq": "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-00003-of-00003.bin",
+    "model.layers.30.mlp.up_proj.weight": "pytorch_model-00003-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-00003-of-00003.bin",
+    "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.30.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
+    "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00003-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.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
+    "model.layers.31.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.rotary_emb.inv_freq": "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.rotary_emb.inv_freq": "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.rotary_emb.inv_freq": "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.rotary_emb.inv_freq": "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.rotary_emb.inv_freq": "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.rotary_emb.inv_freq": "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 +1,6 @@
+{
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "[PAD]",
+  "unk_token": "<unk>"
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,35 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": false,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "legacy": false,
+  "model_max_length": 840,
+  "pad_token": null,
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

trainer_state.json

@@ -0,0 +1,1855 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.9993461915658712,
+  "global_step": 3058,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01,
+      "learning_rate": 6.451612903225806e-06,
+      "loss": 0.2905,
+      "step": 10
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.2903225806451613e-05,
+      "loss": 0.1863,
+      "step": 20
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.935483870967742e-05,
+      "loss": 0.2482,
+      "step": 30
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.999956375870988e-05,
+      "loss": 0.1986,
+      "step": 40
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.999805581299163e-05,
+      "loss": 0.215,
+      "step": 50
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.9995470939538076e-05,
+      "loss": 0.2792,
+      "step": 60
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.999180941677554e-05,
+      "loss": 0.2919,
+      "step": 70
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.998707163910024e-05,
+      "loss": 0.2196,
+      "step": 80
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.9981258116835808e-05,
+      "loss": 0.3381,
+      "step": 90
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.9974369476178333e-05,
+      "loss": 0.1835,
+      "step": 100
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.9966406459128885e-05,
+      "loss": 0.2671,
+      "step": 110
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.9957369923413616e-05,
+      "loss": 0.1615,
+      "step": 120
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.9947260842391358e-05,
+      "loss": 0.1339,
+      "step": 130
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.9936080304948787e-05,
+      "loss": 0.2017,
+      "step": 140
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.992382951538313e-05,
+      "loss": 0.2972,
+      "step": 150
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.9910509793272433e-05,
+      "loss": 0.1995,
+      "step": 160
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.989612257333346e-05,
+      "loss": 0.2271,
+      "step": 170
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.988066940526711e-05,
+      "loss": 0.1475,
+      "step": 180
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.986415195359154e-05,
+      "loss": 0.4046,
+      "step": 190
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.984657199746282e-05,
+      "loss": 0.2995,
+      "step": 200
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.9827931430483342e-05,
+      "loss": 0.2134,
+      "step": 210
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.9808232260497826e-05,
+      "loss": 0.3513,
+      "step": 220
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.9787476609377055e-05,
+      "loss": 0.2049,
+      "step": 230
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.976566671278932e-05,
+      "loss": 0.2787,
+      "step": 240
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.974280491995961e-05,
+      "loss": 0.223,
+      "step": 250
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.9718893693416562e-05,
+      "loss": 0.2959,
+      "step": 260
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.969393560872722e-05,
+      "loss": 0.293,
+      "step": 270
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.966793335421961e-05,
+      "loss": 0.2299,
+      "step": 280
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.964088973069316e-05,
+      "loss": 0.2127,
+      "step": 290
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.9612807651117034e-05,
+      "loss": 0.16,
+      "step": 300
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.958369014031635e-05,
+      "loss": 0.2136,
+      "step": 310
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.955354033464637e-05,
+      "loss": 0.2905,
+      "step": 320
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.952236148165468e-05,
+      "loss": 0.2233,
+      "step": 330
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.9490156939731347e-05,
+      "loss": 0.1722,
+      "step": 340
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.9456930177747247e-05,
+      "loss": 0.197,
+      "step": 350
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.942268477468034e-05,
+      "loss": 0.1626,
+      "step": 360
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.938742441923022e-05,
+      "loss": 0.1259,
+      "step": 370
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.935115290942077e-05,
+      "loss": 0.2693,
+      "step": 380
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.931387415219106e-05,
+      "loss": 0.2404,
+      "step": 390
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.9275592162974527e-05,
+      "loss": 0.1602,
+      "step": 400
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.9236311065266448e-05,
+      "loss": 0.1392,
+      "step": 410
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.9196035090179793e-05,
+      "loss": 0.1638,
+      "step": 420
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.9154768575989466e-05,
+      "loss": 0.1532,
+      "step": 430
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.9112515967665016e-05,
+      "loss": 0.2115,
+      "step": 440
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.9069281816391868e-05,
+      "loss": 0.1884,
+      "step": 450
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.9025070779081064e-05,
+      "loss": 0.1788,
+      "step": 460
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.8979887617867684e-05,
+      "loss": 0.1243,
+      "step": 470
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.8933737199597882e-05,
+      "loss": 0.2044,
+      "step": 480
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.888662449530467e-05,
+      "loss": 0.1791,
+      "step": 490
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.8838554579672443e-05,
+      "loss": 0.2833,
+      "step": 500
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.8789532630490405e-05,
+      "loss": 0.16,
+      "step": 510
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.873956392809482e-05,
+      "loss": 0.1645,
+      "step": 520
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 1.868865385480027e-05,
+      "loss": 0.245,
+      "step": 530
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 1.8636807894319876e-05,
+      "loss": 0.2011,
+      "step": 540
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.8584031631174653e-05,
+      "loss": 0.1425,
+      "step": 550
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.8530330750091978e-05,
+      "loss": 0.2352,
+      "step": 560
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.8475711035393255e-05,
+      "loss": 0.1825,
+      "step": 570
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.8420178370370872e-05,
+      "loss": 0.2032,
+      "step": 580
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.8363738736654484e-05,
+      "loss": 0.2187,
+      "step": 590
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.830639821356672e-05,
+      "loss": 0.1901,
+      "step": 600
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.8248162977468346e-05,
+      "loss": 0.2359,
+      "step": 610
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.818903930109299e-05,
+      "loss": 0.2114,
+      "step": 620
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.8129033552871492e-05,
+      "loss": 0.2116,
+      "step": 630
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.806815219624591e-05,
+      "loss": 0.2054,
+      "step": 640
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.800640178897335e-05,
+      "loss": 0.2725,
+      "step": 650
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1.7943788982419586e-05,
+      "loss": 0.2232,
+      "step": 660
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.788032052084263e-05,
+      "loss": 0.2528,
+      "step": 670
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.781600324066626e-05,
+      "loss": 0.2436,
+      "step": 680
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.7750844069743676e-05,
+      "loss": 0.1689,
+      "step": 690
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.7684850026611248e-05,
+      "loss": 0.1595,
+      "step": 700
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.7618028219732533e-05,
+      "loss": 0.1997,
+      "step": 710
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.7550385846732606e-05,
+      "loss": 0.5174,
+      "step": 720
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.748193019362275e-05,
+      "loss": 0.1299,
+      "step": 730
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.741266863401569e-05,
+      "loss": 0.2168,
+      "step": 740
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.734260862833132e-05,
+      "loss": 0.1283,
+      "step": 750
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.7271757722993133e-05,
+      "loss": 0.4788,
+      "step": 760
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.720012354961536e-05,
+      "loss": 0.1463,
+      "step": 770
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1.712771382418094e-05,
+      "loss": 0.1469,
+      "step": 780
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 1.705453634621042e-05,
+      "loss": 0.2196,
+      "step": 790
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 1.6980598997921793e-05,
+      "loss": 0.1376,
+      "step": 800
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 1.6905909743381544e-05,
+      "loss": 0.2466,
+      "step": 810
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 1.683047662764675e-05,
+      "loss": 0.2474,
+      "step": 820
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 1.6754307775898547e-05,
+      "loss": 0.2719,
+      "step": 830
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 1.6677411392566937e-05,
+      "loss": 0.2841,
+      "step": 840
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 1.659979576044704e-05,
+      "loss": 0.1851,
+      "step": 850
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 1.6521469239806943e-05,
+      "loss": 0.6387,
+      "step": 860
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 1.6442440267487174e-05,
+      "loss": 0.2083,
+      "step": 870
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 1.636271735599194e-05,
+      "loss": 0.1612,
+      "step": 880
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 1.628230909257222e-05,
+      "loss": 0.2165,
+      "step": 890
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 1.6201224138300787e-05,
+      "loss": 0.1853,
+      "step": 900
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 1.6119471227139306e-05,
+      "loss": 0.2882,
+      "step": 910
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 1.603705916499755e-05,
+      "loss": 0.1554,
+      "step": 920
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 1.5953996828784912e-05,
+      "loss": 0.1088,
+      "step": 930
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 1.5870293165454205e-05,
+      "loss": 0.1696,
+      "step": 940
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 1.578595719103797e-05,
+      "loss": 0.225,
+      "step": 950
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 1.5700997989677337e-05,
+      "loss": 0.2903,
+      "step": 960
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 1.56154247126435e-05,
+      "loss": 0.1684,
+      "step": 970
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 1.5529246577352056e-05,
+      "loss": 0.1553,
+      "step": 980
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 1.544247286637011e-05,
+      "loss": 0.1534,
+      "step": 990
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 1.5355112926416442e-05,
+      "loss": 0.1236,
+      "step": 1000
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 1.526717616735474e-05,
+      "loss": 0.2146,
+      "step": 1010
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 1.5178672061180008e-05,
+      "loss": 0.2008,
+      "step": 1020
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 1.5089610140998332e-05,
+      "loss": 0.1754,
+      "step": 1030
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 1.5000000000000002e-05,
+      "loss": 0.2003,
+      "step": 1040
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 1.4909851290426215e-05,
+      "loss": 0.2021,
+      "step": 1050
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 1.4819173722529392e-05,
+      "loss": 0.2995,
+      "step": 1060
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 1.4727977063527248e-05,
+      "loss": 0.1397,
+      "step": 1070
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 1.4636271136550723e-05,
+      "loss": 0.1469,
+      "step": 1080
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 1.4544065819585911e-05,
+      "loss": 0.1932,
+      "step": 1090
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 1.4451371044410057e-05,
+      "loss": 0.1776,
+      "step": 1100
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 1.4358196795521755e-05,
+      "loss": 0.1927,
+      "step": 1110
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 1.4264553109065511e-05,
+      "loss": 0.1359,
+      "step": 1120
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 1.4170450071750686e-05,
+      "loss": 0.2743,
+      "step": 1130
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 1.4075897819765033e-05,
+      "loss": 0.1994,
+      "step": 1140
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 1.3980906537682876e-05,
+      "loss": 0.1961,
+      "step": 1150
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 1.3885486457368118e-05,
+      "loss": 0.2461,
+      "step": 1160
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 1.3789647856872102e-05,
+      "loss": 0.1861,
+      "step": 1170
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 1.369340105932653e-05,
+      "loss": 0.1926,
+      "step": 1180
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 1.359675643183154e-05,
+      "loss": 0.1551,
+      "step": 1190
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 1.3499724384338999e-05,
+      "loss": 0.2548,
+      "step": 1200
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 1.3402315368531226e-05,
+      "loss": 0.2113,
+      "step": 1210
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 1.33045398766952e-05,
+      "loss": 0.1721,
+      "step": 1220
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 1.3206408440592385e-05,
+      "loss": 0.1798,
+      "step": 1230
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1.3107931630324333e-05,
+      "loss": 0.1337,
+      "step": 1240
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.3009120053194133e-05,
+      "loss": 0.2212,
+      "step": 1250
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.2909984352563845e-05,
+      "loss": 0.2069,
+      "step": 1260
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1.2810535206708089e-05,
+      "loss": 0.2119,
+      "step": 1270
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.2710783327663819e-05,
+      "loss": 0.1255,
+      "step": 1280
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.2610739460076522e-05,
+      "loss": 0.1392,
+      "step": 1290
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.2510414380042843e-05,
+      "loss": 0.2273,
+      "step": 1300
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 1.2409818893949874e-05,
+      "loss": 0.202,
+      "step": 1310
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 1.230896383731114e-05,
+      "loss": 0.1433,
+      "step": 1320
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 1.2207860073599478e-05,
+      "loss": 0.1484,
+      "step": 1330
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 1.2106518493076889e-05,
+      "loss": 0.1173,
+      "step": 1340
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 1.2004950011621501e-05,
+      "loss": 0.1549,
+      "step": 1350
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 1.1903165569551792e-05,
+      "loss": 0.1346,
+      "step": 1360
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 1.1801176130448148e-05,
+      "loss": 0.1434,
+      "step": 1370
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 1.1698992679971964e-05,
+      "loss": 0.169,
+      "step": 1380
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 1.1596626224682306e-05,
+      "loss": 0.2079,
+      "step": 1390
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 1.1494087790850375e-05,
+      "loss": 0.1593,
+      "step": 1400
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 1.1391388423271818e-05,
+      "loss": 0.2082,
+      "step": 1410
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 1.1288539184077057e-05,
+      "loss": 0.1683,
+      "step": 1420
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 1.1185551151539737e-05,
+      "loss": 0.1701,
+      "step": 1430
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1.1082435418883457e-05,
+      "loss": 0.179,
+      "step": 1440
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.097920309308686e-05,
+      "loss": 0.2179,
+      "step": 1450
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.0875865293687281e-05,
+      "loss": 0.1826,
+      "step": 1460
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 1.0772433151583001e-05,
+      "loss": 0.2002,
+      "step": 1470
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 1.06689178078343e-05,
+      "loss": 0.1828,
+      "step": 1480
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 1.056533041246343e-05,
+      "loss": 0.1393,
+      "step": 1490
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 1.0461682123253578e-05,
+      "loss": 0.1597,
+      "step": 1500
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 1.0357984104547038e-05,
+      "loss": 0.1738,
+      "step": 1510
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 1.0254247526042656e-05,
+      "loss": 0.2535,
+      "step": 1520
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 1.0150483561592687e-05,
+      "loss": 0.1162,
+      "step": 1530
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 1.0046703387999242e-05,
+      "loss": 0.4422,
+      "step": 1540
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 9.942918183810368e-06,
+      "loss": 0.1518,
+      "step": 1550
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 9.839139128115978e-06,
+      "loss": 0.061,
+      "step": 1560
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 9.735377399343714e-06,
+      "loss": 0.111,
+      "step": 1570
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 9.631644174054862e-06,
+      "loss": 0.0424,
+      "step": 1580
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 9.527950625740502e-06,
+      "loss": 0.035,
+      "step": 1590
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 9.424307923617948e-06,
+      "loss": 0.0563,
+      "step": 1600
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 9.320727231427688e-06,
+      "loss": 0.0894,
+      "step": 1610
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 9.217219706230892e-06,
+      "loss": 0.0344,
+      "step": 1620
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 9.113796497207637e-06,
+      "loss": 0.068,
+      "step": 1630
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 9.010468744455994e-06,
+      "loss": 0.0403,
+      "step": 1640
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 8.907247577792087e-06,
+      "loss": 0.035,
+      "step": 1650
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 8.80414411555125e-06,
+      "loss": 0.071,
+      "step": 1660
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 8.70116946339044e-06,
+      "loss": 0.0448,
+      "step": 1670
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 8.598334713092002e-06,
+      "loss": 0.0634,
+      "step": 1680
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 8.49565094136893e-06,
+      "loss": 0.058,
+      "step": 1690
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 8.39312920867176e-06,
+      "loss": 0.0806,
+      "step": 1700
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 8.290780557997192e-06,
+      "loss": 0.0375,
+      "step": 1710
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 8.188616013698629e-06,
+      "loss": 0.0744,
+      "step": 1720
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 8.086646580298686e-06,
+      "loss": 0.0941,
+      "step": 1730
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 7.984883241303865e-06,
+      "loss": 0.0442,
+      "step": 1740
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 7.883336958021463e-06,
+      "loss": 0.0398,
+      "step": 1750
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 7.78201866837891e-06,
+      "loss": 0.048,
+      "step": 1760
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 7.680939285745589e-06,
+      "loss": 0.0534,
+      "step": 1770
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 7.58010969775732e-06,
+      "loss": 0.0267,
+      "step": 1780
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 7.479540765143619e-06,
+      "loss": 0.0408,
+      "step": 1790
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 7.379243320557841e-06,
+      "loss": 0.0536,
+      "step": 1800
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 7.279228167410356e-06,
+      "loss": 0.03,
+      "step": 1810
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 7.179506078704874e-06,
+      "loss": 0.04,
+      "step": 1820
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 7.080087795878047e-06,
+      "loss": 0.0861,
+      "step": 1830
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 6.980984027642468e-06,
+      "loss": 0.0528,
+      "step": 1840
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 6.8822054488331876e-06,
+      "loss": 0.0319,
+      "step": 1850
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 6.783762699257907e-06,
+      "loss": 0.0628,
+      "step": 1860
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 6.685666382550901e-06,
+      "loss": 0.0377,
+      "step": 1870
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 6.587927065030883e-06,
+      "loss": 0.0466,
+      "step": 1880
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 6.490555274562853e-06,
+      "loss": 0.0481,
+      "step": 1890
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 6.393561499424108e-06,
+      "loss": 0.0634,
+      "step": 1900
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 6.296956187174505e-06,
+      "loss": 0.0676,
+      "step": 1910
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 6.200749743531129e-06,
+      "loss": 0.0525,
+      "step": 1920
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 6.104952531247437e-06,
+      "loss": 0.0784,
+      "step": 1930
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 6.009574868997061e-06,
+      "loss": 0.05,
+      "step": 1940
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 5.9146270302623355e-06,
+      "loss": 0.0371,
+      "step": 1950
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 5.820119242227715e-06,
+      "loss": 0.1927,
+      "step": 1960
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 5.726061684678153e-06,
+      "loss": 0.0825,
+      "step": 1970
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 5.632464488902606e-06,
+      "loss": 0.0259,
+      "step": 1980
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 5.539337736602748e-06,
+      "loss": 0.0442,
+      "step": 1990
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 5.446691458807052e-06,
+      "loss": 0.0398,
+      "step": 2000
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 5.354535634790283e-06,
+      "loss": 0.0491,
+      "step": 2010
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 5.262880190998612e-06,
+      "loss": 0.0754,
+      "step": 2020
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 5.171734999980404e-06,
+      "loss": 0.029,
+      "step": 2030
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 5.081109879322788e-06,
+      "loss": 0.2079,
+      "step": 2040
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 4.991014590594199e-06,
+      "loss": 0.066,
+      "step": 2050
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 4.901458838292891e-06,
+      "loss": 0.0516,
+      "step": 2060
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 4.812452268801658e-06,
+      "loss": 0.043,
+      "step": 2070
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 4.724004469348763e-06,
+      "loss": 0.0311,
+      "step": 2080
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 4.63612496697528e-06,
+      "loss": 0.0295,
+      "step": 2090
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 4.548823227508887e-06,
+      "loss": 0.0641,
+      "step": 2100
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 4.462108654544282e-06,
+      "loss": 0.052,
+      "step": 2110
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 4.375990588430261e-06,
+      "loss": 0.0502,
+      "step": 2120
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 4.290478305263672e-06,
+      "loss": 0.0765,
+      "step": 2130
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 4.205581015890214e-06,
+      "loss": 0.0447,
+      "step": 2140
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 4.121307864912332e-06,
+      "loss": 0.0721,
+      "step": 2150
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 4.037667929704197e-06,
+      "loss": 0.0552,
+      "step": 2160
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 3.954670219433957e-06,
+      "loss": 0.1431,
+      "step": 2170
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 3.8723236740933365e-06,
+      "loss": 0.0592,
+      "step": 2180
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 3.7906371635346485e-06,
+      "loss": 0.0428,
+      "step": 2190
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 3.7096194865154324e-06,
+      "loss": 0.0487,
+      "step": 2200
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 3.629279369750657e-06,
+      "loss": 0.0743,
+      "step": 2210
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 3.549625466972776e-06,
+      "loss": 0.1101,
+      "step": 2220
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 3.4706663579995737e-06,
+      "loss": 0.0394,
+      "step": 2230
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 3.3924105478100245e-06,
+      "loss": 0.0389,
+      "step": 2240
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 3.314866465628167e-06,
+      "loss": 0.0714,
+      "step": 2250
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 3.2380424640151742e-06,
+      "loss": 0.0265,
+      "step": 2260
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 3.1619468179696745e-06,
+      "loss": 0.0235,
+      "step": 2270
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 3.086587724036397e-06,
+      "loss": 0.0216,
+      "step": 2280
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 3.0119732994233254e-06,
+      "loss": 0.0661,
+      "step": 2290
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 2.9381115811273254e-06,
+      "loss": 0.0427,
+      "step": 2300
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 2.8650105250684835e-06,
+      "loss": 0.0399,
+      "step": 2310
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 2.7926780052331192e-06,
+      "loss": 0.0667,
+      "step": 2320
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 2.7211218128256733e-06,
+      "loss": 0.0465,
+      "step": 2330
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 2.6503496554294606e-06,
+      "loss": 0.0335,
+      "step": 2340
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 2.5803691561764855e-06,
+      "loss": 0.038,
+      "step": 2350
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 2.5111878529263e-06,
+      "loss": 0.0473,
+      "step": 2360
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 2.4428131974540982e-06,
+      "loss": 0.0653,
+      "step": 2370
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 2.3752525546480344e-06,
+      "loss": 0.0351,
+      "step": 2380
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 2.3085132017159427e-06,
+      "loss": 0.0225,
+      "step": 2390
+    },
+    {
+      "epoch": 1.57,
+      "learning_rate": 2.2426023274014686e-06,
+      "loss": 0.0689,
+      "step": 2400
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 2.177527031209747e-06,
+      "loss": 0.0715,
+      "step": 2410
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 2.113294322642694e-06,
+      "loss": 0.016,
+      "step": 2420
+    },
+    {
+      "epoch": 1.59,
+      "learning_rate": 2.0499111204439793e-06,
+      "loss": 0.0894,
+      "step": 2430
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 1.987384251853789e-06,
+      "loss": 0.2198,
+      "step": 2440
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 1.9257204518734276e-06,
+      "loss": 0.0503,
+      "step": 2450
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 1.8649263625398806e-06,
+      "loss": 0.0374,
+      "step": 2460
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 1.8050085322103616e-06,
+      "loss": 0.048,
+      "step": 2470
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 1.7459734148569818e-06,
+      "loss": 0.0214,
+      "step": 2480
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 1.6878273693715474e-06,
+      "loss": 0.0383,
+      "step": 2490
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 1.630576658880636e-06,
+      "loss": 0.0333,
+      "step": 2500
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 1.5742274500709686e-06,
+      "loss": 0.0332,
+      "step": 2510
+    },
+    {
+      "epoch": 1.65,
+      "learning_rate": 1.5187858125251642e-06,
+      "loss": 0.0442,
+      "step": 2520
+    },
+    {
+      "epoch": 1.65,
+      "learning_rate": 1.4642577180679795e-06,
+      "loss": 0.0333,
+      "step": 2530
+    },
+    {
+      "epoch": 1.66,
+      "learning_rate": 1.4106490401230388e-06,
+      "loss": 0.0441,
+      "step": 2540
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 1.3579655530802115e-06,
+      "loss": 0.0521,
+      "step": 2550
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 1.3062129316736039e-06,
+      "loss": 0.0296,
+      "step": 2560
+    },
+    {
+      "epoch": 1.68,
+      "learning_rate": 1.2553967503703401e-06,
+      "loss": 0.0174,
+      "step": 2570
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 1.2055224827700895e-06,
+      "loss": 0.0334,
+      "step": 2580
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 1.1565955010155072e-06,
+      "loss": 0.019,
+      "step": 2590
+    },
+    {
+      "epoch": 1.7,
+      "learning_rate": 1.1086210752135628e-06,
+      "loss": 0.0716,
+      "step": 2600
+    },
+    {
+      "epoch": 1.71,
+      "learning_rate": 1.0616043728678915e-06,
+      "loss": 0.0423,
+      "step": 2610
+    },
+    {
+      "epoch": 1.71,
+      "learning_rate": 1.0155504583221708e-06,
+      "loss": 0.0552,
+      "step": 2620
+    },
+    {
+      "epoch": 1.72,
+      "learning_rate": 9.704642922146345e-07,
+      "loss": 0.0365,
+      "step": 2630
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 9.263507309437314e-07,
+      "loss": 0.0911,
+      "step": 2640
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 8.832145261450331e-07,
+      "loss": 0.0219,
+      "step": 2650
+    },
+    {
+      "epoch": 1.74,
+      "learning_rate": 8.410603241794113e-07,
+      "loss": 0.0233,
+      "step": 2660
+    },
+    {
+      "epoch": 1.75,
+      "learning_rate": 7.998926656325668e-07,
+      "loss": 0.105,
+      "step": 2670
+    },
+    {
+      "epoch": 1.75,
+      "learning_rate": 7.597159848259472e-07,
+      "loss": 0.0742,
+      "step": 2680
+    },
+    {
+      "epoch": 1.76,
+      "learning_rate": 7.205346093390964e-07,
+      "loss": 0.0466,
+      "step": 2690
+    },
+    {
+      "epoch": 1.77,
+      "learning_rate": 6.823527595435353e-07,
+      "loss": 0.0266,
+      "step": 2700
+    },
+    {
+      "epoch": 1.77,
+      "learning_rate": 6.451745481481508e-07,
+      "loss": 0.0374,
+      "step": 2710
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 6.090039797562163e-07,
+      "loss": 0.043,
+      "step": 2720
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 5.73844950434026e-07,
+      "loss": 0.0452,
+      "step": 2730
+    },
+    {
+      "epoch": 1.79,
+      "learning_rate": 5.397012472912521e-07,
+      "loss": 0.0237,
+      "step": 2740
+    },
+    {
+      "epoch": 1.8,
+      "learning_rate": 5.065765480730033e-07,
+      "loss": 0.0297,
+      "step": 2750
+    },
+    {
+      "epoch": 1.8,
+      "learning_rate": 4.744744207636942e-07,
+      "loss": 0.039,
+      "step": 2760
+    },
+    {
+      "epoch": 1.81,
+      "learning_rate": 4.4339832320272057e-07,
+      "loss": 0.1598,
+      "step": 2770
+    },
+    {
+      "epoch": 1.82,
+      "learning_rate": 4.1335160271200104e-07,
+      "loss": 0.0168,
+      "step": 2780
+    },
+    {
+      "epoch": 1.82,
+      "learning_rate": 3.843374957354262e-07,
+      "loss": 0.0359,
+      "step": 2790
+    },
+    {
+      "epoch": 1.83,
+      "learning_rate": 3.563591274902467e-07,
+      "loss": 0.0674,
+      "step": 2800
+    },
+    {
+      "epoch": 1.84,
+      "learning_rate": 3.2941951163045215e-07,
+      "loss": 0.0769,
+      "step": 2810
+    },
+    {
+      "epoch": 1.84,
+      "learning_rate": 3.0352154992214557e-07,
+      "loss": 0.0542,
+      "step": 2820
+    },
+    {
+      "epoch": 1.85,
+      "learning_rate": 2.786680319309998e-07,
+      "loss": 0.0338,
+      "step": 2830
+    },
+    {
+      "epoch": 1.86,
+      "learning_rate": 2.5486163472176693e-07,
+      "loss": 0.1245,
+      "step": 2840
+    },
+    {
+      "epoch": 1.86,
+      "learning_rate": 2.3210492256993677e-07,
+      "loss": 0.0397,
+      "step": 2850
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 2.1040034668551646e-07,
+      "loss": 0.0411,
+      "step": 2860
+    },
+    {
+      "epoch": 1.88,
+      "learning_rate": 1.8975024494900963e-07,
+      "loss": 0.0472,
+      "step": 2870
+    },
+    {
+      "epoch": 1.88,
+      "learning_rate": 1.7015684165959113e-07,
+      "loss": 0.03,
+      "step": 2880
+    },
+    {
+      "epoch": 1.89,
+      "learning_rate": 1.5162224729552088e-07,
+      "loss": 0.041,
+      "step": 2890
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 1.3414845828681466e-07,
+      "loss": 0.034,
+      "step": 2900
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 1.1773735680020493e-07,
+      "loss": 0.0426,
+      "step": 2910
+    },
+    {
+      "epoch": 1.91,
+      "learning_rate": 1.0239071053639971e-07,
+      "loss": 0.0581,
+      "step": 2920
+    },
+    {
+      "epoch": 1.92,
+      "learning_rate": 8.811017253968379e-08,
+      "loss": 0.0503,
+      "step": 2930
+    },
+    {
+      "epoch": 1.92,
+      "learning_rate": 7.489728101985671e-08,
+      "loss": 0.0549,
+      "step": 2940
+    },
+    {
+      "epoch": 1.93,
+      "learning_rate": 6.275345918655307e-08,
+      "loss": 0.0429,
+      "step": 2950
+    },
+    {
+      "epoch": 1.94,
+      "learning_rate": 5.1680015095936234e-08,
+      "loss": 0.028,
+      "step": 2960
+    },
+    {
+      "epoch": 1.94,
+      "learning_rate": 4.167814150980887e-08,
+      "loss": 0.0321,
+      "step": 2970
+    },
+    {
+      "epoch": 1.95,
+      "learning_rate": 3.274891576713346e-08,
+      "loss": 0.0646,
+      "step": 2980
+    },
+    {
+      "epoch": 1.95,
+      "learning_rate": 2.489329966798626e-08,
+      "loss": 0.0284,
+      "step": 2990
+    },
+    {
+      "epoch": 1.96,
+      "learning_rate": 1.8112139369962367e-08,
+      "loss": 0.0322,
+      "step": 3000
+    },
+    {
+      "epoch": 1.97,
+      "learning_rate": 1.240616529702976e-08,
+      "loss": 0.0388,
+      "step": 3010
+    },
+    {
+      "epoch": 1.97,
+      "learning_rate": 7.775992060854442e-09,
+      "loss": 0.0574,
+      "step": 3020
+    },
+    {
+      "epoch": 1.98,
+      "learning_rate": 4.2221183945978515e-09,
+      "loss": 0.0359,
+      "step": 3030
+    },
+    {
+      "epoch": 1.99,
+      "learning_rate": 1.744927099193161e-09,
+      "loss": 0.0459,
+      "step": 3040
+    },
+    {
+      "epoch": 1.99,
+      "learning_rate": 3.446850021204817e-10,
+      "loss": 0.0343,
+      "step": 3050
+    },
+    {
+      "epoch": 2.0,
+      "step": 3058,
+      "total_flos": 5.835951563016765e+17,
+      "train_loss": 0.13229776309782418,
+      "train_runtime": 69734.0297,
+      "train_samples_per_second": 0.702,
+      "train_steps_per_second": 0.044
+    }
+  ],
+  "max_steps": 3058,
+  "num_train_epochs": 2,
+  "total_flos": 5.835951563016765e+17,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce51f679978ee2278d404b7c67db77e777500990decb065bce73dfbf92f582b8
+size 3771