Upload 11 files

config.json

@@ -0,0 +1,23 @@
+{
+  "_name_or_path": "yahma/llama-7b-hf",
+  "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": 2048,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "pad_token_id": 0,
+  "rms_norm_eps": 1e-06,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.28.1",
+  "use_cache": false,
+  "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 0,
+  "transformers_version": "4.28.1"
+}

pytorch_model-00001-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc74878929e6c27be9bda6a195165f419ded1146d8348369449e2480245552a3
+size 9877989586

pytorch_model-00002-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d877b113a4a3916075542e7d2bdc7e92a42e56b8d6b2aa08cbad5ec218d7aad
+size 9894801014

pytorch_model-00003-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4d28fc85d3b888f4dbc4988bc00898586ee67d33846043a2c1de9cab37dfa87
+size 7180990649

pytorch_model.bin.index.json

@@ -0,0 +1,330 @@
+{
+  "metadata": {
+    "total_size": 26953670656
+  },
+  "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": "<unk>",
+  "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 +1,34 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "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
+  },
+  "model_max_length": 2048,
+  "pad_token": null,
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

trainer_state.json

@@ -0,0 +1,1861 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.9983673469387755,
+  "global_step": 306,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 3.5154,
+      "step": 1
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 1.6438,
+      "step": 2
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 6e-06,
+      "loss": 5.0573,
+      "step": 3
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 1.3106,
+      "step": 4
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1e-05,
+      "loss": 2.8288,
+      "step": 5
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.2e-05,
+      "loss": 1.3591,
+      "step": 6
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.4e-05,
+      "loss": 1.6707,
+      "step": 7
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 2.8298,
+      "step": 8
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.8e-05,
+      "loss": 1.1492,
+      "step": 9
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 2e-05,
+      "loss": 3.9368,
+      "step": 10
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.9999436774575783e-05,
+      "loss": 1.8524,
+      "step": 11
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.9997747161747696e-05,
+      "loss": 1.5353,
+      "step": 12
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.9994931351842327e-05,
+      "loss": 1.5734,
+      "step": 13
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.999098966204682e-05,
+      "loss": 2.9094,
+      "step": 14
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.998592253637315e-05,
+      "loss": 3.8923,
+      "step": 15
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.9979730545608128e-05,
+      "loss": 1.9739,
+      "step": 16
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.9972414387249074e-05,
+      "loss": 2.0022,
+      "step": 17
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.9963974885425267e-05,
+      "loss": 5.2733,
+      "step": 18
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.9954412990805107e-05,
+      "loss": 2.3556,
+      "step": 19
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.994372978048903e-05,
+      "loss": 1.4909,
+      "step": 20
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.9931926457888155e-05,
+      "loss": 2.0661,
+      "step": 21
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.9919004352588768e-05,
+      "loss": 2.496,
+      "step": 22
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.990496492020252e-05,
+      "loss": 1.8455,
+      "step": 23
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.9889809742202454e-05,
+      "loss": 4.4452,
+      "step": 24
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.9873540525744888e-05,
+      "loss": 2.5161,
+      "step": 25
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.9856159103477085e-05,
+      "loss": 2.9056,
+      "step": 26
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.983766743333084e-05,
+      "loss": 1.56,
+      "step": 27
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.9818067598301894e-05,
+      "loss": 1.3927,
+      "step": 28
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.9797361806215335e-05,
+      "loss": 2.709,
+      "step": 29
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.9775552389476865e-05,
+      "loss": 1.6687,
+      "step": 30
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.9752641804810083e-05,
+      "loss": 1.6412,
+      "step": 31
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.9728632632979746e-05,
+      "loss": 1.0969,
+      "step": 32
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.9703527578501052e-05,
+      "loss": 1.0695,
+      "step": 33
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.967732946933499e-05,
+      "loss": 2.8855,
+      "step": 34
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.9650041256569792e-05,
+      "loss": 2.5798,
+      "step": 35
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.9621666014088495e-05,
+      "loss": 3.1521,
+      "step": 36
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.9592206938222703e-05,
+      "loss": 2.5725,
+      "step": 37
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.956166734739251e-05,
+      "loss": 3.9284,
+      "step": 38
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.953005068173272e-05,
+      "loss": 5.3312,
+      "step": 39
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.949736050270532e-05,
+      "loss": 2.2761,
+      "step": 40
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.9463600492698297e-05,
+      "loss": 2.497,
+      "step": 41
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.9428774454610845e-05,
+      "loss": 1.5918,
+      "step": 42
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.9392886311424975e-05,
+      "loss": 2.6261,
+      "step": 43
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.9355940105763622e-05,
+      "loss": 1.5548,
+      "step": 44
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.9317939999435262e-05,
+      "loss": 1.1697,
+      "step": 45
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.9278890272965097e-05,
+      "loss": 5.6268,
+      "step": 46
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.9238795325112867e-05,
+      "loss": 1.2487,
+      "step": 47
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.9197659672377388e-05,
+      "loss": 1.8595,
+      "step": 48
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.915548794848775e-05,
+      "loss": 2.5708,
+      "step": 49
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.911228490388136e-05,
+      "loss": 1.3086,
+      "step": 50
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.906805540516885e-05,
+      "loss": 1.7013,
+      "step": 51
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.9022804434585854e-05,
+      "loss": 2.2736,
+      "step": 52
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 1.8976537089431793e-05,
+      "loss": 2.6403,
+      "step": 53
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 1.8929258581495688e-05,
+      "loss": 2.3578,
+      "step": 54
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.888097423646907e-05,
+      "loss": 2.7156,
+      "step": 55
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.8831689493346095e-05,
+      "loss": 3.6922,
+      "step": 56
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.8781409903810823e-05,
+      "loss": 2.7563,
+      "step": 57
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.8730141131611882e-05,
+      "loss": 1.3118,
+      "step": 58
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.8677888951924473e-05,
+      "loss": 2.7901,
+      "step": 59
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.8624659250699807e-05,
+      "loss": 3.2185,
+      "step": 60
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.8570458024002094e-05,
+      "loss": 1.7507,
+      "step": 61
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.8515291377333114e-05,
+      "loss": 2.0581,
+      "step": 62
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.8459165524944463e-05,
+      "loss": 2.1775,
+      "step": 63
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.8402086789137547e-05,
+      "loss": 1.598,
+      "step": 64
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.8344061599551397e-05,
+      "loss": 0.9338,
+      "step": 65
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1.8285096492438424e-05,
+      "loss": 1.384,
+      "step": 66
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.8225198109928116e-05,
+      "loss": 2.166,
+      "step": 67
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.8164373199278858e-05,
+      "loss": 3.1482,
+      "step": 68
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.8102628612117868e-05,
+      "loss": 1.6186,
+      "step": 69
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.8039971303669407e-05,
+      "loss": 1.7339,
+      "step": 70
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.79764083319713e-05,
+      "loss": 1.1894,
+      "step": 71
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.7911946857079886e-05,
+      "loss": 2.2082,
+      "step": 72
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.7846594140263475e-05,
+      "loss": 1.7231,
+      "step": 73
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.7780357543184396e-05,
+      "loss": 1.2418,
+      "step": 74
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.771324452706975e-05,
+      "loss": 4.6474,
+      "step": 75
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.7645262651870926e-05,
+      "loss": 1.5081,
+      "step": 76
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.7576419575412028e-05,
+      "loss": 2.6891,
+      "step": 77
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1.7506723052527243e-05,
+      "loss": 1.1384,
+      "step": 78
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 1.7436180934187307e-05,
+      "loss": 1.404,
+      "step": 79
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 1.7364801166615124e-05,
+      "loss": 2.1619,
+      "step": 80
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 1.7292591790390668e-05,
+      "loss": 1.3328,
+      "step": 81
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 1.7219560939545246e-05,
+      "loss": 2.3328,
+      "step": 82
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 1.7145716840645253e-05,
+      "loss": 1.464,
+      "step": 83
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 1.7071067811865477e-05,
+      "loss": 2.488,
+      "step": 84
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 1.6995622262052093e-05,
+      "loss": 1.6033,
+      "step": 85
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 1.6919388689775463e-05,
+      "loss": 1.1031,
+      "step": 86
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 1.6842375682372803e-05,
+      "loss": 2.3181,
+      "step": 87
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 1.676459191498087e-05,
+      "loss": 1.7348,
+      "step": 88
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 1.6686046149558736e-05,
+      "loss": 5.4877,
+      "step": 89
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 1.6606747233900816e-05,
+      "loss": 1.6482,
+      "step": 90
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 1.652670410064019e-05,
+      "loss": 1.2802,
+      "step": 91
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 1.6445925766242392e-05,
+      "loss": 1.3189,
+      "step": 92
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 1.6364421329989758e-05,
+      "loss": 1.2981,
+      "step": 93
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 1.6282199972956425e-05,
+      "loss": 1.9697,
+      "step": 94
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 1.6199270956974128e-05,
+      "loss": 3.1929,
+      "step": 95
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 1.6115643623588915e-05,
+      "loss": 1.2689,
+      "step": 96
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 1.6031327393008848e-05,
+      "loss": 1.7019,
+      "step": 97
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 1.594633176304287e-05,
+      "loss": 1.4936,
+      "step": 98
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 1.5860666308030933e-05,
+      "loss": 1.2408,
+      "step": 99
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 1.5774340677765483e-05,
+      "loss": 2.8245,
+      "step": 100
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 1.568736459640447e-05,
+      "loss": 2.1455,
+      "step": 101
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 1.5599747861375957e-05,
+      "loss": 3.8581,
+      "step": 102
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 1.551150034227449e-05,
+      "loss": 2.0313,
+      "step": 103
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 1.5422631979749354e-05,
+      "loss": 4.0104,
+      "step": 104
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 1.5333152784384777e-05,
+      "loss": 1.5344,
+      "step": 105
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 1.5243072835572319e-05,
+      "loss": 3.7659,
+      "step": 106
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 1.5152402280375454e-05,
+      "loss": 1.7015,
+      "step": 107
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 1.5061151332386565e-05,
+      "loss": 5.6751,
+      "step": 108
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 1.4969330270576428e-05,
+      "loss": 1.3422,
+      "step": 109
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 1.4876949438136348e-05,
+      "loss": 1.605,
+      "step": 110
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 1.4784019241313025e-05,
+      "loss": 1.8969,
+      "step": 111
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 1.4690550148236371e-05,
+      "loss": 2.4543,
+      "step": 112
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 1.4596552687740304e-05,
+      "loss": 1.4271,
+      "step": 113
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 1.4502037448176734e-05,
+      "loss": 1.4843,
+      "step": 114
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 1.4407015076222845e-05,
+      "loss": 1.1347,
+      "step": 115
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 1.4311496275681785e-05,
+      "loss": 7.9969,
+      "step": 116
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 1.4215491806276944e-05,
+      "loss": 1.9128,
+      "step": 117
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 1.4119012482439929e-05,
+      "loss": 2.4068,
+      "step": 118
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 1.4022069172092354e-05,
+      "loss": 1.5273,
+      "step": 119
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 1.3924672795421638e-05,
+      "loss": 1.9067,
+      "step": 120
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 1.3826834323650899e-05,
+      "loss": 1.7889,
+      "step": 121
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 1.3728564777803089e-05,
+      "loss": 1.3609,
+      "step": 122
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 1.3629875227459532e-05,
+      "loss": 0.9619,
+      "step": 123
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1.3530776789513009e-05,
+      "loss": 2.2419,
+      "step": 124
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.3431280626915466e-05,
+      "loss": 1.763,
+      "step": 125
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.3331397947420578e-05,
+      "loss": 2.3687,
+      "step": 126
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1.3231140002321252e-05,
+      "loss": 2.0559,
+      "step": 127
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.3130518085182224e-05,
+      "loss": 3.9069,
+      "step": 128
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.3029543530567884e-05,
+      "loss": 1.6402,
+      "step": 129
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.2928227712765504e-05,
+      "loss": 1.2617,
+      "step": 130
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 1.282658204450398e-05,
+      "loss": 4.8992,
+      "step": 131
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 1.2724617975668229e-05,
+      "loss": 2.4955,
+      "step": 132
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 1.2622346992009447e-05,
+      "loss": 1.0075,
+      "step": 133
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 1.2519780613851254e-05,
+      "loss": 1.2768,
+      "step": 134
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 1.2416930394792026e-05,
+      "loss": 1.9387,
+      "step": 135
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 1.2313807920403419e-05,
+      "loss": 1.8528,
+      "step": 136
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 1.22104248069253e-05,
+      "loss": 2.1736,
+      "step": 137
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 1.2106792699957264e-05,
+      "loss": 1.4472,
+      "step": 138
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 1.2002923273146793e-05,
+      "loss": 1.8027,
+      "step": 139
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 1.1898828226874284e-05,
+      "loss": 2.9745,
+      "step": 140
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 1.1794519286935056e-05,
+      "loss": 1.8866,
+      "step": 141
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 1.1690008203218493e-05,
+      "loss": 2.8159,
+      "step": 142
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 1.158530674838449e-05,
+      "loss": 1.6229,
+      "step": 143
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1.1480426716537316e-05,
+      "loss": 0.9179,
+      "step": 144
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.1375379921897052e-05,
+      "loss": 2.4946,
+      "step": 145
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.1270178197468788e-05,
+      "loss": 1.6329,
+      "step": 146
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 1.1164833393709707e-05,
+      "loss": 4.3928,
+      "step": 147
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 1.1059357377194161e-05,
+      "loss": 9.7322,
+      "step": 148
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 1.0953762029276982e-05,
+      "loss": 2.9052,
+      "step": 149
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 1.0848059244755093e-05,
+      "loss": 0.8878,
+      "step": 150
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 1.0742260930527625e-05,
+      "loss": 3.773,
+      "step": 151
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 1.0636379004254665e-05,
+      "loss": 1.8408,
+      "step": 152
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 1.0530425393014773e-05,
+      "loss": 1.9127,
+      "step": 153
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 1.0424412031961485e-05,
+      "loss": 1.2162,
+      "step": 154
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 1.0318350862978848e-05,
+      "loss": 0.7655,
+      "step": 155
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 1.0212253833336237e-05,
+      "loss": 3.1586,
+      "step": 156
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 1.0106132894342564e-05,
+      "loss": 0.9841,
+      "step": 157
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 1e-05,
+      "loss": 2.6778,
+      "step": 158
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 9.89386710565744e-06,
+      "loss": 0.9375,
+      "step": 159
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 9.787746166663765e-06,
+      "loss": 0.7373,
+      "step": 160
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 9.681649137021158e-06,
+      "loss": 1.4366,
+      "step": 161
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 9.57558796803852e-06,
+      "loss": 0.9225,
+      "step": 162
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 9.46957460698523e-06,
+      "loss": 1.985,
+      "step": 163
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 9.363620995745337e-06,
+      "loss": 1.0628,
+      "step": 164
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 9.257739069472375e-06,
+      "loss": 1.4579,
+      "step": 165
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 9.151940755244912e-06,
+      "loss": 2.1649,
+      "step": 166
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 9.046237970723022e-06,
+      "loss": 0.9303,
+      "step": 167
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 8.94064262280584e-06,
+      "loss": 1.4317,
+      "step": 168
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 8.835166606290295e-06,
+      "loss": 1.5579,
+      "step": 169
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 8.729821802531213e-06,
+      "loss": 0.9049,
+      "step": 170
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 8.624620078102952e-06,
+      "loss": 0.9932,
+      "step": 171
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 8.519573283462688e-06,
+      "loss": 2.6368,
+      "step": 172
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 8.414693251615513e-06,
+      "loss": 2.2779,
+      "step": 173
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 8.309991796781512e-06,
+      "loss": 1.0254,
+      "step": 174
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 8.205480713064947e-06,
+      "loss": 0.7599,
+      "step": 175
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 8.101171773125716e-06,
+      "loss": 1.9378,
+      "step": 176
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 7.99707672685321e-06,
+      "loss": 1.4885,
+      "step": 177
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 7.89320730004274e-06,
+      "loss": 1.6313,
+      "step": 178
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 7.789575193074703e-06,
+      "loss": 3.2386,
+      "step": 179
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 7.686192079596586e-06,
+      "loss": 2.6884,
+      "step": 180
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 7.5830696052079754e-06,
+      "loss": 1.3555,
+      "step": 181
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 7.480219386148751e-06,
+      "loss": 4.0523,
+      "step": 182
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 7.377653007990559e-06,
+      "loss": 1.1748,
+      "step": 183
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 7.275382024331773e-06,
+      "loss": 0.8378,
+      "step": 184
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 7.173417955496025e-06,
+      "loss": 1.3159,
+      "step": 185
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 7.071772287234497e-06,
+      "loss": 2.3162,
+      "step": 186
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 6.970456469432116e-06,
+      "loss": 3.0254,
+      "step": 187
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 6.869481914817779e-06,
+      "loss": 2.1912,
+      "step": 188
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 6.768859997678751e-06,
+      "loss": 1.9934,
+      "step": 189
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 6.668602052579425e-06,
+      "loss": 1.0271,
+      "step": 190
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 6.5687193730845375e-06,
+      "loss": 2.1567,
+      "step": 191
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 6.469223210486992e-06,
+      "loss": 1.1575,
+      "step": 192
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 6.370124772540469e-06,
+      "loss": 1.5536,
+      "step": 193
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 6.2714352221969155e-06,
+      "loss": 1.1635,
+      "step": 194
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 6.173165676349103e-06,
+      "loss": 0.7875,
+      "step": 195
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 6.075327204578363e-06,
+      "loss": 2.6851,
+      "step": 196
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 5.97793082790765e-06,
+      "loss": 1.2779,
+      "step": 197
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 5.880987517560075e-06,
+      "loss": 0.9668,
+      "step": 198
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 5.784508193723058e-06,
+      "loss": 1.077,
+      "step": 199
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 5.688503724318217e-06,
+      "loss": 1.6403,
+      "step": 200
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 5.592984923777156e-06,
+      "loss": 1.4186,
+      "step": 201
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 5.497962551823266e-06,
+      "loss": 1.2574,
+      "step": 202
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 5.403447312259702e-06,
+      "loss": 0.7107,
+      "step": 203
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 5.3094498517636324e-06,
+      "loss": 2.5621,
+      "step": 204
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 5.215980758686978e-06,
+      "loss": 1.3489,
+      "step": 205
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 5.1230505618636575e-06,
+      "loss": 2.8486,
+      "step": 206
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 5.030669729423572e-06,
+      "loss": 1.6635,
+      "step": 207
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 4.938848667613436e-06,
+      "loss": 3.5343,
+      "step": 208
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 4.84759771962455e-06,
+      "loss": 0.7653,
+      "step": 209
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 4.756927164427685e-06,
+      "loss": 1.0844,
+      "step": 210
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 4.666847215615225e-06,
+      "loss": 0.7464,
+      "step": 211
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 4.57736802025065e-06,
+      "loss": 1.7849,
+      "step": 212
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 4.488499657725511e-06,
+      "loss": 1.2126,
+      "step": 213
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 4.400252138624047e-06,
+      "loss": 0.9399,
+      "step": 214
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 4.312635403595532e-06,
+      "loss": 2.6067,
+      "step": 215
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 4.2256593222345185e-06,
+      "loss": 0.7802,
+      "step": 216
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 4.139333691969071e-06,
+      "loss": 1.0666,
+      "step": 217
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 4.053668236957135e-06,
+      "loss": 5.4643,
+      "step": 218
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 3.96867260699116e-06,
+      "loss": 1.1877,
+      "step": 219
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 3.884356376411089e-06,
+      "loss": 0.8967,
+      "step": 220
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 3.8007290430258712e-06,
+      "loss": 2.0022,
+      "step": 221
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 3.7178000270435765e-06,
+      "loss": 1.4914,
+      "step": 222
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 3.6355786700102426e-06,
+      "loss": 1.3213,
+      "step": 223
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 3.5540742337576083e-06,
+      "loss": 1.6499,
+      "step": 224
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 3.4732958993598153e-06,
+      "loss": 0.7294,
+      "step": 225
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 3.3932527660991877e-06,
+      "loss": 1.177,
+      "step": 226
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 3.313953850441266e-06,
+      "loss": 1.9219,
+      "step": 227
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 3.2354080850191328e-06,
+      "loss": 2.6084,
+      "step": 228
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 3.157624317627195e-06,
+      "loss": 0.8047,
+      "step": 229
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 3.0806113102245395e-06,
+      "loss": 1.1592,
+      "step": 230
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 3.00437773794791e-06,
+      "loss": 1.4984,
+      "step": 231
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 2.9289321881345257e-06,
+      "loss": 1.9055,
+      "step": 232
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 2.8542831593547483e-06,
+      "loss": 1.2435,
+      "step": 233
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 2.780439060454756e-06,
+      "loss": 1.2274,
+      "step": 234
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 2.707408209609339e-06,
+      "loss": 0.999,
+      "step": 235
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 2.6351988333848787e-06,
+      "loss": 2.4634,
+      "step": 236
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 2.5638190658126937e-06,
+      "loss": 0.9664,
+      "step": 237
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 2.493276947472756e-06,
+      "loss": 0.9813,
+      "step": 238
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 2.4235804245879723e-06,
+      "loss": 1.4496,
+      "step": 239
+    },
+    {
+      "epoch": 1.57,
+      "learning_rate": 2.354737348129077e-06,
+      "loss": 1.4231,
+      "step": 240
+    },
+    {
+      "epoch": 1.57,
+      "learning_rate": 2.2867554729302545e-06,
+      "loss": 0.91,
+      "step": 241
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 2.2196424568156073e-06,
+      "loss": 1.1398,
+      "step": 242
+    },
+    {
+      "epoch": 1.59,
+      "learning_rate": 2.1534058597365284e-06,
+      "loss": 2.7849,
+      "step": 243
+    },
+    {
+      "epoch": 1.59,
+      "learning_rate": 2.0880531429201146e-06,
+      "loss": 3.0315,
+      "step": 244
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 2.0235916680287015e-06,
+      "loss": 1.903,
+      "step": 245
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 1.960028696330596e-06,
+      "loss": 1.9675,
+      "step": 246
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 1.8973713878821343e-06,
+      "loss": 2.5096,
+      "step": 247
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 1.8356268007211442e-06,
+      "loss": 0.8981,
+      "step": 248
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 1.7748018900718856e-06,
+      "loss": 6.6939,
+      "step": 249
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 1.7149035075615795e-06,
+      "loss": 1.6869,
+      "step": 250
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 1.6559384004486057e-06,
+      "loss": 0.896,
+      "step": 251
+    },
+    {
+      "epoch": 1.65,
+      "learning_rate": 1.5979132108624572e-06,
+      "loss": 1.094,
+      "step": 252
+    },
+    {
+      "epoch": 1.65,
+      "learning_rate": 1.5408344750555382e-06,
+      "loss": 1.3939,
+      "step": 253
+    },
+    {
+      "epoch": 1.66,
+      "learning_rate": 1.4847086226668871e-06,
+      "loss": 0.7714,
+      "step": 254
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 1.4295419759979079e-06,
+      "loss": 1.4316,
+      "step": 255
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 1.3753407493001968e-06,
+      "loss": 0.7033,
+      "step": 256
+    },
+    {
+      "epoch": 1.68,
+      "learning_rate": 1.3221110480755306e-06,
+      "loss": 7.7958,
+      "step": 257
+    },
+    {
+      "epoch": 1.68,
+      "learning_rate": 1.2698588683881185e-06,
+      "loss": 1.0468,
+      "step": 258
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 1.2185900961891794e-06,
+      "loss": 0.9946,
+      "step": 259
+    },
+    {
+      "epoch": 1.7,
+      "learning_rate": 1.1683105066539068e-06,
+      "loss": 0.9566,
+      "step": 260
+    },
+    {
+      "epoch": 1.7,
+      "learning_rate": 1.1190257635309276e-06,
+      "loss": 1.1013,
+      "step": 261
+    },
+    {
+      "epoch": 1.71,
+      "learning_rate": 1.0707414185043163e-06,
+      "loss": 0.8047,
+      "step": 262
+    },
+    {
+      "epoch": 1.72,
+      "learning_rate": 1.0234629105682104e-06,
+      "loss": 1.5056,
+      "step": 263
+    },
+    {
+      "epoch": 1.72,
+      "learning_rate": 9.771955654141496e-07,
+      "loss": 1.1375,
+      "step": 264
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 9.319445948311534e-07,
+      "loss": 2.3292,
+      "step": 265
+    },
+    {
+      "epoch": 1.74,
+      "learning_rate": 8.87715096118642e-07,
+      "loss": 0.7513,
+      "step": 266
+    },
+    {
+      "epoch": 1.74,
+      "learning_rate": 8.445120515122552e-07,
+      "loss": 1.7243,
+      "step": 267
+    },
+    {
+      "epoch": 1.75,
+      "learning_rate": 8.023403276226127e-07,
+      "loss": 1.0411,
+      "step": 268
+    },
+    {
+      "epoch": 1.76,
+      "learning_rate": 7.612046748871327e-07,
+      "loss": 1.1047,
+      "step": 269
+    },
+    {
+      "epoch": 1.76,
+      "learning_rate": 7.211097270349065e-07,
+      "loss": 2.3286,
+      "step": 270
+    },
+    {
+      "epoch": 1.77,
+      "learning_rate": 6.820600005647382e-07,
+      "loss": 1.9476,
+      "step": 271
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 6.440598942363796e-07,
+      "loss": 1.0594,
+      "step": 272
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 6.071136885750272e-07,
+      "loss": 1.2023,
+      "step": 273
+    },
+    {
+      "epoch": 1.79,
+      "learning_rate": 5.71225545389158e-07,
+      "loss": 0.6901,
+      "step": 274
+    },
+    {
+      "epoch": 1.8,
+      "learning_rate": 5.363995073017047e-07,
+      "loss": 1.1539,
+      "step": 275
+    },
+    {
+      "epoch": 1.8,
+      "learning_rate": 5.026394972946813e-07,
+      "loss": 1.5611,
+      "step": 276
+    },
+    {
+      "epoch": 1.81,
+      "learning_rate": 4.6994931826728094e-07,
+      "loss": 1.6712,
+      "step": 277
+    },
+    {
+      "epoch": 1.82,
+      "learning_rate": 4.3833265260749157e-07,
+      "loss": 0.9014,
+      "step": 278
+    },
+    {
+      "epoch": 1.82,
+      "learning_rate": 4.077930617773007e-07,
+      "loss": 0.8915,
+      "step": 279
+    },
+    {
+      "epoch": 1.83,
+      "learning_rate": 3.783339859115065e-07,
+      "loss": 1.2137,
+      "step": 280
+    },
+    {
+      "epoch": 1.84,
+      "learning_rate": 3.49958743430211e-07,
+      "loss": 1.391,
+      "step": 281
+    },
+    {
+      "epoch": 1.84,
+      "learning_rate": 3.226705306650113e-07,
+      "loss": 2.1169,
+      "step": 282
+    },
+    {
+      "epoch": 1.85,
+      "learning_rate": 2.9647242149895005e-07,
+      "loss": 1.0684,
+      "step": 283
+    },
+    {
+      "epoch": 1.85,
+      "learning_rate": 2.7136736702025436e-07,
+      "loss": 1.5766,
+      "step": 284
+    },
+    {
+      "epoch": 1.86,
+      "learning_rate": 2.473581951899184e-07,
+      "loss": 2.034,
+      "step": 285
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 2.2444761052313857e-07,
+      "loss": 1.371,
+      "step": 286
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 2.0263819378466888e-07,
+      "loss": 1.4777,
+      "step": 287
+    },
+    {
+      "epoch": 1.88,
+      "learning_rate": 1.8193240169810943e-07,
+      "loss": 1.6253,
+      "step": 288
+    },
+    {
+      "epoch": 1.89,
+      "learning_rate": 1.623325666691644e-07,
+      "loss": 0.8806,
+      "step": 289
+    },
+    {
+      "epoch": 1.89,
+      "learning_rate": 1.4384089652291544e-07,
+      "loss": 1.2476,
+      "step": 290
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 1.2645947425511397e-07,
+      "loss": 0.93,
+      "step": 291
+    },
+    {
+      "epoch": 1.91,
+      "learning_rate": 1.1019025779754666e-07,
+      "loss": 1.4188,
+      "step": 292
+    },
+    {
+      "epoch": 1.91,
+      "learning_rate": 9.503507979748305e-08,
+      "loss": 0.8485,
+      "step": 293
+    },
+    {
+      "epoch": 1.92,
+      "learning_rate": 8.099564741123167e-08,
+      "loss": 1.1463,
+      "step": 294
+    },
+    {
+      "epoch": 1.93,
+      "learning_rate": 6.807354211184613e-08,
+      "loss": 1.0603,
+      "step": 295
+    },
+    {
+      "epoch": 1.93,
+      "learning_rate": 5.6270219510975445e-08,
+      "loss": 0.8442,
+      "step": 296
+    },
+    {
+      "epoch": 1.94,
+      "learning_rate": 4.5587009194894005e-08,
+      "loss": 1.0673,
+      "step": 297
+    },
+    {
+      "epoch": 1.95,
+      "learning_rate": 3.602511457473479e-08,
+      "loss": 1.3685,
+      "step": 298
+    },
+    {
+      "epoch": 1.95,
+      "learning_rate": 2.758561275092886e-08,
+      "loss": 1.0962,
+      "step": 299
+    },
+    {
+      "epoch": 1.96,
+      "learning_rate": 2.0269454391874665e-08,
+      "loss": 1.5407,
+      "step": 300
+    },
+    {
+      "epoch": 1.97,
+      "learning_rate": 1.4077463626852584e-08,
+      "loss": 1.6339,
+      "step": 301
+    },
+    {
+      "epoch": 1.97,
+      "learning_rate": 9.010337953185843e-09,
+      "loss": 0.7501,
+      "step": 302
+    },
+    {
+      "epoch": 1.98,
+      "learning_rate": 5.068648157675604e-09,
+      "loss": 1.2092,
+      "step": 303
+    },
+    {
+      "epoch": 1.99,
+      "learning_rate": 2.2528382523057115e-09,
+      "loss": 1.0453,
+      "step": 304
+    },
+    {
+      "epoch": 1.99,
+      "learning_rate": 5.632254242204926e-10,
+      "loss": 1.5781,
+      "step": 305
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 0.0,
+      "loss": 1.4923,
+      "step": 306
+    },
+    {
+      "epoch": 2.0,
+      "step": 306,
+      "total_flos": 8.107937674674831e+17,
+      "train_loss": 1.9459447897727193,
+      "train_runtime": 26109.0048,
+      "train_samples_per_second": 0.751,
+      "train_steps_per_second": 0.012
+    }
+  ],
+  "max_steps": 306,
+  "num_train_epochs": 2,
+  "total_flos": 8.107937674674831e+17,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f3c6514e8e4d88981f13e9a5f9df2b0e112331c99a2588569d8a0920c171db9
+size 3771