Delete checkpoint-304

checkpoint-304/config.json

@@ -1,25 +0,0 @@
-{
-  "_name_or_path": "teknium/OpenHermes-2.5-Mistral-7B",
-  "architectures": [
-    "MistralForCausalLM"
-  ],
-  "bos_token_id": 1,
-  "eos_token_id": 2,
-  "hidden_act": "silu",
-  "hidden_size": 4096,
-  "initializer_range": 0.02,
-  "intermediate_size": 14336,
-  "max_position_embeddings": 32768,
-  "model_type": "mistral",
-  "num_attention_heads": 32,
-  "num_hidden_layers": 32,
-  "num_key_value_heads": 8,
-  "rms_norm_eps": 1e-05,
-  "rope_theta": 10000.0,
-  "sliding_window": 4096,
-  "tie_word_embeddings": false,
-  "torch_dtype": "float32",
-  "transformers_version": "4.34.1",
-  "use_cache": false,
-  "vocab_size": 32002
-}

checkpoint-304/generation_config.json

@@ -1,6 +0,0 @@
-{
-  "_from_model_config": true,
-  "bos_token_id": 1,
-  "eos_token_id": 32000,
-  "transformers_version": "4.34.1"
-}

checkpoint-304/optimizer.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:07e6187564e0cb423c502ad7c4c471b40e3a3948b33291e75fe96e5eee8fa136
-size 14512135879

checkpoint-304/pytorch_model-00001-of-00002.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:0460f2ef47ab8ffe104b355e94d643362c5a2d30e7c88ff25309ea8d3dbf6c5a
-size 9886765428

checkpoint-304/pytorch_model-00002-of-00002.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:769dc4ff85335c5680fca0fc804c81420600c1b9d287a32bb36611c418168385
-size 5121688491

checkpoint-304/pytorch_model.bin.index.json

@@ -1,298 +0,0 @@
-{
-  "metadata": {
-    "total_size": 15008350208
-  },
-  "weight_map": {
-    "lm_head.weight": "pytorch_model-00002-of-00002.bin",
-    "model.embed_tokens.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.10.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.10.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.11.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.11.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.11.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.12.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.12.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.12.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.13.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.13.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.13.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.14.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.14.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.14.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.15.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.15.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.15.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.16.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.16.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.16.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.17.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.17.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.17.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.18.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.18.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.18.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.19.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.19.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.19.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.20.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.20.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.20.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.21.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.21.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.21.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.22.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.22.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.22.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.23.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.23.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.23.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.24.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.24.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.24.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.25.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.25.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.25.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.26.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.26.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.26.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.27.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.27.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.27.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.28.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.28.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.28.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.29.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.29.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.29.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.30.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.30.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.30.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.31.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.31.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.31.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.8.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.9.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.9.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.norm.weight": "pytorch_model-00002-of-00002.bin"
-  }
-}

checkpoint-304/rng_state_0.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:2b79fdab1d04d2fef64e6cc48d12f3c84ce5b8c1a21bebdb7dbe2a42d800421e
-size 15607

checkpoint-304/rng_state_1.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:31694b994f0607cfe91452414877c57b870598c9a4bd9bae0760f822c13a1461
-size 15607

checkpoint-304/scheduler.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:7547983ff9227d6a5b68c9efde9fe1bc3541fcc13d36c1688a739942d845584c
-size 627

checkpoint-304/trainer_state.json

@@ -1,1923 +0,0 @@
-{
-  "best_metric": null,
-  "best_model_checkpoint": null,
-  "epoch": 0.9983579638752053,
-  "eval_steps": 31,
-  "global_step": 304,
-  "is_hyper_param_search": false,
-  "is_local_process_zero": true,
-  "is_world_process_zero": true,
-  "log_history": [
-    {
-      "epoch": 0.0,
-      "learning_rate": 5.000000000000001e-07,
-      "loss": 1.1498,
-      "step": 1
-    },
-    {
-      "epoch": 0.0,
-      "eval_loss": 1.1952733993530273,
-      "eval_runtime": 15.2597,
-      "eval_samples_per_second": 6.226,
-      "eval_steps_per_second": 1.573,
-      "step": 1
-    },
-    {
-      "epoch": 0.01,
-      "learning_rate": 1.0000000000000002e-06,
-      "loss": 1.176,
-      "step": 2
-    },
-    {
-      "epoch": 0.01,
-      "learning_rate": 1.5e-06,
-      "loss": 1.1287,
-      "step": 3
-    },
-    {
-      "epoch": 0.01,
-      "learning_rate": 2.0000000000000003e-06,
-      "loss": 1.0172,
-      "step": 4
-    },
-    {
-      "epoch": 0.02,
-      "learning_rate": 2.5e-06,
-      "loss": 0.8997,
-      "step": 5
-    },
-    {
-      "epoch": 0.02,
-      "learning_rate": 3e-06,
-      "loss": 0.8616,
-      "step": 6
-    },
-    {
-      "epoch": 0.02,
-      "learning_rate": 3.5e-06,
-      "loss": 0.7128,
-      "step": 7
-    },
-    {
-      "epoch": 0.03,
-      "learning_rate": 4.000000000000001e-06,
-      "loss": 0.6826,
-      "step": 8
-    },
-    {
-      "epoch": 0.03,
-      "learning_rate": 4.5e-06,
-      "loss": 0.5946,
-      "step": 9
-    },
-    {
-      "epoch": 0.03,
-      "learning_rate": 5e-06,
-      "loss": 0.5616,
-      "step": 10
-    },
-    {
-      "epoch": 0.04,
-      "learning_rate": 4.999965501009142e-06,
-      "loss": 0.4778,
-      "step": 11
-    },
-    {
-      "epoch": 0.04,
-      "learning_rate": 4.999862004988709e-06,
-      "loss": 0.5264,
-      "step": 12
-    },
-    {
-      "epoch": 0.04,
-      "learning_rate": 4.999689514795112e-06,
-      "loss": 0.4518,
-      "step": 13
-    },
-    {
-      "epoch": 0.05,
-      "learning_rate": 4.9994480351889364e-06,
-      "loss": 0.46,
-      "step": 14
-    },
-    {
-      "epoch": 0.05,
-      "learning_rate": 4.999137572834828e-06,
-      "loss": 0.4111,
-      "step": 15
-    },
-    {
-      "epoch": 0.05,
-      "learning_rate": 4.998758136301295e-06,
-      "loss": 0.3646,
-      "step": 16
-    },
-    {
-      "epoch": 0.06,
-      "learning_rate": 4.99830973606048e-06,
-      "loss": 0.4024,
-      "step": 17
-    },
-    {
-      "epoch": 0.06,
-      "learning_rate": 4.997792384487867e-06,
-      "loss": 0.4042,
-      "step": 18
-    },
-    {
-      "epoch": 0.06,
-      "learning_rate": 4.997206095861944e-06,
-      "loss": 0.3659,
-      "step": 19
-    },
-    {
-      "epoch": 0.07,
-      "learning_rate": 4.996550886363801e-06,
-      "loss": 0.3527,
-      "step": 20
-    },
-    {
-      "epoch": 0.07,
-      "learning_rate": 4.995826774076693e-06,
-      "loss": 0.3726,
-      "step": 21
-    },
-    {
-      "epoch": 0.07,
-      "learning_rate": 4.995033778985534e-06,
-      "loss": 0.3551,
-      "step": 22
-    },
-    {
-      "epoch": 0.08,
-      "learning_rate": 4.994171922976349e-06,
-      "loss": 0.382,
-      "step": 23
-    },
-    {
-      "epoch": 0.08,
-      "learning_rate": 4.993241229835666e-06,
-      "loss": 0.3694,
-      "step": 24
-    },
-    {
-      "epoch": 0.08,
-      "learning_rate": 4.992241725249866e-06,
-      "loss": 0.3603,
-      "step": 25
-    },
-    {
-      "epoch": 0.09,
-      "learning_rate": 4.991173436804468e-06,
-      "loss": 0.3383,
-      "step": 26
-    },
-    {
-      "epoch": 0.09,
-      "learning_rate": 4.990036393983372e-06,
-      "loss": 0.3455,
-      "step": 27
-    },
-    {
-      "epoch": 0.09,
-      "learning_rate": 4.9888306281680405e-06,
-      "loss": 0.3428,
-      "step": 28
-    },
-    {
-      "epoch": 0.1,
-      "learning_rate": 4.987556172636637e-06,
-      "loss": 0.3001,
-      "step": 29
-    },
-    {
-      "epoch": 0.1,
-      "learning_rate": 4.986213062563104e-06,
-      "loss": 0.307,
-      "step": 30
-    },
-    {
-      "epoch": 0.1,
-      "learning_rate": 4.984801335016198e-06,
-      "loss": 0.321,
-      "step": 31
-    },
-    {
-      "epoch": 0.1,
-      "eval_loss": 0.3176000714302063,
-      "eval_runtime": 15.512,
-      "eval_samples_per_second": 6.124,
-      "eval_steps_per_second": 1.547,
-      "step": 31
-    },
-    {
-      "epoch": 0.11,
-      "learning_rate": 4.9833210289584574e-06,
-      "loss": 0.2925,
-      "step": 32
-    },
-    {
-      "epoch": 0.11,
-      "learning_rate": 4.981772185245135e-06,
-      "loss": 0.311,
-      "step": 33
-    },
-    {
-      "epoch": 0.11,
-      "learning_rate": 4.980154846623067e-06,
-      "loss": 0.3066,
-      "step": 34
-    },
-    {
-      "epoch": 0.11,
-      "learning_rate": 4.978469057729493e-06,
-      "loss": 0.2879,
-      "step": 35
-    },
-    {
-      "epoch": 0.12,
-      "learning_rate": 4.976714865090827e-06,
-      "loss": 0.3001,
-      "step": 36
-    },
-    {
-      "epoch": 0.12,
-      "learning_rate": 4.974892317121368e-06,
-      "loss": 0.3111,
-      "step": 37
-    },
-    {
-      "epoch": 0.12,
-      "learning_rate": 4.97300146412197e-06,
-      "loss": 0.3067,
-      "step": 38
-    },
-    {
-      "epoch": 0.13,
-      "learning_rate": 4.9710423582786485e-06,
-      "loss": 0.3091,
-      "step": 39
-    },
-    {
-      "epoch": 0.13,
-      "learning_rate": 4.969015053661142e-06,
-      "loss": 0.302,
-      "step": 40
-    },
-    {
-      "epoch": 0.13,
-      "learning_rate": 4.966919606221423e-06,
-      "loss": 0.2991,
-      "step": 41
-    },
-    {
-      "epoch": 0.14,
-      "learning_rate": 4.964756073792148e-06,
-      "loss": 0.3034,
-      "step": 42
-    },
-    {
-      "epoch": 0.14,
-      "learning_rate": 4.9625245160850674e-06,
-      "loss": 0.2877,
-      "step": 43
-    },
-    {
-      "epoch": 0.14,
-      "learning_rate": 4.960224994689371e-06,
-      "loss": 0.283,
-      "step": 44
-    },
-    {
-      "epoch": 0.15,
-      "learning_rate": 4.957857573069992e-06,
-      "loss": 0.2993,
-      "step": 45
-    },
-    {
-      "epoch": 0.15,
-      "learning_rate": 4.955422316565856e-06,
-      "loss": 0.2738,
-      "step": 46
-    },
-    {
-      "epoch": 0.15,
-      "learning_rate": 4.952919292388079e-06,
-      "loss": 0.293,
-      "step": 47
-    },
-    {
-      "epoch": 0.16,
-      "learning_rate": 4.950348569618105e-06,
-      "loss": 0.3053,
-      "step": 48
-    },
-    {
-      "epoch": 0.16,
-      "learning_rate": 4.947710219205808e-06,
-      "loss": 0.2875,
-      "step": 49
-    },
-    {
-      "epoch": 0.16,
-      "learning_rate": 4.9450043139675284e-06,
-      "loss": 0.2798,
-      "step": 50
-    },
-    {
-      "epoch": 0.17,
-      "learning_rate": 4.9422309285840684e-06,
-      "loss": 0.3172,
-      "step": 51
-    },
-    {
-      "epoch": 0.17,
-      "learning_rate": 4.939390139598623e-06,
-      "loss": 0.2713,
-      "step": 52
-    },
-    {
-      "epoch": 0.17,
-      "learning_rate": 4.936482025414677e-06,
-      "loss": 0.2372,
-      "step": 53
-    },
-    {
-      "epoch": 0.18,
-      "learning_rate": 4.933506666293834e-06,
-      "loss": 0.3125,
-      "step": 54
-    },
-    {
-      "epoch": 0.18,
-      "learning_rate": 4.9304641443536015e-06,
-      "loss": 0.2687,
-      "step": 55
-    },
-    {
-      "epoch": 0.18,
-      "learning_rate": 4.927354543565131e-06,
-      "loss": 0.2701,
-      "step": 56
-    },
-    {
-      "epoch": 0.19,
-      "learning_rate": 4.924177949750893e-06,
-      "loss": 0.2681,
-      "step": 57
-    },
-    {
-      "epoch": 0.19,
-      "learning_rate": 4.920934450582311e-06,
-      "loss": 0.2751,
-      "step": 58
-    },
-    {
-      "epoch": 0.19,
-      "learning_rate": 4.917624135577346e-06,
-      "loss": 0.2902,
-      "step": 59
-    },
-    {
-      "epoch": 0.2,
-      "learning_rate": 4.914247096098019e-06,
-      "loss": 0.2618,
-      "step": 60
-    },
-    {
-      "epoch": 0.2,
-      "learning_rate": 4.910803425347892e-06,
-      "loss": 0.2569,
-      "step": 61
-    },
-    {
-      "epoch": 0.2,
-      "learning_rate": 4.907293218369499e-06,
-      "loss": 0.2693,
-      "step": 62
-    },
-    {
-      "epoch": 0.2,
-      "eval_loss": 0.27119407057762146,
-      "eval_runtime": 15.5684,
-      "eval_samples_per_second": 6.102,
-      "eval_steps_per_second": 1.542,
-      "step": 62
-    },
-    {
-      "epoch": 0.21,
-      "learning_rate": 4.903716572041718e-06,
-      "loss": 0.2475,
-      "step": 63
-    },
-    {
-      "epoch": 0.21,
-      "learning_rate": 4.9000735850771e-06,
-      "loss": 0.2492,
-      "step": 64
-    },
-    {
-      "epoch": 0.21,
-      "learning_rate": 4.8963643580191446e-06,
-      "loss": 0.273,
-      "step": 65
-    },
-    {
-      "epoch": 0.22,
-      "learning_rate": 4.8925889932395246e-06,
-      "loss": 0.2193,
-      "step": 66
-    },
-    {
-      "epoch": 0.22,
-      "learning_rate": 4.888747594935259e-06,
-      "loss": 0.2637,
-      "step": 67
-    },
-    {
-      "epoch": 0.22,
-      "learning_rate": 4.88484026912584e-06,
-      "loss": 0.3141,
-      "step": 68
-    },
-    {
-      "epoch": 0.23,
-      "learning_rate": 4.880867123650306e-06,
-      "loss": 0.254,
-      "step": 69
-    },
-    {
-      "epoch": 0.23,
-      "learning_rate": 4.876828268164264e-06,
-      "loss": 0.2778,
-      "step": 70
-    },
-    {
-      "epoch": 0.23,
-      "learning_rate": 4.872723814136866e-06,
-      "loss": 0.2809,
-      "step": 71
-    },
-    {
-      "epoch": 0.24,
-      "learning_rate": 4.868553874847728e-06,
-      "loss": 0.266,
-      "step": 72
-    },
-    {
-      "epoch": 0.24,
-      "learning_rate": 4.864318565383809e-06,
-      "loss": 0.2174,
-      "step": 73
-    },
-    {
-      "epoch": 0.24,
-      "learning_rate": 4.86001800263623e-06,
-      "loss": 0.2732,
-      "step": 74
-    },
-    {
-      "epoch": 0.25,
-      "learning_rate": 4.855652305297052e-06,
-      "loss": 0.2507,
-      "step": 75
-    },
-    {
-      "epoch": 0.25,
-      "learning_rate": 4.8512215938559955e-06,
-      "loss": 0.2514,
-      "step": 76
-    },
-    {
-      "epoch": 0.25,
-      "learning_rate": 4.846725990597122e-06,
-      "loss": 0.268,
-      "step": 77
-    },
-    {
-      "epoch": 0.26,
-      "learning_rate": 4.84216561959545e-06,
-      "loss": 0.228,
-      "step": 78
-    },
-    {
-      "epoch": 0.26,
-      "learning_rate": 4.837540606713538e-06,
-      "loss": 0.2606,
-      "step": 79
-    },
-    {
-      "epoch": 0.26,
-      "learning_rate": 4.832851079598007e-06,
-      "loss": 0.2554,
-      "step": 80
-    },
-    {
-      "epoch": 0.27,
-      "learning_rate": 4.82809716767602e-06,
-      "loss": 0.257,
-      "step": 81
-    },
-    {
-      "epoch": 0.27,
-      "learning_rate": 4.8232790021517094e-06,
-      "loss": 0.2475,
-      "step": 82
-    },
-    {
-      "epoch": 0.27,
-      "learning_rate": 4.818396716002553e-06,
-      "loss": 0.2636,
-      "step": 83
-    },
-    {
-      "epoch": 0.28,
-      "learning_rate": 4.813450443975705e-06,
-      "loss": 0.2076,
-      "step": 84
-    },
-    {
-      "epoch": 0.28,
-      "learning_rate": 4.808440322584283e-06,
-      "loss": 0.2336,
-      "step": 85
-    },
-    {
-      "epoch": 0.28,
-      "learning_rate": 4.803366490103593e-06,
-      "loss": 0.2664,
-      "step": 86
-    },
-    {
-      "epoch": 0.29,
-      "learning_rate": 4.798229086567312e-06,
-      "loss": 0.2559,
-      "step": 87
-    },
-    {
-      "epoch": 0.29,
-      "learning_rate": 4.793028253763633e-06,
-      "loss": 0.2687,
-      "step": 88
-    },
-    {
-      "epoch": 0.29,
-      "learning_rate": 4.787764135231342e-06,
-      "loss": 0.2263,
-      "step": 89
-    },
-    {
-      "epoch": 0.3,
-      "learning_rate": 4.7824368762558595e-06,
-      "loss": 0.2058,
-      "step": 90
-    },
-    {
-      "epoch": 0.3,
-      "learning_rate": 4.7770466238652336e-06,
-      "loss": 0.246,
-      "step": 91
-    },
-    {
-      "epoch": 0.3,
-      "learning_rate": 4.771593526826078e-06,
-      "loss": 0.2592,
-      "step": 92
-    },
-    {
-      "epoch": 0.31,
-      "learning_rate": 4.76607773563947e-06,
-      "loss": 0.2701,
-      "step": 93
-    },
-    {
-      "epoch": 0.31,
-      "eval_loss": 0.25227251648902893,
-      "eval_runtime": 15.5184,
-      "eval_samples_per_second": 6.122,
-      "eval_steps_per_second": 1.547,
-      "step": 93
-    },
-    {
-      "epoch": 0.31,
-      "learning_rate": 4.760499402536792e-06,
-      "loss": 0.2154,
-      "step": 94
-    },
-    {
-      "epoch": 0.31,
-      "learning_rate": 4.754858681475534e-06,
-      "loss": 0.2748,
-      "step": 95
-    },
-    {
-      "epoch": 0.32,
-      "learning_rate": 4.7491557281350455e-06,
-      "loss": 0.2461,
-      "step": 96
-    },
-    {
-      "epoch": 0.32,
-      "learning_rate": 4.743390699912232e-06,
-      "loss": 0.2245,
-      "step": 97
-    },
-    {
-      "epoch": 0.32,
-      "learning_rate": 4.737563755917219e-06,
-      "loss": 0.2446,
-      "step": 98
-    },
-    {
-      "epoch": 0.33,
-      "learning_rate": 4.731675056968958e-06,
-      "loss": 0.2563,
-      "step": 99
-    },
-    {
-      "epoch": 0.33,
-      "learning_rate": 4.7257247655907854e-06,
-      "loss": 0.2512,
-      "step": 100
-    },
-    {
-      "epoch": 0.33,
-      "learning_rate": 4.7197130460059385e-06,
-      "loss": 0.2613,
-      "step": 101
-    },
-    {
-      "epoch": 0.33,
-      "learning_rate": 4.7136400641330245e-06,
-      "loss": 0.2294,
-      "step": 102
-    },
-    {
-      "epoch": 0.34,
-      "learning_rate": 4.7075059875814424e-06,
-      "loss": 0.2162,
-      "step": 103
-    },
-    {
-      "epoch": 0.34,
-      "learning_rate": 4.70131098564675e-06,
-      "loss": 0.251,
-      "step": 104
-    },
-    {
-      "epoch": 0.34,
-      "learning_rate": 4.695055229306001e-06,
-      "loss": 0.2468,
-      "step": 105
-    },
-    {
-      "epoch": 0.35,
-      "learning_rate": 4.6887388912130206e-06,
-      "loss": 0.2467,
-      "step": 106
-    },
-    {
-      "epoch": 0.35,
-      "learning_rate": 4.68236214569364e-06,
-      "loss": 0.2588,
-      "step": 107
-    },
-    {
-      "epoch": 0.35,
-      "learning_rate": 4.675925168740887e-06,
-      "loss": 0.2592,
-      "step": 108
-    },
-    {
-      "epoch": 0.36,
-      "learning_rate": 4.6694281380101304e-06,
-      "loss": 0.2225,
-      "step": 109
-    },
-    {
-      "epoch": 0.36,
-      "learning_rate": 4.662871232814171e-06,
-      "loss": 0.2411,
-      "step": 110
-    },
-    {
-      "epoch": 0.36,
-      "learning_rate": 4.656254634118301e-06,
-      "loss": 0.2512,
-      "step": 111
-    },
-    {
-      "epoch": 0.37,
-      "learning_rate": 4.649578524535302e-06,
-      "loss": 0.2252,
-      "step": 112
-    },
-    {
-      "epoch": 0.37,
-      "learning_rate": 4.642843088320408e-06,
-      "loss": 0.2288,
-      "step": 113
-    },
-    {
-      "epoch": 0.37,
-      "learning_rate": 4.636048511366222e-06,
-      "loss": 0.2339,
-      "step": 114
-    },
-    {
-      "epoch": 0.38,
-      "learning_rate": 4.6291949811975814e-06,
-      "loss": 0.2252,
-      "step": 115
-    },
-    {
-      "epoch": 0.38,
-      "learning_rate": 4.622282686966387e-06,
-      "loss": 0.2497,
-      "step": 116
-    },
-    {
-      "epoch": 0.38,
-      "learning_rate": 4.615311819446379e-06,
-      "loss": 0.2339,
-      "step": 117
-    },
-    {
-      "epoch": 0.39,
-      "learning_rate": 4.6082825710278724e-06,
-      "loss": 0.2946,
-      "step": 118
-    },
-    {
-      "epoch": 0.39,
-      "learning_rate": 4.60119513571245e-06,
-      "loss": 0.2797,
-      "step": 119
-    },
-    {
-      "epoch": 0.39,
-      "learning_rate": 4.594049709107604e-06,
-      "loss": 0.272,
-      "step": 120
-    },
-    {
-      "epoch": 0.4,
-      "learning_rate": 4.58684648842134e-06,
-      "loss": 0.2437,
-      "step": 121
-    },
-    {
-      "epoch": 0.4,
-      "learning_rate": 4.5795856724567344e-06,
-      "loss": 0.2328,
-      "step": 122
-    },
-    {
-      "epoch": 0.4,
-      "learning_rate": 4.572267461606446e-06,
-      "loss": 0.2333,
-      "step": 123
-    },
-    {
-      "epoch": 0.41,
-      "learning_rate": 4.564892057847184e-06,
-      "loss": 0.27,
-      "step": 124
-    },
-    {
-      "epoch": 0.41,
-      "eval_loss": 0.2362014800310135,
-      "eval_runtime": 15.5362,
-      "eval_samples_per_second": 6.115,
-      "eval_steps_per_second": 1.545,
-      "step": 124
-    },
-    {
-      "epoch": 0.41,
-      "learning_rate": 4.5574596647341414e-06,
-      "loss": 0.2202,
-      "step": 125
-    },
-    {
-      "epoch": 0.41,
-      "learning_rate": 4.549970487395365e-06,
-      "loss": 0.2129,
-      "step": 126
-    },
-    {
-      "epoch": 0.42,
-      "learning_rate": 4.542424732526105e-06,
-      "loss": 0.2343,
-      "step": 127
-    },
-    {
-      "epoch": 0.42,
-      "learning_rate": 4.534822608383104e-06,
-      "loss": 0.2527,
-      "step": 128
-    },
-    {
-      "epoch": 0.42,
-      "learning_rate": 4.5271643247788496e-06,
-      "loss": 0.2622,
-      "step": 129
-    },
-    {
-      "epoch": 0.43,
-      "learning_rate": 4.519450093075787e-06,
-      "loss": 0.247,
-      "step": 130
-    },
-    {
-      "epoch": 0.43,
-      "learning_rate": 4.5116801261804846e-06,
-      "loss": 0.2612,
-      "step": 131
-    },
-    {
-      "epoch": 0.43,
-      "learning_rate": 4.503854638537756e-06,
-      "loss": 0.2515,
-      "step": 132
-    },
-    {
-      "epoch": 0.44,
-      "learning_rate": 4.49597384612474e-06,
-      "loss": 0.2164,
-      "step": 133
-    },
-    {
-      "epoch": 0.44,
-      "learning_rate": 4.488037966444948e-06,
-      "loss": 0.2545,
-      "step": 134
-    },
-    {
-      "epoch": 0.44,
-      "learning_rate": 4.48004721852225e-06,
-      "loss": 0.2547,
-      "step": 135
-    },
-    {
-      "epoch": 0.45,
-      "learning_rate": 4.472001822894839e-06,
-      "loss": 0.1869,
-      "step": 136
-    },
-    {
-      "epoch": 0.45,
-      "learning_rate": 4.463902001609139e-06,
-      "loss": 0.2383,
-      "step": 137
-    },
-    {
-      "epoch": 0.45,
-      "learning_rate": 4.455747978213679e-06,
-      "loss": 0.2234,
-      "step": 138
-    },
-    {
-      "epoch": 0.46,
-      "learning_rate": 4.44753997775292e-06,
-      "loss": 0.2356,
-      "step": 139
-    },
-    {
-      "epoch": 0.46,
-      "learning_rate": 4.43927822676105e-06,
-      "loss": 0.232,
-      "step": 140
-    },
-    {
-      "epoch": 0.46,
-      "learning_rate": 4.430962953255725e-06,
-      "loss": 0.2352,
-      "step": 141
-    },
-    {
-      "epoch": 0.47,
-      "learning_rate": 4.4225943867317835e-06,
-      "loss": 0.2199,
-      "step": 142
-    },
-    {
-      "epoch": 0.47,
-      "learning_rate": 4.4141727581549025e-06,
-      "loss": 0.2175,
-      "step": 143
-    },
-    {
-      "epoch": 0.47,
-      "learning_rate": 4.405698299955234e-06,
-      "loss": 0.221,
-      "step": 144
-    },
-    {
-      "epoch": 0.48,
-      "learning_rate": 4.39717124602098e-06,
-      "loss": 0.2522,
-      "step": 145
-    },
-    {
-      "epoch": 0.48,
-      "learning_rate": 4.388591831691948e-06,
-      "loss": 0.2412,
-      "step": 146
-    },
-    {
-      "epoch": 0.48,
-      "learning_rate": 4.3799602937530464e-06,
-      "loss": 0.2176,
-      "step": 147
-    },
-    {
-      "epoch": 0.49,
-      "learning_rate": 4.3712768704277535e-06,
-      "loss": 0.2242,
-      "step": 148
-    },
-    {
-      "epoch": 0.49,
-      "learning_rate": 4.362541801371542e-06,
-      "loss": 0.2156,
-      "step": 149
-    },
-    {
-      "epoch": 0.49,
-      "learning_rate": 4.353755327665268e-06,
-      "loss": 0.2077,
-      "step": 150
-    },
-    {
-      "epoch": 0.5,
-      "learning_rate": 4.344917691808511e-06,
-      "loss": 0.2285,
-      "step": 151
-    },
-    {
-      "epoch": 0.5,
-      "learning_rate": 4.3360291377128864e-06,
-      "loss": 0.2364,
-      "step": 152
-    },
-    {
-      "epoch": 0.5,
-      "learning_rate": 4.32708991069531e-06,
-      "loss": 0.2577,
-      "step": 153
-    },
-    {
-      "epoch": 0.51,
-      "learning_rate": 4.318100257471233e-06,
-      "loss": 0.2347,
-      "step": 154
-    },
-    {
-      "epoch": 0.51,
-      "learning_rate": 4.309060426147826e-06,
-      "loss": 0.2244,
-      "step": 155
-    },
-    {
-      "epoch": 0.51,
-      "eval_loss": 0.22840476036071777,
-      "eval_runtime": 15.5442,
-      "eval_samples_per_second": 6.112,
-      "eval_steps_per_second": 1.544,
-      "step": 155
-    },
-    {
-      "epoch": 0.51,
-      "learning_rate": 4.299970666217135e-06,
-      "loss": 0.2197,
-      "step": 156
-    },
-    {
-      "epoch": 0.52,
-      "learning_rate": 4.290831228549196e-06,
-      "loss": 0.2618,
-      "step": 157
-    },
-    {
-      "epoch": 0.52,
-      "learning_rate": 4.281642365385111e-06,
-      "loss": 0.2498,
-      "step": 158
-    },
-    {
-      "epoch": 0.52,
-      "learning_rate": 4.272404330330084e-06,
-      "loss": 0.2309,
-      "step": 159
-    },
-    {
-      "epoch": 0.53,
-      "learning_rate": 4.263117378346425e-06,
-      "loss": 0.2163,
-      "step": 160
-    },
-    {
-      "epoch": 0.53,
-      "learning_rate": 4.253781765746511e-06,
-      "loss": 0.1968,
-      "step": 161
-    },
-    {
-      "epoch": 0.53,
-      "learning_rate": 4.244397750185714e-06,
-      "loss": 0.2127,
-      "step": 162
-    },
-    {
-      "epoch": 0.54,
-      "learning_rate": 4.234965590655287e-06,
-      "loss": 0.2088,
-      "step": 163
-    },
-    {
-      "epoch": 0.54,
-      "learning_rate": 4.225485547475217e-06,
-      "loss": 0.2082,
-      "step": 164
-    },
-    {
-      "epoch": 0.54,
-      "learning_rate": 4.215957882287044e-06,
-      "loss": 0.2549,
-      "step": 165
-    },
-    {
-      "epoch": 0.55,
-      "learning_rate": 4.206382858046636e-06,
-      "loss": 0.2131,
-      "step": 166
-    },
-    {
-      "epoch": 0.55,
-      "learning_rate": 4.19676073901693e-06,
-      "loss": 0.2048,
-      "step": 167
-    },
-    {
-      "epoch": 0.55,
-      "learning_rate": 4.187091790760644e-06,
-      "loss": 0.2451,
-      "step": 168
-    },
-    {
-      "epoch": 0.56,
-      "learning_rate": 4.177376280132946e-06,
-      "loss": 0.1896,
-      "step": 169
-    },
-    {
-      "epoch": 0.56,
-      "learning_rate": 4.167614475274082e-06,
-      "loss": 0.2253,
-      "step": 170
-    },
-    {
-      "epoch": 0.56,
-      "learning_rate": 4.1578066456019885e-06,
-      "loss": 0.2167,
-      "step": 171
-    },
-    {
-      "epoch": 0.56,
-      "learning_rate": 4.147953061804845e-06,
-      "loss": 0.2262,
-      "step": 172
-    },
-    {
-      "epoch": 0.57,
-      "learning_rate": 4.1380539958336095e-06,
-      "loss": 0.2483,
-      "step": 173
-    },
-    {
-      "epoch": 0.57,
-      "learning_rate": 4.128109720894512e-06,
-      "loss": 0.2824,
-      "step": 174
-    },
-    {
-      "epoch": 0.57,
-      "learning_rate": 4.118120511441512e-06,
-      "loss": 0.2273,
-      "step": 175
-    },
-    {
-      "epoch": 0.58,
-      "learning_rate": 4.108086643168724e-06,
-      "loss": 0.2177,
-      "step": 176
-    },
-    {
-      "epoch": 0.58,
-      "learning_rate": 4.098008393002816e-06,
-      "loss": 0.2147,
-      "step": 177
-    },
-    {
-      "epoch": 0.58,
-      "learning_rate": 4.087886039095353e-06,
-      "loss": 0.1915,
-      "step": 178
-    },
-    {
-      "epoch": 0.59,
-      "learning_rate": 4.077719860815132e-06,
-      "loss": 0.2123,
-      "step": 179
-    },
-    {
-      "epoch": 0.59,
-      "learning_rate": 4.067510138740467e-06,
-      "loss": 0.2418,
-      "step": 180
-    },
-    {
-      "epoch": 0.59,
-      "learning_rate": 4.057257154651444e-06,
-      "loss": 0.2055,
-      "step": 181
-    },
-    {
-      "epoch": 0.6,
-      "learning_rate": 4.046961191522147e-06,
-      "loss": 0.2098,
-      "step": 182
-    },
-    {
-      "epoch": 0.6,
-      "learning_rate": 4.036622533512845e-06,
-      "loss": 0.2304,
-      "step": 183
-    },
-    {
-      "epoch": 0.6,
-      "learning_rate": 4.026241465962154e-06,
-      "loss": 0.2018,
-      "step": 184
-    },
-    {
-      "epoch": 0.61,
-      "learning_rate": 4.0158182753791566e-06,
-      "loss": 0.2009,
-      "step": 185
-    },
-    {
-      "epoch": 0.61,
-      "learning_rate": 4.0053532494354985e-06,
-      "loss": 0.2227,
-      "step": 186
-    },
-    {
-      "epoch": 0.61,
-      "eval_loss": 0.2260431945323944,
-      "eval_runtime": 15.5286,
-      "eval_samples_per_second": 6.118,
-      "eval_steps_per_second": 1.546,
-      "step": 186
-    },
-    {
-      "epoch": 0.61,
-      "learning_rate": 3.994846676957448e-06,
-      "loss": 0.1973,
-      "step": 187
-    },
-    {
-      "epoch": 0.62,
-      "learning_rate": 3.984298847917923e-06,
-      "loss": 0.2192,
-      "step": 188
-    },
-    {
-      "epoch": 0.62,
-      "learning_rate": 3.973710053428487e-06,
-      "loss": 0.2016,
-      "step": 189
-    },
-    {
-      "epoch": 0.62,
-      "learning_rate": 3.963080585731324e-06,
-      "loss": 0.2118,
-      "step": 190
-    },
-    {
-      "epoch": 0.63,
-      "learning_rate": 3.952410738191158e-06,
-      "loss": 0.2361,
-      "step": 191
-    },
-    {
-      "epoch": 0.63,
-      "learning_rate": 3.941700805287169e-06,
-      "loss": 0.2132,
-      "step": 192
-    },
-    {
-      "epoch": 0.63,
-      "learning_rate": 3.9309510826048556e-06,
-      "loss": 0.2117,
-      "step": 193
-    },
-    {
-      "epoch": 0.64,
-      "learning_rate": 3.92016186682789e-06,
-      "loss": 0.2196,
-      "step": 194
-    },
-    {
-      "epoch": 0.64,
-      "learning_rate": 3.909333455729914e-06,
-      "loss": 0.1958,
-      "step": 195
-    },
-    {
-      "epoch": 0.64,
-      "learning_rate": 3.898466148166333e-06,
-      "loss": 0.2318,
-      "step": 196
-    },
-    {
-      "epoch": 0.65,
-      "learning_rate": 3.8875602440660635e-06,
-      "loss": 0.2034,
-      "step": 197
-    },
-    {
-      "epoch": 0.65,
-      "learning_rate": 3.876616044423253e-06,
-      "loss": 0.2119,
-      "step": 198
-    },
-    {
-      "epoch": 0.65,
-      "learning_rate": 3.865633851288975e-06,
-      "loss": 0.2177,
-      "step": 199
-    },
-    {
-      "epoch": 0.66,
-      "learning_rate": 3.854613967762898e-06,
-      "loss": 0.1974,
-      "step": 200
-    },
-    {
-      "epoch": 0.66,
-      "learning_rate": 3.843556697984907e-06,
-      "loss": 0.1902,
-      "step": 201
-    },
-    {
-      "epoch": 0.66,
-      "learning_rate": 3.832462347126722e-06,
-      "loss": 0.1975,
-      "step": 202
-    },
-    {
-      "epoch": 0.67,
-      "learning_rate": 3.821331221383471e-06,
-      "loss": 0.2083,
-      "step": 203
-    },
-    {
-      "epoch": 0.67,
-      "learning_rate": 3.8101636279652375e-06,
-      "loss": 0.2247,
-      "step": 204
-    },
-    {
-      "epoch": 0.67,
-      "learning_rate": 3.798959875088584e-06,
-      "loss": 0.2169,
-      "step": 205
-    },
-    {
-      "epoch": 0.68,
-      "learning_rate": 3.787720271968046e-06,
-      "loss": 0.1854,
-      "step": 206
-    },
-    {
-      "epoch": 0.68,
-      "learning_rate": 3.7764451288075944e-06,
-      "loss": 0.2269,
-      "step": 207
-    },
-    {
-      "epoch": 0.68,
-      "learning_rate": 3.765134756792079e-06,
-      "loss": 0.1946,
-      "step": 208
-    },
-    {
-      "epoch": 0.69,
-      "learning_rate": 3.753789468078636e-06,
-      "loss": 0.1944,
-      "step": 209
-    },
-    {
-      "epoch": 0.69,
-      "learning_rate": 3.742409575788074e-06,
-      "loss": 0.2057,
-      "step": 210
-    },
-    {
-      "epoch": 0.69,
-      "learning_rate": 3.730995393996234e-06,
-      "loss": 0.2427,
-      "step": 211
-    },
-    {
-      "epoch": 0.7,
-      "learning_rate": 3.719547237725319e-06,
-      "loss": 0.227,
-      "step": 212
-    },
-    {
-      "epoch": 0.7,
-      "learning_rate": 3.708065422935198e-06,
-      "loss": 0.2152,
-      "step": 213
-    },
-    {
-      "epoch": 0.7,
-      "learning_rate": 3.6965502665146916e-06,
-      "loss": 0.2177,
-      "step": 214
-    },
-    {
-      "epoch": 0.71,
-      "learning_rate": 3.6850020862728196e-06,
-      "loss": 0.2089,
-      "step": 215
-    },
-    {
-      "epoch": 0.71,
-      "learning_rate": 3.6734212009300346e-06,
-      "loss": 0.2081,
-      "step": 216
-    },
-    {
-      "epoch": 0.71,
-      "learning_rate": 3.661807930109422e-06,
-      "loss": 0.2167,
-      "step": 217
-    },
-    {
-      "epoch": 0.71,
-      "eval_loss": 0.21709737181663513,
-      "eval_runtime": 15.5146,
-      "eval_samples_per_second": 6.123,
-      "eval_steps_per_second": 1.547,
-      "step": 217
-    },
-    {
-      "epoch": 0.72,
-      "learning_rate": 3.650162594327881e-06,
-      "loss": 0.2135,
-      "step": 218
-    },
-    {
-      "epoch": 0.72,
-      "learning_rate": 3.6384855149872776e-06,
-      "loss": 0.1976,
-      "step": 219
-    },
-    {
-      "epoch": 0.72,
-      "learning_rate": 3.6267770143655743e-06,
-      "loss": 0.2073,
-      "step": 220
-    },
-    {
-      "epoch": 0.73,
-      "learning_rate": 3.615037415607937e-06,
-      "loss": 0.2252,
-      "step": 221
-    },
-    {
-      "epoch": 0.73,
-      "learning_rate": 3.603267042717813e-06,
-      "loss": 0.2296,
-      "step": 222
-    },
-    {
-      "epoch": 0.73,
-      "learning_rate": 3.5914662205479923e-06,
-      "loss": 0.181,
-      "step": 223
-    },
-    {
-      "epoch": 0.74,
-      "learning_rate": 3.579635274791639e-06,
-      "loss": 0.2196,
-      "step": 224
-    },
-    {
-      "epoch": 0.74,
-      "learning_rate": 3.567774531973305e-06,
-      "loss": 0.2063,
-      "step": 225
-    },
-    {
-      "epoch": 0.74,
-      "learning_rate": 3.555884319439917e-06,
-      "loss": 0.2313,
-      "step": 226
-    },
-    {
-      "epoch": 0.75,
-      "learning_rate": 3.5439649653517416e-06,
-      "loss": 0.1994,
-      "step": 227
-    },
-    {
-      "epoch": 0.75,
-      "learning_rate": 3.532016798673329e-06,
-      "loss": 0.2143,
-      "step": 228
-    },
-    {
-      "epoch": 0.75,
-      "learning_rate": 3.5200401491644333e-06,
-      "loss": 0.2118,
-      "step": 229
-    },
-    {
-      "epoch": 0.76,
-      "learning_rate": 3.508035347370912e-06,
-      "loss": 0.2081,
-      "step": 230
-    },
-    {
-      "epoch": 0.76,
-      "learning_rate": 3.4960027246156043e-06,
-      "loss": 0.2313,
-      "step": 231
-    },
-    {
-      "epoch": 0.76,
-      "learning_rate": 3.483942612989183e-06,
-      "loss": 0.2071,
-      "step": 232
-    },
-    {
-      "epoch": 0.77,
-      "learning_rate": 3.471855345340992e-06,
-      "loss": 0.2199,
-      "step": 233
-    },
-    {
-      "epoch": 0.77,
-      "learning_rate": 3.4597412552698617e-06,
-      "loss": 0.1879,
-      "step": 234
-    },
-    {
-      "epoch": 0.77,
-      "learning_rate": 3.447600677114898e-06,
-      "loss": 0.1717,
-      "step": 235
-    },
-    {
-      "epoch": 0.78,
-      "learning_rate": 3.4354339459462556e-06,
-      "loss": 0.2273,
-      "step": 236
-    },
-    {
-      "epoch": 0.78,
-      "learning_rate": 3.423241397555893e-06,
-      "loss": 0.2351,
-      "step": 237
-    },
-    {
-      "epoch": 0.78,
-      "learning_rate": 3.4110233684483033e-06,
-      "loss": 0.2165,
-      "step": 238
-    },
-    {
-      "epoch": 0.78,
-      "learning_rate": 3.3987801958312254e-06,
-      "loss": 0.2309,
-      "step": 239
-    },
-    {
-      "epoch": 0.79,
-      "learning_rate": 3.386512217606339e-06,
-      "loss": 0.2023,
-      "step": 240
-    },
-    {
-      "epoch": 0.79,
-      "learning_rate": 3.3742197723599403e-06,
-      "loss": 0.2189,
-      "step": 241
-    },
-    {
-      "epoch": 0.79,
-      "learning_rate": 3.361903199353593e-06,
-      "loss": 0.205,
-      "step": 242
-    },
-    {
-      "epoch": 0.8,
-      "learning_rate": 3.349562838514769e-06,
-      "loss": 0.1912,
-      "step": 243
-    },
-    {
-      "epoch": 0.8,
-      "learning_rate": 3.3371990304274654e-06,
-      "loss": 0.1898,
-      "step": 244
-    },
-    {
-      "epoch": 0.8,
-      "learning_rate": 3.3248121163228037e-06,
-      "loss": 0.2037,
-      "step": 245
-    },
-    {
-      "epoch": 0.81,
-      "learning_rate": 3.3124024380696134e-06,
-      "loss": 0.1959,
-      "step": 246
-    },
-    {
-      "epoch": 0.81,
-      "learning_rate": 3.299970338164995e-06,
-      "loss": 0.1972,
-      "step": 247
-    },
-    {
-      "epoch": 0.81,
-      "learning_rate": 3.28751615972487e-06,
-      "loss": 0.2098,
-      "step": 248
-    },
-    {
-      "epoch": 0.81,
-      "eval_loss": 0.20815877616405487,
-      "eval_runtime": 15.5231,
-      "eval_samples_per_second": 6.12,
-      "eval_steps_per_second": 1.546,
-      "step": 248
-    },
-    {
-      "epoch": 0.82,
-      "learning_rate": 3.2750402464745084e-06,
-      "loss": 0.2322,
-      "step": 249
-    },
-    {
-      "epoch": 0.82,
-      "learning_rate": 3.262542942739044e-06,
-      "loss": 0.1977,
-      "step": 250
-    },
-    {
-      "epoch": 0.82,
-      "learning_rate": 3.2500245934339714e-06,
-      "loss": 0.1983,
-      "step": 251
-    },
-    {
-      "epoch": 0.83,
-      "learning_rate": 3.2374855440556242e-06,
-      "loss": 0.1857,
-      "step": 252
-    },
-    {
-      "epoch": 0.83,
-      "learning_rate": 3.224926140671643e-06,
-      "loss": 0.183,
-      "step": 253
-    },
-    {
-      "epoch": 0.83,
-      "learning_rate": 3.2123467299114216e-06,
-      "loss": 0.2216,
-      "step": 254
-    },
-    {
-      "epoch": 0.84,
-      "learning_rate": 3.199747658956541e-06,
-      "loss": 0.1808,
-      "step": 255
-    },
-    {
-      "epoch": 0.84,
-      "learning_rate": 3.1871292755311887e-06,
-      "loss": 0.2278,
-      "step": 256
-    },
-    {
-      "epoch": 0.84,
-      "learning_rate": 3.174491927892561e-06,
-      "loss": 0.203,
-      "step": 257
-    },
-    {
-      "epoch": 0.85,
-      "learning_rate": 3.1618359648212492e-06,
-      "loss": 0.2209,
-      "step": 258
-    },
-    {
-      "epoch": 0.85,
-      "learning_rate": 3.1491617356116167e-06,
-      "loss": 0.2131,
-      "step": 259
-    },
-    {
-      "epoch": 0.85,
-      "learning_rate": 3.136469590062158e-06,
-      "loss": 0.2111,
-      "step": 260
-    },
-    {
-      "epoch": 0.86,
-      "learning_rate": 3.1237598784658444e-06,
-      "loss": 0.1915,
-      "step": 261
-    },
-    {
-      "epoch": 0.86,
-      "learning_rate": 3.1110329516004546e-06,
-      "loss": 0.2272,
-      "step": 262
-    },
-    {
-      "epoch": 0.86,
-      "learning_rate": 3.0982891607188948e-06,
-      "loss": 0.1784,
-      "step": 263
-    },
-    {
-      "epoch": 0.87,
-      "learning_rate": 3.085528857539506e-06,
-      "loss": 0.2064,
-      "step": 264
-    },
-    {
-      "epoch": 0.87,
-      "learning_rate": 3.0727523942363547e-06,
-      "loss": 0.1857,
-      "step": 265
-    },
-    {
-      "epoch": 0.87,
-      "learning_rate": 3.0599601234295124e-06,
-      "loss": 0.1981,
-      "step": 266
-    },
-    {
-      "epoch": 0.88,
-      "learning_rate": 3.0471523981753266e-06,
-      "loss": 0.2429,
-      "step": 267
-    },
-    {
-      "epoch": 0.88,
-      "learning_rate": 3.0343295719566747e-06,
-      "loss": 0.1755,
-      "step": 268
-    },
-    {
-      "epoch": 0.88,
-      "learning_rate": 3.0214919986732076e-06,
-      "loss": 0.2024,
-      "step": 269
-    },
-    {
-      "epoch": 0.89,
-      "learning_rate": 3.0086400326315853e-06,
-      "loss": 0.1859,
-      "step": 270
-    },
-    {
-      "epoch": 0.89,
-      "learning_rate": 2.9957740285356933e-06,
-      "loss": 0.2056,
-      "step": 271
-    },
-    {
-      "epoch": 0.89,
-      "learning_rate": 2.9828943414768583e-06,
-      "loss": 0.2183,
-      "step": 272
-    },
-    {
-      "epoch": 0.9,
-      "learning_rate": 2.9700013269240463e-06,
-      "loss": 0.1892,
-      "step": 273
-    },
-    {
-      "epoch": 0.9,
-      "learning_rate": 2.957095340714049e-06,
-      "loss": 0.2139,
-      "step": 274
-    },
-    {
-      "epoch": 0.9,
-      "learning_rate": 2.9441767390416665e-06,
-      "loss": 0.2314,
-      "step": 275
-    },
-    {
-      "epoch": 0.91,
-      "learning_rate": 2.9312458784498763e-06,
-      "loss": 0.1897,
-      "step": 276
-    },
-    {
-      "epoch": 0.91,
-      "learning_rate": 2.918303115819992e-06,
-      "loss": 0.1698,
-      "step": 277
-    },
-    {
-      "epoch": 0.91,
-      "learning_rate": 2.9053488083618118e-06,
-      "loss": 0.2147,
-      "step": 278
-    },
-    {
-      "epoch": 0.92,
-      "learning_rate": 2.892383313603765e-06,
-      "loss": 0.1842,
-      "step": 279
-    },
-    {
-      "epoch": 0.92,
-      "eval_loss": 0.20471937954425812,
-      "eval_runtime": 15.5241,
-      "eval_samples_per_second": 6.12,
-      "eval_steps_per_second": 1.546,
-      "step": 279
-    },
-    {
-      "epoch": 0.92,
-      "learning_rate": 2.8794069893830386e-06,
-      "loss": 0.178,
-      "step": 280
-    },
-    {
-      "epoch": 0.92,
-      "learning_rate": 2.8664201938357052e-06,
-      "loss": 0.2245,
-      "step": 281
-    },
-    {
-      "epoch": 0.93,
-      "learning_rate": 2.8534232853868384e-06,
-      "loss": 0.1583,
-      "step": 282
-    },
-    {
-      "epoch": 0.93,
-      "learning_rate": 2.840416622740617e-06,
-      "loss": 0.1752,
-      "step": 283
-    },
-    {
-      "epoch": 0.93,
-      "learning_rate": 2.8274005648704316e-06,
-      "loss": 0.1981,
-      "step": 284
-    },
-    {
-      "epoch": 0.94,
-      "learning_rate": 2.8143754710089694e-06,
-      "loss": 0.2216,
-      "step": 285
-    },
-    {
-      "epoch": 0.94,
-      "learning_rate": 2.8013417006383078e-06,
-      "loss": 0.2075,
-      "step": 286
-    },
-    {
-      "epoch": 0.94,
-      "learning_rate": 2.7882996134799854e-06,
-      "loss": 0.1978,
-      "step": 287
-    },
-    {
-      "epoch": 0.95,
-      "learning_rate": 2.775249569485079e-06,
-      "loss": 0.2302,
-      "step": 288
-    },
-    {
-      "epoch": 0.95,
-      "learning_rate": 2.762191928824267e-06,
-      "loss": 0.2218,
-      "step": 289
-    },
-    {
-      "epoch": 0.95,
-      "learning_rate": 2.7491270518778913e-06,
-      "loss": 0.2033,
-      "step": 290
-    },
-    {
-      "epoch": 0.96,
-      "learning_rate": 2.736055299226007e-06,
-      "loss": 0.2055,
-      "step": 291
-    },
-    {
-      "epoch": 0.96,
-      "learning_rate": 2.722977031638435e-06,
-      "loss": 0.2231,
-      "step": 292
-    },
-    {
-      "epoch": 0.96,
-      "learning_rate": 2.709892610064801e-06,
-      "loss": 0.2233,
-      "step": 293
-    },
-    {
-      "epoch": 0.97,
-      "learning_rate": 2.696802395624579e-06,
-      "loss": 0.2354,
-      "step": 294
-    },
-    {
-      "epoch": 0.97,
-      "learning_rate": 2.683706749597118e-06,
-      "loss": 0.2136,
-      "step": 295
-    },
-    {
-      "epoch": 0.97,
-      "learning_rate": 2.670606033411678e-06,
-      "loss": 0.181,
-      "step": 296
-    },
-    {
-      "epoch": 0.98,
-      "learning_rate": 2.657500608637448e-06,
-      "loss": 0.2051,
-      "step": 297
-    },
-    {
-      "epoch": 0.98,
-      "learning_rate": 2.6443908369735715e-06,
-      "loss": 0.209,
-      "step": 298
-    },
-    {
-      "epoch": 0.98,
-      "learning_rate": 2.631277080239163e-06,
-      "loss": 0.2184,
-      "step": 299
-    },
-    {
-      "epoch": 0.99,
-      "learning_rate": 2.6181597003633218e-06,
-      "loss": 0.1988,
-      "step": 300
-    },
-    {
-      "epoch": 0.99,
-      "learning_rate": 2.605039059375143e-06,
-      "loss": 0.2223,
-      "step": 301
-    },
-    {
-      "epoch": 0.99,
-      "learning_rate": 2.5919155193937244e-06,
-      "loss": 0.2029,
-      "step": 302
-    },
-    {
-      "epoch": 1.0,
-      "learning_rate": 2.578789442618176e-06,
-      "loss": 0.2089,
-      "step": 303
-    },
-    {
-      "epoch": 1.0,
-      "learning_rate": 2.565661191317618e-06,
-      "loss": 0.2065,
-      "step": 304
-    }
-  ],
-  "logging_steps": 1,
-  "max_steps": 608,
-  "num_train_epochs": 2,
-  "save_steps": 500,
-  "total_flos": 1.7027813817943327e+18,
-  "trial_name": null,
-  "trial_params": null
-}

checkpoint-304/training_args.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:0f17f663326682e34d06194ed091725483adeebe21013fe1752885513b5506a8
-size 4411