Upload folder using huggingface_hub

added_tokens.json

@@ -0,0 +1,6 @@
+{
+  "<im_end>": 32002,
+  "<im_patch>": 32000,
+  "<im_start>": 32001,
+  "[PAD]": 32003
+}

config.json

@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "/workspace/LLaVA/checkpoints/july-17-ft-from-llava-13bv0-scicap-multi-turn-30-percent",
+  "architectures": [
+    "LlavaLlamaForCausalLM"
+  ],
+  "bos_token_id": 0,
+  "eos_token_id": 1,
+  "freeze_mm_mlp_adapter": false,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 13824,
+  "max_sequence_length": 2048,
+  "mm_hidden_size": 1024,
+  "mm_use_im_start_end": true,
+  "mm_vision_select_layer": -2,
+  "mm_vision_tower": "openai/clip-vit-large-patch14",
+  "model_type": "llava",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 40,
+  "pad_token_id": -1,
+  "rms_norm_eps": 1e-06,
+  "sep_image_conv_front": false,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.28.0.dev0",
+  "tune_mm_mlp_adapter": false,
+  "use_cache": false,
+  "use_mm_proj": true,
+  "vocab_size": 32004
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 1,
+  "pad_token_id": 0,
+  "transformers_version": "4.28.0.dev0"
+}

pytorch_model-00001-of-00006.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d5ef48fca2f86c1c7aebe5219beccba8867e97d29bfb2a2881f06874ba3ba5c9
+size 9956625803

pytorch_model-00002-of-00006.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05c66f714cb47185de7e7719af1ac56864f9a4406c41158be5d9c11a36d083de
+size 9940856385

pytorch_model-00003-of-00006.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:342490a7d6676e40a357103702ecb58575ea158067db28c8e463929113fb9e57
+size 9940856943

pytorch_model-00004-of-00006.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f91abc1562803adcfb6b2851dedd5ff3bbcf59ef80a1f55aac09062c2460fd89
+size 9867415289

pytorch_model-00005-of-00006.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:739091fe654077c949af20cc699528d7437ab1220d8c50adea525ae3fef4936d
+size 9867456961

pytorch_model-00006-of-00006.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4691a17f663e9d66746eb258d09853899e47f9c6898a52a7f33b2b4df87d70f
+size 2511550739

pytorch_model.bin.index.json

@@ -0,0 +1,412 @@
+{
+  "metadata": {
+    "total_size": 52084623360
+  },
+  "weight_map": {
+    "lm_head.weight": "pytorch_model-00006-of-00006.bin",
+    "model.embed_tokens.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.0.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00006.bin",
+    "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.1.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00006.bin",
+    "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.10.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.10.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.10.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.10.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00006.bin",
+    "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.11.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.11.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.11.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.11.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00006.bin",
+    "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.12.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.12.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.12.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.12.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00006.bin",
+    "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.13.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.13.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.13.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.13.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00006.bin",
+    "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.14.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.14.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.14.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.14.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00006.bin",
+    "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.15.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.15.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.15.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.15.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00006.bin",
+    "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.16.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.16.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.16.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.16.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00006.bin",
+    "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.17.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.17.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.17.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.17.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00006.bin",
+    "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.18.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.18.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.18.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.18.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00006.bin",
+    "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.19.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.19.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.19.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.19.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00006.bin",
+    "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.2.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00006.bin",
+    "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.20.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.20.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.20.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.20.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00006.bin",
+    "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.21.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.21.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.21.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.21.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00006.bin",
+    "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.22.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.22.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.22.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.22.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00006.bin",
+    "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.23.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.23.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.23.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.23.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00006.bin",
+    "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.24.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.24.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.24.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.24.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00006.bin",
+    "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.25.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.25.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.25.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.25.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00006.bin",
+    "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.26.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.26.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.26.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.26.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00006.bin",
+    "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.27.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.27.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.27.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.27.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00006.bin",
+    "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.28.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.28.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.28.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.28.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00006.bin",
+    "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.29.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.29.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.29.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.29.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00006.bin",
+    "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.3.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00006.bin",
+    "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.30.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.30.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.30.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.30.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00006.bin",
+    "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.31.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.31.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.31.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.31.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00006.bin",
+    "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.32.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.32.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.32.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.32.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.32.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.32.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.32.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.32.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.32.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00006.bin",
+    "model.layers.32.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.33.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.33.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.33.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.33.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.33.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.33.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.33.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.33.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.33.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00006.bin",
+    "model.layers.33.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.34.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.34.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.34.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.34.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.34.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.34.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.34.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.34.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.34.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00006.bin",
+    "model.layers.34.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.35.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.35.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.35.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.35.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.35.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.35.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.35.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.35.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.35.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00006.bin",
+    "model.layers.35.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.36.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.36.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.36.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.36.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.36.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.36.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.36.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.36.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.36.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00006.bin",
+    "model.layers.36.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.37.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.37.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.37.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.37.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.37.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.37.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.37.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.37.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.37.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00006.bin",
+    "model.layers.37.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.38.input_layernorm.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.38.mlp.down_proj.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.38.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.38.mlp.up_proj.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.38.post_attention_layernorm.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.38.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.38.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.38.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.38.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00006.bin",
+    "model.layers.38.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.39.input_layernorm.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.39.mlp.down_proj.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.39.mlp.gate_proj.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.39.mlp.up_proj.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.39.post_attention_layernorm.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.39.self_attn.k_proj.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.39.self_attn.o_proj.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.39.self_attn.q_proj.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.39.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00006.bin",
+    "model.layers.39.self_attn.v_proj.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.4.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00006.bin",
+    "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.5.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00006.bin",
+    "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.6.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00006.bin",
+    "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.7.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.7.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.7.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.7.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00006.bin",
+    "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.8.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.8.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.8.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.8.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00006.bin",
+    "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.9.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.9.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.9.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.9.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00006.bin",
+    "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.mm_projector.bias": "pytorch_model-00006-of-00006.bin",
+    "model.mm_projector.weight": "pytorch_model-00006-of-00006.bin",
+    "model.norm.weight": "pytorch_model-00006-of-00006.bin"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "</s>",
+  "eos_token": "</s>",
+  "pad_token": "[PAD]",
+  "unk_token": "<unk>"
+}

tokenizer.model

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

tokenizer_config.json

@@ -0,0 +1,9 @@
+{
+  "bos_token": "",
+  "eos_token": "",
+  "model_max_length": 2048,
+  "padding_side": "right",
+  "special_tokens_map_file": "/home/gcpuser/hf-output/llama-13b/special_tokens_map.json",
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": ""
+}

trainer_state.json

@@ -0,0 +1,1693 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "global_step": 278,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "learning_rate": 2.222222222222222e-06,
+      "loss": 0.9528,
+      "step": 1
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 4.444444444444444e-06,
+      "loss": 0.8803,
+      "step": 2
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 0.8748,
+      "step": 3
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 8.888888888888888e-06,
+      "loss": 0.9064,
+      "step": 4
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.1111111111111113e-05,
+      "loss": 0.8915,
+      "step": 5
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 0.8656,
+      "step": 6
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.555555555555556e-05,
+      "loss": 0.8642,
+      "step": 7
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.7777777777777777e-05,
+      "loss": 0.9196,
+      "step": 8
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 2e-05,
+      "loss": 0.8783,
+      "step": 9
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.9999318037877998e-05,
+      "loss": 0.8703,
+      "step": 10
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.9997272244526454e-05,
+      "loss": 0.9208,
+      "step": 11
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.9993862898976092e-05,
+      "loss": 0.912,
+      "step": 12
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.998909046623581e-05,
+      "loss": 0.8988,
+      "step": 13
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.9982955597229275e-05,
+      "loss": 0.8873,
+      "step": 14
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.9975459128706155e-05,
+      "loss": 0.8688,
+      "step": 15
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.996660208312796e-05,
+      "loss": 0.9077,
+      "step": 16
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.9956385668528614e-05,
+      "loss": 0.8782,
+      "step": 17
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.9944811278349666e-05,
+      "loss": 0.873,
+      "step": 18
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.9931880491250263e-05,
+      "loss": 0.8998,
+      "step": 19
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.9917595070891796e-05,
+      "loss": 0.9115,
+      "step": 20
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.9901956965697387e-05,
+      "loss": 0.9197,
+      "step": 21
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.988496830858612e-05,
+      "loss": 0.898,
+      "step": 22
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.986663141668212e-05,
+      "loss": 0.8908,
+      "step": 23
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.9846948790998532e-05,
+      "loss": 0.8601,
+      "step": 24
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.982592311609639e-05,
+      "loss": 0.859,
+      "step": 25
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.9803557259718472e-05,
+      "loss": 0.9306,
+      "step": 26
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.977985427239815e-05,
+      "loss": 0.906,
+      "step": 27
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.975481738704333e-05,
+      "loss": 0.9386,
+      "step": 28
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.9728450018495506e-05,
+      "loss": 0.8569,
+      "step": 29
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.9700755763064e-05,
+      "loss": 0.8911,
+      "step": 30
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.967173839803545e-05,
+      "loss": 0.9246,
+      "step": 31
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.9641401881158625e-05,
+      "loss": 0.8808,
+      "step": 32
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.960975035010461e-05,
+      "loss": 0.8474,
+      "step": 33
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.9576788121902457e-05,
+      "loss": 0.8672,
+      "step": 34
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.954251969235039e-05,
+      "loss": 0.8729,
+      "step": 35
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.950694973540259e-05,
+      "loss": 0.8927,
+      "step": 36
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.9470083102531724e-05,
+      "loss": 0.9035,
+      "step": 37
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.943192482206723e-05,
+      "loss": 0.9003,
+      "step": 38
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.9392480098509488e-05,
+      "loss": 0.8605,
+      "step": 39
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.9351754311819978e-05,
+      "loss": 0.9471,
+      "step": 40
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.9309753016687478e-05,
+      "loss": 0.9558,
+      "step": 41
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.9266481941770463e-05,
+      "loss": 0.9359,
+      "step": 42
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.9221946988915745e-05,
+      "loss": 0.9561,
+      "step": 43
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.9176154232353513e-05,
+      "loss": 0.9012,
+      "step": 44
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.9129109917868863e-05,
+      "loss": 0.8935,
+      "step": 45
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.9080820461949886e-05,
+      "loss": 0.8635,
+      "step": 46
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.9031292450912565e-05,
+      "loss": 0.9522,
+      "step": 47
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.898053264000239e-05,
+      "loss": 0.9226,
+      "step": 48
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.8928547952473037e-05,
+      "loss": 0.8975,
+      "step": 49
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.8875345478642067e-05,
+      "loss": 0.8776,
+      "step": 50
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.8820932474923874e-05,
+      "loss": 0.8925,
+      "step": 51
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.8765316362839955e-05,
+      "loss": 0.8753,
+      "step": 52
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.8708504728006668e-05,
+      "loss": 0.8859,
+      "step": 53
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.865050531910062e-05,
+      "loss": 0.9087,
+      "step": 54
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.8591326046801813e-05,
+      "loss": 0.8739,
+      "step": 55
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.8530974982714667e-05,
+      "loss": 0.9321,
+      "step": 56
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.8469460358267127e-05,
+      "loss": 0.8945,
+      "step": 57
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.8406790563587958e-05,
+      "loss": 0.9255,
+      "step": 58
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.8342974146362397e-05,
+      "loss": 0.8816,
+      "step": 59
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.8278019810666295e-05,
+      "loss": 0.8863,
+      "step": 60
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.8211936415778986e-05,
+      "loss": 0.9121,
+      "step": 61
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.8144732974974902e-05,
+      "loss": 0.8759,
+      "step": 62
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.8076418654294267e-05,
+      "loss": 0.9008,
+      "step": 63
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.80070027712929e-05,
+      "loss": 0.9176,
+      "step": 64
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.793649479377137e-05,
+      "loss": 0.8681,
+      "step": 65
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.7864904338483676e-05,
+      "loss": 0.915,
+      "step": 66
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.779224116982558e-05,
+      "loss": 0.8937,
+      "step": 67
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.7718515198502816e-05,
+      "loss": 0.8827,
+      "step": 68
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.7643736480179353e-05,
+      "loss": 0.8496,
+      "step": 69
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.7567915214105883e-05,
+      "loss": 0.9188,
+      "step": 70
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.7491061741728703e-05,
+      "loss": 0.8845,
+      "step": 71
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.741318654527923e-05,
+      "loss": 0.863,
+      "step": 72
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.7334300246344318e-05,
+      "loss": 0.9035,
+      "step": 73
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.725441360441752e-05,
+      "loss": 0.8462,
+      "step": 74
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.7173537515431612e-05,
+      "loss": 0.8881,
+      "step": 75
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.7091683010272447e-05,
+      "loss": 0.8944,
+      "step": 76
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.700886125327443e-05,
+      "loss": 0.9079,
+      "step": 77
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.692508354069779e-05,
+      "loss": 0.8947,
+      "step": 78
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.684036129918786e-05,
+      "loss": 0.8519,
+      "step": 79
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.6754706084216556e-05,
+      "loss": 0.9102,
+      "step": 80
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.6668129578506315e-05,
+      "loss": 0.9016,
+      "step": 81
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.658064359043664e-05,
+      "loss": 0.9281,
+      "step": 82
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.6492260052433554e-05,
+      "loss": 0.9072,
+      "step": 83
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.6402991019342073e-05,
+      "loss": 0.9166,
+      "step": 84
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.631284866678205e-05,
+      "loss": 0.8633,
+      "step": 85
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.6221845289487493e-05,
+      "loss": 0.9126,
+      "step": 86
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.6129993299629652e-05,
+      "loss": 0.9278,
+      "step": 87
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.6037305225124122e-05,
+      "loss": 0.895,
+      "step": 88
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.5943793707922086e-05,
+      "loss": 0.909,
+      "step": 89
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.5849471502286088e-05,
+      "loss": 0.8707,
+      "step": 90
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.5754351473050434e-05,
+      "loss": 0.9124,
+      "step": 91
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.5658446593866517e-05,
+      "loss": 0.9002,
+      "step": 92
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.5561769945433326e-05,
+      "loss": 0.8842,
+      "step": 93
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.5464334713713312e-05,
+      "loss": 0.8894,
+      "step": 94
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.5366154188133962e-05,
+      "loss": 0.9092,
+      "step": 95
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 1.526724175977518e-05,
+      "loss": 0.907,
+      "step": 96
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 1.5167610919542885e-05,
+      "loss": 0.975,
+      "step": 97
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 1.5067275256328913e-05,
+      "loss": 0.919,
+      "step": 98
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.4966248455157622e-05,
+      "loss": 0.8805,
+      "step": 99
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.4864544295319357e-05,
+      "loss": 0.8917,
+      "step": 100
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.4762176648491052e-05,
+      "loss": 0.8866,
+      "step": 101
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.4659159476844231e-05,
+      "loss": 0.8638,
+      "step": 102
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.4555506831140698e-05,
+      "loss": 0.8955,
+      "step": 103
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.445123284881609e-05,
+      "loss": 0.9303,
+      "step": 104
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.4346351752051663e-05,
+      "loss": 0.8765,
+      "step": 105
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.4240877845834473e-05,
+      "loss": 0.8824,
+      "step": 106
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.4134825516006307e-05,
+      "loss": 0.8933,
+      "step": 107
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.4028209227301534e-05,
+      "loss": 0.8633,
+      "step": 108
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.392104352137426e-05,
+      "loss": 0.8933,
+      "step": 109
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.3813343014814926e-05,
+      "loss": 0.8914,
+      "step": 110
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.3705122397156727e-05,
+      "loss": 0.8869,
+      "step": 111
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.359639642887208e-05,
+      "loss": 0.8688,
+      "step": 112
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.3487179939359394e-05,
+      "loss": 0.9112,
+      "step": 113
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.3377487824920459e-05,
+      "loss": 0.8622,
+      "step": 114
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.32673350467287e-05,
+      "loss": 0.9195,
+      "step": 115
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.3156736628788585e-05,
+      "loss": 0.9125,
+      "step": 116
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.304570765588648e-05,
+      "loss": 0.8975,
+      "step": 117
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.293426327153317e-05,
+      "loss": 0.8466,
+      "step": 118
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1.2822418675898428e-05,
+      "loss": 0.9109,
+      "step": 119
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1.2710189123737804e-05,
+      "loss": 0.8949,
+      "step": 120
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.2597589922312009e-05,
+      "loss": 0.8578,
+      "step": 121
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.2484636429299113e-05,
+      "loss": 0.8887,
+      "step": 122
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.2371344050699872e-05,
+      "loss": 0.8935,
+      "step": 123
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.2257728238736468e-05,
+      "loss": 0.8413,
+      "step": 124
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.2143804489744941e-05,
+      "loss": 0.8918,
+      "step": 125
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.2029588342061623e-05,
+      "loss": 0.8996,
+      "step": 126
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.1915095373903789e-05,
+      "loss": 0.8716,
+      "step": 127
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.1800341201244954e-05,
+      "loss": 0.8695,
+      "step": 128
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.1685341475684935e-05,
+      "loss": 0.9327,
+      "step": 129
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.15701118823151e-05,
+      "loss": 0.8849,
+      "step": 130
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.1454668137579059e-05,
+      "loss": 0.8831,
+      "step": 131
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.1339025987129033e-05,
+      "loss": 0.8848,
+      "step": 132
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.1223201203678289e-05,
+      "loss": 0.8591,
+      "step": 133
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.1107209584849845e-05,
+      "loss": 0.8592,
+      "step": 134
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.0991066951021802e-05,
+      "loss": 0.8658,
+      "step": 135
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.0874789143169569e-05,
+      "loss": 0.9167,
+      "step": 136
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.0758392020705258e-05,
+      "loss": 0.8967,
+      "step": 137
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.0641891459314598e-05,
+      "loss": 0.9196,
+      "step": 138
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.0525303348791599e-05,
+      "loss": 0.8851,
+      "step": 139
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.0408643590871312e-05,
+      "loss": 0.8484,
+      "step": 140
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1.029192809706095e-05,
+      "loss": 0.9097,
+      "step": 141
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1.017517278646968e-05,
+      "loss": 0.9015,
+      "step": 142
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1.0058393583637376e-05,
+      "loss": 0.8429,
+      "step": 143
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 9.94160641636263e-06,
+      "loss": 0.8631,
+      "step": 144
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 9.824827213530323e-06,
+      "loss": 0.8986,
+      "step": 145
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 9.708071902939053e-06,
+      "loss": 0.897,
+      "step": 146
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 9.591356409128691e-06,
+      "loss": 0.8773,
+      "step": 147
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 9.474696651208406e-06,
+      "loss": 0.8805,
+      "step": 148
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 9.358108540685406e-06,
+      "loss": 0.8887,
+      "step": 149
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 9.241607979294745e-06,
+      "loss": 0.8689,
+      "step": 150
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 9.125210856830433e-06,
+      "loss": 0.8726,
+      "step": 151
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 9.0089330489782e-06,
+      "loss": 0.9044,
+      "step": 152
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 8.892790415150161e-06,
+      "loss": 0.8903,
+      "step": 153
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 8.776798796321715e-06,
+      "loss": 0.8569,
+      "step": 154
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 8.66097401287097e-06,
+      "loss": 0.8636,
+      "step": 155
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 8.545331862420945e-06,
+      "loss": 0.9027,
+      "step": 156
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 8.429888117684904e-06,
+      "loss": 0.8581,
+      "step": 157
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 8.314658524315068e-06,
+      "loss": 0.8882,
+      "step": 158
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 8.199658798755048e-06,
+      "loss": 0.8915,
+      "step": 159
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 8.084904626096211e-06,
+      "loss": 0.9091,
+      "step": 160
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 7.970411657938382e-06,
+      "loss": 0.8708,
+      "step": 161
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 7.856195510255059e-06,
+      "loss": 0.8687,
+      "step": 162
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 7.742271761263537e-06,
+      "loss": 0.8653,
+      "step": 163
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 7.628655949300133e-06,
+      "loss": 0.8938,
+      "step": 164
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 7.51536357070089e-06,
+      "loss": 0.8943,
+      "step": 165
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 7.402410077687994e-06,
+      "loss": 0.871,
+      "step": 166
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 7.2898108762622e-06,
+      "loss": 0.8611,
+      "step": 167
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 7.1775813241015755e-06,
+      "loss": 0.9223,
+      "step": 168
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 7.065736728466832e-06,
+      "loss": 0.8372,
+      "step": 169
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 6.9542923441135226e-06,
+      "loss": 0.8493,
+      "step": 170
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 6.843263371211415e-06,
+      "loss": 0.8764,
+      "step": 171
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 6.732664953271305e-06,
+      "loss": 0.8427,
+      "step": 172
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 6.622512175079543e-06,
+      "loss": 0.9206,
+      "step": 173
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 6.512820060640608e-06,
+      "loss": 0.9046,
+      "step": 174
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 6.403603571127921e-06,
+      "loss": 0.9025,
+      "step": 175
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 6.294877602843276e-06,
+      "loss": 0.8967,
+      "step": 176
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 6.186656985185078e-06,
+      "loss": 0.8848,
+      "step": 177
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 6.078956478625743e-06,
+      "loss": 0.906,
+      "step": 178
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 5.971790772698467e-06,
+      "loss": 0.918,
+      "step": 179
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 5.865174483993697e-06,
+      "loss": 0.893,
+      "step": 180
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 5.759122154165528e-06,
+      "loss": 0.9007,
+      "step": 181
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 5.653648247948342e-06,
+      "loss": 0.8744,
+      "step": 182
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 5.548767151183912e-06,
+      "loss": 0.917,
+      "step": 183
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 5.444493168859304e-06,
+      "loss": 0.8773,
+      "step": 184
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 5.340840523155769e-06,
+      "loss": 0.9227,
+      "step": 185
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 5.237823351508953e-06,
+      "loss": 0.8372,
+      "step": 186
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 5.135455704680646e-06,
+      "loss": 0.9047,
+      "step": 187
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 5.03375154484238e-06,
+      "loss": 0.8698,
+      "step": 188
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 4.932724743671089e-06,
+      "loss": 0.8616,
+      "step": 189
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 4.832389080457118e-06,
+      "loss": 0.9023,
+      "step": 190
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 4.732758240224819e-06,
+      "loss": 0.8613,
+      "step": 191
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 4.633845811866044e-06,
+      "loss": 0.8543,
+      "step": 192
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 4.535665286286691e-06,
+      "loss": 0.9005,
+      "step": 193
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 4.438230054566678e-06,
+      "loss": 0.9237,
+      "step": 194
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 4.34155340613348e-06,
+      "loss": 0.908,
+      "step": 195
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 4.245648526949568e-06,
+      "loss": 0.8667,
+      "step": 196
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 4.150528497713911e-06,
+      "loss": 0.8766,
+      "step": 197
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 4.056206292077916e-06,
+      "loss": 0.8879,
+      "step": 198
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 3.96269477487588e-06,
+      "loss": 0.8712,
+      "step": 199
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 3.870006700370348e-06,
+      "loss": 0.8465,
+      "step": 200
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 3.778154710512513e-06,
+      "loss": 0.9037,
+      "step": 201
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 3.687151333217952e-06,
+      "loss": 0.8617,
+      "step": 202
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 3.597008980657929e-06,
+      "loss": 0.8778,
+      "step": 203
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 3.5077399475664474e-06,
+      "loss": 0.8629,
+      "step": 204
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 3.419356409563361e-06,
+      "loss": 0.8194,
+      "step": 205
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 3.331870421493688e-06,
+      "loss": 0.8806,
+      "step": 206
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 3.245293915783444e-06,
+      "loss": 0.8949,
+      "step": 207
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 3.1596387008121386e-06,
+      "loss": 0.8451,
+      "step": 208
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 3.074916459302211e-06,
+      "loss": 0.8941,
+      "step": 209
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 2.9911387467255737e-06,
+      "loss": 0.8887,
+      "step": 210
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 2.9083169897275554e-06,
+      "loss": 0.8624,
+      "step": 211
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 2.82646248456839e-06,
+      "loss": 0.8769,
+      "step": 212
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 2.745586395582481e-06,
+      "loss": 0.87,
+      "step": 213
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 2.665699753655684e-06,
+      "loss": 0.8524,
+      "step": 214
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 2.586813454720771e-06,
+      "loss": 0.8492,
+      "step": 215
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 2.5089382582712995e-06,
+      "loss": 0.8835,
+      "step": 216
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 2.4320847858941167e-06,
+      "loss": 0.8711,
+      "step": 217
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 2.3562635198206476e-06,
+      "loss": 0.8955,
+      "step": 218
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 2.281484801497186e-06,
+      "loss": 0.8767,
+      "step": 219
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 2.2077588301744234e-06,
+      "loss": 0.8499,
+      "step": 220
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 2.1350956615163254e-06,
+      "loss": 0.835,
+      "step": 221
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 2.0635052062286323e-06,
+      "loss": 0.8427,
+      "step": 222
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 1.992997228707103e-06,
+      "loss": 0.8295,
+      "step": 223
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1.923581345705736e-06,
+      "loss": 0.8669,
+      "step": 224
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1.8552670250251003e-06,
+      "loss": 0.8733,
+      "step": 225
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1.788063584221017e-06,
+      "loss": 0.862,
+      "step": 226
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.7219801893337073e-06,
+      "loss": 0.8726,
+      "step": 227
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.6570258536376083e-06,
+      "loss": 0.8486,
+      "step": 228
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.5932094364120453e-06,
+      "loss": 0.8599,
+      "step": 229
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1.5305396417328755e-06,
+      "loss": 0.8423,
+      "step": 230
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1.469025017285335e-06,
+      "loss": 0.8835,
+      "step": 231
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1.4086739531981886e-06,
+      "loss": 0.9035,
+      "step": 232
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.3494946808993804e-06,
+      "loss": 0.8399,
+      "step": 233
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.291495271993337e-06,
+      "loss": 0.8797,
+      "step": 234
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.234683637160048e-06,
+      "loss": 0.8579,
+      "step": 235
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.1790675250761263e-06,
+      "loss": 0.8749,
+      "step": 236
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.124654521357934e-06,
+      "loss": 0.8661,
+      "step": 237
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 1.0714520475269653e-06,
+      "loss": 0.9152,
+      "step": 238
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 1.0194673599976134e-06,
+      "loss": 0.8602,
+      "step": 239
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 9.687075490874376e-07,
+      "loss": 0.8802,
+      "step": 240
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 9.191795380501133e-07,
+      "loss": 0.8678,
+      "step": 241
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 8.708900821311405e-07,
+      "loss": 0.8902,
+      "step": 242
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 8.238457676464873e-07,
+      "loss": 0.8982,
+      "step": 243
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 7.780530110842566e-07,
+      "loss": 0.8694,
+      "step": 244
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 7.335180582295387e-07,
+      "loss": 0.8896,
+      "step": 245
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 6.902469833125236e-07,
+      "loss": 0.8869,
+      "step": 246
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 6.482456881800248e-07,
+      "loss": 0.9181,
+      "step": 247
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 6.075199014905153e-07,
+      "loss": 0.814,
+      "step": 248
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 5.680751779327742e-07,
+      "loss": 0.885,
+      "step": 249
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 5.299168974682789e-07,
+      "loss": 0.8642,
+      "step": 250
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 4.930502645974122e-07,
+      "loss": 0.8697,
+      "step": 251
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 4.574803076496148e-07,
+      "loss": 0.8614,
+      "step": 252
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 4.232118780975447e-07,
+      "loss": 0.8606,
+      "step": 253
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 3.9024964989539227e-07,
+      "loss": 0.849,
+      "step": 254
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 3.585981188413767e-07,
+      "loss": 0.8665,
+      "step": 255
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 3.2826160196455124e-07,
+      "loss": 0.8916,
+      "step": 256
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 2.9924423693600157e-07,
+      "loss": 0.846,
+      "step": 257
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 2.7154998150449643e-07,
+      "loss": 0.8738,
+      "step": 258
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 2.4518261295667255e-07,
+      "loss": 0.8699,
+      "step": 259
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 2.201457276018526e-07,
+      "loss": 0.8869,
+      "step": 260
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1.9644274028152944e-07,
+      "loss": 0.8696,
+      "step": 261
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1.740768839036111e-07,
+      "loss": 0.8931,
+      "step": 262
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.5305120900146908e-07,
+      "loss": 0.887,
+      "step": 263
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.3336858331787993e-07,
+      "loss": 0.8705,
+      "step": 264
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.1503169141388049e-07,
+      "loss": 0.8813,
+      "step": 265
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 9.804303430261175e-08,
+      "loss": 0.8476,
+      "step": 266
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 8.240492910820407e-08,
+      "loss": 0.8973,
+      "step": 267
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 6.811950874973994e-08,
+      "loss": 0.8578,
+      "step": 268
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 5.518872165033329e-08,
+      "loss": 0.8851,
+      "step": 269
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 4.361433147138772e-08,
+      "loss": 0.8397,
+      "step": 270
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 3.339791687203997e-08,
+      "loss": 0.8525,
+      "step": 271
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 2.4540871293845526e-08,
+      "loss": 0.8295,
+      "step": 272
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 1.7044402770725055e-08,
+      "loss": 0.8433,
+      "step": 273
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 1.0909533764194013e-08,
+      "loss": 0.8829,
+      "step": 274
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 6.137101023910852e-09,
+      "loss": 0.8685,
+      "step": 275
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 2.7277554735449797e-09,
+      "loss": 0.8855,
+      "step": 276
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 6.819621220033323e-10,
+      "loss": 0.8618,
+      "step": 277
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.0,
+      "loss": 0.8748,
+      "step": 278
+    },
+    {
+      "epoch": 1.0,
+      "step": 278,
+      "total_flos": 4.5714113651172966e+17,
+      "train_loss": 0.8846922922048638,
+      "train_runtime": 5115.5251,
+      "train_samples_per_second": 17.336,
+      "train_steps_per_second": 0.054
+    }
+  ],
+  "max_steps": 278,
+  "num_train_epochs": 1,
+  "total_flos": 4.5714113651172966e+17,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f87c714bc8b5d50c41ce6ed079057d6a77cc7a66dbe670c27b727f18a27a1aa1
+size 4155