commit 0f594e04b7c55eff0480c6588b9843ef751b82a6 Author: ModelHub XC Date: Mon Jun 8 08:46:14 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mncai/chatdoctor Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..5e8b411 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,53 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text + + +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text + +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zstandard filter=lfs diff=lfs merge=lfs -text +*.tfevents* filter=lfs diff=lfs merge=lfs -text +*.db* filter=lfs diff=lfs merge=lfs -text +*.ark* filter=lfs diff=lfs merge=lfs -text +**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text +**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text +**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.gguf* filter=lfs diff=lfs merge=lfs -text +*.ggml filter=lfs diff=lfs merge=lfs -text +*.llamafile* filter=lfs diff=lfs merge=lfs -text +*.pt2 filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text + +pytorch_model-00002-of-00003.bin filter=lfs diff=lfs merge=lfs -text +pytorch_model-00001-of-00003.bin filter=lfs diff=lfs merge=lfs -text +tokenizer.model filter=lfs diff=lfs merge=lfs -text +training_args.bin filter=lfs diff=lfs merge=lfs -text +pytorch_model-00003-of-00003.bin filter=lfs diff=lfs merge=lfs -text \ No newline at end of file diff --git a/README.md b/README.md new file mode 100644 index 0000000..154df82 --- /dev/null +++ b/README.md @@ -0,0 +1,3 @@ +--- +license: apache-2.0 +--- diff --git a/added_tokens.json b/added_tokens.json new file mode 100644 index 0000000..e41416d --- /dev/null +++ b/added_tokens.json @@ -0,0 +1,3 @@ +{ + "[PAD]": 32000 +} diff --git a/config.json b/config.json new file mode 100644 index 0000000..068b2cc --- /dev/null +++ b/config.json @@ -0,0 +1,23 @@ +{ + "_name_or_path": "./weights/llama-7b", + "architectures": [ + "LLaMAForCausalLM" + ], + "bos_token_id": 0, + "eos_token_id": 1, + "hidden_act": "silu", + "hidden_size": 4096, + "initializer_range": 0.02, + "intermediate_size": 11008, + "max_sequence_length": 2048, + "model_type": "llama", + "num_attention_heads": 32, + "num_hidden_layers": 32, + "pad_token_id": -1, + "rms_norm_eps": 1e-06, + "tie_word_embeddings": false, + "torch_dtype": "float32", + "transformers_version": "4.27.0.dev0", + "use_cache": true, + "vocab_size": 32001 +} diff --git a/configuration.json b/configuration.json new file mode 100644 index 0000000..bbeeda1 --- /dev/null +++ b/configuration.json @@ -0,0 +1 @@ +{"framework": "pytorch", "task": "text-generation", "allow_remote": true} \ No newline at end of file diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..92540f6 --- /dev/null +++ b/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": "4.27.0.dev0" +} diff --git a/pytorch_model-00001-of-00003.bin b/pytorch_model-00001-of-00003.bin new file mode 100644 index 0000000..6f65be8 --- /dev/null +++ b/pytorch_model-00001-of-00003.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:46100c50cae947e4b731ffa4bd7867da8926bb371d7399070ae1c4f5a5cc1825 +size 9878005970 diff --git a/pytorch_model-00002-of-00003.bin b/pytorch_model-00002-of-00003.bin new file mode 100644 index 0000000..57aa3b1 --- /dev/null +++ b/pytorch_model-00002-of-00003.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:26206cb9d43194d2032e081e053c89b1b04c700f72b9831746c0bf92a92b16df +size 9894801014 diff --git a/pytorch_model-00003-of-00003.bin b/pytorch_model-00003-of-00003.bin new file mode 100644 index 0000000..e2d3f31 --- /dev/null +++ b/pytorch_model-00003-of-00003.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dc3d3be3e9fc40da4a0678b351e0beb91aa02c7ccab60efdad6fc90fd86b92a4 +size 7181007033 diff --git a/pytorch_model.bin.index.json b/pytorch_model.bin.index.json new file mode 100644 index 0000000..e5e614a --- /dev/null +++ b/pytorch_model.bin.index.json @@ -0,0 +1,330 @@ +{ + "metadata": { + "total_size": 26953699328 + }, + "weight_map": { + "lm_head.weight": "pytorch_model-00003-of-00003.bin", + "model.embed_tokens.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.0.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin", + "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.1.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin", + "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.10.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.10.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.10.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin", + "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.11.input_layernorm.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.11.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.11.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.11.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin", + "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.12.input_layernorm.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.12.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.12.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.12.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin", + "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.13.input_layernorm.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.13.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.13.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.13.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin", + "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.14.input_layernorm.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.14.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.14.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.14.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin", + "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.15.input_layernorm.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.15.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.15.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.15.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin", + "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.16.input_layernorm.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.16.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.16.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.16.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin", + "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.17.input_layernorm.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.17.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.17.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.17.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin", + "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.18.input_layernorm.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.18.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.18.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.18.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin", + "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.19.input_layernorm.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.19.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.19.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.19.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin", + "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.2.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin", + "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.20.input_layernorm.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.20.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.20.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.20.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin", + "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.21.input_layernorm.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.21.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.21.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.21.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin", + "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.22.input_layernorm.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.22.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.22.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.22.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin", + "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.23.input_layernorm.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.23.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.23.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.23.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin", + "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.24.input_layernorm.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.24.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.24.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.24.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin", + "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.25.input_layernorm.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.25.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.25.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.25.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin", + "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.26.input_layernorm.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.26.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.26.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.26.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin", + "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.27.input_layernorm.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.27.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.27.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.27.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin", + "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.28.input_layernorm.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.28.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.28.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.28.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin", + "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.29.input_layernorm.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.29.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.29.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.29.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin", + "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.3.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin", + "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.30.input_layernorm.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.30.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.30.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.30.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin", + "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.31.input_layernorm.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.31.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.31.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.31.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin", + "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.4.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin", + "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.5.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin", + "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.6.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin", + "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.7.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin", + "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.8.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.8.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin", + "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.9.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.9.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.9.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin", + "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.norm.weight": "pytorch_model-00003-of-00003.bin" + } +} diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..318f913 --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,6 @@ +{ + "bos_token": "", + "eos_token": "", + "pad_token": "[PAD]", + "unk_token": "" +} diff --git a/tokenizer.model b/tokenizer.model new file mode 100644 index 0000000..6c00c74 --- /dev/null +++ b/tokenizer.model @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347 +size 499723 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..44597bf --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,9 @@ +{ + "bos_token": "", + "eos_token": "", + "model_max_length": 512, + "padding_side": "right", + "special_tokens_map_file": "./weights/llama-7b/special_tokens_map.json", + "tokenizer_class": "LlamaTokenizer", + "unk_token": "" +} diff --git a/trainer_state.json b/trainer_state.json new file mode 100644 index 0000000..b47f631 --- /dev/null +++ b/trainer_state.json @@ -0,0 +1,3679 @@ +{ + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 2.998769987699877, + "global_step": 609, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.0, + "learning_rate": 1.0526315789473685e-06, + "loss": 1.5397, + "step": 1 + }, + { + "epoch": 0.01, + "learning_rate": 2.105263157894737e-06, + "loss": 1.4949, + "step": 2 + }, + { + "epoch": 0.01, + "learning_rate": 3.157894736842105e-06, + "loss": 1.3147, + "step": 3 + }, + { + "epoch": 0.02, + "learning_rate": 4.210526315789474e-06, + "loss": 1.2866, + "step": 4 + }, + { + "epoch": 0.02, + "learning_rate": 5.263157894736842e-06, + "loss": 1.2223, + "step": 5 + }, + { + "epoch": 0.03, + "learning_rate": 6.31578947368421e-06, + "loss": 1.2316, + "step": 6 + }, + { + "epoch": 0.03, + "learning_rate": 7.368421052631579e-06, + "loss": 1.1728, + "step": 7 + }, + { + "epoch": 0.04, + "learning_rate": 8.421052631578948e-06, + "loss": 1.1196, + "step": 8 + }, + { + "epoch": 0.04, + "learning_rate": 9.473684210526315e-06, + "loss": 1.1286, + "step": 9 + }, + { + "epoch": 0.05, + "learning_rate": 1.0526315789473684e-05, + "loss": 1.1144, + "step": 10 + }, + { + "epoch": 0.05, + "learning_rate": 1.1578947368421053e-05, + "loss": 1.1363, + "step": 11 + }, + { + "epoch": 0.06, + "learning_rate": 1.263157894736842e-05, + "loss": 1.145, + "step": 12 + }, + { + "epoch": 0.06, + "learning_rate": 1.3684210526315791e-05, + "loss": 1.1534, + "step": 13 + }, + { + "epoch": 0.07, + "learning_rate": 1.4736842105263159e-05, + "loss": 1.1545, + "step": 14 + }, + { + "epoch": 0.07, + "learning_rate": 1.578947368421053e-05, + "loss": 1.1134, + "step": 15 + }, + { + "epoch": 0.08, + "learning_rate": 1.6842105263157896e-05, + "loss": 1.1728, + "step": 16 + }, + { + "epoch": 0.08, + "learning_rate": 1.7894736842105264e-05, + "loss": 1.066, + "step": 17 + }, + { + "epoch": 0.09, + "learning_rate": 1.894736842105263e-05, + "loss": 1.0792, + "step": 18 + }, + { + "epoch": 0.09, + "learning_rate": 2e-05, + "loss": 1.1199, + "step": 19 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999858236410775e-05, + "loss": 1.0901, + "step": 20 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999432949662483e-05, + "loss": 1.104, + "step": 21 + }, + { + "epoch": 0.11, + "learning_rate": 1.9998724151813157e-05, + "loss": 1.0508, + "step": 22 + }, + { + "epoch": 0.11, + "learning_rate": 1.9997731862959143e-05, + "loss": 1.0277, + "step": 23 + }, + { + "epoch": 0.12, + "learning_rate": 1.999645611123453e-05, + "loss": 1.1162, + "step": 24 + }, + { + "epoch": 0.12, + "learning_rate": 1.999489693281034e-05, + "loss": 1.0931, + "step": 25 + }, + { + "epoch": 0.13, + "learning_rate": 1.9993054371893526e-05, + "loss": 1.0628, + "step": 26 + }, + { + "epoch": 0.13, + "learning_rate": 1.9990928480725694e-05, + "loss": 1.1253, + "step": 27 + }, + { + "epoch": 0.14, + "learning_rate": 1.9988519319581637e-05, + "loss": 1.0444, + "step": 28 + }, + { + "epoch": 0.14, + "learning_rate": 1.998582695676762e-05, + "loss": 1.0667, + "step": 29 + }, + { + "epoch": 0.15, + "learning_rate": 1.998285146861945e-05, + "loss": 1.1212, + "step": 30 + }, + { + "epoch": 0.15, + "learning_rate": 1.99795929395003e-05, + "loss": 1.0649, + "step": 31 + }, + { + "epoch": 0.16, + "learning_rate": 1.997605146179833e-05, + "loss": 1.0489, + "step": 32 + }, + { + "epoch": 0.16, + "learning_rate": 1.997222713592405e-05, + "loss": 1.1362, + "step": 33 + }, + { + "epoch": 0.17, + "learning_rate": 1.9968120070307503e-05, + "loss": 1.0922, + "step": 34 + }, + { + "epoch": 0.17, + "learning_rate": 1.9963730381395154e-05, + "loss": 1.0754, + "step": 35 + }, + { + "epoch": 0.18, + "learning_rate": 1.9959058193646618e-05, + "loss": 1.1088, + "step": 36 + }, + { + "epoch": 0.18, + "learning_rate": 1.9954103639531116e-05, + "loss": 1.068, + "step": 37 + }, + { + "epoch": 0.19, + "learning_rate": 1.9948866859523717e-05, + "loss": 1.0917, + "step": 38 + }, + { + "epoch": 0.19, + "learning_rate": 1.9943348002101374e-05, + "loss": 1.0667, + "step": 39 + }, + { + "epoch": 0.2, + "learning_rate": 1.993754722373869e-05, + "loss": 1.0814, + "step": 40 + }, + { + "epoch": 0.2, + "learning_rate": 1.9931464688903502e-05, + "loss": 1.1246, + "step": 41 + }, + { + "epoch": 0.21, + "learning_rate": 1.9925100570052194e-05, + "loss": 1.1188, + "step": 42 + }, + { + "epoch": 0.21, + "learning_rate": 1.9918455047624847e-05, + "loss": 1.0822, + "step": 43 + }, + { + "epoch": 0.22, + "learning_rate": 1.9911528310040073e-05, + "loss": 1.0676, + "step": 44 + }, + { + "epoch": 0.22, + "learning_rate": 1.990432055368971e-05, + "loss": 1.1395, + "step": 45 + }, + { + "epoch": 0.23, + "learning_rate": 1.989683198293324e-05, + "loss": 1.071, + "step": 46 + }, + { + "epoch": 0.23, + "learning_rate": 1.9889062810092002e-05, + "loss": 1.1088, + "step": 47 + }, + { + "epoch": 0.24, + "learning_rate": 1.9881013255443152e-05, + "loss": 1.0914, + "step": 48 + }, + { + "epoch": 0.24, + "learning_rate": 1.9872683547213446e-05, + "loss": 1.0789, + "step": 49 + }, + { + "epoch": 0.25, + "learning_rate": 1.9864073921572756e-05, + "loss": 1.0881, + "step": 50 + }, + { + "epoch": 0.25, + "learning_rate": 1.9855184622627362e-05, + "loss": 1.0448, + "step": 51 + }, + { + "epoch": 0.26, + "learning_rate": 1.9846015902413053e-05, + "loss": 1.1104, + "step": 52 + }, + { + "epoch": 0.26, + "learning_rate": 1.9836568020887963e-05, + "loss": 1.0214, + "step": 53 + }, + { + "epoch": 0.27, + "learning_rate": 1.982684124592521e-05, + "loss": 1.0767, + "step": 54 + }, + { + "epoch": 0.27, + "learning_rate": 1.9816835853305306e-05, + "loss": 1.0387, + "step": 55 + }, + { + "epoch": 0.28, + "learning_rate": 1.9806552126708322e-05, + "loss": 1.1356, + "step": 56 + }, + { + "epoch": 0.28, + "learning_rate": 1.9795990357705853e-05, + "loss": 1.0805, + "step": 57 + }, + { + "epoch": 0.29, + "learning_rate": 1.978515084575276e-05, + "loss": 1.0632, + "step": 58 + }, + { + "epoch": 0.29, + "learning_rate": 1.9774033898178668e-05, + "loss": 1.03, + "step": 59 + }, + { + "epoch": 0.3, + "learning_rate": 1.976263983017925e-05, + "loss": 1.0842, + "step": 60 + }, + { + "epoch": 0.3, + "learning_rate": 1.9750968964807305e-05, + "loss": 1.0856, + "step": 61 + }, + { + "epoch": 0.31, + "learning_rate": 1.9739021632963584e-05, + "loss": 1.0659, + "step": 62 + }, + { + "epoch": 0.31, + "learning_rate": 1.9726798173387417e-05, + "loss": 1.0767, + "step": 63 + }, + { + "epoch": 0.31, + "learning_rate": 1.97142989326471e-05, + "loss": 1.1169, + "step": 64 + }, + { + "epoch": 0.32, + "learning_rate": 1.9701524265130088e-05, + "loss": 1.0467, + "step": 65 + }, + { + "epoch": 0.32, + "learning_rate": 1.9688474533032916e-05, + "loss": 1.1104, + "step": 66 + }, + { + "epoch": 0.33, + "learning_rate": 1.9675150106350957e-05, + "loss": 1.0493, + "step": 67 + }, + { + "epoch": 0.33, + "learning_rate": 1.9661551362867926e-05, + "loss": 1.0514, + "step": 68 + }, + { + "epoch": 0.34, + "learning_rate": 1.9647678688145163e-05, + "loss": 1.0976, + "step": 69 + }, + { + "epoch": 0.34, + "learning_rate": 1.963353247551069e-05, + "loss": 1.089, + "step": 70 + }, + { + "epoch": 0.35, + "learning_rate": 1.9619113126048086e-05, + "loss": 1.071, + "step": 71 + }, + { + "epoch": 0.35, + "learning_rate": 1.96044210485851e-05, + "loss": 1.0939, + "step": 72 + }, + { + "epoch": 0.36, + "learning_rate": 1.958945665968206e-05, + "loss": 1.0728, + "step": 73 + }, + { + "epoch": 0.36, + "learning_rate": 1.9574220383620054e-05, + "loss": 1.0939, + "step": 74 + }, + { + "epoch": 0.37, + "learning_rate": 1.9558712652388932e-05, + "loss": 1.0701, + "step": 75 + }, + { + "epoch": 0.37, + "learning_rate": 1.954293390567501e-05, + "loss": 1.0396, + "step": 76 + }, + { + "epoch": 0.38, + "learning_rate": 1.9526884590848646e-05, + "loss": 1.0998, + "step": 77 + }, + { + "epoch": 0.38, + "learning_rate": 1.9510565162951538e-05, + "loss": 1.077, + "step": 78 + }, + { + "epoch": 0.39, + "learning_rate": 1.9493976084683814e-05, + "loss": 1.0443, + "step": 79 + }, + { + "epoch": 0.39, + "learning_rate": 1.9477117826390934e-05, + "loss": 1.1079, + "step": 80 + }, + { + "epoch": 0.4, + "learning_rate": 1.9459990866050337e-05, + "loss": 1.0613, + "step": 81 + }, + { + "epoch": 0.4, + "learning_rate": 1.9442595689257898e-05, + "loss": 1.0936, + "step": 82 + }, + { + "epoch": 0.41, + "learning_rate": 1.9424932789214158e-05, + "loss": 1.098, + "step": 83 + }, + { + "epoch": 0.41, + "learning_rate": 1.9407002666710334e-05, + "loss": 1.1072, + "step": 84 + }, + { + "epoch": 0.42, + "learning_rate": 1.9388805830114132e-05, + "loss": 1.0207, + "step": 85 + }, + { + "epoch": 0.42, + "learning_rate": 1.937034279535533e-05, + "loss": 1.059, + "step": 86 + }, + { + "epoch": 0.43, + "learning_rate": 1.9351614085911134e-05, + "loss": 1.0634, + "step": 87 + }, + { + "epoch": 0.43, + "learning_rate": 1.933262023279137e-05, + "loss": 1.0491, + "step": 88 + }, + { + "epoch": 0.44, + "learning_rate": 1.9313361774523387e-05, + "loss": 1.1106, + "step": 89 + }, + { + "epoch": 0.44, + "learning_rate": 1.929383925713682e-05, + "loss": 1.1024, + "step": 90 + }, + { + "epoch": 0.45, + "learning_rate": 1.92740532341481e-05, + "loss": 1.1535, + "step": 91 + }, + { + "epoch": 0.45, + "learning_rate": 1.925400426654475e-05, + "loss": 1.0945, + "step": 92 + }, + { + "epoch": 0.46, + "learning_rate": 1.9233692922769497e-05, + "loss": 1.0854, + "step": 93 + }, + { + "epoch": 0.46, + "learning_rate": 1.921311977870413e-05, + "loss": 1.1276, + "step": 94 + }, + { + "epoch": 0.47, + "learning_rate": 1.9192285417653208e-05, + "loss": 1.0584, + "step": 95 + }, + { + "epoch": 0.47, + "learning_rate": 1.917119043032749e-05, + "loss": 1.0818, + "step": 96 + }, + { + "epoch": 0.48, + "learning_rate": 1.9149835414827193e-05, + "loss": 1.0789, + "step": 97 + }, + { + "epoch": 0.48, + "learning_rate": 1.912822097662505e-05, + "loss": 1.0438, + "step": 98 + }, + { + "epoch": 0.49, + "learning_rate": 1.9106347728549134e-05, + "loss": 1.0522, + "step": 99 + }, + { + "epoch": 0.49, + "learning_rate": 1.908421629076547e-05, + "loss": 1.094, + "step": 100 + }, + { + "epoch": 0.5, + "learning_rate": 1.9061827290760466e-05, + "loss": 1.125, + "step": 101 + }, + { + "epoch": 0.5, + "learning_rate": 1.9039181363323128e-05, + "loss": 1.1126, + "step": 102 + }, + { + "epoch": 0.51, + "learning_rate": 1.9016279150527044e-05, + "loss": 1.0622, + "step": 103 + }, + { + "epoch": 0.51, + "learning_rate": 1.8993121301712194e-05, + "loss": 1.1275, + "step": 104 + }, + { + "epoch": 0.52, + "learning_rate": 1.896970847346653e-05, + "loss": 1.0682, + "step": 105 + }, + { + "epoch": 0.52, + "learning_rate": 1.8946041329607364e-05, + "loss": 1.0499, + "step": 106 + }, + { + "epoch": 0.53, + "learning_rate": 1.892212054116255e-05, + "loss": 1.1032, + "step": 107 + }, + { + "epoch": 0.53, + "learning_rate": 1.889794678635145e-05, + "loss": 1.064, + "step": 108 + }, + { + "epoch": 0.54, + "learning_rate": 1.8873520750565716e-05, + "loss": 1.058, + "step": 109 + }, + { + "epoch": 0.54, + "learning_rate": 1.884884312634985e-05, + "loss": 1.0842, + "step": 110 + }, + { + "epoch": 0.55, + "learning_rate": 1.8823914613381568e-05, + "loss": 1.138, + "step": 111 + }, + { + "epoch": 0.55, + "learning_rate": 1.8798735918451963e-05, + "loss": 1.0833, + "step": 112 + }, + { + "epoch": 0.56, + "learning_rate": 1.8773307755445468e-05, + "loss": 1.0569, + "step": 113 + }, + { + "epoch": 0.56, + "learning_rate": 1.874763084531961e-05, + "loss": 1.1064, + "step": 114 + }, + { + "epoch": 0.57, + "learning_rate": 1.872170591608459e-05, + "loss": 1.0578, + "step": 115 + }, + { + "epoch": 0.57, + "learning_rate": 1.86955337027826e-05, + "loss": 1.0709, + "step": 116 + }, + { + "epoch": 0.58, + "learning_rate": 1.866911494746702e-05, + "loss": 1.0952, + "step": 117 + }, + { + "epoch": 0.58, + "learning_rate": 1.8642450399181373e-05, + "loss": 1.1302, + "step": 118 + }, + { + "epoch": 0.59, + "learning_rate": 1.8615540813938063e-05, + "loss": 1.0602, + "step": 119 + }, + { + "epoch": 0.59, + "learning_rate": 1.8588386954696972e-05, + "loss": 1.0309, + "step": 120 + }, + { + "epoch": 0.6, + "learning_rate": 1.856098959134381e-05, + "loss": 1.0907, + "step": 121 + }, + { + "epoch": 0.6, + "learning_rate": 1.8533349500668295e-05, + "loss": 1.0744, + "step": 122 + }, + { + "epoch": 0.61, + "learning_rate": 1.850546746634211e-05, + "loss": 0.9984, + "step": 123 + }, + { + "epoch": 0.61, + "learning_rate": 1.8477344278896708e-05, + "loss": 1.1185, + "step": 124 + }, + { + "epoch": 0.62, + "learning_rate": 1.84489807357009e-05, + "loss": 1.1292, + "step": 125 + }, + { + "epoch": 0.62, + "learning_rate": 1.8420377640938204e-05, + "loss": 1.0726, + "step": 126 + }, + { + "epoch": 0.62, + "learning_rate": 1.839153580558411e-05, + "loss": 1.079, + "step": 127 + }, + { + "epoch": 0.63, + "learning_rate": 1.8362456047383032e-05, + "loss": 1.0656, + "step": 128 + }, + { + "epoch": 0.63, + "learning_rate": 1.833313919082515e-05, + "loss": 1.0485, + "step": 129 + }, + { + "epoch": 0.64, + "learning_rate": 1.8303586067123028e-05, + "loss": 1.0474, + "step": 130 + }, + { + "epoch": 0.64, + "learning_rate": 1.8273797514188043e-05, + "loss": 1.0556, + "step": 131 + }, + { + "epoch": 0.65, + "learning_rate": 1.824377437660663e-05, + "loss": 1.0481, + "step": 132 + }, + { + "epoch": 0.65, + "learning_rate": 1.821351750561634e-05, + "loss": 1.1042, + "step": 133 + }, + { + "epoch": 0.66, + "learning_rate": 1.818302775908169e-05, + "loss": 1.1081, + "step": 134 + }, + { + "epoch": 0.66, + "learning_rate": 1.8152306001469875e-05, + "loss": 1.0592, + "step": 135 + }, + { + "epoch": 0.67, + "learning_rate": 1.8121353103826213e-05, + "loss": 1.0699, + "step": 136 + }, + { + "epoch": 0.67, + "learning_rate": 1.8090169943749477e-05, + "loss": 1.1112, + "step": 137 + }, + { + "epoch": 0.68, + "learning_rate": 1.8058757405367003e-05, + "loss": 1.0817, + "step": 138 + }, + { + "epoch": 0.68, + "learning_rate": 1.8027116379309637e-05, + "loss": 1.0708, + "step": 139 + }, + { + "epoch": 0.69, + "learning_rate": 1.799524776268646e-05, + "loss": 1.0717, + "step": 140 + }, + { + "epoch": 0.69, + "learning_rate": 1.796315245905936e-05, + "loss": 1.1142, + "step": 141 + }, + { + "epoch": 0.7, + "learning_rate": 1.7930831378417437e-05, + "loss": 1.0944, + "step": 142 + }, + { + "epoch": 0.7, + "learning_rate": 1.7898285437151163e-05, + "loss": 1.0791, + "step": 143 + }, + { + "epoch": 0.71, + "learning_rate": 1.786551555802643e-05, + "loss": 1.0577, + "step": 144 + }, + { + "epoch": 0.71, + "learning_rate": 1.783252267015837e-05, + "loss": 1.0449, + "step": 145 + }, + { + "epoch": 0.72, + "learning_rate": 1.779930770898503e-05, + "loss": 1.0302, + "step": 146 + }, + { + "epoch": 0.72, + "learning_rate": 1.776587161624083e-05, + "loss": 1.0962, + "step": 147 + }, + { + "epoch": 0.73, + "learning_rate": 1.7732215339929874e-05, + "loss": 1.0763, + "step": 148 + }, + { + "epoch": 0.73, + "learning_rate": 1.7698339834299064e-05, + "loss": 1.0331, + "step": 149 + }, + { + "epoch": 0.74, + "learning_rate": 1.7664246059811058e-05, + "loss": 1.056, + "step": 150 + }, + { + "epoch": 0.74, + "learning_rate": 1.7629934983117025e-05, + "loss": 1.0365, + "step": 151 + }, + { + "epoch": 0.75, + "learning_rate": 1.759540757702924e-05, + "loss": 1.0676, + "step": 152 + }, + { + "epoch": 0.75, + "learning_rate": 1.7560664820493502e-05, + "loss": 1.0716, + "step": 153 + }, + { + "epoch": 0.76, + "learning_rate": 1.7525707698561383e-05, + "loss": 1.0745, + "step": 154 + }, + { + "epoch": 0.76, + "learning_rate": 1.7490537202362313e-05, + "loss": 1.0657, + "step": 155 + }, + { + "epoch": 0.77, + "learning_rate": 1.7455154329075427e-05, + "loss": 1.089, + "step": 156 + }, + { + "epoch": 0.77, + "learning_rate": 1.741956008190136e-05, + "loss": 1.1019, + "step": 157 + }, + { + "epoch": 0.78, + "learning_rate": 1.7383755470033756e-05, + "loss": 1.0849, + "step": 158 + }, + { + "epoch": 0.78, + "learning_rate": 1.7347741508630673e-05, + "loss": 1.0804, + "step": 159 + }, + { + "epoch": 0.79, + "learning_rate": 1.73115192187858e-05, + "loss": 1.0713, + "step": 160 + }, + { + "epoch": 0.79, + "learning_rate": 1.7275089627499493e-05, + "loss": 1.0767, + "step": 161 + }, + { + "epoch": 0.8, + "learning_rate": 1.7238453767649683e-05, + "loss": 1.1313, + "step": 162 + }, + { + "epoch": 0.8, + "learning_rate": 1.720161267796256e-05, + "loss": 1.0129, + "step": 163 + }, + { + "epoch": 0.81, + "learning_rate": 1.7164567402983153e-05, + "loss": 1.0909, + "step": 164 + }, + { + "epoch": 0.81, + "learning_rate": 1.7127318993045686e-05, + "loss": 1.1132, + "step": 165 + }, + { + "epoch": 0.82, + "learning_rate": 1.7089868504243816e-05, + "loss": 1.0205, + "step": 166 + }, + { + "epoch": 0.82, + "learning_rate": 1.705221699840069e-05, + "loss": 1.0696, + "step": 167 + }, + { + "epoch": 0.83, + "learning_rate": 1.701436554303882e-05, + "loss": 1.0497, + "step": 168 + }, + { + "epoch": 0.83, + "learning_rate": 1.6976315211349848e-05, + "loss": 1.0987, + "step": 169 + }, + { + "epoch": 0.84, + "learning_rate": 1.6938067082164093e-05, + "loss": 1.0228, + "step": 170 + }, + { + "epoch": 0.84, + "learning_rate": 1.6899622239919965e-05, + "loss": 1.0599, + "step": 171 + }, + { + "epoch": 0.85, + "learning_rate": 1.6860981774633228e-05, + "loss": 1.0491, + "step": 172 + }, + { + "epoch": 0.85, + "learning_rate": 1.6822146781866097e-05, + "loss": 1.0111, + "step": 173 + }, + { + "epoch": 0.86, + "learning_rate": 1.6783118362696162e-05, + "loss": 1.1352, + "step": 174 + }, + { + "epoch": 0.86, + "learning_rate": 1.6743897623685178e-05, + "loss": 1.109, + "step": 175 + }, + { + "epoch": 0.87, + "learning_rate": 1.6704485676847695e-05, + "loss": 1.0585, + "step": 176 + }, + { + "epoch": 0.87, + "learning_rate": 1.666488363961952e-05, + "loss": 1.0871, + "step": 177 + }, + { + "epoch": 0.88, + "learning_rate": 1.662509263482604e-05, + "loss": 1.0678, + "step": 178 + }, + { + "epoch": 0.88, + "learning_rate": 1.658511379065039e-05, + "loss": 1.0743, + "step": 179 + }, + { + "epoch": 0.89, + "learning_rate": 1.6544948240601453e-05, + "loss": 1.0745, + "step": 180 + }, + { + "epoch": 0.89, + "learning_rate": 1.6504597123481737e-05, + "loss": 1.056, + "step": 181 + }, + { + "epoch": 0.9, + "learning_rate": 1.6464061583355088e-05, + "loss": 1.0329, + "step": 182 + }, + { + "epoch": 0.9, + "learning_rate": 1.6423342769514227e-05, + "loss": 1.1175, + "step": 183 + }, + { + "epoch": 0.91, + "learning_rate": 1.6382441836448203e-05, + "loss": 1.0953, + "step": 184 + }, + { + "epoch": 0.91, + "learning_rate": 1.6341359943809626e-05, + "loss": 1.0879, + "step": 185 + }, + { + "epoch": 0.92, + "learning_rate": 1.6300098256381807e-05, + "loss": 1.0804, + "step": 186 + }, + { + "epoch": 0.92, + "learning_rate": 1.625865794404573e-05, + "loss": 1.0758, + "step": 187 + }, + { + "epoch": 0.92, + "learning_rate": 1.621704018174688e-05, + "loss": 1.0341, + "step": 188 + }, + { + "epoch": 0.93, + "learning_rate": 1.617524614946192e-05, + "loss": 1.0104, + "step": 189 + }, + { + "epoch": 0.93, + "learning_rate": 1.6133277032165264e-05, + "loss": 1.0853, + "step": 190 + }, + { + "epoch": 0.94, + "learning_rate": 1.6091134019795447e-05, + "loss": 1.0603, + "step": 191 + }, + { + "epoch": 0.94, + "learning_rate": 1.604881830722141e-05, + "loss": 1.0482, + "step": 192 + }, + { + "epoch": 0.95, + "learning_rate": 1.600633109420861e-05, + "loss": 1.1092, + "step": 193 + }, + { + "epoch": 0.95, + "learning_rate": 1.5963673585385016e-05, + "loss": 1.099, + "step": 194 + }, + { + "epoch": 0.96, + "learning_rate": 1.5920846990206934e-05, + "loss": 1.0475, + "step": 195 + }, + { + "epoch": 0.96, + "learning_rate": 1.5877852522924733e-05, + "loss": 1.0404, + "step": 196 + }, + { + "epoch": 0.97, + "learning_rate": 1.5834691402548415e-05, + "loss": 1.0965, + "step": 197 + }, + { + "epoch": 0.97, + "learning_rate": 1.5791364852813047e-05, + "loss": 1.091, + "step": 198 + }, + { + "epoch": 0.98, + "learning_rate": 1.5747874102144073e-05, + "loss": 1.1011, + "step": 199 + }, + { + "epoch": 0.98, + "learning_rate": 1.5704220383622464e-05, + "loss": 1.0393, + "step": 200 + }, + { + "epoch": 0.99, + "learning_rate": 1.5660404934949798e-05, + "loss": 1.073, + "step": 201 + }, + { + "epoch": 0.99, + "learning_rate": 1.5616428998413122e-05, + "loss": 1.0817, + "step": 202 + }, + { + "epoch": 1.0, + "learning_rate": 1.5572293820849754e-05, + "loss": 1.1357, + "step": 203 + }, + { + "epoch": 1.0, + "learning_rate": 1.5528000653611935e-05, + "loss": 1.0179, + "step": 204 + }, + { + "epoch": 1.01, + "learning_rate": 1.5483550752531337e-05, + "loss": 0.8328, + "step": 205 + }, + { + "epoch": 1.01, + "learning_rate": 1.5438945377883463e-05, + "loss": 0.7736, + "step": 206 + }, + { + "epoch": 1.02, + "learning_rate": 1.5394185794351914e-05, + "loss": 0.7821, + "step": 207 + }, + { + "epoch": 1.02, + "learning_rate": 1.5349273270992537e-05, + "loss": 0.7243, + "step": 208 + }, + { + "epoch": 1.03, + "learning_rate": 1.5304209081197425e-05, + "loss": 0.7692, + "step": 209 + }, + { + "epoch": 1.03, + "learning_rate": 1.5258994502658846e-05, + "loss": 0.7812, + "step": 210 + }, + { + "epoch": 1.04, + "learning_rate": 1.5213630817332985e-05, + "loss": 0.7332, + "step": 211 + }, + { + "epoch": 1.04, + "learning_rate": 1.5168119311403611e-05, + "loss": 0.7696, + "step": 212 + }, + { + "epoch": 1.05, + "learning_rate": 1.512246127524561e-05, + "loss": 0.7406, + "step": 213 + }, + { + "epoch": 1.05, + "learning_rate": 1.50766580033884e-05, + "loss": 0.7596, + "step": 214 + }, + { + "epoch": 1.06, + "learning_rate": 1.5030710794479226e-05, + "loss": 0.7988, + "step": 215 + }, + { + "epoch": 1.06, + "learning_rate": 1.4984620951246333e-05, + "loss": 0.7625, + "step": 216 + }, + { + "epoch": 1.07, + "learning_rate": 1.4938389780462044e-05, + "loss": 0.7679, + "step": 217 + }, + { + "epoch": 1.07, + "learning_rate": 1.4892018592905702e-05, + "loss": 0.7604, + "step": 218 + }, + { + "epoch": 1.08, + "learning_rate": 1.4845508703326504e-05, + "loss": 0.772, + "step": 219 + }, + { + "epoch": 1.08, + "learning_rate": 1.4798861430406221e-05, + "loss": 0.7331, + "step": 220 + }, + { + "epoch": 1.09, + "learning_rate": 1.4752078096721827e-05, + "loss": 0.7808, + "step": 221 + }, + { + "epoch": 1.09, + "learning_rate": 1.4705160028707976e-05, + "loss": 0.8213, + "step": 222 + }, + { + "epoch": 1.1, + "learning_rate": 1.4658108556619417e-05, + "loss": 0.7401, + "step": 223 + }, + { + "epoch": 1.1, + "learning_rate": 1.461092501449326e-05, + "loss": 0.7548, + "step": 224 + }, + { + "epoch": 1.11, + "learning_rate": 1.4563610740111163e-05, + "loss": 0.7505, + "step": 225 + }, + { + "epoch": 1.11, + "learning_rate": 1.4516167074961394e-05, + "loss": 0.7496, + "step": 226 + }, + { + "epoch": 1.12, + "learning_rate": 1.4468595364200808e-05, + "loss": 0.7812, + "step": 227 + }, + { + "epoch": 1.12, + "learning_rate": 1.4420896956616698e-05, + "loss": 0.7651, + "step": 228 + }, + { + "epoch": 1.13, + "learning_rate": 1.4373073204588556e-05, + "loss": 0.7519, + "step": 229 + }, + { + "epoch": 1.13, + "learning_rate": 1.4325125464049725e-05, + "loss": 0.7547, + "step": 230 + }, + { + "epoch": 1.14, + "learning_rate": 1.427705509444897e-05, + "loss": 0.7795, + "step": 231 + }, + { + "epoch": 1.14, + "learning_rate": 1.4228863458711915e-05, + "loss": 0.7737, + "step": 232 + }, + { + "epoch": 1.15, + "learning_rate": 1.4180551923202406e-05, + "loss": 0.765, + "step": 233 + }, + { + "epoch": 1.15, + "learning_rate": 1.4132121857683782e-05, + "loss": 0.7702, + "step": 234 + }, + { + "epoch": 1.16, + "learning_rate": 1.4083574635280029e-05, + "loss": 0.7377, + "step": 235 + }, + { + "epoch": 1.16, + "learning_rate": 1.403491163243684e-05, + "loss": 0.7839, + "step": 236 + }, + { + "epoch": 1.17, + "learning_rate": 1.3986134228882607e-05, + "loss": 0.78, + "step": 237 + }, + { + "epoch": 1.17, + "learning_rate": 1.3937243807589291e-05, + "loss": 0.7625, + "step": 238 + }, + { + "epoch": 1.18, + "learning_rate": 1.388824175473321e-05, + "loss": 0.7124, + "step": 239 + }, + { + "epoch": 1.18, + "learning_rate": 1.383912945965574e-05, + "loss": 0.769, + "step": 240 + }, + { + "epoch": 1.19, + "learning_rate": 1.3789908314823932e-05, + "loss": 0.7558, + "step": 241 + }, + { + "epoch": 1.19, + "learning_rate": 1.3740579715791017e-05, + "loss": 0.7784, + "step": 242 + }, + { + "epoch": 1.2, + "learning_rate": 1.3691145061156843e-05, + "loss": 0.7463, + "step": 243 + }, + { + "epoch": 1.2, + "learning_rate": 1.3641605752528225e-05, + "loss": 0.7399, + "step": 244 + }, + { + "epoch": 1.21, + "learning_rate": 1.3591963194479198e-05, + "loss": 0.7394, + "step": 245 + }, + { + "epoch": 1.21, + "learning_rate": 1.3542218794511212e-05, + "loss": 0.8021, + "step": 246 + }, + { + "epoch": 1.22, + "learning_rate": 1.3492373963013199e-05, + "loss": 0.77, + "step": 247 + }, + { + "epoch": 1.22, + "learning_rate": 1.3442430113221602e-05, + "loss": 0.7032, + "step": 248 + }, + { + "epoch": 1.23, + "learning_rate": 1.3392388661180303e-05, + "loss": 0.7616, + "step": 249 + }, + { + "epoch": 1.23, + "learning_rate": 1.3342251025700474e-05, + "loss": 0.7574, + "step": 250 + }, + { + "epoch": 1.24, + "learning_rate": 1.3292018628320346e-05, + "loss": 0.7177, + "step": 251 + }, + { + "epoch": 1.24, + "learning_rate": 1.3241692893264909e-05, + "loss": 0.7939, + "step": 252 + }, + { + "epoch": 1.25, + "learning_rate": 1.3191275247405525e-05, + "loss": 0.7564, + "step": 253 + }, + { + "epoch": 1.25, + "learning_rate": 1.314076712021949e-05, + "loss": 0.7174, + "step": 254 + }, + { + "epoch": 1.26, + "learning_rate": 1.3090169943749475e-05, + "loss": 0.7017, + "step": 255 + }, + { + "epoch": 1.26, + "learning_rate": 1.3039485152562951e-05, + "loss": 0.7499, + "step": 256 + }, + { + "epoch": 1.27, + "learning_rate": 1.2988714183711504e-05, + "loss": 0.7459, + "step": 257 + }, + { + "epoch": 1.27, + "learning_rate": 1.2937858476690089e-05, + "loss": 0.7913, + "step": 258 + }, + { + "epoch": 1.28, + "learning_rate": 1.2886919473396212e-05, + "loss": 0.7785, + "step": 259 + }, + { + "epoch": 1.28, + "learning_rate": 1.2835898618089064e-05, + "loss": 0.75, + "step": 260 + }, + { + "epoch": 1.29, + "learning_rate": 1.2784797357348562e-05, + "loss": 0.7123, + "step": 261 + }, + { + "epoch": 1.29, + "learning_rate": 1.2733617140034329e-05, + "loss": 0.7353, + "step": 262 + }, + { + "epoch": 1.3, + "learning_rate": 1.268235941724463e-05, + "loss": 0.7229, + "step": 263 + }, + { + "epoch": 1.3, + "learning_rate": 1.2631025642275212e-05, + "loss": 0.7361, + "step": 264 + }, + { + "epoch": 1.31, + "learning_rate": 1.257961727057812e-05, + "loss": 0.7379, + "step": 265 + }, + { + "epoch": 1.31, + "learning_rate": 1.2528135759720403e-05, + "loss": 0.7684, + "step": 266 + }, + { + "epoch": 1.31, + "learning_rate": 1.2476582569342819e-05, + "loss": 0.7953, + "step": 267 + }, + { + "epoch": 1.32, + "learning_rate": 1.2424959161118425e-05, + "loss": 0.7435, + "step": 268 + }, + { + "epoch": 1.32, + "learning_rate": 1.2373266998711152e-05, + "loss": 0.7403, + "step": 269 + }, + { + "epoch": 1.33, + "learning_rate": 1.232150754773429e-05, + "loss": 0.7627, + "step": 270 + }, + { + "epoch": 1.33, + "learning_rate": 1.2269682275708951e-05, + "loss": 0.7323, + "step": 271 + }, + { + "epoch": 1.34, + "learning_rate": 1.2217792652022452e-05, + "loss": 0.7437, + "step": 272 + }, + { + "epoch": 1.34, + "learning_rate": 1.2165840147886656e-05, + "loss": 0.7108, + "step": 273 + }, + { + "epoch": 1.35, + "learning_rate": 1.2113826236296245e-05, + "loss": 0.7599, + "step": 274 + }, + { + "epoch": 1.35, + "learning_rate": 1.2061752391986982e-05, + "loss": 0.7445, + "step": 275 + }, + { + "epoch": 1.36, + "learning_rate": 1.2009620091393885e-05, + "loss": 0.7244, + "step": 276 + }, + { + "epoch": 1.36, + "learning_rate": 1.1957430812609361e-05, + "loss": 0.771, + "step": 277 + }, + { + "epoch": 1.37, + "learning_rate": 1.1905186035341304e-05, + "loss": 0.7079, + "step": 278 + }, + { + "epoch": 1.37, + "learning_rate": 1.1852887240871145e-05, + "loss": 0.7091, + "step": 279 + }, + { + "epoch": 1.38, + "learning_rate": 1.1800535912011846e-05, + "loss": 0.7327, + "step": 280 + }, + { + "epoch": 1.38, + "learning_rate": 1.1748133533065864e-05, + "loss": 0.7545, + "step": 281 + }, + { + "epoch": 1.39, + "learning_rate": 1.1695681589783065e-05, + "loss": 0.7525, + "step": 282 + }, + { + "epoch": 1.39, + "learning_rate": 1.1643181569318596e-05, + "loss": 0.7116, + "step": 283 + }, + { + "epoch": 1.4, + "learning_rate": 1.1590634960190722e-05, + "loss": 0.774, + "step": 284 + }, + { + "epoch": 1.4, + "learning_rate": 1.1538043252238629e-05, + "loss": 0.7504, + "step": 285 + }, + { + "epoch": 1.41, + "learning_rate": 1.1485407936580169e-05, + "loss": 0.7549, + "step": 286 + }, + { + "epoch": 1.41, + "learning_rate": 1.1432730505569597e-05, + "loss": 0.7975, + "step": 287 + }, + { + "epoch": 1.42, + "learning_rate": 1.1380012452755259e-05, + "loss": 0.7763, + "step": 288 + }, + { + "epoch": 1.42, + "learning_rate": 1.1327255272837221e-05, + "loss": 0.7644, + "step": 289 + }, + { + "epoch": 1.43, + "learning_rate": 1.1274460461624925e-05, + "loss": 0.7631, + "step": 290 + }, + { + "epoch": 1.43, + "learning_rate": 1.1221629515994754e-05, + "loss": 0.7855, + "step": 291 + }, + { + "epoch": 1.44, + "learning_rate": 1.1168763933847608e-05, + "loss": 0.718, + "step": 292 + }, + { + "epoch": 1.44, + "learning_rate": 1.1115865214066414e-05, + "loss": 0.7703, + "step": 293 + }, + { + "epoch": 1.45, + "learning_rate": 1.1062934856473655e-05, + "loss": 0.7554, + "step": 294 + }, + { + "epoch": 1.45, + "learning_rate": 1.1009974361788822e-05, + "loss": 0.778, + "step": 295 + }, + { + "epoch": 1.46, + "learning_rate": 1.095698523158588e-05, + "loss": 0.7001, + "step": 296 + }, + { + "epoch": 1.46, + "learning_rate": 1.0903968968250682e-05, + "loss": 0.7327, + "step": 297 + }, + { + "epoch": 1.47, + "learning_rate": 1.085092707493839e-05, + "loss": 0.7771, + "step": 298 + }, + { + "epoch": 1.47, + "learning_rate": 1.0797861055530832e-05, + "loss": 0.7421, + "step": 299 + }, + { + "epoch": 1.48, + "learning_rate": 1.0744772414593889e-05, + "loss": 0.7222, + "step": 300 + }, + { + "epoch": 1.48, + "learning_rate": 1.0691662657334815e-05, + "loss": 0.7769, + "step": 301 + }, + { + "epoch": 1.49, + "learning_rate": 1.0638533289559574e-05, + "loss": 0.7164, + "step": 302 + }, + { + "epoch": 1.49, + "learning_rate": 1.0585385817630137e-05, + "loss": 0.7733, + "step": 303 + }, + { + "epoch": 1.5, + "learning_rate": 1.0532221748421786e-05, + "loss": 0.7594, + "step": 304 + }, + { + "epoch": 1.5, + "learning_rate": 1.047904258928037e-05, + "loss": 0.7598, + "step": 305 + }, + { + "epoch": 1.51, + "learning_rate": 1.0425849847979586e-05, + "loss": 0.77, + "step": 306 + }, + { + "epoch": 1.51, + "learning_rate": 1.0372645032678215e-05, + "loss": 0.8052, + "step": 307 + }, + { + "epoch": 1.52, + "learning_rate": 1.031942965187738e-05, + "loss": 0.7603, + "step": 308 + }, + { + "epoch": 1.52, + "learning_rate": 1.026620521437775e-05, + "loss": 0.7664, + "step": 309 + }, + { + "epoch": 1.53, + "learning_rate": 1.0212973229236787e-05, + "loss": 0.6943, + "step": 310 + }, + { + "epoch": 1.53, + "learning_rate": 1.0159735205725949e-05, + "loss": 0.7268, + "step": 311 + }, + { + "epoch": 1.54, + "learning_rate": 1.0106492653287893e-05, + "loss": 0.7136, + "step": 312 + }, + { + "epoch": 1.54, + "learning_rate": 1.0053247081493684e-05, + "loss": 0.7736, + "step": 313 + }, + { + "epoch": 1.55, + "learning_rate": 1e-05, + "loss": 0.7514, + "step": 314 + }, + { + "epoch": 1.55, + "learning_rate": 9.946752918506319e-06, + "loss": 0.74, + "step": 315 + }, + { + "epoch": 1.56, + "learning_rate": 9.893507346712112e-06, + "loss": 0.7908, + "step": 316 + }, + { + "epoch": 1.56, + "learning_rate": 9.840264794274053e-06, + "loss": 0.7607, + "step": 317 + }, + { + "epoch": 1.57, + "learning_rate": 9.787026770763216e-06, + "loss": 0.759, + "step": 318 + }, + { + "epoch": 1.57, + "learning_rate": 9.733794785622254e-06, + "loss": 0.7486, + "step": 319 + }, + { + "epoch": 1.58, + "learning_rate": 9.680570348122626e-06, + "loss": 0.7446, + "step": 320 + }, + { + "epoch": 1.58, + "learning_rate": 9.627354967321785e-06, + "loss": 0.729, + "step": 321 + }, + { + "epoch": 1.59, + "learning_rate": 9.574150152020415e-06, + "loss": 0.7691, + "step": 322 + }, + { + "epoch": 1.59, + "learning_rate": 9.520957410719632e-06, + "loss": 0.6797, + "step": 323 + }, + { + "epoch": 1.6, + "learning_rate": 9.467778251578217e-06, + "loss": 0.7909, + "step": 324 + }, + { + "epoch": 1.6, + "learning_rate": 9.414614182369862e-06, + "loss": 0.7697, + "step": 325 + }, + { + "epoch": 1.61, + "learning_rate": 9.361466710440428e-06, + "loss": 0.7033, + "step": 326 + }, + { + "epoch": 1.61, + "learning_rate": 9.308337342665188e-06, + "loss": 0.7574, + "step": 327 + }, + { + "epoch": 1.62, + "learning_rate": 9.255227585406116e-06, + "loss": 0.7688, + "step": 328 + }, + { + "epoch": 1.62, + "learning_rate": 9.202138944469168e-06, + "loss": 0.7117, + "step": 329 + }, + { + "epoch": 1.62, + "learning_rate": 9.149072925061614e-06, + "loss": 0.7595, + "step": 330 + }, + { + "epoch": 1.63, + "learning_rate": 9.096031031749321e-06, + "loss": 0.7503, + "step": 331 + }, + { + "epoch": 1.63, + "learning_rate": 9.043014768414125e-06, + "loss": 0.7826, + "step": 332 + }, + { + "epoch": 1.64, + "learning_rate": 8.99002563821118e-06, + "loss": 0.6752, + "step": 333 + }, + { + "epoch": 1.64, + "learning_rate": 8.937065143526349e-06, + "loss": 0.7268, + "step": 334 + }, + { + "epoch": 1.65, + "learning_rate": 8.884134785933588e-06, + "loss": 0.7724, + "step": 335 + }, + { + "epoch": 1.65, + "learning_rate": 8.831236066152397e-06, + "loss": 0.7364, + "step": 336 + }, + { + "epoch": 1.66, + "learning_rate": 8.778370484005245e-06, + "loss": 0.7333, + "step": 337 + }, + { + "epoch": 1.66, + "learning_rate": 8.725539538375078e-06, + "loss": 0.7433, + "step": 338 + }, + { + "epoch": 1.67, + "learning_rate": 8.672744727162782e-06, + "loss": 0.7278, + "step": 339 + }, + { + "epoch": 1.67, + "learning_rate": 8.619987547244746e-06, + "loss": 0.7664, + "step": 340 + }, + { + "epoch": 1.68, + "learning_rate": 8.567269494430404e-06, + "loss": 0.6762, + "step": 341 + }, + { + "epoch": 1.68, + "learning_rate": 8.514592063419833e-06, + "loss": 0.7709, + "step": 342 + }, + { + "epoch": 1.69, + "learning_rate": 8.461956747761375e-06, + "loss": 0.7025, + "step": 343 + }, + { + "epoch": 1.69, + "learning_rate": 8.409365039809282e-06, + "loss": 0.7836, + "step": 344 + }, + { + "epoch": 1.7, + "learning_rate": 8.356818430681409e-06, + "loss": 0.7483, + "step": 345 + }, + { + "epoch": 1.7, + "learning_rate": 8.304318410216937e-06, + "loss": 0.7586, + "step": 346 + }, + { + "epoch": 1.71, + "learning_rate": 8.251866466934137e-06, + "loss": 0.7504, + "step": 347 + }, + { + "epoch": 1.71, + "learning_rate": 8.199464087988158e-06, + "loss": 0.7925, + "step": 348 + }, + { + "epoch": 1.72, + "learning_rate": 8.147112759128859e-06, + "loss": 0.7456, + "step": 349 + }, + { + "epoch": 1.72, + "learning_rate": 8.094813964658698e-06, + "loss": 0.6998, + "step": 350 + }, + { + "epoch": 1.73, + "learning_rate": 8.042569187390642e-06, + "loss": 0.773, + "step": 351 + }, + { + "epoch": 1.73, + "learning_rate": 7.990379908606118e-06, + "loss": 0.7208, + "step": 352 + }, + { + "epoch": 1.74, + "learning_rate": 7.938247608013021e-06, + "loss": 0.7817, + "step": 353 + }, + { + "epoch": 1.74, + "learning_rate": 7.886173763703757e-06, + "loss": 0.6981, + "step": 354 + }, + { + "epoch": 1.75, + "learning_rate": 7.834159852113347e-06, + "loss": 0.7519, + "step": 355 + }, + { + "epoch": 1.75, + "learning_rate": 7.78220734797755e-06, + "loss": 0.7504, + "step": 356 + }, + { + "epoch": 1.76, + "learning_rate": 7.73031772429105e-06, + "loss": 0.7983, + "step": 357 + }, + { + "epoch": 1.76, + "learning_rate": 7.678492452265713e-06, + "loss": 0.7743, + "step": 358 + }, + { + "epoch": 1.77, + "learning_rate": 7.626733001288852e-06, + "loss": 0.7903, + "step": 359 + }, + { + "epoch": 1.77, + "learning_rate": 7.575040838881578e-06, + "loss": 0.7885, + "step": 360 + }, + { + "epoch": 1.78, + "learning_rate": 7.523417430657186e-06, + "loss": 0.7716, + "step": 361 + }, + { + "epoch": 1.78, + "learning_rate": 7.471864240279598e-06, + "loss": 0.7268, + "step": 362 + }, + { + "epoch": 1.79, + "learning_rate": 7.420382729421883e-06, + "loss": 0.757, + "step": 363 + }, + { + "epoch": 1.79, + "learning_rate": 7.368974357724789e-06, + "loss": 0.7131, + "step": 364 + }, + { + "epoch": 1.8, + "learning_rate": 7.317640582755373e-06, + "loss": 0.752, + "step": 365 + }, + { + "epoch": 1.8, + "learning_rate": 7.266382859965673e-06, + "loss": 0.7256, + "step": 366 + }, + { + "epoch": 1.81, + "learning_rate": 7.2152026426514395e-06, + "loss": 0.7745, + "step": 367 + }, + { + "epoch": 1.81, + "learning_rate": 7.164101381910939e-06, + "loss": 0.8009, + "step": 368 + }, + { + "epoch": 1.82, + "learning_rate": 7.113080526603793e-06, + "loss": 0.7996, + "step": 369 + }, + { + "epoch": 1.82, + "learning_rate": 7.062141523309918e-06, + "loss": 0.7669, + "step": 370 + }, + { + "epoch": 1.83, + "learning_rate": 7.011285816288496e-06, + "loss": 0.7323, + "step": 371 + }, + { + "epoch": 1.83, + "learning_rate": 6.96051484743705e-06, + "loss": 0.7264, + "step": 372 + }, + { + "epoch": 1.84, + "learning_rate": 6.909830056250527e-06, + "loss": 0.7302, + "step": 373 + }, + { + "epoch": 1.84, + "learning_rate": 6.859232879780515e-06, + "loss": 0.7375, + "step": 374 + }, + { + "epoch": 1.85, + "learning_rate": 6.8087247525944745e-06, + "loss": 0.7643, + "step": 375 + }, + { + "epoch": 1.85, + "learning_rate": 6.758307106735094e-06, + "loss": 0.7262, + "step": 376 + }, + { + "epoch": 1.86, + "learning_rate": 6.707981371679657e-06, + "loss": 0.7343, + "step": 377 + }, + { + "epoch": 1.86, + "learning_rate": 6.657748974299529e-06, + "loss": 0.7855, + "step": 378 + }, + { + "epoch": 1.87, + "learning_rate": 6.607611338819697e-06, + "loss": 0.7202, + "step": 379 + }, + { + "epoch": 1.87, + "learning_rate": 6.557569886778401e-06, + "loss": 0.7384, + "step": 380 + }, + { + "epoch": 1.88, + "learning_rate": 6.507626036986804e-06, + "loss": 0.7472, + "step": 381 + }, + { + "epoch": 1.88, + "learning_rate": 6.457781205488791e-06, + "loss": 0.7305, + "step": 382 + }, + { + "epoch": 1.89, + "learning_rate": 6.408036805520801e-06, + "loss": 0.7094, + "step": 383 + }, + { + "epoch": 1.89, + "learning_rate": 6.358394247471779e-06, + "loss": 0.6939, + "step": 384 + }, + { + "epoch": 1.9, + "learning_rate": 6.308854938843161e-06, + "loss": 0.7485, + "step": 385 + }, + { + "epoch": 1.9, + "learning_rate": 6.259420284208987e-06, + "loss": 0.7384, + "step": 386 + }, + { + "epoch": 1.91, + "learning_rate": 6.210091685176067e-06, + "loss": 0.6969, + "step": 387 + }, + { + "epoch": 1.91, + "learning_rate": 6.160870540344261e-06, + "loss": 0.7607, + "step": 388 + }, + { + "epoch": 1.92, + "learning_rate": 6.111758245266795e-06, + "loss": 0.7404, + "step": 389 + }, + { + "epoch": 1.92, + "learning_rate": 6.0627561924107145e-06, + "loss": 0.7642, + "step": 390 + }, + { + "epoch": 1.92, + "learning_rate": 6.013865771117394e-06, + "loss": 0.7739, + "step": 391 + }, + { + "epoch": 1.93, + "learning_rate": 5.965088367563162e-06, + "loss": 0.7594, + "step": 392 + }, + { + "epoch": 1.93, + "learning_rate": 5.916425364719975e-06, + "loss": 0.7457, + "step": 393 + }, + { + "epoch": 1.94, + "learning_rate": 5.867878142316221e-06, + "loss": 0.7704, + "step": 394 + }, + { + "epoch": 1.94, + "learning_rate": 5.8194480767976e-06, + "loss": 0.746, + "step": 395 + }, + { + "epoch": 1.95, + "learning_rate": 5.7711365412880895e-06, + "loss": 0.7696, + "step": 396 + }, + { + "epoch": 1.95, + "learning_rate": 5.7229449055510335e-06, + "loss": 0.7265, + "step": 397 + }, + { + "epoch": 1.96, + "learning_rate": 5.674874535950279e-06, + "loss": 0.759, + "step": 398 + }, + { + "epoch": 1.96, + "learning_rate": 5.626926795411447e-06, + "loss": 0.7802, + "step": 399 + }, + { + "epoch": 1.97, + "learning_rate": 5.579103043383305e-06, + "loss": 0.7529, + "step": 400 + }, + { + "epoch": 1.97, + "learning_rate": 5.531404635799191e-06, + "loss": 0.7273, + "step": 401 + }, + { + "epoch": 1.98, + "learning_rate": 5.4838329250386076e-06, + "loss": 0.7826, + "step": 402 + }, + { + "epoch": 1.98, + "learning_rate": 5.436389259888841e-06, + "loss": 0.7893, + "step": 403 + }, + { + "epoch": 1.99, + "learning_rate": 5.38907498550674e-06, + "loss": 0.7119, + "step": 404 + }, + { + "epoch": 1.99, + "learning_rate": 5.341891443380585e-06, + "loss": 0.7694, + "step": 405 + }, + { + "epoch": 2.0, + "learning_rate": 5.294839971292026e-06, + "loss": 0.7911, + "step": 406 + }, + { + "epoch": 2.0, + "learning_rate": 5.247921903278177e-06, + "loss": 0.658, + "step": 407 + }, + { + "epoch": 2.01, + "learning_rate": 5.20113856959378e-06, + "loss": 0.5248, + "step": 408 + }, + { + "epoch": 2.01, + "learning_rate": 5.1544912966735e-06, + "loss": 0.5485, + "step": 409 + }, + { + "epoch": 2.02, + "learning_rate": 5.1079814070943e-06, + "loss": 0.564, + "step": 410 + }, + { + "epoch": 2.02, + "learning_rate": 5.06161021953796e-06, + "loss": 0.5438, + "step": 411 + }, + { + "epoch": 2.03, + "learning_rate": 5.015379048753669e-06, + "loss": 0.4943, + "step": 412 + }, + { + "epoch": 2.03, + "learning_rate": 4.9692892055207784e-06, + "loss": 0.562, + "step": 413 + }, + { + "epoch": 2.04, + "learning_rate": 4.923341996611604e-06, + "loss": 0.5606, + "step": 414 + }, + { + "epoch": 2.04, + "learning_rate": 4.877538724754392e-06, + "loss": 0.5554, + "step": 415 + }, + { + "epoch": 2.05, + "learning_rate": 4.831880688596392e-06, + "loss": 0.5444, + "step": 416 + }, + { + "epoch": 2.05, + "learning_rate": 4.7863691826670146e-06, + "loss": 0.4918, + "step": 417 + }, + { + "epoch": 2.06, + "learning_rate": 4.741005497341154e-06, + "loss": 0.5216, + "step": 418 + }, + { + "epoch": 2.06, + "learning_rate": 4.695790918802577e-06, + "loss": 0.5173, + "step": 419 + }, + { + "epoch": 2.07, + "learning_rate": 4.650726729007465e-06, + "loss": 0.5371, + "step": 420 + }, + { + "epoch": 2.07, + "learning_rate": 4.605814205648087e-06, + "loss": 0.5041, + "step": 421 + }, + { + "epoch": 2.08, + "learning_rate": 4.56105462211654e-06, + "loss": 0.5097, + "step": 422 + }, + { + "epoch": 2.08, + "learning_rate": 4.516449247468666e-06, + "loss": 0.4567, + "step": 423 + }, + { + "epoch": 2.09, + "learning_rate": 4.4719993463880695e-06, + "loss": 0.502, + "step": 424 + }, + { + "epoch": 2.09, + "learning_rate": 4.427706179150247e-06, + "loss": 0.4755, + "step": 425 + }, + { + "epoch": 2.1, + "learning_rate": 4.383571001586883e-06, + "loss": 0.507, + "step": 426 + }, + { + "epoch": 2.1, + "learning_rate": 4.339595065050206e-06, + "loss": 0.474, + "step": 427 + }, + { + "epoch": 2.11, + "learning_rate": 4.29577961637754e-06, + "loss": 0.4874, + "step": 428 + }, + { + "epoch": 2.11, + "learning_rate": 4.2521258978559324e-06, + "loss": 0.4419, + "step": 429 + }, + { + "epoch": 2.12, + "learning_rate": 4.208635147186956e-06, + "loss": 0.4606, + "step": 430 + }, + { + "epoch": 2.12, + "learning_rate": 4.165308597451586e-06, + "loss": 0.5074, + "step": 431 + }, + { + "epoch": 2.13, + "learning_rate": 4.12214747707527e-06, + "loss": 0.5436, + "step": 432 + }, + { + "epoch": 2.13, + "learning_rate": 4.079153009793068e-06, + "loss": 0.4759, + "step": 433 + }, + { + "epoch": 2.14, + "learning_rate": 4.036326414614985e-06, + "loss": 0.5115, + "step": 434 + }, + { + "epoch": 2.14, + "learning_rate": 3.99366890579139e-06, + "loss": 0.4774, + "step": 435 + }, + { + "epoch": 2.15, + "learning_rate": 3.951181692778594e-06, + "loss": 0.5014, + "step": 436 + }, + { + "epoch": 2.15, + "learning_rate": 3.908865980204555e-06, + "loss": 0.5389, + "step": 437 + }, + { + "epoch": 2.16, + "learning_rate": 3.86672296783474e-06, + "loss": 0.498, + "step": 438 + }, + { + "epoch": 2.16, + "learning_rate": 3.824753850538082e-06, + "loss": 0.5112, + "step": 439 + }, + { + "epoch": 2.17, + "learning_rate": 3.782959818253126e-06, + "loss": 0.5149, + "step": 440 + }, + { + "epoch": 2.17, + "learning_rate": 3.741342055954269e-06, + "loss": 0.5024, + "step": 441 + }, + { + "epoch": 2.18, + "learning_rate": 3.699901743618194e-06, + "loss": 0.5269, + "step": 442 + }, + { + "epoch": 2.18, + "learning_rate": 3.658640056190378e-06, + "loss": 0.4601, + "step": 443 + }, + { + "epoch": 2.19, + "learning_rate": 3.617558163551802e-06, + "loss": 0.4366, + "step": 444 + }, + { + "epoch": 2.19, + "learning_rate": 3.576657230485775e-06, + "loss": 0.5111, + "step": 445 + }, + { + "epoch": 2.2, + "learning_rate": 3.5359384166449185e-06, + "loss": 0.4604, + "step": 446 + }, + { + "epoch": 2.2, + "learning_rate": 3.4954028765182633e-06, + "loss": 0.5035, + "step": 447 + }, + { + "epoch": 2.21, + "learning_rate": 3.4550517593985512e-06, + "loss": 0.5145, + "step": 448 + }, + { + "epoch": 2.21, + "learning_rate": 3.414886209349615e-06, + "loss": 0.5113, + "step": 449 + }, + { + "epoch": 2.22, + "learning_rate": 3.3749073651739594e-06, + "loss": 0.4851, + "step": 450 + }, + { + "epoch": 2.22, + "learning_rate": 3.3351163603804805e-06, + "loss": 0.5437, + "step": 451 + }, + { + "epoch": 2.23, + "learning_rate": 3.2955143231523067e-06, + "loss": 0.486, + "step": 452 + }, + { + "epoch": 2.23, + "learning_rate": 3.2561023763148237e-06, + "loss": 0.524, + "step": 453 + }, + { + "epoch": 2.24, + "learning_rate": 3.216881637303839e-06, + "loss": 0.5032, + "step": 454 + }, + { + "epoch": 2.24, + "learning_rate": 3.177853218133905e-06, + "loss": 0.5182, + "step": 455 + }, + { + "epoch": 2.25, + "learning_rate": 3.1390182253667745e-06, + "loss": 0.5124, + "step": 456 + }, + { + "epoch": 2.25, + "learning_rate": 3.100377760080041e-06, + "loss": 0.4383, + "step": 457 + }, + { + "epoch": 2.26, + "learning_rate": 3.0619329178359103e-06, + "loss": 0.4617, + "step": 458 + }, + { + "epoch": 2.26, + "learning_rate": 3.023684788650154e-06, + "loss": 0.4988, + "step": 459 + }, + { + "epoch": 2.27, + "learning_rate": 2.985634456961184e-06, + "loss": 0.479, + "step": 460 + }, + { + "epoch": 2.27, + "learning_rate": 2.947783001599315e-06, + "loss": 0.4731, + "step": 461 + }, + { + "epoch": 2.28, + "learning_rate": 2.9101314957561864e-06, + "loss": 0.4888, + "step": 462 + }, + { + "epoch": 2.28, + "learning_rate": 2.8726810069543156e-06, + "loss": 0.4998, + "step": 463 + }, + { + "epoch": 2.29, + "learning_rate": 2.8354325970168483e-06, + "loss": 0.4837, + "step": 464 + }, + { + "epoch": 2.29, + "learning_rate": 2.7983873220374415e-06, + "loss": 0.4664, + "step": 465 + }, + { + "epoch": 2.3, + "learning_rate": 2.7615462323503186e-06, + "loss": 0.5497, + "step": 466 + }, + { + "epoch": 2.3, + "learning_rate": 2.724910372500508e-06, + "loss": 0.5019, + "step": 467 + }, + { + "epoch": 2.31, + "learning_rate": 2.6884807812142043e-06, + "loss": 0.5103, + "step": 468 + }, + { + "epoch": 2.31, + "learning_rate": 2.6522584913693295e-06, + "loss": 0.4748, + "step": 469 + }, + { + "epoch": 2.31, + "learning_rate": 2.616244529966244e-06, + "loss": 0.4815, + "step": 470 + }, + { + "epoch": 2.32, + "learning_rate": 2.5804399180986417e-06, + "loss": 0.4648, + "step": 471 + }, + { + "epoch": 2.32, + "learning_rate": 2.544845670924575e-06, + "loss": 0.4673, + "step": 472 + }, + { + "epoch": 2.33, + "learning_rate": 2.509462797637693e-06, + "loss": 0.487, + "step": 473 + }, + { + "epoch": 2.33, + "learning_rate": 2.4742923014386154e-06, + "loss": 0.4686, + "step": 474 + }, + { + "epoch": 2.34, + "learning_rate": 2.4393351795065023e-06, + "loss": 0.5048, + "step": 475 + }, + { + "epoch": 2.34, + "learning_rate": 2.4045924229707663e-06, + "loss": 0.548, + "step": 476 + }, + { + "epoch": 2.35, + "learning_rate": 2.3700650168829765e-06, + "loss": 0.4449, + "step": 477 + }, + { + "epoch": 2.35, + "learning_rate": 2.3357539401889438e-06, + "loss": 0.5208, + "step": 478 + }, + { + "epoch": 2.36, + "learning_rate": 2.3016601657009364e-06, + "loss": 0.5427, + "step": 479 + }, + { + "epoch": 2.36, + "learning_rate": 2.2677846600701305e-06, + "loss": 0.5042, + "step": 480 + }, + { + "epoch": 2.37, + "learning_rate": 2.234128383759174e-06, + "loss": 0.5001, + "step": 481 + }, + { + "epoch": 2.37, + "learning_rate": 2.2006922910149743e-06, + "loss": 0.4867, + "step": 482 + }, + { + "epoch": 2.38, + "learning_rate": 2.167477329841633e-06, + "loss": 0.5209, + "step": 483 + }, + { + "epoch": 2.38, + "learning_rate": 2.1344844419735757e-06, + "loss": 0.523, + "step": 484 + }, + { + "epoch": 2.39, + "learning_rate": 2.101714562848841e-06, + "loss": 0.4959, + "step": 485 + }, + { + "epoch": 2.39, + "learning_rate": 2.069168621582567e-06, + "loss": 0.4785, + "step": 486 + }, + { + "epoch": 2.4, + "learning_rate": 2.0368475409406396e-06, + "loss": 0.492, + "step": 487 + }, + { + "epoch": 2.4, + "learning_rate": 2.004752237313544e-06, + "loss": 0.5309, + "step": 488 + }, + { + "epoch": 2.41, + "learning_rate": 1.972883620690366e-06, + "loss": 0.4684, + "step": 489 + }, + { + "epoch": 2.41, + "learning_rate": 1.9412425946329994e-06, + "loss": 0.5455, + "step": 490 + }, + { + "epoch": 2.42, + "learning_rate": 1.9098300562505266e-06, + "loss": 0.4745, + "step": 491 + }, + { + "epoch": 2.42, + "learning_rate": 1.8786468961737902e-06, + "loss": 0.5162, + "step": 492 + }, + { + "epoch": 2.43, + "learning_rate": 1.8476939985301257e-06, + "loss": 0.5259, + "step": 493 + }, + { + "epoch": 2.43, + "learning_rate": 1.81697224091831e-06, + "loss": 0.5124, + "step": 494 + }, + { + "epoch": 2.44, + "learning_rate": 1.7864824943836633e-06, + "loss": 0.4832, + "step": 495 + }, + { + "epoch": 2.44, + "learning_rate": 1.7562256233933717e-06, + "loss": 0.4756, + "step": 496 + }, + { + "epoch": 2.45, + "learning_rate": 1.7262024858119597e-06, + "loss": 0.4907, + "step": 497 + }, + { + "epoch": 2.45, + "learning_rate": 1.6964139328769736e-06, + "loss": 0.5211, + "step": 498 + }, + { + "epoch": 2.46, + "learning_rate": 1.6668608091748495e-06, + "loss": 0.4783, + "step": 499 + }, + { + "epoch": 2.46, + "learning_rate": 1.637543952616969e-06, + "loss": 0.5, + "step": 500 + }, + { + "epoch": 2.47, + "learning_rate": 1.6084641944158918e-06, + "loss": 0.4773, + "step": 501 + }, + { + "epoch": 2.47, + "learning_rate": 1.5796223590617987e-06, + "loss": 0.5039, + "step": 502 + }, + { + "epoch": 2.48, + "learning_rate": 1.5510192642991073e-06, + "loss": 0.5622, + "step": 503 + }, + { + "epoch": 2.48, + "learning_rate": 1.522655721103291e-06, + "loss": 0.4801, + "step": 504 + }, + { + "epoch": 2.49, + "learning_rate": 1.494532533657893e-06, + "loss": 0.4678, + "step": 505 + }, + { + "epoch": 2.49, + "learning_rate": 1.4666504993317089e-06, + "loss": 0.5091, + "step": 506 + }, + { + "epoch": 2.5, + "learning_rate": 1.4390104086561886e-06, + "loss": 0.4625, + "step": 507 + }, + { + "epoch": 2.5, + "learning_rate": 1.4116130453030296e-06, + "loss": 0.502, + "step": 508 + }, + { + "epoch": 2.51, + "learning_rate": 1.3844591860619382e-06, + "loss": 0.5341, + "step": 509 + }, + { + "epoch": 2.51, + "learning_rate": 1.3575496008186307e-06, + "loss": 0.5126, + "step": 510 + }, + { + "epoch": 2.52, + "learning_rate": 1.330885052532981e-06, + "loss": 0.477, + "step": 511 + }, + { + "epoch": 2.52, + "learning_rate": 1.3044662972174005e-06, + "loss": 0.4794, + "step": 512 + }, + { + "epoch": 2.53, + "learning_rate": 1.2782940839154113e-06, + "loss": 0.4699, + "step": 513 + }, + { + "epoch": 2.53, + "learning_rate": 1.2523691546803872e-06, + "loss": 0.4729, + "step": 514 + }, + { + "epoch": 2.54, + "learning_rate": 1.2266922445545348e-06, + "loss": 0.5759, + "step": 515 + }, + { + "epoch": 2.54, + "learning_rate": 1.201264081548038e-06, + "loss": 0.4449, + "step": 516 + }, + { + "epoch": 2.55, + "learning_rate": 1.176085386618434e-06, + "loss": 0.5104, + "step": 517 + }, + { + "epoch": 2.55, + "learning_rate": 1.151156873650151e-06, + "loss": 0.4581, + "step": 518 + }, + { + "epoch": 2.56, + "learning_rate": 1.1264792494342858e-06, + "loss": 0.4846, + "step": 519 + }, + { + "epoch": 2.56, + "learning_rate": 1.1020532136485517e-06, + "loss": 0.4682, + "step": 520 + }, + { + "epoch": 2.57, + "learning_rate": 1.0778794588374542e-06, + "loss": 0.5084, + "step": 521 + }, + { + "epoch": 2.57, + "learning_rate": 1.0539586703926396e-06, + "loss": 0.5208, + "step": 522 + }, + { + "epoch": 2.58, + "learning_rate": 1.0302915265334722e-06, + "loss": 0.485, + "step": 523 + }, + { + "epoch": 2.58, + "learning_rate": 1.0068786982878087e-06, + "loss": 0.5098, + "step": 524 + }, + { + "epoch": 2.59, + "learning_rate": 9.837208494729567e-07, + "loss": 0.4871, + "step": 525 + }, + { + "epoch": 2.59, + "learning_rate": 9.608186366768746e-07, + "loss": 0.5075, + "step": 526 + }, + { + "epoch": 2.6, + "learning_rate": 9.381727092395365e-07, + "loss": 0.5208, + "step": 527 + }, + { + "epoch": 2.6, + "learning_rate": 9.157837092345334e-07, + "loss": 0.4933, + "step": 528 + }, + { + "epoch": 2.61, + "learning_rate": 8.936522714508678e-07, + "loss": 0.5161, + "step": 529 + }, + { + "epoch": 2.61, + "learning_rate": 8.71779023374949e-07, + "loss": 0.4978, + "step": 530 + }, + { + "epoch": 2.62, + "learning_rate": 8.501645851728091e-07, + "loss": 0.547, + "step": 531 + }, + { + "epoch": 2.62, + "learning_rate": 8.28809569672514e-07, + "loss": 0.5379, + "step": 532 + }, + { + "epoch": 2.62, + "learning_rate": 8.077145823467924e-07, + "loss": 0.4738, + "step": 533 + }, + { + "epoch": 2.63, + "learning_rate": 7.868802212958704e-07, + "loss": 0.4614, + "step": 534 + }, + { + "epoch": 2.63, + "learning_rate": 7.663070772305081e-07, + "loss": 0.5242, + "step": 535 + }, + { + "epoch": 2.64, + "learning_rate": 7.459957334552526e-07, + "loss": 0.5406, + "step": 536 + }, + { + "epoch": 2.64, + "learning_rate": 7.259467658519026e-07, + "loss": 0.456, + "step": 537 + }, + { + "epoch": 2.65, + "learning_rate": 7.061607428631823e-07, + "loss": 0.518, + "step": 538 + }, + { + "epoch": 2.65, + "learning_rate": 6.866382254766158e-07, + "loss": 0.4643, + "step": 539 + }, + { + "epoch": 2.66, + "learning_rate": 6.673797672086335e-07, + "loss": 0.5025, + "step": 540 + }, + { + "epoch": 2.66, + "learning_rate": 6.483859140888648e-07, + "loss": 0.5074, + "step": 541 + }, + { + "epoch": 2.67, + "learning_rate": 6.296572046446725e-07, + "loss": 0.5339, + "step": 542 + }, + { + "epoch": 2.67, + "learning_rate": 6.111941698858681e-07, + "loss": 0.463, + "step": 543 + }, + { + "epoch": 2.68, + "learning_rate": 5.929973332896677e-07, + "loss": 0.5048, + "step": 544 + }, + { + "epoch": 2.68, + "learning_rate": 5.750672107858435e-07, + "loss": 0.4865, + "step": 545 + }, + { + "epoch": 2.69, + "learning_rate": 5.574043107421023e-07, + "loss": 0.507, + "step": 546 + }, + { + "epoch": 2.69, + "learning_rate": 5.400091339496638e-07, + "loss": 0.4942, + "step": 547 + }, + { + "epoch": 2.7, + "learning_rate": 5.228821736090684e-07, + "loss": 0.5347, + "step": 548 + }, + { + "epoch": 2.7, + "learning_rate": 5.060239153161872e-07, + "loss": 0.5171, + "step": 549 + }, + { + "epoch": 2.71, + "learning_rate": 4.894348370484648e-07, + "loss": 0.4647, + "step": 550 + }, + { + "epoch": 2.71, + "learning_rate": 4.731154091513546e-07, + "loss": 0.4951, + "step": 551 + }, + { + "epoch": 2.72, + "learning_rate": 4.570660943249927e-07, + "loss": 0.475, + "step": 552 + }, + { + "epoch": 2.72, + "learning_rate": 4.412873476110702e-07, + "loss": 0.5263, + "step": 553 + }, + { + "epoch": 2.73, + "learning_rate": 4.2577961637994544e-07, + "loss": 0.5165, + "step": 554 + }, + { + "epoch": 2.73, + "learning_rate": 4.1054334031794373e-07, + "loss": 0.5298, + "step": 555 + }, + { + "epoch": 2.74, + "learning_rate": 3.955789514149022e-07, + "loss": 0.4882, + "step": 556 + }, + { + "epoch": 2.74, + "learning_rate": 3.808868739519167e-07, + "loss": 0.5237, + "step": 557 + }, + { + "epoch": 2.75, + "learning_rate": 3.6646752448931345e-07, + "loss": 0.4993, + "step": 558 + }, + { + "epoch": 2.75, + "learning_rate": 3.5232131185484075e-07, + "loss": 0.4955, + "step": 559 + }, + { + "epoch": 2.76, + "learning_rate": 3.3844863713207276e-07, + "loss": 0.5372, + "step": 560 + }, + { + "epoch": 2.76, + "learning_rate": 3.2484989364904295e-07, + "loss": 0.4537, + "step": 561 + }, + { + "epoch": 2.77, + "learning_rate": 3.115254669670864e-07, + "loss": 0.4886, + "step": 562 + }, + { + "epoch": 2.77, + "learning_rate": 2.984757348699152e-07, + "loss": 0.4615, + "step": 563 + }, + { + "epoch": 2.78, + "learning_rate": 2.857010673529015e-07, + "loss": 0.483, + "step": 564 + }, + { + "epoch": 2.78, + "learning_rate": 2.7320182661258687e-07, + "loss": 0.4831, + "step": 565 + }, + { + "epoch": 2.79, + "learning_rate": 2.6097836703641856e-07, + "loss": 0.5143, + "step": 566 + }, + { + "epoch": 2.79, + "learning_rate": 2.4903103519269724e-07, + "loss": 0.5071, + "step": 567 + }, + { + "epoch": 2.8, + "learning_rate": 2.3736016982075172e-07, + "loss": 0.471, + "step": 568 + }, + { + "epoch": 2.8, + "learning_rate": 2.2596610182133328e-07, + "loss": 0.5003, + "step": 569 + }, + { + "epoch": 2.81, + "learning_rate": 2.1484915424723973e-07, + "loss": 0.5013, + "step": 570 + }, + { + "epoch": 2.81, + "learning_rate": 2.0400964229414732e-07, + "loss": 0.4693, + "step": 571 + }, + { + "epoch": 2.82, + "learning_rate": 1.9344787329168002e-07, + "loss": 0.4621, + "step": 572 + }, + { + "epoch": 2.82, + "learning_rate": 1.831641466946954e-07, + "loss": 0.4769, + "step": 573 + }, + { + "epoch": 2.83, + "learning_rate": 1.731587540747903e-07, + "loss": 0.4769, + "step": 574 + }, + { + "epoch": 2.83, + "learning_rate": 1.6343197911203978e-07, + "loss": 0.5124, + "step": 575 + }, + { + "epoch": 2.84, + "learning_rate": 1.5398409758695e-07, + "loss": 0.4797, + "step": 576 + }, + { + "epoch": 2.84, + "learning_rate": 1.448153773726402e-07, + "loss": 0.5224, + "step": 577 + }, + { + "epoch": 2.85, + "learning_rate": 1.3592607842724648e-07, + "loss": 0.458, + "step": 578 + }, + { + "epoch": 2.85, + "learning_rate": 1.2731645278655448e-07, + "loss": 0.5218, + "step": 579 + }, + { + "epoch": 2.86, + "learning_rate": 1.1898674455685045e-07, + "loss": 0.4615, + "step": 580 + }, + { + "epoch": 2.86, + "learning_rate": 1.109371899080025e-07, + "loss": 0.4976, + "step": 581 + }, + { + "epoch": 2.87, + "learning_rate": 1.0316801706676038e-07, + "loss": 0.4539, + "step": 582 + }, + { + "epoch": 2.87, + "learning_rate": 9.56794463102917e-08, + "loss": 0.5036, + "step": 583 + }, + { + "epoch": 2.88, + "learning_rate": 8.847168995992916e-08, + "loss": 0.5054, + "step": 584 + }, + { + "epoch": 2.88, + "learning_rate": 8.154495237515436e-08, + "loss": 0.4569, + "step": 585 + }, + { + "epoch": 2.89, + "learning_rate": 7.489942994780452e-08, + "loss": 0.5083, + "step": 586 + }, + { + "epoch": 2.89, + "learning_rate": 6.853531109650147e-08, + "loss": 0.4996, + "step": 587 + }, + { + "epoch": 2.9, + "learning_rate": 6.245277626131142e-08, + "loss": 0.4822, + "step": 588 + }, + { + "epoch": 2.9, + "learning_rate": 5.665199789862907e-08, + "loss": 0.5149, + "step": 589 + }, + { + "epoch": 2.91, + "learning_rate": 5.113314047628493e-08, + "loss": 0.5673, + "step": 590 + }, + { + "epoch": 2.91, + "learning_rate": 4.589636046888779e-08, + "loss": 0.5373, + "step": 591 + }, + { + "epoch": 2.92, + "learning_rate": 4.094180635338396e-08, + "loss": 0.4939, + "step": 592 + }, + { + "epoch": 2.92, + "learning_rate": 3.626961860484723e-08, + "loss": 0.4377, + "step": 593 + }, + { + "epoch": 2.92, + "learning_rate": 3.187992969249876e-08, + "loss": 0.4914, + "step": 594 + }, + { + "epoch": 2.93, + "learning_rate": 2.7772864075950036e-08, + "loss": 0.4969, + "step": 595 + }, + { + "epoch": 2.93, + "learning_rate": 2.3948538201672423e-08, + "loss": 0.5389, + "step": 596 + }, + { + "epoch": 2.94, + "learning_rate": 2.040706049970087e-08, + "loss": 0.5015, + "step": 597 + }, + { + "epoch": 2.94, + "learning_rate": 1.7148531380550836e-08, + "loss": 0.4968, + "step": 598 + }, + { + "epoch": 2.95, + "learning_rate": 1.4173043232380557e-08, + "loss": 0.5145, + "step": 599 + }, + { + "epoch": 2.95, + "learning_rate": 1.1480680418365364e-08, + "loss": 0.4948, + "step": 600 + }, + { + "epoch": 2.96, + "learning_rate": 9.071519274308494e-09, + "loss": 0.4561, + "step": 601 + }, + { + "epoch": 2.96, + "learning_rate": 6.945628106477254e-09, + "loss": 0.5233, + "step": 602 + }, + { + "epoch": 2.97, + "learning_rate": 5.1030671896623585e-09, + "loss": 0.5257, + "step": 603 + }, + { + "epoch": 2.97, + "learning_rate": 3.5438887654737355e-09, + "loss": 0.5416, + "step": 604 + }, + { + "epoch": 2.98, + "learning_rate": 2.268137040859486e-09, + "loss": 0.4912, + "step": 605 + }, + { + "epoch": 2.98, + "learning_rate": 1.275848186845785e-09, + "loss": 0.5545, + "step": 606 + }, + { + "epoch": 2.99, + "learning_rate": 5.670503375188041e-10, + "loss": 0.4912, + "step": 607 + }, + { + "epoch": 2.99, + "learning_rate": 1.4176358922535216e-10, + "loss": 0.4833, + "step": 608 + }, + { + "epoch": 3.0, + "learning_rate": 0.0, + "loss": 0.5261, + "step": 609 + }, + { + "epoch": 3.0, + "step": 609, + "total_flos": 1.474360073298903e+17, + "train_loss": 0.781049705148722, + "train_runtime": 11681.9145, + "train_samples_per_second": 13.354, + "train_steps_per_second": 0.052 + } + ], + "max_steps": 609, + "num_train_epochs": 3, + "total_flos": 1.474360073298903e+17, + "trial_name": null, + "trial_params": null +} diff --git a/training_args.bin b/training_args.bin new file mode 100644 index 0000000..ae57874 --- /dev/null +++ b/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:02f8c3ba14e3c48c05f76880975d7385c878b0e5a0863e352c82f331150d2bd4 +size 3707