Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+rag_truth_hal_detection_model/checkpoint-705/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+rag_truth_hal_detection_model/tokenizer.json filter=lfs diff=lfs merge=lfs -text

rag_truth_hal_detection_model/README.md

@@ -0,0 +1,61 @@
+---
+library_name: transformers
+license: other
+base_model: meta-llama/Meta-Llama-3-8B
+tags:
+- llama-factory
+- full
+- generated_from_trainer
+model-index:
+- name: train_2024-11-22-23-46-34
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# train_2024-11-22-23-46-34
+
+This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B) on the train_hal_detection dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-06
+- train_batch_size: 1
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 8
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 64
+- total_eval_batch_size: 64
+- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 10
+- num_epochs: 3.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.46.1
+- Pytorch 2.3.0a0+ebedce2
+- Datasets 3.1.0
+- Tokenizers 0.20.3

rag_truth_hal_detection_model/all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.9941706412294646,
+    "total_flos": 1.924797037417595e+18,
+    "train_loss": 0.15324530343108989,
+    "train_runtime": 11186.4742,
+    "train_samples_per_second": 4.047,
+    "train_steps_per_second": 0.063
+}

rag_truth_hal_detection_model/checkpoint-705/config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "meta-llama/Meta-Llama-3-8B",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": 128001,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 8192,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.1",
+  "use_cache": false,
+  "vocab_size": 128256
+}

rag_truth_hal_detection_model/checkpoint-705/generation_config.json

@@ -0,0 +1,9 @@
+{
+  "bos_token_id": 128000,
+  "do_sample": true,
+  "eos_token_id": 128001,
+  "max_length": 4096,
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.46.1"
+}

rag_truth_hal_detection_model/checkpoint-705/global_step705/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28dee938251ef965f37617c63a0cd0a12596101249718012cd42e843c117e105
+size 12045399116

rag_truth_hal_detection_model/checkpoint-705/global_step705/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6bef61c493b08e611fd562434b7751e56be14998d03eeb321abfc795aa6a6c6
+size 12045399948

rag_truth_hal_detection_model/checkpoint-705/global_step705/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a8a026d189475013658f45731bba8848ec110218f7ffb494d2a93eec80a23a7
+size 12045400204

rag_truth_hal_detection_model/checkpoint-705/global_step705/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85d794234085a73cc2750f7d05fde3e2f66476a98d3a3890bd353e2655e3f01b
+size 12045399948

rag_truth_hal_detection_model/checkpoint-705/global_step705/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d265c93014143265d16a271508fca137a3e13131673834e4258258c86a91b8b
+size 12045400204

rag_truth_hal_detection_model/checkpoint-705/global_step705/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df5bdcee5268ad925919710d48e205de0008844548317aff5faf635dd6e5b7f3
+size 12045400268

rag_truth_hal_detection_model/checkpoint-705/global_step705/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22cc4fa6fa0a1b67f7a70330ce54e1478fb5d95022345b04756b3bc48f66f4c0
+size 12045399948

rag_truth_hal_detection_model/checkpoint-705/global_step705/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed17f5088db7d2dff50be0d965924222adee8960c588df535c7f720ed7e891ec
+size 12045398796

rag_truth_hal_detection_model/checkpoint-705/global_step705/mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f7d7c326b8246205161a3201c8145a1399b9c691ce09233e8439505ee2648f0
+size 16060610616

rag_truth_hal_detection_model/checkpoint-705/latest

@@ -0,0 +1 @@
+global_step705

rag_truth_hal_detection_model/checkpoint-705/model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78c97c60ccbad3d9a18556229e0610515687a995d517b2bc96b00437b0222f4f
+size 4976698672

rag_truth_hal_detection_model/checkpoint-705/model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64ed7f6307a878b2b67e795b23b331653b75d7b8e24fff12de9988a46b207ea1
+size 4999802720

rag_truth_hal_detection_model/checkpoint-705/model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:146c49a7d418706caae25f4bbba4cf5e6e6106ba2d29c2b1c003f9dc06a324e5
+size 4915916176

rag_truth_hal_detection_model/checkpoint-705/model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65d02ea8ee9562ccc8a8af2a3716d3043b8684d9baca99019a889b749c11c936
+size 1168138808

rag_truth_hal_detection_model/checkpoint-705/model.safetensors.index.json

@@ -0,0 +1,298 @@
+{
+  "metadata": {
+    "total_size": 16060522496
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00004-of-00004.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.norm.weight": "model-00004-of-00004.safetensors"
+  }
+}

rag_truth_hal_detection_model/checkpoint-705/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08282b46825aa78d10fe10e3fea89555c5b5a691b261a3ddfd58fcb58370edff
+size 15984

rag_truth_hal_detection_model/checkpoint-705/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dbab71d98a3a9a92df82a6bba463947327c3a1bcf35cd9f4f46114641fc42dd9
+size 15984

rag_truth_hal_detection_model/checkpoint-705/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:caac82d57d878d30219a4f9ec289a97ff90c53afc160b968f251b3fd3454b8d8
+size 15984

rag_truth_hal_detection_model/checkpoint-705/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19762d2d370222b01817da11bbaa6665d542293373186d66f754e7246bb861ed
+size 15984

rag_truth_hal_detection_model/checkpoint-705/rng_state_4.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00c7508b346a7d3c5c23392845f1d013331114ade778794b76e919cb3ed5d33e
+size 15984

rag_truth_hal_detection_model/checkpoint-705/rng_state_5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b89de7d14dd20a191f56b74c816ef8b7fe5c171e31efbeadbf321c4539ed68c3
+size 15984

rag_truth_hal_detection_model/checkpoint-705/rng_state_6.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c71152053553e6e22d670fbc4fd7550bf8a046b54cad7b71869787986a6a42c
+size 15984

rag_truth_hal_detection_model/checkpoint-705/rng_state_7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b67db12a26a26ffe03d9afc84a43857eb2e5b2fec2dd189653b415f74208190
+size 15984

rag_truth_hal_detection_model/checkpoint-705/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7faf79fdcd0ee6c5f883eb22adcc896794f7004fb8cf26b4315ee381797f1f6
+size 1064

rag_truth_hal_detection_model/checkpoint-705/special_tokens_map.json

@@ -0,0 +1,17 @@
+{
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|end_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|end_of_text|>"
+}

rag_truth_hal_detection_model/checkpoint-705/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c5cf44023714fb39b05e71e425f8d7b92805ff73f7988b083b8c87f0bf87393
+size 17209961

rag_truth_hal_detection_model/checkpoint-705/tokenizer_config.json

@@ -0,0 +1,2065 @@
+{
+  "added_tokens_decoder": {
+    "128000": {
+      "content": "<|begin_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128001": {
+      "content": "<|end_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128002": {
+      "content": "<|reserved_special_token_0|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128003": {
+      "content": "<|reserved_special_token_1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128004": {
+      "content": "<|reserved_special_token_2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128005": {
+      "content": "<|reserved_special_token_3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128006": {
+      "content": "<|start_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128007": {
+      "content": "<|end_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128008": {
+      "content": "<|reserved_special_token_4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128009": {
+      "content": "<|eot_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128010": {
+      "content": "<|reserved_special_token_5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128011": {
+      "content": "<|reserved_special_token_6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128012": {
+      "content": "<|reserved_special_token_7|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128013": {
+      "content": "<|reserved_special_token_8|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128014": {
+      "content": "<|reserved_special_token_9|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128015": {
+      "content": "<|reserved_special_token_10|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128016": {
+      "content": "<|reserved_special_token_11|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128017": {
+      "content": "<|reserved_special_token_12|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128018": {
+      "content": "<|reserved_special_token_13|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128019": {
+      "content": "<|reserved_special_token_14|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128020": {
+      "content": "<|reserved_special_token_15|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128021": {
+      "content": "<|reserved_special_token_16|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128022": {
+      "content": "<|reserved_special_token_17|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128023": {
+      "content": "<|reserved_special_token_18|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128024": {
+      "content": "<|reserved_special_token_19|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128025": {
+      "content": "<|reserved_special_token_20|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128026": {
+      "content": "<|reserved_special_token_21|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128027": {
+      "content": "<|reserved_special_token_22|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128028": {
+      "content": "<|reserved_special_token_23|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128029": {
+      "content": "<|reserved_special_token_24|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128030": {
+      "content": "<|reserved_special_token_25|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128031": {
+      "content": "<|reserved_special_token_26|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128032": {
+      "content": "<|reserved_special_token_27|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128033": {
+      "content": "<|reserved_special_token_28|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128034": {
+      "content": "<|reserved_special_token_29|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128035": {
+      "content": "<|reserved_special_token_30|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128036": {
+      "content": "<|reserved_special_token_31|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128037": {
+      "content": "<|reserved_special_token_32|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128038": {
+      "content": "<|reserved_special_token_33|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128039": {
+      "content": "<|reserved_special_token_34|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128040": {
+      "content": "<|reserved_special_token_35|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128041": {
+      "content": "<|reserved_special_token_36|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128042": {
+      "content": "<|reserved_special_token_37|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128043": {
+      "content": "<|reserved_special_token_38|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128044": {
+      "content": "<|reserved_special_token_39|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128045": {
+      "content": "<|reserved_special_token_40|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128046": {
+      "content": "<|reserved_special_token_41|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128047": {
+      "content": "<|reserved_special_token_42|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128048": {
+      "content": "<|reserved_special_token_43|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128049": {
+      "content": "<|reserved_special_token_44|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128050": {
+      "content": "<|reserved_special_token_45|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128051": {
+      "content": "<|reserved_special_token_46|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128052": {
+      "content": "<|reserved_special_token_47|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128053": {
+      "content": "<|reserved_special_token_48|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128054": {
+      "content": "<|reserved_special_token_49|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128055": {
+      "content": "<|reserved_special_token_50|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128056": {
+      "content": "<|reserved_special_token_51|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128057": {
+      "content": "<|reserved_special_token_52|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128058": {
+      "content": "<|reserved_special_token_53|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128059": {
+      "content": "<|reserved_special_token_54|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128060": {
+      "content": "<|reserved_special_token_55|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128061": {
+      "content": "<|reserved_special_token_56|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128062": {
+      "content": "<|reserved_special_token_57|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128063": {
+      "content": "<|reserved_special_token_58|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128064": {
+      "content": "<|reserved_special_token_59|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128065": {
+      "content": "<|reserved_special_token_60|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128066": {
+      "content": "<|reserved_special_token_61|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128067": {
+      "content": "<|reserved_special_token_62|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128068": {
+      "content": "<|reserved_special_token_63|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128069": {
+      "content": "<|reserved_special_token_64|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128070": {
+      "content": "<|reserved_special_token_65|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128071": {
+      "content": "<|reserved_special_token_66|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128072": {
+      "content": "<|reserved_special_token_67|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128073": {
+      "content": "<|reserved_special_token_68|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128074": {
+      "content": "<|reserved_special_token_69|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128075": {
+      "content": "<|reserved_special_token_70|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128076": {
+      "content": "<|reserved_special_token_71|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128077": {
+      "content": "<|reserved_special_token_72|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128078": {
+      "content": "<|reserved_special_token_73|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128079": {
+      "content": "<|reserved_special_token_74|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128080": {
+      "content": "<|reserved_special_token_75|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128081": {
+      "content": "<|reserved_special_token_76|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128082": {
+      "content": "<|reserved_special_token_77|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128083": {
+      "content": "<|reserved_special_token_78|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128084": {
+      "content": "<|reserved_special_token_79|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128085": {
+      "content": "<|reserved_special_token_80|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128086": {
+      "content": "<|reserved_special_token_81|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128087": {
+      "content": "<|reserved_special_token_82|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128088": {
+      "content": "<|reserved_special_token_83|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128089": {
+      "content": "<|reserved_special_token_84|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128090": {
+      "content": "<|reserved_special_token_85|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128091": {
+      "content": "<|reserved_special_token_86|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128092": {
+      "content": "<|reserved_special_token_87|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128093": {
+      "content": "<|reserved_special_token_88|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128094": {
+      "content": "<|reserved_special_token_89|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128095": {
+      "content": "<|reserved_special_token_90|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128096": {
+      "content": "<|reserved_special_token_91|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128097": {
+      "content": "<|reserved_special_token_92|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128098": {
+      "content": "<|reserved_special_token_93|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128099": {
+      "content": "<|reserved_special_token_94|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128100": {
+      "content": "<|reserved_special_token_95|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128101": {
+      "content": "<|reserved_special_token_96|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128102": {
+      "content": "<|reserved_special_token_97|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128103": {
+      "content": "<|reserved_special_token_98|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128104": {
+      "content": "<|reserved_special_token_99|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128105": {
+      "content": "<|reserved_special_token_100|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128106": {
+      "content": "<|reserved_special_token_101|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128107": {
+      "content": "<|reserved_special_token_102|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128108": {
+      "content": "<|reserved_special_token_103|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128109": {
+      "content": "<|reserved_special_token_104|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128110": {
+      "content": "<|reserved_special_token_105|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128111": {
+      "content": "<|reserved_special_token_106|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128112": {
+      "content": "<|reserved_special_token_107|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128113": {
+      "content": "<|reserved_special_token_108|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128114": {
+      "content": "<|reserved_special_token_109|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128115": {
+      "content": "<|reserved_special_token_110|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128116": {
+      "content": "<|reserved_special_token_111|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128117": {
+      "content": "<|reserved_special_token_112|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128118": {
+      "content": "<|reserved_special_token_113|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128119": {
+      "content": "<|reserved_special_token_114|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128120": {
+      "content": "<|reserved_special_token_115|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128121": {
+      "content": "<|reserved_special_token_116|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128122": {
+      "content": "<|reserved_special_token_117|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128123": {
+      "content": "<|reserved_special_token_118|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128124": {
+      "content": "<|reserved_special_token_119|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128125": {
+      "content": "<|reserved_special_token_120|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128126": {
+      "content": "<|reserved_special_token_121|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128127": {
+      "content": "<|reserved_special_token_122|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128128": {
+      "content": "<|reserved_special_token_123|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128129": {
+      "content": "<|reserved_special_token_124|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128130": {
+      "content": "<|reserved_special_token_125|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128131": {
+      "content": "<|reserved_special_token_126|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128132": {
+      "content": "<|reserved_special_token_127|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128133": {
+      "content": "<|reserved_special_token_128|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128134": {
+      "content": "<|reserved_special_token_129|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128135": {
+      "content": "<|reserved_special_token_130|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128136": {
+      "content": "<|reserved_special_token_131|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128137": {
+      "content": "<|reserved_special_token_132|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128138": {
+      "content": "<|reserved_special_token_133|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128139": {
+      "content": "<|reserved_special_token_134|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128140": {
+      "content": "<|reserved_special_token_135|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128141": {
+      "content": "<|reserved_special_token_136|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128142": {
+      "content": "<|reserved_special_token_137|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128143": {
+      "content": "<|reserved_special_token_138|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128144": {
+      "content": "<|reserved_special_token_139|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128145": {
+      "content": "<|reserved_special_token_140|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128146": {
+      "content": "<|reserved_special_token_141|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128147": {
+      "content": "<|reserved_special_token_142|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128148": {
+      "content": "<|reserved_special_token_143|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128149": {
+      "content": "<|reserved_special_token_144|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128150": {
+      "content": "<|reserved_special_token_145|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128151": {
+      "content": "<|reserved_special_token_146|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128152": {
+      "content": "<|reserved_special_token_147|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128153": {
+      "content": "<|reserved_special_token_148|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128154": {
+      "content": "<|reserved_special_token_149|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128155": {
+      "content": "<|reserved_special_token_150|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128156": {
+      "content": "<|reserved_special_token_151|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128157": {
+      "content": "<|reserved_special_token_152|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128158": {
+      "content": "<|reserved_special_token_153|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128159": {
+      "content": "<|reserved_special_token_154|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128160": {
+      "content": "<|reserved_special_token_155|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128161": {
+      "content": "<|reserved_special_token_156|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128162": {
+      "content": "<|reserved_special_token_157|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128163": {
+      "content": "<|reserved_special_token_158|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128164": {
+      "content": "<|reserved_special_token_159|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128165": {
+      "content": "<|reserved_special_token_160|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128166": {
+      "content": "<|reserved_special_token_161|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128167": {
+      "content": "<|reserved_special_token_162|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128168": {
+      "content": "<|reserved_special_token_163|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128169": {
+      "content": "<|reserved_special_token_164|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128170": {
+      "content": "<|reserved_special_token_165|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128171": {
+      "content": "<|reserved_special_token_166|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128172": {
+      "content": "<|reserved_special_token_167|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128173": {
+      "content": "<|reserved_special_token_168|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128174": {
+      "content": "<|reserved_special_token_169|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128175": {
+      "content": "<|reserved_special_token_170|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128176": {
+      "content": "<|reserved_special_token_171|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128177": {
+      "content": "<|reserved_special_token_172|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128178": {
+      "content": "<|reserved_special_token_173|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128179": {
+      "content": "<|reserved_special_token_174|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128180": {
+      "content": "<|reserved_special_token_175|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128181": {
+      "content": "<|reserved_special_token_176|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128182": {
+      "content": "<|reserved_special_token_177|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128183": {
+      "content": "<|reserved_special_token_178|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128184": {
+      "content": "<|reserved_special_token_179|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128185": {
+      "content": "<|reserved_special_token_180|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128186": {
+      "content": "<|reserved_special_token_181|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128187": {
+      "content": "<|reserved_special_token_182|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128188": {
+      "content": "<|reserved_special_token_183|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128189": {
+      "content": "<|reserved_special_token_184|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128190": {
+      "content": "<|reserved_special_token_185|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128191": {
+      "content": "<|reserved_special_token_186|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128192": {
+      "content": "<|reserved_special_token_187|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128193": {
+      "content": "<|reserved_special_token_188|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128194": {
+      "content": "<|reserved_special_token_189|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128195": {
+      "content": "<|reserved_special_token_190|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128196": {
+      "content": "<|reserved_special_token_191|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128197": {
+      "content": "<|reserved_special_token_192|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128198": {
+      "content": "<|reserved_special_token_193|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128199": {
+      "content": "<|reserved_special_token_194|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128200": {
+      "content": "<|reserved_special_token_195|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128201": {
+      "content": "<|reserved_special_token_196|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128202": {
+      "content": "<|reserved_special_token_197|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128203": {
+      "content": "<|reserved_special_token_198|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128204": {
+      "content": "<|reserved_special_token_199|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128205": {
+      "content": "<|reserved_special_token_200|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128206": {
+      "content": "<|reserved_special_token_201|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128207": {
+      "content": "<|reserved_special_token_202|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128208": {
+      "content": "<|reserved_special_token_203|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128209": {
+      "content": "<|reserved_special_token_204|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128210": {
+      "content": "<|reserved_special_token_205|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128211": {
+      "content": "<|reserved_special_token_206|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128212": {
+      "content": "<|reserved_special_token_207|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128213": {
+      "content": "<|reserved_special_token_208|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128214": {
+      "content": "<|reserved_special_token_209|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128215": {
+      "content": "<|reserved_special_token_210|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128216": {
+      "content": "<|reserved_special_token_211|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128217": {
+      "content": "<|reserved_special_token_212|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128218": {
+      "content": "<|reserved_special_token_213|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128219": {
+      "content": "<|reserved_special_token_214|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128220": {
+      "content": "<|reserved_special_token_215|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128221": {
+      "content": "<|reserved_special_token_216|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128222": {
+      "content": "<|reserved_special_token_217|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128223": {
+      "content": "<|reserved_special_token_218|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128224": {
+      "content": "<|reserved_special_token_219|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128225": {
+      "content": "<|reserved_special_token_220|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128226": {
+      "content": "<|reserved_special_token_221|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128227": {
+      "content": "<|reserved_special_token_222|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128228": {
+      "content": "<|reserved_special_token_223|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128229": {
+      "content": "<|reserved_special_token_224|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128230": {
+      "content": "<|reserved_special_token_225|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128231": {
+      "content": "<|reserved_special_token_226|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128232": {
+      "content": "<|reserved_special_token_227|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128233": {
+      "content": "<|reserved_special_token_228|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128234": {
+      "content": "<|reserved_special_token_229|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128235": {
+      "content": "<|reserved_special_token_230|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128236": {
+      "content": "<|reserved_special_token_231|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128237": {
+      "content": "<|reserved_special_token_232|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128238": {
+      "content": "<|reserved_special_token_233|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128239": {
+      "content": "<|reserved_special_token_234|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128240": {
+      "content": "<|reserved_special_token_235|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128241": {
+      "content": "<|reserved_special_token_236|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128242": {
+      "content": "<|reserved_special_token_237|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128243": {
+      "content": "<|reserved_special_token_238|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128244": {
+      "content": "<|reserved_special_token_239|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128245": {
+      "content": "<|reserved_special_token_240|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128246": {
+      "content": "<|reserved_special_token_241|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128247": {
+      "content": "<|reserved_special_token_242|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128248": {
+      "content": "<|reserved_special_token_243|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128249": {
+      "content": "<|reserved_special_token_244|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128250": {
+      "content": "<|reserved_special_token_245|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128251": {
+      "content": "<|reserved_special_token_246|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128252": {
+      "content": "<|reserved_special_token_247|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128253": {
+      "content": "<|reserved_special_token_248|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128254": {
+      "content": "<|reserved_special_token_249|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128255": {
+      "content": "<|reserved_special_token_250|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|begin_of_text|>",
+  "chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ system_message + '\n' }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ 'Human: ' + content + '\nAssistant:' }}{% elif message['role'] == 'assistant' %}{{ content + '<|end_of_text|>' + '\n' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|end_of_text|>",
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|end_of_text|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}

rag_truth_hal_detection_model/checkpoint-705/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d09813640ec41274376e23c6cb314f140c10d2082cfed6988625515ea961122c
+size 7032

rag_truth_hal_detection_model/checkpoint-705/zero_to_fp32.py

@@ -0,0 +1,674 @@
+#!/usr/bin/env python
+
+# Copyright (c) Microsoft Corporation.
+# SPDX-License-Identifier: Apache-2.0
+
+# DeepSpeed Team
+
+# This script extracts fp32 consolidated weights from a zero 1, 2 and 3 DeepSpeed checkpoints. It gets
+# copied into the top level checkpoint dir, so the user can easily do the conversion at any point in
+# the future. Once extracted, the weights don't require DeepSpeed and can be used in any
+# application.
+#
+# example:
+#   python zero_to_fp32.py . output_dir/
+#   or
+#   python zero_to_fp32.py . output_dir/ --safe_serialization
+
+import argparse
+import torch
+import glob
+import math
+import os
+import re
+import json
+from tqdm import tqdm
+from collections import OrderedDict
+from dataclasses import dataclass
+
+# while this script doesn't use deepspeed to recover data, since the checkpoints are pickled with
+# DeepSpeed data structures it has to be available in the current python environment.
+from deepspeed.utils import logger
+from deepspeed.checkpoint.constants import (DS_VERSION, OPTIMIZER_STATE_DICT, SINGLE_PARTITION_OF_FP32_GROUPS,
+                                            FP32_FLAT_GROUPS, ZERO_STAGE, PARTITION_COUNT, PARAM_SHAPES, BUFFER_NAMES,
+                                            FROZEN_PARAM_SHAPES, FROZEN_PARAM_FRAGMENTS)
+
+
+@dataclass
+class zero_model_state:
+    buffers: dict()
+    param_shapes: dict()
+    shared_params: list
+    ds_version: int
+    frozen_param_shapes: dict()
+    frozen_param_fragments: dict()
+
+
+debug = 0
+
+# load to cpu
+device = torch.device('cpu')
+
+
+def atoi(text):
+    return int(text) if text.isdigit() else text
+
+
+def natural_keys(text):
+    '''
+    alist.sort(key=natural_keys) sorts in human order
+    http://nedbatchelder.com/blog/200712/human_sorting.html
+    (See Toothy's implementation in the comments)
+    '''
+    return [atoi(c) for c in re.split(r'(\d+)', text)]
+
+
+def get_model_state_file(checkpoint_dir, zero_stage):
+    if not os.path.isdir(checkpoint_dir):
+        raise FileNotFoundError(f"Directory '{checkpoint_dir}' doesn't exist")
+
+    # there should be only one file
+    if zero_stage <= 2:
+        file = os.path.join(checkpoint_dir, "mp_rank_00_model_states.pt")
+    elif zero_stage == 3:
+        file = os.path.join(checkpoint_dir, "zero_pp_rank_0_mp_rank_00_model_states.pt")
+
+    if not os.path.exists(file):
+        raise FileNotFoundError(f"can't find model states file at '{file}'")
+
+    return file
+
+
+def get_checkpoint_files(checkpoint_dir, glob_pattern):
+    # XXX: need to test that this simple glob rule works for multi-node setup too
+    ckpt_files = sorted(glob.glob(os.path.join(checkpoint_dir, glob_pattern)), key=natural_keys)
+
+    if len(ckpt_files) == 0:
+        raise FileNotFoundError(f"can't find {glob_pattern} files in directory '{checkpoint_dir}'")
+
+    return ckpt_files
+
+
+def get_optim_files(checkpoint_dir):
+    return get_checkpoint_files(checkpoint_dir, "*_optim_states.pt")
+
+
+def get_model_state_files(checkpoint_dir):
+    return get_checkpoint_files(checkpoint_dir, "*_model_states.pt")
+
+
+def parse_model_states(files):
+    zero_model_states = []
+    for file in files:
+        state_dict = torch.load(file, map_location=device)
+
+        if BUFFER_NAMES not in state_dict:
+            raise ValueError(f"{file} is not a model state checkpoint")
+        buffer_names = state_dict[BUFFER_NAMES]
+        if debug:
+            print("Found buffers:", buffer_names)
+
+        # recover just the buffers while restoring them to fp32 if they were saved in fp16
+        buffers = {k: v.float() for k, v in state_dict["module"].items() if k in buffer_names}
+        param_shapes = state_dict[PARAM_SHAPES]
+
+        # collect parameters that are included in param_shapes
+        param_names = []
+        for s in param_shapes:
+            for name in s.keys():
+                param_names.append(name)
+
+        # update with frozen parameters
+        frozen_param_shapes = state_dict.get(FROZEN_PARAM_SHAPES, None)
+        if frozen_param_shapes is not None:
+            if debug:
+                print(f"Found frozen_param_shapes: {frozen_param_shapes}")
+            param_names += list(frozen_param_shapes.keys())
+
+        # handle shared params
+        shared_params = [[k, v] for k, v in state_dict["shared_params"].items()]
+
+        ds_version = state_dict.get(DS_VERSION, None)
+
+        frozen_param_fragments = state_dict.get(FROZEN_PARAM_FRAGMENTS, None)
+
+        z_model_state = zero_model_state(buffers=buffers,
+                                         param_shapes=param_shapes,
+                                         shared_params=shared_params,
+                                         ds_version=ds_version,
+                                         frozen_param_shapes=frozen_param_shapes,
+                                         frozen_param_fragments=frozen_param_fragments)
+        zero_model_states.append(z_model_state)
+
+    return zero_model_states
+
+
+def parse_optim_states(files, ds_checkpoint_dir):
+    total_files = len(files)
+    state_dicts = []
+    for f in files:
+        state_dict = torch.load(f, map_location=device)
+        # immediately discard the potentially huge 2 optimizer states as we only care for fp32 master weights
+        # and also handle the case where it was already removed by another helper script
+        state_dict["optimizer_state_dict"].pop("optimizer_state_dict", None)
+        state_dicts.append(state_dict)
+
+    if not ZERO_STAGE in state_dicts[0][OPTIMIZER_STATE_DICT]:
+        raise ValueError(f"{files[0]} is not a zero checkpoint")
+    zero_stage = state_dicts[0][OPTIMIZER_STATE_DICT][ZERO_STAGE]
+    world_size = state_dicts[0][OPTIMIZER_STATE_DICT][PARTITION_COUNT]
+
+    # For ZeRO-2 each param group can have different partition_count as data parallelism for expert
+    # parameters can be different from data parallelism for non-expert parameters. So we can just
+    # use the max of the partition_count to get the dp world_size.
+
+    if type(world_size) is list:
+        world_size = max(world_size)
+
+    if world_size != total_files:
+        raise ValueError(
+            f"Expected {world_size} of '*_optim_states.pt' under '{ds_checkpoint_dir}' but found {total_files} files. "
+            "Possibly due to an overwrite of an old checkpoint, or a checkpoint didn't get saved by one or more processes."
+        )
+
+    # the groups are named differently in each stage
+    if zero_stage <= 2:
+        fp32_groups_key = SINGLE_PARTITION_OF_FP32_GROUPS
+    elif zero_stage == 3:
+        fp32_groups_key = FP32_FLAT_GROUPS
+    else:
+        raise ValueError(f"unknown zero stage {zero_stage}")
+
+    if zero_stage <= 2:
+        fp32_flat_groups = [state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key] for i in range(len(state_dicts))]
+    elif zero_stage == 3:
+        # if there is more than one param group, there will be multiple flattened tensors - one
+        # flattened tensor per group - for simplicity merge them into a single tensor
+        #
+        # XXX: could make the script more memory efficient for when there are multiple groups - it
+        # will require matching the sub-lists of param_shapes for each param group flattened tensor
+
+        fp32_flat_groups = [
+            torch.cat(state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key], 0) for i in range(len(state_dicts))
+        ]
+
+    return zero_stage, world_size, fp32_flat_groups
+
+
+def _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters):
+    """
+    Returns fp32 state_dict reconstructed from ds checkpoint
+
+    Args:
+        - ``ds_checkpoint_dir``: path to the deepspeed checkpoint folder (where the optimizer files are)
+
+    """
+    print(f"Processing zero checkpoint '{ds_checkpoint_dir}'")
+
+    optim_files = get_optim_files(ds_checkpoint_dir)
+    zero_stage, world_size, fp32_flat_groups = parse_optim_states(optim_files, ds_checkpoint_dir)
+    print(f"Detected checkpoint of type zero stage {zero_stage}, world_size: {world_size}")
+
+    model_files = get_model_state_files(ds_checkpoint_dir)
+
+    zero_model_states = parse_model_states(model_files)
+    print(f'Parsing checkpoint created by deepspeed=={zero_model_states[0].ds_version}')
+
+    if zero_stage <= 2:
+        return _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                                          exclude_frozen_parameters)
+    elif zero_stage == 3:
+        return _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                                          exclude_frozen_parameters)
+
+
+def _zero2_merge_frozen_params(state_dict, zero_model_states):
+    if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
+        return
+
+    frozen_param_shapes = zero_model_states[0].frozen_param_shapes
+    frozen_param_fragments = zero_model_states[0].frozen_param_fragments
+
+    if debug:
+        num_elem = sum(s.numel() for s in frozen_param_shapes.values())
+        print(f'rank 0: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
+
+        wanted_params = len(frozen_param_shapes)
+        wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
+        avail_numel = sum([p.numel() for p in frozen_param_fragments.values()])
+        print(f'Frozen params: Have {avail_numel} numels to process.')
+        print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
+
+    total_params = 0
+    total_numel = 0
+    for name, shape in frozen_param_shapes.items():
+        total_params += 1
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+
+        state_dict[name] = frozen_param_fragments[name]
+
+        if debug:
+            print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
+
+    print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _has_callable(obj, fn):
+    attr = getattr(obj, fn, None)
+    return callable(attr)
+
+
+def _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
+    param_shapes = zero_model_states[0].param_shapes
+
+    # Reconstruction protocol:
+    #
+    # XXX: document this
+
+    if debug:
+        for i in range(world_size):
+            for j in range(len(fp32_flat_groups[0])):
+                print(f"{FP32_FLAT_GROUPS}[{i}][{j}].shape={fp32_flat_groups[i][j].shape}")
+
+    # XXX: memory usage doubles here (zero2)
+    num_param_groups = len(fp32_flat_groups[0])
+    merged_single_partition_of_fp32_groups = []
+    for i in range(num_param_groups):
+        merged_partitions = [sd[i] for sd in fp32_flat_groups]
+        full_single_fp32_vector = torch.cat(merged_partitions, 0)
+        merged_single_partition_of_fp32_groups.append(full_single_fp32_vector)
+    avail_numel = sum(
+        [full_single_fp32_vector.numel() for full_single_fp32_vector in merged_single_partition_of_fp32_groups])
+
+    if debug:
+        wanted_params = sum([len(shapes) for shapes in param_shapes])
+        wanted_numel = sum([sum(shape.numel() for shape in shapes.values()) for shapes in param_shapes])
+        # not asserting if there is a mismatch due to possible padding
+        print(f"Have {avail_numel} numels to process.")
+        print(f"Need {wanted_numel} numels in {wanted_params} params.")
+
+    # params
+    # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
+    # out-of-core computing solution
+    total_numel = 0
+    total_params = 0
+    for shapes, full_single_fp32_vector in zip(param_shapes, merged_single_partition_of_fp32_groups):
+        offset = 0
+        avail_numel = full_single_fp32_vector.numel()
+        for name, shape in shapes.items():
+
+            unpartitioned_numel = shape.numel() if _has_callable(shape, 'numel') else math.prod(shape)
+            total_numel += unpartitioned_numel
+            total_params += 1
+
+            if debug:
+                print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
+            state_dict[name] = full_single_fp32_vector.narrow(0, offset, unpartitioned_numel).view(shape)
+            offset += unpartitioned_numel
+
+        # Z2 started to align to 2*world_size to improve nccl performance. Therefore both offset and
+        # avail_numel can differ by anywhere between 0..2*world_size. Due to two unrelated complex
+        # paddings performed in the code it's almost impossible to predict the exact numbers w/o the
+        # live optimizer object, so we are checking that the numbers are within the right range
+        align_to = 2 * world_size
+
+        def zero2_align(x):
+            return align_to * math.ceil(x / align_to)
+
+        if debug:
+            print(f"original offset={offset}, avail_numel={avail_numel}")
+
+        offset = zero2_align(offset)
+        avail_numel = zero2_align(avail_numel)
+
+        if debug:
+            print(f"aligned  offset={offset}, avail_numel={avail_numel}")
+
+        # Sanity check
+        if offset != avail_numel:
+            raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
+
+    print(f"Reconstructed fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                               exclude_frozen_parameters):
+    state_dict = OrderedDict()
+
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+
+    if not exclude_frozen_parameters:
+        _zero2_merge_frozen_params(state_dict, zero_model_states)
+
+    _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
+
+    # recover shared parameters
+    for pair in zero_model_states[0].shared_params:
+        if pair[1] in state_dict:
+            state_dict[pair[0]] = state_dict[pair[1]]
+
+    return state_dict
+
+
+def zero3_partitioned_param_info(unpartitioned_numel, world_size):
+    remainder = unpartitioned_numel % world_size
+    padding_numel = (world_size - remainder) if remainder else 0
+    partitioned_numel = math.ceil(unpartitioned_numel / world_size)
+    return partitioned_numel, padding_numel
+
+
+def _zero3_merge_frozen_params(state_dict, world_size, zero_model_states):
+    if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
+        return
+
+    if debug:
+        for i in range(world_size):
+            num_elem = sum(s.numel() for s in zero_model_states[i].frozen_param_fragments.values())
+            print(f'rank {i}: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
+
+        frozen_param_shapes = zero_model_states[0].frozen_param_shapes
+        wanted_params = len(frozen_param_shapes)
+        wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
+        avail_numel = sum([p.numel() for p in zero_model_states[0].frozen_param_fragments.values()]) * world_size
+        print(f'Frozen params: Have {avail_numel} numels to process.')
+        print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
+
+    total_params = 0
+    total_numel = 0
+    for name, shape in zero_model_states[0].frozen_param_shapes.items():
+        total_params += 1
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+
+        param_frags = tuple(model_state.frozen_param_fragments[name] for model_state in zero_model_states)
+        state_dict[name] = torch.cat(param_frags, 0).narrow(0, 0, unpartitioned_numel).view(shape)
+
+        partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
+
+        if debug:
+            print(
+                f"Frozen params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
+            )
+
+    print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
+    param_shapes = zero_model_states[0].param_shapes
+    avail_numel = fp32_flat_groups[0].numel() * world_size
+    # Reconstruction protocol: For zero3 we need to zip the partitions together at boundary of each
+    # param, re-consolidating each param, while dealing with padding if any
+
+    # merge list of dicts, preserving order
+    param_shapes = {k: v for d in param_shapes for k, v in d.items()}
+
+    if debug:
+        for i in range(world_size):
+            print(f"{FP32_FLAT_GROUPS}[{i}].shape={fp32_flat_groups[i].shape}")
+
+        wanted_params = len(param_shapes)
+        wanted_numel = sum(shape.numel() for shape in param_shapes.values())
+        # not asserting if there is a mismatch due to possible padding
+        avail_numel = fp32_flat_groups[0].numel() * world_size
+        print(f"Trainable params: Have {avail_numel} numels to process.")
+        print(f"Trainable params: Need {wanted_numel} numels in {wanted_params} params.")
+
+    # params
+    # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
+    # out-of-core computing solution
+    offset = 0
+    total_numel = 0
+    total_params = 0
+    for name, shape in tqdm(param_shapes.items(), desc='Gathering Sharded Weights'):
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+        total_params += 1
+        partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
+
+        if debug:
+            print(
+                f"Trainable params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
+            )
+
+        # XXX: memory usage doubles here
+        state_dict[name] = torch.cat(
+            tuple(fp32_flat_groups[i].narrow(0, offset, partitioned_numel) for i in range(world_size)),
+            0).narrow(0, 0, unpartitioned_numel).view(shape)
+        offset += partitioned_numel
+
+    offset *= world_size
+
+    # Sanity check
+    if offset != avail_numel:
+        raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
+
+    print(f"Reconstructed Trainable fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                               exclude_frozen_parameters):
+    state_dict = OrderedDict()
+
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+
+    if not exclude_frozen_parameters:
+        _zero3_merge_frozen_params(state_dict, world_size, zero_model_states)
+
+    _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
+
+    # recover shared parameters
+    for pair in zero_model_states[0].shared_params:
+        if pair[1] in state_dict:
+            state_dict[pair[0]] = state_dict[pair[1]]
+
+    return state_dict
+
+
+def get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag=None, exclude_frozen_parameters=False):
+    """
+    Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated state_dict that can be loaded with
+    ``load_state_dict()`` and used for training without DeepSpeed or shared with others, for example
+    via a model hub.
+
+    Args:
+        - ``checkpoint_dir``: path to the desired checkpoint folder
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in 'latest' file. e.g., ``global_step14``
+        - ``exclude_frozen_parameters``: exclude frozen parameters
+
+    Returns:
+        - pytorch ``state_dict``
+
+    Note: this approach may not work if your application doesn't have sufficient free CPU memory and
+    you may need to use the offline approach using the ``zero_to_fp32.py`` script that is saved with
+    the checkpoint.
+
+    A typical usage might be ::
+
+        from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
+        # do the training and checkpoint saving
+        state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir) # already on cpu
+        model = model.cpu() # move to cpu
+        model.load_state_dict(state_dict)
+        # submit to model hub or save the model to share with others
+
+    In this example the ``model`` will no longer be usable in the deepspeed context of the same
+    application. i.e. you will need to re-initialize the deepspeed engine, since
+    ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
+
+    If you want it all done for you, use ``load_state_dict_from_zero_checkpoint`` instead.
+
+    """
+    if tag is None:
+        latest_path = os.path.join(checkpoint_dir, 'latest')
+        if os.path.isfile(latest_path):
+            with open(latest_path, 'r') as fd:
+                tag = fd.read().strip()
+        else:
+            raise ValueError(f"Unable to find 'latest' file at {latest_path}")
+
+    ds_checkpoint_dir = os.path.join(checkpoint_dir, tag)
+
+    if not os.path.isdir(ds_checkpoint_dir):
+        raise FileNotFoundError(f"Directory '{ds_checkpoint_dir}' doesn't exist")
+
+    return _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters)
+
+
+def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir,
+                                               output_dir,
+                                               max_shard_size="5GB",
+                                               safe_serialization=False,
+                                               tag=None,
+                                               exclude_frozen_parameters=False):
+    """
+    Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict`` file that can be
+    loaded with ``torch.load(file)`` + ``load_state_dict()`` and used for training without DeepSpeed.
+
+    Args:
+        - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
+        - ``output_dir``: directory to the pytorch fp32 state_dict output files
+        - ``max_shard_size``: the maximum size for a checkpoint before being sharded, default value is 5GB
+        - ``safe_serialization``:  whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
+        - ``exclude_frozen_parameters``: exclude frozen parameters
+    """
+    # Dependency pre-check
+    if safe_serialization:
+        try:
+            from safetensors.torch import save_file
+        except ImportError:
+            print('If you want to use `safe_serialization`, please `pip install safetensors`')
+            raise
+    if max_shard_size is not None:
+        try:
+            from huggingface_hub import split_torch_state_dict_into_shards
+        except ImportError:
+            print('If you want to use `max_shard_size`, please `pip install huggingface_hub`')
+            raise
+
+    # Convert zero checkpoint to state_dict
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag, exclude_frozen_parameters)
+
+    # Shard the model if it is too big.
+    weights_name = "model.safetensors" if safe_serialization else "pytorch_model.bin"
+    if max_shard_size is not None:
+        filename_pattern = weights_name.replace(".bin", "{suffix}.bin").replace(".safetensors", "{suffix}.safetensors")
+        state_dict_split = split_torch_state_dict_into_shards(state_dict,
+                                                              filename_pattern=filename_pattern,
+                                                              max_shard_size=max_shard_size)
+    else:
+        from collections import namedtuple
+        StateDictSplit = namedtuple("StateDictSplit", ["is_sharded", "filename_to_tensors"])
+        state_dict_split = StateDictSplit(is_sharded=False,
+                                          filename_to_tensors={weights_name: list(state_dict.keys())})
+
+    # Save the model
+    filename_to_tensors = state_dict_split.filename_to_tensors.items()
+    for shard_file, tensors in tqdm(filename_to_tensors, desc="Saving checkpoint shards"):
+        shard = {tensor: state_dict[tensor].contiguous() for tensor in tensors}
+        output_path = os.path.join(output_dir, shard_file)
+        if safe_serialization:
+            save_file(shard, output_path, metadata={"format": "pt"})
+        else:
+            torch.save(shard, output_path)
+
+    # Save index if sharded
+    if state_dict_split.is_sharded:
+        index = {
+            "metadata": state_dict_split.metadata,
+            "weight_map": state_dict_split.tensor_to_filename,
+        }
+        save_index_file = "model.safetensors.index.json" if safe_serialization else "pytorch_model.bin.index.json"
+        save_index_file = os.path.join(output_dir, save_index_file)
+        with open(save_index_file, "w", encoding="utf-8") as f:
+            content = json.dumps(index, indent=2, sort_keys=True) + "\n"
+            f.write(content)
+
+
+def load_state_dict_from_zero_checkpoint(model, checkpoint_dir, tag=None):
+    """
+    1. Put the provided model to cpu
+    2. Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict``
+    3. Load it into the provided model
+
+    Args:
+        - ``model``: the model object to update
+        - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
+
+    Returns:
+        - ``model`: modified model
+
+    Make sure you have plenty of CPU memory available before you call this function. If you don't
+    have enough use the ``zero_to_fp32.py`` utility to do the conversion. You will find it
+    conveniently placed for you in the checkpoint folder.
+
+    A typical usage might be ::
+
+        from deepspeed.utils.zero_to_fp32 import load_state_dict_from_zero_checkpoint
+        model = load_state_dict_from_zero_checkpoint(trainer.model, checkpoint_dir)
+        # submit to model hub or save the model to share with others
+
+    Note, that once this was run, the ``model`` will no longer be usable in the deepspeed context
+    of the same application. i.e. you will need to re-initialize the deepspeed engine, since
+    ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
+
+    """
+    logger.info(f"Extracting fp32 weights")
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
+
+    logger.info(f"Overwriting model with fp32 weights")
+    model = model.cpu()
+    model.load_state_dict(state_dict, strict=False)
+
+    return model
+
+
+if __name__ == "__main__":
+    parser = argparse.ArgumentParser()
+    parser.add_argument("checkpoint_dir",
+                        type=str,
+                        help="path to the desired checkpoint folder, e.g., path/checkpoint-12")
+    parser.add_argument("output_dir",
+                        type=str,
+                        help="directory to the pytorch fp32 state_dict output files"
+                        "(e.g. path/checkpoint-12-output/)")
+    parser.add_argument(
+        "--max_shard_size",
+        type=str,
+        default="5GB",
+        help="The maximum size for a checkpoint before being sharded. Checkpoints shard will then be each of size"
+        "lower than this size. If expressed as a string, needs to be digits followed by a unit (like `5MB`"
+        "We default it to 5GB in order for models to be able to run easily on free-tier google colab instances"
+        "without CPU OOM issues.")
+    parser.add_argument(
+        "--safe_serialization",
+        default=False,
+        action='store_true',
+        help="Whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).")
+    parser.add_argument("-t",
+                        "--tag",
+                        type=str,
+                        default=None,
+                        help="checkpoint tag used as a unique identifier for checkpoint. e.g., global_step1")
+    parser.add_argument("--exclude_frozen_parameters", action='store_true', help="exclude frozen parameters")
+    parser.add_argument("-d", "--debug", action='store_true', help="enable debug")
+    args = parser.parse_args()
+
+    debug = args.debug
+
+    convert_zero_checkpoint_to_fp32_state_dict(args.checkpoint_dir,
+                                               args.output_dir,
+                                               max_shard_size=args.max_shard_size,
+                                               safe_serialization=args.safe_serialization,
+                                               tag=args.tag,
+                                               exclude_frozen_parameters=args.exclude_frozen_parameters)

rag_truth_hal_detection_model/config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "meta-llama/Meta-Llama-3-8B",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": 128001,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 8192,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.1",
+  "use_cache": false,
+  "vocab_size": 128256
+}

rag_truth_hal_detection_model/generation_config.json

@@ -0,0 +1,9 @@
+{
+  "bos_token_id": 128000,
+  "do_sample": true,
+  "eos_token_id": 128001,
+  "max_length": 4096,
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.46.1"
+}

rag_truth_hal_detection_model/llamaboard_config.yaml

@@ -0,0 +1,66 @@
+top.booster: auto
+top.checkpoint_path: null
+top.finetuning_type: full
+top.model_name: Llama-3-8B
+top.quantization_bit: none
+top.quantization_method: bitsandbytes
+top.rope_scaling: none
+top.template: default
+train.additional_target: ''
+train.badam_mode: layer
+train.badam_switch_interval: 50
+train.badam_switch_mode: ascending
+train.badam_update_ratio: 0.05
+train.batch_size: 1
+train.compute_type: bf16
+train.create_new_adapter: false
+train.cutoff_len: 4096
+train.dataset:
+- train_hal_detection
+train.dataset_dir: data
+train.ds_offload: false
+train.ds_stage: '2'
+train.extra_args: '{"optim": "adamw_torch"}'
+train.freeze_extra_modules: ''
+train.freeze_trainable_layers: 2
+train.freeze_trainable_modules: all
+train.galore_rank: 16
+train.galore_scale: 0.25
+train.galore_target: all
+train.galore_update_interval: 200
+train.gradient_accumulation_steps: 8
+train.learning_rate: 5e-6
+train.logging_steps: 1
+train.lora_alpha: 16
+train.lora_dropout: 0
+train.lora_rank: 8
+train.lora_target: ''
+train.loraplus_lr_ratio: 0
+train.lr_scheduler_type: cosine
+train.mask_history: false
+train.max_grad_norm: '1.0'
+train.max_samples: '100000'
+train.neat_packing: false
+train.neftune_alpha: 0
+train.num_train_epochs: '3.0'
+train.packing: false
+train.ppo_score_norm: false
+train.ppo_whiten_rewards: false
+train.pref_beta: 0.1
+train.pref_ftx: 0
+train.pref_loss: sigmoid
+train.report_to: false
+train.resize_vocab: false
+train.reward_model: null
+train.save_steps: 1000
+train.shift_attn: false
+train.train_on_prompt: false
+train.training_stage: Supervised Fine-Tuning
+train.use_badam: false
+train.use_dora: false
+train.use_galore: false
+train.use_llama_pro: false
+train.use_pissa: false
+train.use_rslora: false
+train.val_size: 0
+train.warmup_steps: 10

rag_truth_hal_detection_model/model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78c97c60ccbad3d9a18556229e0610515687a995d517b2bc96b00437b0222f4f
+size 4976698672

rag_truth_hal_detection_model/model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64ed7f6307a878b2b67e795b23b331653b75d7b8e24fff12de9988a46b207ea1
+size 4999802720

rag_truth_hal_detection_model/model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:146c49a7d418706caae25f4bbba4cf5e6e6106ba2d29c2b1c003f9dc06a324e5
+size 4915916176

rag_truth_hal_detection_model/model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65d02ea8ee9562ccc8a8af2a3716d3043b8684d9baca99019a889b749c11c936
+size 1168138808

rag_truth_hal_detection_model/model.safetensors.index.json

@@ -0,0 +1,298 @@
+{
+  "metadata": {
+    "total_size": 16060522496
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00004-of-00004.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.norm.weight": "model-00004-of-00004.safetensors"
+  }
+}

rag_truth_hal_detection_model/running_log.txt

@@ -0,0 +1,1649 @@
+[INFO|2024-11-22 23:48:08] parser.py:355 >> Process rank: 3, device: cuda:3, n_gpu: 1, distributed training: True, compute dtype: torch.bfloat16
+
+[INFO|2024-11-22 23:48:08] parser.py:355 >> Process rank: 5, device: cuda:5, n_gpu: 1, distributed training: True, compute dtype: torch.bfloat16
+
+[INFO|2024-11-22 23:48:08] parser.py:355 >> Process rank: 0, device: cuda:0, n_gpu: 1, distributed training: True, compute dtype: torch.bfloat16
+
+[INFO|2024-11-22 23:48:08] parser.py:355 >> Process rank: 2, device: cuda:2, n_gpu: 1, distributed training: True, compute dtype: torch.bfloat16
+
+[INFO|2024-11-22 23:48:08] parser.py:355 >> Process rank: 1, device: cuda:1, n_gpu: 1, distributed training: True, compute dtype: torch.bfloat16
+
+[INFO|2024-11-22 23:48:08] parser.py:355 >> Process rank: 4, device: cuda:4, n_gpu: 1, distributed training: True, compute dtype: torch.bfloat16
+
+[INFO|2024-11-22 23:48:08] parser.py:355 >> Process rank: 7, device: cuda:7, n_gpu: 1, distributed training: True, compute dtype: torch.bfloat16
+
+[INFO|2024-11-22 23:48:08] parser.py:355 >> Process rank: 6, device: cuda:6, n_gpu: 1, distributed training: True, compute dtype: torch.bfloat16
+
+[INFO|2024-11-22 23:48:08] configuration_utils.py:679 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--meta-llama--Meta-Llama-3-8B/snapshots/8cde5ca8380496c9a6cc7ef3a8b46a0372a1d920/config.json
+
+[INFO|2024-11-22 23:48:08] configuration_utils.py:746 >> Model config LlamaConfig {
+  "_name_or_path": "meta-llama/Meta-Llama-3-8B",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": 128001,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 8192,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.1",
+  "use_cache": true,
+  "vocab_size": 128256
+}
+
+
+[INFO|2024-11-22 23:48:09] tokenization_utils_base.py:2211 >> loading file tokenizer.json from cache at /root/.cache/huggingface/hub/models--meta-llama--Meta-Llama-3-8B/snapshots/8cde5ca8380496c9a6cc7ef3a8b46a0372a1d920/tokenizer.json
+
+[INFO|2024-11-22 23:48:09] tokenization_utils_base.py:2211 >> loading file tokenizer.model from cache at None
+
+[INFO|2024-11-22 23:48:09] tokenization_utils_base.py:2211 >> loading file added_tokens.json from cache at None
+
+[INFO|2024-11-22 23:48:09] tokenization_utils_base.py:2211 >> loading file special_tokens_map.json from cache at /root/.cache/huggingface/hub/models--meta-llama--Meta-Llama-3-8B/snapshots/8cde5ca8380496c9a6cc7ef3a8b46a0372a1d920/special_tokens_map.json
+
+[INFO|2024-11-22 23:48:09] tokenization_utils_base.py:2211 >> loading file tokenizer_config.json from cache at /root/.cache/huggingface/hub/models--meta-llama--Meta-Llama-3-8B/snapshots/8cde5ca8380496c9a6cc7ef3a8b46a0372a1d920/tokenizer_config.json
+
+[INFO|2024-11-22 23:48:09] tokenization_utils_base.py:2475 >> Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
+
+[INFO|2024-11-22 23:48:10] configuration_utils.py:679 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--meta-llama--Meta-Llama-3-8B/snapshots/8cde5ca8380496c9a6cc7ef3a8b46a0372a1d920/config.json
+
+[INFO|2024-11-22 23:48:10] configuration_utils.py:746 >> Model config LlamaConfig {
+  "_name_or_path": "meta-llama/Meta-Llama-3-8B",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": 128001,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 8192,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.1",
+  "use_cache": true,
+  "vocab_size": 128256
+}
+
+
+[INFO|2024-11-22 23:48:11] tokenization_utils_base.py:2211 >> loading file tokenizer.json from cache at /root/.cache/huggingface/hub/models--meta-llama--Meta-Llama-3-8B/snapshots/8cde5ca8380496c9a6cc7ef3a8b46a0372a1d920/tokenizer.json
+
+[INFO|2024-11-22 23:48:11] tokenization_utils_base.py:2211 >> loading file tokenizer.model from cache at None
+
+[INFO|2024-11-22 23:48:11] tokenization_utils_base.py:2211 >> loading file added_tokens.json from cache at None
+
+[INFO|2024-11-22 23:48:11] tokenization_utils_base.py:2211 >> loading file special_tokens_map.json from cache at /root/.cache/huggingface/hub/models--meta-llama--Meta-Llama-3-8B/snapshots/8cde5ca8380496c9a6cc7ef3a8b46a0372a1d920/special_tokens_map.json
+
+[INFO|2024-11-22 23:48:11] tokenization_utils_base.py:2211 >> loading file tokenizer_config.json from cache at /root/.cache/huggingface/hub/models--meta-llama--Meta-Llama-3-8B/snapshots/8cde5ca8380496c9a6cc7ef3a8b46a0372a1d920/tokenizer_config.json
+
+[INFO|2024-11-22 23:48:11] tokenization_utils_base.py:2475 >> Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
+
+[INFO|2024-11-22 23:48:11] logging.py:157 >> Add pad token: <|end_of_text|>
+
+[INFO|2024-11-22 23:48:11] logging.py:157 >> Loading dataset ragtruth_base_data/train_hallucination_detection.json...
+
+[INFO|2024-11-22 23:48:13] configuration_utils.py:679 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--meta-llama--Meta-Llama-3-8B/snapshots/8cde5ca8380496c9a6cc7ef3a8b46a0372a1d920/config.json
+
+[INFO|2024-11-22 23:48:13] configuration_utils.py:746 >> Model config LlamaConfig {
+  "_name_or_path": "meta-llama/Meta-Llama-3-8B",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": 128001,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 8192,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.1",
+  "use_cache": true,
+  "vocab_size": 128256
+}
+
+
+[INFO|2024-11-22 23:48:13] modeling_utils.py:3937 >> loading weights file model.safetensors from cache at /root/.cache/huggingface/hub/models--meta-llama--Meta-Llama-3-8B/snapshots/8cde5ca8380496c9a6cc7ef3a8b46a0372a1d920/model.safetensors.index.json
+
+[INFO|2024-11-22 23:48:13] modeling_utils.py:1670 >> Instantiating LlamaForCausalLM model under default dtype torch.bfloat16.
+
+[INFO|2024-11-22 23:48:13] configuration_utils.py:1096 >> Generate config GenerationConfig {
+  "bos_token_id": 128000,
+  "eos_token_id": 128001
+}
+
+
+[INFO|2024-11-22 23:48:17] modeling_utils.py:4800 >> All model checkpoint weights were used when initializing LlamaForCausalLM.
+
+
+[INFO|2024-11-22 23:48:17] modeling_utils.py:4808 >> All the weights of LlamaForCausalLM were initialized from the model checkpoint at meta-llama/Meta-Llama-3-8B.
+If your task is similar to the task the model of the checkpoint was trained on, you can already use LlamaForCausalLM for predictions without further training.
+
+[INFO|2024-11-22 23:48:17] configuration_utils.py:1051 >> loading configuration file generation_config.json from cache at /root/.cache/huggingface/hub/models--meta-llama--Meta-Llama-3-8B/snapshots/8cde5ca8380496c9a6cc7ef3a8b46a0372a1d920/generation_config.json
+
+[INFO|2024-11-22 23:48:17] configuration_utils.py:1096 >> Generate config GenerationConfig {
+  "bos_token_id": 128000,
+  "do_sample": true,
+  "eos_token_id": 128001,
+  "max_length": 4096,
+  "temperature": 0.6,
+  "top_p": 0.9
+}
+
+
+[INFO|2024-11-22 23:48:17] logging.py:157 >> Gradient checkpointing enabled.
+
+[INFO|2024-11-22 23:48:17] logging.py:157 >> Using torch SDPA for faster training and inference.
+
+[INFO|2024-11-22 23:48:17] logging.py:157 >> Upcasting trainable params to float32.
+
+[INFO|2024-11-22 23:48:17] logging.py:157 >> Fine-tuning method: Full
+
+[INFO|2024-11-22 23:48:17] logging.py:157 >> trainable params: 8,030,261,248 || all params: 8,030,261,248 || trainable%: 100.0000
+
+[INFO|2024-11-22 23:48:17] trainer.py:698 >> Using auto half precision backend
+
+[INFO|2024-11-22 23:48:41] trainer.py:2313 >> ***** Running training *****
+
+[INFO|2024-11-22 23:48:41] trainer.py:2314 >>   Num examples = 15,090
+
+[INFO|2024-11-22 23:48:41] trainer.py:2315 >>   Num Epochs = 3
+
+[INFO|2024-11-22 23:48:41] trainer.py:2316 >>   Instantaneous batch size per device = 1
+
+[INFO|2024-11-22 23:48:41] trainer.py:2319 >>   Total train batch size (w. parallel, distributed & accumulation) = 64
+
+[INFO|2024-11-22 23:48:41] trainer.py:2320 >>   Gradient Accumulation steps = 8
+
+[INFO|2024-11-22 23:48:41] trainer.py:2321 >>   Total optimization steps = 705
+
+[INFO|2024-11-22 23:48:41] trainer.py:2322 >>   Number of trainable parameters = 8,030,261,248
+
+[INFO|2024-11-22 23:49:06] logging.py:157 >> {'loss': 1.8534, 'learning_rate': 5.0000e-07, 'epoch': 0.00}
+
+[INFO|2024-11-22 23:49:22] logging.py:157 >> {'loss': 1.8137, 'learning_rate': 1.0000e-06, 'epoch': 0.01}
+
+[INFO|2024-11-22 23:49:38] logging.py:157 >> {'loss': 1.8310, 'learning_rate': 1.5000e-06, 'epoch': 0.01}
+
+[INFO|2024-11-22 23:49:54] logging.py:157 >> {'loss': 1.7517, 'learning_rate': 2.0000e-06, 'epoch': 0.02}
+
+[INFO|2024-11-22 23:50:11] logging.py:157 >> {'loss': 1.4384, 'learning_rate': 2.5000e-06, 'epoch': 0.02}
+
+[INFO|2024-11-22 23:50:26] logging.py:157 >> {'loss': 1.0929, 'learning_rate': 3.0000e-06, 'epoch': 0.03}
+
+[INFO|2024-11-22 23:50:41] logging.py:157 >> {'loss': 0.9777, 'learning_rate': 3.5000e-06, 'epoch': 0.03}
+
+[INFO|2024-11-22 23:50:57] logging.py:157 >> {'loss': 0.4502, 'learning_rate': 4.0000e-06, 'epoch': 0.03}
+
+[INFO|2024-11-22 23:51:14] logging.py:157 >> {'loss': 0.4524, 'learning_rate': 4.5000e-06, 'epoch': 0.04}
+
+[INFO|2024-11-22 23:51:29] logging.py:157 >> {'loss': 0.3790, 'learning_rate': 5.0000e-06, 'epoch': 0.04}
+
+[INFO|2024-11-22 23:51:46] logging.py:157 >> {'loss': 0.3579, 'learning_rate': 5.0000e-06, 'epoch': 0.05}
+
+[INFO|2024-11-22 23:52:01] logging.py:157 >> {'loss': 0.3469, 'learning_rate': 4.9999e-06, 'epoch': 0.05}
+
+[INFO|2024-11-22 23:52:17] logging.py:157 >> {'loss': 0.3868, 'learning_rate': 4.9998e-06, 'epoch': 0.06}
+
+[INFO|2024-11-22 23:52:33] logging.py:157 >> {'loss': 0.3678, 'learning_rate': 4.9996e-06, 'epoch': 0.06}
+
+[INFO|2024-11-22 23:52:48] logging.py:157 >> {'loss': 0.2992, 'learning_rate': 4.9994e-06, 'epoch': 0.06}
+
+[INFO|2024-11-22 23:53:04] logging.py:157 >> {'loss': 0.3483, 'learning_rate': 4.9991e-06, 'epoch': 0.07}
+
+[INFO|2024-11-22 23:53:20] logging.py:157 >> {'loss': 0.3524, 'learning_rate': 4.9987e-06, 'epoch': 0.07}
+
+[INFO|2024-11-22 23:53:35] logging.py:157 >> {'loss': 0.2594, 'learning_rate': 4.9984e-06, 'epoch': 0.08}
+
+[INFO|2024-11-22 23:53:51] logging.py:157 >> {'loss': 0.2880, 'learning_rate': 4.9979e-06, 'epoch': 0.08}
+
+[INFO|2024-11-22 23:54:07] logging.py:157 >> {'loss': 0.3927, 'learning_rate': 4.9974e-06, 'epoch': 0.08}
+
+[INFO|2024-11-22 23:54:22] logging.py:157 >> {'loss': 0.2830, 'learning_rate': 4.9969e-06, 'epoch': 0.09}
+
+[INFO|2024-11-22 23:54:39] logging.py:157 >> {'loss': 0.3204, 'learning_rate': 4.9963e-06, 'epoch': 0.09}
+
+[INFO|2024-11-22 23:54:55] logging.py:157 >> {'loss': 0.3337, 'learning_rate': 4.9957e-06, 'epoch': 0.10}
+
+[INFO|2024-11-22 23:55:11] logging.py:157 >> {'loss': 0.2419, 'learning_rate': 4.9950e-06, 'epoch': 0.10}
+
+[INFO|2024-11-22 23:55:26] logging.py:157 >> {'loss': 0.3455, 'learning_rate': 4.9943e-06, 'epoch': 0.11}
+
+[INFO|2024-11-22 23:55:42] logging.py:157 >> {'loss': 0.2371, 'learning_rate': 4.9935e-06, 'epoch': 0.11}
+
+[INFO|2024-11-22 23:55:57] logging.py:157 >> {'loss': 0.3668, 'learning_rate': 4.9926e-06, 'epoch': 0.11}
+
+[INFO|2024-11-22 23:56:13] logging.py:157 >> {'loss': 0.3174, 'learning_rate': 4.9917e-06, 'epoch': 0.12}
+
+[INFO|2024-11-22 23:56:29] logging.py:157 >> {'loss': 0.2761, 'learning_rate': 4.9908e-06, 'epoch': 0.12}
+
+[INFO|2024-11-22 23:56:46] logging.py:157 >> {'loss': 0.2524, 'learning_rate': 4.9898e-06, 'epoch': 0.13}
+
+[INFO|2024-11-22 23:57:02] logging.py:157 >> {'loss': 0.3255, 'learning_rate': 4.9887e-06, 'epoch': 0.13}
+
+[INFO|2024-11-22 23:57:17] logging.py:157 >> {'loss': 0.2535, 'learning_rate': 4.9876e-06, 'epoch': 0.14}
+
+[INFO|2024-11-22 23:57:33] logging.py:157 >> {'loss': 0.2511, 'learning_rate': 4.9865e-06, 'epoch': 0.14}
+
+[INFO|2024-11-22 23:57:48] logging.py:157 >> {'loss': 0.3255, 'learning_rate': 4.9853e-06, 'epoch': 0.14}
+
+[INFO|2024-11-22 23:58:04] logging.py:157 >> {'loss': 0.2002, 'learning_rate': 4.9841e-06, 'epoch': 0.15}
+
+[INFO|2024-11-22 23:58:19] logging.py:157 >> {'loss': 0.2609, 'learning_rate': 4.9828e-06, 'epoch': 0.15}
+
+[INFO|2024-11-22 23:58:35] logging.py:157 >> {'loss': 0.2332, 'learning_rate': 4.9814e-06, 'epoch': 0.16}
+
+[INFO|2024-11-22 23:58:51] logging.py:157 >> {'loss': 0.3703, 'learning_rate': 4.9800e-06, 'epoch': 0.16}
+
+[INFO|2024-11-22 23:59:07] logging.py:157 >> {'loss': 0.2274, 'learning_rate': 4.9786e-06, 'epoch': 0.17}
+
+[INFO|2024-11-22 23:59:23] logging.py:157 >> {'loss': 0.2623, 'learning_rate': 4.9770e-06, 'epoch': 0.17}
+
+[INFO|2024-11-22 23:59:39] logging.py:157 >> {'loss': 0.2717, 'learning_rate': 4.9755e-06, 'epoch': 0.17}
+
+[INFO|2024-11-22 23:59:56] logging.py:157 >> {'loss': 0.2680, 'learning_rate': 4.9739e-06, 'epoch': 0.18}
+
+[INFO|2024-11-23 00:00:11] logging.py:157 >> {'loss': 0.2498, 'learning_rate': 4.9722e-06, 'epoch': 0.18}
+
+[INFO|2024-11-23 00:00:27] logging.py:157 >> {'loss': 0.2239, 'learning_rate': 4.9705e-06, 'epoch': 0.19}
+
+[INFO|2024-11-23 00:00:43] logging.py:157 >> {'loss': 0.2145, 'learning_rate': 4.9688e-06, 'epoch': 0.19}
+
+[INFO|2024-11-23 00:00:59] logging.py:157 >> {'loss': 0.2187, 'learning_rate': 4.9670e-06, 'epoch': 0.20}
+
+[INFO|2024-11-23 00:01:15] logging.py:157 >> {'loss': 0.2271, 'learning_rate': 4.9651e-06, 'epoch': 0.20}
+
+[INFO|2024-11-23 00:01:31] logging.py:157 >> {'loss': 0.1612, 'learning_rate': 4.9632e-06, 'epoch': 0.20}
+
+[INFO|2024-11-23 00:01:46] logging.py:157 >> {'loss': 0.2421, 'learning_rate': 4.9613e-06, 'epoch': 0.21}
+
+[INFO|2024-11-23 00:02:01] logging.py:157 >> {'loss': 0.3229, 'learning_rate': 4.9592e-06, 'epoch': 0.21}
+
+[INFO|2024-11-23 00:02:17] logging.py:157 >> {'loss': 0.3008, 'learning_rate': 4.9572e-06, 'epoch': 0.22}
+
+[INFO|2024-11-23 00:02:33] logging.py:157 >> {'loss': 0.1707, 'learning_rate': 4.9551e-06, 'epoch': 0.22}
+
+[INFO|2024-11-23 00:02:49] logging.py:157 >> {'loss': 0.2249, 'learning_rate': 4.9529e-06, 'epoch': 0.22}
+
+[INFO|2024-11-23 00:03:04] logging.py:157 >> {'loss': 0.2401, 'learning_rate': 4.9507e-06, 'epoch': 0.23}
+
+[INFO|2024-11-23 00:03:19] logging.py:157 >> {'loss': 0.2154, 'learning_rate': 4.9485e-06, 'epoch': 0.23}
+
+[INFO|2024-11-23 00:03:35] logging.py:157 >> {'loss': 0.2536, 'learning_rate': 4.9461e-06, 'epoch': 0.24}
+
+[INFO|2024-11-23 00:03:51] logging.py:157 >> {'loss': 0.1949, 'learning_rate': 4.9438e-06, 'epoch': 0.24}
+
+[INFO|2024-11-23 00:04:07] logging.py:157 >> {'loss': 0.2119, 'learning_rate': 4.9414e-06, 'epoch': 0.25}
+
+[INFO|2024-11-23 00:04:23] logging.py:157 >> {'loss': 0.2396, 'learning_rate': 4.9389e-06, 'epoch': 0.25}
+
+[INFO|2024-11-23 00:04:39] logging.py:157 >> {'loss': 0.2781, 'learning_rate': 4.9364e-06, 'epoch': 0.25}
+
+[INFO|2024-11-23 00:04:54] logging.py:157 >> {'loss': 0.2919, 'learning_rate': 4.9339e-06, 'epoch': 0.26}
+
+[INFO|2024-11-23 00:05:10] logging.py:157 >> {'loss': 0.2323, 'learning_rate': 4.9313e-06, 'epoch': 0.26}
+
+[INFO|2024-11-23 00:05:25] logging.py:157 >> {'loss': 0.2101, 'learning_rate': 4.9286e-06, 'epoch': 0.27}
+
+[INFO|2024-11-23 00:05:41] logging.py:157 >> {'loss': 0.2287, 'learning_rate': 4.9259e-06, 'epoch': 0.27}
+
+[INFO|2024-11-23 00:05:57] logging.py:157 >> {'loss': 0.2732, 'learning_rate': 4.9231e-06, 'epoch': 0.28}
+
+[INFO|2024-11-23 00:06:12] logging.py:157 >> {'loss': 0.2250, 'learning_rate': 4.9203e-06, 'epoch': 0.28}
+
+[INFO|2024-11-23 00:06:29] logging.py:157 >> {'loss': 0.2336, 'learning_rate': 4.9175e-06, 'epoch': 0.28}
+
+[INFO|2024-11-23 00:06:44] logging.py:157 >> {'loss': 0.2172, 'learning_rate': 4.9146e-06, 'epoch': 0.29}
+
+[INFO|2024-11-23 00:06:59] logging.py:157 >> {'loss': 0.2177, 'learning_rate': 4.9116e-06, 'epoch': 0.29}
+
+[INFO|2024-11-23 00:07:15] logging.py:157 >> {'loss': 0.2132, 'learning_rate': 4.9086e-06, 'epoch': 0.30}
+
+[INFO|2024-11-23 00:07:31] logging.py:157 >> {'loss': 0.3013, 'learning_rate': 4.9056e-06, 'epoch': 0.30}
+
+[INFO|2024-11-23 00:07:46] logging.py:157 >> {'loss': 0.2327, 'learning_rate': 4.9025e-06, 'epoch': 0.31}
+
+[INFO|2024-11-23 00:08:02] logging.py:157 >> {'loss': 0.1599, 'learning_rate': 4.8993e-06, 'epoch': 0.31}
+
+[INFO|2024-11-23 00:08:17] logging.py:157 >> {'loss': 0.2443, 'learning_rate': 4.8961e-06, 'epoch': 0.31}
+
+[INFO|2024-11-23 00:08:33] logging.py:157 >> {'loss': 0.2563, 'learning_rate': 4.8929e-06, 'epoch': 0.32}
+
+[INFO|2024-11-23 00:08:49] logging.py:157 >> {'loss': 0.2795, 'learning_rate': 4.8896e-06, 'epoch': 0.32}
+
+[INFO|2024-11-23 00:09:05] logging.py:157 >> {'loss': 0.1995, 'learning_rate': 4.8862e-06, 'epoch': 0.33}
+
+[INFO|2024-11-23 00:09:21] logging.py:157 >> {'loss': 0.2720, 'learning_rate': 4.8828e-06, 'epoch': 0.33}
+
+[INFO|2024-11-23 00:09:37] logging.py:157 >> {'loss': 0.2445, 'learning_rate': 4.8794e-06, 'epoch': 0.33}
+
+[INFO|2024-11-23 00:09:53] logging.py:157 >> {'loss': 0.2425, 'learning_rate': 4.8759e-06, 'epoch': 0.34}
+
+[INFO|2024-11-23 00:10:09] logging.py:157 >> {'loss': 0.2192, 'learning_rate': 4.8723e-06, 'epoch': 0.34}
+
+[INFO|2024-11-23 00:10:25] logging.py:157 >> {'loss': 0.2350, 'learning_rate': 4.8688e-06, 'epoch': 0.35}
+
+[INFO|2024-11-23 00:10:39] logging.py:157 >> {'loss': 0.2137, 'learning_rate': 4.8651e-06, 'epoch': 0.35}
+
+[INFO|2024-11-23 00:10:56] logging.py:157 >> {'loss': 0.2150, 'learning_rate': 4.8614e-06, 'epoch': 0.36}
+
+[INFO|2024-11-23 00:11:11] logging.py:157 >> {'loss': 0.1952, 'learning_rate': 4.8577e-06, 'epoch': 0.36}
+
+[INFO|2024-11-23 00:11:28] logging.py:157 >> {'loss': 0.2313, 'learning_rate': 4.8539e-06, 'epoch': 0.36}
+
+[INFO|2024-11-23 00:11:44] logging.py:157 >> {'loss': 0.2113, 'learning_rate': 4.8501e-06, 'epoch': 0.37}
+
+[INFO|2024-11-23 00:12:00] logging.py:157 >> {'loss': 0.2181, 'learning_rate': 4.8462e-06, 'epoch': 0.37}
+
+[INFO|2024-11-23 00:12:16] logging.py:157 >> {'loss': 0.2028, 'learning_rate': 4.8423e-06, 'epoch': 0.38}
+
+[INFO|2024-11-23 00:12:32] logging.py:157 >> {'loss': 0.1991, 'learning_rate': 4.8383e-06, 'epoch': 0.38}
+
+[INFO|2024-11-23 00:12:47] logging.py:157 >> {'loss': 0.1908, 'learning_rate': 4.8343e-06, 'epoch': 0.39}
+
+[INFO|2024-11-23 00:13:03] logging.py:157 >> {'loss': 0.2795, 'learning_rate': 4.8302e-06, 'epoch': 0.39}
+
+[INFO|2024-11-23 00:13:19] logging.py:157 >> {'loss': 0.2237, 'learning_rate': 4.8261e-06, 'epoch': 0.39}
+
+[INFO|2024-11-23 00:13:35] logging.py:157 >> {'loss': 0.2036, 'learning_rate': 4.8219e-06, 'epoch': 0.40}
+
+[INFO|2024-11-23 00:13:51] logging.py:157 >> {'loss': 0.2144, 'learning_rate': 4.8177e-06, 'epoch': 0.40}
+
+[INFO|2024-11-23 00:14:06] logging.py:157 >> {'loss': 0.2720, 'learning_rate': 4.8135e-06, 'epoch': 0.41}
+
+[INFO|2024-11-23 00:14:22] logging.py:157 >> {'loss': 0.2811, 'learning_rate': 4.8092e-06, 'epoch': 0.41}
+
+[INFO|2024-11-23 00:14:37] logging.py:157 >> {'loss': 0.3293, 'learning_rate': 4.8048e-06, 'epoch': 0.42}
+
+[INFO|2024-11-23 00:14:52] logging.py:157 >> {'loss': 0.2373, 'learning_rate': 4.8004e-06, 'epoch': 0.42}
+
+[INFO|2024-11-23 00:15:08] logging.py:157 >> {'loss': 0.2385, 'learning_rate': 4.7960e-06, 'epoch': 0.42}
+
+[INFO|2024-11-23 00:15:24] logging.py:157 >> {'loss': 0.2682, 'learning_rate': 4.7915e-06, 'epoch': 0.43}
+
+[INFO|2024-11-23 00:15:40] logging.py:157 >> {'loss': 0.1882, 'learning_rate': 4.7869e-06, 'epoch': 0.43}
+
+[INFO|2024-11-23 00:15:56] logging.py:157 >> {'loss': 0.2449, 'learning_rate': 4.7823e-06, 'epoch': 0.44}
+
+[INFO|2024-11-23 00:16:11] logging.py:157 >> {'loss': 0.2010, 'learning_rate': 4.7777e-06, 'epoch': 0.44}
+
+[INFO|2024-11-23 00:16:27] logging.py:157 >> {'loss': 0.2531, 'learning_rate': 4.7730e-06, 'epoch': 0.45}
+
+[INFO|2024-11-23 00:16:42] logging.py:157 >> {'loss': 0.2106, 'learning_rate': 4.7683e-06, 'epoch': 0.45}
+
+[INFO|2024-11-23 00:16:58] logging.py:157 >> {'loss': 0.2280, 'learning_rate': 4.7635e-06, 'epoch': 0.45}
+
+[INFO|2024-11-23 00:17:13] logging.py:157 >> {'loss': 0.2520, 'learning_rate': 4.7587e-06, 'epoch': 0.46}
+
+[INFO|2024-11-23 00:17:29] logging.py:157 >> {'loss': 0.2257, 'learning_rate': 4.7538e-06, 'epoch': 0.46}
+
+[INFO|2024-11-23 00:17:45] logging.py:157 >> {'loss': 0.1963, 'learning_rate': 4.7489e-06, 'epoch': 0.47}
+
+[INFO|2024-11-23 00:18:01] logging.py:157 >> {'loss': 0.1714, 'learning_rate': 4.7439e-06, 'epoch': 0.47}
+
+[INFO|2024-11-23 00:18:17] logging.py:157 >> {'loss': 0.2278, 'learning_rate': 4.7389e-06, 'epoch': 0.47}
+
+[INFO|2024-11-23 00:18:33] logging.py:157 >> {'loss': 0.1829, 'learning_rate': 4.7339e-06, 'epoch': 0.48}
+
+[INFO|2024-11-23 00:18:49] logging.py:157 >> {'loss': 0.2468, 'learning_rate': 4.7288e-06, 'epoch': 0.48}
+
+[INFO|2024-11-23 00:19:04] logging.py:157 >> {'loss': 0.2491, 'learning_rate': 4.7237e-06, 'epoch': 0.49}
+
+[INFO|2024-11-23 00:19:20] logging.py:157 >> {'loss': 0.1712, 'learning_rate': 4.7185e-06, 'epoch': 0.49}
+
+[INFO|2024-11-23 00:19:35] logging.py:157 >> {'loss': 0.2324, 'learning_rate': 4.7132e-06, 'epoch': 0.50}
+
+[INFO|2024-11-23 00:19:51] logging.py:157 >> {'loss': 0.2526, 'learning_rate': 4.7080e-06, 'epoch': 0.50}
+
+[INFO|2024-11-23 00:20:07] logging.py:157 >> {'loss': 0.2197, 'learning_rate': 4.7026e-06, 'epoch': 0.50}
+
+[INFO|2024-11-23 00:20:22] logging.py:157 >> {'loss': 0.2658, 'learning_rate': 4.6973e-06, 'epoch': 0.51}
+
+[INFO|2024-11-23 00:20:37] logging.py:157 >> {'loss': 0.1820, 'learning_rate': 4.6919e-06, 'epoch': 0.51}
+
+[INFO|2024-11-23 00:20:53] logging.py:157 >> {'loss': 0.1846, 'learning_rate': 4.6864e-06, 'epoch': 0.52}
+
+[INFO|2024-11-23 00:21:09] logging.py:157 >> {'loss': 0.2116, 'learning_rate': 4.6809e-06, 'epoch': 0.52}
+
+[INFO|2024-11-23 00:21:25] logging.py:157 >> {'loss': 0.2015, 'learning_rate': 4.6753e-06, 'epoch': 0.53}
+
+[INFO|2024-11-23 00:21:41] logging.py:157 >> {'loss': 0.2059, 'learning_rate': 4.6698e-06, 'epoch': 0.53}
+
+[INFO|2024-11-23 00:21:56] logging.py:157 >> {'loss': 0.1641, 'learning_rate': 4.6641e-06, 'epoch': 0.53}
+
+[INFO|2024-11-23 00:22:11] logging.py:157 >> {'loss': 0.1814, 'learning_rate': 4.6584e-06, 'epoch': 0.54}
+
+[INFO|2024-11-23 00:22:27] logging.py:157 >> {'loss': 0.1687, 'learning_rate': 4.6527e-06, 'epoch': 0.54}
+
+[INFO|2024-11-23 00:22:43] logging.py:157 >> {'loss': 0.2088, 'learning_rate': 4.6469e-06, 'epoch': 0.55}
+
+[INFO|2024-11-23 00:22:59] logging.py:157 >> {'loss': 0.1853, 'learning_rate': 4.6411e-06, 'epoch': 0.55}
+
+[INFO|2024-11-23 00:23:15] logging.py:157 >> {'loss': 0.1968, 'learning_rate': 4.6353e-06, 'epoch': 0.56}
+
+[INFO|2024-11-23 00:23:30] logging.py:157 >> {'loss': 0.2257, 'learning_rate': 4.6294e-06, 'epoch': 0.56}
+
+[INFO|2024-11-23 00:23:46] logging.py:157 >> {'loss': 0.2619, 'learning_rate': 4.6234e-06, 'epoch': 0.56}
+
+[INFO|2024-11-23 00:24:01] logging.py:157 >> {'loss': 0.2603, 'learning_rate': 4.6175e-06, 'epoch': 0.57}
+
+[INFO|2024-11-23 00:24:18] logging.py:157 >> {'loss': 0.2470, 'learning_rate': 4.6114e-06, 'epoch': 0.57}
+
+[INFO|2024-11-23 00:24:33] logging.py:157 >> {'loss': 0.1823, 'learning_rate': 4.6054e-06, 'epoch': 0.58}
+
+[INFO|2024-11-23 00:24:49] logging.py:157 >> {'loss': 0.2022, 'learning_rate': 4.5992e-06, 'epoch': 0.58}
+
+[INFO|2024-11-23 00:25:05] logging.py:157 >> {'loss': 0.2211, 'learning_rate': 4.5931e-06, 'epoch': 0.59}
+
+[INFO|2024-11-23 00:25:21] logging.py:157 >> {'loss': 0.1619, 'learning_rate': 4.5869e-06, 'epoch': 0.59}
+
+[INFO|2024-11-23 00:25:37] logging.py:157 >> {'loss': 0.2366, 'learning_rate': 4.5806e-06, 'epoch': 0.59}
+
+[INFO|2024-11-23 00:25:53] logging.py:157 >> {'loss': 0.2268, 'learning_rate': 4.5743e-06, 'epoch': 0.60}
+
+[INFO|2024-11-23 00:26:09] logging.py:157 >> {'loss': 0.2547, 'learning_rate': 4.5680e-06, 'epoch': 0.60}
+
+[INFO|2024-11-23 00:26:25] logging.py:157 >> {'loss': 0.2360, 'learning_rate': 4.5616e-06, 'epoch': 0.61}
+
+[INFO|2024-11-23 00:26:40] logging.py:157 >> {'loss': 0.1979, 'learning_rate': 4.5552e-06, 'epoch': 0.61}
+
+[INFO|2024-11-23 00:26:56] logging.py:157 >> {'loss': 0.2629, 'learning_rate': 4.5488e-06, 'epoch': 0.61}
+
+[INFO|2024-11-23 00:27:12] logging.py:157 >> {'loss': 0.2248, 'learning_rate': 4.5423e-06, 'epoch': 0.62}
+
+[INFO|2024-11-23 00:27:29] logging.py:157 >> {'loss': 0.2475, 'learning_rate': 4.5357e-06, 'epoch': 0.62}
+
+[INFO|2024-11-23 00:27:44] logging.py:157 >> {'loss': 0.2373, 'learning_rate': 4.5292e-06, 'epoch': 0.63}
+
+[INFO|2024-11-23 00:28:00] logging.py:157 >> {'loss': 0.2319, 'learning_rate': 4.5225e-06, 'epoch': 0.63}
+
+[INFO|2024-11-23 00:28:15] logging.py:157 >> {'loss': 0.2065, 'learning_rate': 4.5159e-06, 'epoch': 0.64}
+
+[INFO|2024-11-23 00:28:32] logging.py:157 >> {'loss': 0.2068, 'learning_rate': 4.5092e-06, 'epoch': 0.64}
+
+[INFO|2024-11-23 00:28:47] logging.py:157 >> {'loss': 0.1619, 'learning_rate': 4.5024e-06, 'epoch': 0.64}
+
+[INFO|2024-11-23 00:29:03] logging.py:157 >> {'loss': 0.2448, 'learning_rate': 4.4956e-06, 'epoch': 0.65}
+
+[INFO|2024-11-23 00:29:18] logging.py:157 >> {'loss': 0.2841, 'learning_rate': 4.4888e-06, 'epoch': 0.65}
+
+[INFO|2024-11-23 00:29:35] logging.py:157 >> {'loss': 0.2133, 'learning_rate': 4.4819e-06, 'epoch': 0.66}
+
+[INFO|2024-11-23 00:29:50] logging.py:157 >> {'loss': 0.1809, 'learning_rate': 4.4750e-06, 'epoch': 0.66}
+
+[INFO|2024-11-23 00:30:07] logging.py:157 >> {'loss': 0.2245, 'learning_rate': 4.4681e-06, 'epoch': 0.67}
+
+[INFO|2024-11-23 00:30:22] logging.py:157 >> {'loss': 0.2546, 'learning_rate': 4.4611e-06, 'epoch': 0.67}
+
+[INFO|2024-11-23 00:30:38] logging.py:157 >> {'loss': 0.1628, 'learning_rate': 4.4541e-06, 'epoch': 0.67}
+
+[INFO|2024-11-23 00:30:54] logging.py:157 >> {'loss': 0.2684, 'learning_rate': 4.4470e-06, 'epoch': 0.68}
+
+[INFO|2024-11-23 00:31:10] logging.py:157 >> {'loss': 0.1974, 'learning_rate': 4.4399e-06, 'epoch': 0.68}
+
+[INFO|2024-11-23 00:31:25] logging.py:157 >> {'loss': 0.2065, 'learning_rate': 4.4328e-06, 'epoch': 0.69}
+
+[INFO|2024-11-23 00:31:40] logging.py:157 >> {'loss': 0.1699, 'learning_rate': 4.4256e-06, 'epoch': 0.69}
+
+[INFO|2024-11-23 00:31:55] logging.py:157 >> {'loss': 0.2592, 'learning_rate': 4.4183e-06, 'epoch': 0.70}
+
+[INFO|2024-11-23 00:32:10] logging.py:157 >> {'loss': 0.1710, 'learning_rate': 4.4111e-06, 'epoch': 0.70}
+
+[INFO|2024-11-23 00:32:26] logging.py:157 >> {'loss': 0.2777, 'learning_rate': 4.4038e-06, 'epoch': 0.70}
+
+[INFO|2024-11-23 00:32:41] logging.py:157 >> {'loss': 0.2078, 'learning_rate': 4.3964e-06, 'epoch': 0.71}
+
+[INFO|2024-11-23 00:32:58] logging.py:157 >> {'loss': 0.1959, 'learning_rate': 4.3890e-06, 'epoch': 0.71}
+
+[INFO|2024-11-23 00:33:14] logging.py:157 >> {'loss': 0.1782, 'learning_rate': 4.3816e-06, 'epoch': 0.72}
+
+[INFO|2024-11-23 00:33:29] logging.py:157 >> {'loss': 0.2219, 'learning_rate': 4.3742e-06, 'epoch': 0.72}
+
+[INFO|2024-11-23 00:33:45] logging.py:157 >> {'loss': 0.2189, 'learning_rate': 4.3667e-06, 'epoch': 0.72}
+
+[INFO|2024-11-23 00:34:00] logging.py:157 >> {'loss': 0.1952, 'learning_rate': 4.3591e-06, 'epoch': 0.73}
+
+[INFO|2024-11-23 00:34:16] logging.py:157 >> {'loss': 0.1990, 'learning_rate': 4.3515e-06, 'epoch': 0.73}
+
+[INFO|2024-11-23 00:34:32] logging.py:157 >> {'loss': 0.1921, 'learning_rate': 4.3439e-06, 'epoch': 0.74}
+
+[INFO|2024-11-23 00:34:48] logging.py:157 >> {'loss': 0.1982, 'learning_rate': 4.3363e-06, 'epoch': 0.74}
+
+[INFO|2024-11-23 00:35:04] logging.py:157 >> {'loss': 0.1733, 'learning_rate': 4.3286e-06, 'epoch': 0.75}
+
+[INFO|2024-11-23 00:35:19] logging.py:157 >> {'loss': 0.1843, 'learning_rate': 4.3209e-06, 'epoch': 0.75}
+
+[INFO|2024-11-23 00:35:34] logging.py:157 >> {'loss': 0.2388, 'learning_rate': 4.3131e-06, 'epoch': 0.75}
+
+[INFO|2024-11-23 00:35:50] logging.py:157 >> {'loss': 0.1899, 'learning_rate': 4.3053e-06, 'epoch': 0.76}
+
+[INFO|2024-11-23 00:36:06] logging.py:157 >> {'loss': 0.2144, 'learning_rate': 4.2975e-06, 'epoch': 0.76}
+
+[INFO|2024-11-23 00:36:22] logging.py:157 >> {'loss': 0.2493, 'learning_rate': 4.2896e-06, 'epoch': 0.77}
+
+[INFO|2024-11-23 00:36:37] logging.py:157 >> {'loss': 0.1959, 'learning_rate': 4.2817e-06, 'epoch': 0.77}
+
+[INFO|2024-11-23 00:36:52] logging.py:157 >> {'loss': 0.1965, 'learning_rate': 4.2737e-06, 'epoch': 0.78}
+
+[INFO|2024-11-23 00:37:08] logging.py:157 >> {'loss': 0.1624, 'learning_rate': 4.2658e-06, 'epoch': 0.78}
+
+[INFO|2024-11-23 00:37:24] logging.py:157 >> {'loss': 0.2002, 'learning_rate': 4.2578e-06, 'epoch': 0.78}
+
+[INFO|2024-11-23 00:37:39] logging.py:157 >> {'loss': 0.1735, 'learning_rate': 4.2497e-06, 'epoch': 0.79}
+
+[INFO|2024-11-23 00:37:55] logging.py:157 >> {'loss': 0.2115, 'learning_rate': 4.2416e-06, 'epoch': 0.79}
+
+[INFO|2024-11-23 00:38:10] logging.py:157 >> {'loss': 0.2758, 'learning_rate': 4.2335e-06, 'epoch': 0.80}
+
+[INFO|2024-11-23 00:38:27] logging.py:157 >> {'loss': 0.1754, 'learning_rate': 4.2253e-06, 'epoch': 0.80}
+
+[INFO|2024-11-23 00:38:42] logging.py:157 >> {'loss': 0.2313, 'learning_rate': 4.2171e-06, 'epoch': 0.81}
+
+[INFO|2024-11-23 00:38:58] logging.py:157 >> {'loss': 0.2400, 'learning_rate': 4.2089e-06, 'epoch': 0.81}
+
+[INFO|2024-11-23 00:39:15] logging.py:157 >> {'loss': 0.2453, 'learning_rate': 4.2006e-06, 'epoch': 0.81}
+
+[INFO|2024-11-23 00:39:31] logging.py:157 >> {'loss': 0.2330, 'learning_rate': 4.1923e-06, 'epoch': 0.82}
+
+[INFO|2024-11-23 00:39:47] logging.py:157 >> {'loss': 0.2094, 'learning_rate': 4.1840e-06, 'epoch': 0.82}
+
+[INFO|2024-11-23 00:40:02] logging.py:157 >> {'loss': 0.2293, 'learning_rate': 4.1756e-06, 'epoch': 0.83}
+
+[INFO|2024-11-23 00:40:18] logging.py:157 >> {'loss': 0.2035, 'learning_rate': 4.1672e-06, 'epoch': 0.83}
+
+[INFO|2024-11-23 00:40:34] logging.py:157 >> {'loss': 0.2000, 'learning_rate': 4.1588e-06, 'epoch': 0.84}
+
+[INFO|2024-11-23 00:40:49] logging.py:157 >> {'loss': 0.1449, 'learning_rate': 4.1503e-06, 'epoch': 0.84}
+
+[INFO|2024-11-23 00:41:05] logging.py:157 >> {'loss': 0.2260, 'learning_rate': 4.1418e-06, 'epoch': 0.84}
+
+[INFO|2024-11-23 00:41:20] logging.py:157 >> {'loss': 0.2316, 'learning_rate': 4.1333e-06, 'epoch': 0.85}
+
+[INFO|2024-11-23 00:41:36] logging.py:157 >> {'loss': 0.1400, 'learning_rate': 4.1247e-06, 'epoch': 0.85}
+
+[INFO|2024-11-23 00:41:52] logging.py:157 >> {'loss': 0.2023, 'learning_rate': 4.1161e-06, 'epoch': 0.86}
+
+[INFO|2024-11-23 00:42:08] logging.py:157 >> {'loss': 0.1699, 'learning_rate': 4.1074e-06, 'epoch': 0.86}
+
+[INFO|2024-11-23 00:42:24] logging.py:157 >> {'loss': 0.2354, 'learning_rate': 4.0988e-06, 'epoch': 0.86}
+
+[INFO|2024-11-23 00:42:41] logging.py:157 >> {'loss': 0.1929, 'learning_rate': 4.0901e-06, 'epoch': 0.87}
+
+[INFO|2024-11-23 00:42:56] logging.py:157 >> {'loss': 0.1895, 'learning_rate': 4.0813e-06, 'epoch': 0.87}
+
+[INFO|2024-11-23 00:43:12] logging.py:157 >> {'loss': 0.2700, 'learning_rate': 4.0726e-06, 'epoch': 0.88}
+
+[INFO|2024-11-23 00:43:27] logging.py:157 >> {'loss': 0.1922, 'learning_rate': 4.0638e-06, 'epoch': 0.88}
+
+[INFO|2024-11-23 00:43:43] logging.py:157 >> {'loss': 0.2539, 'learning_rate': 4.0549e-06, 'epoch': 0.89}
+
+[INFO|2024-11-23 00:43:59] logging.py:157 >> {'loss': 0.1931, 'learning_rate': 4.0461e-06, 'epoch': 0.89}
+
+[INFO|2024-11-23 00:44:15] logging.py:157 >> {'loss': 0.1976, 'learning_rate': 4.0372e-06, 'epoch': 0.89}
+
+[INFO|2024-11-23 00:44:30] logging.py:157 >> {'loss': 0.1755, 'learning_rate': 4.0282e-06, 'epoch': 0.90}
+
+[INFO|2024-11-23 00:44:46] logging.py:157 >> {'loss': 0.2102, 'learning_rate': 4.0193e-06, 'epoch': 0.90}
+
+[INFO|2024-11-23 00:45:01] logging.py:157 >> {'loss': 0.2837, 'learning_rate': 4.0103e-06, 'epoch': 0.91}
+
+[INFO|2024-11-23 00:45:18] logging.py:157 >> {'loss': 0.1755, 'learning_rate': 4.0013e-06, 'epoch': 0.91}
+
+[INFO|2024-11-23 00:45:33] logging.py:157 >> {'loss': 0.1966, 'learning_rate': 3.9922e-06, 'epoch': 0.92}
+
+[INFO|2024-11-23 00:45:48] logging.py:157 >> {'loss': 0.2105, 'learning_rate': 3.9831e-06, 'epoch': 0.92}
+
+[INFO|2024-11-23 00:46:05] logging.py:157 >> {'loss': 0.1961, 'learning_rate': 3.9740e-06, 'epoch': 0.92}
+
+[INFO|2024-11-23 00:46:20] logging.py:157 >> {'loss': 0.2695, 'learning_rate': 3.9649e-06, 'epoch': 0.93}
+
+[INFO|2024-11-23 00:46:36] logging.py:157 >> {'loss': 0.1735, 'learning_rate': 3.9557e-06, 'epoch': 0.93}
+
+[INFO|2024-11-23 00:46:51] logging.py:157 >> {'loss': 0.2341, 'learning_rate': 3.9465e-06, 'epoch': 0.94}
+
+[INFO|2024-11-23 00:47:08] logging.py:157 >> {'loss': 0.1903, 'learning_rate': 3.9373e-06, 'epoch': 0.94}
+
+[INFO|2024-11-23 00:47:24] logging.py:157 >> {'loss': 0.1991, 'learning_rate': 3.9280e-06, 'epoch': 0.95}
+
+[INFO|2024-11-23 00:47:39] logging.py:157 >> {'loss': 0.2125, 'learning_rate': 3.9187e-06, 'epoch': 0.95}
+
+[INFO|2024-11-23 00:47:55] logging.py:157 >> {'loss': 0.2113, 'learning_rate': 3.9094e-06, 'epoch': 0.95}
+
+[INFO|2024-11-23 00:48:11] logging.py:157 >> {'loss': 0.1792, 'learning_rate': 3.9001e-06, 'epoch': 0.96}
+
+[INFO|2024-11-23 00:48:27] logging.py:157 >> {'loss': 0.1899, 'learning_rate': 3.8907e-06, 'epoch': 0.96}
+
+[INFO|2024-11-23 00:48:44] logging.py:157 >> {'loss': 0.1723, 'learning_rate': 3.8813e-06, 'epoch': 0.97}
+
+[INFO|2024-11-23 00:49:00] logging.py:157 >> {'loss': 0.1971, 'learning_rate': 3.8718e-06, 'epoch': 0.97}
+
+[INFO|2024-11-23 00:49:16] logging.py:157 >> {'loss': 0.2343, 'learning_rate': 3.8624e-06, 'epoch': 0.98}
+
+[INFO|2024-11-23 00:49:31] logging.py:157 >> {'loss': 0.1988, 'learning_rate': 3.8529e-06, 'epoch': 0.98}
+
+[INFO|2024-11-23 00:49:48] logging.py:157 >> {'loss': 0.1713, 'learning_rate': 3.8434e-06, 'epoch': 0.98}
+
+[INFO|2024-11-23 00:50:03] logging.py:157 >> {'loss': 0.2052, 'learning_rate': 3.8338e-06, 'epoch': 0.99}
+
+[INFO|2024-11-23 00:50:19] logging.py:157 >> {'loss': 0.1691, 'learning_rate': 3.8243e-06, 'epoch': 0.99}
+
+[INFO|2024-11-23 00:50:35] logging.py:157 >> {'loss': 0.1741, 'learning_rate': 3.8147e-06, 'epoch': 1.00}
+
+[INFO|2024-11-23 00:50:51] logging.py:157 >> {'loss': 0.3228, 'learning_rate': 3.8050e-06, 'epoch': 1.00}
+
+[INFO|2024-11-23 00:51:07] logging.py:157 >> {'loss': 0.1392, 'learning_rate': 3.7954e-06, 'epoch': 1.01}
+
+[INFO|2024-11-23 00:51:23] logging.py:157 >> {'loss': 0.1867, 'learning_rate': 3.7857e-06, 'epoch': 1.01}
+
+[INFO|2024-11-23 00:51:40] logging.py:157 >> {'loss': 0.1197, 'learning_rate': 3.7760e-06, 'epoch': 1.02}
+
+[INFO|2024-11-23 00:51:56] logging.py:157 >> {'loss': 0.1587, 'learning_rate': 3.7663e-06, 'epoch': 1.02}
+
+[INFO|2024-11-23 00:52:12] logging.py:157 >> {'loss': 0.2010, 'learning_rate': 3.7565e-06, 'epoch': 1.02}
+
+[INFO|2024-11-23 00:52:28] logging.py:157 >> {'loss': 0.1830, 'learning_rate': 3.7467e-06, 'epoch': 1.03}
+
+[INFO|2024-11-23 00:52:44] logging.py:157 >> {'loss': 0.1495, 'learning_rate': 3.7369e-06, 'epoch': 1.03}
+
+[INFO|2024-11-23 00:53:00] logging.py:157 >> {'loss': 0.1405, 'learning_rate': 3.7271e-06, 'epoch': 1.04}
+
+[INFO|2024-11-23 00:53:15] logging.py:157 >> {'loss': 0.1249, 'learning_rate': 3.7172e-06, 'epoch': 1.04}
+
+[INFO|2024-11-23 00:53:32] logging.py:157 >> {'loss': 0.1218, 'learning_rate': 3.7074e-06, 'epoch': 1.05}
+
+[INFO|2024-11-23 00:53:47] logging.py:157 >> {'loss': 0.1439, 'learning_rate': 3.6974e-06, 'epoch': 1.05}
+
+[INFO|2024-11-23 00:54:03] logging.py:157 >> {'loss': 0.1289, 'learning_rate': 3.6875e-06, 'epoch': 1.05}
+
+[INFO|2024-11-23 00:54:19] logging.py:157 >> {'loss': 0.1245, 'learning_rate': 3.6776e-06, 'epoch': 1.06}
+
+[INFO|2024-11-23 00:54:35] logging.py:157 >> {'loss': 0.1594, 'learning_rate': 3.6676e-06, 'epoch': 1.06}
+
+[INFO|2024-11-23 00:54:50] logging.py:157 >> {'loss': 0.1450, 'learning_rate': 3.6576e-06, 'epoch': 1.07}
+
+[INFO|2024-11-23 00:55:06] logging.py:157 >> {'loss': 0.1429, 'learning_rate': 3.6475e-06, 'epoch': 1.07}
+
+[INFO|2024-11-23 00:55:22] logging.py:157 >> {'loss': 0.1386, 'learning_rate': 3.6375e-06, 'epoch': 1.08}
+
+[INFO|2024-11-23 00:55:37] logging.py:157 >> {'loss': 0.1332, 'learning_rate': 3.6274e-06, 'epoch': 1.08}
+
+[INFO|2024-11-23 00:55:53] logging.py:157 >> {'loss': 0.1078, 'learning_rate': 3.6173e-06, 'epoch': 1.08}
+
+[INFO|2024-11-23 00:56:08] logging.py:157 >> {'loss': 0.1016, 'learning_rate': 3.6072e-06, 'epoch': 1.09}
+
+[INFO|2024-11-23 00:56:24] logging.py:157 >> {'loss': 0.1301, 'learning_rate': 3.5971e-06, 'epoch': 1.09}
+
+[INFO|2024-11-23 00:56:40] logging.py:157 >> {'loss': 0.0992, 'learning_rate': 3.5869e-06, 'epoch': 1.10}
+
+[INFO|2024-11-23 00:56:56] logging.py:157 >> {'loss': 0.1415, 'learning_rate': 3.5767e-06, 'epoch': 1.10}
+
+[INFO|2024-11-23 00:57:12] logging.py:157 >> {'loss': 0.1097, 'learning_rate': 3.5665e-06, 'epoch': 1.10}
+
+[INFO|2024-11-23 00:57:27] logging.py:157 >> {'loss': 0.1454, 'learning_rate': 3.5563e-06, 'epoch': 1.11}
+
+[INFO|2024-11-23 00:57:43] logging.py:157 >> {'loss': 0.1422, 'learning_rate': 3.5460e-06, 'epoch': 1.11}
+
+[INFO|2024-11-23 00:58:00] logging.py:157 >> {'loss': 0.1399, 'learning_rate': 3.5357e-06, 'epoch': 1.12}
+
+[INFO|2024-11-23 00:58:15] logging.py:157 >> {'loss': 0.1614, 'learning_rate': 3.5254e-06, 'epoch': 1.12}
+
+[INFO|2024-11-23 00:58:31] logging.py:157 >> {'loss': 0.1243, 'learning_rate': 3.5151e-06, 'epoch': 1.13}
+
+[INFO|2024-11-23 00:58:47] logging.py:157 >> {'loss': 0.1139, 'learning_rate': 3.5048e-06, 'epoch': 1.13}
+
+[INFO|2024-11-23 00:59:03] logging.py:157 >> {'loss': 0.1068, 'learning_rate': 3.4944e-06, 'epoch': 1.13}
+
+[INFO|2024-11-23 00:59:19] logging.py:157 >> {'loss': 0.1431, 'learning_rate': 3.4840e-06, 'epoch': 1.14}
+
+[INFO|2024-11-23 00:59:34] logging.py:157 >> {'loss': 0.1302, 'learning_rate': 3.4736e-06, 'epoch': 1.14}
+
+[INFO|2024-11-23 00:59:50] logging.py:157 >> {'loss': 0.1128, 'learning_rate': 3.4632e-06, 'epoch': 1.15}
+
+[INFO|2024-11-23 01:00:06] logging.py:157 >> {'loss': 0.1360, 'learning_rate': 3.4528e-06, 'epoch': 1.15}
+
+[INFO|2024-11-23 01:00:22] logging.py:157 >> {'loss': 0.1399, 'learning_rate': 3.4423e-06, 'epoch': 1.16}
+
+[INFO|2024-11-23 01:00:37] logging.py:157 >> {'loss': 0.1420, 'learning_rate': 3.4319e-06, 'epoch': 1.16}
+
+[INFO|2024-11-23 01:00:53] logging.py:157 >> {'loss': 0.1662, 'learning_rate': 3.4214e-06, 'epoch': 1.16}
+
+[INFO|2024-11-23 01:01:09] logging.py:157 >> {'loss': 0.1400, 'learning_rate': 3.4108e-06, 'epoch': 1.17}
+
+[INFO|2024-11-23 01:01:26] logging.py:157 >> {'loss': 0.1074, 'learning_rate': 3.4003e-06, 'epoch': 1.17}
+
+[INFO|2024-11-23 01:01:42] logging.py:157 >> {'loss': 0.1114, 'learning_rate': 3.3898e-06, 'epoch': 1.18}
+
+[INFO|2024-11-23 01:01:57] logging.py:157 >> {'loss': 0.1568, 'learning_rate': 3.3792e-06, 'epoch': 1.18}
+
+[INFO|2024-11-23 01:02:13] logging.py:157 >> {'loss': 0.1554, 'learning_rate': 3.3686e-06, 'epoch': 1.19}
+
+[INFO|2024-11-23 01:02:28] logging.py:157 >> {'loss': 0.1052, 'learning_rate': 3.3580e-06, 'epoch': 1.19}
+
+[INFO|2024-11-23 01:02:44] logging.py:157 >> {'loss': 0.1220, 'learning_rate': 3.3474e-06, 'epoch': 1.19}
+
+[INFO|2024-11-23 01:02:59] logging.py:157 >> {'loss': 0.1047, 'learning_rate': 3.3367e-06, 'epoch': 1.20}
+
+[INFO|2024-11-23 01:03:15] logging.py:157 >> {'loss': 0.1026, 'learning_rate': 3.3261e-06, 'epoch': 1.20}
+
+[INFO|2024-11-23 01:03:31] logging.py:157 >> {'loss': 0.1214, 'learning_rate': 3.3154e-06, 'epoch': 1.21}
+
+[INFO|2024-11-23 01:03:47] logging.py:157 >> {'loss': 0.1351, 'learning_rate': 3.3047e-06, 'epoch': 1.21}
+
+[INFO|2024-11-23 01:04:02] logging.py:157 >> {'loss': 0.0911, 'learning_rate': 3.2940e-06, 'epoch': 1.22}
+
+[INFO|2024-11-23 01:04:18] logging.py:157 >> {'loss': 0.1640, 'learning_rate': 3.2833e-06, 'epoch': 1.22}
+
+[INFO|2024-11-23 01:04:34] logging.py:157 >> {'loss': 0.1613, 'learning_rate': 3.2725e-06, 'epoch': 1.22}
+
+[INFO|2024-11-23 01:04:50] logging.py:157 >> {'loss': 0.1294, 'learning_rate': 3.2618e-06, 'epoch': 1.23}
+
+[INFO|2024-11-23 01:05:05] logging.py:157 >> {'loss': 0.1481, 'learning_rate': 3.2510e-06, 'epoch': 1.23}
+
+[INFO|2024-11-23 01:05:21] logging.py:157 >> {'loss': 0.1645, 'learning_rate': 3.2402e-06, 'epoch': 1.24}
+
+[INFO|2024-11-23 01:05:37] logging.py:157 >> {'loss': 0.1376, 'learning_rate': 3.2294e-06, 'epoch': 1.24}
+
+[INFO|2024-11-23 01:05:53] logging.py:157 >> {'loss': 0.1421, 'learning_rate': 3.2186e-06, 'epoch': 1.24}
+
+[INFO|2024-11-23 01:06:09] logging.py:157 >> {'loss': 0.1201, 'learning_rate': 3.2078e-06, 'epoch': 1.25}
+
+[INFO|2024-11-23 01:06:25] logging.py:157 >> {'loss': 0.1328, 'learning_rate': 3.1969e-06, 'epoch': 1.25}
+
+[INFO|2024-11-23 01:06:40] logging.py:157 >> {'loss': 0.1248, 'learning_rate': 3.1861e-06, 'epoch': 1.26}
+
+[INFO|2024-11-23 01:06:55] logging.py:157 >> {'loss': 0.1352, 'learning_rate': 3.1752e-06, 'epoch': 1.26}
+
+[INFO|2024-11-23 01:07:11] logging.py:157 >> {'loss': 0.1908, 'learning_rate': 3.1643e-06, 'epoch': 1.27}
+
+[INFO|2024-11-23 01:07:27] logging.py:157 >> {'loss': 0.1574, 'learning_rate': 3.1534e-06, 'epoch': 1.27}
+
+[INFO|2024-11-23 01:07:43] logging.py:157 >> {'loss': 0.1497, 'learning_rate': 3.1425e-06, 'epoch': 1.27}
+
+[INFO|2024-11-23 01:07:58] logging.py:157 >> {'loss': 0.1501, 'learning_rate': 3.1316e-06, 'epoch': 1.28}
+
+[INFO|2024-11-23 01:08:14] logging.py:157 >> {'loss': 0.1618, 'learning_rate': 3.1206e-06, 'epoch': 1.28}
+
+[INFO|2024-11-23 01:08:30] logging.py:157 >> {'loss': 0.1104, 'learning_rate': 3.1097e-06, 'epoch': 1.29}
+
+[INFO|2024-11-23 01:08:46] logging.py:157 >> {'loss': 0.1653, 'learning_rate': 3.0987e-06, 'epoch': 1.29}
+
+[INFO|2024-11-23 01:09:01] logging.py:157 >> {'loss': 0.1073, 'learning_rate': 3.0877e-06, 'epoch': 1.30}
+
+[INFO|2024-11-23 01:09:17] logging.py:157 >> {'loss': 0.1338, 'learning_rate': 3.0767e-06, 'epoch': 1.30}
+
+[INFO|2024-11-23 01:09:32] logging.py:157 >> {'loss': 0.1485, 'learning_rate': 3.0657e-06, 'epoch': 1.30}
+
+[INFO|2024-11-23 01:09:48] logging.py:157 >> {'loss': 0.0771, 'learning_rate': 3.0547e-06, 'epoch': 1.31}
+
+[INFO|2024-11-23 01:10:04] logging.py:157 >> {'loss': 0.1234, 'learning_rate': 3.0437e-06, 'epoch': 1.31}
+
+[INFO|2024-11-23 01:10:19] logging.py:157 >> {'loss': 0.1684, 'learning_rate': 3.0327e-06, 'epoch': 1.32}
+
+[INFO|2024-11-23 01:10:35] logging.py:157 >> {'loss': 0.0894, 'learning_rate': 3.0216e-06, 'epoch': 1.32}
+
+[INFO|2024-11-23 01:10:51] logging.py:157 >> {'loss': 0.1119, 'learning_rate': 3.0106e-06, 'epoch': 1.33}
+
+[INFO|2024-11-23 01:11:06] logging.py:157 >> {'loss': 0.1274, 'learning_rate': 2.9995e-06, 'epoch': 1.33}
+
+[INFO|2024-11-23 01:11:22] logging.py:157 >> {'loss': 0.1621, 'learning_rate': 2.9884e-06, 'epoch': 1.33}
+
+[INFO|2024-11-23 01:11:38] logging.py:157 >> {'loss': 0.1058, 'learning_rate': 2.9773e-06, 'epoch': 1.34}
+
+[INFO|2024-11-23 01:11:54] logging.py:157 >> {'loss': 0.1592, 'learning_rate': 2.9662e-06, 'epoch': 1.34}
+
+[INFO|2024-11-23 01:12:10] logging.py:157 >> {'loss': 0.1181, 'learning_rate': 2.9551e-06, 'epoch': 1.35}
+
+[INFO|2024-11-23 01:12:25] logging.py:157 >> {'loss': 0.1396, 'learning_rate': 2.9440e-06, 'epoch': 1.35}
+
+[INFO|2024-11-23 01:12:42] logging.py:157 >> {'loss': 0.1386, 'learning_rate': 2.9329e-06, 'epoch': 1.36}
+
+[INFO|2024-11-23 01:12:57] logging.py:157 >> {'loss': 0.1284, 'learning_rate': 2.9217e-06, 'epoch': 1.36}
+
+[INFO|2024-11-23 01:13:13] logging.py:157 >> {'loss': 0.1261, 'learning_rate': 2.9106e-06, 'epoch': 1.36}
+
+[INFO|2024-11-23 01:13:29] logging.py:157 >> {'loss': 0.1199, 'learning_rate': 2.8995e-06, 'epoch': 1.37}
+
+[INFO|2024-11-23 01:13:44] logging.py:157 >> {'loss': 0.2083, 'learning_rate': 2.8883e-06, 'epoch': 1.37}
+
+[INFO|2024-11-23 01:14:00] logging.py:157 >> {'loss': 0.1651, 'learning_rate': 2.8771e-06, 'epoch': 1.38}
+
+[INFO|2024-11-23 01:14:16] logging.py:157 >> {'loss': 0.0841, 'learning_rate': 2.8660e-06, 'epoch': 1.38}
+
+[INFO|2024-11-23 01:14:32] logging.py:157 >> {'loss': 0.1404, 'learning_rate': 2.8548e-06, 'epoch': 1.38}
+
+[INFO|2024-11-23 01:14:47] logging.py:157 >> {'loss': 0.1482, 'learning_rate': 2.8436e-06, 'epoch': 1.39}
+
+[INFO|2024-11-23 01:15:03] logging.py:157 >> {'loss': 0.1332, 'learning_rate': 2.8324e-06, 'epoch': 1.39}
+
+[INFO|2024-11-23 01:15:18] logging.py:157 >> {'loss': 0.1468, 'learning_rate': 2.8212e-06, 'epoch': 1.40}
+
+[INFO|2024-11-23 01:15:34] logging.py:157 >> {'loss': 0.1270, 'learning_rate': 2.8100e-06, 'epoch': 1.40}
+
+[INFO|2024-11-23 01:15:49] logging.py:157 >> {'loss': 0.1184, 'learning_rate': 2.7988e-06, 'epoch': 1.41}
+
+[INFO|2024-11-23 01:16:04] logging.py:157 >> {'loss': 0.1120, 'learning_rate': 2.7875e-06, 'epoch': 1.41}
+
+[INFO|2024-11-23 01:16:20] logging.py:157 >> {'loss': 0.1338, 'learning_rate': 2.7763e-06, 'epoch': 1.41}
+
+[INFO|2024-11-23 01:16:36] logging.py:157 >> {'loss': 0.1601, 'learning_rate': 2.7651e-06, 'epoch': 1.42}
+
+[INFO|2024-11-23 01:16:53] logging.py:157 >> {'loss': 0.1618, 'learning_rate': 2.7538e-06, 'epoch': 1.42}
+
+[INFO|2024-11-23 01:17:08] logging.py:157 >> {'loss': 0.1368, 'learning_rate': 2.7426e-06, 'epoch': 1.43}
+
+[INFO|2024-11-23 01:17:24] logging.py:157 >> {'loss': 0.1489, 'learning_rate': 2.7313e-06, 'epoch': 1.43}
+
+[INFO|2024-11-23 01:17:40] logging.py:157 >> {'loss': 0.1045, 'learning_rate': 2.7201e-06, 'epoch': 1.44}
+
+[INFO|2024-11-23 01:17:56] logging.py:157 >> {'loss': 0.0851, 'learning_rate': 2.7088e-06, 'epoch': 1.44}
+
+[INFO|2024-11-23 01:18:12] logging.py:157 >> {'loss': 0.1308, 'learning_rate': 2.6976e-06, 'epoch': 1.44}
+
+[INFO|2024-11-23 01:18:27] logging.py:157 >> {'loss': 0.1743, 'learning_rate': 2.6863e-06, 'epoch': 1.45}
+
+[INFO|2024-11-23 01:18:42] logging.py:157 >> {'loss': 0.1234, 'learning_rate': 2.6750e-06, 'epoch': 1.45}
+
+[INFO|2024-11-23 01:18:58] logging.py:157 >> {'loss': 0.1154, 'learning_rate': 2.6637e-06, 'epoch': 1.46}
+
+[INFO|2024-11-23 01:19:15] logging.py:157 >> {'loss': 0.1247, 'learning_rate': 2.6525e-06, 'epoch': 1.46}
+
+[INFO|2024-11-23 01:19:30] logging.py:157 >> {'loss': 0.1587, 'learning_rate': 2.6412e-06, 'epoch': 1.47}
+
+[INFO|2024-11-23 01:19:46] logging.py:157 >> {'loss': 0.1279, 'learning_rate': 2.6299e-06, 'epoch': 1.47}
+
+[INFO|2024-11-23 01:20:01] logging.py:157 >> {'loss': 0.1201, 'learning_rate': 2.6186e-06, 'epoch': 1.47}
+
+[INFO|2024-11-23 01:20:17] logging.py:157 >> {'loss': 0.1827, 'learning_rate': 2.6073e-06, 'epoch': 1.48}
+
+[INFO|2024-11-23 01:20:33] logging.py:157 >> {'loss': 0.0867, 'learning_rate': 2.5960e-06, 'epoch': 1.48}
+
+[INFO|2024-11-23 01:20:48] logging.py:157 >> {'loss': 0.1496, 'learning_rate': 2.5847e-06, 'epoch': 1.49}
+
+[INFO|2024-11-23 01:21:04] logging.py:157 >> {'loss': 0.1001, 'learning_rate': 2.5734e-06, 'epoch': 1.49}
+
+[INFO|2024-11-23 01:21:21] logging.py:157 >> {'loss': 0.1678, 'learning_rate': 2.5621e-06, 'epoch': 1.49}
+
+[INFO|2024-11-23 01:21:37] logging.py:157 >> {'loss': 0.1769, 'learning_rate': 2.5508e-06, 'epoch': 1.50}
+
+[INFO|2024-11-23 01:21:53] logging.py:157 >> {'loss': 0.1519, 'learning_rate': 2.5396e-06, 'epoch': 1.50}
+
+[INFO|2024-11-23 01:22:09] logging.py:157 >> {'loss': 0.1258, 'learning_rate': 2.5283e-06, 'epoch': 1.51}
+
+[INFO|2024-11-23 01:22:24] logging.py:157 >> {'loss': 0.0906, 'learning_rate': 2.5170e-06, 'epoch': 1.51}
+
+[INFO|2024-11-23 01:22:40] logging.py:157 >> {'loss': 0.1225, 'learning_rate': 2.5057e-06, 'epoch': 1.52}
+
+[INFO|2024-11-23 01:22:56] logging.py:157 >> {'loss': 0.1327, 'learning_rate': 2.4943e-06, 'epoch': 1.52}
+
+[INFO|2024-11-23 01:23:11] logging.py:157 >> {'loss': 0.1373, 'learning_rate': 2.4830e-06, 'epoch': 1.52}
+
+[INFO|2024-11-23 01:23:27] logging.py:157 >> {'loss': 0.1492, 'learning_rate': 2.4717e-06, 'epoch': 1.53}
+
+[INFO|2024-11-23 01:23:42] logging.py:157 >> {'loss': 0.1125, 'learning_rate': 2.4604e-06, 'epoch': 1.53}
+
+[INFO|2024-11-23 01:23:58] logging.py:157 >> {'loss': 0.1364, 'learning_rate': 2.4492e-06, 'epoch': 1.54}
+
+[INFO|2024-11-23 01:24:14] logging.py:157 >> {'loss': 0.0885, 'learning_rate': 2.4379e-06, 'epoch': 1.54}
+
+[INFO|2024-11-23 01:24:30] logging.py:157 >> {'loss': 0.1376, 'learning_rate': 2.4266e-06, 'epoch': 1.55}
+
+[INFO|2024-11-23 01:24:46] logging.py:157 >> {'loss': 0.1330, 'learning_rate': 2.4153e-06, 'epoch': 1.55}
+
+[INFO|2024-11-23 01:25:01] logging.py:157 >> {'loss': 0.1599, 'learning_rate': 2.4040e-06, 'epoch': 1.55}
+
+[INFO|2024-11-23 01:25:17] logging.py:157 >> {'loss': 0.1252, 'learning_rate': 2.3927e-06, 'epoch': 1.56}
+
+[INFO|2024-11-23 01:25:34] logging.py:157 >> {'loss': 0.1022, 'learning_rate': 2.3814e-06, 'epoch': 1.56}
+
+[INFO|2024-11-23 01:25:50] logging.py:157 >> {'loss': 0.1288, 'learning_rate': 2.3701e-06, 'epoch': 1.57}
+
+[INFO|2024-11-23 01:26:05] logging.py:157 >> {'loss': 0.1037, 'learning_rate': 2.3588e-06, 'epoch': 1.57}
+
+[INFO|2024-11-23 01:26:21] logging.py:157 >> {'loss': 0.0992, 'learning_rate': 2.3475e-06, 'epoch': 1.58}
+
+[INFO|2024-11-23 01:26:36] logging.py:157 >> {'loss': 0.1263, 'learning_rate': 2.3363e-06, 'epoch': 1.58}
+
+[INFO|2024-11-23 01:26:52] logging.py:157 >> {'loss': 0.1163, 'learning_rate': 2.3250e-06, 'epoch': 1.58}
+
+[INFO|2024-11-23 01:27:08] logging.py:157 >> {'loss': 0.1035, 'learning_rate': 2.3137e-06, 'epoch': 1.59}
+
+[INFO|2024-11-23 01:27:24] logging.py:157 >> {'loss': 0.1196, 'learning_rate': 2.3024e-06, 'epoch': 1.59}
+
+[INFO|2024-11-23 01:27:40] logging.py:157 >> {'loss': 0.1259, 'learning_rate': 2.2912e-06, 'epoch': 1.60}
+
+[INFO|2024-11-23 01:27:57] logging.py:157 >> {'loss': 0.1278, 'learning_rate': 2.2799e-06, 'epoch': 1.60}
+
+[INFO|2024-11-23 01:28:12] logging.py:157 >> {'loss': 0.1214, 'learning_rate': 2.2687e-06, 'epoch': 1.61}
+
+[INFO|2024-11-23 01:28:28] logging.py:157 >> {'loss': 0.1062, 'learning_rate': 2.2574e-06, 'epoch': 1.61}
+
+[INFO|2024-11-23 01:28:43] logging.py:157 >> {'loss': 0.1514, 'learning_rate': 2.2462e-06, 'epoch': 1.61}
+
+[INFO|2024-11-23 01:28:59] logging.py:157 >> {'loss': 0.1086, 'learning_rate': 2.2349e-06, 'epoch': 1.62}
+
+[INFO|2024-11-23 01:29:16] logging.py:157 >> {'loss': 0.1116, 'learning_rate': 2.2237e-06, 'epoch': 1.62}
+
+[INFO|2024-11-23 01:29:31] logging.py:157 >> {'loss': 0.1303, 'learning_rate': 2.2125e-06, 'epoch': 1.63}
+
+[INFO|2024-11-23 01:29:47] logging.py:157 >> {'loss': 0.1283, 'learning_rate': 2.2012e-06, 'epoch': 1.63}
+
+[INFO|2024-11-23 01:30:03] logging.py:157 >> {'loss': 0.1240, 'learning_rate': 2.1900e-06, 'epoch': 1.63}
+
+[INFO|2024-11-23 01:30:18] logging.py:157 >> {'loss': 0.1243, 'learning_rate': 2.1788e-06, 'epoch': 1.64}
+
+[INFO|2024-11-23 01:30:34] logging.py:157 >> {'loss': 0.1349, 'learning_rate': 2.1676e-06, 'epoch': 1.64}
+
+[INFO|2024-11-23 01:30:49] logging.py:157 >> {'loss': 0.1253, 'learning_rate': 2.1564e-06, 'epoch': 1.65}
+
+[INFO|2024-11-23 01:31:05] logging.py:157 >> {'loss': 0.1295, 'learning_rate': 2.1452e-06, 'epoch': 1.65}
+
+[INFO|2024-11-23 01:31:21] logging.py:157 >> {'loss': 0.1533, 'learning_rate': 2.1340e-06, 'epoch': 1.66}
+
+[INFO|2024-11-23 01:31:36] logging.py:157 >> {'loss': 0.1171, 'learning_rate': 2.1229e-06, 'epoch': 1.66}
+
+[INFO|2024-11-23 01:31:52] logging.py:157 >> {'loss': 0.1351, 'learning_rate': 2.1117e-06, 'epoch': 1.66}
+
+[INFO|2024-11-23 01:32:08] logging.py:157 >> {'loss': 0.1287, 'learning_rate': 2.1005e-06, 'epoch': 1.67}
+
+[INFO|2024-11-23 01:32:24] logging.py:157 >> {'loss': 0.1135, 'learning_rate': 2.0894e-06, 'epoch': 1.67}
+
+[INFO|2024-11-23 01:32:40] logging.py:157 >> {'loss': 0.1383, 'learning_rate': 2.0783e-06, 'epoch': 1.68}
+
+[INFO|2024-11-23 01:32:55] logging.py:157 >> {'loss': 0.1369, 'learning_rate': 2.0671e-06, 'epoch': 1.68}
+
+[INFO|2024-11-23 01:33:11] logging.py:157 >> {'loss': 0.1392, 'learning_rate': 2.0560e-06, 'epoch': 1.69}
+
+[INFO|2024-11-23 01:33:27] logging.py:157 >> {'loss': 0.1569, 'learning_rate': 2.0449e-06, 'epoch': 1.69}
+
+[INFO|2024-11-23 01:33:42] logging.py:157 >> {'loss': 0.1081, 'learning_rate': 2.0338e-06, 'epoch': 1.69}
+
+[INFO|2024-11-23 01:33:58] logging.py:157 >> {'loss': 0.1393, 'learning_rate': 2.0227e-06, 'epoch': 1.70}
+
+[INFO|2024-11-23 01:34:14] logging.py:157 >> {'loss': 0.1513, 'learning_rate': 2.0116e-06, 'epoch': 1.70}
+
+[INFO|2024-11-23 01:34:29] logging.py:157 >> {'loss': 0.1014, 'learning_rate': 2.0005e-06, 'epoch': 1.71}
+
+[INFO|2024-11-23 01:34:45] logging.py:157 >> {'loss': 0.1352, 'learning_rate': 1.9894e-06, 'epoch': 1.71}
+
+[INFO|2024-11-23 01:35:01] logging.py:157 >> {'loss': 0.1085, 'learning_rate': 1.9784e-06, 'epoch': 1.72}
+
+[INFO|2024-11-23 01:35:17] logging.py:157 >> {'loss': 0.1210, 'learning_rate': 1.9673e-06, 'epoch': 1.72}
+
+[INFO|2024-11-23 01:35:33] logging.py:157 >> {'loss': 0.0997, 'learning_rate': 1.9563e-06, 'epoch': 1.72}
+
+[INFO|2024-11-23 01:35:49] logging.py:157 >> {'loss': 0.1012, 'learning_rate': 1.9453e-06, 'epoch': 1.73}
+
+[INFO|2024-11-23 01:36:04] logging.py:157 >> {'loss': 0.1549, 'learning_rate': 1.9343e-06, 'epoch': 1.73}
+
+[INFO|2024-11-23 01:36:20] logging.py:157 >> {'loss': 0.1390, 'learning_rate': 1.9233e-06, 'epoch': 1.74}
+
+[INFO|2024-11-23 01:36:36] logging.py:157 >> {'loss': 0.1110, 'learning_rate': 1.9123e-06, 'epoch': 1.74}
+
+[INFO|2024-11-23 01:36:52] logging.py:157 >> {'loss': 0.1612, 'learning_rate': 1.9013e-06, 'epoch': 1.75}
+
+[INFO|2024-11-23 01:37:08] logging.py:157 >> {'loss': 0.1114, 'learning_rate': 1.8903e-06, 'epoch': 1.75}
+
+[INFO|2024-11-23 01:37:23] logging.py:157 >> {'loss': 0.0981, 'learning_rate': 1.8794e-06, 'epoch': 1.75}
+
+[INFO|2024-11-23 01:37:39] logging.py:157 >> {'loss': 0.1582, 'learning_rate': 1.8684e-06, 'epoch': 1.76}
+
+[INFO|2024-11-23 01:37:54] logging.py:157 >> {'loss': 0.1235, 'learning_rate': 1.8575e-06, 'epoch': 1.76}
+
+[INFO|2024-11-23 01:38:10] logging.py:157 >> {'loss': 0.1208, 'learning_rate': 1.8466e-06, 'epoch': 1.77}
+
+[INFO|2024-11-23 01:38:26] logging.py:157 >> {'loss': 0.1357, 'learning_rate': 1.8357e-06, 'epoch': 1.77}
+
+[INFO|2024-11-23 01:38:41] logging.py:157 >> {'loss': 0.1507, 'learning_rate': 1.8248e-06, 'epoch': 1.77}
+
+[INFO|2024-11-23 01:38:56] logging.py:157 >> {'loss': 0.1524, 'learning_rate': 1.8139e-06, 'epoch': 1.78}
+
+[INFO|2024-11-23 01:39:12] logging.py:157 >> {'loss': 0.1424, 'learning_rate': 1.8031e-06, 'epoch': 1.78}
+
+[INFO|2024-11-23 01:39:27] logging.py:157 >> {'loss': 0.1202, 'learning_rate': 1.7922e-06, 'epoch': 1.79}
+
+[INFO|2024-11-23 01:39:43] logging.py:157 >> {'loss': 0.1447, 'learning_rate': 1.7814e-06, 'epoch': 1.79}
+
+[INFO|2024-11-23 01:39:59] logging.py:157 >> {'loss': 0.1122, 'learning_rate': 1.7706e-06, 'epoch': 1.80}
+
+[INFO|2024-11-23 01:40:14] logging.py:157 >> {'loss': 0.1149, 'learning_rate': 1.7598e-06, 'epoch': 1.80}
+
+[INFO|2024-11-23 01:40:30] logging.py:157 >> {'loss': 0.1349, 'learning_rate': 1.7490e-06, 'epoch': 1.80}
+
+[INFO|2024-11-23 01:40:46] logging.py:157 >> {'loss': 0.1209, 'learning_rate': 1.7382e-06, 'epoch': 1.81}
+
+[INFO|2024-11-23 01:41:01] logging.py:157 >> {'loss': 0.0852, 'learning_rate': 1.7275e-06, 'epoch': 1.81}
+
+[INFO|2024-11-23 01:41:16] logging.py:157 >> {'loss': 0.0968, 'learning_rate': 1.7167e-06, 'epoch': 1.82}
+
+[INFO|2024-11-23 01:41:32] logging.py:157 >> {'loss': 0.1095, 'learning_rate': 1.7060e-06, 'epoch': 1.82}
+
+[INFO|2024-11-23 01:41:49] logging.py:157 >> {'loss': 0.1398, 'learning_rate': 1.6953e-06, 'epoch': 1.83}
+
+[INFO|2024-11-23 01:42:05] logging.py:157 >> {'loss': 0.1285, 'learning_rate': 1.6846e-06, 'epoch': 1.83}
+
+[INFO|2024-11-23 01:42:22] logging.py:157 >> {'loss': 0.1402, 'learning_rate': 1.6739e-06, 'epoch': 1.83}
+
+[INFO|2024-11-23 01:42:37] logging.py:157 >> {'loss': 0.1350, 'learning_rate': 1.6633e-06, 'epoch': 1.84}
+
+[INFO|2024-11-23 01:42:53] logging.py:157 >> {'loss': 0.1052, 'learning_rate': 1.6526e-06, 'epoch': 1.84}
+
+[INFO|2024-11-23 01:43:08] logging.py:157 >> {'loss': 0.1133, 'learning_rate': 1.6420e-06, 'epoch': 1.85}
+
+[INFO|2024-11-23 01:43:23] logging.py:157 >> {'loss': 0.1025, 'learning_rate': 1.6314e-06, 'epoch': 1.85}
+
+[INFO|2024-11-23 01:43:39] logging.py:157 >> {'loss': 0.1200, 'learning_rate': 1.6208e-06, 'epoch': 1.86}
+
+[INFO|2024-11-23 01:43:55] logging.py:157 >> {'loss': 0.1466, 'learning_rate': 1.6102e-06, 'epoch': 1.86}
+
+[INFO|2024-11-23 01:44:11] logging.py:157 >> {'loss': 0.1471, 'learning_rate': 1.5997e-06, 'epoch': 1.86}
+
+[INFO|2024-11-23 01:44:27] logging.py:157 >> {'loss': 0.1088, 'learning_rate': 1.5892e-06, 'epoch': 1.87}
+
+[INFO|2024-11-23 01:44:42] logging.py:157 >> {'loss': 0.1100, 'learning_rate': 1.5786e-06, 'epoch': 1.87}
+
+[INFO|2024-11-23 01:44:58] logging.py:157 >> {'loss': 0.1345, 'learning_rate': 1.5681e-06, 'epoch': 1.88}
+
+[INFO|2024-11-23 01:45:14] logging.py:157 >> {'loss': 0.1357, 'learning_rate': 1.5577e-06, 'epoch': 1.88}
+
+[INFO|2024-11-23 01:45:29] logging.py:157 >> {'loss': 0.1457, 'learning_rate': 1.5472e-06, 'epoch': 1.89}
+
+[INFO|2024-11-23 01:45:44] logging.py:157 >> {'loss': 0.1477, 'learning_rate': 1.5368e-06, 'epoch': 1.89}
+
+[INFO|2024-11-23 01:46:00] logging.py:157 >> {'loss': 0.1360, 'learning_rate': 1.5264e-06, 'epoch': 1.89}
+
+[INFO|2024-11-23 01:46:15] logging.py:157 >> {'loss': 0.1285, 'learning_rate': 1.5160e-06, 'epoch': 1.90}
+
+[INFO|2024-11-23 01:46:31] logging.py:157 >> {'loss': 0.1393, 'learning_rate': 1.5056e-06, 'epoch': 1.90}
+
+[INFO|2024-11-23 01:46:46] logging.py:157 >> {'loss': 0.1203, 'learning_rate': 1.4952e-06, 'epoch': 1.91}
+
+[INFO|2024-11-23 01:47:02] logging.py:157 >> {'loss': 0.1237, 'learning_rate': 1.4849e-06, 'epoch': 1.91}
+
+[INFO|2024-11-23 01:47:17] logging.py:157 >> {'loss': 0.0813, 'learning_rate': 1.4746e-06, 'epoch': 1.91}
+
+[INFO|2024-11-23 01:47:33] logging.py:157 >> {'loss': 0.1033, 'learning_rate': 1.4643e-06, 'epoch': 1.92}
+
+[INFO|2024-11-23 01:47:50] logging.py:157 >> {'loss': 0.1601, 'learning_rate': 1.4540e-06, 'epoch': 1.92}
+
+[INFO|2024-11-23 01:48:06] logging.py:157 >> {'loss': 0.1227, 'learning_rate': 1.4437e-06, 'epoch': 1.93}
+
+[INFO|2024-11-23 01:48:22] logging.py:157 >> {'loss': 0.1230, 'learning_rate': 1.4335e-06, 'epoch': 1.93}
+
+[INFO|2024-11-23 01:48:37] logging.py:157 >> {'loss': 0.0752, 'learning_rate': 1.4233e-06, 'epoch': 1.94}
+
+[INFO|2024-11-23 01:48:53] logging.py:157 >> {'loss': 0.1360, 'learning_rate': 1.4131e-06, 'epoch': 1.94}
+
+[INFO|2024-11-23 01:49:08] logging.py:157 >> {'loss': 0.1395, 'learning_rate': 1.4029e-06, 'epoch': 1.94}
+
+[INFO|2024-11-23 01:49:23] logging.py:157 >> {'loss': 0.1315, 'learning_rate': 1.3928e-06, 'epoch': 1.95}
+
+[INFO|2024-11-23 01:49:40] logging.py:157 >> {'loss': 0.0956, 'learning_rate': 1.3827e-06, 'epoch': 1.95}
+
+[INFO|2024-11-23 01:49:55] logging.py:157 >> {'loss': 0.1373, 'learning_rate': 1.3726e-06, 'epoch': 1.96}
+
+[INFO|2024-11-23 01:50:11] logging.py:157 >> {'loss': 0.1289, 'learning_rate': 1.3625e-06, 'epoch': 1.96}
+
+[INFO|2024-11-23 01:50:27] logging.py:157 >> {'loss': 0.1335, 'learning_rate': 1.3525e-06, 'epoch': 1.97}
+
+[INFO|2024-11-23 01:50:43] logging.py:157 >> {'loss': 0.1056, 'learning_rate': 1.3424e-06, 'epoch': 1.97}
+
+[INFO|2024-11-23 01:50:59] logging.py:157 >> {'loss': 0.1651, 'learning_rate': 1.3324e-06, 'epoch': 1.97}
+
+[INFO|2024-11-23 01:51:15] logging.py:157 >> {'loss': 0.1019, 'learning_rate': 1.3224e-06, 'epoch': 1.98}
+
+[INFO|2024-11-23 01:51:31] logging.py:157 >> {'loss': 0.1007, 'learning_rate': 1.3125e-06, 'epoch': 1.98}
+
+[INFO|2024-11-23 01:51:47] logging.py:157 >> {'loss': 0.1156, 'learning_rate': 1.3026e-06, 'epoch': 1.99}
+
+[INFO|2024-11-23 01:52:03] logging.py:157 >> {'loss': 0.1127, 'learning_rate': 1.2926e-06, 'epoch': 1.99}
+
+[INFO|2024-11-23 01:52:19] logging.py:157 >> {'loss': 0.1196, 'learning_rate': 1.2828e-06, 'epoch': 2.00}
+
+[INFO|2024-11-23 01:52:35] logging.py:157 >> {'loss': 0.1078, 'learning_rate': 1.2729e-06, 'epoch': 2.00}
+
+[INFO|2024-11-23 01:52:51] logging.py:157 >> {'loss': 0.0500, 'learning_rate': 1.2631e-06, 'epoch': 2.01}
+
+[INFO|2024-11-23 01:53:08] logging.py:157 >> {'loss': 0.0785, 'learning_rate': 1.2533e-06, 'epoch': 2.01}
+
+[INFO|2024-11-23 01:53:23] logging.py:157 >> {'loss': 0.0746, 'learning_rate': 1.2435e-06, 'epoch': 2.01}
+
+[INFO|2024-11-23 01:53:38] logging.py:157 >> {'loss': 0.0688, 'learning_rate': 1.2337e-06, 'epoch': 2.02}
+
+[INFO|2024-11-23 01:53:54] logging.py:157 >> {'loss': 0.0579, 'learning_rate': 1.2240e-06, 'epoch': 2.02}
+
+[INFO|2024-11-23 01:54:09] logging.py:157 >> {'loss': 0.0550, 'learning_rate': 1.2143e-06, 'epoch': 2.03}
+
+[INFO|2024-11-23 01:54:25] logging.py:157 >> {'loss': 0.0781, 'learning_rate': 1.2046e-06, 'epoch': 2.03}
+
+[INFO|2024-11-23 01:54:41] logging.py:157 >> {'loss': 0.0749, 'learning_rate': 1.1950e-06, 'epoch': 2.04}
+
+[INFO|2024-11-23 01:54:56] logging.py:157 >> {'loss': 0.0565, 'learning_rate': 1.1853e-06, 'epoch': 2.04}
+
+[INFO|2024-11-23 01:55:12] logging.py:157 >> {'loss': 0.0589, 'learning_rate': 1.1757e-06, 'epoch': 2.04}
+
+[INFO|2024-11-23 01:55:27] logging.py:157 >> {'loss': 0.0536, 'learning_rate': 1.1662e-06, 'epoch': 2.05}
+
+[INFO|2024-11-23 01:55:44] logging.py:157 >> {'loss': 0.0706, 'learning_rate': 1.1566e-06, 'epoch': 2.05}
+
+[INFO|2024-11-23 01:55:59] logging.py:157 >> {'loss': 0.0717, 'learning_rate': 1.1471e-06, 'epoch': 2.06}
+
+[INFO|2024-11-23 01:56:14] logging.py:157 >> {'loss': 0.0770, 'learning_rate': 1.1376e-06, 'epoch': 2.06}
+
+[INFO|2024-11-23 01:56:30] logging.py:157 >> {'loss': 0.0707, 'learning_rate': 1.1282e-06, 'epoch': 2.07}
+
+[INFO|2024-11-23 01:56:46] logging.py:157 >> {'loss': 0.0597, 'learning_rate': 1.1187e-06, 'epoch': 2.07}
+
+[INFO|2024-11-23 01:57:02] logging.py:157 >> {'loss': 0.0697, 'learning_rate': 1.1093e-06, 'epoch': 2.07}
+
+[INFO|2024-11-23 01:57:18] logging.py:157 >> {'loss': 0.0524, 'learning_rate': 1.0999e-06, 'epoch': 2.08}
+
+[INFO|2024-11-23 01:57:34] logging.py:157 >> {'loss': 0.0548, 'learning_rate': 1.0906e-06, 'epoch': 2.08}
+
+[INFO|2024-11-23 01:57:49] logging.py:157 >> {'loss': 0.0524, 'learning_rate': 1.0813e-06, 'epoch': 2.09}
+
+[INFO|2024-11-23 01:58:05] logging.py:157 >> {'loss': 0.0444, 'learning_rate': 1.0720e-06, 'epoch': 2.09}
+
+[INFO|2024-11-23 01:58:21] logging.py:157 >> {'loss': 0.0425, 'learning_rate': 1.0627e-06, 'epoch': 2.10}
+
+[INFO|2024-11-23 01:58:37] logging.py:157 >> {'loss': 0.0735, 'learning_rate': 1.0535e-06, 'epoch': 2.10}
+
+[INFO|2024-11-23 01:58:52] logging.py:157 >> {'loss': 0.0617, 'learning_rate': 1.0443e-06, 'epoch': 2.10}
+
+[INFO|2024-11-23 01:59:08] logging.py:157 >> {'loss': 0.0575, 'learning_rate': 1.0351e-06, 'epoch': 2.11}
+
+[INFO|2024-11-23 01:59:24] logging.py:157 >> {'loss': 0.0662, 'learning_rate': 1.0260e-06, 'epoch': 2.11}
+
+[INFO|2024-11-23 01:59:41] logging.py:157 >> {'loss': 0.0615, 'learning_rate': 1.0169e-06, 'epoch': 2.12}
+
+[INFO|2024-11-23 01:59:57] logging.py:157 >> {'loss': 0.0821, 'learning_rate': 1.0078e-06, 'epoch': 2.12}
+
+[INFO|2024-11-23 02:00:13] logging.py:157 >> {'loss': 0.0425, 'learning_rate': 9.9872e-07, 'epoch': 2.13}
+
+[INFO|2024-11-23 02:00:28] logging.py:157 >> {'loss': 0.0695, 'learning_rate': 9.8970e-07, 'epoch': 2.13}
+
+[INFO|2024-11-23 02:00:45] logging.py:157 >> {'loss': 0.0616, 'learning_rate': 9.8071e-07, 'epoch': 2.13}
+
+[INFO|2024-11-23 02:01:00] logging.py:157 >> {'loss': 0.0451, 'learning_rate': 9.7175e-07, 'epoch': 2.14}
+
+[INFO|2024-11-23 02:01:15] logging.py:157 >> {'loss': 0.0467, 'learning_rate': 9.6283e-07, 'epoch': 2.14}
+
+[INFO|2024-11-23 02:01:31] logging.py:157 >> {'loss': 0.0583, 'learning_rate': 9.5393e-07, 'epoch': 2.15}
+
+[INFO|2024-11-23 02:01:47] logging.py:157 >> {'loss': 0.0390, 'learning_rate': 9.4506e-07, 'epoch': 2.15}
+
+[INFO|2024-11-23 02:02:02] logging.py:157 >> {'loss': 0.0666, 'learning_rate': 9.3623e-07, 'epoch': 2.15}
+
+[INFO|2024-11-23 02:02:18] logging.py:157 >> {'loss': 0.0452, 'learning_rate': 9.2743e-07, 'epoch': 2.16}
+
+[INFO|2024-11-23 02:02:33] logging.py:157 >> {'loss': 0.0868, 'learning_rate': 9.1866e-07, 'epoch': 2.16}
+
+[INFO|2024-11-23 02:02:49] logging.py:157 >> {'loss': 0.0751, 'learning_rate': 9.0993e-07, 'epoch': 2.17}
+
+[INFO|2024-11-23 02:03:04] logging.py:157 >> {'loss': 0.0902, 'learning_rate': 9.0122e-07, 'epoch': 2.17}
+
+[INFO|2024-11-23 02:03:20] logging.py:157 >> {'loss': 0.0516, 'learning_rate': 8.9255e-07, 'epoch': 2.18}
+
+[INFO|2024-11-23 02:03:36] logging.py:157 >> {'loss': 0.0583, 'learning_rate': 8.8391e-07, 'epoch': 2.18}
+
+[INFO|2024-11-23 02:03:51] logging.py:157 >> {'loss': 0.0553, 'learning_rate': 8.7531e-07, 'epoch': 2.18}
+
+[INFO|2024-11-23 02:04:06] logging.py:157 >> {'loss': 0.0489, 'learning_rate': 8.6673e-07, 'epoch': 2.19}
+
+[INFO|2024-11-23 02:04:22] logging.py:157 >> {'loss': 0.0793, 'learning_rate': 8.5819e-07, 'epoch': 2.19}
+
+[INFO|2024-11-23 02:04:37] logging.py:157 >> {'loss': 0.0472, 'learning_rate': 8.4969e-07, 'epoch': 2.20}
+
+[INFO|2024-11-23 02:04:52] logging.py:157 >> {'loss': 0.0894, 'learning_rate': 8.4122e-07, 'epoch': 2.20}
+
+[INFO|2024-11-23 02:05:08] logging.py:157 >> {'loss': 0.0553, 'learning_rate': 8.3278e-07, 'epoch': 2.21}
+
+[INFO|2024-11-23 02:05:23] logging.py:157 >> {'loss': 0.0543, 'learning_rate': 8.2438e-07, 'epoch': 2.21}
+
+[INFO|2024-11-23 02:05:39] logging.py:157 >> {'loss': 0.0574, 'learning_rate': 8.1601e-07, 'epoch': 2.21}
+
+[INFO|2024-11-23 02:05:55] logging.py:157 >> {'loss': 0.0402, 'learning_rate': 8.0767e-07, 'epoch': 2.22}
+
+[INFO|2024-11-23 02:06:11] logging.py:157 >> {'loss': 0.0688, 'learning_rate': 7.9937e-07, 'epoch': 2.22}
+
+[INFO|2024-11-23 02:06:27] logging.py:157 >> {'loss': 0.0521, 'learning_rate': 7.9111e-07, 'epoch': 2.23}
+
+[INFO|2024-11-23 02:06:42] logging.py:157 >> {'loss': 0.0649, 'learning_rate': 7.8287e-07, 'epoch': 2.23}
+
+[INFO|2024-11-23 02:06:58] logging.py:157 >> {'loss': 0.0658, 'learning_rate': 7.7468e-07, 'epoch': 2.24}
+
+[INFO|2024-11-23 02:07:13] logging.py:157 >> {'loss': 0.0680, 'learning_rate': 7.6652e-07, 'epoch': 2.24}
+
+[INFO|2024-11-23 02:07:29] logging.py:157 >> {'loss': 0.0593, 'learning_rate': 7.5839e-07, 'epoch': 2.24}
+
+[INFO|2024-11-23 02:07:45] logging.py:157 >> {'loss': 0.0642, 'learning_rate': 7.5030e-07, 'epoch': 2.25}
+
+[INFO|2024-11-23 02:08:01] logging.py:157 >> {'loss': 0.0473, 'learning_rate': 7.4225e-07, 'epoch': 2.25}
+
+[INFO|2024-11-23 02:08:18] logging.py:157 >> {'loss': 0.1014, 'learning_rate': 7.3423e-07, 'epoch': 2.26}
+
+[INFO|2024-11-23 02:08:33] logging.py:157 >> {'loss': 0.0705, 'learning_rate': 7.2625e-07, 'epoch': 2.26}
+
+[INFO|2024-11-23 02:08:49] logging.py:157 >> {'loss': 0.0685, 'learning_rate': 7.1830e-07, 'epoch': 2.26}
+
+[INFO|2024-11-23 02:09:04] logging.py:157 >> {'loss': 0.0452, 'learning_rate': 7.1040e-07, 'epoch': 2.27}
+
+[INFO|2024-11-23 02:09:19] logging.py:157 >> {'loss': 0.0595, 'learning_rate': 7.0252e-07, 'epoch': 2.27}
+
+[INFO|2024-11-23 02:09:36] logging.py:157 >> {'loss': 0.0529, 'learning_rate': 6.9469e-07, 'epoch': 2.28}
+
+[INFO|2024-11-23 02:09:51] logging.py:157 >> {'loss': 0.0619, 'learning_rate': 6.8689e-07, 'epoch': 2.28}
+
+[INFO|2024-11-23 02:10:06] logging.py:157 >> {'loss': 0.0489, 'learning_rate': 6.7913e-07, 'epoch': 2.29}
+
+[INFO|2024-11-23 02:10:22] logging.py:157 >> {'loss': 0.0699, 'learning_rate': 6.7140e-07, 'epoch': 2.29}
+
+[INFO|2024-11-23 02:10:38] logging.py:157 >> {'loss': 0.0646, 'learning_rate': 6.6371e-07, 'epoch': 2.29}
+
+[INFO|2024-11-23 02:10:54] logging.py:157 >> {'loss': 0.0663, 'learning_rate': 6.5606e-07, 'epoch': 2.30}
+
+[INFO|2024-11-23 02:11:10] logging.py:157 >> {'loss': 0.0556, 'learning_rate': 6.4845e-07, 'epoch': 2.30}
+
+[INFO|2024-11-23 02:11:25] logging.py:157 >> {'loss': 0.0614, 'learning_rate': 6.4088e-07, 'epoch': 2.31}
+
+[INFO|2024-11-23 02:11:40] logging.py:157 >> {'loss': 0.0461, 'learning_rate': 6.3334e-07, 'epoch': 2.31}
+
+[INFO|2024-11-23 02:11:56] logging.py:157 >> {'loss': 0.1030, 'learning_rate': 6.2584e-07, 'epoch': 2.32}
+
+[INFO|2024-11-23 02:12:12] logging.py:157 >> {'loss': 0.0449, 'learning_rate': 6.1838e-07, 'epoch': 2.32}
+
+[INFO|2024-11-23 02:12:28] logging.py:157 >> {'loss': 0.0572, 'learning_rate': 6.1096e-07, 'epoch': 2.32}
+
+[INFO|2024-11-23 02:12:44] logging.py:157 >> {'loss': 0.0558, 'learning_rate': 6.0358e-07, 'epoch': 2.33}
+
+[INFO|2024-11-23 02:12:59] logging.py:157 >> {'loss': 0.0522, 'learning_rate': 5.9624e-07, 'epoch': 2.33}
+
+[INFO|2024-11-23 02:13:15] logging.py:157 >> {'loss': 0.0426, 'learning_rate': 5.8893e-07, 'epoch': 2.34}
+
+[INFO|2024-11-23 02:13:31] logging.py:157 >> {'loss': 0.0454, 'learning_rate': 5.8166e-07, 'epoch': 2.34}
+
+[INFO|2024-11-23 02:13:47] logging.py:157 >> {'loss': 0.0745, 'learning_rate': 5.7444e-07, 'epoch': 2.35}
+
+[INFO|2024-11-23 02:14:04] logging.py:157 >> {'loss': 0.0473, 'learning_rate': 5.6725e-07, 'epoch': 2.35}
+
+[INFO|2024-11-23 02:14:21] logging.py:157 >> {'loss': 0.0453, 'learning_rate': 5.6010e-07, 'epoch': 2.35}
+
+[INFO|2024-11-23 02:14:37] logging.py:157 >> {'loss': 0.0651, 'learning_rate': 5.5299e-07, 'epoch': 2.36}
+
+[INFO|2024-11-23 02:14:52] logging.py:157 >> {'loss': 0.0329, 'learning_rate': 5.4592e-07, 'epoch': 2.36}
+
+[INFO|2024-11-23 02:15:08] logging.py:157 >> {'loss': 0.0836, 'learning_rate': 5.3890e-07, 'epoch': 2.37}
+
+[INFO|2024-11-23 02:15:23] logging.py:157 >> {'loss': 0.0579, 'learning_rate': 5.3191e-07, 'epoch': 2.37}
+
+[INFO|2024-11-23 02:15:39] logging.py:157 >> {'loss': 0.0504, 'learning_rate': 5.2496e-07, 'epoch': 2.38}
+
+[INFO|2024-11-23 02:15:54] logging.py:157 >> {'loss': 0.0627, 'learning_rate': 5.1805e-07, 'epoch': 2.38}
+
+[INFO|2024-11-23 02:16:09] logging.py:157 >> {'loss': 0.0387, 'learning_rate': 5.1118e-07, 'epoch': 2.38}
+
+[INFO|2024-11-23 02:16:25] logging.py:157 >> {'loss': 0.0405, 'learning_rate': 5.0436e-07, 'epoch': 2.39}
+
+[INFO|2024-11-23 02:16:41] logging.py:157 >> {'loss': 0.0555, 'learning_rate': 4.9757e-07, 'epoch': 2.39}
+
+[INFO|2024-11-23 02:16:57] logging.py:157 >> {'loss': 0.0623, 'learning_rate': 4.9082e-07, 'epoch': 2.40}
+
+[INFO|2024-11-23 02:17:12] logging.py:157 >> {'loss': 0.0494, 'learning_rate': 4.8412e-07, 'epoch': 2.40}
+
+[INFO|2024-11-23 02:17:27] logging.py:157 >> {'loss': 0.0696, 'learning_rate': 4.7746e-07, 'epoch': 2.40}
+
+[INFO|2024-11-23 02:17:43] logging.py:157 >> {'loss': 0.0432, 'learning_rate': 4.7084e-07, 'epoch': 2.41}
+
+[INFO|2024-11-23 02:17:59] logging.py:157 >> {'loss': 0.0608, 'learning_rate': 4.6426e-07, 'epoch': 2.41}
+
+[INFO|2024-11-23 02:18:15] logging.py:157 >> {'loss': 0.0820, 'learning_rate': 4.5772e-07, 'epoch': 2.42}
+
+[INFO|2024-11-23 02:18:31] logging.py:157 >> {'loss': 0.0677, 'learning_rate': 4.5122e-07, 'epoch': 2.42}
+
+[INFO|2024-11-23 02:18:47] logging.py:157 >> {'loss': 0.0686, 'learning_rate': 4.4476e-07, 'epoch': 2.43}
+
+[INFO|2024-11-23 02:19:02] logging.py:157 >> {'loss': 0.0429, 'learning_rate': 4.3835e-07, 'epoch': 2.43}
+
+[INFO|2024-11-23 02:19:17] logging.py:157 >> {'loss': 0.0832, 'learning_rate': 4.3198e-07, 'epoch': 2.43}
+
+[INFO|2024-11-23 02:19:33] logging.py:157 >> {'loss': 0.0681, 'learning_rate': 4.2565e-07, 'epoch': 2.44}
+
+[INFO|2024-11-23 02:19:49] logging.py:157 >> {'loss': 0.0548, 'learning_rate': 4.1937e-07, 'epoch': 2.44}
+
+[INFO|2024-11-23 02:20:05] logging.py:157 >> {'loss': 0.0368, 'learning_rate': 4.1312e-07, 'epoch': 2.45}
+
+[INFO|2024-11-23 02:20:21] logging.py:157 >> {'loss': 0.0376, 'learning_rate': 4.0692e-07, 'epoch': 2.45}
+
+[INFO|2024-11-23 02:20:36] logging.py:157 >> {'loss': 0.0805, 'learning_rate': 4.0076e-07, 'epoch': 2.46}
+
+[INFO|2024-11-23 02:20:53] logging.py:157 >> {'loss': 0.0399, 'learning_rate': 3.9465e-07, 'epoch': 2.46}
+
+[INFO|2024-11-23 02:21:09] logging.py:157 >> {'loss': 0.0667, 'learning_rate': 3.8857e-07, 'epoch': 2.46}
+
+[INFO|2024-11-23 02:21:26] logging.py:157 >> {'loss': 0.0613, 'learning_rate': 3.8255e-07, 'epoch': 2.47}
+
+[INFO|2024-11-23 02:21:41] logging.py:157 >> {'loss': 0.0496, 'learning_rate': 3.7656e-07, 'epoch': 2.47}
+
+[INFO|2024-11-23 02:21:57] logging.py:157 >> {'loss': 0.0691, 'learning_rate': 3.7062e-07, 'epoch': 2.48}
+
+[INFO|2024-11-23 02:22:13] logging.py:157 >> {'loss': 0.0504, 'learning_rate': 3.6472e-07, 'epoch': 2.48}
+
+[INFO|2024-11-23 02:22:30] logging.py:157 >> {'loss': 0.0752, 'learning_rate': 3.5886e-07, 'epoch': 2.49}
+
+[INFO|2024-11-23 02:22:46] logging.py:157 >> {'loss': 0.0664, 'learning_rate': 3.5305e-07, 'epoch': 2.49}
+
+[INFO|2024-11-23 02:23:01] logging.py:157 >> {'loss': 0.0528, 'learning_rate': 3.4728e-07, 'epoch': 2.49}
+
+[INFO|2024-11-23 02:23:17] logging.py:157 >> {'loss': 0.0733, 'learning_rate': 3.4156e-07, 'epoch': 2.50}
+
+[INFO|2024-11-23 02:23:33] logging.py:157 >> {'loss': 0.0645, 'learning_rate': 3.3588e-07, 'epoch': 2.50}
+
+[INFO|2024-11-23 02:23:49] logging.py:157 >> {'loss': 0.0638, 'learning_rate': 3.3024e-07, 'epoch': 2.51}
+
+[INFO|2024-11-23 02:24:06] logging.py:157 >> {'loss': 0.0523, 'learning_rate': 3.2465e-07, 'epoch': 2.51}
+
+[INFO|2024-11-23 02:24:22] logging.py:157 >> {'loss': 0.0668, 'learning_rate': 3.1911e-07, 'epoch': 2.52}
+
+[INFO|2024-11-23 02:24:38] logging.py:157 >> {'loss': 0.0462, 'learning_rate': 3.1360e-07, 'epoch': 2.52}
+
+[INFO|2024-11-23 02:24:54] logging.py:157 >> {'loss': 0.0958, 'learning_rate': 3.0815e-07, 'epoch': 2.52}
+
+[INFO|2024-11-23 02:25:10] logging.py:157 >> {'loss': 0.0780, 'learning_rate': 3.0273e-07, 'epoch': 2.53}
+
+[INFO|2024-11-23 02:25:25] logging.py:157 >> {'loss': 0.0785, 'learning_rate': 2.9736e-07, 'epoch': 2.53}
+
+[INFO|2024-11-23 02:25:41] logging.py:157 >> {'loss': 0.0426, 'learning_rate': 2.9204e-07, 'epoch': 2.54}
+
+[INFO|2024-11-23 02:25:57] logging.py:157 >> {'loss': 0.0609, 'learning_rate': 2.8676e-07, 'epoch': 2.54}
+
+[INFO|2024-11-23 02:26:13] logging.py:157 >> {'loss': 0.0462, 'learning_rate': 2.8153e-07, 'epoch': 2.54}
+
+[INFO|2024-11-23 02:26:29] logging.py:157 >> {'loss': 0.0432, 'learning_rate': 2.7634e-07, 'epoch': 2.55}
+
+[INFO|2024-11-23 02:26:45] logging.py:157 >> {'loss': 0.0507, 'learning_rate': 2.7120e-07, 'epoch': 2.55}
+
+[INFO|2024-11-23 02:27:02] logging.py:157 >> {'loss': 0.0409, 'learning_rate': 2.6611e-07, 'epoch': 2.56}
+
+[INFO|2024-11-23 02:27:18] logging.py:157 >> {'loss': 0.0574, 'learning_rate': 2.6106e-07, 'epoch': 2.56}
+
+[INFO|2024-11-23 02:27:33] logging.py:157 >> {'loss': 0.0513, 'learning_rate': 2.5605e-07, 'epoch': 2.57}
+
+[INFO|2024-11-23 02:27:49] logging.py:157 >> {'loss': 0.0474, 'learning_rate': 2.5109e-07, 'epoch': 2.57}
+
+[INFO|2024-11-23 02:28:06] logging.py:157 >> {'loss': 0.0706, 'learning_rate': 2.4618e-07, 'epoch': 2.57}
+
+[INFO|2024-11-23 02:28:21] logging.py:157 >> {'loss': 0.0533, 'learning_rate': 2.4131e-07, 'epoch': 2.58}
+
+[INFO|2024-11-23 02:28:37] logging.py:157 >> {'loss': 0.0641, 'learning_rate': 2.3649e-07, 'epoch': 2.58}
+
+[INFO|2024-11-23 02:28:52] logging.py:157 >> {'loss': 0.0537, 'learning_rate': 2.3172e-07, 'epoch': 2.59}
+
+[INFO|2024-11-23 02:29:08] logging.py:157 >> {'loss': 0.0339, 'learning_rate': 2.2699e-07, 'epoch': 2.59}
+
+[INFO|2024-11-23 02:29:24] logging.py:157 >> {'loss': 0.0464, 'learning_rate': 2.2231e-07, 'epoch': 2.60}
+
+[INFO|2024-11-23 02:29:40] logging.py:157 >> {'loss': 0.0438, 'learning_rate': 2.1767e-07, 'epoch': 2.60}
+
+[INFO|2024-11-23 02:29:56] logging.py:157 >> {'loss': 0.0592, 'learning_rate': 2.1308e-07, 'epoch': 2.60}
+
+[INFO|2024-11-23 02:30:11] logging.py:157 >> {'loss': 0.0619, 'learning_rate': 2.0854e-07, 'epoch': 2.61}
+
+[INFO|2024-11-23 02:30:27] logging.py:157 >> {'loss': 0.0345, 'learning_rate': 2.0405e-07, 'epoch': 2.61}
+
+[INFO|2024-11-23 02:30:43] logging.py:157 >> {'loss': 0.0674, 'learning_rate': 1.9960e-07, 'epoch': 2.62}
+
+[INFO|2024-11-23 02:30:58] logging.py:157 >> {'loss': 0.0733, 'learning_rate': 1.9520e-07, 'epoch': 2.62}
+
+[INFO|2024-11-23 02:31:15] logging.py:157 >> {'loss': 0.0439, 'learning_rate': 1.9084e-07, 'epoch': 2.63}
+
+[INFO|2024-11-23 02:31:30] logging.py:157 >> {'loss': 0.0388, 'learning_rate': 1.8654e-07, 'epoch': 2.63}
+
+[INFO|2024-11-23 02:31:46] logging.py:157 >> {'loss': 0.0393, 'learning_rate': 1.8228e-07, 'epoch': 2.63}
+
+[INFO|2024-11-23 02:32:02] logging.py:157 >> {'loss': 0.0420, 'learning_rate': 1.7806e-07, 'epoch': 2.64}
+
+[INFO|2024-11-23 02:32:18] logging.py:157 >> {'loss': 0.0538, 'learning_rate': 1.7390e-07, 'epoch': 2.64}
+
+[INFO|2024-11-23 02:32:33] logging.py:157 >> {'loss': 0.0512, 'learning_rate': 1.6978e-07, 'epoch': 2.65}
+
+[INFO|2024-11-23 02:32:49] logging.py:157 >> {'loss': 0.0693, 'learning_rate': 1.6571e-07, 'epoch': 2.65}
+
+[INFO|2024-11-23 02:33:04] logging.py:157 >> {'loss': 0.0530, 'learning_rate': 1.6169e-07, 'epoch': 2.66}
+
+[INFO|2024-11-23 02:33:20] logging.py:157 >> {'loss': 0.0395, 'learning_rate': 1.5772e-07, 'epoch': 2.66}
+
+[INFO|2024-11-23 02:33:35] logging.py:157 >> {'loss': 0.0516, 'learning_rate': 1.5379e-07, 'epoch': 2.66}
+
+[INFO|2024-11-23 02:33:51] logging.py:157 >> {'loss': 0.0525, 'learning_rate': 1.4991e-07, 'epoch': 2.67}
+
+[INFO|2024-11-23 02:34:06] logging.py:157 >> {'loss': 0.0583, 'learning_rate': 1.4608e-07, 'epoch': 2.67}
+
+[INFO|2024-11-23 02:34:22] logging.py:157 >> {'loss': 0.0461, 'learning_rate': 1.4230e-07, 'epoch': 2.68}
+
+[INFO|2024-11-23 02:34:38] logging.py:157 >> {'loss': 0.0478, 'learning_rate': 1.3856e-07, 'epoch': 2.68}
+
+[INFO|2024-11-23 02:34:54] logging.py:157 >> {'loss': 0.0873, 'learning_rate': 1.3488e-07, 'epoch': 2.68}
+
+[INFO|2024-11-23 02:35:10] logging.py:157 >> {'loss': 0.0740, 'learning_rate': 1.3124e-07, 'epoch': 2.69}
+
+[INFO|2024-11-23 02:35:26] logging.py:157 >> {'loss': 0.0498, 'learning_rate': 1.2765e-07, 'epoch': 2.69}
+
+[INFO|2024-11-23 02:35:41] logging.py:157 >> {'loss': 0.0440, 'learning_rate': 1.2411e-07, 'epoch': 2.70}
+
+[INFO|2024-11-23 02:35:56] logging.py:157 >> {'loss': 0.0690, 'learning_rate': 1.2062e-07, 'epoch': 2.70}
+
+[INFO|2024-11-23 02:36:12] logging.py:157 >> {'loss': 0.0399, 'learning_rate': 1.1718e-07, 'epoch': 2.71}
+
+[INFO|2024-11-23 02:36:27] logging.py:157 >> {'loss': 0.0584, 'learning_rate': 1.1378e-07, 'epoch': 2.71}
+
+[INFO|2024-11-23 02:36:43] logging.py:157 >> {'loss': 0.0628, 'learning_rate': 1.1043e-07, 'epoch': 2.71}
+
+[INFO|2024-11-23 02:36:59] logging.py:157 >> {'loss': 0.0523, 'learning_rate': 1.0714e-07, 'epoch': 2.72}
+
+[INFO|2024-11-23 02:37:16] logging.py:157 >> {'loss': 0.0507, 'learning_rate': 1.0389e-07, 'epoch': 2.72}
+
+[INFO|2024-11-23 02:37:31] logging.py:157 >> {'loss': 0.0577, 'learning_rate': 1.0069e-07, 'epoch': 2.73}
+
+[INFO|2024-11-23 02:37:47] logging.py:157 >> {'loss': 0.0459, 'learning_rate': 9.7539e-08, 'epoch': 2.73}
+
+[INFO|2024-11-23 02:38:03] logging.py:157 >> {'loss': 0.0826, 'learning_rate': 9.4438e-08, 'epoch': 2.74}
+
+[INFO|2024-11-23 02:38:19] logging.py:157 >> {'loss': 0.0626, 'learning_rate': 9.1386e-08, 'epoch': 2.74}
+
+[INFO|2024-11-23 02:38:35] logging.py:157 >> {'loss': 0.0780, 'learning_rate': 8.8383e-08, 'epoch': 2.74}
+
+[INFO|2024-11-23 02:38:51] logging.py:157 >> {'loss': 0.0594, 'learning_rate': 8.5429e-08, 'epoch': 2.75}
+
+[INFO|2024-11-23 02:39:07] logging.py:157 >> {'loss': 0.0482, 'learning_rate': 8.2525e-08, 'epoch': 2.75}
+
+[INFO|2024-11-23 02:39:22] logging.py:157 >> {'loss': 0.0679, 'learning_rate': 7.9670e-08, 'epoch': 2.76}
+
+[INFO|2024-11-23 02:39:37] logging.py:157 >> {'loss': 0.0316, 'learning_rate': 7.6865e-08, 'epoch': 2.76}
+
+[INFO|2024-11-23 02:39:53] logging.py:157 >> {'loss': 0.0425, 'learning_rate': 7.4109e-08, 'epoch': 2.77}
+
+[INFO|2024-11-23 02:40:09] logging.py:157 >> {'loss': 0.0417, 'learning_rate': 7.1403e-08, 'epoch': 2.77}
+
+[INFO|2024-11-23 02:40:25] logging.py:157 >> {'loss': 0.0574, 'learning_rate': 6.8746e-08, 'epoch': 2.77}
+
+[INFO|2024-11-23 02:40:41] logging.py:157 >> {'loss': 0.0647, 'learning_rate': 6.6139e-08, 'epoch': 2.78}
+
+[INFO|2024-11-23 02:40:56] logging.py:157 >> {'loss': 0.0518, 'learning_rate': 6.3581e-08, 'epoch': 2.78}
+
+[INFO|2024-11-23 02:41:11] logging.py:157 >> {'loss': 0.0310, 'learning_rate': 6.1074e-08, 'epoch': 2.79}
+
+[INFO|2024-11-23 02:41:26] logging.py:157 >> {'loss': 0.0518, 'learning_rate': 5.8616e-08, 'epoch': 2.79}
+
+[INFO|2024-11-23 02:41:43] logging.py:157 >> {'loss': 0.0675, 'learning_rate': 5.6208e-08, 'epoch': 2.79}
+
+[INFO|2024-11-23 02:41:59] logging.py:157 >> {'loss': 0.0471, 'learning_rate': 5.3851e-08, 'epoch': 2.80}
+
+[INFO|2024-11-23 02:42:15] logging.py:157 >> {'loss': 0.0539, 'learning_rate': 5.1543e-08, 'epoch': 2.80}
+
+[INFO|2024-11-23 02:42:30] logging.py:157 >> {'loss': 0.0674, 'learning_rate': 4.9285e-08, 'epoch': 2.81}
+
+[INFO|2024-11-23 02:42:46] logging.py:157 >> {'loss': 0.0451, 'learning_rate': 4.7077e-08, 'epoch': 2.81}
+
+[INFO|2024-11-23 02:43:02] logging.py:157 >> {'loss': 0.0392, 'learning_rate': 4.4919e-08, 'epoch': 2.82}
+
+[INFO|2024-11-23 02:43:18] logging.py:157 >> {'loss': 0.0397, 'learning_rate': 4.2812e-08, 'epoch': 2.82}
+
+[INFO|2024-11-23 02:43:34] logging.py:157 >> {'loss': 0.0376, 'learning_rate': 4.0755e-08, 'epoch': 2.82}
+
+[INFO|2024-11-23 02:43:49] logging.py:157 >> {'loss': 0.0469, 'learning_rate': 3.8748e-08, 'epoch': 2.83}
+
+[INFO|2024-11-23 02:44:04] logging.py:157 >> {'loss': 0.0510, 'learning_rate': 3.6791e-08, 'epoch': 2.83}
+
+[INFO|2024-11-23 02:44:21] logging.py:157 >> {'loss': 0.0425, 'learning_rate': 3.4884e-08, 'epoch': 2.84}
+
+[INFO|2024-11-23 02:44:36] logging.py:157 >> {'loss': 0.0473, 'learning_rate': 3.3028e-08, 'epoch': 2.84}
+
+[INFO|2024-11-23 02:44:52] logging.py:157 >> {'loss': 0.0584, 'learning_rate': 3.1223e-08, 'epoch': 2.85}
+
+[INFO|2024-11-23 02:45:08] logging.py:157 >> {'loss': 0.0331, 'learning_rate': 2.9467e-08, 'epoch': 2.85}
+
+[INFO|2024-11-23 02:45:23] logging.py:157 >> {'loss': 0.0694, 'learning_rate': 2.7763e-08, 'epoch': 2.85}
+
+[INFO|2024-11-23 02:45:39] logging.py:157 >> {'loss': 0.0404, 'learning_rate': 2.6109e-08, 'epoch': 2.86}
+
+[INFO|2024-11-23 02:45:54] logging.py:157 >> {'loss': 0.0520, 'learning_rate': 2.4505e-08, 'epoch': 2.86}
+
+[INFO|2024-11-23 02:46:10] logging.py:157 >> {'loss': 0.0622, 'learning_rate': 2.2952e-08, 'epoch': 2.87}
+
+[INFO|2024-11-23 02:46:27] logging.py:157 >> {'loss': 0.0437, 'learning_rate': 2.1449e-08, 'epoch': 2.87}
+
+[INFO|2024-11-23 02:46:42] logging.py:157 >> {'loss': 0.0814, 'learning_rate': 1.9998e-08, 'epoch': 2.88}
+
+[INFO|2024-11-23 02:46:58] logging.py:157 >> {'loss': 0.0293, 'learning_rate': 1.8596e-08, 'epoch': 2.88}
+
+[INFO|2024-11-23 02:47:14] logging.py:157 >> {'loss': 0.0439, 'learning_rate': 1.7246e-08, 'epoch': 2.88}
+
+[INFO|2024-11-23 02:47:29] logging.py:157 >> {'loss': 0.0585, 'learning_rate': 1.5946e-08, 'epoch': 2.89}
+
+[INFO|2024-11-23 02:47:45] logging.py:157 >> {'loss': 0.0536, 'learning_rate': 1.4697e-08, 'epoch': 2.89}
+
+[INFO|2024-11-23 02:48:01] logging.py:157 >> {'loss': 0.0384, 'learning_rate': 1.3499e-08, 'epoch': 2.90}
+
+[INFO|2024-11-23 02:48:17] logging.py:157 >> {'loss': 0.0653, 'learning_rate': 1.2352e-08, 'epoch': 2.90}
+
+[INFO|2024-11-23 02:48:32] logging.py:157 >> {'loss': 0.0488, 'learning_rate': 1.1255e-08, 'epoch': 2.91}
+
+[INFO|2024-11-23 02:48:48] logging.py:157 >> {'loss': 0.0426, 'learning_rate': 1.0209e-08, 'epoch': 2.91}
+
+[INFO|2024-11-23 02:49:04] logging.py:157 >> {'loss': 0.0611, 'learning_rate': 9.2147e-09, 'epoch': 2.91}
+
+[INFO|2024-11-23 02:49:21] logging.py:157 >> {'loss': 0.0415, 'learning_rate': 8.2708e-09, 'epoch': 2.92}
+
+[INFO|2024-11-23 02:49:36] logging.py:157 >> {'loss': 0.0524, 'learning_rate': 7.3778e-09, 'epoch': 2.92}
+
+[INFO|2024-11-23 02:49:53] logging.py:157 >> {'loss': 0.0515, 'learning_rate': 6.5357e-09, 'epoch': 2.93}
+
+[INFO|2024-11-23 02:50:08] logging.py:157 >> {'loss': 0.0603, 'learning_rate': 5.7446e-09, 'epoch': 2.93}
+
+[INFO|2024-11-23 02:50:24] logging.py:157 >> {'loss': 0.0516, 'learning_rate': 5.0044e-09, 'epoch': 2.93}
+
+[INFO|2024-11-23 02:50:39] logging.py:157 >> {'loss': 0.0591, 'learning_rate': 4.3152e-09, 'epoch': 2.94}
+
+[INFO|2024-11-23 02:50:56] logging.py:157 >> {'loss': 0.0569, 'learning_rate': 3.6770e-09, 'epoch': 2.94}
+
+[INFO|2024-11-23 02:51:13] logging.py:157 >> {'loss': 0.0421, 'learning_rate': 3.0898e-09, 'epoch': 2.95}
+
+[INFO|2024-11-23 02:51:29] logging.py:157 >> {'loss': 0.0680, 'learning_rate': 2.5537e-09, 'epoch': 2.95}
+
+[INFO|2024-11-23 02:51:44] logging.py:157 >> {'loss': 0.0469, 'learning_rate': 2.0685e-09, 'epoch': 2.96}
+
+[INFO|2024-11-23 02:52:00] logging.py:157 >> {'loss': 0.0467, 'learning_rate': 1.6345e-09, 'epoch': 2.96}
+
+[INFO|2024-11-23 02:52:16] logging.py:157 >> {'loss': 0.0390, 'learning_rate': 1.2514e-09, 'epoch': 2.96}
+
+[INFO|2024-11-23 02:52:32] logging.py:157 >> {'loss': 0.0692, 'learning_rate': 9.1942e-10, 'epoch': 2.97}
+
+[INFO|2024-11-23 02:52:48] logging.py:157 >> {'loss': 0.0621, 'learning_rate': 6.3850e-10, 'epoch': 2.97}
+
+[INFO|2024-11-23 02:53:04] logging.py:157 >> {'loss': 0.0598, 'learning_rate': 4.0865e-10, 'epoch': 2.98}
+
+[INFO|2024-11-23 02:53:19] logging.py:157 >> {'loss': 0.0588, 'learning_rate': 2.2987e-10, 'epoch': 2.98}
+
+[INFO|2024-11-23 02:53:35] logging.py:157 >> {'loss': 0.0684, 'learning_rate': 1.0216e-10, 'epoch': 2.99}
+
+[INFO|2024-11-23 02:53:50] logging.py:157 >> {'loss': 0.0641, 'learning_rate': 2.5541e-11, 'epoch': 2.99}
+
+[INFO|2024-11-23 02:54:05] logging.py:157 >> {'loss': 0.0308, 'learning_rate': 0.0000e+00, 'epoch': 2.99}
+
+[INFO|2024-11-23 02:54:13] trainer.py:3801 >> Saving model checkpoint to saves/Llama-3-8B/full/train_2024-11-22-23-46-34/checkpoint-705
+
+[INFO|2024-11-23 02:54:13] configuration_utils.py:414 >> Configuration saved in saves/Llama-3-8B/full/train_2024-11-22-23-46-34/checkpoint-705/config.json
+
+[INFO|2024-11-23 02:54:13] configuration_utils.py:865 >> Configuration saved in saves/Llama-3-8B/full/train_2024-11-22-23-46-34/checkpoint-705/generation_config.json
+
+[INFO|2024-11-23 02:54:30] modeling_utils.py:3043 >> The model is bigger than the maximum size per checkpoint (5GB) and is going to be split in 4 checkpoint shards. You can find where each parameters has been saved in the index located at saves/Llama-3-8B/full/train_2024-11-22-23-46-34/checkpoint-705/model.safetensors.index.json.
+
+[INFO|2024-11-23 02:54:30] tokenization_utils_base.py:2646 >> tokenizer config file saved in saves/Llama-3-8B/full/train_2024-11-22-23-46-34/checkpoint-705/tokenizer_config.json
+
+[INFO|2024-11-23 02:54:30] tokenization_utils_base.py:2655 >> Special tokens file saved in saves/Llama-3-8B/full/train_2024-11-22-23-46-34/checkpoint-705/special_tokens_map.json
+
+[INFO|2024-11-23 02:55:07] trainer.py:2584 >> 
+
+Training completed. Do not forget to share your model on huggingface.co/models =)
+
+
+
+[INFO|2024-11-23 02:55:14] trainer.py:3801 >> Saving model checkpoint to saves/Llama-3-8B/full/train_2024-11-22-23-46-34
+
+[INFO|2024-11-23 02:55:14] configuration_utils.py:414 >> Configuration saved in saves/Llama-3-8B/full/train_2024-11-22-23-46-34/config.json
+
+[INFO|2024-11-23 02:55:14] configuration_utils.py:865 >> Configuration saved in saves/Llama-3-8B/full/train_2024-11-22-23-46-34/generation_config.json
+
+[INFO|2024-11-23 02:55:32] modeling_utils.py:3043 >> The model is bigger than the maximum size per checkpoint (5GB) and is going to be split in 4 checkpoint shards. You can find where each parameters has been saved in the index located at saves/Llama-3-8B/full/train_2024-11-22-23-46-34/model.safetensors.index.json.
+
+[INFO|2024-11-23 02:55:32] tokenization_utils_base.py:2646 >> tokenizer config file saved in saves/Llama-3-8B/full/train_2024-11-22-23-46-34/tokenizer_config.json
+
+[INFO|2024-11-23 02:55:32] tokenization_utils_base.py:2655 >> Special tokens file saved in saves/Llama-3-8B/full/train_2024-11-22-23-46-34/special_tokens_map.json
+
+[WARNING|2024-11-23 02:55:34] logging.py:162 >> No metric eval_loss to plot.
+
+[WARNING|2024-11-23 02:55:34] logging.py:162 >> No metric eval_accuracy to plot.
+
+[INFO|2024-11-23 02:55:34] modelcard.py:449 >> Dropping the following result as it does not have all the necessary fields:
+{'task': {'name': 'Causal Language Modeling', 'type': 'text-generation'}}
+

rag_truth_hal_detection_model/special_tokens_map.json

@@ -0,0 +1,17 @@
+{
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|end_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|end_of_text|>"
+}

rag_truth_hal_detection_model/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c5cf44023714fb39b05e71e425f8d7b92805ff73f7988b083b8c87f0bf87393
+size 17209961

rag_truth_hal_detection_model/tokenizer_config.json

@@ -0,0 +1,2065 @@
+{
+  "added_tokens_decoder": {
+    "128000": {
+      "content": "<|begin_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128001": {
+      "content": "<|end_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128002": {
+      "content": "<|reserved_special_token_0|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128003": {
+      "content": "<|reserved_special_token_1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128004": {
+      "content": "<|reserved_special_token_2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128005": {
+      "content": "<|reserved_special_token_3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128006": {
+      "content": "<|start_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128007": {
+      "content": "<|end_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128008": {
+      "content": "<|reserved_special_token_4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128009": {
+      "content": "<|eot_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128010": {
+      "content": "<|reserved_special_token_5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128011": {
+      "content": "<|reserved_special_token_6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128012": {
+      "content": "<|reserved_special_token_7|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128013": {
+      "content": "<|reserved_special_token_8|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128014": {
+      "content": "<|reserved_special_token_9|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128015": {
+      "content": "<|reserved_special_token_10|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128016": {
+      "content": "<|reserved_special_token_11|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128017": {
+      "content": "<|reserved_special_token_12|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128018": {
+      "content": "<|reserved_special_token_13|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128019": {
+      "content": "<|reserved_special_token_14|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128020": {
+      "content": "<|reserved_special_token_15|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128021": {
+      "content": "<|reserved_special_token_16|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128022": {
+      "content": "<|reserved_special_token_17|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128023": {
+      "content": "<|reserved_special_token_18|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128024": {
+      "content": "<|reserved_special_token_19|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128025": {
+      "content": "<|reserved_special_token_20|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128026": {
+      "content": "<|reserved_special_token_21|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128027": {
+      "content": "<|reserved_special_token_22|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128028": {
+      "content": "<|reserved_special_token_23|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128029": {
+      "content": "<|reserved_special_token_24|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128030": {
+      "content": "<|reserved_special_token_25|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128031": {
+      "content": "<|reserved_special_token_26|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128032": {
+      "content": "<|reserved_special_token_27|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128033": {
+      "content": "<|reserved_special_token_28|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128034": {
+      "content": "<|reserved_special_token_29|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128035": {
+      "content": "<|reserved_special_token_30|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128036": {
+      "content": "<|reserved_special_token_31|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128037": {
+      "content": "<|reserved_special_token_32|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128038": {
+      "content": "<|reserved_special_token_33|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128039": {
+      "content": "<|reserved_special_token_34|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128040": {
+      "content": "<|reserved_special_token_35|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128041": {
+      "content": "<|reserved_special_token_36|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128042": {
+      "content": "<|reserved_special_token_37|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128043": {
+      "content": "<|reserved_special_token_38|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128044": {
+      "content": "<|reserved_special_token_39|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128045": {
+      "content": "<|reserved_special_token_40|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128046": {
+      "content": "<|reserved_special_token_41|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128047": {
+      "content": "<|reserved_special_token_42|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128048": {
+      "content": "<|reserved_special_token_43|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128049": {
+      "content": "<|reserved_special_token_44|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128050": {
+      "content": "<|reserved_special_token_45|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128051": {
+      "content": "<|reserved_special_token_46|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128052": {
+      "content": "<|reserved_special_token_47|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128053": {
+      "content": "<|reserved_special_token_48|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128054": {
+      "content": "<|reserved_special_token_49|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128055": {
+      "content": "<|reserved_special_token_50|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128056": {
+      "content": "<|reserved_special_token_51|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128057": {
+      "content": "<|reserved_special_token_52|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128058": {
+      "content": "<|reserved_special_token_53|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128059": {
+      "content": "<|reserved_special_token_54|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128060": {
+      "content": "<|reserved_special_token_55|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128061": {
+      "content": "<|reserved_special_token_56|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128062": {
+      "content": "<|reserved_special_token_57|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128063": {
+      "content": "<|reserved_special_token_58|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128064": {
+      "content": "<|reserved_special_token_59|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128065": {
+      "content": "<|reserved_special_token_60|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128066": {
+      "content": "<|reserved_special_token_61|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128067": {
+      "content": "<|reserved_special_token_62|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128068": {
+      "content": "<|reserved_special_token_63|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128069": {
+      "content": "<|reserved_special_token_64|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128070": {
+      "content": "<|reserved_special_token_65|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128071": {
+      "content": "<|reserved_special_token_66|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128072": {
+      "content": "<|reserved_special_token_67|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128073": {
+      "content": "<|reserved_special_token_68|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128074": {
+      "content": "<|reserved_special_token_69|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128075": {
+      "content": "<|reserved_special_token_70|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128076": {
+      "content": "<|reserved_special_token_71|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128077": {
+      "content": "<|reserved_special_token_72|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128078": {
+      "content": "<|reserved_special_token_73|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128079": {
+      "content": "<|reserved_special_token_74|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128080": {
+      "content": "<|reserved_special_token_75|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128081": {
+      "content": "<|reserved_special_token_76|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128082": {
+      "content": "<|reserved_special_token_77|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128083": {
+      "content": "<|reserved_special_token_78|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128084": {
+      "content": "<|reserved_special_token_79|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128085": {
+      "content": "<|reserved_special_token_80|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128086": {
+      "content": "<|reserved_special_token_81|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128087": {
+      "content": "<|reserved_special_token_82|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128088": {
+      "content": "<|reserved_special_token_83|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128089": {
+      "content": "<|reserved_special_token_84|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128090": {
+      "content": "<|reserved_special_token_85|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128091": {
+      "content": "<|reserved_special_token_86|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128092": {
+      "content": "<|reserved_special_token_87|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128093": {
+      "content": "<|reserved_special_token_88|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128094": {
+      "content": "<|reserved_special_token_89|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128095": {
+      "content": "<|reserved_special_token_90|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128096": {
+      "content": "<|reserved_special_token_91|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128097": {
+      "content": "<|reserved_special_token_92|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128098": {
+      "content": "<|reserved_special_token_93|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128099": {
+      "content": "<|reserved_special_token_94|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128100": {
+      "content": "<|reserved_special_token_95|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128101": {
+      "content": "<|reserved_special_token_96|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128102": {
+      "content": "<|reserved_special_token_97|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128103": {
+      "content": "<|reserved_special_token_98|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128104": {
+      "content": "<|reserved_special_token_99|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128105": {
+      "content": "<|reserved_special_token_100|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128106": {
+      "content": "<|reserved_special_token_101|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128107": {
+      "content": "<|reserved_special_token_102|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128108": {
+      "content": "<|reserved_special_token_103|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128109": {
+      "content": "<|reserved_special_token_104|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128110": {
+      "content": "<|reserved_special_token_105|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128111": {
+      "content": "<|reserved_special_token_106|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128112": {
+      "content": "<|reserved_special_token_107|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128113": {
+      "content": "<|reserved_special_token_108|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128114": {
+      "content": "<|reserved_special_token_109|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128115": {
+      "content": "<|reserved_special_token_110|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128116": {
+      "content": "<|reserved_special_token_111|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128117": {
+      "content": "<|reserved_special_token_112|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128118": {
+      "content": "<|reserved_special_token_113|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128119": {
+      "content": "<|reserved_special_token_114|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128120": {
+      "content": "<|reserved_special_token_115|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128121": {
+      "content": "<|reserved_special_token_116|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128122": {
+      "content": "<|reserved_special_token_117|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128123": {
+      "content": "<|reserved_special_token_118|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128124": {
+      "content": "<|reserved_special_token_119|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128125": {
+      "content": "<|reserved_special_token_120|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128126": {
+      "content": "<|reserved_special_token_121|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128127": {
+      "content": "<|reserved_special_token_122|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128128": {
+      "content": "<|reserved_special_token_123|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128129": {
+      "content": "<|reserved_special_token_124|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128130": {
+      "content": "<|reserved_special_token_125|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128131": {
+      "content": "<|reserved_special_token_126|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128132": {
+      "content": "<|reserved_special_token_127|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128133": {
+      "content": "<|reserved_special_token_128|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128134": {
+      "content": "<|reserved_special_token_129|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128135": {
+      "content": "<|reserved_special_token_130|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128136": {
+      "content": "<|reserved_special_token_131|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128137": {
+      "content": "<|reserved_special_token_132|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128138": {
+      "content": "<|reserved_special_token_133|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128139": {
+      "content": "<|reserved_special_token_134|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128140": {
+      "content": "<|reserved_special_token_135|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128141": {
+      "content": "<|reserved_special_token_136|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128142": {
+      "content": "<|reserved_special_token_137|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128143": {
+      "content": "<|reserved_special_token_138|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128144": {
+      "content": "<|reserved_special_token_139|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128145": {
+      "content": "<|reserved_special_token_140|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128146": {
+      "content": "<|reserved_special_token_141|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128147": {
+      "content": "<|reserved_special_token_142|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128148": {
+      "content": "<|reserved_special_token_143|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128149": {
+      "content": "<|reserved_special_token_144|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128150": {
+      "content": "<|reserved_special_token_145|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128151": {
+      "content": "<|reserved_special_token_146|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128152": {
+      "content": "<|reserved_special_token_147|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128153": {
+      "content": "<|reserved_special_token_148|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128154": {
+      "content": "<|reserved_special_token_149|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128155": {
+      "content": "<|reserved_special_token_150|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128156": {
+      "content": "<|reserved_special_token_151|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128157": {
+      "content": "<|reserved_special_token_152|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128158": {
+      "content": "<|reserved_special_token_153|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128159": {
+      "content": "<|reserved_special_token_154|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128160": {
+      "content": "<|reserved_special_token_155|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128161": {
+      "content": "<|reserved_special_token_156|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128162": {
+      "content": "<|reserved_special_token_157|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128163": {
+      "content": "<|reserved_special_token_158|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128164": {
+      "content": "<|reserved_special_token_159|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128165": {
+      "content": "<|reserved_special_token_160|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128166": {
+      "content": "<|reserved_special_token_161|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128167": {
+      "content": "<|reserved_special_token_162|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128168": {
+      "content": "<|reserved_special_token_163|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128169": {
+      "content": "<|reserved_special_token_164|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128170": {
+      "content": "<|reserved_special_token_165|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128171": {
+      "content": "<|reserved_special_token_166|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128172": {
+      "content": "<|reserved_special_token_167|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128173": {
+      "content": "<|reserved_special_token_168|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128174": {
+      "content": "<|reserved_special_token_169|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128175": {
+      "content": "<|reserved_special_token_170|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128176": {
+      "content": "<|reserved_special_token_171|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128177": {
+      "content": "<|reserved_special_token_172|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128178": {
+      "content": "<|reserved_special_token_173|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128179": {
+      "content": "<|reserved_special_token_174|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128180": {
+      "content": "<|reserved_special_token_175|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128181": {
+      "content": "<|reserved_special_token_176|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128182": {
+      "content": "<|reserved_special_token_177|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128183": {
+      "content": "<|reserved_special_token_178|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128184": {
+      "content": "<|reserved_special_token_179|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128185": {
+      "content": "<|reserved_special_token_180|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128186": {
+      "content": "<|reserved_special_token_181|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128187": {
+      "content": "<|reserved_special_token_182|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128188": {
+      "content": "<|reserved_special_token_183|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128189": {
+      "content": "<|reserved_special_token_184|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128190": {
+      "content": "<|reserved_special_token_185|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128191": {
+      "content": "<|reserved_special_token_186|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128192": {
+      "content": "<|reserved_special_token_187|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128193": {
+      "content": "<|reserved_special_token_188|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128194": {
+      "content": "<|reserved_special_token_189|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128195": {
+      "content": "<|reserved_special_token_190|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128196": {
+      "content": "<|reserved_special_token_191|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128197": {
+      "content": "<|reserved_special_token_192|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128198": {
+      "content": "<|reserved_special_token_193|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128199": {
+      "content": "<|reserved_special_token_194|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128200": {
+      "content": "<|reserved_special_token_195|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128201": {
+      "content": "<|reserved_special_token_196|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128202": {
+      "content": "<|reserved_special_token_197|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128203": {
+      "content": "<|reserved_special_token_198|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128204": {
+      "content": "<|reserved_special_token_199|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128205": {
+      "content": "<|reserved_special_token_200|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128206": {
+      "content": "<|reserved_special_token_201|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128207": {
+      "content": "<|reserved_special_token_202|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128208": {
+      "content": "<|reserved_special_token_203|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128209": {
+      "content": "<|reserved_special_token_204|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128210": {
+      "content": "<|reserved_special_token_205|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128211": {
+      "content": "<|reserved_special_token_206|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128212": {
+      "content": "<|reserved_special_token_207|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128213": {
+      "content": "<|reserved_special_token_208|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128214": {
+      "content": "<|reserved_special_token_209|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128215": {
+      "content": "<|reserved_special_token_210|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128216": {
+      "content": "<|reserved_special_token_211|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128217": {
+      "content": "<|reserved_special_token_212|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128218": {
+      "content": "<|reserved_special_token_213|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128219": {
+      "content": "<|reserved_special_token_214|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128220": {
+      "content": "<|reserved_special_token_215|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128221": {
+      "content": "<|reserved_special_token_216|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128222": {
+      "content": "<|reserved_special_token_217|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128223": {
+      "content": "<|reserved_special_token_218|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128224": {
+      "content": "<|reserved_special_token_219|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128225": {
+      "content": "<|reserved_special_token_220|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128226": {
+      "content": "<|reserved_special_token_221|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128227": {
+      "content": "<|reserved_special_token_222|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128228": {
+      "content": "<|reserved_special_token_223|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128229": {
+      "content": "<|reserved_special_token_224|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128230": {
+      "content": "<|reserved_special_token_225|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128231": {
+      "content": "<|reserved_special_token_226|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128232": {
+      "content": "<|reserved_special_token_227|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128233": {
+      "content": "<|reserved_special_token_228|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128234": {
+      "content": "<|reserved_special_token_229|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128235": {
+      "content": "<|reserved_special_token_230|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128236": {
+      "content": "<|reserved_special_token_231|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128237": {
+      "content": "<|reserved_special_token_232|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128238": {
+      "content": "<|reserved_special_token_233|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128239": {
+      "content": "<|reserved_special_token_234|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128240": {
+      "content": "<|reserved_special_token_235|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128241": {
+      "content": "<|reserved_special_token_236|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128242": {
+      "content": "<|reserved_special_token_237|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128243": {
+      "content": "<|reserved_special_token_238|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128244": {
+      "content": "<|reserved_special_token_239|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128245": {
+      "content": "<|reserved_special_token_240|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128246": {
+      "content": "<|reserved_special_token_241|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128247": {
+      "content": "<|reserved_special_token_242|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128248": {
+      "content": "<|reserved_special_token_243|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128249": {
+      "content": "<|reserved_special_token_244|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128250": {
+      "content": "<|reserved_special_token_245|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128251": {
+      "content": "<|reserved_special_token_246|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128252": {
+      "content": "<|reserved_special_token_247|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128253": {
+      "content": "<|reserved_special_token_248|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128254": {
+      "content": "<|reserved_special_token_249|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128255": {
+      "content": "<|reserved_special_token_250|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|begin_of_text|>",
+  "chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ system_message + '\n' }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ 'Human: ' + content + '\nAssistant:' }}{% elif message['role'] == 'assistant' %}{{ content + '<|end_of_text|>' + '\n' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|end_of_text|>",
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|end_of_text|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}

rag_truth_hal_detection_model/train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.9941706412294646,
+    "total_flos": 1.924797037417595e+18,
+    "train_loss": 0.15324530343108989,
+    "train_runtime": 11186.4742,
+    "train_samples_per_second": 4.047,
+    "train_steps_per_second": 0.063
+}