Upload folder using huggingface_hub

.gitattributes

@@ -37,3 +37,6 @@ checkpoint-5000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 checkpoint-10000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 checkpoint-15000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 checkpoint-20000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-22635/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+eval_2025-02-09-14-03-10/generated_predictions.jsonl filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,60 @@
+---
+library_name: transformers
+license: other
+base_model: Qwen/Qwen2.5-7B-Instruct
+tags:
+- llama-factory
+- full
+- generated_from_trainer
+model-index:
+- name: train_2025-02-07-00-42-22_qwen
+  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_2025-02-07-00-42-22_qwen
+
+This model is a fine-tuned version of [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct) on the train_hal_detection_1125 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: 2
+- total_train_batch_size: 2
+- total_eval_batch_size: 16
+- 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 4.48.2
+- Pytorch 2.3.0a0+ebedce2
+- Datasets 3.2.0
+- Tokenizers 0.21.0

added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 3.0,
+    "num_input_tokens_seen": 44325984,
+    "total_flos": 1.8804729049283297e+18,
+    "train_loss": 0.11007208550827785,
+    "train_runtime": 220429.5839,
+    "train_samples_per_second": 0.205,
+    "train_steps_per_second": 0.103
+}

checkpoint-22635/added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

checkpoint-22635/config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "Qwen/Qwen2.5-7B-Instruct",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.48.2",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

checkpoint-22635/generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.05,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.48.2"
+}

checkpoint-22635/global_step22635/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58fca8b8ab46926e151759ebcb2f68b727696bd69556fe682ebe84864089d8c0
+size 45693717056

checkpoint-22635/global_step22635/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98308d9ae65aaf3b2a047459b5d7bf0c62ea317a7f4f02564c35a7f5739c8471
+size 45693717120

checkpoint-22635/global_step22635/mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f72a976a73691f114381411ec5254957ab141a9d449604429e8c1629c5b6a47d
+size 15231325944

checkpoint-22635/latest

@@ -0,0 +1 @@
+global_step22635

checkpoint-22635/model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec8893ad23f6b4e25d558b7c3652f30827b46c172197c44cf04d009125dded5e
+size 4877660776

checkpoint-22635/model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96ab2dfbebcc95f38e511e5b0634de91a2856ee9f480edfcd2f88526397892d3
+size 4932751008

checkpoint-22635/model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e115bd279bb036f5fa3173fe465ab1a27f86506e63fc66e735f6b532b1649223
+size 4330865200

checkpoint-22635/model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:481a0d59a11f12bacd51df1a156f2f59b5ff564682a2481c428fa925d81f79cc
+size 1089994880

checkpoint-22635/model.safetensors.index.json

@@ -0,0 +1,346 @@
+{
+  "metadata": {
+    "total_size": 15231233024
+  },
+  "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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-00003-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00003-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-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "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.bias": "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.bias": "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-00003-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00003-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.bias": "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.bias": "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.bias": "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-00003-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.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00003-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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.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.bias": "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.bias": "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.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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-00002-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.norm.weight": "model-00003-of-00004.safetensors"
+  }
+}

checkpoint-22635/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34bcae41c589c7e4cab7b2ef263b878c90c2741404a6af11994dc31537b2319b
+size 14512

checkpoint-22635/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d05dc84075e8f7dd1191c36f3be9dda12073208e12f7d2cef433c38d6336774a
+size 14512

checkpoint-22635/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e33bbd4dda7e66662825ace3c1f6e43ac605769744e4e9d2a1226d5ad5f8385
+size 1064

checkpoint-22635/special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-22635/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+size 11421896

checkpoint-22635/tokenizer_config.json

@@ -0,0 +1,209 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 2048,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-22635/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3469befa03cfdc61d08fe4993d0b0451d621d80513a23011f8b231cbcb3efb30
+size 7416

checkpoint-22635/zero_to_fp32.py

@@ -0,0 +1,760 @@
+#!/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 gc
+import json
+import numpy as np
+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, weights_only=False)
+
+        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 tqdm(files, desc='Loading checkpoint shards'):
+        state_dict = torch.load(f, map_location=device, mmap=True, weights_only=False)
+        # 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}")
+
+    fp32_flat_groups = [state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key] 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")
+
+
+class GatheredTensor:
+    """
+    A pseudo tensor that collects partitioned weights.
+    It is more memory efficient when there are multiple groups.
+    """
+
+    def __init__(self, flat_groups, flat_groups_offset, offset, partitioned_numel, shape):
+        self.flat_groups = flat_groups
+        self.flat_groups_offset = flat_groups_offset
+        self.offset = offset
+        self.partitioned_numel = partitioned_numel
+        self.shape = shape
+        self.dtype = self.flat_groups[0][0].dtype
+
+    def contiguous(self):
+        """
+        Merge partitioned weights from flat_groups into a single tensor.
+        """
+        end_idx = self.offset + self.partitioned_numel
+        world_size = len(self.flat_groups)
+        pad_flat_param_chunks = []
+
+        for rank_i in range(world_size):
+            # for each rank, we need to collect weights from related group/groups
+            flat_groups_at_rank_i = self.flat_groups[rank_i]
+            start_group_id = None
+            end_group_id = None
+            for group_id in range(len(self.flat_groups_offset)):
+                if self.flat_groups_offset[group_id] <= self.offset < self.flat_groups_offset[group_id + 1]:
+                    start_group_id = group_id
+                if self.flat_groups_offset[group_id] < end_idx <= self.flat_groups_offset[group_id + 1]:
+                    end_group_id = group_id
+                    break
+            # collect weights from related group/groups
+            for group_id in range(start_group_id, end_group_id + 1):
+                flat_tensor = flat_groups_at_rank_i[group_id]
+                start_offset = self.offset - self.flat_groups_offset[group_id]
+                end_offset = min(end_idx, self.flat_groups_offset[group_id + 1]) - self.flat_groups_offset[group_id]
+                pad_flat_param_chunks.append(flat_tensor[start_offset:end_offset])
+
+        # collect weights from all ranks
+        pad_flat_param = torch.cat(pad_flat_param_chunks, dim=0)
+        param = pad_flat_param[:self.shape.numel()].view(self.shape).contiguous()
+        return param
+
+
+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 = sum([flat_group.numel() for flat_group in fp32_flat_groups[0]]) * 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
+    flat_groups_offset = [0] + list(np.cumsum([flat_tensor.numel() for flat_tensor in fp32_flat_groups[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}"
+            )
+
+        # memory efficient tensor
+        tensor = GatheredTensor(fp32_flat_groups, flat_groups_offset, offset, partitioned_numel, shape)
+        state_dict[name] = tensor
+        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 to_torch_tensor(state_dict, return_empty_tensor=False):
+    """
+    Convert state_dict of GatheredTensor to torch tensor
+    """
+    torch_state_dict = {}
+    converted_tensors = {}
+    for name, tensor in state_dict.items():
+        tensor_id = id(tensor)
+        if tensor_id in converted_tensors:  # shared tensors
+            shared_tensor = torch_state_dict[converted_tensors[tensor_id]]
+            torch_state_dict[name] = shared_tensor
+        else:
+            converted_tensors[tensor_id] = name
+            if return_empty_tensor:
+                torch_state_dict[name] = torch.empty(tensor.shape, dtype=tensor.dtype)
+            else:
+                torch_state_dict[name] = tensor.contiguous()
+    return torch_state_dict
+
+
+def get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir,
+                                             tag=None,
+                                             exclude_frozen_parameters=False,
+                                             lazy_mode=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
+        - ``lazy_mode``: get state_dict in lazy mode. It returns a dict of pesduo tensor instead of torch tensor, which is more memory efficient.
+          Convert the pesduo tensor to torch tensor by ``.contiguous()``
+
+    Returns:
+        - pytorch ``state_dict``
+
+    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.
+
+    Note: the above usage may not work if your application doesn't have sufficient free CPU memory.
+    You may need to use the offline approach using the ``zero_to_fp32.py`` script that is saved with
+    the checkpoint. Or you can load state_dict in lazy mode ::
+
+        from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
+        state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, lazy_mode=True) # not on cpu
+        for name, lazy_tensor in state_dict.item():
+            tensor = lazy_tensor.contiguous()  # to cpu
+            print(name, tensor)
+            # del tensor to release memory if it no longer in use
+    """
+    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")
+
+    state_dict = _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters)
+    if lazy_mode:
+        return state_dict
+    else:
+        return to_torch_tensor(state_dict)
+
+
+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,
+                                                          lazy_mode=True)
+
+    # 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")
+        # an memory-efficient approach for sharding
+        empty_state_dict = to_torch_tensor(state_dict, return_empty_tensor=True)
+        state_dict_split = split_torch_state_dict_into_shards(empty_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 by shard
+    os.makedirs(output_dir, exist_ok=True)
+    filename_to_tensors = state_dict_split.filename_to_tensors.items()
+    for shard_file, tensors in tqdm(filename_to_tensors, desc="Saving checkpoint shards"):
+        shard_state_dict = {tensor_name: state_dict[tensor_name] for tensor_name in tensors}
+        shard_state_dict = to_torch_tensor(shard_state_dict)
+        output_path = os.path.join(output_dir, shard_file)
+        if safe_serialization:
+            save_file(shard_state_dict, output_path, metadata={"format": "pt"})
+        else:
+            torch.save(shard_state_dict, output_path)
+        # release the memory of current shard
+        for tensor_name in list(shard_state_dict.keys()):
+            del state_dict[tensor_name]
+            del shard_state_dict[tensor_name]
+        del shard_state_dict
+        gc.collect()
+
+    # 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)

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "Qwen/Qwen2.5-7B-Instruct",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.48.2",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

eval_2025-02-09-14-03-10/all_results.json

@@ -0,0 +1,10 @@
+{
+    "predict_bleu-4": 78.68414603703702,
+    "predict_model_preparation_time": 0.0084,
+    "predict_rouge-1": 90.219668,
+    "predict_rouge-2": 87.06174974074074,
+    "predict_rouge-l": 89.22581688888889,
+    "predict_runtime": 909.0068,
+    "predict_samples_per_second": 2.97,
+    "predict_steps_per_second": 1.485
+}

eval_2025-02-09-14-03-10/generated_predictions.jsonl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92736eac8ae008e3b9357df2e801a2ef0abdbdbcb4a4e797316f3a211b1c3801
+size 11696749

eval_2025-02-09-14-03-10/llamaboard_config.yaml

@@ -0,0 +1,19 @@
+eval.batch_size: 1
+eval.cutoff_len: 2048
+eval.dataset:
+- test_hal_detection_1125
+eval.dataset_dir: data
+eval.max_new_tokens: 512
+eval.max_samples: '100000'
+eval.output_dir: eval_2025-02-09-14-03-10
+eval.predict: true
+eval.temperature: 0.95
+eval.top_p: 0.7
+top.booster: auto
+top.checkpoint_path: train_2025-02-07-00-42-22_qwen
+top.finetuning_type: full
+top.model_name: Qwen2.5-7B-Instruct
+top.quantization_bit: none
+top.quantization_method: bitsandbytes
+top.rope_scaling: none
+top.template: qwen

eval_2025-02-09-14-03-10/predict_results.json

@@ -0,0 +1,10 @@
+{
+    "predict_bleu-4": 78.68414603703702,
+    "predict_model_preparation_time": 0.0084,
+    "predict_rouge-1": 90.219668,
+    "predict_rouge-2": 87.06174974074074,
+    "predict_rouge-l": 89.22581688888889,
+    "predict_runtime": 909.0068,
+    "predict_samples_per_second": 2.97,
+    "predict_steps_per_second": 1.485
+}

eval_2025-02-09-14-03-10/running_log.txt

@@ -0,0 +1,146 @@
+[INFO|2025-02-09 14:04:47] tokenization_utils_base.py:2032 >> loading file added_tokens.json
+
+[INFO|2025-02-09 14:04:47] tokenization_utils_base.py:2032 >> loading file special_tokens_map.json
+
+[INFO|2025-02-09 14:04:47] tokenization_utils_base.py:2032 >> loading file tokenizer_config.json
+
+[INFO|2025-02-09 14:04:47] tokenization_utils_base.py:2032 >> loading file chat_template.jinja
+
+[INFO|2025-02-09 14:04:47] tokenization_utils_base.py:2304 >> Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
+
+[INFO|2025-02-09 14:04:47] configuration_utils.py:694 >> loading configuration file saves/Qwen2.5-7B-Instruct/full/train_2025-02-07-00-42-22_qwen/config.json
+
+[INFO|2025-02-09 14:04:47] configuration_utils.py:768 >> Model config Qwen2Config {
+  "_name_or_path": "saves/Qwen2.5-7B-Instruct/full/train_2025-02-07-00-42-22_qwen",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.48.2",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}
+
+
+[INFO|2025-02-09 14:04:47] tokenization_utils_base.py:2032 >> loading file vocab.json
+
+[INFO|2025-02-09 14:04:47] tokenization_utils_base.py:2032 >> loading file merges.txt
+
+[INFO|2025-02-09 14:04:47] tokenization_utils_base.py:2032 >> loading file tokenizer.json
+
+[INFO|2025-02-09 14:04:47] tokenization_utils_base.py:2032 >> loading file added_tokens.json
+
+[INFO|2025-02-09 14:04:47] tokenization_utils_base.py:2032 >> loading file special_tokens_map.json
+
+[INFO|2025-02-09 14:04:47] tokenization_utils_base.py:2032 >> loading file tokenizer_config.json
+
+[INFO|2025-02-09 14:04:47] tokenization_utils_base.py:2032 >> loading file chat_template.jinja
+
+[INFO|2025-02-09 14:04:48] tokenization_utils_base.py:2304 >> Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
+
+[INFO|2025-02-09 14:04:48] logging.py:157 >> Add <|im_end|> to stop words.
+
+[INFO|2025-02-09 14:04:48] logging.py:157 >> Loading dataset ragtruth_base_data/test_hallucination_detection_1125.json...
+
+[INFO|2025-02-09 14:04:53] configuration_utils.py:694 >> loading configuration file saves/Qwen2.5-7B-Instruct/full/train_2025-02-07-00-42-22_qwen/config.json
+
+[INFO|2025-02-09 14:04:53] configuration_utils.py:768 >> Model config Qwen2Config {
+  "_name_or_path": "saves/Qwen2.5-7B-Instruct/full/train_2025-02-07-00-42-22_qwen",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.48.2",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}
+
+
+[INFO|2025-02-09 14:04:53] logging.py:157 >> Using KV cache for faster generation.
+
+[INFO|2025-02-09 14:04:53] modeling_utils.py:3901 >> loading weights file saves/Qwen2.5-7B-Instruct/full/train_2025-02-07-00-42-22_qwen/model.safetensors.index.json
+
+[INFO|2025-02-09 14:04:53] modeling_utils.py:1582 >> Instantiating Qwen2ForCausalLM model under default dtype torch.bfloat16.
+
+[INFO|2025-02-09 14:04:53] configuration_utils.py:1140 >> Generate config GenerationConfig {
+  "bos_token_id": 151643,
+  "eos_token_id": 151645
+}
+
+
+[INFO|2025-02-09 14:04:56] modeling_utils.py:4888 >> All model checkpoint weights were used when initializing Qwen2ForCausalLM.
+
+
+[INFO|2025-02-09 14:04:56] modeling_utils.py:4896 >> All the weights of Qwen2ForCausalLM were initialized from the model checkpoint at saves/Qwen2.5-7B-Instruct/full/train_2025-02-07-00-42-22_qwen.
+If your task is similar to the task the model of the checkpoint was trained on, you can already use Qwen2ForCausalLM for predictions without further training.
+
+[INFO|2025-02-09 14:04:57] configuration_utils.py:1093 >> loading configuration file saves/Qwen2.5-7B-Instruct/full/train_2025-02-07-00-42-22_qwen/generation_config.json
+
+[INFO|2025-02-09 14:04:57] configuration_utils.py:1140 >> Generate config GenerationConfig {
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.05,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8
+}
+
+
+[INFO|2025-02-09 14:04:57] logging.py:157 >> Using torch SDPA for faster training and inference.
+
+[INFO|2025-02-09 14:04:57] logging.py:157 >> all params: 7,615,616,512
+
+[WARNING|2025-02-09 14:04:57] logging.py:168 >> Batch generation can be very slow. Consider using `scripts/vllm_infer.py` instead.
+
+[INFO|2025-02-09 14:04:57] trainer.py:4226 >> 
+***** Running Prediction *****
+
+[INFO|2025-02-09 14:04:57] trainer.py:4228 >>   Num examples = 2700
+
+[INFO|2025-02-09 14:04:57] trainer.py:4231 >>   Batch size = 1
+
+[INFO|2025-02-09 14:20:06] logging.py:157 >> Saving prediction results to saves/Qwen2.5-7B-Instruct/full/eval_2025-02-09-14-03-10/generated_predictions.jsonl
+

eval_2025-02-09-14-03-10/trainer_log.jsonl

@@ -0,0 +1,270 @@
+{"current_steps": 5, "total_steps": 1350, "percentage": 0.37, "elapsed_time": "0:00:02", "remaining_time": "0:13:10"}
+{"current_steps": 10, "total_steps": 1350, "percentage": 0.74, "elapsed_time": "0:00:04", "remaining_time": "0:10:21"}
+{"current_steps": 15, "total_steps": 1350, "percentage": 1.11, "elapsed_time": "0:00:09", "remaining_time": "0:14:07"}
+{"current_steps": 20, "total_steps": 1350, "percentage": 1.48, "elapsed_time": "0:00:11", "remaining_time": "0:12:28"}
+{"current_steps": 25, "total_steps": 1350, "percentage": 1.85, "elapsed_time": "0:00:13", "remaining_time": "0:11:46"}
+{"current_steps": 30, "total_steps": 1350, "percentage": 2.22, "elapsed_time": "0:00:15", "remaining_time": "0:11:24"}
+{"current_steps": 35, "total_steps": 1350, "percentage": 2.59, "elapsed_time": "0:00:18", "remaining_time": "0:11:47"}
+{"current_steps": 40, "total_steps": 1350, "percentage": 2.96, "elapsed_time": "0:00:21", "remaining_time": "0:11:37"}
+{"current_steps": 45, "total_steps": 1350, "percentage": 3.33, "elapsed_time": "0:00:24", "remaining_time": "0:11:36"}
+{"current_steps": 50, "total_steps": 1350, "percentage": 3.7, "elapsed_time": "0:00:25", "remaining_time": "0:11:06"}
+{"current_steps": 55, "total_steps": 1350, "percentage": 4.07, "elapsed_time": "0:00:28", "remaining_time": "0:11:14"}
+{"current_steps": 60, "total_steps": 1350, "percentage": 4.44, "elapsed_time": "0:00:32", "remaining_time": "0:11:44"}
+{"current_steps": 65, "total_steps": 1350, "percentage": 4.81, "elapsed_time": "0:00:40", "remaining_time": "0:13:25"}
+{"current_steps": 70, "total_steps": 1350, "percentage": 5.19, "elapsed_time": "0:00:42", "remaining_time": "0:12:54"}
+{"current_steps": 75, "total_steps": 1350, "percentage": 5.56, "elapsed_time": "0:00:44", "remaining_time": "0:12:35"}
+{"current_steps": 80, "total_steps": 1350, "percentage": 5.93, "elapsed_time": "0:00:49", "remaining_time": "0:13:05"}
+{"current_steps": 85, "total_steps": 1350, "percentage": 6.3, "elapsed_time": "0:00:51", "remaining_time": "0:12:53"}
+{"current_steps": 90, "total_steps": 1350, "percentage": 6.67, "elapsed_time": "0:00:56", "remaining_time": "0:13:06"}
+{"current_steps": 95, "total_steps": 1350, "percentage": 7.04, "elapsed_time": "0:00:57", "remaining_time": "0:12:44"}
+{"current_steps": 100, "total_steps": 1350, "percentage": 7.41, "elapsed_time": "0:01:06", "remaining_time": "0:13:56"}
+{"current_steps": 105, "total_steps": 1350, "percentage": 7.78, "elapsed_time": "0:01:19", "remaining_time": "0:15:37"}
+{"current_steps": 110, "total_steps": 1350, "percentage": 8.15, "elapsed_time": "0:01:24", "remaining_time": "0:15:52"}
+{"current_steps": 115, "total_steps": 1350, "percentage": 8.52, "elapsed_time": "0:01:36", "remaining_time": "0:17:12"}
+{"current_steps": 120, "total_steps": 1350, "percentage": 8.89, "elapsed_time": "0:01:37", "remaining_time": "0:16:43"}
+{"current_steps": 125, "total_steps": 1350, "percentage": 9.26, "elapsed_time": "0:01:39", "remaining_time": "0:16:18"}
+{"current_steps": 130, "total_steps": 1350, "percentage": 9.63, "elapsed_time": "0:01:41", "remaining_time": "0:15:53"}
+{"current_steps": 135, "total_steps": 1350, "percentage": 10.0, "elapsed_time": "0:01:45", "remaining_time": "0:15:48"}
+{"current_steps": 140, "total_steps": 1350, "percentage": 10.37, "elapsed_time": "0:01:47", "remaining_time": "0:15:27"}
+{"current_steps": 145, "total_steps": 1350, "percentage": 10.74, "elapsed_time": "0:01:49", "remaining_time": "0:15:11"}
+{"current_steps": 150, "total_steps": 1350, "percentage": 11.11, "elapsed_time": "0:01:51", "remaining_time": "0:14:55"}
+{"current_steps": 155, "total_steps": 1350, "percentage": 11.48, "elapsed_time": "0:01:53", "remaining_time": "0:14:38"}
+{"current_steps": 160, "total_steps": 1350, "percentage": 11.85, "elapsed_time": "0:01:58", "remaining_time": "0:14:43"}
+{"current_steps": 165, "total_steps": 1350, "percentage": 12.22, "elapsed_time": "0:02:00", "remaining_time": "0:14:26"}
+{"current_steps": 170, "total_steps": 1350, "percentage": 12.59, "elapsed_time": "0:02:02", "remaining_time": "0:14:10"}
+{"current_steps": 175, "total_steps": 1350, "percentage": 12.96, "elapsed_time": "0:02:08", "remaining_time": "0:14:22"}
+{"current_steps": 180, "total_steps": 1350, "percentage": 13.33, "elapsed_time": "0:02:10", "remaining_time": "0:14:11"}
+{"current_steps": 185, "total_steps": 1350, "percentage": 13.7, "elapsed_time": "0:02:16", "remaining_time": "0:14:21"}
+{"current_steps": 190, "total_steps": 1350, "percentage": 14.07, "elapsed_time": "0:02:18", "remaining_time": "0:14:05"}
+{"current_steps": 195, "total_steps": 1350, "percentage": 14.44, "elapsed_time": "0:02:21", "remaining_time": "0:14:00"}
+{"current_steps": 200, "total_steps": 1350, "percentage": 14.81, "elapsed_time": "0:02:25", "remaining_time": "0:13:59"}
+{"current_steps": 205, "total_steps": 1350, "percentage": 15.19, "elapsed_time": "0:02:27", "remaining_time": "0:13:46"}
+{"current_steps": 210, "total_steps": 1350, "percentage": 15.56, "elapsed_time": "0:02:32", "remaining_time": "0:13:47"}
+{"current_steps": 215, "total_steps": 1350, "percentage": 15.93, "elapsed_time": "0:02:36", "remaining_time": "0:13:44"}
+{"current_steps": 220, "total_steps": 1350, "percentage": 16.3, "elapsed_time": "0:02:39", "remaining_time": "0:13:37"}
+{"current_steps": 225, "total_steps": 1350, "percentage": 16.67, "elapsed_time": "0:02:42", "remaining_time": "0:13:32"}
+{"current_steps": 230, "total_steps": 1350, "percentage": 17.04, "elapsed_time": "0:02:48", "remaining_time": "0:13:39"}
+{"current_steps": 235, "total_steps": 1350, "percentage": 17.41, "elapsed_time": "0:02:50", "remaining_time": "0:13:28"}
+{"current_steps": 240, "total_steps": 1350, "percentage": 17.78, "elapsed_time": "0:02:53", "remaining_time": "0:13:21"}
+{"current_steps": 245, "total_steps": 1350, "percentage": 18.15, "elapsed_time": "0:02:54", "remaining_time": "0:13:08"}
+{"current_steps": 250, "total_steps": 1350, "percentage": 18.52, "elapsed_time": "0:02:57", "remaining_time": "0:13:02"}
+{"current_steps": 255, "total_steps": 1350, "percentage": 18.89, "elapsed_time": "0:03:01", "remaining_time": "0:12:59"}
+{"current_steps": 260, "total_steps": 1350, "percentage": 19.26, "elapsed_time": "0:03:03", "remaining_time": "0:12:48"}
+{"current_steps": 265, "total_steps": 1350, "percentage": 19.63, "elapsed_time": "0:03:05", "remaining_time": "0:12:37"}
+{"current_steps": 270, "total_steps": 1350, "percentage": 20.0, "elapsed_time": "0:03:09", "remaining_time": "0:12:36"}
+{"current_steps": 275, "total_steps": 1350, "percentage": 20.37, "elapsed_time": "0:03:12", "remaining_time": "0:12:33"}
+{"current_steps": 280, "total_steps": 1350, "percentage": 20.74, "elapsed_time": "0:03:14", "remaining_time": "0:12:25"}
+{"current_steps": 285, "total_steps": 1350, "percentage": 21.11, "elapsed_time": "0:03:18", "remaining_time": "0:12:21"}
+{"current_steps": 290, "total_steps": 1350, "percentage": 21.48, "elapsed_time": "0:03:20", "remaining_time": "0:12:14"}
+{"current_steps": 295, "total_steps": 1350, "percentage": 21.85, "elapsed_time": "0:03:25", "remaining_time": "0:12:16"}
+{"current_steps": 300, "total_steps": 1350, "percentage": 22.22, "elapsed_time": "0:03:35", "remaining_time": "0:12:32"}
+{"current_steps": 305, "total_steps": 1350, "percentage": 22.59, "elapsed_time": "0:03:38", "remaining_time": "0:12:27"}
+{"current_steps": 310, "total_steps": 1350, "percentage": 22.96, "elapsed_time": "0:03:41", "remaining_time": "0:12:22"}
+{"current_steps": 315, "total_steps": 1350, "percentage": 23.33, "elapsed_time": "0:03:43", "remaining_time": "0:12:14"}
+{"current_steps": 320, "total_steps": 1350, "percentage": 23.7, "elapsed_time": "0:03:45", "remaining_time": "0:12:07"}
+{"current_steps": 325, "total_steps": 1350, "percentage": 24.07, "elapsed_time": "0:03:47", "remaining_time": "0:11:58"}
+{"current_steps": 330, "total_steps": 1350, "percentage": 24.44, "elapsed_time": "0:03:52", "remaining_time": "0:11:59"}
+{"current_steps": 335, "total_steps": 1350, "percentage": 24.81, "elapsed_time": "0:03:54", "remaining_time": "0:11:50"}
+{"current_steps": 340, "total_steps": 1350, "percentage": 25.19, "elapsed_time": "0:03:59", "remaining_time": "0:11:50"}
+{"current_steps": 345, "total_steps": 1350, "percentage": 25.56, "elapsed_time": "0:04:02", "remaining_time": "0:11:45"}
+{"current_steps": 350, "total_steps": 1350, "percentage": 25.93, "elapsed_time": "0:04:05", "remaining_time": "0:11:40"}
+{"current_steps": 355, "total_steps": 1350, "percentage": 26.3, "elapsed_time": "0:04:07", "remaining_time": "0:11:34"}
+{"current_steps": 360, "total_steps": 1350, "percentage": 26.67, "elapsed_time": "0:04:09", "remaining_time": "0:11:25"}
+{"current_steps": 365, "total_steps": 1350, "percentage": 27.04, "elapsed_time": "0:04:17", "remaining_time": "0:11:33"}
+{"current_steps": 370, "total_steps": 1350, "percentage": 27.41, "elapsed_time": "0:04:20", "remaining_time": "0:11:30"}
+{"current_steps": 375, "total_steps": 1350, "percentage": 27.78, "elapsed_time": "0:04:32", "remaining_time": "0:11:48"}
+{"current_steps": 380, "total_steps": 1350, "percentage": 28.15, "elapsed_time": "0:04:34", "remaining_time": "0:11:40"}
+{"current_steps": 385, "total_steps": 1350, "percentage": 28.52, "elapsed_time": "0:04:37", "remaining_time": "0:11:35"}
+{"current_steps": 390, "total_steps": 1350, "percentage": 28.89, "elapsed_time": "0:04:39", "remaining_time": "0:11:27"}
+{"current_steps": 395, "total_steps": 1350, "percentage": 29.26, "elapsed_time": "0:04:45", "remaining_time": "0:11:30"}
+{"current_steps": 400, "total_steps": 1350, "percentage": 29.63, "elapsed_time": "0:04:47", "remaining_time": "0:11:23"}
+{"current_steps": 405, "total_steps": 1350, "percentage": 30.0, "elapsed_time": "0:04:49", "remaining_time": "0:11:16"}
+{"current_steps": 410, "total_steps": 1350, "percentage": 30.37, "elapsed_time": "0:04:51", "remaining_time": "0:11:08"}
+{"current_steps": 415, "total_steps": 1350, "percentage": 30.74, "elapsed_time": "0:04:53", "remaining_time": "0:11:00"}
+{"current_steps": 420, "total_steps": 1350, "percentage": 31.11, "elapsed_time": "0:05:02", "remaining_time": "0:11:09"}
+{"current_steps": 425, "total_steps": 1350, "percentage": 31.48, "elapsed_time": "0:05:03", "remaining_time": "0:11:01"}
+{"current_steps": 430, "total_steps": 1350, "percentage": 31.85, "elapsed_time": "0:05:05", "remaining_time": "0:10:53"}
+{"current_steps": 435, "total_steps": 1350, "percentage": 32.22, "elapsed_time": "0:05:10", "remaining_time": "0:10:52"}
+{"current_steps": 440, "total_steps": 1350, "percentage": 32.59, "elapsed_time": "0:05:12", "remaining_time": "0:10:45"}
+{"current_steps": 445, "total_steps": 1350, "percentage": 32.96, "elapsed_time": "0:05:15", "remaining_time": "0:10:42"}
+{"current_steps": 450, "total_steps": 1350, "percentage": 33.33, "elapsed_time": "0:05:17", "remaining_time": "0:10:35"}
+{"current_steps": 455, "total_steps": 1350, "percentage": 33.7, "elapsed_time": "0:05:19", "remaining_time": "0:10:28"}
+{"current_steps": 460, "total_steps": 1350, "percentage": 34.07, "elapsed_time": "0:05:22", "remaining_time": "0:10:23"}
+{"current_steps": 465, "total_steps": 1350, "percentage": 34.44, "elapsed_time": "0:05:24", "remaining_time": "0:10:17"}
+{"current_steps": 470, "total_steps": 1350, "percentage": 34.81, "elapsed_time": "0:05:26", "remaining_time": "0:10:11"}
+{"current_steps": 475, "total_steps": 1350, "percentage": 35.19, "elapsed_time": "0:05:29", "remaining_time": "0:10:06"}
+{"current_steps": 480, "total_steps": 1350, "percentage": 35.56, "elapsed_time": "0:05:31", "remaining_time": "0:10:01"}
+{"current_steps": 485, "total_steps": 1350, "percentage": 35.93, "elapsed_time": "0:05:34", "remaining_time": "0:09:55"}
+{"current_steps": 490, "total_steps": 1350, "percentage": 36.3, "elapsed_time": "0:05:36", "remaining_time": "0:09:49"}
+{"current_steps": 495, "total_steps": 1350, "percentage": 36.67, "elapsed_time": "0:05:38", "remaining_time": "0:09:44"}
+{"current_steps": 500, "total_steps": 1350, "percentage": 37.04, "elapsed_time": "0:05:40", "remaining_time": "0:09:38"}
+{"current_steps": 505, "total_steps": 1350, "percentage": 37.41, "elapsed_time": "0:05:45", "remaining_time": "0:09:37"}
+{"current_steps": 510, "total_steps": 1350, "percentage": 37.78, "elapsed_time": "0:05:47", "remaining_time": "0:09:32"}
+{"current_steps": 515, "total_steps": 1350, "percentage": 38.15, "elapsed_time": "0:05:50", "remaining_time": "0:09:28"}
+{"current_steps": 520, "total_steps": 1350, "percentage": 38.52, "elapsed_time": "0:05:53", "remaining_time": "0:09:24"}
+{"current_steps": 525, "total_steps": 1350, "percentage": 38.89, "elapsed_time": "0:05:55", "remaining_time": "0:09:19"}
+{"current_steps": 530, "total_steps": 1350, "percentage": 39.26, "elapsed_time": "0:05:58", "remaining_time": "0:09:14"}
+{"current_steps": 535, "total_steps": 1350, "percentage": 39.63, "elapsed_time": "0:06:01", "remaining_time": "0:09:10"}
+{"current_steps": 540, "total_steps": 1350, "percentage": 40.0, "elapsed_time": "0:06:03", "remaining_time": "0:09:05"}
+{"current_steps": 545, "total_steps": 1350, "percentage": 40.37, "elapsed_time": "0:06:06", "remaining_time": "0:09:01"}
+{"current_steps": 550, "total_steps": 1350, "percentage": 40.74, "elapsed_time": "0:06:10", "remaining_time": "0:08:58"}
+{"current_steps": 555, "total_steps": 1350, "percentage": 41.11, "elapsed_time": "0:06:12", "remaining_time": "0:08:52"}
+{"current_steps": 560, "total_steps": 1350, "percentage": 41.48, "elapsed_time": "0:06:14", "remaining_time": "0:08:47"}
+{"current_steps": 565, "total_steps": 1350, "percentage": 41.85, "elapsed_time": "0:06:15", "remaining_time": "0:08:42"}
+{"current_steps": 570, "total_steps": 1350, "percentage": 42.22, "elapsed_time": "0:06:20", "remaining_time": "0:08:40"}
+{"current_steps": 575, "total_steps": 1350, "percentage": 42.59, "elapsed_time": "0:06:22", "remaining_time": "0:08:35"}
+{"current_steps": 580, "total_steps": 1350, "percentage": 42.96, "elapsed_time": "0:06:24", "remaining_time": "0:08:30"}
+{"current_steps": 585, "total_steps": 1350, "percentage": 43.33, "elapsed_time": "0:06:28", "remaining_time": "0:08:28"}
+{"current_steps": 590, "total_steps": 1350, "percentage": 43.7, "elapsed_time": "0:06:30", "remaining_time": "0:08:23"}
+{"current_steps": 595, "total_steps": 1350, "percentage": 44.07, "elapsed_time": "0:06:33", "remaining_time": "0:08:18"}
+{"current_steps": 600, "total_steps": 1350, "percentage": 44.44, "elapsed_time": "0:06:35", "remaining_time": "0:08:14"}
+{"current_steps": 605, "total_steps": 1350, "percentage": 44.81, "elapsed_time": "0:06:38", "remaining_time": "0:08:11"}
+{"current_steps": 610, "total_steps": 1350, "percentage": 45.19, "elapsed_time": "0:06:41", "remaining_time": "0:08:07"}
+{"current_steps": 615, "total_steps": 1350, "percentage": 45.56, "elapsed_time": "0:06:45", "remaining_time": "0:08:04"}
+{"current_steps": 620, "total_steps": 1350, "percentage": 45.93, "elapsed_time": "0:06:48", "remaining_time": "0:08:01"}
+{"current_steps": 625, "total_steps": 1350, "percentage": 46.3, "elapsed_time": "0:06:51", "remaining_time": "0:07:56"}
+{"current_steps": 630, "total_steps": 1350, "percentage": 46.67, "elapsed_time": "0:06:53", "remaining_time": "0:07:52"}
+{"current_steps": 635, "total_steps": 1350, "percentage": 47.04, "elapsed_time": "0:06:55", "remaining_time": "0:07:48"}
+{"current_steps": 640, "total_steps": 1350, "percentage": 47.41, "elapsed_time": "0:06:57", "remaining_time": "0:07:43"}
+{"current_steps": 645, "total_steps": 1350, "percentage": 47.78, "elapsed_time": "0:07:01", "remaining_time": "0:07:40"}
+{"current_steps": 650, "total_steps": 1350, "percentage": 48.15, "elapsed_time": "0:07:03", "remaining_time": "0:07:35"}
+{"current_steps": 655, "total_steps": 1350, "percentage": 48.52, "elapsed_time": "0:07:05", "remaining_time": "0:07:31"}
+{"current_steps": 660, "total_steps": 1350, "percentage": 48.89, "elapsed_time": "0:07:07", "remaining_time": "0:07:27"}
+{"current_steps": 665, "total_steps": 1350, "percentage": 49.26, "elapsed_time": "0:07:11", "remaining_time": "0:07:24"}
+{"current_steps": 670, "total_steps": 1350, "percentage": 49.63, "elapsed_time": "0:07:13", "remaining_time": "0:07:19"}
+{"current_steps": 675, "total_steps": 1350, "percentage": 50.0, "elapsed_time": "0:07:15", "remaining_time": "0:07:15"}
+{"current_steps": 680, "total_steps": 1350, "percentage": 50.37, "elapsed_time": "0:07:20", "remaining_time": "0:07:13"}
+{"current_steps": 685, "total_steps": 1350, "percentage": 50.74, "elapsed_time": "0:07:22", "remaining_time": "0:07:09"}
+{"current_steps": 690, "total_steps": 1350, "percentage": 51.11, "elapsed_time": "0:07:23", "remaining_time": "0:07:04"}
+{"current_steps": 695, "total_steps": 1350, "percentage": 51.48, "elapsed_time": "0:07:26", "remaining_time": "0:07:00"}
+{"current_steps": 700, "total_steps": 1350, "percentage": 51.85, "elapsed_time": "0:07:28", "remaining_time": "0:06:56"}
+{"current_steps": 705, "total_steps": 1350, "percentage": 52.22, "elapsed_time": "0:07:30", "remaining_time": "0:06:52"}
+{"current_steps": 710, "total_steps": 1350, "percentage": 52.59, "elapsed_time": "0:07:33", "remaining_time": "0:06:48"}
+{"current_steps": 715, "total_steps": 1350, "percentage": 52.96, "elapsed_time": "0:07:34", "remaining_time": "0:06:43"}
+{"current_steps": 720, "total_steps": 1350, "percentage": 53.33, "elapsed_time": "0:07:38", "remaining_time": "0:06:41"}
+{"current_steps": 725, "total_steps": 1350, "percentage": 53.7, "elapsed_time": "0:07:41", "remaining_time": "0:06:38"}
+{"current_steps": 730, "total_steps": 1350, "percentage": 54.07, "elapsed_time": "0:07:44", "remaining_time": "0:06:34"}
+{"current_steps": 735, "total_steps": 1350, "percentage": 54.44, "elapsed_time": "0:07:47", "remaining_time": "0:06:30"}
+{"current_steps": 740, "total_steps": 1350, "percentage": 54.81, "elapsed_time": "0:07:51", "remaining_time": "0:06:28"}
+{"current_steps": 745, "total_steps": 1350, "percentage": 55.19, "elapsed_time": "0:07:53", "remaining_time": "0:06:24"}
+{"current_steps": 750, "total_steps": 1350, "percentage": 55.56, "elapsed_time": "0:07:57", "remaining_time": "0:06:21"}
+{"current_steps": 755, "total_steps": 1350, "percentage": 55.93, "elapsed_time": "0:08:00", "remaining_time": "0:06:18"}
+{"current_steps": 760, "total_steps": 1350, "percentage": 56.3, "elapsed_time": "0:08:02", "remaining_time": "0:06:14"}
+{"current_steps": 765, "total_steps": 1350, "percentage": 56.67, "elapsed_time": "0:08:04", "remaining_time": "0:06:10"}
+{"current_steps": 770, "total_steps": 1350, "percentage": 57.04, "elapsed_time": "0:08:06", "remaining_time": "0:06:06"}
+{"current_steps": 775, "total_steps": 1350, "percentage": 57.41, "elapsed_time": "0:08:09", "remaining_time": "0:06:03"}
+{"current_steps": 780, "total_steps": 1350, "percentage": 57.78, "elapsed_time": "0:08:11", "remaining_time": "0:05:58"}
+{"current_steps": 785, "total_steps": 1350, "percentage": 58.15, "elapsed_time": "0:08:12", "remaining_time": "0:05:54"}
+{"current_steps": 790, "total_steps": 1350, "percentage": 58.52, "elapsed_time": "0:08:15", "remaining_time": "0:05:51"}
+{"current_steps": 795, "total_steps": 1350, "percentage": 58.89, "elapsed_time": "0:08:16", "remaining_time": "0:05:46"}
+{"current_steps": 800, "total_steps": 1350, "percentage": 59.26, "elapsed_time": "0:08:19", "remaining_time": "0:05:43"}
+{"current_steps": 805, "total_steps": 1350, "percentage": 59.63, "elapsed_time": "0:08:22", "remaining_time": "0:05:40"}
+{"current_steps": 810, "total_steps": 1350, "percentage": 60.0, "elapsed_time": "0:08:24", "remaining_time": "0:05:36"}
+{"current_steps": 815, "total_steps": 1350, "percentage": 60.37, "elapsed_time": "0:08:26", "remaining_time": "0:05:32"}
+{"current_steps": 820, "total_steps": 1350, "percentage": 60.74, "elapsed_time": "0:08:29", "remaining_time": "0:05:29"}
+{"current_steps": 825, "total_steps": 1350, "percentage": 61.11, "elapsed_time": "0:08:31", "remaining_time": "0:05:25"}
+{"current_steps": 830, "total_steps": 1350, "percentage": 61.48, "elapsed_time": "0:08:33", "remaining_time": "0:05:21"}
+{"current_steps": 835, "total_steps": 1350, "percentage": 61.85, "elapsed_time": "0:08:35", "remaining_time": "0:05:17"}
+{"current_steps": 840, "total_steps": 1350, "percentage": 62.22, "elapsed_time": "0:08:37", "remaining_time": "0:05:14"}
+{"current_steps": 845, "total_steps": 1350, "percentage": 62.59, "elapsed_time": "0:08:40", "remaining_time": "0:05:10"}
+{"current_steps": 850, "total_steps": 1350, "percentage": 62.96, "elapsed_time": "0:08:41", "remaining_time": "0:05:06"}
+{"current_steps": 855, "total_steps": 1350, "percentage": 63.33, "elapsed_time": "0:08:43", "remaining_time": "0:05:03"}
+{"current_steps": 860, "total_steps": 1350, "percentage": 63.7, "elapsed_time": "0:08:46", "remaining_time": "0:04:59"}
+{"current_steps": 865, "total_steps": 1350, "percentage": 64.07, "elapsed_time": "0:08:48", "remaining_time": "0:04:56"}
+{"current_steps": 870, "total_steps": 1350, "percentage": 64.44, "elapsed_time": "0:08:50", "remaining_time": "0:04:52"}
+{"current_steps": 875, "total_steps": 1350, "percentage": 64.81, "elapsed_time": "0:08:52", "remaining_time": "0:04:48"}
+{"current_steps": 880, "total_steps": 1350, "percentage": 65.19, "elapsed_time": "0:08:54", "remaining_time": "0:04:45"}
+{"current_steps": 885, "total_steps": 1350, "percentage": 65.56, "elapsed_time": "0:08:56", "remaining_time": "0:04:41"}
+{"current_steps": 890, "total_steps": 1350, "percentage": 65.93, "elapsed_time": "0:08:58", "remaining_time": "0:04:38"}
+{"current_steps": 895, "total_steps": 1350, "percentage": 66.3, "elapsed_time": "0:09:01", "remaining_time": "0:04:35"}
+{"current_steps": 900, "total_steps": 1350, "percentage": 66.67, "elapsed_time": "0:09:03", "remaining_time": "0:04:31"}
+{"current_steps": 905, "total_steps": 1350, "percentage": 67.04, "elapsed_time": "0:09:07", "remaining_time": "0:04:29"}
+{"current_steps": 910, "total_steps": 1350, "percentage": 67.41, "elapsed_time": "0:09:11", "remaining_time": "0:04:26"}
+{"current_steps": 915, "total_steps": 1350, "percentage": 67.78, "elapsed_time": "0:09:15", "remaining_time": "0:04:24"}
+{"current_steps": 920, "total_steps": 1350, "percentage": 68.15, "elapsed_time": "0:09:18", "remaining_time": "0:04:21"}
+{"current_steps": 925, "total_steps": 1350, "percentage": 68.52, "elapsed_time": "0:09:22", "remaining_time": "0:04:18"}
+{"current_steps": 930, "total_steps": 1350, "percentage": 68.89, "elapsed_time": "0:09:26", "remaining_time": "0:04:15"}
+{"current_steps": 935, "total_steps": 1350, "percentage": 69.26, "elapsed_time": "0:09:30", "remaining_time": "0:04:13"}
+{"current_steps": 940, "total_steps": 1350, "percentage": 69.63, "elapsed_time": "0:09:33", "remaining_time": "0:04:10"}
+{"current_steps": 945, "total_steps": 1350, "percentage": 70.0, "elapsed_time": "0:09:36", "remaining_time": "0:04:07"}
+{"current_steps": 950, "total_steps": 1350, "percentage": 70.37, "elapsed_time": "0:09:40", "remaining_time": "0:04:04"}
+{"current_steps": 955, "total_steps": 1350, "percentage": 70.74, "elapsed_time": "0:09:44", "remaining_time": "0:04:01"}
+{"current_steps": 960, "total_steps": 1350, "percentage": 71.11, "elapsed_time": "0:09:50", "remaining_time": "0:04:00"}
+{"current_steps": 965, "total_steps": 1350, "percentage": 71.48, "elapsed_time": "0:09:54", "remaining_time": "0:03:57"}
+{"current_steps": 970, "total_steps": 1350, "percentage": 71.85, "elapsed_time": "0:09:59", "remaining_time": "0:03:54"}
+{"current_steps": 975, "total_steps": 1350, "percentage": 72.22, "elapsed_time": "0:10:03", "remaining_time": "0:03:52"}
+{"current_steps": 980, "total_steps": 1350, "percentage": 72.59, "elapsed_time": "0:10:06", "remaining_time": "0:03:49"}
+{"current_steps": 985, "total_steps": 1350, "percentage": 72.96, "elapsed_time": "0:10:12", "remaining_time": "0:03:47"}
+{"current_steps": 990, "total_steps": 1350, "percentage": 73.33, "elapsed_time": "0:10:16", "remaining_time": "0:03:44"}
+{"current_steps": 995, "total_steps": 1350, "percentage": 73.7, "elapsed_time": "0:10:19", "remaining_time": "0:03:40"}
+{"current_steps": 1000, "total_steps": 1350, "percentage": 74.07, "elapsed_time": "0:10:22", "remaining_time": "0:03:37"}
+{"current_steps": 1005, "total_steps": 1350, "percentage": 74.44, "elapsed_time": "0:10:26", "remaining_time": "0:03:35"}
+{"current_steps": 1010, "total_steps": 1350, "percentage": 74.81, "elapsed_time": "0:10:30", "remaining_time": "0:03:32"}
+{"current_steps": 1015, "total_steps": 1350, "percentage": 75.19, "elapsed_time": "0:10:34", "remaining_time": "0:03:29"}
+{"current_steps": 1020, "total_steps": 1350, "percentage": 75.56, "elapsed_time": "0:10:40", "remaining_time": "0:03:27"}
+{"current_steps": 1025, "total_steps": 1350, "percentage": 75.93, "elapsed_time": "0:10:43", "remaining_time": "0:03:24"}
+{"current_steps": 1030, "total_steps": 1350, "percentage": 76.3, "elapsed_time": "0:10:47", "remaining_time": "0:03:21"}
+{"current_steps": 1035, "total_steps": 1350, "percentage": 76.67, "elapsed_time": "0:10:53", "remaining_time": "0:03:18"}
+{"current_steps": 1040, "total_steps": 1350, "percentage": 77.04, "elapsed_time": "0:10:56", "remaining_time": "0:03:15"}
+{"current_steps": 1045, "total_steps": 1350, "percentage": 77.41, "elapsed_time": "0:11:00", "remaining_time": "0:03:12"}
+{"current_steps": 1050, "total_steps": 1350, "percentage": 77.78, "elapsed_time": "0:11:05", "remaining_time": "0:03:10"}
+{"current_steps": 1055, "total_steps": 1350, "percentage": 78.15, "elapsed_time": "0:11:09", "remaining_time": "0:03:07"}
+{"current_steps": 1060, "total_steps": 1350, "percentage": 78.52, "elapsed_time": "0:11:14", "remaining_time": "0:03:04"}
+{"current_steps": 1065, "total_steps": 1350, "percentage": 78.89, "elapsed_time": "0:11:18", "remaining_time": "0:03:01"}
+{"current_steps": 1070, "total_steps": 1350, "percentage": 79.26, "elapsed_time": "0:11:22", "remaining_time": "0:02:58"}
+{"current_steps": 1075, "total_steps": 1350, "percentage": 79.63, "elapsed_time": "0:11:26", "remaining_time": "0:02:55"}
+{"current_steps": 1080, "total_steps": 1350, "percentage": 80.0, "elapsed_time": "0:11:32", "remaining_time": "0:02:53"}
+{"current_steps": 1085, "total_steps": 1350, "percentage": 80.37, "elapsed_time": "0:11:37", "remaining_time": "0:02:50"}
+{"current_steps": 1090, "total_steps": 1350, "percentage": 80.74, "elapsed_time": "0:11:41", "remaining_time": "0:02:47"}
+{"current_steps": 1095, "total_steps": 1350, "percentage": 81.11, "elapsed_time": "0:11:45", "remaining_time": "0:02:44"}
+{"current_steps": 1100, "total_steps": 1350, "percentage": 81.48, "elapsed_time": "0:11:49", "remaining_time": "0:02:41"}
+{"current_steps": 1105, "total_steps": 1350, "percentage": 81.85, "elapsed_time": "0:11:53", "remaining_time": "0:02:38"}
+{"current_steps": 1110, "total_steps": 1350, "percentage": 82.22, "elapsed_time": "0:11:56", "remaining_time": "0:02:35"}
+{"current_steps": 1115, "total_steps": 1350, "percentage": 82.59, "elapsed_time": "0:12:01", "remaining_time": "0:02:31"}
+{"current_steps": 1120, "total_steps": 1350, "percentage": 82.96, "elapsed_time": "0:12:06", "remaining_time": "0:02:29"}
+{"current_steps": 1125, "total_steps": 1350, "percentage": 83.33, "elapsed_time": "0:12:11", "remaining_time": "0:02:26"}
+{"current_steps": 1130, "total_steps": 1350, "percentage": 83.7, "elapsed_time": "0:12:16", "remaining_time": "0:02:23"}
+{"current_steps": 1135, "total_steps": 1350, "percentage": 84.07, "elapsed_time": "0:12:20", "remaining_time": "0:02:20"}
+{"current_steps": 1140, "total_steps": 1350, "percentage": 84.44, "elapsed_time": "0:12:23", "remaining_time": "0:02:17"}
+{"current_steps": 1145, "total_steps": 1350, "percentage": 84.81, "elapsed_time": "0:12:26", "remaining_time": "0:02:13"}
+{"current_steps": 1150, "total_steps": 1350, "percentage": 85.19, "elapsed_time": "0:12:30", "remaining_time": "0:02:10"}
+{"current_steps": 1155, "total_steps": 1350, "percentage": 85.56, "elapsed_time": "0:12:35", "remaining_time": "0:02:07"}
+{"current_steps": 1160, "total_steps": 1350, "percentage": 85.93, "elapsed_time": "0:12:38", "remaining_time": "0:02:04"}
+{"current_steps": 1165, "total_steps": 1350, "percentage": 86.3, "elapsed_time": "0:12:44", "remaining_time": "0:02:01"}
+{"current_steps": 1170, "total_steps": 1350, "percentage": 86.67, "elapsed_time": "0:12:48", "remaining_time": "0:01:58"}
+{"current_steps": 1175, "total_steps": 1350, "percentage": 87.04, "elapsed_time": "0:12:51", "remaining_time": "0:01:54"}
+{"current_steps": 1180, "total_steps": 1350, "percentage": 87.41, "elapsed_time": "0:12:56", "remaining_time": "0:01:51"}
+{"current_steps": 1185, "total_steps": 1350, "percentage": 87.78, "elapsed_time": "0:12:59", "remaining_time": "0:01:48"}
+{"current_steps": 1190, "total_steps": 1350, "percentage": 88.15, "elapsed_time": "0:13:04", "remaining_time": "0:01:45"}
+{"current_steps": 1195, "total_steps": 1350, "percentage": 88.52, "elapsed_time": "0:13:06", "remaining_time": "0:01:42"}
+{"current_steps": 1200, "total_steps": 1350, "percentage": 88.89, "elapsed_time": "0:13:10", "remaining_time": "0:01:38"}
+{"current_steps": 1205, "total_steps": 1350, "percentage": 89.26, "elapsed_time": "0:13:14", "remaining_time": "0:01:35"}
+{"current_steps": 1210, "total_steps": 1350, "percentage": 89.63, "elapsed_time": "0:13:17", "remaining_time": "0:01:32"}
+{"current_steps": 1215, "total_steps": 1350, "percentage": 90.0, "elapsed_time": "0:13:22", "remaining_time": "0:01:29"}
+{"current_steps": 1220, "total_steps": 1350, "percentage": 90.37, "elapsed_time": "0:13:25", "remaining_time": "0:01:25"}
+{"current_steps": 1225, "total_steps": 1350, "percentage": 90.74, "elapsed_time": "0:13:28", "remaining_time": "0:01:22"}
+{"current_steps": 1230, "total_steps": 1350, "percentage": 91.11, "elapsed_time": "0:13:32", "remaining_time": "0:01:19"}
+{"current_steps": 1235, "total_steps": 1350, "percentage": 91.48, "elapsed_time": "0:13:35", "remaining_time": "0:01:15"}
+{"current_steps": 1240, "total_steps": 1350, "percentage": 91.85, "elapsed_time": "0:13:37", "remaining_time": "0:01:12"}
+{"current_steps": 1245, "total_steps": 1350, "percentage": 92.22, "elapsed_time": "0:13:44", "remaining_time": "0:01:09"}
+{"current_steps": 1250, "total_steps": 1350, "percentage": 92.59, "elapsed_time": "0:13:48", "remaining_time": "0:01:06"}
+{"current_steps": 1255, "total_steps": 1350, "percentage": 92.96, "elapsed_time": "0:13:52", "remaining_time": "0:01:03"}
+{"current_steps": 1260, "total_steps": 1350, "percentage": 93.33, "elapsed_time": "0:13:55", "remaining_time": "0:00:59"}
+{"current_steps": 1265, "total_steps": 1350, "percentage": 93.7, "elapsed_time": "0:13:59", "remaining_time": "0:00:56"}
+{"current_steps": 1270, "total_steps": 1350, "percentage": 94.07, "elapsed_time": "0:14:03", "remaining_time": "0:00:53"}
+{"current_steps": 1275, "total_steps": 1350, "percentage": 94.44, "elapsed_time": "0:14:08", "remaining_time": "0:00:49"}
+{"current_steps": 1280, "total_steps": 1350, "percentage": 94.81, "elapsed_time": "0:14:10", "remaining_time": "0:00:46"}
+{"current_steps": 1285, "total_steps": 1350, "percentage": 95.19, "elapsed_time": "0:14:14", "remaining_time": "0:00:43"}
+{"current_steps": 1290, "total_steps": 1350, "percentage": 95.56, "elapsed_time": "0:14:17", "remaining_time": "0:00:39"}
+{"current_steps": 1295, "total_steps": 1350, "percentage": 95.93, "elapsed_time": "0:14:20", "remaining_time": "0:00:36"}
+{"current_steps": 1300, "total_steps": 1350, "percentage": 96.3, "elapsed_time": "0:14:25", "remaining_time": "0:00:33"}
+{"current_steps": 1305, "total_steps": 1350, "percentage": 96.67, "elapsed_time": "0:14:29", "remaining_time": "0:00:29"}
+{"current_steps": 1310, "total_steps": 1350, "percentage": 97.04, "elapsed_time": "0:14:32", "remaining_time": "0:00:26"}
+{"current_steps": 1315, "total_steps": 1350, "percentage": 97.41, "elapsed_time": "0:14:36", "remaining_time": "0:00:23"}
+{"current_steps": 1320, "total_steps": 1350, "percentage": 97.78, "elapsed_time": "0:14:40", "remaining_time": "0:00:20"}
+{"current_steps": 1325, "total_steps": 1350, "percentage": 98.15, "elapsed_time": "0:14:43", "remaining_time": "0:00:16"}
+{"current_steps": 1330, "total_steps": 1350, "percentage": 98.52, "elapsed_time": "0:14:47", "remaining_time": "0:00:13"}
+{"current_steps": 1335, "total_steps": 1350, "percentage": 98.89, "elapsed_time": "0:14:50", "remaining_time": "0:00:10"}
+{"current_steps": 1340, "total_steps": 1350, "percentage": 99.26, "elapsed_time": "0:14:55", "remaining_time": "0:00:06"}
+{"current_steps": 1345, "total_steps": 1350, "percentage": 99.63, "elapsed_time": "0:14:59", "remaining_time": "0:00:03"}
+{"current_steps": 1350, "total_steps": 1350, "percentage": 100.0, "elapsed_time": "0:15:03", "remaining_time": "0:00:00"}

eval_2025-02-09-14-03-10/training_args.yaml

@@ -0,0 +1,19 @@
+cutoff_len: 2048
+dataset_dir: data
+do_predict: true
+eval_dataset: test_hal_detection_1125
+finetuning_type: full
+flash_attn: auto
+max_new_tokens: 512
+max_samples: 100000
+model_name_or_path: saves/Qwen2.5-7B-Instruct/full/train_2025-02-07-00-42-22_qwen
+output_dir: saves/Qwen2.5-7B-Instruct/full/eval_2025-02-09-14-03-10
+per_device_eval_batch_size: 1
+predict_with_generate: true
+preprocessing_num_workers: 16
+quantization_method: bitsandbytes
+stage: sft
+temperature: 0.95
+template: qwen
+top_p: 0.7
+trust_remote_code: true

generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.05,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.48.2"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec8893ad23f6b4e25d558b7c3652f30827b46c172197c44cf04d009125dded5e
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96ab2dfbebcc95f38e511e5b0634de91a2856ee9f480edfcd2f88526397892d3
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e115bd279bb036f5fa3173fe465ab1a27f86506e63fc66e735f6b532b1649223
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:481a0d59a11f12bacd51df1a156f2f59b5ff564682a2481c428fa925d81f79cc
+size 1089994880

model.safetensors.index.json

@@ -0,0 +1,346 @@
+{
+  "metadata": {
+    "total_size": 15231233024
+  },
+  "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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-00003-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00003-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-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "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.bias": "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.bias": "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-00003-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00003-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.bias": "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.bias": "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.bias": "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-00003-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.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00003-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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.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.bias": "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.bias": "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.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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-00002-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.norm.weight": "model-00003-of-00004.safetensors"
+  }
+}

running_log.txt

@@ -44582,3 +44582,972 @@ If your task is similar to the task the model of the checkpoint was trained on,
 
 [INFO|2025-02-09 12:44:33] logging.py:157 >> {'loss': 0.0269, 'learning_rate': 5.2318e-09, 'epoch': 2.94, 'throughput': 201.07}
 
+[INFO|2025-02-09 12:44:43] logging.py:157 >> {'loss': 0.2277, 'learning_rate': 5.2094e-09, 'epoch': 2.94, 'throughput': 201.07}
+
+[INFO|2025-02-09 12:44:52] logging.py:157 >> {'loss': 0.0273, 'learning_rate': 5.1870e-09, 'epoch': 2.94, 'throughput': 201.07}
+
+[INFO|2025-02-09 12:45:02] logging.py:157 >> {'loss': 0.0001, 'learning_rate': 5.1647e-09, 'epoch': 2.94, 'throughput': 201.07}
+
+[INFO|2025-02-09 12:45:11] logging.py:157 >> {'loss': 0.0000, 'learning_rate': 5.1424e-09, 'epoch': 2.94, 'throughput': 201.07}
+
+[INFO|2025-02-09 12:45:21] logging.py:157 >> {'loss': 0.0000, 'learning_rate': 5.1202e-09, 'epoch': 2.94, 'throughput': 201.07}
+
+[INFO|2025-02-09 12:45:31] logging.py:157 >> {'loss': 0.2074, 'learning_rate': 5.0980e-09, 'epoch': 2.94, 'throughput': 201.07}
+
+[INFO|2025-02-09 12:45:40] logging.py:157 >> {'loss': 0.0000, 'learning_rate': 5.0759e-09, 'epoch': 2.94, 'throughput': 201.07}
+
+[INFO|2025-02-09 12:45:49] logging.py:157 >> {'loss': 0.0410, 'learning_rate': 5.0538e-09, 'epoch': 2.94, 'throughput': 201.07}
+
+[INFO|2025-02-09 12:45:58] logging.py:157 >> {'loss': 0.0204, 'learning_rate': 5.0318e-09, 'epoch': 2.94, 'throughput': 201.07}
+
+[INFO|2025-02-09 12:46:07] logging.py:157 >> {'loss': 0.0695, 'learning_rate': 5.0098e-09, 'epoch': 2.94, 'throughput': 201.07}
+
+[INFO|2025-02-09 12:46:17] logging.py:157 >> {'loss': 0.0000, 'learning_rate': 4.9878e-09, 'epoch': 2.94, 'throughput': 201.07}
+
+[INFO|2025-02-09 12:46:25] logging.py:157 >> {'loss': 0.0009, 'learning_rate': 4.9659e-09, 'epoch': 2.94, 'throughput': 201.07}
+
+[INFO|2025-02-09 12:46:35] logging.py:157 >> {'loss': 0.3224, 'learning_rate': 4.9441e-09, 'epoch': 2.94, 'throughput': 201.07}
+
+[INFO|2025-02-09 12:46:45] logging.py:157 >> {'loss': 0.0001, 'learning_rate': 4.9223e-09, 'epoch': 2.94, 'throughput': 201.07}
+
+[INFO|2025-02-09 12:46:53] logging.py:157 >> {'loss': 0.0000, 'learning_rate': 4.9005e-09, 'epoch': 2.94, 'throughput': 201.06}
+
+[INFO|2025-02-09 12:47:03] logging.py:157 >> {'loss': 0.0433, 'learning_rate': 4.8788e-09, 'epoch': 2.94, 'throughput': 201.07}
+
+[INFO|2025-02-09 12:47:13] logging.py:157 >> {'loss': 0.0003, 'learning_rate': 4.8572e-09, 'epoch': 2.94, 'throughput': 201.08}
+
+[INFO|2025-02-09 12:47:23] logging.py:157 >> {'loss': 0.0011, 'learning_rate': 4.8356e-09, 'epoch': 2.94, 'throughput': 201.08}
+
+[INFO|2025-02-09 12:47:32] logging.py:157 >> {'loss': 0.3077, 'learning_rate': 4.8140e-09, 'epoch': 2.94, 'throughput': 201.08}
+
+[INFO|2025-02-09 12:47:43] logging.py:157 >> {'loss': 0.0001, 'learning_rate': 4.7925e-09, 'epoch': 2.94, 'throughput': 201.08}
+
+[INFO|2025-02-09 12:47:52] logging.py:157 >> {'loss': 0.0165, 'learning_rate': 4.7711e-09, 'epoch': 2.94, 'throughput': 201.08}
+
+[INFO|2025-02-09 12:48:01] logging.py:157 >> {'loss': 0.0132, 'learning_rate': 4.7496e-09, 'epoch': 2.94, 'throughput': 201.08}
+
+[INFO|2025-02-09 12:48:10] logging.py:157 >> {'loss': 0.0000, 'learning_rate': 4.7283e-09, 'epoch': 2.94, 'throughput': 201.08}
+
+[INFO|2025-02-09 12:48:19] logging.py:157 >> {'loss': 0.0192, 'learning_rate': 4.7070e-09, 'epoch': 2.94, 'throughput': 201.08}
+
+[INFO|2025-02-09 12:48:29] logging.py:157 >> {'loss': 0.0018, 'learning_rate': 4.6857e-09, 'epoch': 2.94, 'throughput': 201.08}
+
+[INFO|2025-02-09 12:48:39] logging.py:157 >> {'loss': 0.2126, 'learning_rate': 4.6645e-09, 'epoch': 2.94, 'throughput': 201.09}
+
+[INFO|2025-02-09 12:48:49] logging.py:157 >> {'loss': 0.0003, 'learning_rate': 4.6433e-09, 'epoch': 2.94, 'throughput': 201.09}
+
+[INFO|2025-02-09 12:48:58] logging.py:157 >> {'loss': 0.0016, 'learning_rate': 4.6222e-09, 'epoch': 2.94, 'throughput': 201.09}
+
+[INFO|2025-02-09 12:49:08] logging.py:157 >> {'loss': 0.0036, 'learning_rate': 4.6011e-09, 'epoch': 2.94, 'throughput': 201.10}
+
+[INFO|2025-02-09 12:49:19] logging.py:157 >> {'loss': 0.1609, 'learning_rate': 4.5801e-09, 'epoch': 2.94, 'throughput': 201.10}
+
+[INFO|2025-02-09 12:49:27] logging.py:157 >> {'loss': 0.0000, 'learning_rate': 4.5591e-09, 'epoch': 2.94, 'throughput': 201.10}
+
+[INFO|2025-02-09 12:49:37] logging.py:157 >> {'loss': 0.0485, 'learning_rate': 4.5382e-09, 'epoch': 2.94, 'throughput': 201.10}
+
+[INFO|2025-02-09 12:49:46] logging.py:157 >> {'loss': 0.0075, 'learning_rate': 4.5173e-09, 'epoch': 2.94, 'throughput': 201.10}
+
+[INFO|2025-02-09 12:49:56] logging.py:157 >> {'loss': 0.1725, 'learning_rate': 4.4965e-09, 'epoch': 2.94, 'throughput': 201.10}
+
+[INFO|2025-02-09 12:50:06] logging.py:157 >> {'loss': 0.0000, 'learning_rate': 4.4757e-09, 'epoch': 2.94, 'throughput': 201.10}
+
+[INFO|2025-02-09 12:50:14] logging.py:157 >> {'loss': 0.1437, 'learning_rate': 4.4549e-09, 'epoch': 2.94, 'throughput': 201.10}
+
+[INFO|2025-02-09 12:50:24] logging.py:157 >> {'loss': 0.0232, 'learning_rate': 4.4342e-09, 'epoch': 2.94, 'throughput': 201.10}
+
+[INFO|2025-02-09 12:50:33] logging.py:157 >> {'loss': 0.2381, 'learning_rate': 4.4136e-09, 'epoch': 2.94, 'throughput': 201.10}
+
+[INFO|2025-02-09 12:50:42] logging.py:157 >> {'loss': 0.0521, 'learning_rate': 4.3930e-09, 'epoch': 2.94, 'throughput': 201.10}
+
+[INFO|2025-02-09 12:50:51] logging.py:157 >> {'loss': 0.0143, 'learning_rate': 4.3725e-09, 'epoch': 2.94, 'throughput': 201.10}
+
+[INFO|2025-02-09 12:51:01] logging.py:157 >> {'loss': 0.0007, 'learning_rate': 4.3520e-09, 'epoch': 2.94, 'throughput': 201.10}
+
+[INFO|2025-02-09 12:51:11] logging.py:157 >> {'loss': 0.0056, 'learning_rate': 4.3315e-09, 'epoch': 2.94, 'throughput': 201.10}
+
+[INFO|2025-02-09 12:51:20] logging.py:157 >> {'loss': 0.2447, 'learning_rate': 4.3111e-09, 'epoch': 2.94, 'throughput': 201.11}
+
+[INFO|2025-02-09 12:51:31] logging.py:157 >> {'loss': 0.0752, 'learning_rate': 4.2908e-09, 'epoch': 2.94, 'throughput': 201.12}
+
+[INFO|2025-02-09 12:51:41] logging.py:157 >> {'loss': 0.0000, 'learning_rate': 4.2704e-09, 'epoch': 2.94, 'throughput': 201.12}
+
+[INFO|2025-02-09 12:51:49] logging.py:157 >> {'loss': 0.0647, 'learning_rate': 4.2502e-09, 'epoch': 2.94, 'throughput': 201.12}
+
+[INFO|2025-02-09 12:52:00] logging.py:157 >> {'loss': 0.0005, 'learning_rate': 4.2300e-09, 'epoch': 2.94, 'throughput': 201.12}
+
+[INFO|2025-02-09 12:52:09] logging.py:157 >> {'loss': 0.0001, 'learning_rate': 4.2098e-09, 'epoch': 2.94, 'throughput': 201.11}
+
+[INFO|2025-02-09 12:52:19] logging.py:157 >> {'loss': 0.0003, 'learning_rate': 4.1897e-09, 'epoch': 2.94, 'throughput': 201.11}
+
+[INFO|2025-02-09 12:52:29] logging.py:157 >> {'loss': 0.0024, 'learning_rate': 4.1696e-09, 'epoch': 2.94, 'throughput': 201.12}
+
+[INFO|2025-02-09 12:52:38] logging.py:157 >> {'loss': 0.0002, 'learning_rate': 4.1496e-09, 'epoch': 2.94, 'throughput': 201.12}
+
+[INFO|2025-02-09 12:52:49] logging.py:157 >> {'loss': 0.0597, 'learning_rate': 4.1297e-09, 'epoch': 2.95, 'throughput': 201.12}
+
+[INFO|2025-02-09 12:52:59] logging.py:157 >> {'loss': 0.0000, 'learning_rate': 4.1097e-09, 'epoch': 2.95, 'throughput': 201.12}
+
+[INFO|2025-02-09 12:53:09] logging.py:157 >> {'loss': 0.0007, 'learning_rate': 4.0899e-09, 'epoch': 2.95, 'throughput': 201.12}
+
+[INFO|2025-02-09 12:53:19] logging.py:157 >> {'loss': 0.0002, 'learning_rate': 4.0700e-09, 'epoch': 2.95, 'throughput': 201.12}
+
+[INFO|2025-02-09 12:53:29] logging.py:157 >> {'loss': 0.0007, 'learning_rate': 4.0503e-09, 'epoch': 2.95, 'throughput': 201.12}
+
+[INFO|2025-02-09 12:53:38] logging.py:157 >> {'loss': 0.0007, 'learning_rate': 4.0305e-09, 'epoch': 2.95, 'throughput': 201.12}
+
+[INFO|2025-02-09 12:53:48] logging.py:157 >> {'loss': 0.0426, 'learning_rate': 4.0109e-09, 'epoch': 2.95, 'throughput': 201.12}
+
+[INFO|2025-02-09 12:53:58] logging.py:157 >> {'loss': 0.0000, 'learning_rate': 3.9912e-09, 'epoch': 2.95, 'throughput': 201.11}
+
+[INFO|2025-02-09 12:54:08] logging.py:157 >> {'loss': 0.0149, 'learning_rate': 3.9716e-09, 'epoch': 2.95, 'throughput': 201.11}
+
+[INFO|2025-02-09 12:54:18] logging.py:157 >> {'loss': 0.0002, 'learning_rate': 3.9521e-09, 'epoch': 2.95, 'throughput': 201.11}
+
+[INFO|2025-02-09 12:54:27] logging.py:157 >> {'loss': 0.0262, 'learning_rate': 3.9326e-09, 'epoch': 2.95, 'throughput': 201.12}
+
+[INFO|2025-02-09 12:54:37] logging.py:157 >> {'loss': 0.0317, 'learning_rate': 3.9132e-09, 'epoch': 2.95, 'throughput': 201.12}
+
+[INFO|2025-02-09 12:54:46] logging.py:157 >> {'loss': 0.0392, 'learning_rate': 3.8938e-09, 'epoch': 2.95, 'throughput': 201.12}
+
+[INFO|2025-02-09 12:54:56] logging.py:157 >> {'loss': 0.0008, 'learning_rate': 3.8744e-09, 'epoch': 2.95, 'throughput': 201.11}
+
+[INFO|2025-02-09 12:55:04] logging.py:157 >> {'loss': 0.0000, 'learning_rate': 3.8551e-09, 'epoch': 2.95, 'throughput': 201.11}
+
+[INFO|2025-02-09 12:55:14] logging.py:157 >> {'loss': 0.0002, 'learning_rate': 3.8359e-09, 'epoch': 2.95, 'throughput': 201.11}
+
+[INFO|2025-02-09 12:55:24] logging.py:157 >> {'loss': 0.0000, 'learning_rate': 3.8167e-09, 'epoch': 2.95, 'throughput': 201.11}
+
+[INFO|2025-02-09 12:55:33] logging.py:157 >> {'loss': 0.0733, 'learning_rate': 3.7976e-09, 'epoch': 2.95, 'throughput': 201.12}
+
+[INFO|2025-02-09 12:55:44] logging.py:157 >> {'loss': 0.0000, 'learning_rate': 3.7784e-09, 'epoch': 2.95, 'throughput': 201.11}
+
+[INFO|2025-02-09 12:55:52] logging.py:157 >> {'loss': 0.0003, 'learning_rate': 3.7594e-09, 'epoch': 2.95, 'throughput': 201.11}
+
+[INFO|2025-02-09 12:56:02] logging.py:157 >> {'loss': 0.0075, 'learning_rate': 3.7404e-09, 'epoch': 2.95, 'throughput': 201.11}
+
+[INFO|2025-02-09 12:56:12] logging.py:157 >> {'loss': 0.0856, 'learning_rate': 3.7214e-09, 'epoch': 2.95, 'throughput': 201.11}
+
+[INFO|2025-02-09 12:56:20] logging.py:157 >> {'loss': 0.0888, 'learning_rate': 3.7025e-09, 'epoch': 2.95, 'throughput': 201.11}
+
+[INFO|2025-02-09 12:56:31] logging.py:157 >> {'loss': 0.0841, 'learning_rate': 3.6837e-09, 'epoch': 2.95, 'throughput': 201.11}
+
+[INFO|2025-02-09 12:56:40] logging.py:157 >> {'loss': 0.0604, 'learning_rate': 3.6648e-09, 'epoch': 2.95, 'throughput': 201.11}
+
+[INFO|2025-02-09 12:56:50] logging.py:157 >> {'loss': 0.0017, 'learning_rate': 3.6461e-09, 'epoch': 2.95, 'throughput': 201.11}
+
+[INFO|2025-02-09 12:57:00] logging.py:157 >> {'loss': 0.0554, 'learning_rate': 3.6274e-09, 'epoch': 2.95, 'throughput': 201.11}
+
+[INFO|2025-02-09 12:57:09] logging.py:157 >> {'loss': 0.0753, 'learning_rate': 3.6087e-09, 'epoch': 2.95, 'throughput': 201.12}
+
+[INFO|2025-02-09 12:57:19] logging.py:157 >> {'loss': 0.1406, 'learning_rate': 3.5901e-09, 'epoch': 2.95, 'throughput': 201.11}
+
+[INFO|2025-02-09 12:57:28] logging.py:157 >> {'loss': 0.0000, 'learning_rate': 3.5715e-09, 'epoch': 2.95, 'throughput': 201.11}
+
+[INFO|2025-02-09 12:57:38] logging.py:157 >> {'loss': 0.0037, 'learning_rate': 3.5530e-09, 'epoch': 2.95, 'throughput': 201.12}
+
+[INFO|2025-02-09 12:57:47] logging.py:157 >> {'loss': 0.0001, 'learning_rate': 3.5345e-09, 'epoch': 2.95, 'throughput': 201.12}
+
+[INFO|2025-02-09 12:57:56] logging.py:157 >> {'loss': 0.0000, 'learning_rate': 3.5161e-09, 'epoch': 2.95, 'throughput': 201.11}
+
+[INFO|2025-02-09 12:58:06] logging.py:157 >> {'loss': 0.0003, 'learning_rate': 3.4977e-09, 'epoch': 2.95, 'throughput': 201.11}
+
+[INFO|2025-02-09 12:58:16] logging.py:157 >> {'loss': 0.1349, 'learning_rate': 3.4794e-09, 'epoch': 2.95, 'throughput': 201.11}
+
+[INFO|2025-02-09 12:58:25] logging.py:157 >> {'loss': 0.0048, 'learning_rate': 3.4611e-09, 'epoch': 2.95, 'throughput': 201.11}
+
+[INFO|2025-02-09 12:58:35] logging.py:157 >> {'loss': 0.0103, 'learning_rate': 3.4428e-09, 'epoch': 2.95, 'throughput': 201.11}
+
+[INFO|2025-02-09 12:58:45] logging.py:157 >> {'loss': 0.0002, 'learning_rate': 3.4246e-09, 'epoch': 2.95, 'throughput': 201.11}
+
+[INFO|2025-02-09 12:58:56] logging.py:157 >> {'loss': 0.0027, 'learning_rate': 3.4065e-09, 'epoch': 2.95, 'throughput': 201.11}
+
+[INFO|2025-02-09 12:59:05] logging.py:157 >> {'loss': 0.0001, 'learning_rate': 3.3884e-09, 'epoch': 2.95, 'throughput': 201.11}
+
+[INFO|2025-02-09 12:59:15] logging.py:157 >> {'loss': 0.0267, 'learning_rate': 3.3704e-09, 'epoch': 2.95, 'throughput': 201.11}
+
+[INFO|2025-02-09 12:59:26] logging.py:157 >> {'loss': 0.0568, 'learning_rate': 3.3524e-09, 'epoch': 2.95, 'throughput': 201.11}
+
+[INFO|2025-02-09 12:59:35] logging.py:157 >> {'loss': 0.0001, 'learning_rate': 3.3344e-09, 'epoch': 2.95, 'throughput': 201.11}
+
+[INFO|2025-02-09 12:59:44] logging.py:157 >> {'loss': 0.0011, 'learning_rate': 3.3165e-09, 'epoch': 2.95, 'throughput': 201.11}
+
+[INFO|2025-02-09 12:59:55] logging.py:157 >> {'loss': 0.0030, 'learning_rate': 3.2987e-09, 'epoch': 2.95, 'throughput': 201.11}
+
+[INFO|2025-02-09 13:00:05] logging.py:157 >> {'loss': 0.0001, 'learning_rate': 3.2809e-09, 'epoch': 2.95, 'throughput': 201.11}
+
+[INFO|2025-02-09 13:00:15] logging.py:157 >> {'loss': 0.0000, 'learning_rate': 3.2631e-09, 'epoch': 2.95, 'throughput': 201.11}
+
+[INFO|2025-02-09 13:00:24] logging.py:157 >> {'loss': 0.1412, 'learning_rate': 3.2454e-09, 'epoch': 2.95, 'throughput': 201.11}
+
+[INFO|2025-02-09 13:00:33] logging.py:157 >> {'loss': 0.0002, 'learning_rate': 3.2278e-09, 'epoch': 2.95, 'throughput': 201.11}
+
+[INFO|2025-02-09 13:00:44] logging.py:157 >> {'loss': 0.1279, 'learning_rate': 3.2102e-09, 'epoch': 2.95, 'throughput': 201.11}
+
+[INFO|2025-02-09 13:00:53] logging.py:157 >> {'loss': 0.0000, 'learning_rate': 3.1926e-09, 'epoch': 2.95, 'throughput': 201.11}
+
+[INFO|2025-02-09 13:01:02] logging.py:157 >> {'loss': 0.0000, 'learning_rate': 3.1751e-09, 'epoch': 2.95, 'throughput': 201.11}
+
+[INFO|2025-02-09 13:01:12] logging.py:157 >> {'loss': 0.0123, 'learning_rate': 3.1576e-09, 'epoch': 2.95, 'throughput': 201.11}
+
+[INFO|2025-02-09 13:01:21] logging.py:157 >> {'loss': 0.0935, 'learning_rate': 3.1402e-09, 'epoch': 2.95, 'throughput': 201.11}
+
+[INFO|2025-02-09 13:01:31] logging.py:157 >> {'loss': 0.0270, 'learning_rate': 3.1228e-09, 'epoch': 2.95, 'throughput': 201.11}
+
+[INFO|2025-02-09 13:01:40] logging.py:157 >> {'loss': 0.0003, 'learning_rate': 3.1055e-09, 'epoch': 2.95, 'throughput': 201.11}
+
+[INFO|2025-02-09 13:01:49] logging.py:157 >> {'loss': 0.0012, 'learning_rate': 3.0882e-09, 'epoch': 2.95, 'throughput': 201.11}
+
+[INFO|2025-02-09 13:01:58] logging.py:157 >> {'loss': 0.0000, 'learning_rate': 3.0710e-09, 'epoch': 2.95, 'throughput': 201.11}
+
+[INFO|2025-02-09 13:02:08] logging.py:157 >> {'loss': 0.0001, 'learning_rate': 3.0538e-09, 'epoch': 2.95, 'throughput': 201.12}
+
+[INFO|2025-02-09 13:02:18] logging.py:157 >> {'loss': 0.0218, 'learning_rate': 3.0367e-09, 'epoch': 2.95, 'throughput': 201.12}
+
+[INFO|2025-02-09 13:02:26] logging.py:157 >> {'loss': 0.0393, 'learning_rate': 3.0196e-09, 'epoch': 2.95, 'throughput': 201.12}
+
+[INFO|2025-02-09 13:02:36] logging.py:157 >> {'loss': 0.0003, 'learning_rate': 3.0026e-09, 'epoch': 2.95, 'throughput': 201.12}
+
+[INFO|2025-02-09 13:02:46] logging.py:157 >> {'loss': 0.0291, 'learning_rate': 2.9856e-09, 'epoch': 2.95, 'throughput': 201.12}
+
+[INFO|2025-02-09 13:02:55] logging.py:157 >> {'loss': 0.0003, 'learning_rate': 2.9687e-09, 'epoch': 2.95, 'throughput': 201.12}
+
+[INFO|2025-02-09 13:03:04] logging.py:157 >> {'loss': 0.0000, 'learning_rate': 2.9518e-09, 'epoch': 2.95, 'throughput': 201.12}
+
+[INFO|2025-02-09 13:03:13] logging.py:157 >> {'loss': 0.0001, 'learning_rate': 2.9349e-09, 'epoch': 2.95, 'throughput': 201.12}
+
+[INFO|2025-02-09 13:03:23] logging.py:157 >> {'loss': 0.0004, 'learning_rate': 2.9181e-09, 'epoch': 2.95, 'throughput': 201.12}
+
+[INFO|2025-02-09 13:03:33] logging.py:157 >> {'loss': 0.0000, 'learning_rate': 2.9014e-09, 'epoch': 2.95, 'throughput': 201.13}
+
+[INFO|2025-02-09 13:03:41] logging.py:157 >> {'loss': 0.0000, 'learning_rate': 2.8847e-09, 'epoch': 2.95, 'throughput': 201.12}
+
+[INFO|2025-02-09 13:03:52] logging.py:157 >> {'loss': 0.0238, 'learning_rate': 2.8681e-09, 'epoch': 2.95, 'throughput': 201.12}
+
+[INFO|2025-02-09 13:04:00] logging.py:157 >> {'loss': 0.0003, 'learning_rate': 2.8515e-09, 'epoch': 2.95, 'throughput': 201.12}
+
+[INFO|2025-02-09 13:04:10] logging.py:157 >> {'loss': 0.0000, 'learning_rate': 2.8349e-09, 'epoch': 2.95, 'throughput': 201.12}
+
+[INFO|2025-02-09 13:04:19] logging.py:157 >> {'loss': 0.0048, 'learning_rate': 2.8184e-09, 'epoch': 2.95, 'throughput': 201.12}
+
+[INFO|2025-02-09 13:04:28] logging.py:157 >> {'loss': 0.0437, 'learning_rate': 2.8019e-09, 'epoch': 2.95, 'throughput': 201.12}
+
+[INFO|2025-02-09 13:04:38] logging.py:157 >> {'loss': 0.0001, 'learning_rate': 2.7855e-09, 'epoch': 2.95, 'throughput': 201.12}
+
+[INFO|2025-02-09 13:04:47] logging.py:157 >> {'loss': 0.0716, 'learning_rate': 2.7692e-09, 'epoch': 2.96, 'throughput': 201.12}
+
+[INFO|2025-02-09 13:04:57] logging.py:157 >> {'loss': 0.0523, 'learning_rate': 2.7529e-09, 'epoch': 2.96, 'throughput': 201.12}
+
+[INFO|2025-02-09 13:05:06] logging.py:157 >> {'loss': 0.2490, 'learning_rate': 2.7366e-09, 'epoch': 2.96, 'throughput': 201.12}
+
+[INFO|2025-02-09 13:05:15] logging.py:157 >> {'loss': 0.0003, 'learning_rate': 2.7204e-09, 'epoch': 2.96, 'throughput': 201.12}
+
+[INFO|2025-02-09 13:05:26] logging.py:157 >> {'loss': 0.0184, 'learning_rate': 2.7042e-09, 'epoch': 2.96, 'throughput': 201.12}
+
+[INFO|2025-02-09 13:05:35] logging.py:157 >> {'loss': 0.0000, 'learning_rate': 2.6881e-09, 'epoch': 2.96, 'throughput': 201.12}
+
+[INFO|2025-02-09 13:05:44] logging.py:157 >> {'loss': 0.0000, 'learning_rate': 2.6720e-09, 'epoch': 2.96, 'throughput': 201.12}
+
+[INFO|2025-02-09 13:05:55] logging.py:157 >> {'loss': 0.0389, 'learning_rate': 2.6560e-09, 'epoch': 2.96, 'throughput': 201.12}
+
+[INFO|2025-02-09 13:06:04] logging.py:157 >> {'loss': 0.0542, 'learning_rate': 2.6400e-09, 'epoch': 2.96, 'throughput': 201.13}
+
+[INFO|2025-02-09 13:06:15] logging.py:157 >> {'loss': 0.0775, 'learning_rate': 2.6241e-09, 'epoch': 2.96, 'throughput': 201.13}
+
+[INFO|2025-02-09 13:06:25] logging.py:157 >> {'loss': 0.2101, 'learning_rate': 2.6082e-09, 'epoch': 2.96, 'throughput': 201.13}
+
+[INFO|2025-02-09 13:06:34] logging.py:157 >> {'loss': 0.0641, 'learning_rate': 2.5924e-09, 'epoch': 2.96, 'throughput': 201.13}
+
+[INFO|2025-02-09 13:06:43] logging.py:157 >> {'loss': 0.0001, 'learning_rate': 2.5766e-09, 'epoch': 2.96, 'throughput': 201.13}
+
+[INFO|2025-02-09 13:06:54] logging.py:157 >> {'loss': 0.0166, 'learning_rate': 2.5609e-09, 'epoch': 2.96, 'throughput': 201.13}
+
+[INFO|2025-02-09 13:07:04] logging.py:157 >> {'loss': 0.0239, 'learning_rate': 2.5452e-09, 'epoch': 2.96, 'throughput': 201.13}
+
+[INFO|2025-02-09 13:07:14] logging.py:157 >> {'loss': 0.0005, 'learning_rate': 2.5296e-09, 'epoch': 2.96, 'throughput': 201.14}
+
+[INFO|2025-02-09 13:07:23] logging.py:157 >> {'loss': 0.0411, 'learning_rate': 2.5140e-09, 'epoch': 2.96, 'throughput': 201.14}
+
+[INFO|2025-02-09 13:07:33] logging.py:157 >> {'loss': 0.0000, 'learning_rate': 2.4985e-09, 'epoch': 2.96, 'throughput': 201.14}
+
+[INFO|2025-02-09 13:07:43] logging.py:157 >> {'loss': 0.0281, 'learning_rate': 2.4830e-09, 'epoch': 2.96, 'throughput': 201.14}
+
+[INFO|2025-02-09 13:07:54] logging.py:157 >> {'loss': 0.0002, 'learning_rate': 2.4675e-09, 'epoch': 2.96, 'throughput': 201.14}
+
+[INFO|2025-02-09 13:08:04] logging.py:157 >> {'loss': 0.0235, 'learning_rate': 2.4521e-09, 'epoch': 2.96, 'throughput': 201.14}
+
+[INFO|2025-02-09 13:08:14] logging.py:157 >> {'loss': 0.0004, 'learning_rate': 2.4368e-09, 'epoch': 2.96, 'throughput': 201.14}
+
+[INFO|2025-02-09 13:08:23] logging.py:157 >> {'loss': 0.0001, 'learning_rate': 2.4215e-09, 'epoch': 2.96, 'throughput': 201.14}
+
+[INFO|2025-02-09 13:08:33] logging.py:157 >> {'loss': 0.0006, 'learning_rate': 2.4062e-09, 'epoch': 2.96, 'throughput': 201.14}
+
+[INFO|2025-02-09 13:08:42] logging.py:157 >> {'loss': 0.0001, 'learning_rate': 2.3910e-09, 'epoch': 2.96, 'throughput': 201.14}
+
+[INFO|2025-02-09 13:08:52] logging.py:157 >> {'loss': 0.0000, 'learning_rate': 2.3759e-09, 'epoch': 2.96, 'throughput': 201.14}
+
+[INFO|2025-02-09 13:09:01] logging.py:157 >> {'loss': 0.0000, 'learning_rate': 2.3608e-09, 'epoch': 2.96, 'throughput': 201.13}
+
+[INFO|2025-02-09 13:09:11] logging.py:157 >> {'loss': 0.0005, 'learning_rate': 2.3457e-09, 'epoch': 2.96, 'throughput': 201.13}
+
+[INFO|2025-02-09 13:09:21] logging.py:157 >> {'loss': 0.0026, 'learning_rate': 2.3307e-09, 'epoch': 2.96, 'throughput': 201.13}
+
+[INFO|2025-02-09 13:09:31] logging.py:157 >> {'loss': 0.0761, 'learning_rate': 2.3157e-09, 'epoch': 2.96, 'throughput': 201.13}
+
+[INFO|2025-02-09 13:09:41] logging.py:157 >> {'loss': 0.0549, 'learning_rate': 2.3008e-09, 'epoch': 2.96, 'throughput': 201.13}
+
+[INFO|2025-02-09 13:09:50] logging.py:157 >> {'loss': 0.0001, 'learning_rate': 2.2860e-09, 'epoch': 2.96, 'throughput': 201.13}
+
+[INFO|2025-02-09 13:09:59] logging.py:157 >> {'loss': 0.0000, 'learning_rate': 2.2711e-09, 'epoch': 2.96, 'throughput': 201.13}
+
+[INFO|2025-02-09 13:10:08] logging.py:157 >> {'loss': 0.0270, 'learning_rate': 2.2564e-09, 'epoch': 2.96, 'throughput': 201.13}
+
+[INFO|2025-02-09 13:10:17] logging.py:157 >> {'loss': 0.0796, 'learning_rate': 2.2416e-09, 'epoch': 2.96, 'throughput': 201.13}
+
+[INFO|2025-02-09 13:10:27] logging.py:157 >> {'loss': 0.1543, 'learning_rate': 2.2270e-09, 'epoch': 2.96, 'throughput': 201.13}
+
+[INFO|2025-02-09 13:10:38] logging.py:157 >> {'loss': 0.0043, 'learning_rate': 2.2123e-09, 'epoch': 2.96, 'throughput': 201.14}
+
+[INFO|2025-02-09 13:10:46] logging.py:157 >> {'loss': 0.0172, 'learning_rate': 2.1978e-09, 'epoch': 2.96, 'throughput': 201.13}
+
+[INFO|2025-02-09 13:10:57] logging.py:157 >> {'loss': 0.0066, 'learning_rate': 2.1832e-09, 'epoch': 2.96, 'throughput': 201.14}
+
+[INFO|2025-02-09 13:11:07] logging.py:157 >> {'loss': 0.0000, 'learning_rate': 2.1688e-09, 'epoch': 2.96, 'throughput': 201.13}
+
+[INFO|2025-02-09 13:11:16] logging.py:157 >> {'loss': 0.0427, 'learning_rate': 2.1543e-09, 'epoch': 2.96, 'throughput': 201.13}
+
+[INFO|2025-02-09 13:11:25] logging.py:157 >> {'loss': 0.0000, 'learning_rate': 2.1399e-09, 'epoch': 2.96, 'throughput': 201.13}
+
+[INFO|2025-02-09 13:11:34] logging.py:157 >> {'loss': 0.0000, 'learning_rate': 2.1256e-09, 'epoch': 2.96, 'throughput': 201.13}
+
+[INFO|2025-02-09 13:11:45] logging.py:157 >> {'loss': 0.1574, 'learning_rate': 2.1113e-09, 'epoch': 2.96, 'throughput': 201.13}
+
+[INFO|2025-02-09 13:11:55] logging.py:157 >> {'loss': 0.0004, 'learning_rate': 2.0971e-09, 'epoch': 2.96, 'throughput': 201.14}
+
+[INFO|2025-02-09 13:12:05] logging.py:157 >> {'loss': 0.1038, 'learning_rate': 2.0829e-09, 'epoch': 2.96, 'throughput': 201.14}
+
+[INFO|2025-02-09 13:12:15] logging.py:157 >> {'loss': 0.1581, 'learning_rate': 2.0687e-09, 'epoch': 2.96, 'throughput': 201.14}
+
+[INFO|2025-02-09 13:12:24] logging.py:157 >> {'loss': 0.0003, 'learning_rate': 2.0547e-09, 'epoch': 2.96, 'throughput': 201.13}
+
+[INFO|2025-02-09 13:12:34] logging.py:157 >> {'loss': 0.0001, 'learning_rate': 2.0406e-09, 'epoch': 2.96, 'throughput': 201.13}
+
+[INFO|2025-02-09 13:12:44] logging.py:157 >> {'loss': 0.0000, 'learning_rate': 2.0266e-09, 'epoch': 2.96, 'throughput': 201.13}
+
+[INFO|2025-02-09 13:12:53] logging.py:157 >> {'loss': 0.0001, 'learning_rate': 2.0127e-09, 'epoch': 2.96, 'throughput': 201.13}
+
+[INFO|2025-02-09 13:13:04] logging.py:157 >> {'loss': 0.0000, 'learning_rate': 1.9988e-09, 'epoch': 2.96, 'throughput': 201.13}
+
+[INFO|2025-02-09 13:13:13] logging.py:157 >> {'loss': 0.0304, 'learning_rate': 1.9849e-09, 'epoch': 2.96, 'throughput': 201.13}
+
+[INFO|2025-02-09 13:13:22] logging.py:157 >> {'loss': 0.0000, 'learning_rate': 1.9711e-09, 'epoch': 2.96, 'throughput': 201.13}
+
+[INFO|2025-02-09 13:13:32] logging.py:157 >> {'loss': 0.0195, 'learning_rate': 1.9573e-09, 'epoch': 2.96, 'throughput': 201.13}
+
+[INFO|2025-02-09 13:13:42] logging.py:157 >> {'loss': 0.0299, 'learning_rate': 1.9436e-09, 'epoch': 2.96, 'throughput': 201.13}
+
+[INFO|2025-02-09 13:13:53] logging.py:157 >> {'loss': 0.0000, 'learning_rate': 1.9300e-09, 'epoch': 2.96, 'throughput': 201.13}
+
+[INFO|2025-02-09 13:14:03] logging.py:157 >> {'loss': 0.0175, 'learning_rate': 1.9164e-09, 'epoch': 2.96, 'throughput': 201.14}
+
+[INFO|2025-02-09 13:14:13] logging.py:157 >> {'loss': 0.0000, 'learning_rate': 1.9028e-09, 'epoch': 2.96, 'throughput': 201.14}
+
+[INFO|2025-02-09 13:14:23] logging.py:157 >> {'loss': 0.0983, 'learning_rate': 1.8893e-09, 'epoch': 2.96, 'throughput': 201.14}
+
+[INFO|2025-02-09 13:14:32] logging.py:157 >> {'loss': 0.0002, 'learning_rate': 1.8758e-09, 'epoch': 2.96, 'throughput': 201.14}
+
+[INFO|2025-02-09 13:14:42] logging.py:157 >> {'loss': 0.0002, 'learning_rate': 1.8624e-09, 'epoch': 2.96, 'throughput': 201.14}
+
+[INFO|2025-02-09 13:14:52] logging.py:157 >> {'loss': 0.0000, 'learning_rate': 1.8490e-09, 'epoch': 2.96, 'throughput': 201.14}
+
+[INFO|2025-02-09 13:15:01] logging.py:157 >> {'loss': 0.0043, 'learning_rate': 1.8357e-09, 'epoch': 2.96, 'throughput': 201.14}
+
+[INFO|2025-02-09 13:15:11] logging.py:157 >> {'loss': 0.1020, 'learning_rate': 1.8224e-09, 'epoch': 2.96, 'throughput': 201.14}
+
+[INFO|2025-02-09 13:15:20] logging.py:157 >> {'loss': 0.0007, 'learning_rate': 1.8092e-09, 'epoch': 2.96, 'throughput': 201.14}
+
+[INFO|2025-02-09 13:15:30] logging.py:157 >> {'loss': 0.0112, 'learning_rate': 1.7960e-09, 'epoch': 2.96, 'throughput': 201.14}
+
+[INFO|2025-02-09 13:15:40] logging.py:157 >> {'loss': 0.0126, 'learning_rate': 1.7829e-09, 'epoch': 2.96, 'throughput': 201.14}
+
+[INFO|2025-02-09 13:15:49] logging.py:157 >> {'loss': 0.0002, 'learning_rate': 1.7698e-09, 'epoch': 2.96, 'throughput': 201.14}
+
+[INFO|2025-02-09 13:15:58] logging.py:157 >> {'loss': 0.0001, 'learning_rate': 1.7567e-09, 'epoch': 2.96, 'throughput': 201.14}
+
+[INFO|2025-02-09 13:16:07] logging.py:157 >> {'loss': 0.0014, 'learning_rate': 1.7438e-09, 'epoch': 2.96, 'throughput': 201.14}
+
+[INFO|2025-02-09 13:16:18] logging.py:157 >> {'loss': 0.0000, 'learning_rate': 1.7308e-09, 'epoch': 2.96, 'throughput': 201.15}
+
+[INFO|2025-02-09 13:16:27] logging.py:157 >> {'loss': 0.0001, 'learning_rate': 1.7179e-09, 'epoch': 2.96, 'throughput': 201.14}
+
+[INFO|2025-02-09 13:16:37] logging.py:157 >> {'loss': 0.0619, 'learning_rate': 1.7051e-09, 'epoch': 2.96, 'throughput': 201.14}
+
+[INFO|2025-02-09 13:16:48] logging.py:157 >> {'loss': 0.0000, 'learning_rate': 1.6923e-09, 'epoch': 2.96, 'throughput': 201.14}
+
+[INFO|2025-02-09 13:16:57] logging.py:157 >> {'loss': 0.0001, 'learning_rate': 1.6795e-09, 'epoch': 2.97, 'throughput': 201.14}
+
+[INFO|2025-02-09 13:17:06] logging.py:157 >> {'loss': 0.0384, 'learning_rate': 1.6668e-09, 'epoch': 2.97, 'throughput': 201.14}
+
+[INFO|2025-02-09 13:17:15] logging.py:157 >> {'loss': 0.0337, 'learning_rate': 1.6542e-09, 'epoch': 2.97, 'throughput': 201.14}
+
+[INFO|2025-02-09 13:17:24] logging.py:157 >> {'loss': 0.0213, 'learning_rate': 1.6416e-09, 'epoch': 2.97, 'throughput': 201.14}
+
+[INFO|2025-02-09 13:17:34] logging.py:157 >> {'loss': 0.0059, 'learning_rate': 1.6290e-09, 'epoch': 2.97, 'throughput': 201.14}
+
+[INFO|2025-02-09 13:17:44] logging.py:157 >> {'loss': 0.1520, 'learning_rate': 1.6165e-09, 'epoch': 2.97, 'throughput': 201.14}
+
+[INFO|2025-02-09 13:17:53] logging.py:157 >> {'loss': 0.0384, 'learning_rate': 1.6041e-09, 'epoch': 2.97, 'throughput': 201.14}
+
+[INFO|2025-02-09 13:18:04] logging.py:157 >> {'loss': 0.0211, 'learning_rate': 1.5917e-09, 'epoch': 2.97, 'throughput': 201.14}
+
+[INFO|2025-02-09 13:18:13] logging.py:157 >> {'loss': 0.0941, 'learning_rate': 1.5793e-09, 'epoch': 2.97, 'throughput': 201.14}
+
+[INFO|2025-02-09 13:18:22] logging.py:157 >> {'loss': 0.0004, 'learning_rate': 1.5670e-09, 'epoch': 2.97, 'throughput': 201.14}
+
+[INFO|2025-02-09 13:18:33] logging.py:157 >> {'loss': 0.2061, 'learning_rate': 1.5547e-09, 'epoch': 2.97, 'throughput': 201.15}
+
+[INFO|2025-02-09 13:18:42] logging.py:157 >> {'loss': 0.0001, 'learning_rate': 1.5425e-09, 'epoch': 2.97, 'throughput': 201.15}
+
+[INFO|2025-02-09 13:18:52] logging.py:157 >> {'loss': 0.0031, 'learning_rate': 1.5303e-09, 'epoch': 2.97, 'throughput': 201.15}
+
+[INFO|2025-02-09 13:19:02] logging.py:157 >> {'loss': 0.0101, 'learning_rate': 1.5182e-09, 'epoch': 2.97, 'throughput': 201.15}
+
+[INFO|2025-02-09 13:19:11] logging.py:157 >> {'loss': 0.0364, 'learning_rate': 1.5062e-09, 'epoch': 2.97, 'throughput': 201.15}
+
+[INFO|2025-02-09 13:19:20] logging.py:157 >> {'loss': 0.0001, 'learning_rate': 1.4941e-09, 'epoch': 2.97, 'throughput': 201.15}
+
+[INFO|2025-02-09 13:19:29] logging.py:157 >> {'loss': 0.0000, 'learning_rate': 1.4822e-09, 'epoch': 2.97, 'throughput': 201.16}
+
+[INFO|2025-02-09 13:19:39] logging.py:157 >> {'loss': 0.1423, 'learning_rate': 1.4702e-09, 'epoch': 2.97, 'throughput': 201.16}
+
+[INFO|2025-02-09 13:19:48] logging.py:157 >> {'loss': 0.0001, 'learning_rate': 1.4583e-09, 'epoch': 2.97, 'throughput': 201.15}
+
+[INFO|2025-02-09 13:19:57] logging.py:157 >> {'loss': 0.0361, 'learning_rate': 1.4465e-09, 'epoch': 2.97, 'throughput': 201.15}
+
+[INFO|2025-02-09 13:20:07] logging.py:157 >> {'loss': 0.0001, 'learning_rate': 1.4347e-09, 'epoch': 2.97, 'throughput': 201.15}
+
+[INFO|2025-02-09 13:20:15] logging.py:157 >> {'loss': 0.0008, 'learning_rate': 1.4230e-09, 'epoch': 2.97, 'throughput': 201.15}
+
+[INFO|2025-02-09 13:20:26] logging.py:157 >> {'loss': 0.0911, 'learning_rate': 1.4113e-09, 'epoch': 2.97, 'throughput': 201.15}
+
+[INFO|2025-02-09 13:20:36] logging.py:157 >> {'loss': 0.0997, 'learning_rate': 1.3997e-09, 'epoch': 2.97, 'throughput': 201.16}
+
+[INFO|2025-02-09 13:20:44] logging.py:157 >> {'loss': 0.0003, 'learning_rate': 1.3881e-09, 'epoch': 2.97, 'throughput': 201.16}
+
+[INFO|2025-02-09 13:20:54] logging.py:157 >> {'loss': 0.1293, 'learning_rate': 1.3765e-09, 'epoch': 2.97, 'throughput': 201.16}
+
+[INFO|2025-02-09 13:21:04] logging.py:157 >> {'loss': 0.0002, 'learning_rate': 1.3650e-09, 'epoch': 2.97, 'throughput': 201.16}
+
+[INFO|2025-02-09 13:21:13] logging.py:157 >> {'loss': 0.0000, 'learning_rate': 1.3536e-09, 'epoch': 2.97, 'throughput': 201.16}
+
+[INFO|2025-02-09 13:21:23] logging.py:157 >> {'loss': 0.0006, 'learning_rate': 1.3422e-09, 'epoch': 2.97, 'throughput': 201.16}
+
+[INFO|2025-02-09 13:21:32] logging.py:157 >> {'loss': 0.0022, 'learning_rate': 1.3309e-09, 'epoch': 2.97, 'throughput': 201.16}
+
+[INFO|2025-02-09 13:21:43] logging.py:157 >> {'loss': 0.1092, 'learning_rate': 1.3196e-09, 'epoch': 2.97, 'throughput': 201.16}
+
+[INFO|2025-02-09 13:21:53] logging.py:157 >> {'loss': 0.0722, 'learning_rate': 1.3083e-09, 'epoch': 2.97, 'throughput': 201.16}
+
+[INFO|2025-02-09 13:22:02] logging.py:157 >> {'loss': 0.0058, 'learning_rate': 1.2971e-09, 'epoch': 2.97, 'throughput': 201.16}
+
+[INFO|2025-02-09 13:22:12] logging.py:157 >> {'loss': 0.0001, 'learning_rate': 1.2859e-09, 'epoch': 2.97, 'throughput': 201.16}
+
+[INFO|2025-02-09 13:22:22] logging.py:157 >> {'loss': 0.0004, 'learning_rate': 1.2748e-09, 'epoch': 2.97, 'throughput': 201.16}
+
+[INFO|2025-02-09 13:22:31] logging.py:157 >> {'loss': 0.0159, 'learning_rate': 1.2638e-09, 'epoch': 2.97, 'throughput': 201.16}
+
+[INFO|2025-02-09 13:22:41] logging.py:157 >> {'loss': 0.0000, 'learning_rate': 1.2528e-09, 'epoch': 2.97, 'throughput': 201.16}
+
+[INFO|2025-02-09 13:22:51] logging.py:157 >> {'loss': 0.0019, 'learning_rate': 1.2418e-09, 'epoch': 2.97, 'throughput': 201.16}
+
+[INFO|2025-02-09 13:23:01] logging.py:157 >> {'loss': 0.0001, 'learning_rate': 1.2309e-09, 'epoch': 2.97, 'throughput': 201.16}
+
+[INFO|2025-02-09 13:23:11] logging.py:157 >> {'loss': 0.0000, 'learning_rate': 1.2200e-09, 'epoch': 2.97, 'throughput': 201.16}
+
+[INFO|2025-02-09 13:23:20] logging.py:157 >> {'loss': 0.0001, 'learning_rate': 1.2092e-09, 'epoch': 2.97, 'throughput': 201.16}
+
+[INFO|2025-02-09 13:23:29] logging.py:157 >> {'loss': 0.0892, 'learning_rate': 1.1984e-09, 'epoch': 2.97, 'throughput': 201.16}
+
+[INFO|2025-02-09 13:23:39] logging.py:157 >> {'loss': 0.0000, 'learning_rate': 1.1877e-09, 'epoch': 2.97, 'throughput': 201.16}
+
+[INFO|2025-02-09 13:23:49] logging.py:157 >> {'loss': 0.0021, 'learning_rate': 1.1770e-09, 'epoch': 2.97, 'throughput': 201.16}
+
+[INFO|2025-02-09 13:23:58] logging.py:157 >> {'loss': 0.0021, 'learning_rate': 1.1664e-09, 'epoch': 2.97, 'throughput': 201.16}
+
+[INFO|2025-02-09 13:24:08] logging.py:157 >> {'loss': 0.0255, 'learning_rate': 1.1558e-09, 'epoch': 2.97, 'throughput': 201.16}
+
+[INFO|2025-02-09 13:24:18] logging.py:157 >> {'loss': 0.0001, 'learning_rate': 1.1453e-09, 'epoch': 2.97, 'throughput': 201.16}
+
+[INFO|2025-02-09 13:24:28] logging.py:157 >> {'loss': 0.0001, 'learning_rate': 1.1348e-09, 'epoch': 2.97, 'throughput': 201.15}
+
+[INFO|2025-02-09 13:24:38] logging.py:157 >> {'loss': 0.0064, 'learning_rate': 1.1244e-09, 'epoch': 2.97, 'throughput': 201.16}
+
+[INFO|2025-02-09 13:24:49] logging.py:157 >> {'loss': 0.1398, 'learning_rate': 1.1140e-09, 'epoch': 2.97, 'throughput': 201.16}
+
+[INFO|2025-02-09 13:24:58] logging.py:157 >> {'loss': 0.0000, 'learning_rate': 1.1036e-09, 'epoch': 2.97, 'throughput': 201.16}
+
+[INFO|2025-02-09 13:25:08] logging.py:157 >> {'loss': 0.0001, 'learning_rate': 1.0934e-09, 'epoch': 2.97, 'throughput': 201.16}
+
+[INFO|2025-02-09 13:25:18] logging.py:157 >> {'loss': 0.0241, 'learning_rate': 1.0831e-09, 'epoch': 2.97, 'throughput': 201.16}
+
+[INFO|2025-02-09 13:25:28] logging.py:157 >> {'loss': 0.0001, 'learning_rate': 1.0729e-09, 'epoch': 2.97, 'throughput': 201.16}
+
+[INFO|2025-02-09 13:25:38] logging.py:157 >> {'loss': 0.1080, 'learning_rate': 1.0628e-09, 'epoch': 2.97, 'throughput': 201.17}
+
+[INFO|2025-02-09 13:25:49] logging.py:157 >> {'loss': 0.1110, 'learning_rate': 1.0527e-09, 'epoch': 2.97, 'throughput': 201.17}
+
+[INFO|2025-02-09 13:25:58] logging.py:157 >> {'loss': 0.0991, 'learning_rate': 1.0426e-09, 'epoch': 2.97, 'throughput': 201.17}
+
+[INFO|2025-02-09 13:26:09] logging.py:157 >> {'loss': 0.0647, 'learning_rate': 1.0326e-09, 'epoch': 2.97, 'throughput': 201.17}
+
+[INFO|2025-02-09 13:26:19] logging.py:157 >> {'loss': 0.1327, 'learning_rate': 1.0227e-09, 'epoch': 2.97, 'throughput': 201.17}
+
+[INFO|2025-02-09 13:26:28] logging.py:157 >> {'loss': 0.0001, 'learning_rate': 1.0128e-09, 'epoch': 2.97, 'throughput': 201.17}
+
+[INFO|2025-02-09 13:26:39] logging.py:157 >> {'loss': 0.0006, 'learning_rate': 1.0029e-09, 'epoch': 2.97, 'throughput': 201.17}
+
+[INFO|2025-02-09 13:26:48] logging.py:157 >> {'loss': 0.0431, 'learning_rate': 9.9311e-10, 'epoch': 2.97, 'throughput': 201.17}
+
+[INFO|2025-02-09 13:26:58] logging.py:157 >> {'loss': 0.2594, 'learning_rate': 9.8335e-10, 'epoch': 2.97, 'throughput': 201.17}
+
+[INFO|2025-02-09 13:27:07] logging.py:157 >> {'loss': 0.0051, 'learning_rate': 9.7364e-10, 'epoch': 2.97, 'throughput': 201.17}
+
+[INFO|2025-02-09 13:27:16] logging.py:157 >> {'loss': 0.0515, 'learning_rate': 9.6397e-10, 'epoch': 2.97, 'throughput': 201.17}
+
+[INFO|2025-02-09 13:27:26] logging.py:157 >> {'loss': 0.1407, 'learning_rate': 9.5436e-10, 'epoch': 2.97, 'throughput': 201.17}
+
+[INFO|2025-02-09 13:27:36] logging.py:157 >> {'loss': 0.1695, 'learning_rate': 9.4479e-10, 'epoch': 2.97, 'throughput': 201.18}
+
+[INFO|2025-02-09 13:27:45] logging.py:157 >> {'loss': 0.0046, 'learning_rate': 9.3527e-10, 'epoch': 2.97, 'throughput': 201.18}
+
+[INFO|2025-02-09 13:27:54] logging.py:157 >> {'loss': 0.0000, 'learning_rate': 9.2580e-10, 'epoch': 2.97, 'throughput': 201.18}
+
+[INFO|2025-02-09 13:28:03] logging.py:157 >> {'loss': 0.0596, 'learning_rate': 9.1638e-10, 'epoch': 2.97, 'throughput': 201.18}
+
+[INFO|2025-02-09 13:28:13] logging.py:157 >> {'loss': 0.0613, 'learning_rate': 9.0701e-10, 'epoch': 2.97, 'throughput': 201.18}
+
+[INFO|2025-02-09 13:28:22] logging.py:157 >> {'loss': 0.0003, 'learning_rate': 8.9768e-10, 'epoch': 2.97, 'throughput': 201.17}
+
+[INFO|2025-02-09 13:28:32] logging.py:157 >> {'loss': 0.1559, 'learning_rate': 8.8840e-10, 'epoch': 2.97, 'throughput': 201.18}
+
+[INFO|2025-02-09 13:28:42] logging.py:157 >> {'loss': 0.0074, 'learning_rate': 8.7917e-10, 'epoch': 2.97, 'throughput': 201.17}
+
+[INFO|2025-02-09 13:28:51] logging.py:157 >> {'loss': 0.0635, 'learning_rate': 8.6999e-10, 'epoch': 2.97, 'throughput': 201.17}
+
+[INFO|2025-02-09 13:29:01] logging.py:157 >> {'loss': 0.0020, 'learning_rate': 8.6086e-10, 'epoch': 2.97, 'throughput': 201.18}
+
+[INFO|2025-02-09 13:29:10] logging.py:157 >> {'loss': 0.2347, 'learning_rate': 8.5177e-10, 'epoch': 2.98, 'throughput': 201.18}
+
+[INFO|2025-02-09 13:29:19] logging.py:157 >> {'loss': 0.0000, 'learning_rate': 8.4274e-10, 'epoch': 2.98, 'throughput': 201.17}
+
+[INFO|2025-02-09 13:29:29] logging.py:157 >> {'loss': 0.0012, 'learning_rate': 8.3375e-10, 'epoch': 2.98, 'throughput': 201.17}
+
+[INFO|2025-02-09 13:29:37] logging.py:157 >> {'loss': 0.2888, 'learning_rate': 8.2481e-10, 'epoch': 2.98, 'throughput': 201.17}
+
+[INFO|2025-02-09 13:29:48] logging.py:157 >> {'loss': 0.0190, 'learning_rate': 8.1591e-10, 'epoch': 2.98, 'throughput': 201.17}
+
+[INFO|2025-02-09 13:29:57] logging.py:157 >> {'loss': 0.0001, 'learning_rate': 8.0707e-10, 'epoch': 2.98, 'throughput': 201.17}
+
+[INFO|2025-02-09 13:30:06] logging.py:157 >> {'loss': 0.0436, 'learning_rate': 7.9827e-10, 'epoch': 2.98, 'throughput': 201.17}
+
+[INFO|2025-02-09 13:30:17] logging.py:157 >> {'loss': 0.0334, 'learning_rate': 7.8953e-10, 'epoch': 2.98, 'throughput': 201.17}
+
+[INFO|2025-02-09 13:30:26] logging.py:157 >> {'loss': 0.0158, 'learning_rate': 7.8083e-10, 'epoch': 2.98, 'throughput': 201.17}
+
+[INFO|2025-02-09 13:30:36] logging.py:157 >> {'loss': 0.0003, 'learning_rate': 7.7218e-10, 'epoch': 2.98, 'throughput': 201.18}
+
+[INFO|2025-02-09 13:30:45] logging.py:157 >> {'loss': 0.0000, 'learning_rate': 7.6357e-10, 'epoch': 2.98, 'throughput': 201.17}
+
+[INFO|2025-02-09 13:30:54] logging.py:157 >> {'loss': 0.0001, 'learning_rate': 7.5502e-10, 'epoch': 2.98, 'throughput': 201.17}
+
+[INFO|2025-02-09 13:31:04] logging.py:157 >> {'loss': 0.0429, 'learning_rate': 7.4651e-10, 'epoch': 2.98, 'throughput': 201.18}
+
+[INFO|2025-02-09 13:31:13] logging.py:157 >> {'loss': 0.0062, 'learning_rate': 7.3805e-10, 'epoch': 2.98, 'throughput': 201.18}
+
+[INFO|2025-02-09 13:31:22] logging.py:157 >> {'loss': 0.1086, 'learning_rate': 7.2964e-10, 'epoch': 2.98, 'throughput': 201.18}
+
+[INFO|2025-02-09 13:31:32] logging.py:157 >> {'loss': 0.0002, 'learning_rate': 7.2128e-10, 'epoch': 2.98, 'throughput': 201.18}
+
+[INFO|2025-02-09 13:31:41] logging.py:157 >> {'loss': 0.0018, 'learning_rate': 7.1297e-10, 'epoch': 2.98, 'throughput': 201.18}
+
+[INFO|2025-02-09 13:31:52] logging.py:157 >> {'loss': 0.0773, 'learning_rate': 7.0470e-10, 'epoch': 2.98, 'throughput': 201.19}
+
+[INFO|2025-02-09 13:32:02] logging.py:157 >> {'loss': 0.0002, 'learning_rate': 6.9648e-10, 'epoch': 2.98, 'throughput': 201.19}
+
+[INFO|2025-02-09 13:32:10] logging.py:157 >> {'loss': 0.0013, 'learning_rate': 6.8831e-10, 'epoch': 2.98, 'throughput': 201.19}
+
+[INFO|2025-02-09 13:32:21] logging.py:157 >> {'loss': 0.0000, 'learning_rate': 6.8019e-10, 'epoch': 2.98, 'throughput': 201.19}
+
+[INFO|2025-02-09 13:32:30] logging.py:157 >> {'loss': 0.0000, 'learning_rate': 6.7212e-10, 'epoch': 2.98, 'throughput': 201.19}
+
+[INFO|2025-02-09 13:32:39] logging.py:157 >> {'loss': 0.2480, 'learning_rate': 6.6409e-10, 'epoch': 2.98, 'throughput': 201.19}
+
+[INFO|2025-02-09 13:32:49] logging.py:157 >> {'loss': 0.0000, 'learning_rate': 6.5612e-10, 'epoch': 2.98, 'throughput': 201.18}
+
+[INFO|2025-02-09 13:32:58] logging.py:157 >> {'loss': 0.0003, 'learning_rate': 6.4819e-10, 'epoch': 2.98, 'throughput': 201.19}
+
+[INFO|2025-02-09 13:33:08] logging.py:157 >> {'loss': 0.0262, 'learning_rate': 6.4031e-10, 'epoch': 2.98, 'throughput': 201.18}
+
+[INFO|2025-02-09 13:33:18] logging.py:157 >> {'loss': 0.0834, 'learning_rate': 6.3248e-10, 'epoch': 2.98, 'throughput': 201.18}
+
+[INFO|2025-02-09 13:33:27] logging.py:157 >> {'loss': 0.0000, 'learning_rate': 6.2469e-10, 'epoch': 2.98, 'throughput': 201.18}
+
+[INFO|2025-02-09 13:33:37] logging.py:157 >> {'loss': 0.0005, 'learning_rate': 6.1696e-10, 'epoch': 2.98, 'throughput': 201.18}
+
+[INFO|2025-02-09 13:33:47] logging.py:157 >> {'loss': 0.0006, 'learning_rate': 6.0927e-10, 'epoch': 2.98, 'throughput': 201.18}
+
+[INFO|2025-02-09 13:33:57] logging.py:157 >> {'loss': 0.0004, 'learning_rate': 6.0163e-10, 'epoch': 2.98, 'throughput': 201.18}
+
+[INFO|2025-02-09 13:34:07] logging.py:157 >> {'loss': 0.0040, 'learning_rate': 5.9404e-10, 'epoch': 2.98, 'throughput': 201.18}
+
+[INFO|2025-02-09 13:34:16] logging.py:157 >> {'loss': 0.0158, 'learning_rate': 5.8650e-10, 'epoch': 2.98, 'throughput': 201.18}
+
+[INFO|2025-02-09 13:34:27] logging.py:157 >> {'loss': 0.0358, 'learning_rate': 5.7900e-10, 'epoch': 2.98, 'throughput': 201.18}
+
+[INFO|2025-02-09 13:34:37] logging.py:157 >> {'loss': 0.0005, 'learning_rate': 5.7155e-10, 'epoch': 2.98, 'throughput': 201.18}
+
+[INFO|2025-02-09 13:34:46] logging.py:157 >> {'loss': 0.0778, 'learning_rate': 5.6416e-10, 'epoch': 2.98, 'throughput': 201.18}
+
+[INFO|2025-02-09 13:34:55] logging.py:157 >> {'loss': 0.0000, 'learning_rate': 5.5681e-10, 'epoch': 2.98, 'throughput': 201.18}
+
+[INFO|2025-02-09 13:35:05] logging.py:157 >> {'loss': 0.0007, 'learning_rate': 5.4950e-10, 'epoch': 2.98, 'throughput': 201.18}
+
+[INFO|2025-02-09 13:35:15] logging.py:157 >> {'loss': 0.0062, 'learning_rate': 5.4225e-10, 'epoch': 2.98, 'throughput': 201.18}
+
+[INFO|2025-02-09 13:35:24] logging.py:157 >> {'loss': 0.0001, 'learning_rate': 5.3504e-10, 'epoch': 2.98, 'throughput': 201.18}
+
+[INFO|2025-02-09 13:35:33] logging.py:157 >> {'loss': 0.0000, 'learning_rate': 5.2789e-10, 'epoch': 2.98, 'throughput': 201.18}
+
+[INFO|2025-02-09 13:35:44] logging.py:157 >> {'loss': 0.0019, 'learning_rate': 5.2078e-10, 'epoch': 2.98, 'throughput': 201.18}
+
+[INFO|2025-02-09 13:35:54] logging.py:157 >> {'loss': 0.3176, 'learning_rate': 5.1372e-10, 'epoch': 2.98, 'throughput': 201.18}
+
+[INFO|2025-02-09 13:36:04] logging.py:157 >> {'loss': 0.0064, 'learning_rate': 5.0670e-10, 'epoch': 2.98, 'throughput': 201.18}
+
+[INFO|2025-02-09 13:36:14] logging.py:157 >> {'loss': 0.0015, 'learning_rate': 4.9974e-10, 'epoch': 2.98, 'throughput': 201.18}
+
+[INFO|2025-02-09 13:36:24] logging.py:157 >> {'loss': 0.0001, 'learning_rate': 4.9282e-10, 'epoch': 2.98, 'throughput': 201.17}
+
+[INFO|2025-02-09 13:36:34] logging.py:157 >> {'loss': 0.0228, 'learning_rate': 4.8595e-10, 'epoch': 2.98, 'throughput': 201.18}
+
+[INFO|2025-02-09 13:36:44] logging.py:157 >> {'loss': 0.0003, 'learning_rate': 4.7913e-10, 'epoch': 2.98, 'throughput': 201.18}
+
+[INFO|2025-02-09 13:36:54] logging.py:157 >> {'loss': 0.0001, 'learning_rate': 4.7236e-10, 'epoch': 2.98, 'throughput': 201.18}
+
+[INFO|2025-02-09 13:37:05] logging.py:157 >> {'loss': 0.1020, 'learning_rate': 4.6564e-10, 'epoch': 2.98, 'throughput': 201.18}
+
+[INFO|2025-02-09 13:37:14] logging.py:157 >> {'loss': 0.0000, 'learning_rate': 4.5896e-10, 'epoch': 2.98, 'throughput': 201.17}
+
+[INFO|2025-02-09 13:37:24] logging.py:157 >> {'loss': 0.0207, 'learning_rate': 4.5234e-10, 'epoch': 2.98, 'throughput': 201.17}
+
+[INFO|2025-02-09 13:37:35] logging.py:157 >> {'loss': 0.0189, 'learning_rate': 4.4576e-10, 'epoch': 2.98, 'throughput': 201.17}
+
+[INFO|2025-02-09 13:37:44] logging.py:157 >> {'loss': 0.0000, 'learning_rate': 4.3923e-10, 'epoch': 2.98, 'throughput': 201.17}
+
+[INFO|2025-02-09 13:37:54] logging.py:157 >> {'loss': 0.0003, 'learning_rate': 4.3274e-10, 'epoch': 2.98, 'throughput': 201.17}
+
+[INFO|2025-02-09 13:38:04] logging.py:157 >> {'loss': 0.0209, 'learning_rate': 4.2631e-10, 'epoch': 2.98, 'throughput': 201.17}
+
+[INFO|2025-02-09 13:38:13] logging.py:157 >> {'loss': 0.0001, 'learning_rate': 4.1992e-10, 'epoch': 2.98, 'throughput': 201.17}
+
+[INFO|2025-02-09 13:38:23] logging.py:157 >> {'loss': 0.0084, 'learning_rate': 4.1358e-10, 'epoch': 2.98, 'throughput': 201.17}
+
+[INFO|2025-02-09 13:38:32] logging.py:157 >> {'loss': 0.0361, 'learning_rate': 4.0729e-10, 'epoch': 2.98, 'throughput': 201.17}
+
+[INFO|2025-02-09 13:38:42] logging.py:157 >> {'loss': 0.0002, 'learning_rate': 4.0105e-10, 'epoch': 2.98, 'throughput': 201.16}
+
+[INFO|2025-02-09 13:38:52] logging.py:157 >> {'loss': 0.0600, 'learning_rate': 3.9486e-10, 'epoch': 2.98, 'throughput': 201.16}
+
+[INFO|2025-02-09 13:39:01] logging.py:157 >> {'loss': 0.0085, 'learning_rate': 3.8871e-10, 'epoch': 2.98, 'throughput': 201.16}
+
+[INFO|2025-02-09 13:39:10] logging.py:157 >> {'loss': 0.0001, 'learning_rate': 3.8262e-10, 'epoch': 2.98, 'throughput': 201.16}
+
+[INFO|2025-02-09 13:39:20] logging.py:157 >> {'loss': 0.0249, 'learning_rate': 3.7657e-10, 'epoch': 2.98, 'throughput': 201.16}
+
+[INFO|2025-02-09 13:39:29] logging.py:157 >> {'loss': 0.0412, 'learning_rate': 3.7057e-10, 'epoch': 2.98, 'throughput': 201.17}
+
+[INFO|2025-02-09 13:39:40] logging.py:157 >> {'loss': 0.0919, 'learning_rate': 3.6461e-10, 'epoch': 2.98, 'throughput': 201.17}
+
+[INFO|2025-02-09 13:39:50] logging.py:157 >> {'loss': 0.1375, 'learning_rate': 3.5871e-10, 'epoch': 2.98, 'throughput': 201.17}
+
+[INFO|2025-02-09 13:39:59] logging.py:157 >> {'loss': 0.2204, 'learning_rate': 3.5285e-10, 'epoch': 2.98, 'throughput': 201.17}
+
+[INFO|2025-02-09 13:40:09] logging.py:157 >> {'loss': 0.0002, 'learning_rate': 3.4704e-10, 'epoch': 2.98, 'throughput': 201.17}
+
+[INFO|2025-02-09 13:40:19] logging.py:157 >> {'loss': 0.0713, 'learning_rate': 3.4128e-10, 'epoch': 2.98, 'throughput': 201.17}
+
+[INFO|2025-02-09 13:40:28] logging.py:157 >> {'loss': 0.0082, 'learning_rate': 3.3557e-10, 'epoch': 2.98, 'throughput': 201.17}
+
+[INFO|2025-02-09 13:40:38] logging.py:157 >> {'loss': 0.0015, 'learning_rate': 3.2991e-10, 'epoch': 2.98, 'throughput': 201.17}
+
+[INFO|2025-02-09 13:40:47] logging.py:157 >> {'loss': 0.0451, 'learning_rate': 3.2429e-10, 'epoch': 2.98, 'throughput': 201.17}
+
+[INFO|2025-02-09 13:40:57] logging.py:157 >> {'loss': 0.2993, 'learning_rate': 3.1873e-10, 'epoch': 2.98, 'throughput': 201.17}
+
+[INFO|2025-02-09 13:41:07] logging.py:157 >> {'loss': 0.0263, 'learning_rate': 3.1321e-10, 'epoch': 2.98, 'throughput': 201.17}
+
+[INFO|2025-02-09 13:41:16] logging.py:157 >> {'loss': 0.0732, 'learning_rate': 3.0774e-10, 'epoch': 2.99, 'throughput': 201.17}
+
+[INFO|2025-02-09 13:41:27] logging.py:157 >> {'loss': 0.0123, 'learning_rate': 3.0232e-10, 'epoch': 2.99, 'throughput': 201.17}
+
+[INFO|2025-02-09 13:41:35] logging.py:157 >> {'loss': 0.0527, 'learning_rate': 2.9694e-10, 'epoch': 2.99, 'throughput': 201.17}
+
+[INFO|2025-02-09 13:41:45] logging.py:157 >> {'loss': 0.0001, 'learning_rate': 2.9161e-10, 'epoch': 2.99, 'throughput': 201.17}
+
+[INFO|2025-02-09 13:41:54] logging.py:157 >> {'loss': 0.0000, 'learning_rate': 2.8634e-10, 'epoch': 2.99, 'throughput': 201.17}
+
+[INFO|2025-02-09 13:42:02] logging.py:157 >> {'loss': 0.0321, 'learning_rate': 2.8111e-10, 'epoch': 2.99, 'throughput': 201.17}
+
+[INFO|2025-02-09 13:42:11] logging.py:157 >> {'loss': 0.1726, 'learning_rate': 2.7593e-10, 'epoch': 2.99, 'throughput': 201.17}
+
+[INFO|2025-02-09 13:42:21] logging.py:157 >> {'loss': 0.0026, 'learning_rate': 2.7079e-10, 'epoch': 2.99, 'throughput': 201.17}
+
+[INFO|2025-02-09 13:42:31] logging.py:157 >> {'loss': 0.0018, 'learning_rate': 2.6571e-10, 'epoch': 2.99, 'throughput': 201.17}
+
+[INFO|2025-02-09 13:42:39] logging.py:157 >> {'loss': 0.1835, 'learning_rate': 2.6067e-10, 'epoch': 2.99, 'throughput': 201.17}
+
+[INFO|2025-02-09 13:42:49] logging.py:157 >> {'loss': 0.0000, 'learning_rate': 2.5568e-10, 'epoch': 2.99, 'throughput': 201.17}
+
+[INFO|2025-02-09 13:42:59] logging.py:157 >> {'loss': 0.2299, 'learning_rate': 2.5074e-10, 'epoch': 2.99, 'throughput': 201.17}
+
+[INFO|2025-02-09 13:43:07] logging.py:157 >> {'loss': 0.0087, 'learning_rate': 2.4585e-10, 'epoch': 2.99, 'throughput': 201.17}
+
+[INFO|2025-02-09 13:43:17] logging.py:157 >> {'loss': 0.0028, 'learning_rate': 2.4100e-10, 'epoch': 2.99, 'throughput': 201.17}
+
+[INFO|2025-02-09 13:43:26] logging.py:157 >> {'loss': 0.0003, 'learning_rate': 2.3621e-10, 'epoch': 2.99, 'throughput': 201.17}
+
+[INFO|2025-02-09 13:43:36] logging.py:157 >> {'loss': 0.0072, 'learning_rate': 2.3146e-10, 'epoch': 2.99, 'throughput': 201.17}
+
+[INFO|2025-02-09 13:43:45] logging.py:157 >> {'loss': 0.0001, 'learning_rate': 2.2676e-10, 'epoch': 2.99, 'throughput': 201.17}
+
+[INFO|2025-02-09 13:43:54] logging.py:157 >> {'loss': 0.0001, 'learning_rate': 2.2211e-10, 'epoch': 2.99, 'throughput': 201.17}
+
+[INFO|2025-02-09 13:44:04] logging.py:157 >> {'loss': 0.0000, 'learning_rate': 2.1751e-10, 'epoch': 2.99, 'throughput': 201.17}
+
+[INFO|2025-02-09 13:44:13] logging.py:157 >> {'loss': 0.0159, 'learning_rate': 2.1295e-10, 'epoch': 2.99, 'throughput': 201.17}
+
+[INFO|2025-02-09 13:44:23] logging.py:157 >> {'loss': 0.0038, 'learning_rate': 2.0845e-10, 'epoch': 2.99, 'throughput': 201.17}
+
+[INFO|2025-02-09 13:44:33] logging.py:157 >> {'loss': 0.0016, 'learning_rate': 2.0399e-10, 'epoch': 2.99, 'throughput': 201.17}
+
+[INFO|2025-02-09 13:44:42] logging.py:157 >> {'loss': 0.0290, 'learning_rate': 1.9958e-10, 'epoch': 2.99, 'throughput': 201.18}
+
+[INFO|2025-02-09 13:44:53] logging.py:157 >> {'loss': 0.1973, 'learning_rate': 1.9521e-10, 'epoch': 2.99, 'throughput': 201.18}
+
+[INFO|2025-02-09 13:45:02] logging.py:157 >> {'loss': 0.0165, 'learning_rate': 1.9090e-10, 'epoch': 2.99, 'throughput': 201.18}
+
+[INFO|2025-02-09 13:45:12] logging.py:157 >> {'loss': 0.0885, 'learning_rate': 1.8663e-10, 'epoch': 2.99, 'throughput': 201.18}
+
+[INFO|2025-02-09 13:45:21] logging.py:157 >> {'loss': 0.0012, 'learning_rate': 1.8242e-10, 'epoch': 2.99, 'throughput': 201.18}
+
+[INFO|2025-02-09 13:45:31] logging.py:157 >> {'loss': 0.1119, 'learning_rate': 1.7825e-10, 'epoch': 2.99, 'throughput': 201.18}
+
+[INFO|2025-02-09 13:45:41] logging.py:157 >> {'loss': 0.0001, 'learning_rate': 1.7413e-10, 'epoch': 2.99, 'throughput': 201.18}
+
+[INFO|2025-02-09 13:45:51] logging.py:157 >> {'loss': 0.0004, 'learning_rate': 1.7005e-10, 'epoch': 2.99, 'throughput': 201.18}
+
+[INFO|2025-02-09 13:46:00] logging.py:157 >> {'loss': 0.0027, 'learning_rate': 1.6603e-10, 'epoch': 2.99, 'throughput': 201.18}
+
+[INFO|2025-02-09 13:46:11] logging.py:157 >> {'loss': 0.0138, 'learning_rate': 1.6205e-10, 'epoch': 2.99, 'throughput': 201.18}
+
+[INFO|2025-02-09 13:46:20] logging.py:157 >> {'loss': 0.1212, 'learning_rate': 1.5812e-10, 'epoch': 2.99, 'throughput': 201.17}
+
+[INFO|2025-02-09 13:46:30] logging.py:157 >> {'loss': 0.0301, 'learning_rate': 1.5424e-10, 'epoch': 2.99, 'throughput': 201.17}
+
+[INFO|2025-02-09 13:46:40] logging.py:157 >> {'loss': 0.0013, 'learning_rate': 1.5041e-10, 'epoch': 2.99, 'throughput': 201.17}
+
+[INFO|2025-02-09 13:46:49] logging.py:157 >> {'loss': 0.0217, 'learning_rate': 1.4663e-10, 'epoch': 2.99, 'throughput': 201.17}
+
+[INFO|2025-02-09 13:46:59] logging.py:157 >> {'loss': 0.0000, 'learning_rate': 1.4289e-10, 'epoch': 2.99, 'throughput': 201.17}
+
+[INFO|2025-02-09 13:47:09] logging.py:157 >> {'loss': 0.0118, 'learning_rate': 1.3921e-10, 'epoch': 2.99, 'throughput': 201.17}
+
+[INFO|2025-02-09 13:47:18] logging.py:157 >> {'loss': 0.0456, 'learning_rate': 1.3557e-10, 'epoch': 2.99, 'throughput': 201.17}
+
+[INFO|2025-02-09 13:47:28] logging.py:157 >> {'loss': 0.0196, 'learning_rate': 1.3198e-10, 'epoch': 2.99, 'throughput': 201.17}
+
+[INFO|2025-02-09 13:47:38] logging.py:157 >> {'loss': 0.2508, 'learning_rate': 1.2843e-10, 'epoch': 2.99, 'throughput': 201.17}
+
+[INFO|2025-02-09 13:47:48] logging.py:157 >> {'loss': 0.0005, 'learning_rate': 1.2494e-10, 'epoch': 2.99, 'throughput': 201.17}
+
+[INFO|2025-02-09 13:47:58] logging.py:157 >> {'loss': 0.0001, 'learning_rate': 1.2149e-10, 'epoch': 2.99, 'throughput': 201.17}
+
+[INFO|2025-02-09 13:48:08] logging.py:157 >> {'loss': 0.0000, 'learning_rate': 1.1809e-10, 'epoch': 2.99, 'throughput': 201.17}
+
+[INFO|2025-02-09 13:48:18] logging.py:157 >> {'loss': 0.0001, 'learning_rate': 1.1474e-10, 'epoch': 2.99, 'throughput': 201.17}
+
+[INFO|2025-02-09 13:48:28] logging.py:157 >> {'loss': 0.0052, 'learning_rate': 1.1144e-10, 'epoch': 2.99, 'throughput': 201.17}
+
+[INFO|2025-02-09 13:48:37] logging.py:157 >> {'loss': 0.0010, 'learning_rate': 1.0819e-10, 'epoch': 2.99, 'throughput': 201.17}
+
+[INFO|2025-02-09 13:48:48] logging.py:157 >> {'loss': 0.0001, 'learning_rate': 1.0498e-10, 'epoch': 2.99, 'throughput': 201.17}
+
+[INFO|2025-02-09 13:48:57] logging.py:157 >> {'loss': 0.0000, 'learning_rate': 1.0183e-10, 'epoch': 2.99, 'throughput': 201.17}
+
+[INFO|2025-02-09 13:49:07] logging.py:157 >> {'loss': 0.0086, 'learning_rate': 9.8716e-11, 'epoch': 2.99, 'throughput': 201.17}
+
+[INFO|2025-02-09 13:49:17] logging.py:157 >> {'loss': 0.0000, 'learning_rate': 9.5656e-11, 'epoch': 2.99, 'throughput': 201.17}
+
+[INFO|2025-02-09 13:49:26] logging.py:157 >> {'loss': 0.0005, 'learning_rate': 9.2643e-11, 'epoch': 2.99, 'throughput': 201.17}
+
+[INFO|2025-02-09 13:49:37] logging.py:157 >> {'loss': 0.0492, 'learning_rate': 8.9679e-11, 'epoch': 2.99, 'throughput': 201.17}
+
+[INFO|2025-02-09 13:49:46] logging.py:157 >> {'loss': 0.0009, 'learning_rate': 8.6763e-11, 'epoch': 2.99, 'throughput': 201.18}
+
+[INFO|2025-02-09 13:49:56] logging.py:157 >> {'loss': 0.0000, 'learning_rate': 8.3895e-11, 'epoch': 2.99, 'throughput': 201.17}
+
+[INFO|2025-02-09 13:50:06] logging.py:157 >> {'loss': 0.0002, 'learning_rate': 8.1075e-11, 'epoch': 2.99, 'throughput': 201.17}
+
+[INFO|2025-02-09 13:50:15] logging.py:157 >> {'loss': 0.0002, 'learning_rate': 7.8303e-11, 'epoch': 2.99, 'throughput': 201.17}
+
+[INFO|2025-02-09 13:50:24] logging.py:157 >> {'loss': 0.0005, 'learning_rate': 7.5580e-11, 'epoch': 2.99, 'throughput': 201.17}
+
+[INFO|2025-02-09 13:50:33] logging.py:157 >> {'loss': 0.0376, 'learning_rate': 7.2905e-11, 'epoch': 2.99, 'throughput': 201.17}
+
+[INFO|2025-02-09 13:50:42] logging.py:157 >> {'loss': 0.0000, 'learning_rate': 7.0278e-11, 'epoch': 2.99, 'throughput': 201.17}
+
+[INFO|2025-02-09 13:50:52] logging.py:157 >> {'loss': 0.0003, 'learning_rate': 6.7699e-11, 'epoch': 2.99, 'throughput': 201.17}
+
+[INFO|2025-02-09 13:51:01] logging.py:157 >> {'loss': 0.0337, 'learning_rate': 6.5168e-11, 'epoch': 2.99, 'throughput': 201.17}
+
+[INFO|2025-02-09 13:51:11] logging.py:157 >> {'loss': 0.0174, 'learning_rate': 6.2686e-11, 'epoch': 2.99, 'throughput': 201.16}
+
+[INFO|2025-02-09 13:51:21] logging.py:157 >> {'loss': 0.0402, 'learning_rate': 6.0252e-11, 'epoch': 2.99, 'throughput': 201.17}
+
+[INFO|2025-02-09 13:51:30] logging.py:157 >> {'loss': 0.0000, 'learning_rate': 5.7866e-11, 'epoch': 2.99, 'throughput': 201.17}
+
+[INFO|2025-02-09 13:51:39] logging.py:157 >> {'loss': 0.0903, 'learning_rate': 5.5528e-11, 'epoch': 2.99, 'throughput': 201.16}
+
+[INFO|2025-02-09 13:51:48] logging.py:157 >> {'loss': 0.0011, 'learning_rate': 5.3239e-11, 'epoch': 2.99, 'throughput': 201.16}
+
+[INFO|2025-02-09 13:51:59] logging.py:157 >> {'loss': 0.0902, 'learning_rate': 5.0997e-11, 'epoch': 2.99, 'throughput': 201.16}
+
+[INFO|2025-02-09 13:52:07] logging.py:157 >> {'loss': 0.0000, 'learning_rate': 4.8804e-11, 'epoch': 2.99, 'throughput': 201.16}
+
+[INFO|2025-02-09 13:52:17] logging.py:157 >> {'loss': 0.0000, 'learning_rate': 4.6659e-11, 'epoch': 2.99, 'throughput': 201.16}
+
+[INFO|2025-02-09 13:52:27] logging.py:157 >> {'loss': 0.1789, 'learning_rate': 4.4562e-11, 'epoch': 2.99, 'throughput': 201.16}
+
+[INFO|2025-02-09 13:52:35] logging.py:157 >> {'loss': 0.0072, 'learning_rate': 4.2514e-11, 'epoch': 2.99, 'throughput': 201.16}
+
+[INFO|2025-02-09 13:52:45] logging.py:157 >> {'loss': 0.0887, 'learning_rate': 4.0513e-11, 'epoch': 2.99, 'throughput': 201.16}
+
+[INFO|2025-02-09 13:52:54] logging.py:157 >> {'loss': 0.0000, 'learning_rate': 3.8561e-11, 'epoch': 2.99, 'throughput': 201.16}
+
+[INFO|2025-02-09 13:53:04] logging.py:157 >> {'loss': 0.0030, 'learning_rate': 3.6657e-11, 'epoch': 2.99, 'throughput': 201.16}
+
+[INFO|2025-02-09 13:53:14] logging.py:157 >> {'loss': 0.0001, 'learning_rate': 3.4802e-11, 'epoch': 2.99, 'throughput': 201.15}
+
+[INFO|2025-02-09 13:53:23] logging.py:157 >> {'loss': 0.0901, 'learning_rate': 3.2994e-11, 'epoch': 3.00, 'throughput': 201.16}
+
+[INFO|2025-02-09 13:53:34] logging.py:157 >> {'loss': 0.0525, 'learning_rate': 3.1235e-11, 'epoch': 3.00, 'throughput': 201.16}
+
+[INFO|2025-02-09 13:53:44] logging.py:157 >> {'loss': 0.0296, 'learning_rate': 2.9523e-11, 'epoch': 3.00, 'throughput': 201.16}
+
+[INFO|2025-02-09 13:53:54] logging.py:157 >> {'loss': 0.0000, 'learning_rate': 2.7861e-11, 'epoch': 3.00, 'throughput': 201.16}
+
+[INFO|2025-02-09 13:54:04] logging.py:157 >> {'loss': 0.1933, 'learning_rate': 2.6246e-11, 'epoch': 3.00, 'throughput': 201.16}
+
+[INFO|2025-02-09 13:54:14] logging.py:157 >> {'loss': 0.0000, 'learning_rate': 2.4679e-11, 'epoch': 3.00, 'throughput': 201.16}
+
+[INFO|2025-02-09 13:54:24] logging.py:157 >> {'loss': 0.0009, 'learning_rate': 2.3161e-11, 'epoch': 3.00, 'throughput': 201.16}
+
+[INFO|2025-02-09 13:54:34] logging.py:157 >> {'loss': 0.0103, 'learning_rate': 2.1691e-11, 'epoch': 3.00, 'throughput': 201.15}
+
+[INFO|2025-02-09 13:54:43] logging.py:157 >> {'loss': 0.0001, 'learning_rate': 2.0269e-11, 'epoch': 3.00, 'throughput': 201.15}
+
+[INFO|2025-02-09 13:54:54] logging.py:157 >> {'loss': 0.2132, 'learning_rate': 1.8895e-11, 'epoch': 3.00, 'throughput': 201.15}
+
+[INFO|2025-02-09 13:55:04] logging.py:157 >> {'loss': 0.0072, 'learning_rate': 1.7570e-11, 'epoch': 3.00, 'throughput': 201.16}
+
+[INFO|2025-02-09 13:55:15] logging.py:157 >> {'loss': 0.0885, 'learning_rate': 1.6292e-11, 'epoch': 3.00, 'throughput': 201.16}
+
+[INFO|2025-02-09 13:55:25] logging.py:157 >> {'loss': 0.0000, 'learning_rate': 1.5063e-11, 'epoch': 3.00, 'throughput': 201.16}
+
+[INFO|2025-02-09 13:55:35] logging.py:157 >> {'loss': 0.0449, 'learning_rate': 1.3882e-11, 'epoch': 3.00, 'throughput': 201.16}
+
+[INFO|2025-02-09 13:55:45] logging.py:157 >> {'loss': 0.0851, 'learning_rate': 1.2749e-11, 'epoch': 3.00, 'throughput': 201.16}
+
+[INFO|2025-02-09 13:55:55] logging.py:157 >> {'loss': 0.0001, 'learning_rate': 1.1665e-11, 'epoch': 3.00, 'throughput': 201.16}
+
+[INFO|2025-02-09 13:56:05] logging.py:157 >> {'loss': 0.0001, 'learning_rate': 1.0628e-11, 'epoch': 3.00, 'throughput': 201.16}
+
+[INFO|2025-02-09 13:56:15] logging.py:157 >> {'loss': 0.0000, 'learning_rate': 9.6403e-12, 'epoch': 3.00, 'throughput': 201.15}
+
+[INFO|2025-02-09 13:56:25] logging.py:157 >> {'loss': 0.0014, 'learning_rate': 8.7004e-12, 'epoch': 3.00, 'throughput': 201.15}
+
+[INFO|2025-02-09 13:56:35] logging.py:157 >> {'loss': 0.0045, 'learning_rate': 7.8087e-12, 'epoch': 3.00, 'throughput': 201.15}
+
+[INFO|2025-02-09 13:56:45] logging.py:157 >> {'loss': 0.0670, 'learning_rate': 6.9651e-12, 'epoch': 3.00, 'throughput': 201.16}
+
+[INFO|2025-02-09 13:56:56] logging.py:157 >> {'loss': 0.2274, 'learning_rate': 6.1698e-12, 'epoch': 3.00, 'throughput': 201.16}
+
+[INFO|2025-02-09 13:57:05] logging.py:157 >> {'loss': 0.0000, 'learning_rate': 5.4227e-12, 'epoch': 3.00, 'throughput': 201.16}
+
+[INFO|2025-02-09 13:57:15] logging.py:157 >> {'loss': 0.2020, 'learning_rate': 4.7238e-12, 'epoch': 3.00, 'throughput': 201.16}
+
+[INFO|2025-02-09 13:57:24] logging.py:157 >> {'loss': 0.0000, 'learning_rate': 4.0730e-12, 'epoch': 3.00, 'throughput': 201.15}
+
+[INFO|2025-02-09 13:57:34] logging.py:157 >> {'loss': 0.0001, 'learning_rate': 3.4705e-12, 'epoch': 3.00, 'throughput': 201.15}
+
+[INFO|2025-02-09 13:57:44] logging.py:157 >> {'loss': 0.0003, 'learning_rate': 2.9162e-12, 'epoch': 3.00, 'throughput': 201.15}
+
+[INFO|2025-02-09 13:57:54] logging.py:157 >> {'loss': 0.0000, 'learning_rate': 2.4101e-12, 'epoch': 3.00, 'throughput': 201.15}
+
+[INFO|2025-02-09 13:58:03] logging.py:157 >> {'loss': 0.0002, 'learning_rate': 1.9522e-12, 'epoch': 3.00, 'throughput': 201.15}
+
+[INFO|2025-02-09 13:58:14] logging.py:157 >> {'loss': 0.0007, 'learning_rate': 1.5425e-12, 'epoch': 3.00, 'throughput': 201.16}
+
+[INFO|2025-02-09 13:58:23] logging.py:157 >> {'loss': 0.0105, 'learning_rate': 1.1809e-12, 'epoch': 3.00, 'throughput': 201.16}
+
+[INFO|2025-02-09 13:58:33] logging.py:157 >> {'loss': 0.0000, 'learning_rate': 8.6763e-13, 'epoch': 3.00, 'throughput': 201.16}
+
+[INFO|2025-02-09 13:58:43] logging.py:157 >> {'loss': 0.1049, 'learning_rate': 6.0252e-13, 'epoch': 3.00, 'throughput': 201.15}
+
+[INFO|2025-02-09 13:58:52] logging.py:157 >> {'loss': 0.0017, 'learning_rate': 3.8561e-13, 'epoch': 3.00, 'throughput': 201.16}
+
+[INFO|2025-02-09 13:59:01] logging.py:157 >> {'loss': 0.0622, 'learning_rate': 2.1691e-13, 'epoch': 3.00, 'throughput': 201.16}
+
+[INFO|2025-02-09 13:59:11] logging.py:157 >> {'loss': 0.0457, 'learning_rate': 9.6403e-14, 'epoch': 3.00, 'throughput': 201.15}
+
+[INFO|2025-02-09 13:59:19] logging.py:157 >> {'loss': 0.0001, 'learning_rate': 2.4101e-14, 'epoch': 3.00, 'throughput': 201.16}
+
+[INFO|2025-02-09 13:59:30] logging.py:157 >> {'loss': 0.0017, 'learning_rate': 0.0000e+00, 'epoch': 3.00, 'throughput': 201.15}
+
+[INFO|2025-02-09 13:59:35] trainer.py:3910 >> Saving model checkpoint to saves/Qwen2.5-7B-Instruct/full/train_2025-02-07-00-42-22_qwen/checkpoint-22635
+
+[INFO|2025-02-09 13:59:35] configuration_utils.py:420 >> Configuration saved in saves/Qwen2.5-7B-Instruct/full/train_2025-02-07-00-42-22_qwen/checkpoint-22635/config.json
+
+[INFO|2025-02-09 13:59:35] configuration_utils.py:909 >> Configuration saved in saves/Qwen2.5-7B-Instruct/full/train_2025-02-07-00-42-22_qwen/checkpoint-22635/generation_config.json
+
+[INFO|2025-02-09 13:59:46] modeling_utils.py:2996 >> 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/Qwen2.5-7B-Instruct/full/train_2025-02-07-00-42-22_qwen/checkpoint-22635/model.safetensors.index.json.
+
+[INFO|2025-02-09 13:59:46] tokenization_utils_base.py:2491 >> tokenizer config file saved in saves/Qwen2.5-7B-Instruct/full/train_2025-02-07-00-42-22_qwen/checkpoint-22635/tokenizer_config.json
+
+[INFO|2025-02-09 13:59:46] tokenization_utils_base.py:2500 >> Special tokens file saved in saves/Qwen2.5-7B-Instruct/full/train_2025-02-07-00-42-22_qwen/checkpoint-22635/special_tokens_map.json
+
+[INFO|2025-02-09 14:00:41] trainer.py:2643 >> 
+
+Training completed. Do not forget to share your model on huggingface.co/models =)
+
+
+
+[INFO|2025-02-09 14:00:46] trainer.py:3910 >> Saving model checkpoint to saves/Qwen2.5-7B-Instruct/full/train_2025-02-07-00-42-22_qwen
+
+[INFO|2025-02-09 14:00:46] configuration_utils.py:420 >> Configuration saved in saves/Qwen2.5-7B-Instruct/full/train_2025-02-07-00-42-22_qwen/config.json
+
+[INFO|2025-02-09 14:00:46] configuration_utils.py:909 >> Configuration saved in saves/Qwen2.5-7B-Instruct/full/train_2025-02-07-00-42-22_qwen/generation_config.json
+
+[INFO|2025-02-09 14:01:01] modeling_utils.py:2996 >> 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/Qwen2.5-7B-Instruct/full/train_2025-02-07-00-42-22_qwen/model.safetensors.index.json.
+
+[INFO|2025-02-09 14:01:01] tokenization_utils_base.py:2491 >> tokenizer config file saved in saves/Qwen2.5-7B-Instruct/full/train_2025-02-07-00-42-22_qwen/tokenizer_config.json
+
+[INFO|2025-02-09 14:01:01] tokenization_utils_base.py:2500 >> Special tokens file saved in saves/Qwen2.5-7B-Instruct/full/train_2025-02-07-00-42-22_qwen/special_tokens_map.json
+
+[WARNING|2025-02-09 14:01:03] logging.py:162 >> No metric eval_loss to plot.
+
+[WARNING|2025-02-09 14:01:03] logging.py:162 >> No metric eval_accuracy to plot.
+
+[INFO|2025-02-09 14:01:03] modelcard.py:449 >> Dropping the following result as it does not have all the necessary fields:
+{'task': {'name': 'Causal Language Modeling', 'type': 'text-generation'}}
+

special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+size 11421896

tokenizer_config.json

@@ -0,0 +1,209 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 2048,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 3.0,
+    "num_input_tokens_seen": 44325984,
+    "total_flos": 1.8804729049283297e+18,
+    "train_loss": 0.11007208550827785,
+    "train_runtime": 220429.5839,
+    "train_samples_per_second": 0.205,
+    "train_steps_per_second": 0.103
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3469befa03cfdc61d08fe4993d0b0451d621d80513a23011f8b231cbcb3efb30
+size 7416