Upload model

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,61 @@
+---
+library_name: transformers
+license: other
+base_model: Qwen/Qwen2.5-7B-Instruct
+tags:
+- llama-factory
+- full
+- generated_from_trainer
+model-index:
+- name: nemo_nano_science_100k
+  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. -->
+
+# nemo_nano_science_100k
+
+This model is a fine-tuned version of [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct) on the mlfoundations-dev/nemo_nano_science_100k 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: 8e-05
+- train_batch_size: 1
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 16
+- gradient_accumulation_steps: 32
+- total_train_batch_size: 512
+- total_eval_batch_size: 128
+- 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_ratio: 0.1
+- num_epochs: 5.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.46.1
+- Pytorch 2.5.0a0+b465a5843b.nv24.09
+- Datasets 3.5.0
+- Tokenizers 0.20.3

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 +1,8 @@
+{
+    "epoch": 4.924760601915184,
+    "total_flos": 2.9249198798007173e+18,
+    "train_loss": 1.1118553096597845,
+    "train_runtime": 25822.1288,
+    "train_samples_per_second": 2.263,
+    "train_steps_per_second": 0.004
+}

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "/p/data1/mmlaion/dcft/hub/models--Qwen--Qwen2.5-7B-Instruct/snapshots/a09a35458c702b33eeacc393d103063234e8bc28",
+  "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": "4.46.1",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

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": "4.46.1"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a09fcc8e45ca5aca3b1f7a5a580e3ceb661ad640c37c6fe1e48b396e3dd7edf
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa42c1622564b8efec1693ae30bffe14b173ed6a04a6c1460e0c64a50c6af22a
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:462705fd2d40ad9545adc2693d9ed7a0d0870ed0d5fd45eef472f38857b8bfdc
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8ab7ed27d035a1a15f8967837a286d0397467ebb76d50155a7849b446d050e1
+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"
+  }
+}

runs/May11_11-07-56_jrc0911/events.out.tfevents.1746954547.jrc0911.2611293.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e70c6d53f96bf4a8dcc0d0d3b241db95300b5e65e28161399a41d45e2d7e3dc9
+size 28635

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": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

start_end.json

@@ -0,0 +1 @@
+{"start_time": "2025-05-11 11:07:56", "end_time": "2025-05-11 18:19:40"}

tokenizer.json

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

tokenizer_config.json

@@ -0,0 +1,208 @@
+{
+  "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": "<|endoftext|>",
+  "errors": "replace",
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 4.924760601915184,
+    "total_flos": 2.9249198798007173e+18,
+    "train_loss": 1.1118553096597845,
+    "train_runtime": 25822.1288,
+    "train_samples_per_second": 2.263,
+    "train_steps_per_second": 0.004
+}

trainer_log.jsonl

@@ -0,0 +1,111 @@
+{"current_steps": 1, "total_steps": 110, "loss": 1.6783, "lr": 7.272727272727273e-06, "epoch": 0.04377564979480164, "percentage": 0.91, "elapsed_time": "0:04:07", "remaining_time": "7:30:08"}
+{"current_steps": 2, "total_steps": 110, "loss": 1.6756, "lr": 1.4545454545454546e-05, "epoch": 0.08755129958960328, "percentage": 1.82, "elapsed_time": "0:08:01", "remaining_time": "7:13:23"}
+{"current_steps": 3, "total_steps": 110, "loss": 1.5708, "lr": 2.1818181818181818e-05, "epoch": 0.13132694938440492, "percentage": 2.73, "elapsed_time": "0:11:55", "remaining_time": "7:05:02"}
+{"current_steps": 4, "total_steps": 110, "loss": 1.5415, "lr": 2.9090909090909093e-05, "epoch": 0.17510259917920656, "percentage": 3.64, "elapsed_time": "0:15:47", "remaining_time": "6:58:31"}
+{"current_steps": 5, "total_steps": 110, "loss": 1.5506, "lr": 3.6363636363636364e-05, "epoch": 0.2188782489740082, "percentage": 4.55, "elapsed_time": "0:19:40", "remaining_time": "6:53:05"}
+{"current_steps": 6, "total_steps": 110, "loss": 1.4494, "lr": 4.3636363636363636e-05, "epoch": 0.26265389876880985, "percentage": 5.45, "elapsed_time": "0:23:33", "remaining_time": "6:48:24"}
+{"current_steps": 7, "total_steps": 110, "loss": 1.3764, "lr": 5.0909090909090914e-05, "epoch": 0.3064295485636115, "percentage": 6.36, "elapsed_time": "0:27:26", "remaining_time": "6:43:52"}
+{"current_steps": 8, "total_steps": 110, "loss": 1.3124, "lr": 5.8181818181818185e-05, "epoch": 0.35020519835841313, "percentage": 7.27, "elapsed_time": "0:31:19", "remaining_time": "6:39:20"}
+{"current_steps": 9, "total_steps": 110, "loss": 1.3263, "lr": 6.545454545454546e-05, "epoch": 0.39398084815321477, "percentage": 8.18, "elapsed_time": "0:35:12", "remaining_time": "6:35:03"}
+{"current_steps": 10, "total_steps": 110, "loss": 1.302, "lr": 7.272727272727273e-05, "epoch": 0.4377564979480164, "percentage": 9.09, "elapsed_time": "0:39:05", "remaining_time": "6:30:50"}
+{"current_steps": 11, "total_steps": 110, "loss": 1.2851, "lr": 8e-05, "epoch": 0.48153214774281805, "percentage": 10.0, "elapsed_time": "0:42:58", "remaining_time": "6:26:50"}
+{"current_steps": 12, "total_steps": 110, "loss": 1.2886, "lr": 7.997986169532741e-05, "epoch": 0.5253077975376197, "percentage": 10.91, "elapsed_time": "0:46:51", "remaining_time": "6:22:40"}
+{"current_steps": 13, "total_steps": 110, "loss": 1.2546, "lr": 7.991946705887539e-05, "epoch": 0.5690834473324213, "percentage": 11.82, "elapsed_time": "0:50:44", "remaining_time": "6:18:39"}
+{"current_steps": 14, "total_steps": 110, "loss": 1.2314, "lr": 7.981887690292339e-05, "epoch": 0.612859097127223, "percentage": 12.73, "elapsed_time": "0:54:40", "remaining_time": "6:14:51"}
+{"current_steps": 15, "total_steps": 110, "loss": 1.2315, "lr": 7.967819251323182e-05, "epoch": 0.6566347469220246, "percentage": 13.64, "elapsed_time": "0:58:33", "remaining_time": "6:10:51"}
+{"current_steps": 16, "total_steps": 110, "loss": 1.2093, "lr": 7.949755554705577e-05, "epoch": 0.7004103967168263, "percentage": 14.55, "elapsed_time": "1:02:27", "remaining_time": "6:06:53"}
+{"current_steps": 17, "total_steps": 110, "loss": 1.196, "lr": 7.927714789050826e-05, "epoch": 0.7441860465116279, "percentage": 15.45, "elapsed_time": "1:06:20", "remaining_time": "6:02:54"}
+{"current_steps": 18, "total_steps": 110, "loss": 1.2348, "lr": 7.90171914754163e-05, "epoch": 0.7879616963064295, "percentage": 16.36, "elapsed_time": "1:10:12", "remaining_time": "5:58:50"}
+{"current_steps": 19, "total_steps": 110, "loss": 1.2053, "lr": 7.871794805585427e-05, "epoch": 0.8317373461012312, "percentage": 17.27, "elapsed_time": "1:14:04", "remaining_time": "5:54:48"}
+{"current_steps": 20, "total_steps": 110, "loss": 1.1834, "lr": 7.837971894457991e-05, "epoch": 0.8755129958960328, "percentage": 18.18, "elapsed_time": "1:17:58", "remaining_time": "5:50:51"}
+{"current_steps": 21, "total_steps": 110, "loss": 1.1831, "lr": 7.800284470963783e-05, "epoch": 0.9192886456908345, "percentage": 19.09, "elapsed_time": "1:21:51", "remaining_time": "5:46:54"}
+{"current_steps": 22, "total_steps": 110, "loss": 1.1698, "lr": 7.758770483143634e-05, "epoch": 0.9630642954856361, "percentage": 20.0, "elapsed_time": "1:25:44", "remaining_time": "5:42:57"}
+{"current_steps": 23, "total_steps": 110, "loss": 2.0516, "lr": 7.71347173206429e-05, "epoch": 1.0341997264021887, "percentage": 20.91, "elapsed_time": "1:30:06", "remaining_time": "5:40:52"}
+{"current_steps": 24, "total_steps": 110, "loss": 1.152, "lr": 7.664433829728279e-05, "epoch": 1.0779753761969904, "percentage": 21.82, "elapsed_time": "1:33:59", "remaining_time": "5:36:48"}
+{"current_steps": 25, "total_steps": 110, "loss": 1.1468, "lr": 7.611706153146486e-05, "epoch": 1.121751025991792, "percentage": 22.73, "elapsed_time": "1:37:52", "remaining_time": "5:32:46"}
+{"current_steps": 26, "total_steps": 110, "loss": 1.1408, "lr": 7.555341794619695e-05, "epoch": 1.1655266757865936, "percentage": 23.64, "elapsed_time": "1:41:45", "remaining_time": "5:28:46"}
+{"current_steps": 27, "total_steps": 110, "loss": 1.1219, "lr": 7.49539750827914e-05, "epoch": 1.2093023255813953, "percentage": 24.55, "elapsed_time": "1:45:38", "remaining_time": "5:24:43"}
+{"current_steps": 28, "total_steps": 110, "loss": 1.1136, "lr": 7.431933652939909e-05, "epoch": 1.253077975376197, "percentage": 25.45, "elapsed_time": "1:49:31", "remaining_time": "5:20:44"}
+{"current_steps": 29, "total_steps": 110, "loss": 1.1191, "lr": 7.365014131324725e-05, "epoch": 1.2968536251709986, "percentage": 26.36, "elapsed_time": "1:53:23", "remaining_time": "5:16:44"}
+{"current_steps": 30, "total_steps": 110, "loss": 1.1145, "lr": 7.294706325719331e-05, "epoch": 1.3406292749658002, "percentage": 27.27, "elapsed_time": "1:57:16", "remaining_time": "5:12:43"}
+{"current_steps": 31, "total_steps": 110, "loss": 1.1269, "lr": 7.221081030124235e-05, "epoch": 1.3844049247606018, "percentage": 28.18, "elapsed_time": "2:01:09", "remaining_time": "5:08:45"}
+{"current_steps": 32, "total_steps": 110, "loss": 1.1065, "lr": 7.144212378971151e-05, "epoch": 1.4281805745554035, "percentage": 29.09, "elapsed_time": "2:05:02", "remaining_time": "5:04:47"}
+{"current_steps": 33, "total_steps": 110, "loss": 1.1347, "lr": 7.064177772475912e-05, "epoch": 1.4719562243502051, "percentage": 30.0, "elapsed_time": "2:08:55", "remaining_time": "5:00:48"}
+{"current_steps": 34, "total_steps": 110, "loss": 1.1176, "lr": 6.98105779870302e-05, "epoch": 1.5157318741450068, "percentage": 30.91, "elapsed_time": "2:12:47", "remaining_time": "4:56:50"}
+{"current_steps": 35, "total_steps": 110, "loss": 1.0969, "lr": 6.89493615242028e-05, "epoch": 1.5595075239398084, "percentage": 31.82, "elapsed_time": "2:16:41", "remaining_time": "4:52:55"}
+{"current_steps": 36, "total_steps": 110, "loss": 1.1039, "lr": 6.805899550825285e-05, "epoch": 1.60328317373461, "percentage": 32.73, "elapsed_time": "2:20:34", "remaining_time": "4:48:58"}
+{"current_steps": 37, "total_steps": 110, "loss": 1.1059, "lr": 6.714037646228529e-05, "epoch": 1.6470588235294117, "percentage": 33.64, "elapsed_time": "2:24:27", "remaining_time": "4:45:00"}
+{"current_steps": 38, "total_steps": 110, "loss": 1.098, "lr": 6.619442935781141e-05, "epoch": 1.6908344733242133, "percentage": 34.55, "elapsed_time": "2:28:20", "remaining_time": "4:41:03"}
+{"current_steps": 39, "total_steps": 110, "loss": 1.0852, "lr": 6.52221066833809e-05, "epoch": 1.734610123119015, "percentage": 35.45, "elapsed_time": "2:32:13", "remaining_time": "4:37:07"}
+{"current_steps": 40, "total_steps": 110, "loss": 1.0901, "lr": 6.422438748550667e-05, "epoch": 1.7783857729138166, "percentage": 36.36, "elapsed_time": "2:36:06", "remaining_time": "4:33:11"}
+{"current_steps": 41, "total_steps": 110, "loss": 1.0781, "lr": 6.320227638284793e-05, "epoch": 1.8221614227086183, "percentage": 37.27, "elapsed_time": "2:39:59", "remaining_time": "4:29:15"}
+{"current_steps": 42, "total_steps": 110, "loss": 1.0825, "lr": 6.215680255464442e-05, "epoch": 1.86593707250342, "percentage": 38.18, "elapsed_time": "2:43:53", "remaining_time": "4:25:20"}
+{"current_steps": 43, "total_steps": 110, "loss": 1.0766, "lr": 6.10890187044201e-05, "epoch": 1.9097127222982215, "percentage": 39.09, "elapsed_time": "2:47:46", "remaining_time": "4:21:25"}
+{"current_steps": 44, "total_steps": 110, "loss": 1.0763, "lr": 6.000000000000001e-05, "epoch": 1.9534883720930232, "percentage": 40.0, "elapsed_time": "2:51:39", "remaining_time": "4:17:29"}
+{"current_steps": 45, "total_steps": 110, "loss": 1.9051, "lr": 5.889084299090732e-05, "epoch": 2.024623803009576, "percentage": 40.91, "elapsed_time": "2:56:00", "remaining_time": "4:14:13"}
+{"current_steps": 46, "total_steps": 110, "loss": 1.0442, "lr": 5.776266450423097e-05, "epoch": 2.0683994528043774, "percentage": 41.82, "elapsed_time": "2:59:53", "remaining_time": "4:10:16"}
+{"current_steps": 47, "total_steps": 110, "loss": 1.0507, "lr": 5.661660052007547e-05, "epoch": 2.112175102599179, "percentage": 42.73, "elapsed_time": "3:03:46", "remaining_time": "4:06:20"}
+{"current_steps": 48, "total_steps": 110, "loss": 1.0499, "lr": 5.5453805027725145e-05, "epoch": 2.1559507523939807, "percentage": 43.64, "elapsed_time": "3:07:39", "remaining_time": "4:02:23"}
+{"current_steps": 49, "total_steps": 110, "loss": 1.0381, "lr": 5.427544886367488e-05, "epoch": 2.1997264021887823, "percentage": 44.55, "elapsed_time": "3:11:32", "remaining_time": "3:58:27"}
+{"current_steps": 50, "total_steps": 110, "loss": 1.0437, "lr": 5.3082718532696874e-05, "epoch": 2.243502051983584, "percentage": 45.45, "elapsed_time": "3:15:25", "remaining_time": "3:54:31"}
+{"current_steps": 51, "total_steps": 110, "loss": 1.0329, "lr": 5.1876815013131e-05, "epoch": 2.2872777017783856, "percentage": 46.36, "elapsed_time": "3:19:18", "remaining_time": "3:50:34"}
+{"current_steps": 52, "total_steps": 110, "loss": 1.0287, "lr": 5.06589525476014e-05, "epoch": 2.3310533515731873, "percentage": 47.27, "elapsed_time": "3:23:12", "remaining_time": "3:46:39"}
+{"current_steps": 53, "total_steps": 110, "loss": 1.04, "lr": 4.94303574203771e-05, "epoch": 2.374829001367989, "percentage": 48.18, "elapsed_time": "3:27:06", "remaining_time": "3:42:43"}
+{"current_steps": 54, "total_steps": 110, "loss": 1.0331, "lr": 4.819226672260763e-05, "epoch": 2.4186046511627906, "percentage": 49.09, "elapsed_time": "3:30:59", "remaining_time": "3:38:48"}
+{"current_steps": 55, "total_steps": 110, "loss": 1.0243, "lr": 4.694592710667723e-05, "epoch": 2.462380300957592, "percentage": 50.0, "elapsed_time": "3:34:52", "remaining_time": "3:34:52"}
+{"current_steps": 56, "total_steps": 110, "loss": 1.0052, "lr": 4.5692593530931416e-05, "epoch": 2.506155950752394, "percentage": 50.91, "elapsed_time": "3:38:45", "remaining_time": "3:30:56"}
+{"current_steps": 57, "total_steps": 110, "loss": 1.0299, "lr": 4.4433527996040443e-05, "epoch": 2.5499316005471955, "percentage": 51.82, "elapsed_time": "3:42:37", "remaining_time": "3:27:00"}
+{"current_steps": 58, "total_steps": 110, "loss": 1.0344, "lr": 4.316999827427154e-05, "epoch": 2.593707250341997, "percentage": 52.73, "elapsed_time": "3:46:30", "remaining_time": "3:23:04"}
+{"current_steps": 59, "total_steps": 110, "loss": 1.0197, "lr": 4.19032766329497e-05, "epoch": 2.6374829001367988, "percentage": 53.64, "elapsed_time": "3:50:24", "remaining_time": "3:19:09"}
+{"current_steps": 60, "total_steps": 110, "loss": 1.0142, "lr": 4.063463855339232e-05, "epoch": 2.6812585499316004, "percentage": 54.55, "elapsed_time": "3:54:16", "remaining_time": "3:15:14"}
+{"current_steps": 61, "total_steps": 110, "loss": 1.0194, "lr": 3.9365361446607684e-05, "epoch": 2.725034199726402, "percentage": 55.45, "elapsed_time": "3:58:10", "remaining_time": "3:11:18"}
+{"current_steps": 62, "total_steps": 110, "loss": 1.021, "lr": 3.809672336705031e-05, "epoch": 2.7688098495212037, "percentage": 56.36, "elapsed_time": "4:02:03", "remaining_time": "3:07:24"}
+{"current_steps": 63, "total_steps": 110, "loss": 1.0145, "lr": 3.683000172572846e-05, "epoch": 2.8125854993160053, "percentage": 57.27, "elapsed_time": "4:05:57", "remaining_time": "3:03:29"}
+{"current_steps": 64, "total_steps": 110, "loss": 1.0159, "lr": 3.556647200395956e-05, "epoch": 2.856361149110807, "percentage": 58.18, "elapsed_time": "4:09:50", "remaining_time": "2:59:34"}
+{"current_steps": 65, "total_steps": 110, "loss": 1.0037, "lr": 3.4307406469068604e-05, "epoch": 2.9001367989056086, "percentage": 59.09, "elapsed_time": "4:13:43", "remaining_time": "2:55:39"}
+{"current_steps": 66, "total_steps": 110, "loss": 1.0124, "lr": 3.305407289332279e-05, "epoch": 2.9439124487004102, "percentage": 60.0, "elapsed_time": "4:17:36", "remaining_time": "2:51:44"}
+{"current_steps": 67, "total_steps": 110, "loss": 1.8113, "lr": 3.180773327739238e-05, "epoch": 3.015047879616963, "percentage": 60.91, "elapsed_time": "4:21:56", "remaining_time": "2:48:07"}
+{"current_steps": 68, "total_steps": 110, "loss": 0.9808, "lr": 3.0569642579622905e-05, "epoch": 3.0588235294117645, "percentage": 61.82, "elapsed_time": "4:25:50", "remaining_time": "2:44:12"}
+{"current_steps": 69, "total_steps": 110, "loss": 0.9786, "lr": 2.9341047452398607e-05, "epoch": 3.102599179206566, "percentage": 62.73, "elapsed_time": "4:29:43", "remaining_time": "2:40:16"}
+{"current_steps": 70, "total_steps": 110, "loss": 0.9807, "lr": 2.8123184986869022e-05, "epoch": 3.146374829001368, "percentage": 63.64, "elapsed_time": "4:33:37", "remaining_time": "2:36:21"}
+{"current_steps": 71, "total_steps": 110, "loss": 0.9801, "lr": 2.691728146730314e-05, "epoch": 3.19015047879617, "percentage": 64.55, "elapsed_time": "4:37:30", "remaining_time": "2:32:26"}
+{"current_steps": 72, "total_steps": 110, "loss": 0.9752, "lr": 2.5724551136325132e-05, "epoch": 3.233926128590971, "percentage": 65.45, "elapsed_time": "4:41:23", "remaining_time": "2:28:30"}
+{"current_steps": 73, "total_steps": 110, "loss": 0.9833, "lr": 2.4546194972274852e-05, "epoch": 3.277701778385773, "percentage": 66.36, "elapsed_time": "4:45:17", "remaining_time": "2:24:35"}
+{"current_steps": 74, "total_steps": 110, "loss": 0.9704, "lr": 2.338339947992455e-05, "epoch": 3.3214774281805743, "percentage": 67.27, "elapsed_time": "4:49:10", "remaining_time": "2:20:40"}
+{"current_steps": 75, "total_steps": 110, "loss": 0.9832, "lr": 2.2237335495769035e-05, "epoch": 3.3652530779753764, "percentage": 68.18, "elapsed_time": "4:53:03", "remaining_time": "2:16:45"}
+{"current_steps": 76, "total_steps": 110, "loss": 0.9832, "lr": 2.11091570090927e-05, "epoch": 3.4090287277701776, "percentage": 69.09, "elapsed_time": "4:56:56", "remaining_time": "2:12:50"}
+{"current_steps": 77, "total_steps": 110, "loss": 0.9925, "lr": 2.0000000000000012e-05, "epoch": 3.4528043775649797, "percentage": 70.0, "elapsed_time": "5:00:49", "remaining_time": "2:08:55"}
+{"current_steps": 78, "total_steps": 110, "loss": 0.9693, "lr": 1.8910981295579903e-05, "epoch": 3.496580027359781, "percentage": 70.91, "elapsed_time": "5:04:42", "remaining_time": "2:05:00"}
+{"current_steps": 79, "total_steps": 110, "loss": 0.9687, "lr": 1.7843197445355593e-05, "epoch": 3.540355677154583, "percentage": 71.82, "elapsed_time": "5:08:35", "remaining_time": "2:01:05"}
+{"current_steps": 80, "total_steps": 110, "loss": 0.9792, "lr": 1.679772361715208e-05, "epoch": 3.584131326949384, "percentage": 72.73, "elapsed_time": "5:12:29", "remaining_time": "1:57:10"}
+{"current_steps": 81, "total_steps": 110, "loss": 0.9716, "lr": 1.5775612514493343e-05, "epoch": 3.6279069767441863, "percentage": 73.64, "elapsed_time": "5:16:22", "remaining_time": "1:53:16"}
+{"current_steps": 82, "total_steps": 110, "loss": 0.9791, "lr": 1.4777893316619114e-05, "epoch": 3.6716826265389875, "percentage": 74.55, "elapsed_time": "5:20:15", "remaining_time": "1:49:21"}
+{"current_steps": 83, "total_steps": 110, "loss": 0.9686, "lr": 1.3805570642188602e-05, "epoch": 3.7154582763337896, "percentage": 75.45, "elapsed_time": "5:24:08", "remaining_time": "1:45:26"}
+{"current_steps": 84, "total_steps": 110, "loss": 0.9674, "lr": 1.2859623537714719e-05, "epoch": 3.7592339261285908, "percentage": 76.36, "elapsed_time": "5:28:02", "remaining_time": "1:41:32"}
+{"current_steps": 85, "total_steps": 110, "loss": 0.9639, "lr": 1.1941004491747145e-05, "epoch": 3.803009575923393, "percentage": 77.27, "elapsed_time": "5:31:55", "remaining_time": "1:37:37"}
+{"current_steps": 86, "total_steps": 110, "loss": 0.9609, "lr": 1.1050638475797193e-05, "epoch": 3.846785225718194, "percentage": 78.18, "elapsed_time": "5:35:48", "remaining_time": "1:33:42"}
+{"current_steps": 87, "total_steps": 110, "loss": 0.9722, "lr": 1.0189422012969814e-05, "epoch": 3.890560875512996, "percentage": 79.09, "elapsed_time": "5:39:42", "remaining_time": "1:29:48"}
+{"current_steps": 88, "total_steps": 110, "loss": 0.968, "lr": 9.358222275240884e-06, "epoch": 3.9343365253077973, "percentage": 80.0, "elapsed_time": "5:43:35", "remaining_time": "1:25:53"}
+{"current_steps": 89, "total_steps": 110, "loss": 1.746, "lr": 8.55787621028851e-06, "epoch": 4.00547195622435, "percentage": 80.91, "elapsed_time": "5:47:55", "remaining_time": "1:22:05"}
+{"current_steps": 90, "total_steps": 110, "loss": 0.9564, "lr": 7.789189698757656e-06, "epoch": 4.049247606019152, "percentage": 81.82, "elapsed_time": "5:51:47", "remaining_time": "1:18:10"}
+{"current_steps": 91, "total_steps": 110, "loss": 0.9593, "lr": 7.052936742806693e-06, "epoch": 4.093023255813954, "percentage": 82.73, "elapsed_time": "5:55:41", "remaining_time": "1:14:15"}
+{"current_steps": 92, "total_steps": 110, "loss": 0.9627, "lr": 6.349858686752748e-06, "epoch": 4.136798905608755, "percentage": 83.64, "elapsed_time": "5:59:34", "remaining_time": "1:10:21"}
+{"current_steps": 93, "total_steps": 110, "loss": 0.9486, "lr": 5.680663470600918e-06, "epoch": 4.180574555403557, "percentage": 84.55, "elapsed_time": "6:03:27", "remaining_time": "1:06:26"}
+{"current_steps": 94, "total_steps": 110, "loss": 0.9564, "lr": 5.046024917208603e-06, "epoch": 4.224350205198358, "percentage": 85.45, "elapsed_time": "6:07:19", "remaining_time": "1:02:31"}
+{"current_steps": 95, "total_steps": 110, "loss": 0.9532, "lr": 4.446582053803066e-06, "epoch": 4.26812585499316, "percentage": 86.36, "elapsed_time": "6:11:13", "remaining_time": "0:58:36"}
+{"current_steps": 96, "total_steps": 110, "loss": 0.9441, "lr": 3.882938468535158e-06, "epoch": 4.311901504787961, "percentage": 87.27, "elapsed_time": "6:15:06", "remaining_time": "0:54:42"}
+{"current_steps": 97, "total_steps": 110, "loss": 0.9502, "lr": 3.3556617027172168e-06, "epoch": 4.3556771545827635, "percentage": 88.18, "elapsed_time": "6:18:59", "remaining_time": "0:50:47"}
+{"current_steps": 98, "total_steps": 110, "loss": 0.9499, "lr": 2.8652826793570975e-06, "epoch": 4.399452804377565, "percentage": 89.09, "elapsed_time": "6:22:53", "remaining_time": "0:46:53"}
+{"current_steps": 99, "total_steps": 110, "loss": 0.9623, "lr": 2.4122951685636674e-06, "epoch": 4.443228454172367, "percentage": 90.0, "elapsed_time": "6:26:49", "remaining_time": "0:42:58"}
+{"current_steps": 100, "total_steps": 110, "loss": 0.9546, "lr": 1.997155290362187e-06, "epoch": 4.487004103967168, "percentage": 90.91, "elapsed_time": "6:30:42", "remaining_time": "0:39:04"}
+{"current_steps": 101, "total_steps": 110, "loss": 0.9634, "lr": 1.6202810554201099e-06, "epoch": 4.53077975376197, "percentage": 91.82, "elapsed_time": "6:34:34", "remaining_time": "0:35:09"}
+{"current_steps": 102, "total_steps": 110, "loss": 0.9489, "lr": 1.2820519441457502e-06, "epoch": 4.574555403556771, "percentage": 92.73, "elapsed_time": "6:38:28", "remaining_time": "0:31:15"}
+{"current_steps": 103, "total_steps": 110, "loss": 0.9481, "lr": 9.828085245837183e-07, "epoch": 4.618331053351573, "percentage": 93.64, "elapsed_time": "6:42:21", "remaining_time": "0:27:20"}
+{"current_steps": 104, "total_steps": 110, "loss": 0.9517, "lr": 7.228521094917318e-07, "epoch": 4.6621067031463745, "percentage": 94.55, "elapsed_time": "6:46:14", "remaining_time": "0:23:26"}
+{"current_steps": 105, "total_steps": 110, "loss": 0.9544, "lr": 5.024444529442285e-07, "epoch": 4.705882352941177, "percentage": 95.45, "elapsed_time": "6:50:06", "remaining_time": "0:19:31"}
+{"current_steps": 106, "total_steps": 110, "loss": 0.9384, "lr": 3.218074867681864e-07, "epoch": 4.749658002735978, "percentage": 96.36, "elapsed_time": "6:53:59", "remaining_time": "0:15:37"}
+{"current_steps": 107, "total_steps": 110, "loss": 0.943, "lr": 1.8112309707661647e-07, "epoch": 4.79343365253078, "percentage": 97.27, "elapsed_time": "6:57:53", "remaining_time": "0:11:42"}
+{"current_steps": 108, "total_steps": 110, "loss": 0.9525, "lr": 8.053294112462696e-08, "epoch": 4.837209302325581, "percentage": 98.18, "elapsed_time": "7:01:45", "remaining_time": "0:07:48"}
+{"current_steps": 109, "total_steps": 110, "loss": 0.9539, "lr": 2.01383046725967e-08, "epoch": 4.880984952120383, "percentage": 99.09, "elapsed_time": "7:05:38", "remaining_time": "0:03:54"}
+{"current_steps": 110, "total_steps": 110, "loss": 0.9416, "lr": 0.0, "epoch": 4.924760601915184, "percentage": 100.0, "elapsed_time": "7:09:30", "remaining_time": "0:00:00"}
+{"current_steps": 110, "total_steps": 110, "epoch": 4.924760601915184, "percentage": 100.0, "elapsed_time": "7:10:00", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,812 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.924760601915184,
+  "eval_steps": 500,
+  "global_step": 110,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.04377564979480164,
+      "grad_norm": 10.977038416240942,
+      "learning_rate": 7.272727272727273e-06,
+      "loss": 1.6783,
+      "step": 1
+    },
+    {
+      "epoch": 0.08755129958960328,
+      "grad_norm": 10.685982173301461,
+      "learning_rate": 1.4545454545454546e-05,
+      "loss": 1.6756,
+      "step": 2
+    },
+    {
+      "epoch": 0.13132694938440492,
+      "grad_norm": 7.560341958816415,
+      "learning_rate": 2.1818181818181818e-05,
+      "loss": 1.5708,
+      "step": 3
+    },
+    {
+      "epoch": 0.17510259917920656,
+      "grad_norm": 6.257863682610026,
+      "learning_rate": 2.9090909090909093e-05,
+      "loss": 1.5415,
+      "step": 4
+    },
+    {
+      "epoch": 0.2188782489740082,
+      "grad_norm": 9.338746208897016,
+      "learning_rate": 3.6363636363636364e-05,
+      "loss": 1.5506,
+      "step": 5
+    },
+    {
+      "epoch": 0.26265389876880985,
+      "grad_norm": 6.7019369753380404,
+      "learning_rate": 4.3636363636363636e-05,
+      "loss": 1.4494,
+      "step": 6
+    },
+    {
+      "epoch": 0.3064295485636115,
+      "grad_norm": 2.7387345576832467,
+      "learning_rate": 5.0909090909090914e-05,
+      "loss": 1.3764,
+      "step": 7
+    },
+    {
+      "epoch": 0.35020519835841313,
+      "grad_norm": 2.9905508612885416,
+      "learning_rate": 5.8181818181818185e-05,
+      "loss": 1.3124,
+      "step": 8
+    },
+    {
+      "epoch": 0.39398084815321477,
+      "grad_norm": 5.142107061812394,
+      "learning_rate": 6.545454545454546e-05,
+      "loss": 1.3263,
+      "step": 9
+    },
+    {
+      "epoch": 0.4377564979480164,
+      "grad_norm": 6.498361005724975,
+      "learning_rate": 7.272727272727273e-05,
+      "loss": 1.302,
+      "step": 10
+    },
+    {
+      "epoch": 0.48153214774281805,
+      "grad_norm": 4.736561117836272,
+      "learning_rate": 8e-05,
+      "loss": 1.2851,
+      "step": 11
+    },
+    {
+      "epoch": 0.5253077975376197,
+      "grad_norm": 4.913666681984767,
+      "learning_rate": 7.997986169532741e-05,
+      "loss": 1.2886,
+      "step": 12
+    },
+    {
+      "epoch": 0.5690834473324213,
+      "grad_norm": 3.3337518195815763,
+      "learning_rate": 7.991946705887539e-05,
+      "loss": 1.2546,
+      "step": 13
+    },
+    {
+      "epoch": 0.612859097127223,
+      "grad_norm": 2.7069045612640275,
+      "learning_rate": 7.981887690292339e-05,
+      "loss": 1.2314,
+      "step": 14
+    },
+    {
+      "epoch": 0.6566347469220246,
+      "grad_norm": 2.8584488966099855,
+      "learning_rate": 7.967819251323182e-05,
+      "loss": 1.2315,
+      "step": 15
+    },
+    {
+      "epoch": 0.7004103967168263,
+      "grad_norm": 3.1377249425512765,
+      "learning_rate": 7.949755554705577e-05,
+      "loss": 1.2093,
+      "step": 16
+    },
+    {
+      "epoch": 0.7441860465116279,
+      "grad_norm": 1.3936091349070174,
+      "learning_rate": 7.927714789050826e-05,
+      "loss": 1.196,
+      "step": 17
+    },
+    {
+      "epoch": 0.7879616963064295,
+      "grad_norm": 3.028923392641176,
+      "learning_rate": 7.90171914754163e-05,
+      "loss": 1.2348,
+      "step": 18
+    },
+    {
+      "epoch": 0.8317373461012312,
+      "grad_norm": 2.196134083608347,
+      "learning_rate": 7.871794805585427e-05,
+      "loss": 1.2053,
+      "step": 19
+    },
+    {
+      "epoch": 0.8755129958960328,
+      "grad_norm": 1.6611206571415684,
+      "learning_rate": 7.837971894457991e-05,
+      "loss": 1.1834,
+      "step": 20
+    },
+    {
+      "epoch": 0.9192886456908345,
+      "grad_norm": 2.681882547825232,
+      "learning_rate": 7.800284470963783e-05,
+      "loss": 1.1831,
+      "step": 21
+    },
+    {
+      "epoch": 0.9630642954856361,
+      "grad_norm": 1.5845981079722795,
+      "learning_rate": 7.758770483143634e-05,
+      "loss": 1.1698,
+      "step": 22
+    },
+    {
+      "epoch": 1.0341997264021887,
+      "grad_norm": 4.534657915532011,
+      "learning_rate": 7.71347173206429e-05,
+      "loss": 2.0516,
+      "step": 23
+    },
+    {
+      "epoch": 1.0779753761969904,
+      "grad_norm": 2.8451498787070433,
+      "learning_rate": 7.664433829728279e-05,
+      "loss": 1.152,
+      "step": 24
+    },
+    {
+      "epoch": 1.121751025991792,
+      "grad_norm": 1.9899709698106878,
+      "learning_rate": 7.611706153146486e-05,
+      "loss": 1.1468,
+      "step": 25
+    },
+    {
+      "epoch": 1.1655266757865936,
+      "grad_norm": 2.8389265579783345,
+      "learning_rate": 7.555341794619695e-05,
+      "loss": 1.1408,
+      "step": 26
+    },
+    {
+      "epoch": 1.2093023255813953,
+      "grad_norm": 2.038952629316326,
+      "learning_rate": 7.49539750827914e-05,
+      "loss": 1.1219,
+      "step": 27
+    },
+    {
+      "epoch": 1.253077975376197,
+      "grad_norm": 2.0796847065206743,
+      "learning_rate": 7.431933652939909e-05,
+      "loss": 1.1136,
+      "step": 28
+    },
+    {
+      "epoch": 1.2968536251709986,
+      "grad_norm": 1.447940531771876,
+      "learning_rate": 7.365014131324725e-05,
+      "loss": 1.1191,
+      "step": 29
+    },
+    {
+      "epoch": 1.3406292749658002,
+      "grad_norm": 1.337447462838519,
+      "learning_rate": 7.294706325719331e-05,
+      "loss": 1.1145,
+      "step": 30
+    },
+    {
+      "epoch": 1.3844049247606018,
+      "grad_norm": 2.831107849480652,
+      "learning_rate": 7.221081030124235e-05,
+      "loss": 1.1269,
+      "step": 31
+    },
+    {
+      "epoch": 1.4281805745554035,
+      "grad_norm": 1.3913695315986807,
+      "learning_rate": 7.144212378971151e-05,
+      "loss": 1.1065,
+      "step": 32
+    },
+    {
+      "epoch": 1.4719562243502051,
+      "grad_norm": 2.9279595696419647,
+      "learning_rate": 7.064177772475912e-05,
+      "loss": 1.1347,
+      "step": 33
+    },
+    {
+      "epoch": 1.5157318741450068,
+      "grad_norm": 2.1607556666180012,
+      "learning_rate": 6.98105779870302e-05,
+      "loss": 1.1176,
+      "step": 34
+    },
+    {
+      "epoch": 1.5595075239398084,
+      "grad_norm": 2.035595521860542,
+      "learning_rate": 6.89493615242028e-05,
+      "loss": 1.0969,
+      "step": 35
+    },
+    {
+      "epoch": 1.60328317373461,
+      "grad_norm": 1.9632755753820994,
+      "learning_rate": 6.805899550825285e-05,
+      "loss": 1.1039,
+      "step": 36
+    },
+    {
+      "epoch": 1.6470588235294117,
+      "grad_norm": 1.756863438311583,
+      "learning_rate": 6.714037646228529e-05,
+      "loss": 1.1059,
+      "step": 37
+    },
+    {
+      "epoch": 1.6908344733242133,
+      "grad_norm": 1.6660401725071718,
+      "learning_rate": 6.619442935781141e-05,
+      "loss": 1.098,
+      "step": 38
+    },
+    {
+      "epoch": 1.734610123119015,
+      "grad_norm": 1.4739841905330868,
+      "learning_rate": 6.52221066833809e-05,
+      "loss": 1.0852,
+      "step": 39
+    },
+    {
+      "epoch": 1.7783857729138166,
+      "grad_norm": 1.3135170392231592,
+      "learning_rate": 6.422438748550667e-05,
+      "loss": 1.0901,
+      "step": 40
+    },
+    {
+      "epoch": 1.8221614227086183,
+      "grad_norm": 1.3850190455081264,
+      "learning_rate": 6.320227638284793e-05,
+      "loss": 1.0781,
+      "step": 41
+    },
+    {
+      "epoch": 1.86593707250342,
+      "grad_norm": 0.9405053138714191,
+      "learning_rate": 6.215680255464442e-05,
+      "loss": 1.0825,
+      "step": 42
+    },
+    {
+      "epoch": 1.9097127222982215,
+      "grad_norm": 1.1113532920678866,
+      "learning_rate": 6.10890187044201e-05,
+      "loss": 1.0766,
+      "step": 43
+    },
+    {
+      "epoch": 1.9534883720930232,
+      "grad_norm": 1.187498515237833,
+      "learning_rate": 6.000000000000001e-05,
+      "loss": 1.0763,
+      "step": 44
+    },
+    {
+      "epoch": 2.024623803009576,
+      "grad_norm": 2.160651041437791,
+      "learning_rate": 5.889084299090732e-05,
+      "loss": 1.9051,
+      "step": 45
+    },
+    {
+      "epoch": 2.0683994528043774,
+      "grad_norm": 0.9784307660310307,
+      "learning_rate": 5.776266450423097e-05,
+      "loss": 1.0442,
+      "step": 46
+    },
+    {
+      "epoch": 2.112175102599179,
+      "grad_norm": 1.031157632132424,
+      "learning_rate": 5.661660052007547e-05,
+      "loss": 1.0507,
+      "step": 47
+    },
+    {
+      "epoch": 2.1559507523939807,
+      "grad_norm": 1.4533738667722713,
+      "learning_rate": 5.5453805027725145e-05,
+      "loss": 1.0499,
+      "step": 48
+    },
+    {
+      "epoch": 2.1997264021887823,
+      "grad_norm": 0.875133136635367,
+      "learning_rate": 5.427544886367488e-05,
+      "loss": 1.0381,
+      "step": 49
+    },
+    {
+      "epoch": 2.243502051983584,
+      "grad_norm": 0.9817484749723364,
+      "learning_rate": 5.3082718532696874e-05,
+      "loss": 1.0437,
+      "step": 50
+    },
+    {
+      "epoch": 2.2872777017783856,
+      "grad_norm": 1.223185197293581,
+      "learning_rate": 5.1876815013131e-05,
+      "loss": 1.0329,
+      "step": 51
+    },
+    {
+      "epoch": 2.3310533515731873,
+      "grad_norm": 0.8071734287546062,
+      "learning_rate": 5.06589525476014e-05,
+      "loss": 1.0287,
+      "step": 52
+    },
+    {
+      "epoch": 2.374829001367989,
+      "grad_norm": 1.290044073399014,
+      "learning_rate": 4.94303574203771e-05,
+      "loss": 1.04,
+      "step": 53
+    },
+    {
+      "epoch": 2.4186046511627906,
+      "grad_norm": 0.6470063533070358,
+      "learning_rate": 4.819226672260763e-05,
+      "loss": 1.0331,
+      "step": 54
+    },
+    {
+      "epoch": 2.462380300957592,
+      "grad_norm": 0.9069681051512629,
+      "learning_rate": 4.694592710667723e-05,
+      "loss": 1.0243,
+      "step": 55
+    },
+    {
+      "epoch": 2.506155950752394,
+      "grad_norm": 0.8654968713633596,
+      "learning_rate": 4.5692593530931416e-05,
+      "loss": 1.0052,
+      "step": 56
+    },
+    {
+      "epoch": 2.5499316005471955,
+      "grad_norm": 1.0033676935022624,
+      "learning_rate": 4.4433527996040443e-05,
+      "loss": 1.0299,
+      "step": 57
+    },
+    {
+      "epoch": 2.593707250341997,
+      "grad_norm": 0.6256956675554375,
+      "learning_rate": 4.316999827427154e-05,
+      "loss": 1.0344,
+      "step": 58
+    },
+    {
+      "epoch": 2.6374829001367988,
+      "grad_norm": 0.7160307755017002,
+      "learning_rate": 4.19032766329497e-05,
+      "loss": 1.0197,
+      "step": 59
+    },
+    {
+      "epoch": 2.6812585499316004,
+      "grad_norm": 0.7016377338794068,
+      "learning_rate": 4.063463855339232e-05,
+      "loss": 1.0142,
+      "step": 60
+    },
+    {
+      "epoch": 2.725034199726402,
+      "grad_norm": 0.5412134943726296,
+      "learning_rate": 3.9365361446607684e-05,
+      "loss": 1.0194,
+      "step": 61
+    },
+    {
+      "epoch": 2.7688098495212037,
+      "grad_norm": 0.5581535816981518,
+      "learning_rate": 3.809672336705031e-05,
+      "loss": 1.021,
+      "step": 62
+    },
+    {
+      "epoch": 2.8125854993160053,
+      "grad_norm": 0.4895297941884866,
+      "learning_rate": 3.683000172572846e-05,
+      "loss": 1.0145,
+      "step": 63
+    },
+    {
+      "epoch": 2.856361149110807,
+      "grad_norm": 0.5430942752350344,
+      "learning_rate": 3.556647200395956e-05,
+      "loss": 1.0159,
+      "step": 64
+    },
+    {
+      "epoch": 2.9001367989056086,
+      "grad_norm": 0.43778465011409384,
+      "learning_rate": 3.4307406469068604e-05,
+      "loss": 1.0037,
+      "step": 65
+    },
+    {
+      "epoch": 2.9439124487004102,
+      "grad_norm": 0.5574066963629686,
+      "learning_rate": 3.305407289332279e-05,
+      "loss": 1.0124,
+      "step": 66
+    },
+    {
+      "epoch": 3.015047879616963,
+      "grad_norm": 0.8597898186828361,
+      "learning_rate": 3.180773327739238e-05,
+      "loss": 1.8113,
+      "step": 67
+    },
+    {
+      "epoch": 3.0588235294117645,
+      "grad_norm": 0.7562084727521547,
+      "learning_rate": 3.0569642579622905e-05,
+      "loss": 0.9808,
+      "step": 68
+    },
+    {
+      "epoch": 3.102599179206566,
+      "grad_norm": 0.5467749248417106,
+      "learning_rate": 2.9341047452398607e-05,
+      "loss": 0.9786,
+      "step": 69
+    },
+    {
+      "epoch": 3.146374829001368,
+      "grad_norm": 0.7317552492863292,
+      "learning_rate": 2.8123184986869022e-05,
+      "loss": 0.9807,
+      "step": 70
+    },
+    {
+      "epoch": 3.19015047879617,
+      "grad_norm": 0.4988928521059118,
+      "learning_rate": 2.691728146730314e-05,
+      "loss": 0.9801,
+      "step": 71
+    },
+    {
+      "epoch": 3.233926128590971,
+      "grad_norm": 0.6214726877620874,
+      "learning_rate": 2.5724551136325132e-05,
+      "loss": 0.9752,
+      "step": 72
+    },
+    {
+      "epoch": 3.277701778385773,
+      "grad_norm": 0.5723924398692547,
+      "learning_rate": 2.4546194972274852e-05,
+      "loss": 0.9833,
+      "step": 73
+    },
+    {
+      "epoch": 3.3214774281805743,
+      "grad_norm": 0.3802903109677986,
+      "learning_rate": 2.338339947992455e-05,
+      "loss": 0.9704,
+      "step": 74
+    },
+    {
+      "epoch": 3.3652530779753764,
+      "grad_norm": 0.5679922591981417,
+      "learning_rate": 2.2237335495769035e-05,
+      "loss": 0.9832,
+      "step": 75
+    },
+    {
+      "epoch": 3.4090287277701776,
+      "grad_norm": 0.32921569959729985,
+      "learning_rate": 2.11091570090927e-05,
+      "loss": 0.9832,
+      "step": 76
+    },
+    {
+      "epoch": 3.4528043775649797,
+      "grad_norm": 0.41963134099051513,
+      "learning_rate": 2.0000000000000012e-05,
+      "loss": 0.9925,
+      "step": 77
+    },
+    {
+      "epoch": 3.496580027359781,
+      "grad_norm": 0.4216326585626274,
+      "learning_rate": 1.8910981295579903e-05,
+      "loss": 0.9693,
+      "step": 78
+    },
+    {
+      "epoch": 3.540355677154583,
+      "grad_norm": 0.281097341488956,
+      "learning_rate": 1.7843197445355593e-05,
+      "loss": 0.9687,
+      "step": 79
+    },
+    {
+      "epoch": 3.584131326949384,
+      "grad_norm": 0.34537711442895225,
+      "learning_rate": 1.679772361715208e-05,
+      "loss": 0.9792,
+      "step": 80
+    },
+    {
+      "epoch": 3.6279069767441863,
+      "grad_norm": 0.38729234396659473,
+      "learning_rate": 1.5775612514493343e-05,
+      "loss": 0.9716,
+      "step": 81
+    },
+    {
+      "epoch": 3.6716826265389875,
+      "grad_norm": 0.23216602871427763,
+      "learning_rate": 1.4777893316619114e-05,
+      "loss": 0.9791,
+      "step": 82
+    },
+    {
+      "epoch": 3.7154582763337896,
+      "grad_norm": 0.34978409677834293,
+      "learning_rate": 1.3805570642188602e-05,
+      "loss": 0.9686,
+      "step": 83
+    },
+    {
+      "epoch": 3.7592339261285908,
+      "grad_norm": 0.2917010744705113,
+      "learning_rate": 1.2859623537714719e-05,
+      "loss": 0.9674,
+      "step": 84
+    },
+    {
+      "epoch": 3.803009575923393,
+      "grad_norm": 0.2659722448857111,
+      "learning_rate": 1.1941004491747145e-05,
+      "loss": 0.9639,
+      "step": 85
+    },
+    {
+      "epoch": 3.846785225718194,
+      "grad_norm": 0.2936639116335773,
+      "learning_rate": 1.1050638475797193e-05,
+      "loss": 0.9609,
+      "step": 86
+    },
+    {
+      "epoch": 3.890560875512996,
+      "grad_norm": 0.22955492375415615,
+      "learning_rate": 1.0189422012969814e-05,
+      "loss": 0.9722,
+      "step": 87
+    },
+    {
+      "epoch": 3.9343365253077973,
+      "grad_norm": 0.20270732194600466,
+      "learning_rate": 9.358222275240884e-06,
+      "loss": 0.968,
+      "step": 88
+    },
+    {
+      "epoch": 4.00547195622435,
+      "grad_norm": 0.4286144089204306,
+      "learning_rate": 8.55787621028851e-06,
+      "loss": 1.746,
+      "step": 89
+    },
+    {
+      "epoch": 4.049247606019152,
+      "grad_norm": 0.156416222673832,
+      "learning_rate": 7.789189698757656e-06,
+      "loss": 0.9564,
+      "step": 90
+    },
+    {
+      "epoch": 4.093023255813954,
+      "grad_norm": 0.23495972177315438,
+      "learning_rate": 7.052936742806693e-06,
+      "loss": 0.9593,
+      "step": 91
+    },
+    {
+      "epoch": 4.136798905608755,
+      "grad_norm": 0.2226318621452638,
+      "learning_rate": 6.349858686752748e-06,
+      "loss": 0.9627,
+      "step": 92
+    },
+    {
+      "epoch": 4.180574555403557,
+      "grad_norm": 0.16215755051665368,
+      "learning_rate": 5.680663470600918e-06,
+      "loss": 0.9486,
+      "step": 93
+    },
+    {
+      "epoch": 4.224350205198358,
+      "grad_norm": 0.17528331588918997,
+      "learning_rate": 5.046024917208603e-06,
+      "loss": 0.9564,
+      "step": 94
+    },
+    {
+      "epoch": 4.26812585499316,
+      "grad_norm": 0.19247905962597153,
+      "learning_rate": 4.446582053803066e-06,
+      "loss": 0.9532,
+      "step": 95
+    },
+    {
+      "epoch": 4.311901504787961,
+      "grad_norm": 0.1497248018118723,
+      "learning_rate": 3.882938468535158e-06,
+      "loss": 0.9441,
+      "step": 96
+    },
+    {
+      "epoch": 4.3556771545827635,
+      "grad_norm": 0.1368167463262844,
+      "learning_rate": 3.3556617027172168e-06,
+      "loss": 0.9502,
+      "step": 97
+    },
+    {
+      "epoch": 4.399452804377565,
+      "grad_norm": 0.14584282376533797,
+      "learning_rate": 2.8652826793570975e-06,
+      "loss": 0.9499,
+      "step": 98
+    },
+    {
+      "epoch": 4.443228454172367,
+      "grad_norm": 0.1507749360921821,
+      "learning_rate": 2.4122951685636674e-06,
+      "loss": 0.9623,
+      "step": 99
+    },
+    {
+      "epoch": 4.487004103967168,
+      "grad_norm": 0.12741172341135956,
+      "learning_rate": 1.997155290362187e-06,
+      "loss": 0.9546,
+      "step": 100
+    },
+    {
+      "epoch": 4.53077975376197,
+      "grad_norm": 0.11988388634885762,
+      "learning_rate": 1.6202810554201099e-06,
+      "loss": 0.9634,
+      "step": 101
+    },
+    {
+      "epoch": 4.574555403556771,
+      "grad_norm": 0.10876564961414978,
+      "learning_rate": 1.2820519441457502e-06,
+      "loss": 0.9489,
+      "step": 102
+    },
+    {
+      "epoch": 4.618331053351573,
+      "grad_norm": 0.10280656448879005,
+      "learning_rate": 9.828085245837183e-07,
+      "loss": 0.9481,
+      "step": 103
+    },
+    {
+      "epoch": 4.6621067031463745,
+      "grad_norm": 0.10558127777006338,
+      "learning_rate": 7.228521094917318e-07,
+      "loss": 0.9517,
+      "step": 104
+    },
+    {
+      "epoch": 4.705882352941177,
+      "grad_norm": 0.10826937864073408,
+      "learning_rate": 5.024444529442285e-07,
+      "loss": 0.9544,
+      "step": 105
+    },
+    {
+      "epoch": 4.749658002735978,
+      "grad_norm": 0.10594923812863334,
+      "learning_rate": 3.218074867681864e-07,
+      "loss": 0.9384,
+      "step": 106
+    },
+    {
+      "epoch": 4.79343365253078,
+      "grad_norm": 0.10786116991531677,
+      "learning_rate": 1.8112309707661647e-07,
+      "loss": 0.943,
+      "step": 107
+    },
+    {
+      "epoch": 4.837209302325581,
+      "grad_norm": 0.11373942157615996,
+      "learning_rate": 8.053294112462696e-08,
+      "loss": 0.9525,
+      "step": 108
+    },
+    {
+      "epoch": 4.880984952120383,
+      "grad_norm": 0.10941188396825419,
+      "learning_rate": 2.01383046725967e-08,
+      "loss": 0.9539,
+      "step": 109
+    },
+    {
+      "epoch": 4.924760601915184,
+      "grad_norm": 0.10542013778303103,
+      "learning_rate": 0.0,
+      "loss": 0.9416,
+      "step": 110
+    },
+    {
+      "epoch": 4.924760601915184,
+      "step": 110,
+      "total_flos": 2.9249198798007173e+18,
+      "train_loss": 1.1118553096597845,
+      "train_runtime": 25822.1288,
+      "train_samples_per_second": 2.263,
+      "train_steps_per_second": 0.004
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 110,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.9249198798007173e+18,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70d589620e26aeac02c9bb7caad0f1a045bb944ec5c2eba0851376efa0bd1891
+size 7352