Upload folder using huggingface_hub

.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 +1,64 @@
+---
+library_name: transformers
+license: other
+base_model: Qwen/Qwen2.5-1.5B-Instruct
+tags:
+- llama-factory
+- full
+- generated_from_trainer
+model-index:
+- name: output
+  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. -->
+
+# output
+
+This model is a fine-tuned version of [Qwen/Qwen2.5-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-1.5B-Instruct) on the identity and the alpaca_en_demo datasets.
+It achieves the following results on the evaluation set:
+- Loss: 2.5144
+
+## 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: 1e-05
+- train_batch_size: 1
+- eval_batch_size: 1
+- seed: 42
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 8
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- training_steps: 1080
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 0.193         | 4.0775 | 500  | 1.6843          |
+| 0.0083        | 8.1549 | 1000 | 2.4750          |
+
+
+### Framework versions
+
+- Transformers 4.45.0
+- Pytorch 2.2.0+cu121
+- Datasets 2.21.0
+- Tokenizers 0.20.0

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 +1,12 @@
+{
+    "epoch": 8.807339449541285,
+    "eval_loss": 2.514443874359131,
+    "eval_runtime": 4.0149,
+    "eval_samples_per_second": 27.398,
+    "eval_steps_per_second": 27.398,
+    "total_flos": 1.2056852760477696e+16,
+    "train_loss": 0.3479360826589443,
+    "train_runtime": 1723.5404,
+    "train_samples_per_second": 5.013,
+    "train_steps_per_second": 0.627
+}

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "Qwen/Qwen2.5-1.5B-Instruct",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 1536,
+  "initializer_range": 0.02,
+  "intermediate_size": 8960,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 21,
+  "model_type": "qwen2",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 2,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.45.0",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 8.807339449541285,
+    "eval_loss": 2.514443874359131,
+    "eval_runtime": 4.0149,
+    "eval_samples_per_second": 27.398,
+    "eval_steps_per_second": 27.398
+}

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": 1.1,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.45.0"
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28bc109962b27fb63e116107e8689cc9aace55f013b8d8627a32ba63495d12db
+size 4996670464

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d7d5b9646b41538b0aead6c00bc3bc57e0dd13a466d71f4be00c0b6d1a5f9a7
+size 1178224960

model.safetensors.index.json

@@ -0,0 +1,345 @@
+{
+  "metadata": {
+    "total_size": 6174857216
+  },
+  "weight_map": {
+    "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.norm.weight": "model-00002-of-00002.safetensors"
+  }
+}

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 +1,208 @@
+{
+  "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": "<|im_end|>",
+  "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": 8.807339449541285,
+    "total_flos": 1.2056852760477696e+16,
+    "train_loss": 0.3479360826589443,
+    "train_runtime": 1723.5404,
+    "train_samples_per_second": 5.013,
+    "train_steps_per_second": 0.627
+}

trainer_log.jsonl

@@ -0,0 +1,111 @@
+{"current_steps": 10, "total_steps": 1080, "loss": 1.1833, "learning_rate": 9.259259259259259e-07, "epoch": 0.08154943934760449, "percentage": 0.93, "elapsed_time": "0:00:16", "remaining_time": "0:28:42"}
+{"current_steps": 20, "total_steps": 1080, "loss": 1.0856, "learning_rate": 1.8518518518518519e-06, "epoch": 0.16309887869520898, "percentage": 1.85, "elapsed_time": "0:00:31", "remaining_time": "0:28:02"}
+{"current_steps": 30, "total_steps": 1080, "loss": 1.0896, "learning_rate": 2.7777777777777783e-06, "epoch": 0.24464831804281345, "percentage": 2.78, "elapsed_time": "0:00:46", "remaining_time": "0:27:11"}
+{"current_steps": 40, "total_steps": 1080, "loss": 0.9945, "learning_rate": 3.7037037037037037e-06, "epoch": 0.32619775739041795, "percentage": 3.7, "elapsed_time": "0:01:01", "remaining_time": "0:26:38"}
+{"current_steps": 50, "total_steps": 1080, "loss": 1.0562, "learning_rate": 4.62962962962963e-06, "epoch": 0.4077471967380224, "percentage": 4.63, "elapsed_time": "0:01:16", "remaining_time": "0:26:10"}
+{"current_steps": 60, "total_steps": 1080, "loss": 1.0866, "learning_rate": 5.555555555555557e-06, "epoch": 0.4892966360856269, "percentage": 5.56, "elapsed_time": "0:01:31", "remaining_time": "0:25:49"}
+{"current_steps": 70, "total_steps": 1080, "loss": 1.151, "learning_rate": 6.481481481481482e-06, "epoch": 0.5708460754332314, "percentage": 6.48, "elapsed_time": "0:01:45", "remaining_time": "0:25:29"}
+{"current_steps": 80, "total_steps": 1080, "loss": 0.9591, "learning_rate": 7.4074074074074075e-06, "epoch": 0.6523955147808359, "percentage": 7.41, "elapsed_time": "0:02:00", "remaining_time": "0:25:11"}
+{"current_steps": 90, "total_steps": 1080, "loss": 1.1466, "learning_rate": 8.333333333333334e-06, "epoch": 0.7339449541284404, "percentage": 8.33, "elapsed_time": "0:02:15", "remaining_time": "0:24:54"}
+{"current_steps": 100, "total_steps": 1080, "loss": 1.0284, "learning_rate": 9.25925925925926e-06, "epoch": 0.8154943934760448, "percentage": 9.26, "elapsed_time": "0:02:30", "remaining_time": "0:24:36"}
+{"current_steps": 110, "total_steps": 1080, "loss": 1.2601, "learning_rate": 9.999895536228031e-06, "epoch": 0.8970438328236493, "percentage": 10.19, "elapsed_time": "0:02:44", "remaining_time": "0:24:14"}
+{"current_steps": 120, "total_steps": 1080, "loss": 1.1091, "learning_rate": 9.996239762521152e-06, "epoch": 0.9785932721712538, "percentage": 11.11, "elapsed_time": "0:02:59", "remaining_time": "0:23:55"}
+{"current_steps": 130, "total_steps": 1080, "loss": 0.9699, "learning_rate": 9.987365164467767e-06, "epoch": 1.0601427115188584, "percentage": 12.04, "elapsed_time": "0:03:14", "remaining_time": "0:23:41"}
+{"current_steps": 140, "total_steps": 1080, "loss": 0.8974, "learning_rate": 9.973281012033009e-06, "epoch": 1.1416921508664628, "percentage": 12.96, "elapsed_time": "0:03:29", "remaining_time": "0:23:25"}
+{"current_steps": 150, "total_steps": 1080, "loss": 0.9152, "learning_rate": 9.954002016824226e-06, "epoch": 1.2232415902140672, "percentage": 13.89, "elapsed_time": "0:03:44", "remaining_time": "0:23:12"}
+{"current_steps": 160, "total_steps": 1080, "loss": 0.8205, "learning_rate": 9.929548316723983e-06, "epoch": 1.3047910295616718, "percentage": 14.81, "elapsed_time": "0:03:59", "remaining_time": "0:22:56"}
+{"current_steps": 170, "total_steps": 1080, "loss": 0.852, "learning_rate": 9.899945454855007e-06, "epoch": 1.3863404689092762, "percentage": 15.74, "elapsed_time": "0:04:14", "remaining_time": "0:22:42"}
+{"current_steps": 180, "total_steps": 1080, "loss": 0.7172, "learning_rate": 9.86522435289912e-06, "epoch": 1.4678899082568808, "percentage": 16.67, "elapsed_time": "0:04:29", "remaining_time": "0:22:27"}
+{"current_steps": 190, "total_steps": 1080, "loss": 0.7586, "learning_rate": 9.825421278797984e-06, "epoch": 1.5494393476044852, "percentage": 17.59, "elapsed_time": "0:04:44", "remaining_time": "0:22:12"}
+{"current_steps": 200, "total_steps": 1080, "loss": 0.802, "learning_rate": 9.7805778088694e-06, "epoch": 1.6309887869520896, "percentage": 18.52, "elapsed_time": "0:04:59", "remaining_time": "0:21:59"}
+{"current_steps": 210, "total_steps": 1080, "loss": 0.8788, "learning_rate": 9.730740784378755e-06, "epoch": 1.7125382262996942, "percentage": 19.44, "elapsed_time": "0:05:15", "remaining_time": "0:21:46"}
+{"current_steps": 220, "total_steps": 1080, "loss": 0.8143, "learning_rate": 9.67596226261095e-06, "epoch": 1.7940876656472988, "percentage": 20.37, "elapsed_time": "0:05:30", "remaining_time": "0:21:33"}
+{"current_steps": 230, "total_steps": 1080, "loss": 0.8228, "learning_rate": 9.616299462493952e-06, "epoch": 1.8756371049949032, "percentage": 21.3, "elapsed_time": "0:05:45", "remaining_time": "0:21:18"}
+{"current_steps": 240, "total_steps": 1080, "loss": 0.7194, "learning_rate": 9.551814704830734e-06, "epoch": 1.9571865443425076, "percentage": 22.22, "elapsed_time": "0:06:01", "remaining_time": "0:21:04"}
+{"current_steps": 250, "total_steps": 1080, "loss": 0.6792, "learning_rate": 9.482575347202047e-06, "epoch": 2.038735983690112, "percentage": 23.15, "elapsed_time": "0:06:16", "remaining_time": "0:20:50"}
+{"current_steps": 260, "total_steps": 1080, "loss": 0.5799, "learning_rate": 9.40865371360804e-06, "epoch": 2.120285423037717, "percentage": 24.07, "elapsed_time": "0:06:33", "remaining_time": "0:20:39"}
+{"current_steps": 270, "total_steps": 1080, "loss": 0.5307, "learning_rate": 9.330127018922195e-06, "epoch": 2.2018348623853212, "percentage": 25.0, "elapsed_time": "0:06:49", "remaining_time": "0:20:27"}
+{"current_steps": 280, "total_steps": 1080, "loss": 0.5052, "learning_rate": 9.247077288236488e-06, "epoch": 2.2833843017329256, "percentage": 25.93, "elapsed_time": "0:07:04", "remaining_time": "0:20:13"}
+{"current_steps": 290, "total_steps": 1080, "loss": 0.4944, "learning_rate": 9.159591271182058e-06, "epoch": 2.36493374108053, "percentage": 26.85, "elapsed_time": "0:07:20", "remaining_time": "0:19:59"}
+{"current_steps": 300, "total_steps": 1080, "loss": 0.5803, "learning_rate": 9.067760351314838e-06, "epoch": 2.4464831804281344, "percentage": 27.78, "elapsed_time": "0:07:36", "remaining_time": "0:19:46"}
+{"current_steps": 310, "total_steps": 1080, "loss": 0.4859, "learning_rate": 8.97168045066082e-06, "epoch": 2.528032619775739, "percentage": 28.7, "elapsed_time": "0:07:52", "remaining_time": "0:19:33"}
+{"current_steps": 320, "total_steps": 1080, "loss": 0.5261, "learning_rate": 8.871451929520662e-06, "epoch": 2.6095820591233436, "percentage": 29.63, "elapsed_time": "0:08:08", "remaining_time": "0:19:19"}
+{"current_steps": 330, "total_steps": 1080, "loss": 0.5705, "learning_rate": 8.767179481638303e-06, "epoch": 2.691131498470948, "percentage": 30.56, "elapsed_time": "0:08:23", "remaining_time": "0:19:05"}
+{"current_steps": 340, "total_steps": 1080, "loss": 0.5248, "learning_rate": 8.658972024843063e-06, "epoch": 2.7726809378185524, "percentage": 31.48, "elapsed_time": "0:08:39", "remaining_time": "0:18:50"}
+{"current_steps": 350, "total_steps": 1080, "loss": 0.4764, "learning_rate": 8.546942587279465e-06, "epoch": 2.8542303771661572, "percentage": 32.41, "elapsed_time": "0:08:54", "remaining_time": "0:18:35"}
+{"current_steps": 360, "total_steps": 1080, "loss": 0.5481, "learning_rate": 8.43120818934367e-06, "epoch": 2.9357798165137616, "percentage": 33.33, "elapsed_time": "0:09:10", "remaining_time": "0:18:20"}
+{"current_steps": 370, "total_steps": 1080, "loss": 0.4215, "learning_rate": 8.31188972144974e-06, "epoch": 3.017329255861366, "percentage": 34.26, "elapsed_time": "0:09:25", "remaining_time": "0:18:04"}
+{"current_steps": 380, "total_steps": 1080, "loss": 0.3038, "learning_rate": 8.18911181775353e-06, "epoch": 3.0988786952089704, "percentage": 35.19, "elapsed_time": "0:09:40", "remaining_time": "0:17:49"}
+{"current_steps": 390, "total_steps": 1080, "loss": 0.3173, "learning_rate": 8.063002725966014e-06, "epoch": 3.180428134556575, "percentage": 36.11, "elapsed_time": "0:09:56", "remaining_time": "0:17:34"}
+{"current_steps": 400, "total_steps": 1080, "loss": 0.3345, "learning_rate": 7.93369417339209e-06, "epoch": 3.261977573904179, "percentage": 37.04, "elapsed_time": "0:10:11", "remaining_time": "0:17:18"}
+{"current_steps": 410, "total_steps": 1080, "loss": 0.3165, "learning_rate": 7.801321229334764e-06, "epoch": 3.343527013251784, "percentage": 37.96, "elapsed_time": "0:10:26", "remaining_time": "0:17:04"}
+{"current_steps": 420, "total_steps": 1080, "loss": 0.2921, "learning_rate": 7.666022164008458e-06, "epoch": 3.4250764525993884, "percentage": 38.89, "elapsed_time": "0:10:42", "remaining_time": "0:16:50"}
+{"current_steps": 430, "total_steps": 1080, "loss": 0.3062, "learning_rate": 7.527938304108795e-06, "epoch": 3.506625891946993, "percentage": 39.81, "elapsed_time": "0:10:57", "remaining_time": "0:16:34"}
+{"current_steps": 440, "total_steps": 1080, "loss": 0.2924, "learning_rate": 7.387213885189746e-06, "epoch": 3.588175331294597, "percentage": 40.74, "elapsed_time": "0:11:13", "remaining_time": "0:16:19"}
+{"current_steps": 450, "total_steps": 1080, "loss": 0.2929, "learning_rate": 7.243995901002312e-06, "epoch": 3.669724770642202, "percentage": 41.67, "elapsed_time": "0:11:28", "remaining_time": "0:16:03"}
+{"current_steps": 460, "total_steps": 1080, "loss": 0.3544, "learning_rate": 7.098433949952146e-06, "epoch": 3.7512742099898064, "percentage": 42.59, "elapsed_time": "0:11:43", "remaining_time": "0:15:48"}
+{"current_steps": 470, "total_steps": 1080, "loss": 0.3103, "learning_rate": 6.950680078836475e-06, "epoch": 3.832823649337411, "percentage": 43.52, "elapsed_time": "0:11:58", "remaining_time": "0:15:32"}
+{"current_steps": 480, "total_steps": 1080, "loss": 0.2742, "learning_rate": 6.800888624023552e-06, "epoch": 3.914373088685015, "percentage": 44.44, "elapsed_time": "0:12:13", "remaining_time": "0:15:17"}
+{"current_steps": 490, "total_steps": 1080, "loss": 0.3339, "learning_rate": 6.649216050240539e-06, "epoch": 3.9959225280326196, "percentage": 45.37, "elapsed_time": "0:12:29", "remaining_time": "0:15:02"}
+{"current_steps": 500, "total_steps": 1080, "loss": 0.193, "learning_rate": 6.495820787138209e-06, "epoch": 4.077471967380224, "percentage": 46.3, "elapsed_time": "0:12:45", "remaining_time": "0:14:47"}
+{"current_steps": 500, "total_steps": 1080, "eval_loss": 1.6843377351760864, "epoch": 4.077471967380224, "percentage": 46.3, "elapsed_time": "0:12:49", "remaining_time": "0:14:52"}
+{"current_steps": 510, "total_steps": 1080, "loss": 0.2102, "learning_rate": 6.340863063803187e-06, "epoch": 4.159021406727828, "percentage": 47.22, "elapsed_time": "0:13:24", "remaining_time": "0:14:59"}
+{"current_steps": 520, "total_steps": 1080, "loss": 0.1799, "learning_rate": 6.184504741390596e-06, "epoch": 4.240570846075434, "percentage": 48.15, "elapsed_time": "0:13:39", "remaining_time": "0:14:43"}
+{"current_steps": 530, "total_steps": 1080, "loss": 0.1945, "learning_rate": 6.02690914405191e-06, "epoch": 4.322120285423038, "percentage": 49.07, "elapsed_time": "0:13:55", "remaining_time": "0:14:27"}
+{"current_steps": 540, "total_steps": 1080, "loss": 0.1186, "learning_rate": 5.8682408883346535e-06, "epoch": 4.4036697247706424, "percentage": 50.0, "elapsed_time": "0:14:10", "remaining_time": "0:14:10"}
+{"current_steps": 550, "total_steps": 1080, "loss": 0.1761, "learning_rate": 5.708665711232103e-06, "epoch": 4.485219164118247, "percentage": 50.93, "elapsed_time": "0:14:26", "remaining_time": "0:13:54"}
+{"current_steps": 560, "total_steps": 1080, "loss": 0.1747, "learning_rate": 5.548350297062659e-06, "epoch": 4.566768603465851, "percentage": 51.85, "elapsed_time": "0:14:41", "remaining_time": "0:13:38"}
+{"current_steps": 570, "total_steps": 1080, "loss": 0.205, "learning_rate": 5.387462103359655e-06, "epoch": 4.648318042813456, "percentage": 52.78, "elapsed_time": "0:14:56", "remaining_time": "0:13:22"}
+{"current_steps": 580, "total_steps": 1080, "loss": 0.1384, "learning_rate": 5.2261691859535325e-06, "epoch": 4.72986748216106, "percentage": 53.7, "elapsed_time": "0:15:11", "remaining_time": "0:13:06"}
+{"current_steps": 590, "total_steps": 1080, "loss": 0.1475, "learning_rate": 5.064640023429042e-06, "epoch": 4.811416921508664, "percentage": 54.63, "elapsed_time": "0:15:27", "remaining_time": "0:12:49"}
+{"current_steps": 600, "total_steps": 1080, "loss": 0.1647, "learning_rate": 4.903043341140879e-06, "epoch": 4.892966360856269, "percentage": 55.56, "elapsed_time": "0:15:42", "remaining_time": "0:12:33"}
+{"current_steps": 610, "total_steps": 1080, "loss": 0.1691, "learning_rate": 4.741547934971528e-06, "epoch": 4.974515800203873, "percentage": 56.48, "elapsed_time": "0:15:57", "remaining_time": "0:12:17"}
+{"current_steps": 620, "total_steps": 1080, "loss": 0.1022, "learning_rate": 4.580322495015466e-06, "epoch": 5.0560652395514785, "percentage": 57.41, "elapsed_time": "0:16:13", "remaining_time": "0:12:02"}
+{"current_steps": 630, "total_steps": 1080, "loss": 0.0677, "learning_rate": 4.4195354293738484e-06, "epoch": 5.137614678899083, "percentage": 58.33, "elapsed_time": "0:16:28", "remaining_time": "0:11:45"}
+{"current_steps": 640, "total_steps": 1080, "loss": 0.0761, "learning_rate": 4.259354688243758e-06, "epoch": 5.219164118246687, "percentage": 59.26, "elapsed_time": "0:16:43", "remaining_time": "0:11:30"}
+{"current_steps": 650, "total_steps": 1080, "loss": 0.0733, "learning_rate": 4.099947588485744e-06, "epoch": 5.300713557594292, "percentage": 60.19, "elapsed_time": "0:16:58", "remaining_time": "0:11:13"}
+{"current_steps": 660, "total_steps": 1080, "loss": 0.0841, "learning_rate": 3.941480638852948e-06, "epoch": 5.382262996941896, "percentage": 61.11, "elapsed_time": "0:17:13", "remaining_time": "0:10:57"}
+{"current_steps": 670, "total_steps": 1080, "loss": 0.0929, "learning_rate": 3.784119366064293e-06, "epoch": 5.4638124362895, "percentage": 62.04, "elapsed_time": "0:17:29", "remaining_time": "0:10:42"}
+{"current_steps": 680, "total_steps": 1080, "loss": 0.0634, "learning_rate": 3.6280281419034934e-06, "epoch": 5.545361875637105, "percentage": 62.96, "elapsed_time": "0:17:44", "remaining_time": "0:10:26"}
+{"current_steps": 690, "total_steps": 1080, "loss": 0.1201, "learning_rate": 3.473370011524435e-06, "epoch": 5.626911314984709, "percentage": 63.89, "elapsed_time": "0:18:00", "remaining_time": "0:10:10"}
+{"current_steps": 700, "total_steps": 1080, "loss": 0.0811, "learning_rate": 3.3203065231422904e-06, "epoch": 5.708460754332314, "percentage": 64.81, "elapsed_time": "0:18:15", "remaining_time": "0:09:54"}
+{"current_steps": 710, "total_steps": 1080, "loss": 0.0708, "learning_rate": 3.1689975592882603e-06, "epoch": 5.790010193679919, "percentage": 65.74, "elapsed_time": "0:18:30", "remaining_time": "0:09:38"}
+{"current_steps": 720, "total_steps": 1080, "loss": 0.0846, "learning_rate": 3.019601169804216e-06, "epoch": 5.871559633027523, "percentage": 66.67, "elapsed_time": "0:18:46", "remaining_time": "0:09:23"}
+{"current_steps": 730, "total_steps": 1080, "loss": 0.0782, "learning_rate": 2.8722734067516637e-06, "epoch": 5.953109072375128, "percentage": 67.59, "elapsed_time": "0:19:01", "remaining_time": "0:09:07"}
+{"current_steps": 740, "total_steps": 1080, "loss": 0.0624, "learning_rate": 2.7271681614074973e-06, "epoch": 6.034658511722732, "percentage": 68.52, "elapsed_time": "0:19:16", "remaining_time": "0:08:51"}
+{"current_steps": 750, "total_steps": 1080, "loss": 0.0373, "learning_rate": 2.5844370035168077e-06, "epoch": 6.116207951070336, "percentage": 69.44, "elapsed_time": "0:19:32", "remaining_time": "0:08:35"}
+{"current_steps": 760, "total_steps": 1080, "loss": 0.0331, "learning_rate": 2.4442290229706344e-06, "epoch": 6.197757390417941, "percentage": 70.37, "elapsed_time": "0:19:47", "remaining_time": "0:08:19"}
+{"current_steps": 770, "total_steps": 1080, "loss": 0.0232, "learning_rate": 2.3066906740740626e-06, "epoch": 6.279306829765545, "percentage": 71.3, "elapsed_time": "0:20:02", "remaining_time": "0:08:04"}
+{"current_steps": 780, "total_steps": 1080, "loss": 0.0356, "learning_rate": 2.171965622567308e-06, "epoch": 6.36085626911315, "percentage": 72.22, "elapsed_time": "0:20:17", "remaining_time": "0:07:48"}
+{"current_steps": 790, "total_steps": 1080, "loss": 0.0599, "learning_rate": 2.0401945955596206e-06, "epoch": 6.442405708460754, "percentage": 73.15, "elapsed_time": "0:20:33", "remaining_time": "0:07:32"}
+{"current_steps": 800, "total_steps": 1080, "loss": 0.0298, "learning_rate": 1.9115152345327154e-06, "epoch": 6.523955147808358, "percentage": 74.07, "elapsed_time": "0:20:48", "remaining_time": "0:07:16"}
+{"current_steps": 810, "total_steps": 1080, "loss": 0.029, "learning_rate": 1.7860619515673034e-06, "epoch": 6.605504587155964, "percentage": 75.0, "elapsed_time": "0:21:03", "remaining_time": "0:07:01"}
+{"current_steps": 820, "total_steps": 1080, "loss": 0.0322, "learning_rate": 1.6639657889429017e-06, "epoch": 6.687054026503568, "percentage": 75.93, "elapsed_time": "0:21:19", "remaining_time": "0:06:45"}
+{"current_steps": 830, "total_steps": 1080, "loss": 0.0276, "learning_rate": 1.5453542822575624e-06, "epoch": 6.7686034658511725, "percentage": 76.85, "elapsed_time": "0:21:34", "remaining_time": "0:06:29"}
+{"current_steps": 840, "total_steps": 1080, "loss": 0.0307, "learning_rate": 1.4303513272105057e-06, "epoch": 6.850152905198777, "percentage": 77.78, "elapsed_time": "0:21:49", "remaining_time": "0:06:14"}
+{"current_steps": 850, "total_steps": 1080, "loss": 0.0439, "learning_rate": 1.3190770501868243e-06, "epoch": 6.931702344546381, "percentage": 78.7, "elapsed_time": "0:22:04", "remaining_time": "0:05:58"}
+{"current_steps": 860, "total_steps": 1080, "loss": 0.0349, "learning_rate": 1.2116476827794104e-06, "epoch": 7.013251783893986, "percentage": 79.63, "elapsed_time": "0:22:19", "remaining_time": "0:05:42"}
+{"current_steps": 870, "total_steps": 1080, "loss": 0.0141, "learning_rate": 1.1081754403792e-06, "epoch": 7.09480122324159, "percentage": 80.56, "elapsed_time": "0:22:34", "remaining_time": "0:05:26"}
+{"current_steps": 880, "total_steps": 1080, "loss": 0.0131, "learning_rate": 1.008768404960535e-06, "epoch": 7.176350662589194, "percentage": 81.48, "elapsed_time": "0:22:49", "remaining_time": "0:05:11"}
+{"current_steps": 890, "total_steps": 1080, "loss": 0.0156, "learning_rate": 9.135304121840976e-07, "epoch": 7.257900101936799, "percentage": 82.41, "elapsed_time": "0:23:04", "remaining_time": "0:04:55"}
+{"current_steps": 900, "total_steps": 1080, "loss": 0.0129, "learning_rate": 8.225609429353187e-07, "epoch": 7.339449541284404, "percentage": 83.33, "elapsed_time": "0:23:19", "remaining_time": "0:04:39"}
+{"current_steps": 910, "total_steps": 1080, "loss": 0.0142, "learning_rate": 7.35955019411585e-07, "epoch": 7.4209989806320085, "percentage": 84.26, "elapsed_time": "0:23:35", "remaining_time": "0:04:24"}
+{"current_steps": 920, "total_steps": 1080, "loss": 0.0103, "learning_rate": 6.53803105866761e-07, "epoch": 7.502548419979613, "percentage": 85.19, "elapsed_time": "0:23:50", "remaining_time": "0:04:08"}
+{"current_steps": 930, "total_steps": 1080, "loss": 0.0166, "learning_rate": 5.76191014116711e-07, "epoch": 7.584097859327217, "percentage": 86.11, "elapsed_time": "0:24:05", "remaining_time": "0:03:53"}
+{"current_steps": 940, "total_steps": 1080, "loss": 0.0144, "learning_rate": 5.031998139045352e-07, "epoch": 7.665647298674822, "percentage": 87.04, "elapsed_time": "0:24:21", "remaining_time": "0:03:37"}
+{"current_steps": 950, "total_steps": 1080, "loss": 0.0165, "learning_rate": 4.349057482191299e-07, "epoch": 7.747196738022426, "percentage": 87.96, "elapsed_time": "0:24:36", "remaining_time": "0:03:22"}
+{"current_steps": 960, "total_steps": 1080, "loss": 0.0118, "learning_rate": 3.7138015365554834e-07, "epoch": 7.82874617737003, "percentage": 88.89, "elapsed_time": "0:24:51", "remaining_time": "0:03:06"}
+{"current_steps": 970, "total_steps": 1080, "loss": 0.0141, "learning_rate": 3.1268938590032495e-07, "epoch": 7.910295616717635, "percentage": 89.81, "elapsed_time": "0:25:07", "remaining_time": "0:02:50"}
+{"current_steps": 980, "total_steps": 1080, "loss": 0.0096, "learning_rate": 2.5889475041961767e-07, "epoch": 7.991845056065239, "percentage": 90.74, "elapsed_time": "0:25:22", "remaining_time": "0:02:35"}
+{"current_steps": 990, "total_steps": 1080, "loss": 0.0207, "learning_rate": 2.1005243842255552e-07, "epoch": 8.073394495412844, "percentage": 91.67, "elapsed_time": "0:25:38", "remaining_time": "0:02:19"}
+{"current_steps": 1000, "total_steps": 1080, "loss": 0.0083, "learning_rate": 1.6621346816668993e-07, "epoch": 8.154943934760448, "percentage": 92.59, "elapsed_time": "0:25:53", "remaining_time": "0:02:04"}
+{"current_steps": 1000, "total_steps": 1080, "eval_loss": 2.4749834537506104, "epoch": 8.154943934760448, "percentage": 92.59, "elapsed_time": "0:25:57", "remaining_time": "0:02:04"}
+{"current_steps": 1010, "total_steps": 1080, "loss": 0.0084, "learning_rate": 1.2742363166685035e-07, "epoch": 8.236493374108052, "percentage": 93.52, "elapsed_time": "0:26:32", "remaining_time": "0:01:50"}
+{"current_steps": 1020, "total_steps": 1080, "loss": 0.0065, "learning_rate": 9.372344686307655e-08, "epoch": 8.318042813455657, "percentage": 94.44, "elapsed_time": "0:26:47", "remaining_time": "0:01:34"}
+{"current_steps": 1030, "total_steps": 1080, "loss": 0.0116, "learning_rate": 6.514811529758747e-08, "epoch": 8.399592252803261, "percentage": 95.37, "elapsed_time": "0:27:02", "remaining_time": "0:01:18"}
+{"current_steps": 1040, "total_steps": 1080, "loss": 0.0108, "learning_rate": 4.172748534499449e-08, "epoch": 8.481141692150867, "percentage": 96.3, "elapsed_time": "0:27:17", "remaining_time": "0:01:02"}
+{"current_steps": 1050, "total_steps": 1080, "loss": 0.0088, "learning_rate": 2.3486021034170857e-08, "epoch": 8.562691131498472, "percentage": 97.22, "elapsed_time": "0:27:33", "remaining_time": "0:00:47"}
+{"current_steps": 1060, "total_steps": 1080, "loss": 0.0086, "learning_rate": 1.044277649433989e-08, "epoch": 8.644240570846076, "percentage": 98.15, "elapsed_time": "0:27:48", "remaining_time": "0:00:31"}
+{"current_steps": 1070, "total_steps": 1080, "loss": 0.0086, "learning_rate": 2.611376052073511e-09, "epoch": 8.72579001019368, "percentage": 99.07, "elapsed_time": "0:28:04", "remaining_time": "0:00:15"}
+{"current_steps": 1080, "total_steps": 1080, "loss": 0.0063, "learning_rate": 0.0, "epoch": 8.807339449541285, "percentage": 100.0, "elapsed_time": "0:28:19", "remaining_time": "0:00:00"}
+{"current_steps": 1080, "total_steps": 1080, "epoch": 8.807339449541285, "percentage": 100.0, "elapsed_time": "0:28:42", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,814 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 8.807339449541285,
+  "eval_steps": 500,
+  "global_step": 1080,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.08154943934760449,
+      "grad_norm": 12.287543296813965,
+      "learning_rate": 9.259259259259259e-07,
+      "loss": 1.1833,
+      "step": 10
+    },
+    {
+      "epoch": 0.16309887869520898,
+      "grad_norm": 11.78052043914795,
+      "learning_rate": 1.8518518518518519e-06,
+      "loss": 1.0856,
+      "step": 20
+    },
+    {
+      "epoch": 0.24464831804281345,
+      "grad_norm": 15.526741981506348,
+      "learning_rate": 2.7777777777777783e-06,
+      "loss": 1.0896,
+      "step": 30
+    },
+    {
+      "epoch": 0.32619775739041795,
+      "grad_norm": 8.213525772094727,
+      "learning_rate": 3.7037037037037037e-06,
+      "loss": 0.9945,
+      "step": 40
+    },
+    {
+      "epoch": 0.4077471967380224,
+      "grad_norm": 12.257412910461426,
+      "learning_rate": 4.62962962962963e-06,
+      "loss": 1.0562,
+      "step": 50
+    },
+    {
+      "epoch": 0.4892966360856269,
+      "grad_norm": 8.546279907226562,
+      "learning_rate": 5.555555555555557e-06,
+      "loss": 1.0866,
+      "step": 60
+    },
+    {
+      "epoch": 0.5708460754332314,
+      "grad_norm": 13.490253448486328,
+      "learning_rate": 6.481481481481482e-06,
+      "loss": 1.151,
+      "step": 70
+    },
+    {
+      "epoch": 0.6523955147808359,
+      "grad_norm": 19.235937118530273,
+      "learning_rate": 7.4074074074074075e-06,
+      "loss": 0.9591,
+      "step": 80
+    },
+    {
+      "epoch": 0.7339449541284404,
+      "grad_norm": 6.614363193511963,
+      "learning_rate": 8.333333333333334e-06,
+      "loss": 1.1466,
+      "step": 90
+    },
+    {
+      "epoch": 0.8154943934760448,
+      "grad_norm": 9.026179313659668,
+      "learning_rate": 9.25925925925926e-06,
+      "loss": 1.0284,
+      "step": 100
+    },
+    {
+      "epoch": 0.8970438328236493,
+      "grad_norm": 10.798940658569336,
+      "learning_rate": 9.999895536228031e-06,
+      "loss": 1.2601,
+      "step": 110
+    },
+    {
+      "epoch": 0.9785932721712538,
+      "grad_norm": 9.451533317565918,
+      "learning_rate": 9.996239762521152e-06,
+      "loss": 1.1091,
+      "step": 120
+    },
+    {
+      "epoch": 1.0601427115188584,
+      "grad_norm": 6.230576992034912,
+      "learning_rate": 9.987365164467767e-06,
+      "loss": 0.9699,
+      "step": 130
+    },
+    {
+      "epoch": 1.1416921508664628,
+      "grad_norm": 7.345333099365234,
+      "learning_rate": 9.973281012033009e-06,
+      "loss": 0.8974,
+      "step": 140
+    },
+    {
+      "epoch": 1.2232415902140672,
+      "grad_norm": 8.226116180419922,
+      "learning_rate": 9.954002016824226e-06,
+      "loss": 0.9152,
+      "step": 150
+    },
+    {
+      "epoch": 1.3047910295616718,
+      "grad_norm": 5.226821422576904,
+      "learning_rate": 9.929548316723983e-06,
+      "loss": 0.8205,
+      "step": 160
+    },
+    {
+      "epoch": 1.3863404689092762,
+      "grad_norm": 14.963723182678223,
+      "learning_rate": 9.899945454855007e-06,
+      "loss": 0.852,
+      "step": 170
+    },
+    {
+      "epoch": 1.4678899082568808,
+      "grad_norm": 6.257207870483398,
+      "learning_rate": 9.86522435289912e-06,
+      "loss": 0.7172,
+      "step": 180
+    },
+    {
+      "epoch": 1.5494393476044852,
+      "grad_norm": 5.380673885345459,
+      "learning_rate": 9.825421278797984e-06,
+      "loss": 0.7586,
+      "step": 190
+    },
+    {
+      "epoch": 1.6309887869520896,
+      "grad_norm": 6.626143455505371,
+      "learning_rate": 9.7805778088694e-06,
+      "loss": 0.802,
+      "step": 200
+    },
+    {
+      "epoch": 1.7125382262996942,
+      "grad_norm": 5.537201881408691,
+      "learning_rate": 9.730740784378755e-06,
+      "loss": 0.8788,
+      "step": 210
+    },
+    {
+      "epoch": 1.7940876656472988,
+      "grad_norm": 14.645645141601562,
+      "learning_rate": 9.67596226261095e-06,
+      "loss": 0.8143,
+      "step": 220
+    },
+    {
+      "epoch": 1.8756371049949032,
+      "grad_norm": 5.771991729736328,
+      "learning_rate": 9.616299462493952e-06,
+      "loss": 0.8228,
+      "step": 230
+    },
+    {
+      "epoch": 1.9571865443425076,
+      "grad_norm": 7.7364091873168945,
+      "learning_rate": 9.551814704830734e-06,
+      "loss": 0.7194,
+      "step": 240
+    },
+    {
+      "epoch": 2.038735983690112,
+      "grad_norm": 7.201632499694824,
+      "learning_rate": 9.482575347202047e-06,
+      "loss": 0.6792,
+      "step": 250
+    },
+    {
+      "epoch": 2.120285423037717,
+      "grad_norm": 10.6597318649292,
+      "learning_rate": 9.40865371360804e-06,
+      "loss": 0.5799,
+      "step": 260
+    },
+    {
+      "epoch": 2.2018348623853212,
+      "grad_norm": 5.66484260559082,
+      "learning_rate": 9.330127018922195e-06,
+      "loss": 0.5307,
+      "step": 270
+    },
+    {
+      "epoch": 2.2833843017329256,
+      "grad_norm": 11.373878479003906,
+      "learning_rate": 9.247077288236488e-06,
+      "loss": 0.5052,
+      "step": 280
+    },
+    {
+      "epoch": 2.36493374108053,
+      "grad_norm": 7.9306864738464355,
+      "learning_rate": 9.159591271182058e-06,
+      "loss": 0.4944,
+      "step": 290
+    },
+    {
+      "epoch": 2.4464831804281344,
+      "grad_norm": 4.888540267944336,
+      "learning_rate": 9.067760351314838e-06,
+      "loss": 0.5803,
+      "step": 300
+    },
+    {
+      "epoch": 2.528032619775739,
+      "grad_norm": 5.445197582244873,
+      "learning_rate": 8.97168045066082e-06,
+      "loss": 0.4859,
+      "step": 310
+    },
+    {
+      "epoch": 2.6095820591233436,
+      "grad_norm": 6.764598369598389,
+      "learning_rate": 8.871451929520662e-06,
+      "loss": 0.5261,
+      "step": 320
+    },
+    {
+      "epoch": 2.691131498470948,
+      "grad_norm": 4.372009754180908,
+      "learning_rate": 8.767179481638303e-06,
+      "loss": 0.5705,
+      "step": 330
+    },
+    {
+      "epoch": 2.7726809378185524,
+      "grad_norm": 5.150655746459961,
+      "learning_rate": 8.658972024843063e-06,
+      "loss": 0.5248,
+      "step": 340
+    },
+    {
+      "epoch": 2.8542303771661572,
+      "grad_norm": 7.280877590179443,
+      "learning_rate": 8.546942587279465e-06,
+      "loss": 0.4764,
+      "step": 350
+    },
+    {
+      "epoch": 2.9357798165137616,
+      "grad_norm": 6.407410621643066,
+      "learning_rate": 8.43120818934367e-06,
+      "loss": 0.5481,
+      "step": 360
+    },
+    {
+      "epoch": 3.017329255861366,
+      "grad_norm": 3.3497812747955322,
+      "learning_rate": 8.31188972144974e-06,
+      "loss": 0.4215,
+      "step": 370
+    },
+    {
+      "epoch": 3.0988786952089704,
+      "grad_norm": 8.869242668151855,
+      "learning_rate": 8.18911181775353e-06,
+      "loss": 0.3038,
+      "step": 380
+    },
+    {
+      "epoch": 3.180428134556575,
+      "grad_norm": 7.462818622589111,
+      "learning_rate": 8.063002725966014e-06,
+      "loss": 0.3173,
+      "step": 390
+    },
+    {
+      "epoch": 3.261977573904179,
+      "grad_norm": 4.446223258972168,
+      "learning_rate": 7.93369417339209e-06,
+      "loss": 0.3345,
+      "step": 400
+    },
+    {
+      "epoch": 3.343527013251784,
+      "grad_norm": 4.583369255065918,
+      "learning_rate": 7.801321229334764e-06,
+      "loss": 0.3165,
+      "step": 410
+    },
+    {
+      "epoch": 3.4250764525993884,
+      "grad_norm": 3.839564323425293,
+      "learning_rate": 7.666022164008458e-06,
+      "loss": 0.2921,
+      "step": 420
+    },
+    {
+      "epoch": 3.506625891946993,
+      "grad_norm": 3.111229181289673,
+      "learning_rate": 7.527938304108795e-06,
+      "loss": 0.3062,
+      "step": 430
+    },
+    {
+      "epoch": 3.588175331294597,
+      "grad_norm": 4.569026470184326,
+      "learning_rate": 7.387213885189746e-06,
+      "loss": 0.2924,
+      "step": 440
+    },
+    {
+      "epoch": 3.669724770642202,
+      "grad_norm": 6.843806266784668,
+      "learning_rate": 7.243995901002312e-06,
+      "loss": 0.2929,
+      "step": 450
+    },
+    {
+      "epoch": 3.7512742099898064,
+      "grad_norm": 3.574108839035034,
+      "learning_rate": 7.098433949952146e-06,
+      "loss": 0.3544,
+      "step": 460
+    },
+    {
+      "epoch": 3.832823649337411,
+      "grad_norm": 3.691032886505127,
+      "learning_rate": 6.950680078836475e-06,
+      "loss": 0.3103,
+      "step": 470
+    },
+    {
+      "epoch": 3.914373088685015,
+      "grad_norm": 3.9971020221710205,
+      "learning_rate": 6.800888624023552e-06,
+      "loss": 0.2742,
+      "step": 480
+    },
+    {
+      "epoch": 3.9959225280326196,
+      "grad_norm": 2.556887149810791,
+      "learning_rate": 6.649216050240539e-06,
+      "loss": 0.3339,
+      "step": 490
+    },
+    {
+      "epoch": 4.077471967380224,
+      "grad_norm": 2.1896212100982666,
+      "learning_rate": 6.495820787138209e-06,
+      "loss": 0.193,
+      "step": 500
+    },
+    {
+      "epoch": 4.077471967380224,
+      "eval_loss": 1.6843377351760864,
+      "eval_runtime": 4.0486,
+      "eval_samples_per_second": 27.17,
+      "eval_steps_per_second": 27.17,
+      "step": 500
+    },
+    {
+      "epoch": 4.159021406727828,
+      "grad_norm": 4.995784282684326,
+      "learning_rate": 6.340863063803187e-06,
+      "loss": 0.2102,
+      "step": 510
+    },
+    {
+      "epoch": 4.240570846075434,
+      "grad_norm": 3.022165536880493,
+      "learning_rate": 6.184504741390596e-06,
+      "loss": 0.1799,
+      "step": 520
+    },
+    {
+      "epoch": 4.322120285423038,
+      "grad_norm": 3.73397159576416,
+      "learning_rate": 6.02690914405191e-06,
+      "loss": 0.1945,
+      "step": 530
+    },
+    {
+      "epoch": 4.4036697247706424,
+      "grad_norm": 3.1206557750701904,
+      "learning_rate": 5.8682408883346535e-06,
+      "loss": 0.1186,
+      "step": 540
+    },
+    {
+      "epoch": 4.485219164118247,
+      "grad_norm": 6.9254326820373535,
+      "learning_rate": 5.708665711232103e-06,
+      "loss": 0.1761,
+      "step": 550
+    },
+    {
+      "epoch": 4.566768603465851,
+      "grad_norm": 1.7940961122512817,
+      "learning_rate": 5.548350297062659e-06,
+      "loss": 0.1747,
+      "step": 560
+    },
+    {
+      "epoch": 4.648318042813456,
+      "grad_norm": 3.6487746238708496,
+      "learning_rate": 5.387462103359655e-06,
+      "loss": 0.205,
+      "step": 570
+    },
+    {
+      "epoch": 4.72986748216106,
+      "grad_norm": 2.9038984775543213,
+      "learning_rate": 5.2261691859535325e-06,
+      "loss": 0.1384,
+      "step": 580
+    },
+    {
+      "epoch": 4.811416921508664,
+      "grad_norm": 7.9458842277526855,
+      "learning_rate": 5.064640023429042e-06,
+      "loss": 0.1475,
+      "step": 590
+    },
+    {
+      "epoch": 4.892966360856269,
+      "grad_norm": 3.393327236175537,
+      "learning_rate": 4.903043341140879e-06,
+      "loss": 0.1647,
+      "step": 600
+    },
+    {
+      "epoch": 4.974515800203873,
+      "grad_norm": 5.027682781219482,
+      "learning_rate": 4.741547934971528e-06,
+      "loss": 0.1691,
+      "step": 610
+    },
+    {
+      "epoch": 5.0560652395514785,
+      "grad_norm": 1.468493938446045,
+      "learning_rate": 4.580322495015466e-06,
+      "loss": 0.1022,
+      "step": 620
+    },
+    {
+      "epoch": 5.137614678899083,
+      "grad_norm": 1.9386202096939087,
+      "learning_rate": 4.4195354293738484e-06,
+      "loss": 0.0677,
+      "step": 630
+    },
+    {
+      "epoch": 5.219164118246687,
+      "grad_norm": 2.2345311641693115,
+      "learning_rate": 4.259354688243758e-06,
+      "loss": 0.0761,
+      "step": 640
+    },
+    {
+      "epoch": 5.300713557594292,
+      "grad_norm": 2.380667209625244,
+      "learning_rate": 4.099947588485744e-06,
+      "loss": 0.0733,
+      "step": 650
+    },
+    {
+      "epoch": 5.382262996941896,
+      "grad_norm": 1.2158432006835938,
+      "learning_rate": 3.941480638852948e-06,
+      "loss": 0.0841,
+      "step": 660
+    },
+    {
+      "epoch": 5.4638124362895,
+      "grad_norm": 2.382153034210205,
+      "learning_rate": 3.784119366064293e-06,
+      "loss": 0.0929,
+      "step": 670
+    },
+    {
+      "epoch": 5.545361875637105,
+      "grad_norm": 2.7093493938446045,
+      "learning_rate": 3.6280281419034934e-06,
+      "loss": 0.0634,
+      "step": 680
+    },
+    {
+      "epoch": 5.626911314984709,
+      "grad_norm": 1.597835659980774,
+      "learning_rate": 3.473370011524435e-06,
+      "loss": 0.1201,
+      "step": 690
+    },
+    {
+      "epoch": 5.708460754332314,
+      "grad_norm": 2.351442575454712,
+      "learning_rate": 3.3203065231422904e-06,
+      "loss": 0.0811,
+      "step": 700
+    },
+    {
+      "epoch": 5.790010193679919,
+      "grad_norm": 2.5688395500183105,
+      "learning_rate": 3.1689975592882603e-06,
+      "loss": 0.0708,
+      "step": 710
+    },
+    {
+      "epoch": 5.871559633027523,
+      "grad_norm": 3.0511674880981445,
+      "learning_rate": 3.019601169804216e-06,
+      "loss": 0.0846,
+      "step": 720
+    },
+    {
+      "epoch": 5.953109072375128,
+      "grad_norm": 5.8331298828125,
+      "learning_rate": 2.8722734067516637e-06,
+      "loss": 0.0782,
+      "step": 730
+    },
+    {
+      "epoch": 6.034658511722732,
+      "grad_norm": 1.1434911489486694,
+      "learning_rate": 2.7271681614074973e-06,
+      "loss": 0.0624,
+      "step": 740
+    },
+    {
+      "epoch": 6.116207951070336,
+      "grad_norm": 2.7258777618408203,
+      "learning_rate": 2.5844370035168077e-06,
+      "loss": 0.0373,
+      "step": 750
+    },
+    {
+      "epoch": 6.197757390417941,
+      "grad_norm": 0.5002675652503967,
+      "learning_rate": 2.4442290229706344e-06,
+      "loss": 0.0331,
+      "step": 760
+    },
+    {
+      "epoch": 6.279306829765545,
+      "grad_norm": 0.7639961242675781,
+      "learning_rate": 2.3066906740740626e-06,
+      "loss": 0.0232,
+      "step": 770
+    },
+    {
+      "epoch": 6.36085626911315,
+      "grad_norm": 2.4113121032714844,
+      "learning_rate": 2.171965622567308e-06,
+      "loss": 0.0356,
+      "step": 780
+    },
+    {
+      "epoch": 6.442405708460754,
+      "grad_norm": 1.4164212942123413,
+      "learning_rate": 2.0401945955596206e-06,
+      "loss": 0.0599,
+      "step": 790
+    },
+    {
+      "epoch": 6.523955147808358,
+      "grad_norm": 1.6531766653060913,
+      "learning_rate": 1.9115152345327154e-06,
+      "loss": 0.0298,
+      "step": 800
+    },
+    {
+      "epoch": 6.605504587155964,
+      "grad_norm": 1.0268425941467285,
+      "learning_rate": 1.7860619515673034e-06,
+      "loss": 0.029,
+      "step": 810
+    },
+    {
+      "epoch": 6.687054026503568,
+      "grad_norm": 1.7151083946228027,
+      "learning_rate": 1.6639657889429017e-06,
+      "loss": 0.0322,
+      "step": 820
+    },
+    {
+      "epoch": 6.7686034658511725,
+      "grad_norm": 1.3095351457595825,
+      "learning_rate": 1.5453542822575624e-06,
+      "loss": 0.0276,
+      "step": 830
+    },
+    {
+      "epoch": 6.850152905198777,
+      "grad_norm": 2.322570323944092,
+      "learning_rate": 1.4303513272105057e-06,
+      "loss": 0.0307,
+      "step": 840
+    },
+    {
+      "epoch": 6.931702344546381,
+      "grad_norm": 5.283768653869629,
+      "learning_rate": 1.3190770501868243e-06,
+      "loss": 0.0439,
+      "step": 850
+    },
+    {
+      "epoch": 7.013251783893986,
+      "grad_norm": 2.021864414215088,
+      "learning_rate": 1.2116476827794104e-06,
+      "loss": 0.0349,
+      "step": 860
+    },
+    {
+      "epoch": 7.09480122324159,
+      "grad_norm": 1.7383687496185303,
+      "learning_rate": 1.1081754403792e-06,
+      "loss": 0.0141,
+      "step": 870
+    },
+    {
+      "epoch": 7.176350662589194,
+      "grad_norm": 0.9524487853050232,
+      "learning_rate": 1.008768404960535e-06,
+      "loss": 0.0131,
+      "step": 880
+    },
+    {
+      "epoch": 7.257900101936799,
+      "grad_norm": 0.6132211089134216,
+      "learning_rate": 9.135304121840976e-07,
+      "loss": 0.0156,
+      "step": 890
+    },
+    {
+      "epoch": 7.339449541284404,
+      "grad_norm": 0.16791853308677673,
+      "learning_rate": 8.225609429353187e-07,
+      "loss": 0.0129,
+      "step": 900
+    },
+    {
+      "epoch": 7.4209989806320085,
+      "grad_norm": 0.24683955311775208,
+      "learning_rate": 7.35955019411585e-07,
+      "loss": 0.0142,
+      "step": 910
+    },
+    {
+      "epoch": 7.502548419979613,
+      "grad_norm": 0.177597314119339,
+      "learning_rate": 6.53803105866761e-07,
+      "loss": 0.0103,
+      "step": 920
+    },
+    {
+      "epoch": 7.584097859327217,
+      "grad_norm": 1.1235181093215942,
+      "learning_rate": 5.76191014116711e-07,
+      "loss": 0.0166,
+      "step": 930
+    },
+    {
+      "epoch": 7.665647298674822,
+      "grad_norm": 0.7732178568840027,
+      "learning_rate": 5.031998139045352e-07,
+      "loss": 0.0144,
+      "step": 940
+    },
+    {
+      "epoch": 7.747196738022426,
+      "grad_norm": 1.0395855903625488,
+      "learning_rate": 4.349057482191299e-07,
+      "loss": 0.0165,
+      "step": 950
+    },
+    {
+      "epoch": 7.82874617737003,
+      "grad_norm": 0.6988322734832764,
+      "learning_rate": 3.7138015365554834e-07,
+      "loss": 0.0118,
+      "step": 960
+    },
+    {
+      "epoch": 7.910295616717635,
+      "grad_norm": 0.8800845742225647,
+      "learning_rate": 3.1268938590032495e-07,
+      "loss": 0.0141,
+      "step": 970
+    },
+    {
+      "epoch": 7.991845056065239,
+      "grad_norm": 0.32935312390327454,
+      "learning_rate": 2.5889475041961767e-07,
+      "loss": 0.0096,
+      "step": 980
+    },
+    {
+      "epoch": 8.073394495412844,
+      "grad_norm": 0.8593177199363708,
+      "learning_rate": 2.1005243842255552e-07,
+      "loss": 0.0207,
+      "step": 990
+    },
+    {
+      "epoch": 8.154943934760448,
+      "grad_norm": 0.561518132686615,
+      "learning_rate": 1.6621346816668993e-07,
+      "loss": 0.0083,
+      "step": 1000
+    },
+    {
+      "epoch": 8.154943934760448,
+      "eval_loss": 2.4749834537506104,
+      "eval_runtime": 3.9418,
+      "eval_samples_per_second": 27.906,
+      "eval_steps_per_second": 27.906,
+      "step": 1000
+    },
+    {
+      "epoch": 8.236493374108052,
+      "grad_norm": 0.1318514049053192,
+      "learning_rate": 1.2742363166685035e-07,
+      "loss": 0.0084,
+      "step": 1010
+    },
+    {
+      "epoch": 8.318042813455657,
+      "grad_norm": 0.09888464212417603,
+      "learning_rate": 9.372344686307655e-08,
+      "loss": 0.0065,
+      "step": 1020
+    },
+    {
+      "epoch": 8.399592252803261,
+      "grad_norm": 0.2378782033920288,
+      "learning_rate": 6.514811529758747e-08,
+      "loss": 0.0116,
+      "step": 1030
+    },
+    {
+      "epoch": 8.481141692150867,
+      "grad_norm": 0.2287997156381607,
+      "learning_rate": 4.172748534499449e-08,
+      "loss": 0.0108,
+      "step": 1040
+    },
+    {
+      "epoch": 8.562691131498472,
+      "grad_norm": 0.5172834992408752,
+      "learning_rate": 2.3486021034170857e-08,
+      "loss": 0.0088,
+      "step": 1050
+    },
+    {
+      "epoch": 8.644240570846076,
+      "grad_norm": 0.272684246301651,
+      "learning_rate": 1.044277649433989e-08,
+      "loss": 0.0086,
+      "step": 1060
+    },
+    {
+      "epoch": 8.72579001019368,
+      "grad_norm": 0.2911706864833832,
+      "learning_rate": 2.611376052073511e-09,
+      "loss": 0.0086,
+      "step": 1070
+    },
+    {
+      "epoch": 8.807339449541285,
+      "grad_norm": 0.5013861060142517,
+      "learning_rate": 0.0,
+      "loss": 0.0063,
+      "step": 1080
+    },
+    {
+      "epoch": 8.807339449541285,
+      "step": 1080,
+      "total_flos": 1.2056852760477696e+16,
+      "train_loss": 0.3479360826589443,
+      "train_runtime": 1723.5404,
+      "train_samples_per_second": 5.013,
+      "train_steps_per_second": 0.627
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1080,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 9,
+  "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": 1.2056852760477696e+16,
+  "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 sha256:196ae8248ccbc3c2ec3672dee7242eeae31c6eaea7ac924c8f23e938ef0ff4e8
+size 5368