add model

mta_7b_full/README.md

@@ -0,0 +1,59 @@
+---
+library_name: transformers
+license: other
+base_model: /mnt/workspace/Models/Qwen2.5-7B
+tags:
+- llama-factory
+- full
+- generated_from_trainer
+model-index:
+- name: mta_7b_full
+  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. -->
+
+# mta_7b_full
+
+This model is a fine-tuned version of [/mnt/workspace/Models/Qwen2.5-7B](https://huggingface.co//mnt/workspace/Models/Qwen2.5-7B) on the mta_multi_turn_mamrp 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: 1e-05
+- train_batch_size: 1
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 8
+- total_train_batch_size: 8
+- total_eval_batch_size: 64
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- num_epochs: 3.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.45.2
+- Pytorch 2.4.0+cu121
+- Datasets 3.1.0
+- Tokenizers 0.20.3

mta_7b_full/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
+}

mta_7b_full/all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 3.0,
+    "eval_loss": 0.758097767829895,
+    "eval_runtime": 1.6704,
+    "eval_samples_per_second": 20.952,
+    "eval_steps_per_second": 2.993,
+    "total_flos": 1.7932809270617702e+17,
+    "train_loss": 0.5420024356869764,
+    "train_runtime": 227.6568,
+    "train_samples_per_second": 4.533,
+    "train_steps_per_second": 0.567
+}

mta_7b_full/config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "/mnt/workspace/Models/Qwen2.5-7B",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 131072,
+  "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": "4.45.2",
+  "use_cache": false,
+  "use_mrope": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

mta_7b_full/eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 3.0,
+    "eval_loss": 0.758097767829895,
+    "eval_runtime": 1.6704,
+    "eval_samples_per_second": 20.952,
+    "eval_steps_per_second": 2.993
+}

mta_7b_full/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "max_new_tokens": 2048,
+  "transformers_version": "4.45.2"
+}

mta_7b_full/model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e035e9e7eb2597c262b9a4fdf4b524076a8a2f09eea949e7ee53f68f6d4ff63
+size 4877660776

mta_7b_full/model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33409107b797ccc169cb9381b47cb117814acbe4098831fc6cb7661a27a4755b
+size 4932751008

mta_7b_full/model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc56536c43c528bfc109cb630aa9330eccdbdee2fb363556077c05a71455b050
+size 4330865200

mta_7b_full/model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:526857ce47d1ce55c48b9f6d01fab81359b47c77ca04d7c7baeb325dc6e0406e
+size 1089994880

mta_7b_full/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"
+  }
+}

mta_7b_full/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
+  }
+}

mta_7b_full/tokenizer.json

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

mta_7b_full/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 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 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
+}

mta_7b_full/train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "total_flos": 1.7932809270617702e+17,
+    "train_loss": 0.5420024356869764,
+    "train_runtime": 227.6568,
+    "train_samples_per_second": 4.533,
+    "train_steps_per_second": 0.567
+}

mta_7b_full/trainer_log.jsonl

@@ -0,0 +1,130 @@
+{"current_steps": 1, "total_steps": 129, "loss": 1.279, "lr": 9.998517349225698e-06, "epoch": 0.023255813953488372, "percentage": 0.78, "elapsed_time": "0:00:02", "remaining_time": "0:05:16"}
+{"current_steps": 2, "total_steps": 129, "loss": 1.04, "lr": 9.994070276204115e-06, "epoch": 0.046511627906976744, "percentage": 1.55, "elapsed_time": "0:00:04", "remaining_time": "0:04:24"}
+{"current_steps": 3, "total_steps": 129, "loss": 11.9749, "lr": 9.986661418317759e-06, "epoch": 0.06976744186046512, "percentage": 2.33, "elapsed_time": "0:00:05", "remaining_time": "0:04:06"}
+{"current_steps": 4, "total_steps": 129, "loss": 1.0116, "lr": 9.97629516946618e-06, "epoch": 0.09302325581395349, "percentage": 3.1, "elapsed_time": "0:00:07", "remaining_time": "0:03:56"}
+{"current_steps": 5, "total_steps": 129, "loss": 0.8886, "lr": 9.962977677460132e-06, "epoch": 0.11627906976744186, "percentage": 3.88, "elapsed_time": "0:00:09", "remaining_time": "0:03:50"}
+{"current_steps": 6, "total_steps": 129, "loss": 0.9208, "lr": 9.946716840375552e-06, "epoch": 0.13953488372093023, "percentage": 4.65, "elapsed_time": "0:00:10", "remaining_time": "0:03:45"}
+{"current_steps": 7, "total_steps": 129, "loss": 0.8859, "lr": 9.927522301869515e-06, "epoch": 0.16279069767441862, "percentage": 5.43, "elapsed_time": "0:00:12", "remaining_time": "0:03:41"}
+{"current_steps": 8, "total_steps": 129, "loss": 0.669, "lr": 9.905405445460972e-06, "epoch": 0.18604651162790697, "percentage": 6.2, "elapsed_time": "0:00:14", "remaining_time": "0:03:37"}
+{"current_steps": 9, "total_steps": 129, "loss": 0.9212, "lr": 9.880379387779637e-06, "epoch": 0.20930232558139536, "percentage": 6.98, "elapsed_time": "0:00:16", "remaining_time": "0:03:34"}
+{"current_steps": 10, "total_steps": 129, "loss": 0.7304, "lr": 9.852458970787027e-06, "epoch": 0.23255813953488372, "percentage": 7.75, "elapsed_time": "0:00:17", "remaining_time": "0:03:32"}
+{"current_steps": 11, "total_steps": 129, "loss": 0.8411, "lr": 9.821660752974294e-06, "epoch": 0.2558139534883721, "percentage": 8.53, "elapsed_time": "0:00:19", "remaining_time": "0:03:29"}
+{"current_steps": 12, "total_steps": 129, "loss": 0.7511, "lr": 9.78800299954203e-06, "epoch": 0.27906976744186046, "percentage": 9.3, "elapsed_time": "0:00:21", "remaining_time": "0:03:27"}
+{"current_steps": 13, "total_steps": 129, "loss": 0.763, "lr": 9.751505671567914e-06, "epoch": 0.3023255813953488, "percentage": 10.08, "elapsed_time": "0:00:22", "remaining_time": "0:03:24"}
+{"current_steps": 14, "total_steps": 129, "loss": 0.8875, "lr": 9.712190414168573e-06, "epoch": 0.32558139534883723, "percentage": 10.85, "elapsed_time": "0:00:24", "remaining_time": "0:03:22"}
+{"current_steps": 15, "total_steps": 129, "loss": 0.6891, "lr": 9.670080543662742e-06, "epoch": 0.3488372093023256, "percentage": 11.63, "elapsed_time": "0:00:26", "remaining_time": "0:03:20"}
+{"current_steps": 16, "total_steps": 129, "loss": 0.8419, "lr": 9.625201033743262e-06, "epoch": 0.37209302325581395, "percentage": 12.4, "elapsed_time": "0:00:28", "remaining_time": "0:03:18"}
+{"current_steps": 17, "total_steps": 129, "loss": 0.7341, "lr": 9.577578500666187e-06, "epoch": 0.3953488372093023, "percentage": 13.18, "elapsed_time": "0:00:29", "remaining_time": "0:03:16"}
+{"current_steps": 18, "total_steps": 129, "loss": 0.8575, "lr": 9.527241187465735e-06, "epoch": 0.4186046511627907, "percentage": 13.95, "elapsed_time": "0:00:31", "remaining_time": "0:03:14"}
+{"current_steps": 19, "total_steps": 129, "loss": 0.7854, "lr": 9.47421894720446e-06, "epoch": 0.4418604651162791, "percentage": 14.73, "elapsed_time": "0:00:33", "remaining_time": "0:03:12"}
+{"current_steps": 20, "total_steps": 129, "loss": 0.7404, "lr": 9.418543225268598e-06, "epoch": 0.46511627906976744, "percentage": 15.5, "elapsed_time": "0:00:34", "remaining_time": "0:03:10"}
+{"current_steps": 21, "total_steps": 129, "loss": 0.8586, "lr": 9.36024704071904e-06, "epoch": 0.4883720930232558, "percentage": 16.28, "elapsed_time": "0:00:36", "remaining_time": "0:03:08"}
+{"current_steps": 22, "total_steps": 129, "loss": 0.7443, "lr": 9.299364966709051e-06, "epoch": 0.5116279069767442, "percentage": 17.05, "elapsed_time": "0:00:38", "remaining_time": "0:03:06"}
+{"current_steps": 23, "total_steps": 129, "loss": 0.6506, "lr": 9.235933109980302e-06, "epoch": 0.5348837209302325, "percentage": 17.83, "elapsed_time": "0:00:40", "remaining_time": "0:03:04"}
+{"current_steps": 24, "total_steps": 129, "loss": 0.7598, "lr": 9.16998908944939e-06, "epoch": 0.5581395348837209, "percentage": 18.6, "elapsed_time": "0:00:41", "remaining_time": "0:03:02"}
+{"current_steps": 25, "total_steps": 129, "loss": 0.7469, "lr": 9.101572013897555e-06, "epoch": 0.5813953488372093, "percentage": 19.38, "elapsed_time": "0:00:43", "remaining_time": "0:03:01"}
+{"current_steps": 26, "total_steps": 129, "loss": 0.8682, "lr": 9.030722458776815e-06, "epoch": 0.6046511627906976, "percentage": 20.16, "elapsed_time": "0:00:45", "remaining_time": "0:02:59"}
+{"current_steps": 27, "total_steps": 129, "loss": 0.8632, "lr": 8.957482442146271e-06, "epoch": 0.627906976744186, "percentage": 20.93, "elapsed_time": "0:00:46", "remaining_time": "0:02:57"}
+{"current_steps": 28, "total_steps": 129, "loss": 0.6599, "lr": 8.881895399752873e-06, "epoch": 0.6511627906976745, "percentage": 21.71, "elapsed_time": "0:00:48", "remaining_time": "0:02:55"}
+{"current_steps": 29, "total_steps": 129, "loss": 0.8089, "lr": 8.80400615927139e-06, "epoch": 0.6744186046511628, "percentage": 22.48, "elapsed_time": "0:00:50", "remaining_time": "0:02:53"}
+{"current_steps": 30, "total_steps": 129, "loss": 0.7626, "lr": 8.72386091371891e-06, "epoch": 0.6976744186046512, "percentage": 23.26, "elapsed_time": "0:00:52", "remaining_time": "0:02:51"}
+{"current_steps": 31, "total_steps": 129, "loss": 0.7286, "lr": 8.64150719405958e-06, "epoch": 0.7209302325581395, "percentage": 24.03, "elapsed_time": "0:00:53", "remaining_time": "0:02:50"}
+{"current_steps": 32, "total_steps": 129, "loss": 0.7357, "lr": 8.55699384101589e-06, "epoch": 0.7441860465116279, "percentage": 24.81, "elapsed_time": "0:00:55", "remaining_time": "0:02:48"}
+{"current_steps": 33, "total_steps": 129, "loss": 0.703, "lr": 8.470370976103171e-06, "epoch": 0.7674418604651163, "percentage": 25.58, "elapsed_time": "0:00:57", "remaining_time": "0:02:46"}
+{"current_steps": 34, "total_steps": 129, "loss": 0.6339, "lr": 8.381689971904514e-06, "epoch": 0.7906976744186046, "percentage": 26.36, "elapsed_time": "0:00:58", "remaining_time": "0:02:44"}
+{"current_steps": 35, "total_steps": 129, "loss": 0.7153, "lr": 8.29100342160374e-06, "epoch": 0.813953488372093, "percentage": 27.13, "elapsed_time": "0:01:00", "remaining_time": "0:02:43"}
+{"current_steps": 36, "total_steps": 129, "loss": 0.6737, "lr": 8.198365107794457e-06, "epoch": 0.8372093023255814, "percentage": 27.91, "elapsed_time": "0:01:02", "remaining_time": "0:02:41"}
+{"current_steps": 37, "total_steps": 129, "loss": 0.7295, "lr": 8.103829970583742e-06, "epoch": 0.8604651162790697, "percentage": 28.68, "elapsed_time": "0:01:04", "remaining_time": "0:02:39"}
+{"current_steps": 38, "total_steps": 129, "loss": 0.6999, "lr": 8.007454075009352e-06, "epoch": 0.8837209302325582, "percentage": 29.46, "elapsed_time": "0:01:05", "remaining_time": "0:02:37"}
+{"current_steps": 39, "total_steps": 129, "loss": 0.6917, "lr": 7.909294577789765e-06, "epoch": 0.9069767441860465, "percentage": 30.23, "elapsed_time": "0:01:07", "remaining_time": "0:02:35"}
+{"current_steps": 40, "total_steps": 129, "loss": 0.7131, "lr": 7.809409693426803e-06, "epoch": 0.9302325581395349, "percentage": 31.01, "elapsed_time": "0:01:09", "remaining_time": "0:02:34"}
+{"current_steps": 41, "total_steps": 129, "loss": 0.7, "lr": 7.707858659680924e-06, "epoch": 0.9534883720930233, "percentage": 31.78, "elapsed_time": "0:01:11", "remaining_time": "0:02:32"}
+{"current_steps": 42, "total_steps": 129, "loss": 0.6538, "lr": 7.604701702439652e-06, "epoch": 0.9767441860465116, "percentage": 32.56, "elapsed_time": "0:01:12", "remaining_time": "0:02:30"}
+{"current_steps": 43, "total_steps": 129, "loss": 0.6142, "lr": 7.500000000000001e-06, "epoch": 1.0, "percentage": 33.33, "elapsed_time": "0:01:14", "remaining_time": "0:02:28"}
+{"current_steps": 44, "total_steps": 129, "loss": 0.4602, "lr": 7.393815646786047e-06, "epoch": 1.0232558139534884, "percentage": 34.11, "elapsed_time": "0:01:16", "remaining_time": "0:02:27"}
+{"current_steps": 45, "total_steps": 129, "loss": 0.3917, "lr": 7.286211616523193e-06, "epoch": 1.0465116279069768, "percentage": 34.88, "elapsed_time": "0:01:17", "remaining_time": "0:02:25"}
+{"current_steps": 46, "total_steps": 129, "loss": 0.377, "lr": 7.177251724890957e-06, "epoch": 1.069767441860465, "percentage": 35.66, "elapsed_time": "0:01:19", "remaining_time": "0:02:23"}
+{"current_steps": 47, "total_steps": 129, "loss": 0.4112, "lr": 7.067000591676416e-06, "epoch": 1.0930232558139534, "percentage": 36.43, "elapsed_time": "0:01:21", "remaining_time": "0:02:21"}
+{"current_steps": 48, "total_steps": 129, "loss": 0.3741, "lr": 6.95552360245078e-06, "epoch": 1.1162790697674418, "percentage": 37.21, "elapsed_time": "0:01:23", "remaining_time": "0:02:20"}
+{"current_steps": 49, "total_steps": 129, "loss": 0.3554, "lr": 6.84288686979181e-06, "epoch": 1.1395348837209303, "percentage": 37.98, "elapsed_time": "0:01:24", "remaining_time": "0:02:18"}
+{"current_steps": 50, "total_steps": 129, "loss": 0.3973, "lr": 6.7291571940750575e-06, "epoch": 1.1627906976744187, "percentage": 38.76, "elapsed_time": "0:01:26", "remaining_time": "0:02:16"}
+{"current_steps": 51, "total_steps": 129, "loss": 0.4135, "lr": 6.614402023857231e-06, "epoch": 1.1860465116279069, "percentage": 39.53, "elapsed_time": "0:01:28", "remaining_time": "0:02:14"}
+{"current_steps": 52, "total_steps": 129, "loss": 0.3736, "lr": 6.498689415875121e-06, "epoch": 1.2093023255813953, "percentage": 40.31, "elapsed_time": "0:01:29", "remaining_time": "0:02:13"}
+{"current_steps": 53, "total_steps": 129, "loss": 0.4754, "lr": 6.3820879946838585e-06, "epoch": 1.2325581395348837, "percentage": 41.09, "elapsed_time": "0:01:31", "remaining_time": "0:02:11"}
+{"current_steps": 54, "total_steps": 129, "loss": 0.3985, "lr": 6.264666911958404e-06, "epoch": 1.255813953488372, "percentage": 41.86, "elapsed_time": "0:01:33", "remaining_time": "0:02:09"}
+{"current_steps": 55, "total_steps": 129, "loss": 0.3718, "lr": 6.146495805482451e-06, "epoch": 1.2790697674418605, "percentage": 42.64, "elapsed_time": "0:01:35", "remaining_time": "0:02:07"}
+{"current_steps": 56, "total_steps": 129, "loss": 0.4304, "lr": 6.027644757849004e-06, "epoch": 1.302325581395349, "percentage": 43.41, "elapsed_time": "0:01:36", "remaining_time": "0:02:06"}
+{"current_steps": 57, "total_steps": 129, "loss": 0.2778, "lr": 5.908184254897183e-06, "epoch": 1.3255813953488373, "percentage": 44.19, "elapsed_time": "0:01:38", "remaining_time": "0:02:04"}
+{"current_steps": 58, "total_steps": 129, "loss": 0.3507, "lr": 5.788185143909868e-06, "epoch": 1.3488372093023255, "percentage": 44.96, "elapsed_time": "0:01:40", "remaining_time": "0:02:02"}
+{"current_steps": 59, "total_steps": 129, "loss": 0.3503, "lr": 5.66771859159699e-06, "epoch": 1.372093023255814, "percentage": 45.74, "elapsed_time": "0:01:41", "remaining_time": "0:02:00"}
+{"current_steps": 60, "total_steps": 129, "loss": 0.3828, "lr": 5.546856041889374e-06, "epoch": 1.3953488372093024, "percentage": 46.51, "elapsed_time": "0:01:43", "remaining_time": "0:01:59"}
+{"current_steps": 61, "total_steps": 129, "loss": 0.4213, "lr": 5.425669173568179e-06, "epoch": 1.4186046511627908, "percentage": 47.29, "elapsed_time": "0:01:45", "remaining_time": "0:01:57"}
+{"current_steps": 62, "total_steps": 129, "loss": 0.4199, "lr": 5.30422985775507e-06, "epoch": 1.441860465116279, "percentage": 48.06, "elapsed_time": "0:01:47", "remaining_time": "0:01:55"}
+{"current_steps": 63, "total_steps": 129, "loss": 0.3162, "lr": 5.182610115288296e-06, "epoch": 1.4651162790697674, "percentage": 48.84, "elapsed_time": "0:01:48", "remaining_time": "0:01:53"}
+{"current_steps": 64, "total_steps": 129, "loss": 0.3888, "lr": 5.060882074009988e-06, "epoch": 1.4883720930232558, "percentage": 49.61, "elapsed_time": "0:01:50", "remaining_time": "0:01:52"}
+{"current_steps": 65, "total_steps": 129, "loss": 0.354, "lr": 4.939117925990013e-06, "epoch": 1.5116279069767442, "percentage": 50.39, "elapsed_time": "0:01:52", "remaining_time": "0:01:50"}
+{"current_steps": 66, "total_steps": 129, "loss": 0.3896, "lr": 4.817389884711706e-06, "epoch": 1.5348837209302326, "percentage": 51.16, "elapsed_time": "0:01:53", "remaining_time": "0:01:48"}
+{"current_steps": 67, "total_steps": 129, "loss": 0.381, "lr": 4.695770142244931e-06, "epoch": 1.558139534883721, "percentage": 51.94, "elapsed_time": "0:01:55", "remaining_time": "0:01:47"}
+{"current_steps": 68, "total_steps": 129, "loss": 0.4143, "lr": 4.574330826431822e-06, "epoch": 1.5813953488372094, "percentage": 52.71, "elapsed_time": "0:01:57", "remaining_time": "0:01:45"}
+{"current_steps": 69, "total_steps": 129, "loss": 0.3577, "lr": 4.4531439581106295e-06, "epoch": 1.6046511627906976, "percentage": 53.49, "elapsed_time": "0:01:59", "remaining_time": "0:01:43"}
+{"current_steps": 70, "total_steps": 129, "loss": 0.4366, "lr": 4.332281408403011e-06, "epoch": 1.627906976744186, "percentage": 54.26, "elapsed_time": "0:02:00", "remaining_time": "0:01:41"}
+{"current_steps": 71, "total_steps": 129, "loss": 0.375, "lr": 4.2118148560901325e-06, "epoch": 1.6511627906976745, "percentage": 55.04, "elapsed_time": "0:02:02", "remaining_time": "0:01:40"}
+{"current_steps": 72, "total_steps": 129, "loss": 0.3676, "lr": 4.091815745102818e-06, "epoch": 1.6744186046511627, "percentage": 55.81, "elapsed_time": "0:02:04", "remaining_time": "0:01:38"}
+{"current_steps": 73, "total_steps": 129, "loss": 0.3855, "lr": 3.9723552421509975e-06, "epoch": 1.697674418604651, "percentage": 56.59, "elapsed_time": "0:02:05", "remaining_time": "0:01:36"}
+{"current_steps": 74, "total_steps": 129, "loss": 0.4233, "lr": 3.853504194517551e-06, "epoch": 1.7209302325581395, "percentage": 57.36, "elapsed_time": "0:02:07", "remaining_time": "0:01:34"}
+{"current_steps": 75, "total_steps": 129, "loss": 0.3835, "lr": 3.7353330880415963e-06, "epoch": 1.744186046511628, "percentage": 58.14, "elapsed_time": "0:02:09", "remaining_time": "0:01:33"}
+{"current_steps": 76, "total_steps": 129, "loss": 0.4012, "lr": 3.617912005316142e-06, "epoch": 1.7674418604651163, "percentage": 58.91, "elapsed_time": "0:02:11", "remaining_time": "0:01:31"}
+{"current_steps": 77, "total_steps": 129, "loss": 0.3615, "lr": 3.5013105841248794e-06, "epoch": 1.7906976744186047, "percentage": 59.69, "elapsed_time": "0:02:12", "remaining_time": "0:01:29"}
+{"current_steps": 78, "total_steps": 129, "loss": 0.3489, "lr": 3.3855979761427705e-06, "epoch": 1.8139534883720931, "percentage": 60.47, "elapsed_time": "0:02:14", "remaining_time": "0:01:27"}
+{"current_steps": 79, "total_steps": 129, "loss": 0.4164, "lr": 3.2708428059249437e-06, "epoch": 1.8372093023255816, "percentage": 61.24, "elapsed_time": "0:02:16", "remaining_time": "0:01:26"}
+{"current_steps": 80, "total_steps": 129, "loss": 0.374, "lr": 3.1571131302081916e-06, "epoch": 1.8604651162790697, "percentage": 62.02, "elapsed_time": "0:02:18", "remaining_time": "0:01:24"}
+{"current_steps": 81, "total_steps": 129, "loss": 0.4293, "lr": 3.044476397549221e-06, "epoch": 1.8837209302325582, "percentage": 62.79, "elapsed_time": "0:02:19", "remaining_time": "0:01:22"}
+{"current_steps": 82, "total_steps": 129, "loss": 0.3804, "lr": 2.9329994083235857e-06, "epoch": 1.9069767441860463, "percentage": 63.57, "elapsed_time": "0:02:21", "remaining_time": "0:01:21"}
+{"current_steps": 83, "total_steps": 129, "loss": 0.4171, "lr": 2.8227482751090445e-06, "epoch": 1.9302325581395348, "percentage": 64.34, "elapsed_time": "0:02:23", "remaining_time": "0:01:19"}
+{"current_steps": 84, "total_steps": 129, "loss": 0.3308, "lr": 2.7137883834768076e-06, "epoch": 1.9534883720930232, "percentage": 65.12, "elapsed_time": "0:02:24", "remaining_time": "0:01:17"}
+{"current_steps": 85, "total_steps": 129, "loss": 0.3149, "lr": 2.6061843532139563e-06, "epoch": 1.9767441860465116, "percentage": 65.89, "elapsed_time": "0:02:26", "remaining_time": "0:01:15"}
+{"current_steps": 86, "total_steps": 129, "loss": 0.4402, "lr": 2.5000000000000015e-06, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "0:02:28", "remaining_time": "0:01:14"}
+{"current_steps": 87, "total_steps": 129, "loss": 0.2177, "lr": 2.3952982975603494e-06, "epoch": 2.0232558139534884, "percentage": 67.44, "elapsed_time": "0:02:30", "remaining_time": "0:01:12"}
+{"current_steps": 88, "total_steps": 129, "loss": 0.223, "lr": 2.2921413403190774e-06, "epoch": 2.046511627906977, "percentage": 68.22, "elapsed_time": "0:02:31", "remaining_time": "0:01:10"}
+{"current_steps": 89, "total_steps": 129, "loss": 0.2095, "lr": 2.190590306573198e-06, "epoch": 2.0697674418604652, "percentage": 68.99, "elapsed_time": "0:02:33", "remaining_time": "0:01:08"}
+{"current_steps": 90, "total_steps": 129, "loss": 0.2738, "lr": 2.0907054222102367e-06, "epoch": 2.0930232558139537, "percentage": 69.77, "elapsed_time": "0:02:35", "remaining_time": "0:01:07"}
+{"current_steps": 91, "total_steps": 129, "loss": 0.1668, "lr": 1.9925459249906488e-06, "epoch": 2.116279069767442, "percentage": 70.54, "elapsed_time": "0:02:36", "remaining_time": "0:01:05"}
+{"current_steps": 92, "total_steps": 129, "loss": 0.2361, "lr": 1.8961700294162578e-06, "epoch": 2.13953488372093, "percentage": 71.32, "elapsed_time": "0:02:38", "remaining_time": "0:01:03"}
+{"current_steps": 93, "total_steps": 129, "loss": 0.1405, "lr": 1.8016348922055448e-06, "epoch": 2.1627906976744184, "percentage": 72.09, "elapsed_time": "0:02:40", "remaining_time": "0:01:02"}
+{"current_steps": 94, "total_steps": 129, "loss": 0.1582, "lr": 1.7089965783962608e-06, "epoch": 2.186046511627907, "percentage": 72.87, "elapsed_time": "0:02:42", "remaining_time": "0:01:00"}
+{"current_steps": 95, "total_steps": 129, "loss": 0.2072, "lr": 1.618310028095486e-06, "epoch": 2.2093023255813953, "percentage": 73.64, "elapsed_time": "0:02:43", "remaining_time": "0:00:58"}
+{"current_steps": 96, "total_steps": 129, "loss": 0.2166, "lr": 1.5296290238968303e-06, "epoch": 2.2325581395348837, "percentage": 74.42, "elapsed_time": "0:02:45", "remaining_time": "0:00:56"}
+{"current_steps": 97, "total_steps": 129, "loss": 0.2256, "lr": 1.4430061589841122e-06, "epoch": 2.255813953488372, "percentage": 75.19, "elapsed_time": "0:02:47", "remaining_time": "0:00:55"}
+{"current_steps": 98, "total_steps": 129, "loss": 0.1825, "lr": 1.3584928059404207e-06, "epoch": 2.2790697674418605, "percentage": 75.97, "elapsed_time": "0:02:48", "remaining_time": "0:00:53"}
+{"current_steps": 99, "total_steps": 129, "loss": 0.2092, "lr": 1.2761390862810907e-06, "epoch": 2.302325581395349, "percentage": 76.74, "elapsed_time": "0:02:50", "remaining_time": "0:00:51"}
+{"current_steps": 100, "total_steps": 129, "loss": 0.1779, "lr": 1.1959938407286099e-06, "epoch": 2.3255813953488373, "percentage": 77.52, "elapsed_time": "0:02:52", "remaining_time": "0:00:49"}
+{"current_steps": 101, "total_steps": 129, "loss": 0.2296, "lr": 1.1181046002471292e-06, "epoch": 2.3488372093023258, "percentage": 78.29, "elapsed_time": "0:02:54", "remaining_time": "0:00:48"}
+{"current_steps": 102, "total_steps": 129, "loss": 0.1937, "lr": 1.04251755785373e-06, "epoch": 2.3720930232558137, "percentage": 79.07, "elapsed_time": "0:02:55", "remaining_time": "0:00:46"}
+{"current_steps": 103, "total_steps": 129, "loss": 0.1514, "lr": 9.692775412231863e-07, "epoch": 2.395348837209302, "percentage": 79.84, "elapsed_time": "0:02:57", "remaining_time": "0:00:44"}
+{"current_steps": 104, "total_steps": 129, "loss": 0.2083, "lr": 8.984279861024453e-07, "epoch": 2.4186046511627906, "percentage": 80.62, "elapsed_time": "0:02:59", "remaining_time": "0:00:43"}
+{"current_steps": 105, "total_steps": 129, "loss": 0.1608, "lr": 8.30010910550611e-07, "epoch": 2.441860465116279, "percentage": 81.4, "elapsed_time": "0:03:00", "remaining_time": "0:00:41"}
+{"current_steps": 106, "total_steps": 129, "loss": 0.1763, "lr": 7.640668900196985e-07, "epoch": 2.4651162790697674, "percentage": 82.17, "elapsed_time": "0:03:02", "remaining_time": "0:00:39"}
+{"current_steps": 107, "total_steps": 129, "loss": 0.227, "lr": 7.006350332909495e-07, "epoch": 2.488372093023256, "percentage": 82.95, "elapsed_time": "0:03:04", "remaining_time": "0:00:37"}
+{"current_steps": 108, "total_steps": 129, "loss": 0.1635, "lr": 6.397529592809615e-07, "epoch": 2.511627906976744, "percentage": 83.72, "elapsed_time": "0:03:06", "remaining_time": "0:00:36"}
+{"current_steps": 109, "total_steps": 129, "loss": 0.1909, "lr": 5.814567747314049e-07, "epoch": 2.5348837209302326, "percentage": 84.5, "elapsed_time": "0:03:07", "remaining_time": "0:00:34"}
+{"current_steps": 110, "total_steps": 129, "loss": 0.1529, "lr": 5.25781052795541e-07, "epoch": 2.558139534883721, "percentage": 85.27, "elapsed_time": "0:03:09", "remaining_time": "0:00:32"}
+{"current_steps": 111, "total_steps": 129, "loss": 0.2039, "lr": 4.727588125342669e-07, "epoch": 2.5813953488372094, "percentage": 86.05, "elapsed_time": "0:03:11", "remaining_time": "0:00:31"}
+{"current_steps": 112, "total_steps": 129, "loss": 0.1689, "lr": 4.224214993338149e-07, "epoch": 2.604651162790698, "percentage": 86.82, "elapsed_time": "0:03:13", "remaining_time": "0:00:29"}
+{"current_steps": 113, "total_steps": 129, "loss": 0.2066, "lr": 3.747989662567403e-07, "epoch": 2.6279069767441863, "percentage": 87.6, "elapsed_time": "0:03:14", "remaining_time": "0:00:27"}
+{"current_steps": 114, "total_steps": 129, "loss": 0.1758, "lr": 3.299194563372604e-07, "epoch": 2.6511627906976747, "percentage": 88.37, "elapsed_time": "0:03:16", "remaining_time": "0:00:25"}
+{"current_steps": 115, "total_steps": 129, "loss": 0.2181, "lr": 2.878095858314278e-07, "epoch": 2.6744186046511627, "percentage": 89.15, "elapsed_time": "0:03:18", "remaining_time": "0:00:24"}
+{"current_steps": 116, "total_steps": 129, "loss": 0.1818, "lr": 2.4849432843208786e-07, "epoch": 2.697674418604651, "percentage": 89.92, "elapsed_time": "0:03:19", "remaining_time": "0:00:22"}
+{"current_steps": 117, "total_steps": 129, "loss": 0.1548, "lr": 2.1199700045797077e-07, "epoch": 2.7209302325581395, "percentage": 90.7, "elapsed_time": "0:03:21", "remaining_time": "0:00:20"}
+{"current_steps": 118, "total_steps": 129, "loss": 0.1717, "lr": 1.7833924702570725e-07, "epoch": 2.744186046511628, "percentage": 91.47, "elapsed_time": "0:03:23", "remaining_time": "0:00:18"}
+{"current_steps": 119, "total_steps": 129, "loss": 0.1926, "lr": 1.4754102921297363e-07, "epoch": 2.7674418604651163, "percentage": 92.25, "elapsed_time": "0:03:25", "remaining_time": "0:00:17"}
+{"current_steps": 120, "total_steps": 129, "loss": 0.2606, "lr": 1.196206122203647e-07, "epoch": 2.7906976744186047, "percentage": 93.02, "elapsed_time": "0:03:26", "remaining_time": "0:00:15"}
+{"current_steps": 121, "total_steps": 129, "loss": 0.2704, "lr": 9.459455453902866e-08, "epoch": 2.813953488372093, "percentage": 93.8, "elapsed_time": "0:03:28", "remaining_time": "0:00:13"}
+{"current_steps": 122, "total_steps": 129, "loss": 0.1719, "lr": 7.247769813048644e-08, "epoch": 2.8372093023255816, "percentage": 94.57, "elapsed_time": "0:03:30", "remaining_time": "0:00:12"}
+{"current_steps": 123, "total_steps": 129, "loss": 0.1712, "lr": 5.3283159624448745e-08, "epoch": 2.8604651162790695, "percentage": 95.35, "elapsed_time": "0:03:31", "remaining_time": "0:00:10"}
+{"current_steps": 124, "total_steps": 129, "loss": 0.2064, "lr": 3.702232253986804e-08, "epoch": 2.883720930232558, "percentage": 96.12, "elapsed_time": "0:03:33", "remaining_time": "0:00:08"}
+{"current_steps": 125, "total_steps": 129, "loss": 0.1649, "lr": 2.370483053382111e-08, "epoch": 2.9069767441860463, "percentage": 96.9, "elapsed_time": "0:03:35", "remaining_time": "0:00:06"}
+{"current_steps": 126, "total_steps": 129, "loss": 0.1835, "lr": 1.333858168224178e-08, "epoch": 2.9302325581395348, "percentage": 97.67, "elapsed_time": "0:03:37", "remaining_time": "0:00:05"}
+{"current_steps": 127, "total_steps": 129, "loss": 0.1688, "lr": 5.929723795884967e-09, "epoch": 2.953488372093023, "percentage": 98.45, "elapsed_time": "0:03:38", "remaining_time": "0:00:03"}
+{"current_steps": 128, "total_steps": 129, "loss": 0.1765, "lr": 1.4826507743032071e-09, "epoch": 2.9767441860465116, "percentage": 99.22, "elapsed_time": "0:03:40", "remaining_time": "0:00:01"}
+{"current_steps": 129, "total_steps": 129, "loss": 0.2224, "lr": 0.0, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "0:03:42", "remaining_time": "0:00:00"}
+{"current_steps": 129, "total_steps": 129, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "0:03:42", "remaining_time": "0:00:00"}

mta_7b_full/trainer_state.json

@@ -0,0 +1,945 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 129,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.023255813953488372,
+      "grad_norm": 70.32077026367188,
+      "learning_rate": 9.998517349225698e-06,
+      "loss": 1.279,
+      "step": 1
+    },
+    {
+      "epoch": 0.046511627906976744,
+      "grad_norm": 37.53902816772461,
+      "learning_rate": 9.994070276204115e-06,
+      "loss": 1.04,
+      "step": 2
+    },
+    {
+      "epoch": 0.06976744186046512,
+      "grad_norm": 1184.9375,
+      "learning_rate": 9.986661418317759e-06,
+      "loss": 11.9749,
+      "step": 3
+    },
+    {
+      "epoch": 0.09302325581395349,
+      "grad_norm": 9.502654075622559,
+      "learning_rate": 9.97629516946618e-06,
+      "loss": 1.0116,
+      "step": 4
+    },
+    {
+      "epoch": 0.11627906976744186,
+      "grad_norm": 17.266721725463867,
+      "learning_rate": 9.962977677460132e-06,
+      "loss": 0.8886,
+      "step": 5
+    },
+    {
+      "epoch": 0.13953488372093023,
+      "grad_norm": 6.6040143966674805,
+      "learning_rate": 9.946716840375552e-06,
+      "loss": 0.9208,
+      "step": 6
+    },
+    {
+      "epoch": 0.16279069767441862,
+      "grad_norm": 6.375622749328613,
+      "learning_rate": 9.927522301869515e-06,
+      "loss": 0.8859,
+      "step": 7
+    },
+    {
+      "epoch": 0.18604651162790697,
+      "grad_norm": 4.993012428283691,
+      "learning_rate": 9.905405445460972e-06,
+      "loss": 0.669,
+      "step": 8
+    },
+    {
+      "epoch": 0.20930232558139536,
+      "grad_norm": 6.4952216148376465,
+      "learning_rate": 9.880379387779637e-06,
+      "loss": 0.9212,
+      "step": 9
+    },
+    {
+      "epoch": 0.23255813953488372,
+      "grad_norm": 6.618288993835449,
+      "learning_rate": 9.852458970787027e-06,
+      "loss": 0.7304,
+      "step": 10
+    },
+    {
+      "epoch": 0.2558139534883721,
+      "grad_norm": 6.736837863922119,
+      "learning_rate": 9.821660752974294e-06,
+      "loss": 0.8411,
+      "step": 11
+    },
+    {
+      "epoch": 0.27906976744186046,
+      "grad_norm": 5.618810653686523,
+      "learning_rate": 9.78800299954203e-06,
+      "loss": 0.7511,
+      "step": 12
+    },
+    {
+      "epoch": 0.3023255813953488,
+      "grad_norm": 5.360226154327393,
+      "learning_rate": 9.751505671567914e-06,
+      "loss": 0.763,
+      "step": 13
+    },
+    {
+      "epoch": 0.32558139534883723,
+      "grad_norm": 5.810384273529053,
+      "learning_rate": 9.712190414168573e-06,
+      "loss": 0.8875,
+      "step": 14
+    },
+    {
+      "epoch": 0.3488372093023256,
+      "grad_norm": 5.617706775665283,
+      "learning_rate": 9.670080543662742e-06,
+      "loss": 0.6891,
+      "step": 15
+    },
+    {
+      "epoch": 0.37209302325581395,
+      "grad_norm": 6.497030735015869,
+      "learning_rate": 9.625201033743262e-06,
+      "loss": 0.8419,
+      "step": 16
+    },
+    {
+      "epoch": 0.3953488372093023,
+      "grad_norm": 5.2556376457214355,
+      "learning_rate": 9.577578500666187e-06,
+      "loss": 0.7341,
+      "step": 17
+    },
+    {
+      "epoch": 0.4186046511627907,
+      "grad_norm": 5.314729690551758,
+      "learning_rate": 9.527241187465735e-06,
+      "loss": 0.8575,
+      "step": 18
+    },
+    {
+      "epoch": 0.4418604651162791,
+      "grad_norm": 5.208122253417969,
+      "learning_rate": 9.47421894720446e-06,
+      "loss": 0.7854,
+      "step": 19
+    },
+    {
+      "epoch": 0.46511627906976744,
+      "grad_norm": 6.187365531921387,
+      "learning_rate": 9.418543225268598e-06,
+      "loss": 0.7404,
+      "step": 20
+    },
+    {
+      "epoch": 0.4883720930232558,
+      "grad_norm": 5.329397678375244,
+      "learning_rate": 9.36024704071904e-06,
+      "loss": 0.8586,
+      "step": 21
+    },
+    {
+      "epoch": 0.5116279069767442,
+      "grad_norm": 24.103546142578125,
+      "learning_rate": 9.299364966709051e-06,
+      "loss": 0.7443,
+      "step": 22
+    },
+    {
+      "epoch": 0.5348837209302325,
+      "grad_norm": 5.24066162109375,
+      "learning_rate": 9.235933109980302e-06,
+      "loss": 0.6506,
+      "step": 23
+    },
+    {
+      "epoch": 0.5581395348837209,
+      "grad_norm": 5.420989990234375,
+      "learning_rate": 9.16998908944939e-06,
+      "loss": 0.7598,
+      "step": 24
+    },
+    {
+      "epoch": 0.5813953488372093,
+      "grad_norm": 6.250035285949707,
+      "learning_rate": 9.101572013897555e-06,
+      "loss": 0.7469,
+      "step": 25
+    },
+    {
+      "epoch": 0.6046511627906976,
+      "grad_norm": 6.451432228088379,
+      "learning_rate": 9.030722458776815e-06,
+      "loss": 0.8682,
+      "step": 26
+    },
+    {
+      "epoch": 0.627906976744186,
+      "grad_norm": 5.302152156829834,
+      "learning_rate": 8.957482442146271e-06,
+      "loss": 0.8632,
+      "step": 27
+    },
+    {
+      "epoch": 0.6511627906976745,
+      "grad_norm": 5.19851016998291,
+      "learning_rate": 8.881895399752873e-06,
+      "loss": 0.6599,
+      "step": 28
+    },
+    {
+      "epoch": 0.6744186046511628,
+      "grad_norm": 5.469644546508789,
+      "learning_rate": 8.80400615927139e-06,
+      "loss": 0.8089,
+      "step": 29
+    },
+    {
+      "epoch": 0.6976744186046512,
+      "grad_norm": 5.14939022064209,
+      "learning_rate": 8.72386091371891e-06,
+      "loss": 0.7626,
+      "step": 30
+    },
+    {
+      "epoch": 0.7209302325581395,
+      "grad_norm": 6.020998954772949,
+      "learning_rate": 8.64150719405958e-06,
+      "loss": 0.7286,
+      "step": 31
+    },
+    {
+      "epoch": 0.7441860465116279,
+      "grad_norm": 5.150403022766113,
+      "learning_rate": 8.55699384101589e-06,
+      "loss": 0.7357,
+      "step": 32
+    },
+    {
+      "epoch": 0.7674418604651163,
+      "grad_norm": 5.131527900695801,
+      "learning_rate": 8.470370976103171e-06,
+      "loss": 0.703,
+      "step": 33
+    },
+    {
+      "epoch": 0.7906976744186046,
+      "grad_norm": 4.434912204742432,
+      "learning_rate": 8.381689971904514e-06,
+      "loss": 0.6339,
+      "step": 34
+    },
+    {
+      "epoch": 0.813953488372093,
+      "grad_norm": 5.456267833709717,
+      "learning_rate": 8.29100342160374e-06,
+      "loss": 0.7153,
+      "step": 35
+    },
+    {
+      "epoch": 0.8372093023255814,
+      "grad_norm": 5.515677452087402,
+      "learning_rate": 8.198365107794457e-06,
+      "loss": 0.6737,
+      "step": 36
+    },
+    {
+      "epoch": 0.8604651162790697,
+      "grad_norm": 4.451297760009766,
+      "learning_rate": 8.103829970583742e-06,
+      "loss": 0.7295,
+      "step": 37
+    },
+    {
+      "epoch": 0.8837209302325582,
+      "grad_norm": 4.353997230529785,
+      "learning_rate": 8.007454075009352e-06,
+      "loss": 0.6999,
+      "step": 38
+    },
+    {
+      "epoch": 0.9069767441860465,
+      "grad_norm": 4.120194435119629,
+      "learning_rate": 7.909294577789765e-06,
+      "loss": 0.6917,
+      "step": 39
+    },
+    {
+      "epoch": 0.9302325581395349,
+      "grad_norm": 3.990830659866333,
+      "learning_rate": 7.809409693426803e-06,
+      "loss": 0.7131,
+      "step": 40
+    },
+    {
+      "epoch": 0.9534883720930233,
+      "grad_norm": 4.564643859863281,
+      "learning_rate": 7.707858659680924e-06,
+      "loss": 0.7,
+      "step": 41
+    },
+    {
+      "epoch": 0.9767441860465116,
+      "grad_norm": 3.074939727783203,
+      "learning_rate": 7.604701702439652e-06,
+      "loss": 0.6538,
+      "step": 42
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 3.021503210067749,
+      "learning_rate": 7.500000000000001e-06,
+      "loss": 0.6142,
+      "step": 43
+    },
+    {
+      "epoch": 1.0232558139534884,
+      "grad_norm": 2.9651846885681152,
+      "learning_rate": 7.393815646786047e-06,
+      "loss": 0.4602,
+      "step": 44
+    },
+    {
+      "epoch": 1.0465116279069768,
+      "grad_norm": 3.287748336791992,
+      "learning_rate": 7.286211616523193e-06,
+      "loss": 0.3917,
+      "step": 45
+    },
+    {
+      "epoch": 1.069767441860465,
+      "grad_norm": 3.1998941898345947,
+      "learning_rate": 7.177251724890957e-06,
+      "loss": 0.377,
+      "step": 46
+    },
+    {
+      "epoch": 1.0930232558139534,
+      "grad_norm": 3.309541702270508,
+      "learning_rate": 7.067000591676416e-06,
+      "loss": 0.4112,
+      "step": 47
+    },
+    {
+      "epoch": 1.1162790697674418,
+      "grad_norm": 2.465728521347046,
+      "learning_rate": 6.95552360245078e-06,
+      "loss": 0.3741,
+      "step": 48
+    },
+    {
+      "epoch": 1.1395348837209303,
+      "grad_norm": 2.2689056396484375,
+      "learning_rate": 6.84288686979181e-06,
+      "loss": 0.3554,
+      "step": 49
+    },
+    {
+      "epoch": 1.1627906976744187,
+      "grad_norm": 2.2925970554351807,
+      "learning_rate": 6.7291571940750575e-06,
+      "loss": 0.3973,
+      "step": 50
+    },
+    {
+      "epoch": 1.1860465116279069,
+      "grad_norm": 2.615603446960449,
+      "learning_rate": 6.614402023857231e-06,
+      "loss": 0.4135,
+      "step": 51
+    },
+    {
+      "epoch": 1.2093023255813953,
+      "grad_norm": 2.3845252990722656,
+      "learning_rate": 6.498689415875121e-06,
+      "loss": 0.3736,
+      "step": 52
+    },
+    {
+      "epoch": 1.2325581395348837,
+      "grad_norm": 2.9121689796447754,
+      "learning_rate": 6.3820879946838585e-06,
+      "loss": 0.4754,
+      "step": 53
+    },
+    {
+      "epoch": 1.255813953488372,
+      "grad_norm": 2.641319990158081,
+      "learning_rate": 6.264666911958404e-06,
+      "loss": 0.3985,
+      "step": 54
+    },
+    {
+      "epoch": 1.2790697674418605,
+      "grad_norm": 2.2791640758514404,
+      "learning_rate": 6.146495805482451e-06,
+      "loss": 0.3718,
+      "step": 55
+    },
+    {
+      "epoch": 1.302325581395349,
+      "grad_norm": 2.5073883533477783,
+      "learning_rate": 6.027644757849004e-06,
+      "loss": 0.4304,
+      "step": 56
+    },
+    {
+      "epoch": 1.3255813953488373,
+      "grad_norm": 2.0381178855895996,
+      "learning_rate": 5.908184254897183e-06,
+      "loss": 0.2778,
+      "step": 57
+    },
+    {
+      "epoch": 1.3488372093023255,
+      "grad_norm": 2.2005438804626465,
+      "learning_rate": 5.788185143909868e-06,
+      "loss": 0.3507,
+      "step": 58
+    },
+    {
+      "epoch": 1.372093023255814,
+      "grad_norm": 2.378105878829956,
+      "learning_rate": 5.66771859159699e-06,
+      "loss": 0.3503,
+      "step": 59
+    },
+    {
+      "epoch": 1.3953488372093024,
+      "grad_norm": 2.3897085189819336,
+      "learning_rate": 5.546856041889374e-06,
+      "loss": 0.3828,
+      "step": 60
+    },
+    {
+      "epoch": 1.4186046511627908,
+      "grad_norm": 2.4368221759796143,
+      "learning_rate": 5.425669173568179e-06,
+      "loss": 0.4213,
+      "step": 61
+    },
+    {
+      "epoch": 1.441860465116279,
+      "grad_norm": 2.285449981689453,
+      "learning_rate": 5.30422985775507e-06,
+      "loss": 0.4199,
+      "step": 62
+    },
+    {
+      "epoch": 1.4651162790697674,
+      "grad_norm": 2.3676199913024902,
+      "learning_rate": 5.182610115288296e-06,
+      "loss": 0.3162,
+      "step": 63
+    },
+    {
+      "epoch": 1.4883720930232558,
+      "grad_norm": 2.5123531818389893,
+      "learning_rate": 5.060882074009988e-06,
+      "loss": 0.3888,
+      "step": 64
+    },
+    {
+      "epoch": 1.5116279069767442,
+      "grad_norm": 2.4387993812561035,
+      "learning_rate": 4.939117925990013e-06,
+      "loss": 0.354,
+      "step": 65
+    },
+    {
+      "epoch": 1.5348837209302326,
+      "grad_norm": 2.3216540813446045,
+      "learning_rate": 4.817389884711706e-06,
+      "loss": 0.3896,
+      "step": 66
+    },
+    {
+      "epoch": 1.558139534883721,
+      "grad_norm": 2.0474302768707275,
+      "learning_rate": 4.695770142244931e-06,
+      "loss": 0.381,
+      "step": 67
+    },
+    {
+      "epoch": 1.5813953488372094,
+      "grad_norm": 2.384861707687378,
+      "learning_rate": 4.574330826431822e-06,
+      "loss": 0.4143,
+      "step": 68
+    },
+    {
+      "epoch": 1.6046511627906976,
+      "grad_norm": 2.3092775344848633,
+      "learning_rate": 4.4531439581106295e-06,
+      "loss": 0.3577,
+      "step": 69
+    },
+    {
+      "epoch": 1.627906976744186,
+      "grad_norm": 2.454482078552246,
+      "learning_rate": 4.332281408403011e-06,
+      "loss": 0.4366,
+      "step": 70
+    },
+    {
+      "epoch": 1.6511627906976745,
+      "grad_norm": 2.139082908630371,
+      "learning_rate": 4.2118148560901325e-06,
+      "loss": 0.375,
+      "step": 71
+    },
+    {
+      "epoch": 1.6744186046511627,
+      "grad_norm": 2.11677885055542,
+      "learning_rate": 4.091815745102818e-06,
+      "loss": 0.3676,
+      "step": 72
+    },
+    {
+      "epoch": 1.697674418604651,
+      "grad_norm": 14.376790046691895,
+      "learning_rate": 3.9723552421509975e-06,
+      "loss": 0.3855,
+      "step": 73
+    },
+    {
+      "epoch": 1.7209302325581395,
+      "grad_norm": 2.3848206996917725,
+      "learning_rate": 3.853504194517551e-06,
+      "loss": 0.4233,
+      "step": 74
+    },
+    {
+      "epoch": 1.744186046511628,
+      "grad_norm": 2.1235015392303467,
+      "learning_rate": 3.7353330880415963e-06,
+      "loss": 0.3835,
+      "step": 75
+    },
+    {
+      "epoch": 1.7674418604651163,
+      "grad_norm": 2.2856810092926025,
+      "learning_rate": 3.617912005316142e-06,
+      "loss": 0.4012,
+      "step": 76
+    },
+    {
+      "epoch": 1.7906976744186047,
+      "grad_norm": 2.401136636734009,
+      "learning_rate": 3.5013105841248794e-06,
+      "loss": 0.3615,
+      "step": 77
+    },
+    {
+      "epoch": 1.8139534883720931,
+      "grad_norm": 2.0682361125946045,
+      "learning_rate": 3.3855979761427705e-06,
+      "loss": 0.3489,
+      "step": 78
+    },
+    {
+      "epoch": 1.8372093023255816,
+      "grad_norm": 2.219710350036621,
+      "learning_rate": 3.2708428059249437e-06,
+      "loss": 0.4164,
+      "step": 79
+    },
+    {
+      "epoch": 1.8604651162790697,
+      "grad_norm": 2.318739175796509,
+      "learning_rate": 3.1571131302081916e-06,
+      "loss": 0.374,
+      "step": 80
+    },
+    {
+      "epoch": 1.8837209302325582,
+      "grad_norm": 2.390282154083252,
+      "learning_rate": 3.044476397549221e-06,
+      "loss": 0.4293,
+      "step": 81
+    },
+    {
+      "epoch": 1.9069767441860463,
+      "grad_norm": 1.9498318433761597,
+      "learning_rate": 2.9329994083235857e-06,
+      "loss": 0.3804,
+      "step": 82
+    },
+    {
+      "epoch": 1.9302325581395348,
+      "grad_norm": 2.142402172088623,
+      "learning_rate": 2.8227482751090445e-06,
+      "loss": 0.4171,
+      "step": 83
+    },
+    {
+      "epoch": 1.9534883720930232,
+      "grad_norm": 2.194898843765259,
+      "learning_rate": 2.7137883834768076e-06,
+      "loss": 0.3308,
+      "step": 84
+    },
+    {
+      "epoch": 1.9767441860465116,
+      "grad_norm": 2.0601766109466553,
+      "learning_rate": 2.6061843532139563e-06,
+      "loss": 0.3149,
+      "step": 85
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 2.1713063716888428,
+      "learning_rate": 2.5000000000000015e-06,
+      "loss": 0.4402,
+      "step": 86
+    },
+    {
+      "epoch": 2.0232558139534884,
+      "grad_norm": 1.9286260604858398,
+      "learning_rate": 2.3952982975603494e-06,
+      "loss": 0.2177,
+      "step": 87
+    },
+    {
+      "epoch": 2.046511627906977,
+      "grad_norm": 2.0531747341156006,
+      "learning_rate": 2.2921413403190774e-06,
+      "loss": 0.223,
+      "step": 88
+    },
+    {
+      "epoch": 2.0697674418604652,
+      "grad_norm": 1.9692027568817139,
+      "learning_rate": 2.190590306573198e-06,
+      "loss": 0.2095,
+      "step": 89
+    },
+    {
+      "epoch": 2.0930232558139537,
+      "grad_norm": 1.801230788230896,
+      "learning_rate": 2.0907054222102367e-06,
+      "loss": 0.2738,
+      "step": 90
+    },
+    {
+      "epoch": 2.116279069767442,
+      "grad_norm": 1.6908445358276367,
+      "learning_rate": 1.9925459249906488e-06,
+      "loss": 0.1668,
+      "step": 91
+    },
+    {
+      "epoch": 2.13953488372093,
+      "grad_norm": 1.8621448278427124,
+      "learning_rate": 1.8961700294162578e-06,
+      "loss": 0.2361,
+      "step": 92
+    },
+    {
+      "epoch": 2.1627906976744184,
+      "grad_norm": 1.6637578010559082,
+      "learning_rate": 1.8016348922055448e-06,
+      "loss": 0.1405,
+      "step": 93
+    },
+    {
+      "epoch": 2.186046511627907,
+      "grad_norm": 1.8127702474594116,
+      "learning_rate": 1.7089965783962608e-06,
+      "loss": 0.1582,
+      "step": 94
+    },
+    {
+      "epoch": 2.2093023255813953,
+      "grad_norm": 1.9022613763809204,
+      "learning_rate": 1.618310028095486e-06,
+      "loss": 0.2072,
+      "step": 95
+    },
+    {
+      "epoch": 2.2325581395348837,
+      "grad_norm": 2.235344648361206,
+      "learning_rate": 1.5296290238968303e-06,
+      "loss": 0.2166,
+      "step": 96
+    },
+    {
+      "epoch": 2.255813953488372,
+      "grad_norm": 2.583035945892334,
+      "learning_rate": 1.4430061589841122e-06,
+      "loss": 0.2256,
+      "step": 97
+    },
+    {
+      "epoch": 2.2790697674418605,
+      "grad_norm": 2.1760542392730713,
+      "learning_rate": 1.3584928059404207e-06,
+      "loss": 0.1825,
+      "step": 98
+    },
+    {
+      "epoch": 2.302325581395349,
+      "grad_norm": 2.2850911617279053,
+      "learning_rate": 1.2761390862810907e-06,
+      "loss": 0.2092,
+      "step": 99
+    },
+    {
+      "epoch": 2.3255813953488373,
+      "grad_norm": 2.945713996887207,
+      "learning_rate": 1.1959938407286099e-06,
+      "loss": 0.1779,
+      "step": 100
+    },
+    {
+      "epoch": 2.3488372093023258,
+      "grad_norm": 2.0344932079315186,
+      "learning_rate": 1.1181046002471292e-06,
+      "loss": 0.2296,
+      "step": 101
+    },
+    {
+      "epoch": 2.3720930232558137,
+      "grad_norm": 1.7861090898513794,
+      "learning_rate": 1.04251755785373e-06,
+      "loss": 0.1937,
+      "step": 102
+    },
+    {
+      "epoch": 2.395348837209302,
+      "grad_norm": 1.96769380569458,
+      "learning_rate": 9.692775412231863e-07,
+      "loss": 0.1514,
+      "step": 103
+    },
+    {
+      "epoch": 2.4186046511627906,
+      "grad_norm": 1.9104843139648438,
+      "learning_rate": 8.984279861024453e-07,
+      "loss": 0.2083,
+      "step": 104
+    },
+    {
+      "epoch": 2.441860465116279,
+      "grad_norm": 1.8474905490875244,
+      "learning_rate": 8.30010910550611e-07,
+      "loss": 0.1608,
+      "step": 105
+    },
+    {
+      "epoch": 2.4651162790697674,
+      "grad_norm": 1.7861213684082031,
+      "learning_rate": 7.640668900196985e-07,
+      "loss": 0.1763,
+      "step": 106
+    },
+    {
+      "epoch": 2.488372093023256,
+      "grad_norm": 1.8975013494491577,
+      "learning_rate": 7.006350332909495e-07,
+      "loss": 0.227,
+      "step": 107
+    },
+    {
+      "epoch": 2.511627906976744,
+      "grad_norm": 1.894180178642273,
+      "learning_rate": 6.397529592809615e-07,
+      "loss": 0.1635,
+      "step": 108
+    },
+    {
+      "epoch": 2.5348837209302326,
+      "grad_norm": 1.73007071018219,
+      "learning_rate": 5.814567747314049e-07,
+      "loss": 0.1909,
+      "step": 109
+    },
+    {
+      "epoch": 2.558139534883721,
+      "grad_norm": 1.6185288429260254,
+      "learning_rate": 5.25781052795541e-07,
+      "loss": 0.1529,
+      "step": 110
+    },
+    {
+      "epoch": 2.5813953488372094,
+      "grad_norm": 1.830949068069458,
+      "learning_rate": 4.727588125342669e-07,
+      "loss": 0.2039,
+      "step": 111
+    },
+    {
+      "epoch": 2.604651162790698,
+      "grad_norm": 1.7728360891342163,
+      "learning_rate": 4.224214993338149e-07,
+      "loss": 0.1689,
+      "step": 112
+    },
+    {
+      "epoch": 2.6279069767441863,
+      "grad_norm": 1.7013224363327026,
+      "learning_rate": 3.747989662567403e-07,
+      "loss": 0.2066,
+      "step": 113
+    },
+    {
+      "epoch": 2.6511627906976747,
+      "grad_norm": 1.7414528131484985,
+      "learning_rate": 3.299194563372604e-07,
+      "loss": 0.1758,
+      "step": 114
+    },
+    {
+      "epoch": 2.6744186046511627,
+      "grad_norm": 1.971104621887207,
+      "learning_rate": 2.878095858314278e-07,
+      "loss": 0.2181,
+      "step": 115
+    },
+    {
+      "epoch": 2.697674418604651,
+      "grad_norm": 1.7847325801849365,
+      "learning_rate": 2.4849432843208786e-07,
+      "loss": 0.1818,
+      "step": 116
+    },
+    {
+      "epoch": 2.7209302325581395,
+      "grad_norm": 1.6964150667190552,
+      "learning_rate": 2.1199700045797077e-07,
+      "loss": 0.1548,
+      "step": 117
+    },
+    {
+      "epoch": 2.744186046511628,
+      "grad_norm": 1.8193210363388062,
+      "learning_rate": 1.7833924702570725e-07,
+      "loss": 0.1717,
+      "step": 118
+    },
+    {
+      "epoch": 2.7674418604651163,
+      "grad_norm": 1.6728464365005493,
+      "learning_rate": 1.4754102921297363e-07,
+      "loss": 0.1926,
+      "step": 119
+    },
+    {
+      "epoch": 2.7906976744186047,
+      "grad_norm": 2.0328001976013184,
+      "learning_rate": 1.196206122203647e-07,
+      "loss": 0.2606,
+      "step": 120
+    },
+    {
+      "epoch": 2.813953488372093,
+      "grad_norm": 2.100332021713257,
+      "learning_rate": 9.459455453902866e-08,
+      "loss": 0.2704,
+      "step": 121
+    },
+    {
+      "epoch": 2.8372093023255816,
+      "grad_norm": 1.8182084560394287,
+      "learning_rate": 7.247769813048644e-08,
+      "loss": 0.1719,
+      "step": 122
+    },
+    {
+      "epoch": 2.8604651162790695,
+      "grad_norm": 1.5356546640396118,
+      "learning_rate": 5.3283159624448745e-08,
+      "loss": 0.1712,
+      "step": 123
+    },
+    {
+      "epoch": 2.883720930232558,
+      "grad_norm": 1.764734148979187,
+      "learning_rate": 3.702232253986804e-08,
+      "loss": 0.2064,
+      "step": 124
+    },
+    {
+      "epoch": 2.9069767441860463,
+      "grad_norm": 1.8702075481414795,
+      "learning_rate": 2.370483053382111e-08,
+      "loss": 0.1649,
+      "step": 125
+    },
+    {
+      "epoch": 2.9302325581395348,
+      "grad_norm": 1.7619831562042236,
+      "learning_rate": 1.333858168224178e-08,
+      "loss": 0.1835,
+      "step": 126
+    },
+    {
+      "epoch": 2.953488372093023,
+      "grad_norm": 1.5731347799301147,
+      "learning_rate": 5.929723795884967e-09,
+      "loss": 0.1688,
+      "step": 127
+    },
+    {
+      "epoch": 2.9767441860465116,
+      "grad_norm": 1.7342948913574219,
+      "learning_rate": 1.4826507743032071e-09,
+      "loss": 0.1765,
+      "step": 128
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 1.701012134552002,
+      "learning_rate": 0.0,
+      "loss": 0.2224,
+      "step": 129
+    },
+    {
+      "epoch": 3.0,
+      "step": 129,
+      "total_flos": 1.7932809270617702e+17,
+      "train_loss": 0.5420024356869764,
+      "train_runtime": 227.6568,
+      "train_samples_per_second": 4.533,
+      "train_steps_per_second": 0.567
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 129,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": false,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.7932809270617702e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

mta_7b_full/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a3832ca5a39911e809d59bd3f4a0cf592064aa93a22395d6494a7bb627d748c
+size 7096

ra_7b_full/README.md

@@ -0,0 +1,59 @@
+---
+library_name: transformers
+license: other
+base_model: /mnt/workspace/Models/Qwen2.5-7B
+tags:
+- llama-factory
+- full
+- generated_from_trainer
+model-index:
+- name: ra_7b_full
+  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. -->
+
+# ra_7b_full
+
+This model is a fine-tuned version of [/mnt/workspace/Models/Qwen2.5-7B](https://huggingface.co//mnt/workspace/Models/Qwen2.5-7B) on the ra_multi_turn_mamrp 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: 1e-05
+- train_batch_size: 1
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 8
+- total_train_batch_size: 8
+- total_eval_batch_size: 64
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- num_epochs: 3.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.45.2
+- Pytorch 2.4.0+cu121
+- Datasets 3.1.0
+- Tokenizers 0.20.3

ra_7b_full/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
+}

ra_7b_full/all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 3.0,
+    "eval_loss": 0.4410874843597412,
+    "eval_runtime": 1.6644,
+    "eval_samples_per_second": 20.428,
+    "eval_steps_per_second": 3.004,
+    "total_flos": 1.7932809270617702e+17,
+    "train_loss": 0.22525020212281582,
+    "train_runtime": 228.5945,
+    "train_samples_per_second": 4.449,
+    "train_steps_per_second": 0.564
+}

ra_7b_full/config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "/mnt/workspace/Models/Qwen2.5-7B",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 131072,
+  "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": "4.45.2",
+  "use_cache": false,
+  "use_mrope": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

ra_7b_full/eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 3.0,
+    "eval_loss": 0.4410874843597412,
+    "eval_runtime": 1.6644,
+    "eval_samples_per_second": 20.428,
+    "eval_steps_per_second": 3.004
+}

ra_7b_full/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "max_new_tokens": 2048,
+  "transformers_version": "4.45.2"
+}

ra_7b_full/model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8885ce6cfb96a9336223992992ec4b172ebe5aaf9502455c1af046bcdce6625e
+size 4877660776

ra_7b_full/model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:207fd3fc204500dda4e1fa4e19763907b8ffbcf9418f77991c3da4b8c18ecf6f
+size 4932751008

ra_7b_full/model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:860c5023321d7b1864226a7a0bfed6c481db80d02f104fae3d08c7cb724b36a5
+size 4330865200

ra_7b_full/model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13ddf55da229723f198935adadc75ba5edf209509bd36962e5abc0ed9cc54c6a
+size 1089994880

ra_7b_full/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"
+  }
+}

ra_7b_full/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
+  }
+}

ra_7b_full/tokenizer.json

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

ra_7b_full/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 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 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
+}

ra_7b_full/train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "total_flos": 1.7932809270617702e+17,
+    "train_loss": 0.22525020212281582,
+    "train_runtime": 228.5945,
+    "train_samples_per_second": 4.449,
+    "train_steps_per_second": 0.564
+}

ra_7b_full/trainer_log.jsonl

@@ -0,0 +1,130 @@
+{"current_steps": 1, "total_steps": 129, "loss": 0.5915, "lr": 9.998517349225698e-06, "epoch": 0.023255813953488372, "percentage": 0.78, "elapsed_time": "0:00:02", "remaining_time": "0:05:04"}
+{"current_steps": 2, "total_steps": 129, "loss": 0.5619, "lr": 9.994070276204115e-06, "epoch": 0.046511627906976744, "percentage": 1.55, "elapsed_time": "0:00:04", "remaining_time": "0:04:19"}
+{"current_steps": 3, "total_steps": 129, "loss": 0.5208, "lr": 9.986661418317759e-06, "epoch": 0.06976744186046512, "percentage": 2.33, "elapsed_time": "0:00:05", "remaining_time": "0:04:03"}
+{"current_steps": 4, "total_steps": 129, "loss": 0.4364, "lr": 9.97629516946618e-06, "epoch": 0.09302325581395349, "percentage": 3.1, "elapsed_time": "0:00:07", "remaining_time": "0:03:54"}
+{"current_steps": 5, "total_steps": 129, "loss": 0.5167, "lr": 9.962977677460132e-06, "epoch": 0.11627906976744186, "percentage": 3.88, "elapsed_time": "0:00:09", "remaining_time": "0:03:48"}
+{"current_steps": 6, "total_steps": 129, "loss": 0.523, "lr": 9.946716840375552e-06, "epoch": 0.13953488372093023, "percentage": 4.65, "elapsed_time": "0:00:10", "remaining_time": "0:03:43"}
+{"current_steps": 7, "total_steps": 129, "loss": 0.4686, "lr": 9.927522301869515e-06, "epoch": 0.16279069767441862, "percentage": 5.43, "elapsed_time": "0:00:12", "remaining_time": "0:03:39"}
+{"current_steps": 8, "total_steps": 129, "loss": 0.3999, "lr": 9.905405445460972e-06, "epoch": 0.18604651162790697, "percentage": 6.2, "elapsed_time": "0:00:14", "remaining_time": "0:03:36"}
+{"current_steps": 9, "total_steps": 129, "loss": 0.3737, "lr": 9.880379387779637e-06, "epoch": 0.20930232558139536, "percentage": 6.98, "elapsed_time": "0:00:16", "remaining_time": "0:03:33"}
+{"current_steps": 10, "total_steps": 129, "loss": 0.5348, "lr": 9.852458970787027e-06, "epoch": 0.23255813953488372, "percentage": 7.75, "elapsed_time": "0:00:17", "remaining_time": "0:03:30"}
+{"current_steps": 11, "total_steps": 129, "loss": 0.4295, "lr": 9.821660752974294e-06, "epoch": 0.2558139534883721, "percentage": 8.53, "elapsed_time": "0:00:19", "remaining_time": "0:03:28"}
+{"current_steps": 12, "total_steps": 129, "loss": 0.4027, "lr": 9.78800299954203e-06, "epoch": 0.27906976744186046, "percentage": 9.3, "elapsed_time": "0:00:21", "remaining_time": "0:03:26"}
+{"current_steps": 13, "total_steps": 129, "loss": 0.439, "lr": 9.751505671567914e-06, "epoch": 0.3023255813953488, "percentage": 10.08, "elapsed_time": "0:00:22", "remaining_time": "0:03:23"}
+{"current_steps": 14, "total_steps": 129, "loss": 0.3994, "lr": 9.712190414168573e-06, "epoch": 0.32558139534883723, "percentage": 10.85, "elapsed_time": "0:00:24", "remaining_time": "0:03:21"}
+{"current_steps": 15, "total_steps": 129, "loss": 0.374, "lr": 9.670080543662742e-06, "epoch": 0.3488372093023256, "percentage": 11.63, "elapsed_time": "0:00:26", "remaining_time": "0:03:19"}
+{"current_steps": 16, "total_steps": 129, "loss": 0.4716, "lr": 9.625201033743262e-06, "epoch": 0.37209302325581395, "percentage": 12.4, "elapsed_time": "0:00:28", "remaining_time": "0:03:17"}
+{"current_steps": 17, "total_steps": 129, "loss": 0.4829, "lr": 9.577578500666187e-06, "epoch": 0.3953488372093023, "percentage": 13.18, "elapsed_time": "0:00:29", "remaining_time": "0:03:15"}
+{"current_steps": 18, "total_steps": 129, "loss": 0.4792, "lr": 9.527241187465735e-06, "epoch": 0.4186046511627907, "percentage": 13.95, "elapsed_time": "0:00:31", "remaining_time": "0:03:14"}
+{"current_steps": 19, "total_steps": 129, "loss": 0.2867, "lr": 9.47421894720446e-06, "epoch": 0.4418604651162791, "percentage": 14.73, "elapsed_time": "0:00:33", "remaining_time": "0:03:12"}
+{"current_steps": 20, "total_steps": 129, "loss": 0.4133, "lr": 9.418543225268598e-06, "epoch": 0.46511627906976744, "percentage": 15.5, "elapsed_time": "0:00:34", "remaining_time": "0:03:10"}
+{"current_steps": 21, "total_steps": 129, "loss": 0.4108, "lr": 9.36024704071904e-06, "epoch": 0.4883720930232558, "percentage": 16.28, "elapsed_time": "0:00:36", "remaining_time": "0:03:08"}
+{"current_steps": 22, "total_steps": 129, "loss": 0.3883, "lr": 9.299364966709051e-06, "epoch": 0.5116279069767442, "percentage": 17.05, "elapsed_time": "0:00:38", "remaining_time": "0:03:06"}
+{"current_steps": 23, "total_steps": 129, "loss": 0.3584, "lr": 9.235933109980302e-06, "epoch": 0.5348837209302325, "percentage": 17.83, "elapsed_time": "0:00:40", "remaining_time": "0:03:04"}
+{"current_steps": 24, "total_steps": 129, "loss": 0.3716, "lr": 9.16998908944939e-06, "epoch": 0.5581395348837209, "percentage": 18.6, "elapsed_time": "0:00:41", "remaining_time": "0:03:02"}
+{"current_steps": 25, "total_steps": 129, "loss": 0.4743, "lr": 9.101572013897555e-06, "epoch": 0.5813953488372093, "percentage": 19.38, "elapsed_time": "0:00:43", "remaining_time": "0:03:00"}
+{"current_steps": 26, "total_steps": 129, "loss": 0.4169, "lr": 9.030722458776815e-06, "epoch": 0.6046511627906976, "percentage": 20.16, "elapsed_time": "0:00:45", "remaining_time": "0:02:59"}
+{"current_steps": 27, "total_steps": 129, "loss": 0.4298, "lr": 8.957482442146271e-06, "epoch": 0.627906976744186, "percentage": 20.93, "elapsed_time": "0:00:46", "remaining_time": "0:02:57"}
+{"current_steps": 28, "total_steps": 129, "loss": 0.4511, "lr": 8.881895399752873e-06, "epoch": 0.6511627906976745, "percentage": 21.71, "elapsed_time": "0:00:48", "remaining_time": "0:02:55"}
+{"current_steps": 29, "total_steps": 129, "loss": 0.4405, "lr": 8.80400615927139e-06, "epoch": 0.6744186046511628, "percentage": 22.48, "elapsed_time": "0:00:50", "remaining_time": "0:02:53"}
+{"current_steps": 30, "total_steps": 129, "loss": 0.3792, "lr": 8.72386091371891e-06, "epoch": 0.6976744186046512, "percentage": 23.26, "elapsed_time": "0:00:52", "remaining_time": "0:02:51"}
+{"current_steps": 31, "total_steps": 129, "loss": 0.3209, "lr": 8.64150719405958e-06, "epoch": 0.7209302325581395, "percentage": 24.03, "elapsed_time": "0:00:53", "remaining_time": "0:02:50"}
+{"current_steps": 32, "total_steps": 129, "loss": 0.5218, "lr": 8.55699384101589e-06, "epoch": 0.7441860465116279, "percentage": 24.81, "elapsed_time": "0:00:55", "remaining_time": "0:02:48"}
+{"current_steps": 33, "total_steps": 129, "loss": 0.3964, "lr": 8.470370976103171e-06, "epoch": 0.7674418604651163, "percentage": 25.58, "elapsed_time": "0:00:57", "remaining_time": "0:02:46"}
+{"current_steps": 34, "total_steps": 129, "loss": 0.4212, "lr": 8.381689971904514e-06, "epoch": 0.7906976744186046, "percentage": 26.36, "elapsed_time": "0:00:58", "remaining_time": "0:02:44"}
+{"current_steps": 35, "total_steps": 129, "loss": 0.3213, "lr": 8.29100342160374e-06, "epoch": 0.813953488372093, "percentage": 27.13, "elapsed_time": "0:01:00", "remaining_time": "0:02:43"}
+{"current_steps": 36, "total_steps": 129, "loss": 0.3899, "lr": 8.198365107794457e-06, "epoch": 0.8372093023255814, "percentage": 27.91, "elapsed_time": "0:01:02", "remaining_time": "0:02:41"}
+{"current_steps": 37, "total_steps": 129, "loss": 0.4202, "lr": 8.103829970583742e-06, "epoch": 0.8604651162790697, "percentage": 28.68, "elapsed_time": "0:01:04", "remaining_time": "0:02:39"}
+{"current_steps": 38, "total_steps": 129, "loss": 0.3792, "lr": 8.007454075009352e-06, "epoch": 0.8837209302325582, "percentage": 29.46, "elapsed_time": "0:01:05", "remaining_time": "0:02:37"}
+{"current_steps": 39, "total_steps": 129, "loss": 0.3039, "lr": 7.909294577789765e-06, "epoch": 0.9069767441860465, "percentage": 30.23, "elapsed_time": "0:01:07", "remaining_time": "0:02:35"}
+{"current_steps": 40, "total_steps": 129, "loss": 0.3319, "lr": 7.809409693426803e-06, "epoch": 0.9302325581395349, "percentage": 31.01, "elapsed_time": "0:01:09", "remaining_time": "0:02:34"}
+{"current_steps": 41, "total_steps": 129, "loss": 0.4377, "lr": 7.707858659680924e-06, "epoch": 0.9534883720930233, "percentage": 31.78, "elapsed_time": "0:01:11", "remaining_time": "0:02:32"}
+{"current_steps": 42, "total_steps": 129, "loss": 0.2886, "lr": 7.604701702439652e-06, "epoch": 0.9767441860465116, "percentage": 32.56, "elapsed_time": "0:01:12", "remaining_time": "0:02:30"}
+{"current_steps": 43, "total_steps": 129, "loss": 0.2611, "lr": 7.500000000000001e-06, "epoch": 1.0, "percentage": 33.33, "elapsed_time": "0:01:14", "remaining_time": "0:02:28"}
+{"current_steps": 44, "total_steps": 129, "loss": 0.2508, "lr": 7.393815646786047e-06, "epoch": 1.0232558139534884, "percentage": 34.11, "elapsed_time": "0:01:16", "remaining_time": "0:02:27"}
+{"current_steps": 45, "total_steps": 129, "loss": 0.1855, "lr": 7.286211616523193e-06, "epoch": 1.0465116279069768, "percentage": 34.88, "elapsed_time": "0:01:17", "remaining_time": "0:02:25"}
+{"current_steps": 46, "total_steps": 129, "loss": 0.1717, "lr": 7.177251724890957e-06, "epoch": 1.069767441860465, "percentage": 35.66, "elapsed_time": "0:01:19", "remaining_time": "0:02:23"}
+{"current_steps": 47, "total_steps": 129, "loss": 0.1738, "lr": 7.067000591676416e-06, "epoch": 1.0930232558139534, "percentage": 36.43, "elapsed_time": "0:01:21", "remaining_time": "0:02:21"}
+{"current_steps": 48, "total_steps": 129, "loss": 0.207, "lr": 6.95552360245078e-06, "epoch": 1.1162790697674418, "percentage": 37.21, "elapsed_time": "0:01:23", "remaining_time": "0:02:20"}
+{"current_steps": 49, "total_steps": 129, "loss": 0.1661, "lr": 6.84288686979181e-06, "epoch": 1.1395348837209303, "percentage": 37.98, "elapsed_time": "0:01:24", "remaining_time": "0:02:18"}
+{"current_steps": 50, "total_steps": 129, "loss": 0.2372, "lr": 6.7291571940750575e-06, "epoch": 1.1627906976744187, "percentage": 38.76, "elapsed_time": "0:01:26", "remaining_time": "0:02:16"}
+{"current_steps": 51, "total_steps": 129, "loss": 0.193, "lr": 6.614402023857231e-06, "epoch": 1.1860465116279069, "percentage": 39.53, "elapsed_time": "0:01:28", "remaining_time": "0:02:14"}
+{"current_steps": 52, "total_steps": 129, "loss": 0.1534, "lr": 6.498689415875121e-06, "epoch": 1.2093023255813953, "percentage": 40.31, "elapsed_time": "0:01:29", "remaining_time": "0:02:13"}
+{"current_steps": 53, "total_steps": 129, "loss": 0.1902, "lr": 6.3820879946838585e-06, "epoch": 1.2325581395348837, "percentage": 41.09, "elapsed_time": "0:01:31", "remaining_time": "0:02:11"}
+{"current_steps": 54, "total_steps": 129, "loss": 0.1829, "lr": 6.264666911958404e-06, "epoch": 1.255813953488372, "percentage": 41.86, "elapsed_time": "0:01:33", "remaining_time": "0:02:09"}
+{"current_steps": 55, "total_steps": 129, "loss": 0.1887, "lr": 6.146495805482451e-06, "epoch": 1.2790697674418605, "percentage": 42.64, "elapsed_time": "0:01:35", "remaining_time": "0:02:07"}
+{"current_steps": 56, "total_steps": 129, "loss": 0.1868, "lr": 6.027644757849004e-06, "epoch": 1.302325581395349, "percentage": 43.41, "elapsed_time": "0:01:36", "remaining_time": "0:02:06"}
+{"current_steps": 57, "total_steps": 129, "loss": 0.1618, "lr": 5.908184254897183e-06, "epoch": 1.3255813953488373, "percentage": 44.19, "elapsed_time": "0:01:38", "remaining_time": "0:02:04"}
+{"current_steps": 58, "total_steps": 129, "loss": 0.1542, "lr": 5.788185143909868e-06, "epoch": 1.3488372093023255, "percentage": 44.96, "elapsed_time": "0:01:40", "remaining_time": "0:02:02"}
+{"current_steps": 59, "total_steps": 129, "loss": 0.1777, "lr": 5.66771859159699e-06, "epoch": 1.372093023255814, "percentage": 45.74, "elapsed_time": "0:01:41", "remaining_time": "0:02:00"}
+{"current_steps": 60, "total_steps": 129, "loss": 0.1527, "lr": 5.546856041889374e-06, "epoch": 1.3953488372093024, "percentage": 46.51, "elapsed_time": "0:01:43", "remaining_time": "0:01:59"}
+{"current_steps": 61, "total_steps": 129, "loss": 0.217, "lr": 5.425669173568179e-06, "epoch": 1.4186046511627908, "percentage": 47.29, "elapsed_time": "0:01:45", "remaining_time": "0:01:57"}
+{"current_steps": 62, "total_steps": 129, "loss": 0.1896, "lr": 5.30422985775507e-06, "epoch": 1.441860465116279, "percentage": 48.06, "elapsed_time": "0:01:47", "remaining_time": "0:01:55"}
+{"current_steps": 63, "total_steps": 129, "loss": 0.1729, "lr": 5.182610115288296e-06, "epoch": 1.4651162790697674, "percentage": 48.84, "elapsed_time": "0:01:48", "remaining_time": "0:01:53"}
+{"current_steps": 64, "total_steps": 129, "loss": 0.263, "lr": 5.060882074009988e-06, "epoch": 1.4883720930232558, "percentage": 49.61, "elapsed_time": "0:01:50", "remaining_time": "0:01:52"}
+{"current_steps": 65, "total_steps": 129, "loss": 0.1975, "lr": 4.939117925990013e-06, "epoch": 1.5116279069767442, "percentage": 50.39, "elapsed_time": "0:01:52", "remaining_time": "0:01:50"}
+{"current_steps": 66, "total_steps": 129, "loss": 0.1681, "lr": 4.817389884711706e-06, "epoch": 1.5348837209302326, "percentage": 51.16, "elapsed_time": "0:01:53", "remaining_time": "0:01:48"}
+{"current_steps": 67, "total_steps": 129, "loss": 0.1547, "lr": 4.695770142244931e-06, "epoch": 1.558139534883721, "percentage": 51.94, "elapsed_time": "0:01:55", "remaining_time": "0:01:47"}
+{"current_steps": 68, "total_steps": 129, "loss": 0.1394, "lr": 4.574330826431822e-06, "epoch": 1.5813953488372094, "percentage": 52.71, "elapsed_time": "0:01:57", "remaining_time": "0:01:45"}
+{"current_steps": 69, "total_steps": 129, "loss": 0.1612, "lr": 4.4531439581106295e-06, "epoch": 1.6046511627906976, "percentage": 53.49, "elapsed_time": "0:01:59", "remaining_time": "0:01:43"}
+{"current_steps": 70, "total_steps": 129, "loss": 0.1686, "lr": 4.332281408403011e-06, "epoch": 1.627906976744186, "percentage": 54.26, "elapsed_time": "0:02:00", "remaining_time": "0:01:41"}
+{"current_steps": 71, "total_steps": 129, "loss": 0.2138, "lr": 4.2118148560901325e-06, "epoch": 1.6511627906976745, "percentage": 55.04, "elapsed_time": "0:02:02", "remaining_time": "0:01:40"}
+{"current_steps": 72, "total_steps": 129, "loss": 0.1673, "lr": 4.091815745102818e-06, "epoch": 1.6744186046511627, "percentage": 55.81, "elapsed_time": "0:02:04", "remaining_time": "0:01:38"}
+{"current_steps": 73, "total_steps": 129, "loss": 0.1913, "lr": 3.9723552421509975e-06, "epoch": 1.697674418604651, "percentage": 56.59, "elapsed_time": "0:02:05", "remaining_time": "0:01:36"}
+{"current_steps": 74, "total_steps": 129, "loss": 0.1832, "lr": 3.853504194517551e-06, "epoch": 1.7209302325581395, "percentage": 57.36, "elapsed_time": "0:02:07", "remaining_time": "0:01:34"}
+{"current_steps": 75, "total_steps": 129, "loss": 0.1939, "lr": 3.7353330880415963e-06, "epoch": 1.744186046511628, "percentage": 58.14, "elapsed_time": "0:02:09", "remaining_time": "0:01:33"}
+{"current_steps": 76, "total_steps": 129, "loss": 0.1787, "lr": 3.617912005316142e-06, "epoch": 1.7674418604651163, "percentage": 58.91, "elapsed_time": "0:02:11", "remaining_time": "0:01:31"}
+{"current_steps": 77, "total_steps": 129, "loss": 0.202, "lr": 3.5013105841248794e-06, "epoch": 1.7906976744186047, "percentage": 59.69, "elapsed_time": "0:02:12", "remaining_time": "0:01:29"}
+{"current_steps": 78, "total_steps": 129, "loss": 0.1411, "lr": 3.3855979761427705e-06, "epoch": 1.8139534883720931, "percentage": 60.47, "elapsed_time": "0:02:14", "remaining_time": "0:01:27"}
+{"current_steps": 79, "total_steps": 129, "loss": 0.2009, "lr": 3.2708428059249437e-06, "epoch": 1.8372093023255816, "percentage": 61.24, "elapsed_time": "0:02:16", "remaining_time": "0:01:26"}
+{"current_steps": 80, "total_steps": 129, "loss": 0.158, "lr": 3.1571131302081916e-06, "epoch": 1.8604651162790697, "percentage": 62.02, "elapsed_time": "0:02:17", "remaining_time": "0:01:24"}
+{"current_steps": 81, "total_steps": 129, "loss": 0.1597, "lr": 3.044476397549221e-06, "epoch": 1.8837209302325582, "percentage": 62.79, "elapsed_time": "0:02:19", "remaining_time": "0:01:22"}
+{"current_steps": 82, "total_steps": 129, "loss": 0.1948, "lr": 2.9329994083235857e-06, "epoch": 1.9069767441860463, "percentage": 63.57, "elapsed_time": "0:02:21", "remaining_time": "0:01:21"}
+{"current_steps": 83, "total_steps": 129, "loss": 0.1755, "lr": 2.8227482751090445e-06, "epoch": 1.9302325581395348, "percentage": 64.34, "elapsed_time": "0:02:23", "remaining_time": "0:01:19"}
+{"current_steps": 84, "total_steps": 129, "loss": 0.1706, "lr": 2.7137883834768076e-06, "epoch": 1.9534883720930232, "percentage": 65.12, "elapsed_time": "0:02:24", "remaining_time": "0:01:17"}
+{"current_steps": 85, "total_steps": 129, "loss": 0.1673, "lr": 2.6061843532139563e-06, "epoch": 1.9767441860465116, "percentage": 65.89, "elapsed_time": "0:02:26", "remaining_time": "0:01:15"}
+{"current_steps": 86, "total_steps": 129, "loss": 0.1348, "lr": 2.5000000000000015e-06, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "0:02:28", "remaining_time": "0:01:14"}
+{"current_steps": 87, "total_steps": 129, "loss": 0.0709, "lr": 2.3952982975603494e-06, "epoch": 2.0232558139534884, "percentage": 67.44, "elapsed_time": "0:02:30", "remaining_time": "0:01:12"}
+{"current_steps": 88, "total_steps": 129, "loss": 0.1071, "lr": 2.2921413403190774e-06, "epoch": 2.046511627906977, "percentage": 68.22, "elapsed_time": "0:02:31", "remaining_time": "0:01:10"}
+{"current_steps": 89, "total_steps": 129, "loss": 0.0846, "lr": 2.190590306573198e-06, "epoch": 2.0697674418604652, "percentage": 68.99, "elapsed_time": "0:02:33", "remaining_time": "0:01:08"}
+{"current_steps": 90, "total_steps": 129, "loss": 0.0973, "lr": 2.0907054222102367e-06, "epoch": 2.0930232558139537, "percentage": 69.77, "elapsed_time": "0:02:35", "remaining_time": "0:01:07"}
+{"current_steps": 91, "total_steps": 129, "loss": 0.0665, "lr": 1.9925459249906488e-06, "epoch": 2.116279069767442, "percentage": 70.54, "elapsed_time": "0:02:36", "remaining_time": "0:01:05"}
+{"current_steps": 92, "total_steps": 129, "loss": 0.0804, "lr": 1.8961700294162578e-06, "epoch": 2.13953488372093, "percentage": 71.32, "elapsed_time": "0:02:38", "remaining_time": "0:01:03"}
+{"current_steps": 93, "total_steps": 129, "loss": 0.0863, "lr": 1.8016348922055448e-06, "epoch": 2.1627906976744184, "percentage": 72.09, "elapsed_time": "0:02:40", "remaining_time": "0:01:02"}
+{"current_steps": 94, "total_steps": 129, "loss": 0.0761, "lr": 1.7089965783962608e-06, "epoch": 2.186046511627907, "percentage": 72.87, "elapsed_time": "0:02:42", "remaining_time": "0:01:00"}
+{"current_steps": 95, "total_steps": 129, "loss": 0.0744, "lr": 1.618310028095486e-06, "epoch": 2.2093023255813953, "percentage": 73.64, "elapsed_time": "0:02:43", "remaining_time": "0:00:58"}
+{"current_steps": 96, "total_steps": 129, "loss": 0.0596, "lr": 1.5296290238968303e-06, "epoch": 2.2325581395348837, "percentage": 74.42, "elapsed_time": "0:02:45", "remaining_time": "0:00:56"}
+{"current_steps": 97, "total_steps": 129, "loss": 0.0601, "lr": 1.4430061589841122e-06, "epoch": 2.255813953488372, "percentage": 75.19, "elapsed_time": "0:02:47", "remaining_time": "0:00:55"}
+{"current_steps": 98, "total_steps": 129, "loss": 0.0729, "lr": 1.3584928059404207e-06, "epoch": 2.2790697674418605, "percentage": 75.97, "elapsed_time": "0:02:48", "remaining_time": "0:00:53"}
+{"current_steps": 99, "total_steps": 129, "loss": 0.0687, "lr": 1.2761390862810907e-06, "epoch": 2.302325581395349, "percentage": 76.74, "elapsed_time": "0:02:50", "remaining_time": "0:00:51"}
+{"current_steps": 100, "total_steps": 129, "loss": 0.0773, "lr": 1.1959938407286099e-06, "epoch": 2.3255813953488373, "percentage": 77.52, "elapsed_time": "0:02:52", "remaining_time": "0:00:49"}
+{"current_steps": 101, "total_steps": 129, "loss": 0.0826, "lr": 1.1181046002471292e-06, "epoch": 2.3488372093023258, "percentage": 78.29, "elapsed_time": "0:02:54", "remaining_time": "0:00:48"}
+{"current_steps": 102, "total_steps": 129, "loss": 0.0692, "lr": 1.04251755785373e-06, "epoch": 2.3720930232558137, "percentage": 79.07, "elapsed_time": "0:02:55", "remaining_time": "0:00:46"}
+{"current_steps": 103, "total_steps": 129, "loss": 0.0739, "lr": 9.692775412231863e-07, "epoch": 2.395348837209302, "percentage": 79.84, "elapsed_time": "0:02:57", "remaining_time": "0:00:44"}
+{"current_steps": 104, "total_steps": 129, "loss": 0.1036, "lr": 8.984279861024453e-07, "epoch": 2.4186046511627906, "percentage": 80.62, "elapsed_time": "0:02:59", "remaining_time": "0:00:43"}
+{"current_steps": 105, "total_steps": 129, "loss": 0.0793, "lr": 8.30010910550611e-07, "epoch": 2.441860465116279, "percentage": 81.4, "elapsed_time": "0:03:00", "remaining_time": "0:00:41"}
+{"current_steps": 106, "total_steps": 129, "loss": 0.0722, "lr": 7.640668900196985e-07, "epoch": 2.4651162790697674, "percentage": 82.17, "elapsed_time": "0:03:02", "remaining_time": "0:00:39"}
+{"current_steps": 107, "total_steps": 129, "loss": 0.1013, "lr": 7.006350332909495e-07, "epoch": 2.488372093023256, "percentage": 82.95, "elapsed_time": "0:03:04", "remaining_time": "0:00:37"}
+{"current_steps": 108, "total_steps": 129, "loss": 0.0813, "lr": 6.397529592809615e-07, "epoch": 2.511627906976744, "percentage": 83.72, "elapsed_time": "0:03:06", "remaining_time": "0:00:36"}
+{"current_steps": 109, "total_steps": 129, "loss": 0.0684, "lr": 5.814567747314049e-07, "epoch": 2.5348837209302326, "percentage": 84.5, "elapsed_time": "0:03:07", "remaining_time": "0:00:34"}
+{"current_steps": 110, "total_steps": 129, "loss": 0.071, "lr": 5.25781052795541e-07, "epoch": 2.558139534883721, "percentage": 85.27, "elapsed_time": "0:03:09", "remaining_time": "0:00:32"}
+{"current_steps": 111, "total_steps": 129, "loss": 0.0672, "lr": 4.727588125342669e-07, "epoch": 2.5813953488372094, "percentage": 86.05, "elapsed_time": "0:03:11", "remaining_time": "0:00:31"}
+{"current_steps": 112, "total_steps": 129, "loss": 0.0781, "lr": 4.224214993338149e-07, "epoch": 2.604651162790698, "percentage": 86.82, "elapsed_time": "0:03:12", "remaining_time": "0:00:29"}
+{"current_steps": 113, "total_steps": 129, "loss": 0.0658, "lr": 3.747989662567403e-07, "epoch": 2.6279069767441863, "percentage": 87.6, "elapsed_time": "0:03:14", "remaining_time": "0:00:27"}
+{"current_steps": 114, "total_steps": 129, "loss": 0.0597, "lr": 3.299194563372604e-07, "epoch": 2.6511627906976747, "percentage": 88.37, "elapsed_time": "0:03:16", "remaining_time": "0:00:25"}
+{"current_steps": 115, "total_steps": 129, "loss": 0.0662, "lr": 2.878095858314278e-07, "epoch": 2.6744186046511627, "percentage": 89.15, "elapsed_time": "0:03:18", "remaining_time": "0:00:24"}
+{"current_steps": 116, "total_steps": 129, "loss": 0.0489, "lr": 2.4849432843208786e-07, "epoch": 2.697674418604651, "percentage": 89.92, "elapsed_time": "0:03:19", "remaining_time": "0:00:22"}
+{"current_steps": 117, "total_steps": 129, "loss": 0.0941, "lr": 2.1199700045797077e-07, "epoch": 2.7209302325581395, "percentage": 90.7, "elapsed_time": "0:03:21", "remaining_time": "0:00:20"}
+{"current_steps": 118, "total_steps": 129, "loss": 0.0533, "lr": 1.7833924702570725e-07, "epoch": 2.744186046511628, "percentage": 91.47, "elapsed_time": "0:03:23", "remaining_time": "0:00:18"}
+{"current_steps": 119, "total_steps": 129, "loss": 0.0696, "lr": 1.4754102921297363e-07, "epoch": 2.7674418604651163, "percentage": 92.25, "elapsed_time": "0:03:25", "remaining_time": "0:00:17"}
+{"current_steps": 120, "total_steps": 129, "loss": 0.063, "lr": 1.196206122203647e-07, "epoch": 2.7906976744186047, "percentage": 93.02, "elapsed_time": "0:03:26", "remaining_time": "0:00:15"}
+{"current_steps": 121, "total_steps": 129, "loss": 0.0543, "lr": 9.459455453902866e-08, "epoch": 2.813953488372093, "percentage": 93.8, "elapsed_time": "0:03:28", "remaining_time": "0:00:13"}
+{"current_steps": 122, "total_steps": 129, "loss": 0.0796, "lr": 7.247769813048644e-08, "epoch": 2.8372093023255816, "percentage": 94.57, "elapsed_time": "0:03:30", "remaining_time": "0:00:12"}
+{"current_steps": 123, "total_steps": 129, "loss": 0.072, "lr": 5.3283159624448745e-08, "epoch": 2.8604651162790695, "percentage": 95.35, "elapsed_time": "0:03:31", "remaining_time": "0:00:10"}
+{"current_steps": 124, "total_steps": 129, "loss": 0.0693, "lr": 3.702232253986804e-08, "epoch": 2.883720930232558, "percentage": 96.12, "elapsed_time": "0:03:33", "remaining_time": "0:00:08"}
+{"current_steps": 125, "total_steps": 129, "loss": 0.0585, "lr": 2.370483053382111e-08, "epoch": 2.9069767441860463, "percentage": 96.9, "elapsed_time": "0:03:35", "remaining_time": "0:00:06"}
+{"current_steps": 126, "total_steps": 129, "loss": 0.1004, "lr": 1.333858168224178e-08, "epoch": 2.9302325581395348, "percentage": 97.67, "elapsed_time": "0:03:37", "remaining_time": "0:00:05"}
+{"current_steps": 127, "total_steps": 129, "loss": 0.0701, "lr": 5.929723795884967e-09, "epoch": 2.953488372093023, "percentage": 98.45, "elapsed_time": "0:03:38", "remaining_time": "0:00:03"}
+{"current_steps": 128, "total_steps": 129, "loss": 0.1268, "lr": 1.4826507743032071e-09, "epoch": 2.9767441860465116, "percentage": 99.22, "elapsed_time": "0:03:40", "remaining_time": "0:00:01"}
+{"current_steps": 129, "total_steps": 129, "loss": 0.0564, "lr": 0.0, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "0:03:42", "remaining_time": "0:00:00"}
+{"current_steps": 129, "total_steps": 129, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "0:03:42", "remaining_time": "0:00:00"}

ra_7b_full/trainer_state.json

@@ -0,0 +1,945 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 129,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.023255813953488372,
+      "grad_norm": 30.726245880126953,
+      "learning_rate": 9.998517349225698e-06,
+      "loss": 0.5915,
+      "step": 1
+    },
+    {
+      "epoch": 0.046511627906976744,
+      "grad_norm": 7.12315034866333,
+      "learning_rate": 9.994070276204115e-06,
+      "loss": 0.5619,
+      "step": 2
+    },
+    {
+      "epoch": 0.06976744186046512,
+      "grad_norm": 5.9968791007995605,
+      "learning_rate": 9.986661418317759e-06,
+      "loss": 0.5208,
+      "step": 3
+    },
+    {
+      "epoch": 0.09302325581395349,
+      "grad_norm": 4.386000633239746,
+      "learning_rate": 9.97629516946618e-06,
+      "loss": 0.4364,
+      "step": 4
+    },
+    {
+      "epoch": 0.11627906976744186,
+      "grad_norm": 4.898772239685059,
+      "learning_rate": 9.962977677460132e-06,
+      "loss": 0.5167,
+      "step": 5
+    },
+    {
+      "epoch": 0.13953488372093023,
+      "grad_norm": 4.850924968719482,
+      "learning_rate": 9.946716840375552e-06,
+      "loss": 0.523,
+      "step": 6
+    },
+    {
+      "epoch": 0.16279069767441862,
+      "grad_norm": 4.238646030426025,
+      "learning_rate": 9.927522301869515e-06,
+      "loss": 0.4686,
+      "step": 7
+    },
+    {
+      "epoch": 0.18604651162790697,
+      "grad_norm": 3.0810768604278564,
+      "learning_rate": 9.905405445460972e-06,
+      "loss": 0.3999,
+      "step": 8
+    },
+    {
+      "epoch": 0.20930232558139536,
+      "grad_norm": 2.9611237049102783,
+      "learning_rate": 9.880379387779637e-06,
+      "loss": 0.3737,
+      "step": 9
+    },
+    {
+      "epoch": 0.23255813953488372,
+      "grad_norm": 3.815927743911743,
+      "learning_rate": 9.852458970787027e-06,
+      "loss": 0.5348,
+      "step": 10
+    },
+    {
+      "epoch": 0.2558139534883721,
+      "grad_norm": 3.4122841358184814,
+      "learning_rate": 9.821660752974294e-06,
+      "loss": 0.4295,
+      "step": 11
+    },
+    {
+      "epoch": 0.27906976744186046,
+      "grad_norm": 3.0015509128570557,
+      "learning_rate": 9.78800299954203e-06,
+      "loss": 0.4027,
+      "step": 12
+    },
+    {
+      "epoch": 0.3023255813953488,
+      "grad_norm": 3.2473697662353516,
+      "learning_rate": 9.751505671567914e-06,
+      "loss": 0.439,
+      "step": 13
+    },
+    {
+      "epoch": 0.32558139534883723,
+      "grad_norm": 2.9830455780029297,
+      "learning_rate": 9.712190414168573e-06,
+      "loss": 0.3994,
+      "step": 14
+    },
+    {
+      "epoch": 0.3488372093023256,
+      "grad_norm": 2.9557268619537354,
+      "learning_rate": 9.670080543662742e-06,
+      "loss": 0.374,
+      "step": 15
+    },
+    {
+      "epoch": 0.37209302325581395,
+      "grad_norm": 3.1986701488494873,
+      "learning_rate": 9.625201033743262e-06,
+      "loss": 0.4716,
+      "step": 16
+    },
+    {
+      "epoch": 0.3953488372093023,
+      "grad_norm": 3.5774526596069336,
+      "learning_rate": 9.577578500666187e-06,
+      "loss": 0.4829,
+      "step": 17
+    },
+    {
+      "epoch": 0.4186046511627907,
+      "grad_norm": 3.577956438064575,
+      "learning_rate": 9.527241187465735e-06,
+      "loss": 0.4792,
+      "step": 18
+    },
+    {
+      "epoch": 0.4418604651162791,
+      "grad_norm": 2.157691478729248,
+      "learning_rate": 9.47421894720446e-06,
+      "loss": 0.2867,
+      "step": 19
+    },
+    {
+      "epoch": 0.46511627906976744,
+      "grad_norm": 2.8371741771698,
+      "learning_rate": 9.418543225268598e-06,
+      "loss": 0.4133,
+      "step": 20
+    },
+    {
+      "epoch": 0.4883720930232558,
+      "grad_norm": 3.108774185180664,
+      "learning_rate": 9.36024704071904e-06,
+      "loss": 0.4108,
+      "step": 21
+    },
+    {
+      "epoch": 0.5116279069767442,
+      "grad_norm": 3.178828001022339,
+      "learning_rate": 9.299364966709051e-06,
+      "loss": 0.3883,
+      "step": 22
+    },
+    {
+      "epoch": 0.5348837209302325,
+      "grad_norm": 2.621211528778076,
+      "learning_rate": 9.235933109980302e-06,
+      "loss": 0.3584,
+      "step": 23
+    },
+    {
+      "epoch": 0.5581395348837209,
+      "grad_norm": 2.799783706665039,
+      "learning_rate": 9.16998908944939e-06,
+      "loss": 0.3716,
+      "step": 24
+    },
+    {
+      "epoch": 0.5813953488372093,
+      "grad_norm": 3.1680638790130615,
+      "learning_rate": 9.101572013897555e-06,
+      "loss": 0.4743,
+      "step": 25
+    },
+    {
+      "epoch": 0.6046511627906976,
+      "grad_norm": 2.896028518676758,
+      "learning_rate": 9.030722458776815e-06,
+      "loss": 0.4169,
+      "step": 26
+    },
+    {
+      "epoch": 0.627906976744186,
+      "grad_norm": 3.443052053451538,
+      "learning_rate": 8.957482442146271e-06,
+      "loss": 0.4298,
+      "step": 27
+    },
+    {
+      "epoch": 0.6511627906976745,
+      "grad_norm": 3.4685962200164795,
+      "learning_rate": 8.881895399752873e-06,
+      "loss": 0.4511,
+      "step": 28
+    },
+    {
+      "epoch": 0.6744186046511628,
+      "grad_norm": 3.0390939712524414,
+      "learning_rate": 8.80400615927139e-06,
+      "loss": 0.4405,
+      "step": 29
+    },
+    {
+      "epoch": 0.6976744186046512,
+      "grad_norm": 3.1846044063568115,
+      "learning_rate": 8.72386091371891e-06,
+      "loss": 0.3792,
+      "step": 30
+    },
+    {
+      "epoch": 0.7209302325581395,
+      "grad_norm": 2.192141532897949,
+      "learning_rate": 8.64150719405958e-06,
+      "loss": 0.3209,
+      "step": 31
+    },
+    {
+      "epoch": 0.7441860465116279,
+      "grad_norm": 3.440671443939209,
+      "learning_rate": 8.55699384101589e-06,
+      "loss": 0.5218,
+      "step": 32
+    },
+    {
+      "epoch": 0.7674418604651163,
+      "grad_norm": 2.478684663772583,
+      "learning_rate": 8.470370976103171e-06,
+      "loss": 0.3964,
+      "step": 33
+    },
+    {
+      "epoch": 0.7906976744186046,
+      "grad_norm": 2.612114667892456,
+      "learning_rate": 8.381689971904514e-06,
+      "loss": 0.4212,
+      "step": 34
+    },
+    {
+      "epoch": 0.813953488372093,
+      "grad_norm": 2.1670122146606445,
+      "learning_rate": 8.29100342160374e-06,
+      "loss": 0.3213,
+      "step": 35
+    },
+    {
+      "epoch": 0.8372093023255814,
+      "grad_norm": 2.373817205429077,
+      "learning_rate": 8.198365107794457e-06,
+      "loss": 0.3899,
+      "step": 36
+    },
+    {
+      "epoch": 0.8604651162790697,
+      "grad_norm": 2.4413201808929443,
+      "learning_rate": 8.103829970583742e-06,
+      "loss": 0.4202,
+      "step": 37
+    },
+    {
+      "epoch": 0.8837209302325582,
+      "grad_norm": 2.552819013595581,
+      "learning_rate": 8.007454075009352e-06,
+      "loss": 0.3792,
+      "step": 38
+    },
+    {
+      "epoch": 0.9069767441860465,
+      "grad_norm": 1.4976168870925903,
+      "learning_rate": 7.909294577789765e-06,
+      "loss": 0.3039,
+      "step": 39
+    },
+    {
+      "epoch": 0.9302325581395349,
+      "grad_norm": 1.9250071048736572,
+      "learning_rate": 7.809409693426803e-06,
+      "loss": 0.3319,
+      "step": 40
+    },
+    {
+      "epoch": 0.9534883720930233,
+      "grad_norm": 2.4655659198760986,
+      "learning_rate": 7.707858659680924e-06,
+      "loss": 0.4377,
+      "step": 41
+    },
+    {
+      "epoch": 0.9767441860465116,
+      "grad_norm": 1.9646581411361694,
+      "learning_rate": 7.604701702439652e-06,
+      "loss": 0.2886,
+      "step": 42
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.5175514221191406,
+      "learning_rate": 7.500000000000001e-06,
+      "loss": 0.2611,
+      "step": 43
+    },
+    {
+      "epoch": 1.0232558139534884,
+      "grad_norm": 1.652040958404541,
+      "learning_rate": 7.393815646786047e-06,
+      "loss": 0.2508,
+      "step": 44
+    },
+    {
+      "epoch": 1.0465116279069768,
+      "grad_norm": 1.3295698165893555,
+      "learning_rate": 7.286211616523193e-06,
+      "loss": 0.1855,
+      "step": 45
+    },
+    {
+      "epoch": 1.069767441860465,
+      "grad_norm": 1.108451247215271,
+      "learning_rate": 7.177251724890957e-06,
+      "loss": 0.1717,
+      "step": 46
+    },
+    {
+      "epoch": 1.0930232558139534,
+      "grad_norm": 1.239182710647583,
+      "learning_rate": 7.067000591676416e-06,
+      "loss": 0.1738,
+      "step": 47
+    },
+    {
+      "epoch": 1.1162790697674418,
+      "grad_norm": 1.250343680381775,
+      "learning_rate": 6.95552360245078e-06,
+      "loss": 0.207,
+      "step": 48
+    },
+    {
+      "epoch": 1.1395348837209303,
+      "grad_norm": 1.2105518579483032,
+      "learning_rate": 6.84288686979181e-06,
+      "loss": 0.1661,
+      "step": 49
+    },
+    {
+      "epoch": 1.1627906976744187,
+      "grad_norm": 1.6453056335449219,
+      "learning_rate": 6.7291571940750575e-06,
+      "loss": 0.2372,
+      "step": 50
+    },
+    {
+      "epoch": 1.1860465116279069,
+      "grad_norm": 1.5206165313720703,
+      "learning_rate": 6.614402023857231e-06,
+      "loss": 0.193,
+      "step": 51
+    },
+    {
+      "epoch": 1.2093023255813953,
+      "grad_norm": 1.2247314453125,
+      "learning_rate": 6.498689415875121e-06,
+      "loss": 0.1534,
+      "step": 52
+    },
+    {
+      "epoch": 1.2325581395348837,
+      "grad_norm": 1.3760303258895874,
+      "learning_rate": 6.3820879946838585e-06,
+      "loss": 0.1902,
+      "step": 53
+    },
+    {
+      "epoch": 1.255813953488372,
+      "grad_norm": 1.1041628122329712,
+      "learning_rate": 6.264666911958404e-06,
+      "loss": 0.1829,
+      "step": 54
+    },
+    {
+      "epoch": 1.2790697674418605,
+      "grad_norm": 1.358738899230957,
+      "learning_rate": 6.146495805482451e-06,
+      "loss": 0.1887,
+      "step": 55
+    },
+    {
+      "epoch": 1.302325581395349,
+      "grad_norm": 1.2233117818832397,
+      "learning_rate": 6.027644757849004e-06,
+      "loss": 0.1868,
+      "step": 56
+    },
+    {
+      "epoch": 1.3255813953488373,
+      "grad_norm": 1.1027579307556152,
+      "learning_rate": 5.908184254897183e-06,
+      "loss": 0.1618,
+      "step": 57
+    },
+    {
+      "epoch": 1.3488372093023255,
+      "grad_norm": 1.0374614000320435,
+      "learning_rate": 5.788185143909868e-06,
+      "loss": 0.1542,
+      "step": 58
+    },
+    {
+      "epoch": 1.372093023255814,
+      "grad_norm": 1.3504281044006348,
+      "learning_rate": 5.66771859159699e-06,
+      "loss": 0.1777,
+      "step": 59
+    },
+    {
+      "epoch": 1.3953488372093024,
+      "grad_norm": 1.5078482627868652,
+      "learning_rate": 5.546856041889374e-06,
+      "loss": 0.1527,
+      "step": 60
+    },
+    {
+      "epoch": 1.4186046511627908,
+      "grad_norm": 1.2992072105407715,
+      "learning_rate": 5.425669173568179e-06,
+      "loss": 0.217,
+      "step": 61
+    },
+    {
+      "epoch": 1.441860465116279,
+      "grad_norm": 1.1256506443023682,
+      "learning_rate": 5.30422985775507e-06,
+      "loss": 0.1896,
+      "step": 62
+    },
+    {
+      "epoch": 1.4651162790697674,
+      "grad_norm": 1.2497133016586304,
+      "learning_rate": 5.182610115288296e-06,
+      "loss": 0.1729,
+      "step": 63
+    },
+    {
+      "epoch": 1.4883720930232558,
+      "grad_norm": 1.7545222043991089,
+      "learning_rate": 5.060882074009988e-06,
+      "loss": 0.263,
+      "step": 64
+    },
+    {
+      "epoch": 1.5116279069767442,
+      "grad_norm": 1.2929202318191528,
+      "learning_rate": 4.939117925990013e-06,
+      "loss": 0.1975,
+      "step": 65
+    },
+    {
+      "epoch": 1.5348837209302326,
+      "grad_norm": 1.0699827671051025,
+      "learning_rate": 4.817389884711706e-06,
+      "loss": 0.1681,
+      "step": 66
+    },
+    {
+      "epoch": 1.558139534883721,
+      "grad_norm": 1.1378083229064941,
+      "learning_rate": 4.695770142244931e-06,
+      "loss": 0.1547,
+      "step": 67
+    },
+    {
+      "epoch": 1.5813953488372094,
+      "grad_norm": 1.2051218748092651,
+      "learning_rate": 4.574330826431822e-06,
+      "loss": 0.1394,
+      "step": 68
+    },
+    {
+      "epoch": 1.6046511627906976,
+      "grad_norm": 1.1266852617263794,
+      "learning_rate": 4.4531439581106295e-06,
+      "loss": 0.1612,
+      "step": 69
+    },
+    {
+      "epoch": 1.627906976744186,
+      "grad_norm": 1.482691764831543,
+      "learning_rate": 4.332281408403011e-06,
+      "loss": 0.1686,
+      "step": 70
+    },
+    {
+      "epoch": 1.6511627906976745,
+      "grad_norm": 1.5284996032714844,
+      "learning_rate": 4.2118148560901325e-06,
+      "loss": 0.2138,
+      "step": 71
+    },
+    {
+      "epoch": 1.6744186046511627,
+      "grad_norm": 1.1368211507797241,
+      "learning_rate": 4.091815745102818e-06,
+      "loss": 0.1673,
+      "step": 72
+    },
+    {
+      "epoch": 1.697674418604651,
+      "grad_norm": 1.4666715860366821,
+      "learning_rate": 3.9723552421509975e-06,
+      "loss": 0.1913,
+      "step": 73
+    },
+    {
+      "epoch": 1.7209302325581395,
+      "grad_norm": 1.107043743133545,
+      "learning_rate": 3.853504194517551e-06,
+      "loss": 0.1832,
+      "step": 74
+    },
+    {
+      "epoch": 1.744186046511628,
+      "grad_norm": 1.2265022993087769,
+      "learning_rate": 3.7353330880415963e-06,
+      "loss": 0.1939,
+      "step": 75
+    },
+    {
+      "epoch": 1.7674418604651163,
+      "grad_norm": 1.387879490852356,
+      "learning_rate": 3.617912005316142e-06,
+      "loss": 0.1787,
+      "step": 76
+    },
+    {
+      "epoch": 1.7906976744186047,
+      "grad_norm": 1.2133986949920654,
+      "learning_rate": 3.5013105841248794e-06,
+      "loss": 0.202,
+      "step": 77
+    },
+    {
+      "epoch": 1.8139534883720931,
+      "grad_norm": 0.9675338268280029,
+      "learning_rate": 3.3855979761427705e-06,
+      "loss": 0.1411,
+      "step": 78
+    },
+    {
+      "epoch": 1.8372093023255816,
+      "grad_norm": 1.2217375040054321,
+      "learning_rate": 3.2708428059249437e-06,
+      "loss": 0.2009,
+      "step": 79
+    },
+    {
+      "epoch": 1.8604651162790697,
+      "grad_norm": 1.2863670587539673,
+      "learning_rate": 3.1571131302081916e-06,
+      "loss": 0.158,
+      "step": 80
+    },
+    {
+      "epoch": 1.8837209302325582,
+      "grad_norm": 1.1228820085525513,
+      "learning_rate": 3.044476397549221e-06,
+      "loss": 0.1597,
+      "step": 81
+    },
+    {
+      "epoch": 1.9069767441860463,
+      "grad_norm": 1.182486891746521,
+      "learning_rate": 2.9329994083235857e-06,
+      "loss": 0.1948,
+      "step": 82
+    },
+    {
+      "epoch": 1.9302325581395348,
+      "grad_norm": 1.060689926147461,
+      "learning_rate": 2.8227482751090445e-06,
+      "loss": 0.1755,
+      "step": 83
+    },
+    {
+      "epoch": 1.9534883720930232,
+      "grad_norm": 1.1752835512161255,
+      "learning_rate": 2.7137883834768076e-06,
+      "loss": 0.1706,
+      "step": 84
+    },
+    {
+      "epoch": 1.9767441860465116,
+      "grad_norm": 1.1354871988296509,
+      "learning_rate": 2.6061843532139563e-06,
+      "loss": 0.1673,
+      "step": 85
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.0031702518463135,
+      "learning_rate": 2.5000000000000015e-06,
+      "loss": 0.1348,
+      "step": 86
+    },
+    {
+      "epoch": 2.0232558139534884,
+      "grad_norm": 1.0273747444152832,
+      "learning_rate": 2.3952982975603494e-06,
+      "loss": 0.0709,
+      "step": 87
+    },
+    {
+      "epoch": 2.046511627906977,
+      "grad_norm": 1.0820266008377075,
+      "learning_rate": 2.2921413403190774e-06,
+      "loss": 0.1071,
+      "step": 88
+    },
+    {
+      "epoch": 2.0697674418604652,
+      "grad_norm": 0.9130030870437622,
+      "learning_rate": 2.190590306573198e-06,
+      "loss": 0.0846,
+      "step": 89
+    },
+    {
+      "epoch": 2.0930232558139537,
+      "grad_norm": 0.8466348648071289,
+      "learning_rate": 2.0907054222102367e-06,
+      "loss": 0.0973,
+      "step": 90
+    },
+    {
+      "epoch": 2.116279069767442,
+      "grad_norm": 0.9126643538475037,
+      "learning_rate": 1.9925459249906488e-06,
+      "loss": 0.0665,
+      "step": 91
+    },
+    {
+      "epoch": 2.13953488372093,
+      "grad_norm": 0.8634910583496094,
+      "learning_rate": 1.8961700294162578e-06,
+      "loss": 0.0804,
+      "step": 92
+    },
+    {
+      "epoch": 2.1627906976744184,
+      "grad_norm": 0.824974536895752,
+      "learning_rate": 1.8016348922055448e-06,
+      "loss": 0.0863,
+      "step": 93
+    },
+    {
+      "epoch": 2.186046511627907,
+      "grad_norm": 0.849765956401825,
+      "learning_rate": 1.7089965783962608e-06,
+      "loss": 0.0761,
+      "step": 94
+    },
+    {
+      "epoch": 2.2093023255813953,
+      "grad_norm": 0.8969545364379883,
+      "learning_rate": 1.618310028095486e-06,
+      "loss": 0.0744,
+      "step": 95
+    },
+    {
+      "epoch": 2.2325581395348837,
+      "grad_norm": 0.8042866587638855,
+      "learning_rate": 1.5296290238968303e-06,
+      "loss": 0.0596,
+      "step": 96
+    },
+    {
+      "epoch": 2.255813953488372,
+      "grad_norm": 0.8959429860115051,
+      "learning_rate": 1.4430061589841122e-06,
+      "loss": 0.0601,
+      "step": 97
+    },
+    {
+      "epoch": 2.2790697674418605,
+      "grad_norm": 1.016892910003662,
+      "learning_rate": 1.3584928059404207e-06,
+      "loss": 0.0729,
+      "step": 98
+    },
+    {
+      "epoch": 2.302325581395349,
+      "grad_norm": 1.116010308265686,
+      "learning_rate": 1.2761390862810907e-06,
+      "loss": 0.0687,
+      "step": 99
+    },
+    {
+      "epoch": 2.3255813953488373,
+      "grad_norm": 1.242315411567688,
+      "learning_rate": 1.1959938407286099e-06,
+      "loss": 0.0773,
+      "step": 100
+    },
+    {
+      "epoch": 2.3488372093023258,
+      "grad_norm": 1.1936157941818237,
+      "learning_rate": 1.1181046002471292e-06,
+      "loss": 0.0826,
+      "step": 101
+    },
+    {
+      "epoch": 2.3720930232558137,
+      "grad_norm": 1.3546022176742554,
+      "learning_rate": 1.04251755785373e-06,
+      "loss": 0.0692,
+      "step": 102
+    },
+    {
+      "epoch": 2.395348837209302,
+      "grad_norm": 1.184714913368225,
+      "learning_rate": 9.692775412231863e-07,
+      "loss": 0.0739,
+      "step": 103
+    },
+    {
+      "epoch": 2.4186046511627906,
+      "grad_norm": 1.2117191553115845,
+      "learning_rate": 8.984279861024453e-07,
+      "loss": 0.1036,
+      "step": 104
+    },
+    {
+      "epoch": 2.441860465116279,
+      "grad_norm": 1.1204442977905273,
+      "learning_rate": 8.30010910550611e-07,
+      "loss": 0.0793,
+      "step": 105
+    },
+    {
+      "epoch": 2.4651162790697674,
+      "grad_norm": 1.8685438632965088,
+      "learning_rate": 7.640668900196985e-07,
+      "loss": 0.0722,
+      "step": 106
+    },
+    {
+      "epoch": 2.488372093023256,
+      "grad_norm": 1.3149610757827759,
+      "learning_rate": 7.006350332909495e-07,
+      "loss": 0.1013,
+      "step": 107
+    },
+    {
+      "epoch": 2.511627906976744,
+      "grad_norm": 1.2621856927871704,
+      "learning_rate": 6.397529592809615e-07,
+      "loss": 0.0813,
+      "step": 108
+    },
+    {
+      "epoch": 2.5348837209302326,
+      "grad_norm": 1.111955165863037,
+      "learning_rate": 5.814567747314049e-07,
+      "loss": 0.0684,
+      "step": 109
+    },
+    {
+      "epoch": 2.558139534883721,
+      "grad_norm": 1.051204800605774,
+      "learning_rate": 5.25781052795541e-07,
+      "loss": 0.071,
+      "step": 110
+    },
+    {
+      "epoch": 2.5813953488372094,
+      "grad_norm": 0.8967148065567017,
+      "learning_rate": 4.727588125342669e-07,
+      "loss": 0.0672,
+      "step": 111
+    },
+    {
+      "epoch": 2.604651162790698,
+      "grad_norm": 0.9757853150367737,
+      "learning_rate": 4.224214993338149e-07,
+      "loss": 0.0781,
+      "step": 112
+    },
+    {
+      "epoch": 2.6279069767441863,
+      "grad_norm": 0.8907418847084045,
+      "learning_rate": 3.747989662567403e-07,
+      "loss": 0.0658,
+      "step": 113
+    },
+    {
+      "epoch": 2.6511627906976747,
+      "grad_norm": 0.819481611251831,
+      "learning_rate": 3.299194563372604e-07,
+      "loss": 0.0597,
+      "step": 114
+    },
+    {
+      "epoch": 2.6744186046511627,
+      "grad_norm": 0.8849020004272461,
+      "learning_rate": 2.878095858314278e-07,
+      "loss": 0.0662,
+      "step": 115
+    },
+    {
+      "epoch": 2.697674418604651,
+      "grad_norm": 0.7910754680633545,
+      "learning_rate": 2.4849432843208786e-07,
+      "loss": 0.0489,
+      "step": 116
+    },
+    {
+      "epoch": 2.7209302325581395,
+      "grad_norm": 1.1265588998794556,
+      "learning_rate": 2.1199700045797077e-07,
+      "loss": 0.0941,
+      "step": 117
+    },
+    {
+      "epoch": 2.744186046511628,
+      "grad_norm": 0.7776470184326172,
+      "learning_rate": 1.7833924702570725e-07,
+      "loss": 0.0533,
+      "step": 118
+    },
+    {
+      "epoch": 2.7674418604651163,
+      "grad_norm": 0.8456980586051941,
+      "learning_rate": 1.4754102921297363e-07,
+      "loss": 0.0696,
+      "step": 119
+    },
+    {
+      "epoch": 2.7906976744186047,
+      "grad_norm": 0.8181210160255432,
+      "learning_rate": 1.196206122203647e-07,
+      "loss": 0.063,
+      "step": 120
+    },
+    {
+      "epoch": 2.813953488372093,
+      "grad_norm": 0.767279326915741,
+      "learning_rate": 9.459455453902866e-08,
+      "loss": 0.0543,
+      "step": 121
+    },
+    {
+      "epoch": 2.8372093023255816,
+      "grad_norm": 0.9494999647140503,
+      "learning_rate": 7.247769813048644e-08,
+      "loss": 0.0796,
+      "step": 122
+    },
+    {
+      "epoch": 2.8604651162790695,
+      "grad_norm": 0.9212082028388977,
+      "learning_rate": 5.3283159624448745e-08,
+      "loss": 0.072,
+      "step": 123
+    },
+    {
+      "epoch": 2.883720930232558,
+      "grad_norm": 0.8605324029922485,
+      "learning_rate": 3.702232253986804e-08,
+      "loss": 0.0693,
+      "step": 124
+    },
+    {
+      "epoch": 2.9069767441860463,
+      "grad_norm": 0.9437394142150879,
+      "learning_rate": 2.370483053382111e-08,
+      "loss": 0.0585,
+      "step": 125
+    },
+    {
+      "epoch": 2.9302325581395348,
+      "grad_norm": 0.9854469895362854,
+      "learning_rate": 1.333858168224178e-08,
+      "loss": 0.1004,
+      "step": 126
+    },
+    {
+      "epoch": 2.953488372093023,
+      "grad_norm": 0.950158953666687,
+      "learning_rate": 5.929723795884967e-09,
+      "loss": 0.0701,
+      "step": 127
+    },
+    {
+      "epoch": 2.9767441860465116,
+      "grad_norm": 1.2735469341278076,
+      "learning_rate": 1.4826507743032071e-09,
+      "loss": 0.1268,
+      "step": 128
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.7876803874969482,
+      "learning_rate": 0.0,
+      "loss": 0.0564,
+      "step": 129
+    },
+    {
+      "epoch": 3.0,
+      "step": 129,
+      "total_flos": 1.7932809270617702e+17,
+      "train_loss": 0.22525020212281582,
+      "train_runtime": 228.5945,
+      "train_samples_per_second": 4.449,
+      "train_steps_per_second": 0.564
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 129,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": false,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.7932809270617702e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

ra_7b_full/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af76b91b532430b69e91b4c4939e211d898d79d118ecb0a9160e3834e70dbb03
+size 7096