add checkpoints/codi1.5b_a1.0_b1.0_g1.0_ls2

.gitattributes

@@ -49,3 +49,10 @@ checkpoints/codi1.5b_a1.0_b1.0_g1.0_ls1/checkpoint-1500/tokenizer.json filter=lf
 checkpoints/codi1.5b_a1.0_b1.0_g1.0_ls1/checkpoint-2000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 checkpoints/codi1.5b_a1.0_b1.0_g1.0_ls1/checkpoint-500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 checkpoints/codi1.5b_a1.0_b1.0_g1.0_ls1/wandb/offline-run-20260619_215302-q1wgok6t/run-q1wgok6t.wandb filter=lfs diff=lfs merge=lfs -text
+checkpoints/codi1.5b_a1.0_b1.0_g1.0_ls2/checkpoint-1000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoints/codi1.5b_a1.0_b1.0_g1.0_ls2/checkpoint-200/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoints/codi1.5b_a1.0_b1.0_g1.0_ls2/checkpoint-400/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoints/codi1.5b_a1.0_b1.0_g1.0_ls2/checkpoint-600/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoints/codi1.5b_a1.0_b1.0_g1.0_ls2/checkpoint-800/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoints/codi1.5b_a1.0_b1.0_g1.0_ls2/wandb/offline-run-20260620_130138-bqeecd43/run-bqeecd43.wandb filter=lfs diff=lfs merge=lfs -text
+checkpoints/codi1.5b_a1.0_b1.0_g1.0_ls2/wandb/offline-run-20260621_033730-ue0j104y/run-ue0j104y.wandb filter=lfs diff=lfs merge=lfs -text

checkpoints/codi1.5b_a1.0_b1.0_g1.0_ls2/checkpoint-1000/added_tokens.json

@@ -0,0 +1,35 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|action_sep|>": 151670,
+  "<|arg_sep|>": 151671,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|call_sep|>": 151666,
+  "<|end_of_text|>": 151673,
+  "<|endoftext|>": 151643,
+  "<|exception_sep|>": 151669,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|frame_sep|>": 151672,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|latent_end|>": 151675,
+  "<|latent_start|>": 151674,
+  "<|line_sep|>": 151667,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|return_sep|>": 151668,
+  "<|trace_context_start|>": 151665,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

checkpoints/codi1.5b_a1.0_b1.0_g1.0_ls2/checkpoint-1000/chat_template.jinja

@@ -0,0 +1,54 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
+    {%- endif %}
+    {{- "\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>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\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" }}
+{%- else %}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
+    {%- else %}
+        {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role }}
+        {%- if message.content %}
+            {{- '\n' + message.content }}
+        {%- endif %}
+        {%- for tool_call in message.tool_calls %}
+            {%- if tool_call.function is defined %}
+                {%- set tool_call = tool_call.function %}
+            {%- endif %}
+            {{- '\n<tool_call>\n{"name": "' }}
+            {{- tool_call.name }}
+            {{- '", "arguments": ' }}
+            {{- tool_call.arguments | tojson }}
+            {{- '}\n</tool_call>' }}
+        {%- endfor %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}

checkpoints/codi1.5b_a1.0_b1.0_g1.0_ls2/checkpoint-1000/config.json

@@ -0,0 +1,58 @@
+{
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "dtype": "bfloat16",
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 1536,
+  "initializer_range": 0.02,
+  "intermediate_size": 8960,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 2,
+  "pad_token_id": 151643,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "transformers_version": "4.57.6",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151676
+}

checkpoints/codi1.5b_a1.0_b1.0_g1.0_ls2/checkpoint-1000/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e0e3318e37fa1a259755f87da55e3348b8afa9883834de39a4cb2422e95c9be
+size 3096275515

checkpoints/codi1.5b_a1.0_b1.0_g1.0_ls2/checkpoint-1000/special_tokens_map.json

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

checkpoints/codi1.5b_a1.0_b1.0_g1.0_ls2/checkpoint-1000/thought_projector.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d29253b502e8e69a15fcfac33948fabd531aff3b6a6398fe133b3ae2c1fb7b8
+size 9445953

checkpoints/codi1.5b_a1.0_b1.0_g1.0_ls2/checkpoint-1000/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83a790d654474f5dfe225f889afd0210313eb1083f942671f2c4b8e95a1c922b
+size 11424004

checkpoints/codi1.5b_a1.0_b1.0_g1.0_ls2/checkpoint-1000/tokenizer_config.json

@@ -0,0 +1,295 @@
+{
+  "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
+    },
+    "151665": {
+      "content": "<|trace_context_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151666": {
+      "content": "<|call_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151667": {
+      "content": "<|line_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151668": {
+      "content": "<|return_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151669": {
+      "content": "<|exception_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151670": {
+      "content": "<|action_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151671": {
+      "content": "<|arg_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151672": {
+      "content": "<|frame_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151673": {
+      "content": "<|end_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151674": {
+      "content": "<|latent_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151675": {
+      "content": "<|latent_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "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,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoints/codi1.5b_a1.0_b1.0_g1.0_ls2/checkpoint-1000/trainer_state.json

@@ -0,0 +1,2046 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.28835063437139563,
+  "eval_steps": 500,
+  "global_step": 1000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0014417531718569781,
+      "grad_norm": 52992.0,
+      "kd_loss": 0.3193017542362213,
+      "learning_rate": 1.3333333333333334e-06,
+      "loss": 0.473,
+      "step": 5,
+      "student_loss": 0.15727384388446808,
+      "teacher_loss": 0.0004137983196415007
+    },
+    {
+      "epoch": 0.0028835063437139563,
+      "grad_norm": 16121856.0,
+      "kd_loss": 0.3087984025478363,
+      "learning_rate": 3e-06,
+      "loss": 0.466,
+      "step": 10,
+      "student_loss": 0.2608874440193176,
+      "teacher_loss": 0.0007329508662223816
+    },
+    {
+      "epoch": 0.004325259515570935,
+      "grad_norm": 2240.0,
+      "kd_loss": 0.25935155153274536,
+      "learning_rate": 4.666666666666667e-06,
+      "loss": 0.4585,
+      "step": 15,
+      "student_loss": 0.1052168533205986,
+      "teacher_loss": 0.000609480426646769
+    },
+    {
+      "epoch": 0.0057670126874279125,
+      "grad_norm": 4194304.0,
+      "kd_loss": 0.25011566281318665,
+      "learning_rate": 6.333333333333333e-06,
+      "loss": 0.4707,
+      "step": 20,
+      "student_loss": 0.15271778404712677,
+      "teacher_loss": 0.0002972046786453575
+    },
+    {
+      "epoch": 0.00720876585928489,
+      "grad_norm": 41680896.0,
+      "kd_loss": 0.2633170485496521,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 0.4368,
+      "step": 25,
+      "student_loss": 0.09109362959861755,
+      "teacher_loss": 0.0009600125486031175
+    },
+    {
+      "epoch": 0.00865051903114187,
+      "grad_norm": 512.0,
+      "kd_loss": 0.2533612847328186,
+      "learning_rate": 9.666666666666667e-06,
+      "loss": 0.4187,
+      "step": 30,
+      "student_loss": 0.22675999999046326,
+      "teacher_loss": 0.00035076512722298503
+    },
+    {
+      "epoch": 0.010092272202998846,
+      "grad_norm": 48.75,
+      "kd_loss": 0.2179471105337143,
+      "learning_rate": 9.99958042442916e-06,
+      "loss": 0.3713,
+      "step": 35,
+      "student_loss": 0.09486500918865204,
+      "teacher_loss": 0.00026503618573769927
+    },
+    {
+      "epoch": 0.011534025374855825,
+      "grad_norm": 10.0,
+      "kd_loss": 0.17874062061309814,
+      "learning_rate": 9.997876019358083e-06,
+      "loss": 0.2647,
+      "step": 40,
+      "student_loss": 0.07879351079463959,
+      "teacher_loss": 0.05543303117156029
+    },
+    {
+      "epoch": 0.012975778546712802,
+      "grad_norm": 4.9375,
+      "kd_loss": 0.19365739822387695,
+      "learning_rate": 9.99486100792044e-06,
+      "loss": 0.1686,
+      "step": 45,
+      "student_loss": 0.07774724811315536,
+      "teacher_loss": 0.0008653572876937687
+    },
+    {
+      "epoch": 0.01441753171856978,
+      "grad_norm": 3.359375,
+      "kd_loss": 0.06108914315700531,
+      "learning_rate": 9.990536180750724e-06,
+      "loss": 0.1396,
+      "step": 50,
+      "student_loss": 0.008677379228174686,
+      "teacher_loss": 0.005272893700748682
+    },
+    {
+      "epoch": 0.015859284890426758,
+      "grad_norm": 3.71875,
+      "kd_loss": 0.04330182075500488,
+      "learning_rate": 9.984902671959911e-06,
+      "loss": 0.1065,
+      "step": 55,
+      "student_loss": 0.001041711075231433,
+      "teacher_loss": 0.0005072589847259223
+    },
+    {
+      "epoch": 0.01730103806228374,
+      "grad_norm": 4.125,
+      "kd_loss": 0.03823668882250786,
+      "learning_rate": 9.97796195883804e-06,
+      "loss": 0.0862,
+      "step": 60,
+      "student_loss": 0.0209807138890028,
+      "teacher_loss": 0.0038409351836889982
+    },
+    {
+      "epoch": 0.018742791234140715,
+      "grad_norm": 10.1875,
+      "kd_loss": 0.03922531381249428,
+      "learning_rate": 9.969715861466839e-06,
+      "loss": 0.0844,
+      "step": 65,
+      "student_loss": 0.04678678512573242,
+      "teacher_loss": 0.05432586744427681
+    },
+    {
+      "epoch": 0.020184544405997693,
+      "grad_norm": 2.03125,
+      "kd_loss": 0.0549621656537056,
+      "learning_rate": 9.96016654224243e-06,
+      "loss": 0.0797,
+      "step": 70,
+      "student_loss": 0.016930116340517998,
+      "teacher_loss": 0.0029678302817046642
+    },
+    {
+      "epoch": 0.02162629757785467,
+      "grad_norm": 2.5625,
+      "kd_loss": 0.023080041632056236,
+      "learning_rate": 9.94931650530827e-06,
+      "loss": 0.0756,
+      "step": 75,
+      "student_loss": 0.002210108330473304,
+      "teacher_loss": 0.0013834249693900347
+    },
+    {
+      "epoch": 0.02306805074971165,
+      "grad_norm": 2.296875,
+      "kd_loss": 0.025744518265128136,
+      "learning_rate": 9.93716859589851e-06,
+      "loss": 0.0644,
+      "step": 80,
+      "student_loss": 0.0015430074417963624,
+      "teacher_loss": 0.000761081581003964
+    },
+    {
+      "epoch": 0.024509803921568627,
+      "grad_norm": 3.125,
+      "kd_loss": 0.023152953013777733,
+      "learning_rate": 9.923725999591846e-06,
+      "loss": 0.0609,
+      "step": 85,
+      "student_loss": 0.0187687948346138,
+      "teacher_loss": 0.011518553830683231
+    },
+    {
+      "epoch": 0.025951557093425604,
+      "grad_norm": 1.8359375,
+      "kd_loss": 0.06841632723808289,
+      "learning_rate": 9.908992241476189e-06,
+      "loss": 0.0622,
+      "step": 90,
+      "student_loss": 0.05537872016429901,
+      "teacher_loss": 0.011890009045600891
+    },
+    {
+      "epoch": 0.027393310265282585,
+      "grad_norm": 4.21875,
+      "kd_loss": 0.041227906942367554,
+      "learning_rate": 9.892971185224244e-06,
+      "loss": 0.0626,
+      "step": 95,
+      "student_loss": 0.009465624578297138,
+      "teacher_loss": 0.005057212430983782
+    },
+    {
+      "epoch": 0.02883506343713956,
+      "grad_norm": 1.8359375,
+      "kd_loss": 0.021006152033805847,
+      "learning_rate": 9.875667032080354e-06,
+      "loss": 0.0538,
+      "step": 100,
+      "student_loss": 0.0007415671134367585,
+      "teacher_loss": 0.0005348982522264123
+    },
+    {
+      "epoch": 0.03027681660899654,
+      "grad_norm": 1.6328125,
+      "kd_loss": 0.035115621984004974,
+      "learning_rate": 9.857084319758772e-06,
+      "loss": 0.0541,
+      "step": 105,
+      "student_loss": 0.005187581293284893,
+      "teacher_loss": 0.00030648778192698956
+    },
+    {
+      "epoch": 0.031718569780853516,
+      "grad_norm": 2.953125,
+      "kd_loss": 0.03037514165043831,
+      "learning_rate": 9.837227921253747e-06,
+      "loss": 0.06,
+      "step": 110,
+      "student_loss": 0.031953420490026474,
+      "teacher_loss": 0.0175339188426733
+    },
+    {
+      "epoch": 0.03316032295271049,
+      "grad_norm": 1.484375,
+      "kd_loss": 0.023421702906489372,
+      "learning_rate": 9.816103043561648e-06,
+      "loss": 0.0563,
+      "step": 115,
+      "student_loss": 0.0006847245967946947,
+      "teacher_loss": 0.0003864571626763791
+    },
+    {
+      "epoch": 0.03460207612456748,
+      "grad_norm": 1.8203125,
+      "kd_loss": 0.018447211012244225,
+      "learning_rate": 9.79371522631553e-06,
+      "loss": 0.0478,
+      "step": 120,
+      "student_loss": 0.0015498347347602248,
+      "teacher_loss": 0.0010675351368263364
+    },
+    {
+      "epoch": 0.036043829296424454,
+      "grad_norm": 1.96875,
+      "kd_loss": 0.05630031228065491,
+      "learning_rate": 9.770070340332457e-06,
+      "loss": 0.0527,
+      "step": 125,
+      "student_loss": 0.04758762940764427,
+      "teacher_loss": 0.0004967509885318577
+    },
+    {
+      "epoch": 0.03748558246828143,
+      "grad_norm": 1.859375,
+      "kd_loss": 0.018152693286538124,
+      "learning_rate": 9.745174586073982e-06,
+      "loss": 0.0518,
+      "step": 130,
+      "student_loss": 0.0008988101035356522,
+      "teacher_loss": 0.0007278143893927336
+    },
+    {
+      "epoch": 0.03892733564013841,
+      "grad_norm": 1.6640625,
+      "kd_loss": 0.030904680490493774,
+      "learning_rate": 9.719034492020183e-06,
+      "loss": 0.0526,
+      "step": 135,
+      "student_loss": 0.0127235297113657,
+      "teacher_loss": 0.0011665972415357828
+    },
+    {
+      "epoch": 0.040369088811995385,
+      "grad_norm": 1.1640625,
+      "kd_loss": 0.01759810373187065,
+      "learning_rate": 9.691656912957686e-06,
+      "loss": 0.0494,
+      "step": 140,
+      "student_loss": 0.0008300879271700978,
+      "teacher_loss": 0.0005129938363097608
+    },
+    {
+      "epoch": 0.04181084198385236,
+      "grad_norm": 1.0234375,
+      "kd_loss": 0.061179179698228836,
+      "learning_rate": 9.663049028182112e-06,
+      "loss": 0.0457,
+      "step": 145,
+      "student_loss": 0.04404008761048317,
+      "teacher_loss": 0.009324059821665287
+    },
+    {
+      "epoch": 0.04325259515570934,
+      "grad_norm": 1.15625,
+      "kd_loss": 0.01291500125080347,
+      "learning_rate": 9.633218339615433e-06,
+      "loss": 0.0455,
+      "step": 150,
+      "student_loss": 0.0008404091349802911,
+      "teacher_loss": 0.0008450732566416264
+    },
+    {
+      "epoch": 0.04469434832756632,
+      "grad_norm": 1.4921875,
+      "kd_loss": 0.017479021102190018,
+      "learning_rate": 9.602172669838721e-06,
+      "loss": 0.0575,
+      "step": 155,
+      "student_loss": 0.0009151780977845192,
+      "teacher_loss": 0.0006974826683290303
+    },
+    {
+      "epoch": 0.0461361014994233,
+      "grad_norm": 1.671875,
+      "kd_loss": 0.022708255797624588,
+      "learning_rate": 9.569920160040815e-06,
+      "loss": 0.0503,
+      "step": 160,
+      "student_loss": 0.07660368084907532,
+      "teacher_loss": 0.04039459675550461
+    },
+    {
+      "epoch": 0.04757785467128028,
+      "grad_norm": 1.0703125,
+      "kd_loss": 0.027437202632427216,
+      "learning_rate": 9.536469267883432e-06,
+      "loss": 0.0451,
+      "step": 165,
+      "student_loss": 0.0005943832220509648,
+      "teacher_loss": 0.005336699075996876
+    },
+    {
+      "epoch": 0.049019607843137254,
+      "grad_norm": 1.71875,
+      "kd_loss": 0.014546042308211327,
+      "learning_rate": 9.501828765283295e-06,
+      "loss": 0.0459,
+      "step": 170,
+      "student_loss": 0.0006958618760108948,
+      "teacher_loss": 0.0005218263831920922
+    },
+    {
+      "epoch": 0.05046136101499423,
+      "grad_norm": 1.4453125,
+      "kd_loss": 0.02377346158027649,
+      "learning_rate": 9.466007736111846e-06,
+      "loss": 0.0465,
+      "step": 175,
+      "student_loss": 0.003214897122234106,
+      "teacher_loss": 0.0006713470793329179
+    },
+    {
+      "epoch": 0.05190311418685121,
+      "grad_norm": 1.296875,
+      "kd_loss": 0.02517828531563282,
+      "learning_rate": 9.429015573813163e-06,
+      "loss": 0.0454,
+      "step": 180,
+      "student_loss": 0.0007039233460091054,
+      "teacher_loss": 0.0003641469811554998
+    },
+    {
+      "epoch": 0.05334486735870819,
+      "grad_norm": 1.25,
+      "kd_loss": 0.029188504442572594,
+      "learning_rate": 9.390861978940687e-06,
+      "loss": 0.0473,
+      "step": 185,
+      "student_loss": 0.04238048940896988,
+      "teacher_loss": 0.00033479384728707373
+    },
+    {
+      "epoch": 0.05478662053056517,
+      "grad_norm": 1.484375,
+      "kd_loss": 0.03749082237482071,
+      "learning_rate": 9.351556956613423e-06,
+      "loss": 0.0436,
+      "step": 190,
+      "student_loss": 0.010270334780216217,
+      "teacher_loss": 0.0024021982681006193
+    },
+    {
+      "epoch": 0.056228373702422146,
+      "grad_norm": 2.0,
+      "kd_loss": 0.030336912721395493,
+      "learning_rate": 9.31111081389227e-06,
+      "loss": 0.0442,
+      "step": 195,
+      "student_loss": 0.010534510016441345,
+      "teacher_loss": 0.0003890562220476568
+    },
+    {
+      "epoch": 0.05767012687427912,
+      "grad_norm": 0.921875,
+      "kd_loss": 0.026554003357887268,
+      "learning_rate": 9.269534157077177e-06,
+      "loss": 0.0497,
+      "step": 200,
+      "student_loss": 0.0034760867711156607,
+      "teacher_loss": 0.00022423896007239819
+    },
+    {
+      "epoch": 0.0591118800461361,
+      "grad_norm": 1.9140625,
+      "kd_loss": 0.023410219699144363,
+      "learning_rate": 9.226837888925813e-06,
+      "loss": 0.0471,
+      "step": 205,
+      "student_loss": 0.03611442819237709,
+      "teacher_loss": 0.027781842276453972
+    },
+    {
+      "epoch": 0.06055363321799308,
+      "grad_norm": 1.7578125,
+      "kd_loss": 0.022867349907755852,
+      "learning_rate": 9.183033205794525e-06,
+      "loss": 0.0428,
+      "step": 210,
+      "student_loss": 0.001971556106582284,
+      "teacher_loss": 0.0009746765717864037
+    },
+    {
+      "epoch": 0.061995386389850055,
+      "grad_norm": 1.0234375,
+      "kd_loss": 0.028235338628292084,
+      "learning_rate": 9.13813159470227e-06,
+      "loss": 0.0449,
+      "step": 215,
+      "student_loss": 0.0009558866149745882,
+      "teacher_loss": 0.0004049334966111928
+    },
+    {
+      "epoch": 0.06343713956170703,
+      "grad_norm": 1.4296875,
+      "kd_loss": 0.03134317323565483,
+      "learning_rate": 9.092144830318357e-06,
+      "loss": 0.0438,
+      "step": 220,
+      "student_loss": 0.048195730894804,
+      "teacher_loss": 0.009161758236587048
+    },
+    {
+      "epoch": 0.06487889273356401,
+      "grad_norm": 1.1328125,
+      "kd_loss": 0.014049015007913113,
+      "learning_rate": 9.045084971874738e-06,
+      "loss": 0.0487,
+      "step": 225,
+      "student_loss": 0.05373133346438408,
+      "teacher_loss": 0.0009734037448652089
+    },
+    {
+      "epoch": 0.06632064590542099,
+      "grad_norm": 1.7265625,
+      "kd_loss": 0.021539395675063133,
+      "learning_rate": 8.99696436000368e-06,
+      "loss": 0.0384,
+      "step": 230,
+      "student_loss": 0.0008717047749087214,
+      "teacher_loss": 0.0028650674503296614
+    },
+    {
+      "epoch": 0.06776239907727798,
+      "grad_norm": 1.0390625,
+      "kd_loss": 0.045927971601486206,
+      "learning_rate": 8.947795613501658e-06,
+      "loss": 0.0397,
+      "step": 235,
+      "student_loss": 0.012143217958509922,
+      "teacher_loss": 0.0006723064580000937
+    },
+    {
+      "epoch": 0.06920415224913495,
+      "grad_norm": 0.78125,
+      "kd_loss": 0.01626853086054325,
+      "learning_rate": 8.897591626020284e-06,
+      "loss": 0.0425,
+      "step": 240,
+      "student_loss": 0.0004826921212952584,
+      "teacher_loss": 0.0003007515915669501
+    },
+    {
+      "epoch": 0.07064590542099193,
+      "grad_norm": 1.078125,
+      "kd_loss": 0.010876834392547607,
+      "learning_rate": 8.846365562685178e-06,
+      "loss": 0.0379,
+      "step": 245,
+      "student_loss": 0.00123109039850533,
+      "teacher_loss": 0.0017208561766892672
+    },
+    {
+      "epoch": 0.07208765859284891,
+      "grad_norm": 1.6484375,
+      "kd_loss": 0.012208702974021435,
+      "learning_rate": 8.794130856643635e-06,
+      "loss": 0.0402,
+      "step": 250,
+      "student_loss": 0.0006701876409351826,
+      "teacher_loss": 0.00039402375114150345
+    },
+    {
+      "epoch": 0.07352941176470588,
+      "grad_norm": 3.859375,
+      "kd_loss": 0.010964477434754372,
+      "learning_rate": 8.74090120554202e-06,
+      "loss": 0.0428,
+      "step": 255,
+      "student_loss": 0.0004243800649419427,
+      "teacher_loss": 0.0003773768839892
+    },
+    {
+      "epoch": 0.07497116493656286,
+      "grad_norm": 2.015625,
+      "kd_loss": 0.018098091706633568,
+      "learning_rate": 8.686690567933803e-06,
+      "loss": 0.0436,
+      "step": 260,
+      "student_loss": 0.040437813848257065,
+      "teacher_loss": 0.032756391912698746
+    },
+    {
+      "epoch": 0.07641291810841984,
+      "grad_norm": 1.125,
+      "kd_loss": 0.011841603554785252,
+      "learning_rate": 8.63151315961915e-06,
+      "loss": 0.0412,
+      "step": 265,
+      "student_loss": 0.0006605261587537825,
+      "teacher_loss": 0.0004997120704501867
+    },
+    {
+      "epoch": 0.07785467128027682,
+      "grad_norm": 1.046875,
+      "kd_loss": 0.01046097930520773,
+      "learning_rate": 8.575383449917103e-06,
+      "loss": 0.044,
+      "step": 270,
+      "student_loss": 0.0009966753423213959,
+      "teacher_loss": 0.0006801315466873348
+    },
+    {
+      "epoch": 0.07929642445213379,
+      "grad_norm": 1.515625,
+      "kd_loss": 0.01713527925312519,
+      "learning_rate": 8.518316157871232e-06,
+      "loss": 0.0403,
+      "step": 275,
+      "student_loss": 0.04822665825486183,
+      "teacher_loss": 0.03450855612754822
+    },
+    {
+      "epoch": 0.08073817762399077,
+      "grad_norm": 1.3828125,
+      "kd_loss": 0.021968362852931023,
+      "learning_rate": 8.460326248389825e-06,
+      "loss": 0.0401,
+      "step": 280,
+      "student_loss": 0.0006340977270156145,
+      "teacher_loss": 0.0001483594678575173
+    },
+    {
+      "epoch": 0.08217993079584775,
+      "grad_norm": 1.3203125,
+      "kd_loss": 0.01131309662014246,
+      "learning_rate": 8.401428928321607e-06,
+      "loss": 0.0435,
+      "step": 285,
+      "student_loss": 0.0005278023309074342,
+      "teacher_loss": 0.0004103762039449066
+    },
+    {
+      "epoch": 0.08362168396770472,
+      "grad_norm": 1.1015625,
+      "kd_loss": 0.00958277191966772,
+      "learning_rate": 8.341639642468002e-06,
+      "loss": 0.0469,
+      "step": 290,
+      "student_loss": 0.005627856124192476,
+      "teacher_loss": 0.0034064538776874542
+    },
+    {
+      "epoch": 0.0850634371395617,
+      "grad_norm": 1.140625,
+      "kd_loss": 0.009735080413520336,
+      "learning_rate": 8.280974069532999e-06,
+      "loss": 0.0409,
+      "step": 295,
+      "student_loss": 0.000509344507008791,
+      "teacher_loss": 0.0004550877492874861
+    },
+    {
+      "epoch": 0.08650519031141868,
+      "grad_norm": 1.09375,
+      "kd_loss": 0.031678151339292526,
+      "learning_rate": 8.219448118011687e-06,
+      "loss": 0.0379,
+      "step": 300,
+      "student_loss": 0.016466177999973297,
+      "teacher_loss": 0.002865313785150647
+    },
+    {
+      "epoch": 0.08794694348327567,
+      "grad_norm": 1.1015625,
+      "kd_loss": 0.013346894644200802,
+      "learning_rate": 8.157077922018537e-06,
+      "loss": 0.0353,
+      "step": 305,
+      "student_loss": 0.009980602189898491,
+      "teacher_loss": 0.0014113991055637598
+    },
+    {
+      "epoch": 0.08938869665513265,
+      "grad_norm": 1.90625,
+      "kd_loss": 0.010920979082584381,
+      "learning_rate": 8.093879837056486e-06,
+      "loss": 0.0384,
+      "step": 310,
+      "student_loss": 0.00036570793599821627,
+      "teacher_loss": 0.0002939177502412349
+    },
+    {
+      "epoch": 0.09083044982698962,
+      "grad_norm": 1.0078125,
+      "kd_loss": 0.021986963227391243,
+      "learning_rate": 8.029870435728018e-06,
+      "loss": 0.0385,
+      "step": 315,
+      "student_loss": 0.01466396264731884,
+      "teacher_loss": 0.0008777049370110035
+    },
+    {
+      "epoch": 0.0922722029988466,
+      "grad_norm": 1.640625,
+      "kd_loss": 0.014081098139286041,
+      "learning_rate": 7.965066503389264e-06,
+      "loss": 0.0417,
+      "step": 320,
+      "student_loss": 0.0004964058171026409,
+      "teacher_loss": 0.0003025036712642759
+    },
+    {
+      "epoch": 0.09371395617070358,
+      "grad_norm": 1.2421875,
+      "kd_loss": 0.03542112559080124,
+      "learning_rate": 7.89948503374835e-06,
+      "loss": 0.0378,
+      "step": 325,
+      "student_loss": 0.01556178368628025,
+      "teacher_loss": 0.018082890659570694
+    },
+    {
+      "epoch": 0.09515570934256055,
+      "grad_norm": 1.40625,
+      "kd_loss": 0.04085119441151619,
+      "learning_rate": 7.833143224409076e-06,
+      "loss": 0.0394,
+      "step": 330,
+      "student_loss": 0.024770811200141907,
+      "teacher_loss": 0.0021320905070751905
+    },
+    {
+      "epoch": 0.09659746251441753,
+      "grad_norm": 1.0234375,
+      "kd_loss": 0.008477268740534782,
+      "learning_rate": 7.766058472361154e-06,
+      "loss": 0.0338,
+      "step": 335,
+      "student_loss": 0.0009084849734790623,
+      "teacher_loss": 0.0007285018800757825
+    },
+    {
+      "epoch": 0.09803921568627451,
+      "grad_norm": 1.28125,
+      "kd_loss": 0.014947460032999516,
+      "learning_rate": 7.698248369418146e-06,
+      "loss": 0.0388,
+      "step": 340,
+      "student_loss": 0.009875037707388401,
+      "teacher_loss": 0.00507500022649765
+    },
+    {
+      "epoch": 0.09948096885813149,
+      "grad_norm": 1.2421875,
+      "kd_loss": 0.019748909398913383,
+      "learning_rate": 7.629730697604314e-06,
+      "loss": 0.0437,
+      "step": 345,
+      "student_loss": 0.008698839694261551,
+      "teacher_loss": 0.00021470236242748797
+    },
+    {
+      "epoch": 0.10092272202998846,
+      "grad_norm": 1.453125,
+      "kd_loss": 0.038638580590486526,
+      "learning_rate": 7.560523424491595e-06,
+      "loss": 0.0333,
+      "step": 350,
+      "student_loss": 0.007182905916124582,
+      "teacher_loss": 0.0004611952172126621
+    },
+    {
+      "epoch": 0.10236447520184544,
+      "grad_norm": 1.4375,
+      "kd_loss": 0.008461177349090576,
+      "learning_rate": 7.490644698487909e-06,
+      "loss": 0.0405,
+      "step": 355,
+      "student_loss": 0.0004199718532618135,
+      "teacher_loss": 0.00038222281727939844
+    },
+    {
+      "epoch": 0.10380622837370242,
+      "grad_norm": 1.1796875,
+      "kd_loss": 0.008598582819104195,
+      "learning_rate": 7.420112844078066e-06,
+      "loss": 0.0396,
+      "step": 360,
+      "student_loss": 0.00045404830598272383,
+      "teacher_loss": 0.0003997418680228293
+    },
+    {
+      "epoch": 0.1052479815455594,
+      "grad_norm": 1.78125,
+      "kd_loss": 0.018130140379071236,
+      "learning_rate": 7.348946357018479e-06,
+      "loss": 0.0425,
+      "step": 365,
+      "student_loss": 0.06869062036275864,
+      "teacher_loss": 0.027944643050432205
+    },
+    {
+      "epoch": 0.10668973471741638,
+      "grad_norm": 1.03125,
+      "kd_loss": 0.0350988432765007,
+      "learning_rate": 7.277163899486975e-06,
+      "loss": 0.0447,
+      "step": 370,
+      "student_loss": 0.015085455030202866,
+      "teacher_loss": 0.0004648211761377752
+    },
+    {
+      "epoch": 0.10813148788927336,
+      "grad_norm": 1.0703125,
+      "kd_loss": 0.01613399013876915,
+      "learning_rate": 7.204784295188959e-06,
+      "loss": 0.0365,
+      "step": 375,
+      "student_loss": 0.03554360568523407,
+      "teacher_loss": 0.021264519542455673
+    },
+    {
+      "epoch": 0.10957324106113034,
+      "grad_norm": 1.296875,
+      "kd_loss": 0.010999550111591816,
+      "learning_rate": 7.1318265244212305e-06,
+      "loss": 0.0381,
+      "step": 380,
+      "student_loss": 0.0004269553755875677,
+      "teacher_loss": 0.0003071910759899765
+    },
+    {
+      "epoch": 0.11101499423298732,
+      "grad_norm": 0.875,
+      "kd_loss": 0.015028773806989193,
+      "learning_rate": 7.05830971909472e-06,
+      "loss": 0.0349,
+      "step": 385,
+      "student_loss": 0.0005910908803343773,
+      "teacher_loss": 0.0003781717678066343
+    },
+    {
+      "epoch": 0.11245674740484429,
+      "grad_norm": 1.25,
+      "kd_loss": 0.010998338460922241,
+      "learning_rate": 6.9842531577174865e-06,
+      "loss": 0.033,
+      "step": 390,
+      "student_loss": 0.00025347189512103796,
+      "teacher_loss": 0.00023755666916258633
+    },
+    {
+      "epoch": 0.11389850057670127,
+      "grad_norm": 1.390625,
+      "kd_loss": 0.010839108377695084,
+      "learning_rate": 6.9096762603392595e-06,
+      "loss": 0.0393,
+      "step": 395,
+      "student_loss": 0.00046008970821276307,
+      "teacher_loss": 0.00034296512603759766
+    },
+    {
+      "epoch": 0.11534025374855825,
+      "grad_norm": 2.40625,
+      "kd_loss": 0.015689171850681305,
+      "learning_rate": 6.834598583458862e-06,
+      "loss": 0.0333,
+      "step": 400,
+      "student_loss": 0.0004951858427375555,
+      "teacher_loss": 0.0002840181696228683
+    },
+    {
+      "epoch": 0.11678200692041522,
+      "grad_norm": 1.328125,
+      "kd_loss": 0.014689328148961067,
+      "learning_rate": 6.7590398148958625e-06,
+      "loss": 0.0425,
+      "step": 405,
+      "student_loss": 0.005328211933374405,
+      "teacher_loss": 0.0002102136058965698
+    },
+    {
+      "epoch": 0.1182237600922722,
+      "grad_norm": 1.4609375,
+      "kd_loss": 0.026721687987446785,
+      "learning_rate": 6.6830197686277945e-06,
+      "loss": 0.0417,
+      "step": 410,
+      "student_loss": 0.015544440597295761,
+      "teacher_loss": 0.00868156086653471
+    },
+    {
+      "epoch": 0.11966551326412918,
+      "grad_norm": 1.1640625,
+      "kd_loss": 0.0165933258831501,
+      "learning_rate": 6.6065583795942625e-06,
+      "loss": 0.0409,
+      "step": 415,
+      "student_loss": 0.0018743074033409357,
+      "teacher_loss": 0.002361958846449852
+    },
+    {
+      "epoch": 0.12110726643598616,
+      "grad_norm": 1.34375,
+      "kd_loss": 0.02428903616964817,
+      "learning_rate": 6.52967569846937e-06,
+      "loss": 0.0376,
+      "step": 420,
+      "student_loss": 0.05027158558368683,
+      "teacher_loss": 0.022369280457496643
+    },
+    {
+      "epoch": 0.12254901960784313,
+      "grad_norm": 1.171875,
+      "kd_loss": 0.00989749375730753,
+      "learning_rate": 6.452391886403767e-06,
+      "loss": 0.0366,
+      "step": 425,
+      "student_loss": 0.001526529318653047,
+      "teacher_loss": 0.001954666106030345
+    },
+    {
+      "epoch": 0.12399077277970011,
+      "grad_norm": 1.40625,
+      "kd_loss": 0.025572113692760468,
+      "learning_rate": 6.374727209737743e-06,
+      "loss": 0.0457,
+      "step": 430,
+      "student_loss": 0.05225735530257225,
+      "teacher_loss": 0.06261400878429413
+    },
+    {
+      "epoch": 0.1254325259515571,
+      "grad_norm": 1.1953125,
+      "kd_loss": 0.009243296459317207,
+      "learning_rate": 6.296702034686726e-06,
+      "loss": 0.0351,
+      "step": 435,
+      "student_loss": 0.0006208799313753843,
+      "teacher_loss": 0.0005131844663992524
+    },
+    {
+      "epoch": 0.12687427912341406,
+      "grad_norm": 1.140625,
+      "kd_loss": 0.025882720947265625,
+      "learning_rate": 6.218336822000598e-06,
+      "loss": 0.0366,
+      "step": 440,
+      "student_loss": 0.022235309705138206,
+      "teacher_loss": 0.005665617063641548
+    },
+    {
+      "epoch": 0.12831603229527105,
+      "grad_norm": 1.5546875,
+      "kd_loss": 0.020934544503688812,
+      "learning_rate": 6.139652121598219e-06,
+      "loss": 0.0381,
+      "step": 445,
+      "student_loss": 0.02492375858128071,
+      "teacher_loss": 0.01704920269548893
+    },
+    {
+      "epoch": 0.12975778546712802,
+      "grad_norm": 1.078125,
+      "kd_loss": 0.021503543481230736,
+      "learning_rate": 6.060668567178561e-06,
+      "loss": 0.039,
+      "step": 450,
+      "student_loss": 0.0008401675149798393,
+      "teacher_loss": 0.0007966886623762548
+    },
+    {
+      "epoch": 0.131199538638985,
+      "grad_norm": 0.99609375,
+      "kd_loss": 0.011403748765587807,
+      "learning_rate": 5.981406870809889e-06,
+      "loss": 0.0383,
+      "step": 455,
+      "student_loss": 0.0014924939023330808,
+      "teacher_loss": 0.000647007254883647
+    },
+    {
+      "epoch": 0.13264129181084197,
+      "grad_norm": 1.515625,
+      "kd_loss": 0.013661489821970463,
+      "learning_rate": 5.9018878174983674e-06,
+      "loss": 0.0329,
+      "step": 460,
+      "student_loss": 0.0015512986574321985,
+      "teacher_loss": 0.0012551237596198916
+    },
+    {
+      "epoch": 0.13408304498269896,
+      "grad_norm": 1.265625,
+      "kd_loss": 0.020031817257404327,
+      "learning_rate": 5.822132259737565e-06,
+      "loss": 0.0399,
+      "step": 465,
+      "student_loss": 0.0005617028218694031,
+      "teacher_loss": 0.0006807463942095637
+    },
+    {
+      "epoch": 0.13552479815455595,
+      "grad_norm": 1.171875,
+      "kd_loss": 0.012775675393640995,
+      "learning_rate": 5.742161112040237e-06,
+      "loss": 0.0377,
+      "step": 470,
+      "student_loss": 0.00029168292530812323,
+      "teacher_loss": 0.00020419349311850965
+    },
+    {
+      "epoch": 0.13696655132641292,
+      "grad_norm": 0.87109375,
+      "kd_loss": 0.016445137560367584,
+      "learning_rate": 5.661995345453867e-06,
+      "loss": 0.0315,
+      "step": 475,
+      "student_loss": 0.0005847346619702876,
+      "teacher_loss": 0.0003634036984294653
+    },
+    {
+      "epoch": 0.1384083044982699,
+      "grad_norm": 0.95703125,
+      "kd_loss": 0.014534696005284786,
+      "learning_rate": 5.581655982061367e-06,
+      "loss": 0.0466,
+      "step": 480,
+      "student_loss": 0.0203537754714489,
+      "teacher_loss": 0.014939186163246632
+    },
+    {
+      "epoch": 0.13985005767012687,
+      "grad_norm": 1.1640625,
+      "kd_loss": 0.008392157033085823,
+      "learning_rate": 5.501164089468406e-06,
+      "loss": 0.0357,
+      "step": 485,
+      "student_loss": 0.0004224316217005253,
+      "teacher_loss": 0.00044211489148437977
+    },
+    {
+      "epoch": 0.14129181084198386,
+      "grad_norm": 1.8984375,
+      "kd_loss": 0.014247741550207138,
+      "learning_rate": 5.4205407752787884e-06,
+      "loss": 0.0428,
+      "step": 490,
+      "student_loss": 0.019939009100198746,
+      "teacher_loss": 0.009562309831380844
+    },
+    {
+      "epoch": 0.14273356401384082,
+      "grad_norm": 1.828125,
+      "kd_loss": 0.026821549981832504,
+      "learning_rate": 5.339807181559359e-06,
+      "loss": 0.0484,
+      "step": 495,
+      "student_loss": 0.01085620652884245,
+      "teacher_loss": 0.001887582358904183
+    },
+    {
+      "epoch": 0.14417531718569782,
+      "grad_norm": 1.03125,
+      "kd_loss": 0.011890986934304237,
+      "learning_rate": 5.258984479295853e-06,
+      "loss": 0.0366,
+      "step": 500,
+      "student_loss": 0.0007122078677639365,
+      "teacher_loss": 0.0006097567966207862
+    },
+    {
+      "epoch": 0.14561707035755478,
+      "grad_norm": 1.0,
+      "kd_loss": 0.01012763474136591,
+      "learning_rate": 5.1780938628411795e-06,
+      "loss": 0.0433,
+      "step": 505,
+      "student_loss": 0.0004120942030567676,
+      "teacher_loss": 0.00030555034754797816
+    },
+    {
+      "epoch": 0.14705882352941177,
+      "grad_norm": 1.90625,
+      "kd_loss": 0.010170744732022285,
+      "learning_rate": 5.097156544357567e-06,
+      "loss": 0.0382,
+      "step": 510,
+      "student_loss": 0.0002881335385609418,
+      "teacher_loss": 0.000244438968366012
+    },
+    {
+      "epoch": 0.14850057670126873,
+      "grad_norm": 1.359375,
+      "kd_loss": 0.0138414166867733,
+      "learning_rate": 5.016193748254045e-06,
+      "loss": 0.031,
+      "step": 515,
+      "student_loss": 0.005790602881461382,
+      "teacher_loss": 0.0001912783191073686
+    },
+    {
+      "epoch": 0.14994232987312572,
+      "grad_norm": 1.9921875,
+      "kd_loss": 0.03539569675922394,
+      "learning_rate": 4.935226705620699e-06,
+      "loss": 0.0397,
+      "step": 520,
+      "student_loss": 0.04242030531167984,
+      "teacher_loss": 0.011500299908220768
+    },
+    {
+      "epoch": 0.1513840830449827,
+      "grad_norm": 0.67578125,
+      "kd_loss": 0.018779262900352478,
+      "learning_rate": 4.8542766486612035e-06,
+      "loss": 0.0403,
+      "step": 525,
+      "student_loss": 0.00041962284012697637,
+      "teacher_loss": 0.00021298698266036808
+    },
+    {
+      "epoch": 0.15282583621683968,
+      "grad_norm": 1.2421875,
+      "kd_loss": 0.01180377509444952,
+      "learning_rate": 4.773364805125025e-06,
+      "loss": 0.0351,
+      "step": 530,
+      "student_loss": 0.00039459849358536303,
+      "teacher_loss": 0.0003135094593744725
+    },
+    {
+      "epoch": 0.15426758938869667,
+      "grad_norm": 0.96484375,
+      "kd_loss": 0.022030461579561234,
+      "learning_rate": 4.6925123927408265e-06,
+      "loss": 0.0343,
+      "step": 535,
+      "student_loss": 0.000637000659480691,
+      "teacher_loss": 0.00034665301791392267
+    },
+    {
+      "epoch": 0.15570934256055363,
+      "grad_norm": 1.234375,
+      "kd_loss": 0.01367215160280466,
+      "learning_rate": 4.611740613652485e-06,
+      "loss": 0.0333,
+      "step": 540,
+      "student_loss": 0.0006559583125635982,
+      "teacher_loss": 0.0003204621316399425
+    },
+    {
+      "epoch": 0.15715109573241062,
+      "grad_norm": 2.234375,
+      "kd_loss": 0.00888274796307087,
+      "learning_rate": 4.531070648859186e-06,
+      "loss": 0.0319,
+      "step": 545,
+      "student_loss": 0.01682436652481556,
+      "teacher_loss": 0.013372495770454407
+    },
+    {
+      "epoch": 0.15859284890426759,
+      "grad_norm": 1.640625,
+      "kd_loss": 0.026771951466798782,
+      "learning_rate": 4.450523652661086e-06,
+      "loss": 0.0306,
+      "step": 550,
+      "student_loss": 0.0001725157053442672,
+      "teacher_loss": 0.012681440450251102
+    },
+    {
+      "epoch": 0.16003460207612458,
+      "grad_norm": 1.1015625,
+      "kd_loss": 0.03767453879117966,
+      "learning_rate": 4.370120747111956e-06,
+      "loss": 0.0381,
+      "step": 555,
+      "student_loss": 0.009898228570818901,
+      "teacher_loss": 0.0022960191126912832
+    },
+    {
+      "epoch": 0.16147635524798154,
+      "grad_norm": 1.734375,
+      "kd_loss": 0.0351857915520668,
+      "learning_rate": 4.289883016480291e-06,
+      "loss": 0.0381,
+      "step": 560,
+      "student_loss": 0.027657803148031235,
+      "teacher_loss": 0.00034597894409671426
+    },
+    {
+      "epoch": 0.16291810841983853,
+      "grad_norm": 1.4296875,
+      "kd_loss": 0.019546959549188614,
+      "learning_rate": 4.209831501720328e-06,
+      "loss": 0.0346,
+      "step": 565,
+      "student_loss": 0.028599649667739868,
+      "teacher_loss": 0.018787631765007973
+    },
+    {
+      "epoch": 0.1643598615916955,
+      "grad_norm": 1.5625,
+      "kd_loss": 0.020644016563892365,
+      "learning_rate": 4.129987194954421e-06,
+      "loss": 0.0405,
+      "step": 570,
+      "student_loss": 0.010047786869108677,
+      "teacher_loss": 0.006790643557906151
+    },
+    {
+      "epoch": 0.16580161476355249,
+      "grad_norm": 1.4921875,
+      "kd_loss": 0.01332971639931202,
+      "learning_rate": 4.050371033968216e-06,
+      "loss": 0.0376,
+      "step": 575,
+      "student_loss": 0.0004119194345548749,
+      "teacher_loss": 0.00025748086045496166
+    },
+    {
+      "epoch": 0.16724336793540945,
+      "grad_norm": 1.3515625,
+      "kd_loss": 0.012037251144647598,
+      "learning_rate": 3.9710038967200825e-06,
+      "loss": 0.0342,
+      "step": 580,
+      "student_loss": 0.0030028573237359524,
+      "teacher_loss": 0.0012405890738591552
+    },
+    {
+      "epoch": 0.16868512110726644,
+      "grad_norm": 0.88671875,
+      "kd_loss": 0.01703016459941864,
+      "learning_rate": 3.89190659586623e-06,
+      "loss": 0.032,
+      "step": 585,
+      "student_loss": 0.0007975402986630797,
+      "teacher_loss": 0.0002710323315113783
+    },
+    {
+      "epoch": 0.1701268742791234,
+      "grad_norm": 1.1171875,
+      "kd_loss": 0.01272827759385109,
+      "learning_rate": 3.8130998733029517e-06,
+      "loss": 0.035,
+      "step": 590,
+      "student_loss": 0.000885407323949039,
+      "teacher_loss": 0.00043826864566653967
+    },
+    {
+      "epoch": 0.1715686274509804,
+      "grad_norm": 1.3828125,
+      "kd_loss": 0.009466774761676788,
+      "learning_rate": 3.734604394727419e-06,
+      "loss": 0.0345,
+      "step": 595,
+      "student_loss": 0.0005723866051994264,
+      "teacher_loss": 0.0005249618552625179
+    },
+    {
+      "epoch": 0.17301038062283736,
+      "grad_norm": 1.4765625,
+      "kd_loss": 0.020295076072216034,
+      "learning_rate": 3.656440744218464e-06,
+      "loss": 0.04,
+      "step": 600,
+      "student_loss": 0.04926498606801033,
+      "teacher_loss": 0.00894973799586296
+    },
+    {
+      "epoch": 0.17445213379469435,
+      "grad_norm": 1.1484375,
+      "kd_loss": 0.020013822242617607,
+      "learning_rate": 3.578629418838757e-06,
+      "loss": 0.0378,
+      "step": 605,
+      "student_loss": 0.06380540132522583,
+      "teacher_loss": 0.03696807473897934
+    },
+    {
+      "epoch": 0.17589388696655134,
+      "grad_norm": 1.1796875,
+      "kd_loss": 0.026783978566527367,
+      "learning_rate": 3.5011908232598124e-06,
+      "loss": 0.0342,
+      "step": 610,
+      "student_loss": 0.007228103466331959,
+      "teacher_loss": 0.0016964355017989874
+    },
+    {
+      "epoch": 0.1773356401384083,
+      "grad_norm": 1.0625,
+      "kd_loss": 0.013121667318046093,
+      "learning_rate": 3.4241452644112085e-06,
+      "loss": 0.0302,
+      "step": 615,
+      "student_loss": 0.000252434954745695,
+      "teacher_loss": 0.0002282678324263543
+    },
+    {
+      "epoch": 0.1787773933102653,
+      "grad_norm": 1.0390625,
+      "kd_loss": 0.01814274862408638,
+      "learning_rate": 3.3475129461554567e-06,
+      "loss": 0.0412,
+      "step": 620,
+      "student_loss": 0.010608767159283161,
+      "teacher_loss": 0.006938976235687733
+    },
+    {
+      "epoch": 0.18021914648212226,
+      "grad_norm": 1.21875,
+      "kd_loss": 0.016144433990120888,
+      "learning_rate": 3.271313963989886e-06,
+      "loss": 0.0318,
+      "step": 625,
+      "student_loss": 0.003376360982656479,
+      "teacher_loss": 0.003628369187936187
+    },
+    {
+      "epoch": 0.18166089965397925,
+      "grad_norm": 1.6796875,
+      "kd_loss": 0.01930667646229267,
+      "learning_rate": 3.195568299776945e-06,
+      "loss": 0.0392,
+      "step": 630,
+      "student_loss": 0.042429447174072266,
+      "teacher_loss": 0.02139645628631115
+    },
+    {
+      "epoch": 0.1831026528258362,
+      "grad_norm": 1.1640625,
+      "kd_loss": 0.015184500254690647,
+      "learning_rate": 3.1202958165043053e-06,
+      "loss": 0.0522,
+      "step": 635,
+      "student_loss": 0.0015469329664483666,
+      "teacher_loss": 0.0002648464578669518
+    },
+    {
+      "epoch": 0.1845444059976932,
+      "grad_norm": 1.6875,
+      "kd_loss": 0.01360522024333477,
+      "learning_rate": 3.045516253076137e-06,
+      "loss": 0.0321,
+      "step": 640,
+      "student_loss": 0.000489354133605957,
+      "teacher_loss": 0.0003778399550355971
+    },
+    {
+      "epoch": 0.18598615916955016,
+      "grad_norm": 1.328125,
+      "kd_loss": 0.016992032527923584,
+      "learning_rate": 2.9712492191369245e-06,
+      "loss": 0.0325,
+      "step": 645,
+      "student_loss": 0.0005057267262600362,
+      "teacher_loss": 0.0007710132049396634
+    },
+    {
+      "epoch": 0.18742791234140715,
+      "grad_norm": 1.34375,
+      "kd_loss": 0.009760286659002304,
+      "learning_rate": 2.8975141899291777e-06,
+      "loss": 0.0316,
+      "step": 650,
+      "student_loss": 0.0006846904871053994,
+      "teacher_loss": 0.0006360806291922927
+    },
+    {
+      "epoch": 0.18886966551326412,
+      "grad_norm": 1.140625,
+      "kd_loss": 0.01777932234108448,
+      "learning_rate": 2.8243305011863843e-06,
+      "loss": 0.035,
+      "step": 655,
+      "student_loss": 0.0004645780718419701,
+      "teacher_loss": 0.0002376337070018053
+    },
+    {
+      "epoch": 0.1903114186851211,
+      "grad_norm": 1.328125,
+      "kd_loss": 0.012804077006876469,
+      "learning_rate": 2.751717344062552e-06,
+      "loss": 0.0393,
+      "step": 660,
+      "student_loss": 0.0006086655776016414,
+      "teacher_loss": 0.0005673821433447301
+    },
+    {
+      "epoch": 0.19175317185697807,
+      "grad_norm": 2.71875,
+      "kd_loss": 0.04194798693060875,
+      "learning_rate": 2.6796937600996587e-06,
+      "loss": 0.0417,
+      "step": 665,
+      "student_loss": 0.004477351903915405,
+      "teacher_loss": 0.0028319216798990965
+    },
+    {
+      "epoch": 0.19319492502883506,
+      "grad_norm": 1.4453125,
+      "kd_loss": 0.020050913095474243,
+      "learning_rate": 2.6082786362343377e-06,
+      "loss": 0.0387,
+      "step": 670,
+      "student_loss": 0.008853067643940449,
+      "teacher_loss": 0.005904260091483593
+    },
+    {
+      "epoch": 0.19463667820069205,
+      "grad_norm": 1.09375,
+      "kd_loss": 0.008323847316205502,
+      "learning_rate": 2.5374906998451094e-06,
+      "loss": 0.0365,
+      "step": 675,
+      "student_loss": 0.0005440004752017558,
+      "teacher_loss": 0.00048730146954767406
+    },
+    {
+      "epoch": 0.19607843137254902,
+      "grad_norm": 1.5234375,
+      "kd_loss": 0.025357170030474663,
+      "learning_rate": 2.467348513841447e-06,
+      "loss": 0.033,
+      "step": 680,
+      "student_loss": 0.07211022824048996,
+      "teacher_loss": 0.03345099464058876
+    },
+    {
+      "epoch": 0.197520184544406,
+      "grad_norm": 1.6171875,
+      "kd_loss": 0.016125330701470375,
+      "learning_rate": 2.3978704717959777e-06,
+      "loss": 0.035,
+      "step": 685,
+      "student_loss": 0.035295210778713226,
+      "teacher_loss": 0.02864968776702881
+    },
+    {
+      "epoch": 0.19896193771626297,
+      "grad_norm": 1.21875,
+      "kd_loss": 0.042695559561252594,
+      "learning_rate": 2.329074793121085e-06,
+      "loss": 0.038,
+      "step": 690,
+      "student_loss": 0.015520169399678707,
+      "teacher_loss": 0.006200406700372696
+    },
+    {
+      "epoch": 0.20040369088811996,
+      "grad_norm": 1.390625,
+      "kd_loss": 0.016068480908870697,
+      "learning_rate": 2.260979518291186e-06,
+      "loss": 0.0406,
+      "step": 695,
+      "student_loss": 0.006739252246916294,
+      "teacher_loss": 0.004444445949047804
+    },
+    {
+      "epoch": 0.20184544405997693,
+      "grad_norm": 1.5390625,
+      "kd_loss": 0.010956254787743092,
+      "learning_rate": 2.1936025041119268e-06,
+      "loss": 0.0352,
+      "step": 700,
+      "student_loss": 0.0009333753259852529,
+      "teacher_loss": 0.0003666435368359089
+    },
+    {
+      "epoch": 0.20328719723183392,
+      "grad_norm": 1.3828125,
+      "kd_loss": 0.00898037664592266,
+      "learning_rate": 2.1269614190375477e-06,
+      "loss": 0.0344,
+      "step": 705,
+      "student_loss": 0.0006648478447459638,
+      "teacher_loss": 0.0005693589337170124
+    },
+    {
+      "epoch": 0.20472895040369088,
+      "grad_norm": 1.5,
+      "kd_loss": 0.041511427611112595,
+      "learning_rate": 2.061073738537635e-06,
+      "loss": 0.0396,
+      "step": 710,
+      "student_loss": 0.0163543913513422,
+      "teacher_loss": 0.00382953486405313
+    },
+    {
+      "epoch": 0.20617070357554787,
+      "grad_norm": 2.0,
+      "kd_loss": 0.014297292567789555,
+      "learning_rate": 1.9959567405144825e-06,
+      "loss": 0.0476,
+      "step": 715,
+      "student_loss": 0.004557440988719463,
+      "teacher_loss": 0.009534560143947601
+    },
+    {
+      "epoch": 0.20761245674740483,
+      "grad_norm": 1.109375,
+      "kd_loss": 0.013292558491230011,
+      "learning_rate": 1.931627500772263e-06,
+      "loss": 0.0378,
+      "step": 720,
+      "student_loss": 0.0005340321222320199,
+      "teacher_loss": 0.000525432638823986
+    },
+    {
+      "epoch": 0.20905420991926182,
+      "grad_norm": 0.93359375,
+      "kd_loss": 0.01108925137668848,
+      "learning_rate": 1.8681028885391905e-06,
+      "loss": 0.0297,
+      "step": 725,
+      "student_loss": 0.0002994259411934763,
+      "teacher_loss": 0.0002954052179120481
+    },
+    {
+      "epoch": 0.2104959630911188,
+      "grad_norm": 1.2109375,
+      "kd_loss": 0.01718929037451744,
+      "learning_rate": 1.8053995620438625e-06,
+      "loss": 0.0354,
+      "step": 730,
+      "student_loss": 0.00870412029325962,
+      "teacher_loss": 0.0017060510581359267
+    },
+    {
+      "epoch": 0.21193771626297578,
+      "grad_norm": 1.515625,
+      "kd_loss": 0.016554107889533043,
+      "learning_rate": 1.743533964146924e-06,
+      "loss": 0.041,
+      "step": 735,
+      "student_loss": 0.00043048406951129436,
+      "teacher_loss": 0.0002133132511517033
+    },
+    {
+      "epoch": 0.21337946943483277,
+      "grad_norm": 0.9140625,
+      "kd_loss": 0.023798726499080658,
+      "learning_rate": 1.6825223180292138e-06,
+      "loss": 0.0324,
+      "step": 740,
+      "student_loss": 0.0012331322068348527,
+      "teacher_loss": 0.0018722045933827758
+    },
+    {
+      "epoch": 0.21482122260668973,
+      "grad_norm": 1.890625,
+      "kd_loss": 0.014276617206633091,
+      "learning_rate": 1.6223806229375182e-06,
+      "loss": 0.0367,
+      "step": 745,
+      "student_loss": 0.040091373026371,
+      "teacher_loss": 0.019951729103922844
+    },
+    {
+      "epoch": 0.21626297577854672,
+      "grad_norm": 1.2265625,
+      "kd_loss": 0.03414074704051018,
+      "learning_rate": 1.563124649989043e-06,
+      "loss": 0.0366,
+      "step": 750,
+      "student_loss": 0.017988989129662514,
+      "teacher_loss": 0.006315938197076321
+    },
+    {
+      "epoch": 0.2177047289504037,
+      "grad_norm": 1.9375,
+      "kd_loss": 0.013627647422254086,
+      "learning_rate": 1.5047699380357134e-06,
+      "loss": 0.0418,
+      "step": 755,
+      "student_loss": 0.024281585589051247,
+      "teacher_loss": 0.0027684655506163836
+    },
+    {
+      "epoch": 0.21914648212226068,
+      "grad_norm": 1.5,
+      "kd_loss": 0.030101457610726357,
+      "learning_rate": 1.4473317895893773e-06,
+      "loss": 0.0317,
+      "step": 760,
+      "student_loss": 0.024278033524751663,
+      "teacher_loss": 0.00042108772322535515
+    },
+    {
+      "epoch": 0.22058823529411764,
+      "grad_norm": 1.265625,
+      "kd_loss": 0.03181413933634758,
+      "learning_rate": 1.39082526680899e-06,
+      "loss": 0.0404,
+      "step": 765,
+      "student_loss": 0.004552094731479883,
+      "teacher_loss": 0.001384846051223576
+    },
+    {
+      "epoch": 0.22202998846597463,
+      "grad_norm": 1.0546875,
+      "kd_loss": 0.03087952919304371,
+      "learning_rate": 1.3352651875508204e-06,
+      "loss": 0.0359,
+      "step": 770,
+      "student_loss": 0.00462262611836195,
+      "teacher_loss": 0.0008631970267742872
+    },
+    {
+      "epoch": 0.2234717416378316,
+      "grad_norm": 1.0703125,
+      "kd_loss": 0.01582036353647709,
+      "learning_rate": 1.2806661214827286e-06,
+      "loss": 0.0327,
+      "step": 775,
+      "student_loss": 0.00521172396838665,
+      "teacher_loss": 0.002128555905073881
+    },
+    {
+      "epoch": 0.22491349480968859,
+      "grad_norm": 1.078125,
+      "kd_loss": 0.017553336918354034,
+      "learning_rate": 1.2270423862635188e-06,
+      "loss": 0.0375,
+      "step": 780,
+      "student_loss": 0.0012290088925510645,
+      "teacher_loss": 0.00023391979630105197
+    },
+    {
+      "epoch": 0.22635524798154555,
+      "grad_norm": 1.578125,
+      "kd_loss": 0.009543483145534992,
+      "learning_rate": 1.1744080437883859e-06,
+      "loss": 0.0324,
+      "step": 785,
+      "student_loss": 0.00035309791564941406,
+      "teacher_loss": 0.00032548559829592705
+    },
+    {
+      "epoch": 0.22779700115340254,
+      "grad_norm": 1.3203125,
+      "kd_loss": 0.00901024416089058,
+      "learning_rate": 1.1227768965014246e-06,
+      "loss": 0.032,
+      "step": 790,
+      "student_loss": 0.000992319663055241,
+      "teacher_loss": 0.0008018451044335961
+    },
+    {
+      "epoch": 0.2292387543252595,
+      "grad_norm": 1.25,
+      "kd_loss": 0.013804268091917038,
+      "learning_rate": 1.0721624837761768e-06,
+      "loss": 0.0368,
+      "step": 795,
+      "student_loss": 0.00046814189408905804,
+      "teacher_loss": 0.00019660216639749706
+    },
+    {
+      "epoch": 0.2306805074971165,
+      "grad_norm": 1.8046875,
+      "kd_loss": 0.025934722274541855,
+      "learning_rate": 1.0225780783651689e-06,
+      "loss": 0.0436,
+      "step": 800,
+      "student_loss": 0.09193355590105057,
+      "teacher_loss": 0.045340001583099365
+    },
+    {
+      "epoch": 0.23212226066897348,
+      "grad_norm": 1.40625,
+      "kd_loss": 0.01032049860805273,
+      "learning_rate": 9.740366829193587e-07,
+      "loss": 0.0412,
+      "step": 805,
+      "student_loss": 0.0004188880557194352,
+      "teacher_loss": 0.00034304597647860646
+    },
+    {
+      "epoch": 0.23356401384083045,
+      "grad_norm": 5.96875,
+      "kd_loss": 0.01783071458339691,
+      "learning_rate": 9.265510265784189e-07,
+      "loss": 0.0363,
+      "step": 810,
+      "student_loss": 0.0005420530214905739,
+      "teacher_loss": 0.00027590151876211166
+    },
+    {
+      "epoch": 0.23500576701268744,
+      "grad_norm": 1.9140625,
+      "kd_loss": 0.011872808448970318,
+      "learning_rate": 8.801335616327378e-07,
+      "loss": 0.0351,
+      "step": 815,
+      "student_loss": 0.004859322682023048,
+      "teacher_loss": 0.013330879621207714
+    },
+    {
+      "epoch": 0.2364475201845444,
+      "grad_norm": 1.2265625,
+      "kd_loss": 0.01942305825650692,
+      "learning_rate": 8.347964602580245e-07,
+      "loss": 0.0359,
+      "step": 820,
+      "student_loss": 0.003229373600333929,
+      "teacher_loss": 0.0003580668126232922
+    },
+    {
+      "epoch": 0.2378892733564014,
+      "grad_norm": 1.3828125,
+      "kd_loss": 0.019788295030593872,
+      "learning_rate": 7.905516113233652e-07,
+      "loss": 0.0346,
+      "step": 825,
+      "student_loss": 0.0008779842173680663,
+      "teacher_loss": 0.016724394634366035
+    },
+    {
+      "epoch": 0.23933102652825836,
+      "grad_norm": 1.421875,
+      "kd_loss": 0.018033282831311226,
+      "learning_rate": 7.474106172735746e-07,
+      "loss": 0.0358,
+      "step": 830,
+      "student_loss": 0.008363536559045315,
+      "teacher_loss": 0.005316237919032574
+    },
+    {
+      "epoch": 0.24077277970011535,
+      "grad_norm": 1.109375,
+      "kd_loss": 0.016192706301808357,
+      "learning_rate": 7.053847910866513e-07,
+      "loss": 0.0315,
+      "step": 835,
+      "student_loss": 0.014144017361104488,
+      "teacher_loss": 0.0013847900554537773
+    },
+    {
+      "epoch": 0.2422145328719723,
+      "grad_norm": 1.71875,
+      "kd_loss": 0.019871558994054794,
+      "learning_rate": 6.644851533071556e-07,
+      "loss": 0.0359,
+      "step": 840,
+      "student_loss": 0.001529853092506528,
+      "teacher_loss": 0.0001909300044644624
+    },
+    {
+      "epoch": 0.2436562860438293,
+      "grad_norm": 1.0234375,
+      "kd_loss": 0.011251869611442089,
+      "learning_rate": 6.24722429156251e-07,
+      "loss": 0.0532,
+      "step": 845,
+      "student_loss": 0.0005619142320938408,
+      "teacher_loss": 0.0004758336581289768
+    },
+    {
+      "epoch": 0.24509803921568626,
+      "grad_norm": 2.390625,
+      "kd_loss": 0.02860349230468273,
+      "learning_rate": 5.861070457192081e-07,
+      "loss": 0.0371,
+      "step": 850,
+      "student_loss": 0.012859327718615532,
+      "teacher_loss": 0.0003160137275699526
+    },
+    {
+      "epoch": 0.24653979238754326,
+      "grad_norm": 1.015625,
+      "kd_loss": 0.016554828733205795,
+      "learning_rate": 5.486491292110796e-07,
+      "loss": 0.0368,
+      "step": 855,
+      "student_loss": 0.0005889005260542035,
+      "teacher_loss": 0.0003898893191944808
+    },
+    {
+      "epoch": 0.24798154555940022,
+      "grad_norm": 0.78125,
+      "kd_loss": 0.012213003821671009,
+      "learning_rate": 5.123585023212785e-07,
+      "loss": 0.0417,
+      "step": 860,
+      "student_loss": 0.0005682500777766109,
+      "teacher_loss": 0.00047416481538675725
+    },
+    {
+      "epoch": 0.2494232987312572,
+      "grad_norm": 1.21875,
+      "kd_loss": 0.01672137714922428,
+      "learning_rate": 4.772446816377408e-07,
+      "loss": 0.037,
+      "step": 865,
+      "student_loss": 0.0010720123536884785,
+      "teacher_loss": 0.0008305139490403235
+    },
+    {
+      "epoch": 0.2508650519031142,
+      "grad_norm": 1.046875,
+      "kd_loss": 0.018183542415499687,
+      "learning_rate": 4.4331687515137614e-07,
+      "loss": 0.0354,
+      "step": 870,
+      "student_loss": 0.001711298362351954,
+      "teacher_loss": 0.0007006946834735572
+    },
+    {
+      "epoch": 0.25230680507497116,
+      "grad_norm": 1.53125,
+      "kd_loss": 0.015019524842500687,
+      "learning_rate": 4.1058397984142405e-07,
+      "loss": 0.0375,
+      "step": 875,
+      "student_loss": 0.00019167628488503397,
+      "teacher_loss": 0.0002023013075813651
+    },
+    {
+      "epoch": 0.2537485582468281,
+      "grad_norm": 1.0859375,
+      "kd_loss": 0.016358323395252228,
+      "learning_rate": 3.790545793423761e-07,
+      "loss": 0.039,
+      "step": 880,
+      "student_loss": 0.00405404157936573,
+      "teacher_loss": 0.0018468407215550542
+    },
+    {
+      "epoch": 0.25519031141868515,
+      "grad_norm": 1.28125,
+      "kd_loss": 0.04253898561000824,
+      "learning_rate": 3.4873694169306915e-07,
+      "loss": 0.0316,
+      "step": 885,
+      "student_loss": 0.011344845406711102,
+      "teacher_loss": 0.044258587062358856
+    },
+    {
+      "epoch": 0.2566320645905421,
+      "grad_norm": 1.3359375,
+      "kd_loss": 0.009111128747463226,
+      "learning_rate": 3.196390171685343e-07,
+      "loss": 0.0369,
+      "step": 890,
+      "student_loss": 0.0003722853143699467,
+      "teacher_loss": 0.00034851342206820846
+    },
+    {
+      "epoch": 0.25807381776239907,
+      "grad_norm": 1.4921875,
+      "kd_loss": 0.02147591859102249,
+      "learning_rate": 2.917684361951728e-07,
+      "loss": 0.0352,
+      "step": 895,
+      "student_loss": 0.005593026988208294,
+      "teacher_loss": 0.0024380958639085293
+    },
+    {
+      "epoch": 0.25951557093425603,
+      "grad_norm": 1.296875,
+      "kd_loss": 0.017156513407826424,
+      "learning_rate": 2.65132507349814e-07,
+      "loss": 0.0382,
+      "step": 900,
+      "student_loss": 0.030825650319457054,
+      "teacher_loss": 0.022559169679880142
+    },
+    {
+      "epoch": 0.26095732410611305,
+      "grad_norm": 1.296875,
+      "kd_loss": 0.014595987275242805,
+      "learning_rate": 2.397382154431621e-07,
+      "loss": 0.0329,
+      "step": 905,
+      "student_loss": 0.0070388843305408955,
+      "teacher_loss": 0.0033032468054443598
+    },
+    {
+      "epoch": 0.26239907727797,
+      "grad_norm": 1.1796875,
+      "kd_loss": 0.00915343314409256,
+      "learning_rate": 2.1559221968815547e-07,
+      "loss": 0.0309,
+      "step": 910,
+      "student_loss": 0.0003465732734184712,
+      "teacher_loss": 0.0003652082523331046
+    },
+    {
+      "epoch": 0.263840830449827,
+      "grad_norm": 1.4765625,
+      "kd_loss": 0.047718290239572525,
+      "learning_rate": 1.9270085195370048e-07,
+      "loss": 0.0354,
+      "step": 915,
+      "student_loss": 0.07753528654575348,
+      "teacher_loss": 0.00128907710313797
+    },
+    {
+      "epoch": 0.26528258362168394,
+      "grad_norm": 1.1171875,
+      "kd_loss": 0.013440879993140697,
+      "learning_rate": 1.7107011510424766e-07,
+      "loss": 0.0341,
+      "step": 920,
+      "student_loss": 0.013975732028484344,
+      "teacher_loss": 0.011724431999027729
+    },
+    {
+      "epoch": 0.26672433679354096,
+      "grad_norm": 0.96484375,
+      "kd_loss": 0.010464920662343502,
+      "learning_rate": 1.5070568142564912e-07,
+      "loss": 0.0324,
+      "step": 925,
+      "student_loss": 0.0003131957200821489,
+      "teacher_loss": 0.00029044810798950493
+    },
+    {
+      "epoch": 0.2681660899653979,
+      "grad_norm": 0.98828125,
+      "kd_loss": 0.016116317361593246,
+      "learning_rate": 1.3161289113769405e-07,
+      "loss": 0.0326,
+      "step": 930,
+      "student_loss": 0.013056068681180477,
+      "teacher_loss": 0.0016408703522756696
+    },
+    {
+      "epoch": 0.2696078431372549,
+      "grad_norm": 0.94921875,
+      "kd_loss": 0.011886276304721832,
+      "learning_rate": 1.1379675099373489e-07,
+      "loss": 0.0334,
+      "step": 935,
+      "student_loss": 0.002202346222475171,
+      "teacher_loss": 0.0023580535780638456
+    },
+    {
+      "epoch": 0.2710495963091119,
+      "grad_norm": 1.0390625,
+      "kd_loss": 0.02240722067654133,
+      "learning_rate": 9.726193296774767e-08,
+      "loss": 0.0353,
+      "step": 940,
+      "student_loss": 0.008520473726093769,
+      "teacher_loss": 0.000717982358764857
+    },
+    {
+      "epoch": 0.27249134948096887,
+      "grad_norm": 0.98046875,
+      "kd_loss": 0.010714667849242687,
+      "learning_rate": 8.201277302919086e-08,
+      "loss": 0.0384,
+      "step": 945,
+      "student_loss": 0.003037899499759078,
+      "teacher_loss": 0.001546806888654828
+    },
+    {
+      "epoch": 0.27393310265282583,
+      "grad_norm": 0.91796875,
+      "kd_loss": 0.01626349613070488,
+      "learning_rate": 6.805327000596995e-08,
+      "loss": 0.0319,
+      "step": 950,
+      "student_loss": 0.00029273482505232096,
+      "teacher_loss": 0.00015759514644742012
+    },
+    {
+      "epoch": 0.2753748558246828,
+      "grad_norm": 1.0625,
+      "kd_loss": 0.016484661027789116,
+      "learning_rate": 5.538708453581787e-08,
+      "loss": 0.0353,
+      "step": 955,
+      "student_loss": 0.0004839501343667507,
+      "teacher_loss": 0.00021457124967128038
+    },
+    {
+      "epoch": 0.2768166089965398,
+      "grad_norm": 1.609375,
+      "kd_loss": 0.016130708158016205,
+      "learning_rate": 4.40175381063529e-08,
+      "loss": 0.039,
+      "step": 960,
+      "student_loss": 0.0031732963398098946,
+      "teacher_loss": 0.0024704965762794018
+    },
+    {
+      "epoch": 0.2782583621683968,
+      "grad_norm": 1.1328125,
+      "kd_loss": 0.022074589505791664,
+      "learning_rate": 3.394761218407705e-08,
+      "loss": 0.0341,
+      "step": 965,
+      "student_loss": 0.010913808830082417,
+      "teacher_loss": 0.006757721304893494
+    },
+    {
+      "epoch": 0.27970011534025374,
+      "grad_norm": 1.34375,
+      "kd_loss": 0.01725686714053154,
+      "learning_rate": 2.5179947432540376e-08,
+      "loss": 0.035,
+      "step": 970,
+      "student_loss": 0.00032446443219669163,
+      "teacher_loss": 0.00020874734036624432
+    },
+    {
+      "epoch": 0.2811418685121107,
+      "grad_norm": 1.0,
+      "kd_loss": 0.012324236333370209,
+      "learning_rate": 1.7716843019867646e-08,
+      "loss": 0.034,
+      "step": 975,
+      "student_loss": 0.02250129170715809,
+      "teacher_loss": 0.0008003146504051983
+    },
+    {
+      "epoch": 0.2825836216839677,
+      "grad_norm": 0.97265625,
+      "kd_loss": 0.01817537285387516,
+      "learning_rate": 1.156025601584676e-08,
+      "loss": 0.0372,
+      "step": 980,
+      "student_loss": 0.0004171262844465673,
+      "teacher_loss": 0.00023037723440211266
+    },
+    {
+      "epoch": 0.2840253748558247,
+      "grad_norm": 1.203125,
+      "kd_loss": 0.017179273068904877,
+      "learning_rate": 6.711800878718144e-09,
+      "loss": 0.0365,
+      "step": 985,
+      "student_loss": 0.000331983930664137,
+      "teacher_loss": 0.000896628072950989
+    },
+    {
+      "epoch": 0.28546712802768165,
+      "grad_norm": 1.3671875,
+      "kd_loss": 0.01191702764481306,
+      "learning_rate": 3.1727490318111953e-09,
+      "loss": 0.0315,
+      "step": 990,
+      "student_loss": 0.0003260337980464101,
+      "teacher_loss": 0.00025129789719358087
+    },
+    {
+      "epoch": 0.2869088811995386,
+      "grad_norm": 1.4609375,
+      "kd_loss": 0.027709918096661568,
+      "learning_rate": 9.440285301370865e-10,
+      "loss": 0.0405,
+      "step": 995,
+      "student_loss": 0.00899884570389986,
+      "teacher_loss": 0.0006192626315169036
+    },
+    {
+      "epoch": 0.28835063437139563,
+      "grad_norm": 0.77734375,
+      "kd_loss": 0.020871583372354507,
+      "learning_rate": 2.622381702066523e-11,
+      "loss": 0.0348,
+      "step": 1000,
+      "student_loss": 0.008410735987126827,
+      "teacher_loss": 0.0003241391386836767
+    },
+    {
+      "epoch": 0.28835063437139563,
+      "kd_loss": 0.020871583372354507,
+      "step": 1000,
+      "student_loss": 0.008410735987126827,
+      "teacher_loss": 0.0003241391386836767,
+      "total_flos": 0.0,
+      "train_loss": 0.05713042087852955,
+      "train_runtime": 32582.8193,
+      "train_samples_per_second": 0.491,
+      "train_steps_per_second": 0.031
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 1000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 200,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": false,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoints/codi1.5b_a1.0_b1.0_g1.0_ls2/checkpoint-200/added_tokens.json

@@ -0,0 +1,35 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|action_sep|>": 151670,
+  "<|arg_sep|>": 151671,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|call_sep|>": 151666,
+  "<|end_of_text|>": 151673,
+  "<|endoftext|>": 151643,
+  "<|exception_sep|>": 151669,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|frame_sep|>": 151672,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|latent_end|>": 151675,
+  "<|latent_start|>": 151674,
+  "<|line_sep|>": 151667,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|return_sep|>": 151668,
+  "<|trace_context_start|>": 151665,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

checkpoints/codi1.5b_a1.0_b1.0_g1.0_ls2/checkpoint-200/chat_template.jinja

@@ -0,0 +1,54 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
+    {%- endif %}
+    {{- "\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>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\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" }}
+{%- else %}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
+    {%- else %}
+        {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role }}
+        {%- if message.content %}
+            {{- '\n' + message.content }}
+        {%- endif %}
+        {%- for tool_call in message.tool_calls %}
+            {%- if tool_call.function is defined %}
+                {%- set tool_call = tool_call.function %}
+            {%- endif %}
+            {{- '\n<tool_call>\n{"name": "' }}
+            {{- tool_call.name }}
+            {{- '", "arguments": ' }}
+            {{- tool_call.arguments | tojson }}
+            {{- '}\n</tool_call>' }}
+        {%- endfor %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}

checkpoints/codi1.5b_a1.0_b1.0_g1.0_ls2/checkpoint-200/config.json

@@ -0,0 +1,58 @@
+{
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "dtype": "bfloat16",
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 1536,
+  "initializer_range": 0.02,
+  "intermediate_size": 8960,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 2,
+  "pad_token_id": 151643,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "transformers_version": "4.57.6",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151676
+}

checkpoints/codi1.5b_a1.0_b1.0_g1.0_ls2/checkpoint-200/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12535971b61e18cd0094b867d83a111ff4684c13edee216d1be7223d0d041c5f
+size 3096275515

checkpoints/codi1.5b_a1.0_b1.0_g1.0_ls2/checkpoint-200/special_tokens_map.json

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

checkpoints/codi1.5b_a1.0_b1.0_g1.0_ls2/checkpoint-200/thought_projector.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:454d5f5d4f97032f2c4ef6c292c2418e4799c6b9d0eedba3e52c675aa7ef61ad
+size 9445953

checkpoints/codi1.5b_a1.0_b1.0_g1.0_ls2/checkpoint-200/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83a790d654474f5dfe225f889afd0210313eb1083f942671f2c4b8e95a1c922b
+size 11424004

checkpoints/codi1.5b_a1.0_b1.0_g1.0_ls2/checkpoint-200/tokenizer_config.json

@@ -0,0 +1,295 @@
+{
+  "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
+    },
+    "151665": {
+      "content": "<|trace_context_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151666": {
+      "content": "<|call_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151667": {
+      "content": "<|line_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151668": {
+      "content": "<|return_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151669": {
+      "content": "<|exception_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151670": {
+      "content": "<|action_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151671": {
+      "content": "<|arg_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151672": {
+      "content": "<|frame_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151673": {
+      "content": "<|end_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151674": {
+      "content": "<|latent_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151675": {
+      "content": "<|latent_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "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,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoints/codi1.5b_a1.0_b1.0_g1.0_ls2/checkpoint-200/trainer_state.json

@@ -0,0 +1,434 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.05767012687427912,
+  "eval_steps": 500,
+  "global_step": 200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0014417531718569781,
+      "grad_norm": 52992.0,
+      "kd_loss": 0.3193017542362213,
+      "learning_rate": 1.3333333333333334e-06,
+      "loss": 0.473,
+      "step": 5,
+      "student_loss": 0.15727384388446808,
+      "teacher_loss": 0.0004137983196415007
+    },
+    {
+      "epoch": 0.0028835063437139563,
+      "grad_norm": 16121856.0,
+      "kd_loss": 0.3087984025478363,
+      "learning_rate": 3e-06,
+      "loss": 0.466,
+      "step": 10,
+      "student_loss": 0.2608874440193176,
+      "teacher_loss": 0.0007329508662223816
+    },
+    {
+      "epoch": 0.004325259515570935,
+      "grad_norm": 2240.0,
+      "kd_loss": 0.25935155153274536,
+      "learning_rate": 4.666666666666667e-06,
+      "loss": 0.4585,
+      "step": 15,
+      "student_loss": 0.1052168533205986,
+      "teacher_loss": 0.000609480426646769
+    },
+    {
+      "epoch": 0.0057670126874279125,
+      "grad_norm": 4194304.0,
+      "kd_loss": 0.25011566281318665,
+      "learning_rate": 6.333333333333333e-06,
+      "loss": 0.4707,
+      "step": 20,
+      "student_loss": 0.15271778404712677,
+      "teacher_loss": 0.0002972046786453575
+    },
+    {
+      "epoch": 0.00720876585928489,
+      "grad_norm": 41680896.0,
+      "kd_loss": 0.2633170485496521,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 0.4368,
+      "step": 25,
+      "student_loss": 0.09109362959861755,
+      "teacher_loss": 0.0009600125486031175
+    },
+    {
+      "epoch": 0.00865051903114187,
+      "grad_norm": 512.0,
+      "kd_loss": 0.2533612847328186,
+      "learning_rate": 9.666666666666667e-06,
+      "loss": 0.4187,
+      "step": 30,
+      "student_loss": 0.22675999999046326,
+      "teacher_loss": 0.00035076512722298503
+    },
+    {
+      "epoch": 0.010092272202998846,
+      "grad_norm": 48.75,
+      "kd_loss": 0.2179471105337143,
+      "learning_rate": 9.99958042442916e-06,
+      "loss": 0.3713,
+      "step": 35,
+      "student_loss": 0.09486500918865204,
+      "teacher_loss": 0.00026503618573769927
+    },
+    {
+      "epoch": 0.011534025374855825,
+      "grad_norm": 10.0,
+      "kd_loss": 0.17874062061309814,
+      "learning_rate": 9.997876019358083e-06,
+      "loss": 0.2647,
+      "step": 40,
+      "student_loss": 0.07879351079463959,
+      "teacher_loss": 0.05543303117156029
+    },
+    {
+      "epoch": 0.012975778546712802,
+      "grad_norm": 4.9375,
+      "kd_loss": 0.19365739822387695,
+      "learning_rate": 9.99486100792044e-06,
+      "loss": 0.1686,
+      "step": 45,
+      "student_loss": 0.07774724811315536,
+      "teacher_loss": 0.0008653572876937687
+    },
+    {
+      "epoch": 0.01441753171856978,
+      "grad_norm": 3.359375,
+      "kd_loss": 0.06108914315700531,
+      "learning_rate": 9.990536180750724e-06,
+      "loss": 0.1396,
+      "step": 50,
+      "student_loss": 0.008677379228174686,
+      "teacher_loss": 0.005272893700748682
+    },
+    {
+      "epoch": 0.015859284890426758,
+      "grad_norm": 3.71875,
+      "kd_loss": 0.04330182075500488,
+      "learning_rate": 9.984902671959911e-06,
+      "loss": 0.1065,
+      "step": 55,
+      "student_loss": 0.001041711075231433,
+      "teacher_loss": 0.0005072589847259223
+    },
+    {
+      "epoch": 0.01730103806228374,
+      "grad_norm": 4.125,
+      "kd_loss": 0.03823668882250786,
+      "learning_rate": 9.97796195883804e-06,
+      "loss": 0.0862,
+      "step": 60,
+      "student_loss": 0.0209807138890028,
+      "teacher_loss": 0.0038409351836889982
+    },
+    {
+      "epoch": 0.018742791234140715,
+      "grad_norm": 10.1875,
+      "kd_loss": 0.03922531381249428,
+      "learning_rate": 9.969715861466839e-06,
+      "loss": 0.0844,
+      "step": 65,
+      "student_loss": 0.04678678512573242,
+      "teacher_loss": 0.05432586744427681
+    },
+    {
+      "epoch": 0.020184544405997693,
+      "grad_norm": 2.03125,
+      "kd_loss": 0.0549621656537056,
+      "learning_rate": 9.96016654224243e-06,
+      "loss": 0.0797,
+      "step": 70,
+      "student_loss": 0.016930116340517998,
+      "teacher_loss": 0.0029678302817046642
+    },
+    {
+      "epoch": 0.02162629757785467,
+      "grad_norm": 2.5625,
+      "kd_loss": 0.023080041632056236,
+      "learning_rate": 9.94931650530827e-06,
+      "loss": 0.0756,
+      "step": 75,
+      "student_loss": 0.002210108330473304,
+      "teacher_loss": 0.0013834249693900347
+    },
+    {
+      "epoch": 0.02306805074971165,
+      "grad_norm": 2.296875,
+      "kd_loss": 0.025744518265128136,
+      "learning_rate": 9.93716859589851e-06,
+      "loss": 0.0644,
+      "step": 80,
+      "student_loss": 0.0015430074417963624,
+      "teacher_loss": 0.000761081581003964
+    },
+    {
+      "epoch": 0.024509803921568627,
+      "grad_norm": 3.125,
+      "kd_loss": 0.023152953013777733,
+      "learning_rate": 9.923725999591846e-06,
+      "loss": 0.0609,
+      "step": 85,
+      "student_loss": 0.0187687948346138,
+      "teacher_loss": 0.011518553830683231
+    },
+    {
+      "epoch": 0.025951557093425604,
+      "grad_norm": 1.8359375,
+      "kd_loss": 0.06841632723808289,
+      "learning_rate": 9.908992241476189e-06,
+      "loss": 0.0622,
+      "step": 90,
+      "student_loss": 0.05537872016429901,
+      "teacher_loss": 0.011890009045600891
+    },
+    {
+      "epoch": 0.027393310265282585,
+      "grad_norm": 4.21875,
+      "kd_loss": 0.041227906942367554,
+      "learning_rate": 9.892971185224244e-06,
+      "loss": 0.0626,
+      "step": 95,
+      "student_loss": 0.009465624578297138,
+      "teacher_loss": 0.005057212430983782
+    },
+    {
+      "epoch": 0.02883506343713956,
+      "grad_norm": 1.8359375,
+      "kd_loss": 0.021006152033805847,
+      "learning_rate": 9.875667032080354e-06,
+      "loss": 0.0538,
+      "step": 100,
+      "student_loss": 0.0007415671134367585,
+      "teacher_loss": 0.0005348982522264123
+    },
+    {
+      "epoch": 0.03027681660899654,
+      "grad_norm": 1.6328125,
+      "kd_loss": 0.035115621984004974,
+      "learning_rate": 9.857084319758772e-06,
+      "loss": 0.0541,
+      "step": 105,
+      "student_loss": 0.005187581293284893,
+      "teacher_loss": 0.00030648778192698956
+    },
+    {
+      "epoch": 0.031718569780853516,
+      "grad_norm": 2.953125,
+      "kd_loss": 0.03037514165043831,
+      "learning_rate": 9.837227921253747e-06,
+      "loss": 0.06,
+      "step": 110,
+      "student_loss": 0.031953420490026474,
+      "teacher_loss": 0.0175339188426733
+    },
+    {
+      "epoch": 0.03316032295271049,
+      "grad_norm": 1.484375,
+      "kd_loss": 0.023421702906489372,
+      "learning_rate": 9.816103043561648e-06,
+      "loss": 0.0563,
+      "step": 115,
+      "student_loss": 0.0006847245967946947,
+      "teacher_loss": 0.0003864571626763791
+    },
+    {
+      "epoch": 0.03460207612456748,
+      "grad_norm": 1.8203125,
+      "kd_loss": 0.018447211012244225,
+      "learning_rate": 9.79371522631553e-06,
+      "loss": 0.0478,
+      "step": 120,
+      "student_loss": 0.0015498347347602248,
+      "teacher_loss": 0.0010675351368263364
+    },
+    {
+      "epoch": 0.036043829296424454,
+      "grad_norm": 1.96875,
+      "kd_loss": 0.05630031228065491,
+      "learning_rate": 9.770070340332457e-06,
+      "loss": 0.0527,
+      "step": 125,
+      "student_loss": 0.04758762940764427,
+      "teacher_loss": 0.0004967509885318577
+    },
+    {
+      "epoch": 0.03748558246828143,
+      "grad_norm": 1.859375,
+      "kd_loss": 0.018152693286538124,
+      "learning_rate": 9.745174586073982e-06,
+      "loss": 0.0518,
+      "step": 130,
+      "student_loss": 0.0008988101035356522,
+      "teacher_loss": 0.0007278143893927336
+    },
+    {
+      "epoch": 0.03892733564013841,
+      "grad_norm": 1.6640625,
+      "kd_loss": 0.030904680490493774,
+      "learning_rate": 9.719034492020183e-06,
+      "loss": 0.0526,
+      "step": 135,
+      "student_loss": 0.0127235297113657,
+      "teacher_loss": 0.0011665972415357828
+    },
+    {
+      "epoch": 0.040369088811995385,
+      "grad_norm": 1.1640625,
+      "kd_loss": 0.01759810373187065,
+      "learning_rate": 9.691656912957686e-06,
+      "loss": 0.0494,
+      "step": 140,
+      "student_loss": 0.0008300879271700978,
+      "teacher_loss": 0.0005129938363097608
+    },
+    {
+      "epoch": 0.04181084198385236,
+      "grad_norm": 1.0234375,
+      "kd_loss": 0.061179179698228836,
+      "learning_rate": 9.663049028182112e-06,
+      "loss": 0.0457,
+      "step": 145,
+      "student_loss": 0.04404008761048317,
+      "teacher_loss": 0.009324059821665287
+    },
+    {
+      "epoch": 0.04325259515570934,
+      "grad_norm": 1.15625,
+      "kd_loss": 0.01291500125080347,
+      "learning_rate": 9.633218339615433e-06,
+      "loss": 0.0455,
+      "step": 150,
+      "student_loss": 0.0008404091349802911,
+      "teacher_loss": 0.0008450732566416264
+    },
+    {
+      "epoch": 0.04469434832756632,
+      "grad_norm": 1.4921875,
+      "kd_loss": 0.017479021102190018,
+      "learning_rate": 9.602172669838721e-06,
+      "loss": 0.0575,
+      "step": 155,
+      "student_loss": 0.0009151780977845192,
+      "teacher_loss": 0.0006974826683290303
+    },
+    {
+      "epoch": 0.0461361014994233,
+      "grad_norm": 1.671875,
+      "kd_loss": 0.022708255797624588,
+      "learning_rate": 9.569920160040815e-06,
+      "loss": 0.0503,
+      "step": 160,
+      "student_loss": 0.07660368084907532,
+      "teacher_loss": 0.04039459675550461
+    },
+    {
+      "epoch": 0.04757785467128028,
+      "grad_norm": 1.0703125,
+      "kd_loss": 0.027437202632427216,
+      "learning_rate": 9.536469267883432e-06,
+      "loss": 0.0451,
+      "step": 165,
+      "student_loss": 0.0005943832220509648,
+      "teacher_loss": 0.005336699075996876
+    },
+    {
+      "epoch": 0.049019607843137254,
+      "grad_norm": 1.71875,
+      "kd_loss": 0.014546042308211327,
+      "learning_rate": 9.501828765283295e-06,
+      "loss": 0.0459,
+      "step": 170,
+      "student_loss": 0.0006958618760108948,
+      "teacher_loss": 0.0005218263831920922
+    },
+    {
+      "epoch": 0.05046136101499423,
+      "grad_norm": 1.4453125,
+      "kd_loss": 0.02377346158027649,
+      "learning_rate": 9.466007736111846e-06,
+      "loss": 0.0465,
+      "step": 175,
+      "student_loss": 0.003214897122234106,
+      "teacher_loss": 0.0006713470793329179
+    },
+    {
+      "epoch": 0.05190311418685121,
+      "grad_norm": 1.296875,
+      "kd_loss": 0.02517828531563282,
+      "learning_rate": 9.429015573813163e-06,
+      "loss": 0.0454,
+      "step": 180,
+      "student_loss": 0.0007039233460091054,
+      "teacher_loss": 0.0003641469811554998
+    },
+    {
+      "epoch": 0.05334486735870819,
+      "grad_norm": 1.25,
+      "kd_loss": 0.029188504442572594,
+      "learning_rate": 9.390861978940687e-06,
+      "loss": 0.0473,
+      "step": 185,
+      "student_loss": 0.04238048940896988,
+      "teacher_loss": 0.00033479384728707373
+    },
+    {
+      "epoch": 0.05478662053056517,
+      "grad_norm": 1.484375,
+      "kd_loss": 0.03749082237482071,
+      "learning_rate": 9.351556956613423e-06,
+      "loss": 0.0436,
+      "step": 190,
+      "student_loss": 0.010270334780216217,
+      "teacher_loss": 0.0024021982681006193
+    },
+    {
+      "epoch": 0.056228373702422146,
+      "grad_norm": 2.0,
+      "kd_loss": 0.030336912721395493,
+      "learning_rate": 9.31111081389227e-06,
+      "loss": 0.0442,
+      "step": 195,
+      "student_loss": 0.010534510016441345,
+      "teacher_loss": 0.0003890562220476568
+    },
+    {
+      "epoch": 0.05767012687427912,
+      "grad_norm": 0.921875,
+      "kd_loss": 0.026554003357887268,
+      "learning_rate": 9.269534157077177e-06,
+      "loss": 0.0497,
+      "step": 200,
+      "student_loss": 0.0034760867711156607,
+      "teacher_loss": 0.00022423896007239819
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 1000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 200,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoints/codi1.5b_a1.0_b1.0_g1.0_ls2/checkpoint-400/added_tokens.json

@@ -0,0 +1,35 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|action_sep|>": 151670,
+  "<|arg_sep|>": 151671,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|call_sep|>": 151666,
+  "<|end_of_text|>": 151673,
+  "<|endoftext|>": 151643,
+  "<|exception_sep|>": 151669,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|frame_sep|>": 151672,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|latent_end|>": 151675,
+  "<|latent_start|>": 151674,
+  "<|line_sep|>": 151667,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|return_sep|>": 151668,
+  "<|trace_context_start|>": 151665,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

checkpoints/codi1.5b_a1.0_b1.0_g1.0_ls2/checkpoint-400/chat_template.jinja

@@ -0,0 +1,54 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
+    {%- endif %}
+    {{- "\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>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\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" }}
+{%- else %}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
+    {%- else %}
+        {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role }}
+        {%- if message.content %}
+            {{- '\n' + message.content }}
+        {%- endif %}
+        {%- for tool_call in message.tool_calls %}
+            {%- if tool_call.function is defined %}
+                {%- set tool_call = tool_call.function %}
+            {%- endif %}
+            {{- '\n<tool_call>\n{"name": "' }}
+            {{- tool_call.name }}
+            {{- '", "arguments": ' }}
+            {{- tool_call.arguments | tojson }}
+            {{- '}\n</tool_call>' }}
+        {%- endfor %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}

checkpoints/codi1.5b_a1.0_b1.0_g1.0_ls2/checkpoint-400/config.json

@@ -0,0 +1,58 @@
+{
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "dtype": "bfloat16",
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 1536,
+  "initializer_range": 0.02,
+  "intermediate_size": 8960,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 2,
+  "pad_token_id": 151643,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "transformers_version": "4.57.6",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151676
+}

checkpoints/codi1.5b_a1.0_b1.0_g1.0_ls2/checkpoint-400/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99416fef5a180a223d39281c8652c677e98b3f665130cbcf397aa051ef9253a2
+size 3096275515

checkpoints/codi1.5b_a1.0_b1.0_g1.0_ls2/checkpoint-400/special_tokens_map.json

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

checkpoints/codi1.5b_a1.0_b1.0_g1.0_ls2/checkpoint-400/thought_projector.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d96e186b0d1d947b9da71c4baff93cdf3c8f2746fae25062cf9ad1925b99b38
+size 9445953

checkpoints/codi1.5b_a1.0_b1.0_g1.0_ls2/checkpoint-400/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83a790d654474f5dfe225f889afd0210313eb1083f942671f2c4b8e95a1c922b
+size 11424004

checkpoints/codi1.5b_a1.0_b1.0_g1.0_ls2/checkpoint-400/tokenizer_config.json

@@ -0,0 +1,295 @@
+{
+  "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
+    },
+    "151665": {
+      "content": "<|trace_context_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151666": {
+      "content": "<|call_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151667": {
+      "content": "<|line_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151668": {
+      "content": "<|return_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151669": {
+      "content": "<|exception_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151670": {
+      "content": "<|action_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151671": {
+      "content": "<|arg_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151672": {
+      "content": "<|frame_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151673": {
+      "content": "<|end_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151674": {
+      "content": "<|latent_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151675": {
+      "content": "<|latent_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "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,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoints/codi1.5b_a1.0_b1.0_g1.0_ls2/checkpoint-400/trainer_state.json

@@ -0,0 +1,834 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.11534025374855825,
+  "eval_steps": 500,
+  "global_step": 400,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0014417531718569781,
+      "grad_norm": 52992.0,
+      "kd_loss": 0.3193017542362213,
+      "learning_rate": 1.3333333333333334e-06,
+      "loss": 0.473,
+      "step": 5,
+      "student_loss": 0.15727384388446808,
+      "teacher_loss": 0.0004137983196415007
+    },
+    {
+      "epoch": 0.0028835063437139563,
+      "grad_norm": 16121856.0,
+      "kd_loss": 0.3087984025478363,
+      "learning_rate": 3e-06,
+      "loss": 0.466,
+      "step": 10,
+      "student_loss": 0.2608874440193176,
+      "teacher_loss": 0.0007329508662223816
+    },
+    {
+      "epoch": 0.004325259515570935,
+      "grad_norm": 2240.0,
+      "kd_loss": 0.25935155153274536,
+      "learning_rate": 4.666666666666667e-06,
+      "loss": 0.4585,
+      "step": 15,
+      "student_loss": 0.1052168533205986,
+      "teacher_loss": 0.000609480426646769
+    },
+    {
+      "epoch": 0.0057670126874279125,
+      "grad_norm": 4194304.0,
+      "kd_loss": 0.25011566281318665,
+      "learning_rate": 6.333333333333333e-06,
+      "loss": 0.4707,
+      "step": 20,
+      "student_loss": 0.15271778404712677,
+      "teacher_loss": 0.0002972046786453575
+    },
+    {
+      "epoch": 0.00720876585928489,
+      "grad_norm": 41680896.0,
+      "kd_loss": 0.2633170485496521,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 0.4368,
+      "step": 25,
+      "student_loss": 0.09109362959861755,
+      "teacher_loss": 0.0009600125486031175
+    },
+    {
+      "epoch": 0.00865051903114187,
+      "grad_norm": 512.0,
+      "kd_loss": 0.2533612847328186,
+      "learning_rate": 9.666666666666667e-06,
+      "loss": 0.4187,
+      "step": 30,
+      "student_loss": 0.22675999999046326,
+      "teacher_loss": 0.00035076512722298503
+    },
+    {
+      "epoch": 0.010092272202998846,
+      "grad_norm": 48.75,
+      "kd_loss": 0.2179471105337143,
+      "learning_rate": 9.99958042442916e-06,
+      "loss": 0.3713,
+      "step": 35,
+      "student_loss": 0.09486500918865204,
+      "teacher_loss": 0.00026503618573769927
+    },
+    {
+      "epoch": 0.011534025374855825,
+      "grad_norm": 10.0,
+      "kd_loss": 0.17874062061309814,
+      "learning_rate": 9.997876019358083e-06,
+      "loss": 0.2647,
+      "step": 40,
+      "student_loss": 0.07879351079463959,
+      "teacher_loss": 0.05543303117156029
+    },
+    {
+      "epoch": 0.012975778546712802,
+      "grad_norm": 4.9375,
+      "kd_loss": 0.19365739822387695,
+      "learning_rate": 9.99486100792044e-06,
+      "loss": 0.1686,
+      "step": 45,
+      "student_loss": 0.07774724811315536,
+      "teacher_loss": 0.0008653572876937687
+    },
+    {
+      "epoch": 0.01441753171856978,
+      "grad_norm": 3.359375,
+      "kd_loss": 0.06108914315700531,
+      "learning_rate": 9.990536180750724e-06,
+      "loss": 0.1396,
+      "step": 50,
+      "student_loss": 0.008677379228174686,
+      "teacher_loss": 0.005272893700748682
+    },
+    {
+      "epoch": 0.015859284890426758,
+      "grad_norm": 3.71875,
+      "kd_loss": 0.04330182075500488,
+      "learning_rate": 9.984902671959911e-06,
+      "loss": 0.1065,
+      "step": 55,
+      "student_loss": 0.001041711075231433,
+      "teacher_loss": 0.0005072589847259223
+    },
+    {
+      "epoch": 0.01730103806228374,
+      "grad_norm": 4.125,
+      "kd_loss": 0.03823668882250786,
+      "learning_rate": 9.97796195883804e-06,
+      "loss": 0.0862,
+      "step": 60,
+      "student_loss": 0.0209807138890028,
+      "teacher_loss": 0.0038409351836889982
+    },
+    {
+      "epoch": 0.018742791234140715,
+      "grad_norm": 10.1875,
+      "kd_loss": 0.03922531381249428,
+      "learning_rate": 9.969715861466839e-06,
+      "loss": 0.0844,
+      "step": 65,
+      "student_loss": 0.04678678512573242,
+      "teacher_loss": 0.05432586744427681
+    },
+    {
+      "epoch": 0.020184544405997693,
+      "grad_norm": 2.03125,
+      "kd_loss": 0.0549621656537056,
+      "learning_rate": 9.96016654224243e-06,
+      "loss": 0.0797,
+      "step": 70,
+      "student_loss": 0.016930116340517998,
+      "teacher_loss": 0.0029678302817046642
+    },
+    {
+      "epoch": 0.02162629757785467,
+      "grad_norm": 2.5625,
+      "kd_loss": 0.023080041632056236,
+      "learning_rate": 9.94931650530827e-06,
+      "loss": 0.0756,
+      "step": 75,
+      "student_loss": 0.002210108330473304,
+      "teacher_loss": 0.0013834249693900347
+    },
+    {
+      "epoch": 0.02306805074971165,
+      "grad_norm": 2.296875,
+      "kd_loss": 0.025744518265128136,
+      "learning_rate": 9.93716859589851e-06,
+      "loss": 0.0644,
+      "step": 80,
+      "student_loss": 0.0015430074417963624,
+      "teacher_loss": 0.000761081581003964
+    },
+    {
+      "epoch": 0.024509803921568627,
+      "grad_norm": 3.125,
+      "kd_loss": 0.023152953013777733,
+      "learning_rate": 9.923725999591846e-06,
+      "loss": 0.0609,
+      "step": 85,
+      "student_loss": 0.0187687948346138,
+      "teacher_loss": 0.011518553830683231
+    },
+    {
+      "epoch": 0.025951557093425604,
+      "grad_norm": 1.8359375,
+      "kd_loss": 0.06841632723808289,
+      "learning_rate": 9.908992241476189e-06,
+      "loss": 0.0622,
+      "step": 90,
+      "student_loss": 0.05537872016429901,
+      "teacher_loss": 0.011890009045600891
+    },
+    {
+      "epoch": 0.027393310265282585,
+      "grad_norm": 4.21875,
+      "kd_loss": 0.041227906942367554,
+      "learning_rate": 9.892971185224244e-06,
+      "loss": 0.0626,
+      "step": 95,
+      "student_loss": 0.009465624578297138,
+      "teacher_loss": 0.005057212430983782
+    },
+    {
+      "epoch": 0.02883506343713956,
+      "grad_norm": 1.8359375,
+      "kd_loss": 0.021006152033805847,
+      "learning_rate": 9.875667032080354e-06,
+      "loss": 0.0538,
+      "step": 100,
+      "student_loss": 0.0007415671134367585,
+      "teacher_loss": 0.0005348982522264123
+    },
+    {
+      "epoch": 0.03027681660899654,
+      "grad_norm": 1.6328125,
+      "kd_loss": 0.035115621984004974,
+      "learning_rate": 9.857084319758772e-06,
+      "loss": 0.0541,
+      "step": 105,
+      "student_loss": 0.005187581293284893,
+      "teacher_loss": 0.00030648778192698956
+    },
+    {
+      "epoch": 0.031718569780853516,
+      "grad_norm": 2.953125,
+      "kd_loss": 0.03037514165043831,
+      "learning_rate": 9.837227921253747e-06,
+      "loss": 0.06,
+      "step": 110,
+      "student_loss": 0.031953420490026474,
+      "teacher_loss": 0.0175339188426733
+    },
+    {
+      "epoch": 0.03316032295271049,
+      "grad_norm": 1.484375,
+      "kd_loss": 0.023421702906489372,
+      "learning_rate": 9.816103043561648e-06,
+      "loss": 0.0563,
+      "step": 115,
+      "student_loss": 0.0006847245967946947,
+      "teacher_loss": 0.0003864571626763791
+    },
+    {
+      "epoch": 0.03460207612456748,
+      "grad_norm": 1.8203125,
+      "kd_loss": 0.018447211012244225,
+      "learning_rate": 9.79371522631553e-06,
+      "loss": 0.0478,
+      "step": 120,
+      "student_loss": 0.0015498347347602248,
+      "teacher_loss": 0.0010675351368263364
+    },
+    {
+      "epoch": 0.036043829296424454,
+      "grad_norm": 1.96875,
+      "kd_loss": 0.05630031228065491,
+      "learning_rate": 9.770070340332457e-06,
+      "loss": 0.0527,
+      "step": 125,
+      "student_loss": 0.04758762940764427,
+      "teacher_loss": 0.0004967509885318577
+    },
+    {
+      "epoch": 0.03748558246828143,
+      "grad_norm": 1.859375,
+      "kd_loss": 0.018152693286538124,
+      "learning_rate": 9.745174586073982e-06,
+      "loss": 0.0518,
+      "step": 130,
+      "student_loss": 0.0008988101035356522,
+      "teacher_loss": 0.0007278143893927336
+    },
+    {
+      "epoch": 0.03892733564013841,
+      "grad_norm": 1.6640625,
+      "kd_loss": 0.030904680490493774,
+      "learning_rate": 9.719034492020183e-06,
+      "loss": 0.0526,
+      "step": 135,
+      "student_loss": 0.0127235297113657,
+      "teacher_loss": 0.0011665972415357828
+    },
+    {
+      "epoch": 0.040369088811995385,
+      "grad_norm": 1.1640625,
+      "kd_loss": 0.01759810373187065,
+      "learning_rate": 9.691656912957686e-06,
+      "loss": 0.0494,
+      "step": 140,
+      "student_loss": 0.0008300879271700978,
+      "teacher_loss": 0.0005129938363097608
+    },
+    {
+      "epoch": 0.04181084198385236,
+      "grad_norm": 1.0234375,
+      "kd_loss": 0.061179179698228836,
+      "learning_rate": 9.663049028182112e-06,
+      "loss": 0.0457,
+      "step": 145,
+      "student_loss": 0.04404008761048317,
+      "teacher_loss": 0.009324059821665287
+    },
+    {
+      "epoch": 0.04325259515570934,
+      "grad_norm": 1.15625,
+      "kd_loss": 0.01291500125080347,
+      "learning_rate": 9.633218339615433e-06,
+      "loss": 0.0455,
+      "step": 150,
+      "student_loss": 0.0008404091349802911,
+      "teacher_loss": 0.0008450732566416264
+    },
+    {
+      "epoch": 0.04469434832756632,
+      "grad_norm": 1.4921875,
+      "kd_loss": 0.017479021102190018,
+      "learning_rate": 9.602172669838721e-06,
+      "loss": 0.0575,
+      "step": 155,
+      "student_loss": 0.0009151780977845192,
+      "teacher_loss": 0.0006974826683290303
+    },
+    {
+      "epoch": 0.0461361014994233,
+      "grad_norm": 1.671875,
+      "kd_loss": 0.022708255797624588,
+      "learning_rate": 9.569920160040815e-06,
+      "loss": 0.0503,
+      "step": 160,
+      "student_loss": 0.07660368084907532,
+      "teacher_loss": 0.04039459675550461
+    },
+    {
+      "epoch": 0.04757785467128028,
+      "grad_norm": 1.0703125,
+      "kd_loss": 0.027437202632427216,
+      "learning_rate": 9.536469267883432e-06,
+      "loss": 0.0451,
+      "step": 165,
+      "student_loss": 0.0005943832220509648,
+      "teacher_loss": 0.005336699075996876
+    },
+    {
+      "epoch": 0.049019607843137254,
+      "grad_norm": 1.71875,
+      "kd_loss": 0.014546042308211327,
+      "learning_rate": 9.501828765283295e-06,
+      "loss": 0.0459,
+      "step": 170,
+      "student_loss": 0.0006958618760108948,
+      "teacher_loss": 0.0005218263831920922
+    },
+    {
+      "epoch": 0.05046136101499423,
+      "grad_norm": 1.4453125,
+      "kd_loss": 0.02377346158027649,
+      "learning_rate": 9.466007736111846e-06,
+      "loss": 0.0465,
+      "step": 175,
+      "student_loss": 0.003214897122234106,
+      "teacher_loss": 0.0006713470793329179
+    },
+    {
+      "epoch": 0.05190311418685121,
+      "grad_norm": 1.296875,
+      "kd_loss": 0.02517828531563282,
+      "learning_rate": 9.429015573813163e-06,
+      "loss": 0.0454,
+      "step": 180,
+      "student_loss": 0.0007039233460091054,
+      "teacher_loss": 0.0003641469811554998
+    },
+    {
+      "epoch": 0.05334486735870819,
+      "grad_norm": 1.25,
+      "kd_loss": 0.029188504442572594,
+      "learning_rate": 9.390861978940687e-06,
+      "loss": 0.0473,
+      "step": 185,
+      "student_loss": 0.04238048940896988,
+      "teacher_loss": 0.00033479384728707373
+    },
+    {
+      "epoch": 0.05478662053056517,
+      "grad_norm": 1.484375,
+      "kd_loss": 0.03749082237482071,
+      "learning_rate": 9.351556956613423e-06,
+      "loss": 0.0436,
+      "step": 190,
+      "student_loss": 0.010270334780216217,
+      "teacher_loss": 0.0024021982681006193
+    },
+    {
+      "epoch": 0.056228373702422146,
+      "grad_norm": 2.0,
+      "kd_loss": 0.030336912721395493,
+      "learning_rate": 9.31111081389227e-06,
+      "loss": 0.0442,
+      "step": 195,
+      "student_loss": 0.010534510016441345,
+      "teacher_loss": 0.0003890562220476568
+    },
+    {
+      "epoch": 0.05767012687427912,
+      "grad_norm": 0.921875,
+      "kd_loss": 0.026554003357887268,
+      "learning_rate": 9.269534157077177e-06,
+      "loss": 0.0497,
+      "step": 200,
+      "student_loss": 0.0034760867711156607,
+      "teacher_loss": 0.00022423896007239819
+    },
+    {
+      "epoch": 0.0591118800461361,
+      "grad_norm": 1.9140625,
+      "kd_loss": 0.023410219699144363,
+      "learning_rate": 9.226837888925813e-06,
+      "loss": 0.0471,
+      "step": 205,
+      "student_loss": 0.03611442819237709,
+      "teacher_loss": 0.027781842276453972
+    },
+    {
+      "epoch": 0.06055363321799308,
+      "grad_norm": 1.7578125,
+      "kd_loss": 0.022867349907755852,
+      "learning_rate": 9.183033205794525e-06,
+      "loss": 0.0428,
+      "step": 210,
+      "student_loss": 0.001971556106582284,
+      "teacher_loss": 0.0009746765717864037
+    },
+    {
+      "epoch": 0.061995386389850055,
+      "grad_norm": 1.0234375,
+      "kd_loss": 0.028235338628292084,
+      "learning_rate": 9.13813159470227e-06,
+      "loss": 0.0449,
+      "step": 215,
+      "student_loss": 0.0009558866149745882,
+      "teacher_loss": 0.0004049334966111928
+    },
+    {
+      "epoch": 0.06343713956170703,
+      "grad_norm": 1.4296875,
+      "kd_loss": 0.03134317323565483,
+      "learning_rate": 9.092144830318357e-06,
+      "loss": 0.0438,
+      "step": 220,
+      "student_loss": 0.048195730894804,
+      "teacher_loss": 0.009161758236587048
+    },
+    {
+      "epoch": 0.06487889273356401,
+      "grad_norm": 1.1328125,
+      "kd_loss": 0.014049015007913113,
+      "learning_rate": 9.045084971874738e-06,
+      "loss": 0.0487,
+      "step": 225,
+      "student_loss": 0.05373133346438408,
+      "teacher_loss": 0.0009734037448652089
+    },
+    {
+      "epoch": 0.06632064590542099,
+      "grad_norm": 1.7265625,
+      "kd_loss": 0.021539395675063133,
+      "learning_rate": 8.99696436000368e-06,
+      "loss": 0.0384,
+      "step": 230,
+      "student_loss": 0.0008717047749087214,
+      "teacher_loss": 0.0028650674503296614
+    },
+    {
+      "epoch": 0.06776239907727798,
+      "grad_norm": 1.0390625,
+      "kd_loss": 0.045927971601486206,
+      "learning_rate": 8.947795613501658e-06,
+      "loss": 0.0397,
+      "step": 235,
+      "student_loss": 0.012143217958509922,
+      "teacher_loss": 0.0006723064580000937
+    },
+    {
+      "epoch": 0.06920415224913495,
+      "grad_norm": 0.78125,
+      "kd_loss": 0.01626853086054325,
+      "learning_rate": 8.897591626020284e-06,
+      "loss": 0.0425,
+      "step": 240,
+      "student_loss": 0.0004826921212952584,
+      "teacher_loss": 0.0003007515915669501
+    },
+    {
+      "epoch": 0.07064590542099193,
+      "grad_norm": 1.078125,
+      "kd_loss": 0.010876834392547607,
+      "learning_rate": 8.846365562685178e-06,
+      "loss": 0.0379,
+      "step": 245,
+      "student_loss": 0.00123109039850533,
+      "teacher_loss": 0.0017208561766892672
+    },
+    {
+      "epoch": 0.07208765859284891,
+      "grad_norm": 1.6484375,
+      "kd_loss": 0.012208702974021435,
+      "learning_rate": 8.794130856643635e-06,
+      "loss": 0.0402,
+      "step": 250,
+      "student_loss": 0.0006701876409351826,
+      "teacher_loss": 0.00039402375114150345
+    },
+    {
+      "epoch": 0.07352941176470588,
+      "grad_norm": 3.859375,
+      "kd_loss": 0.010964477434754372,
+      "learning_rate": 8.74090120554202e-06,
+      "loss": 0.0428,
+      "step": 255,
+      "student_loss": 0.0004243800649419427,
+      "teacher_loss": 0.0003773768839892
+    },
+    {
+      "epoch": 0.07497116493656286,
+      "grad_norm": 2.015625,
+      "kd_loss": 0.018098091706633568,
+      "learning_rate": 8.686690567933803e-06,
+      "loss": 0.0436,
+      "step": 260,
+      "student_loss": 0.040437813848257065,
+      "teacher_loss": 0.032756391912698746
+    },
+    {
+      "epoch": 0.07641291810841984,
+      "grad_norm": 1.125,
+      "kd_loss": 0.011841603554785252,
+      "learning_rate": 8.63151315961915e-06,
+      "loss": 0.0412,
+      "step": 265,
+      "student_loss": 0.0006605261587537825,
+      "teacher_loss": 0.0004997120704501867
+    },
+    {
+      "epoch": 0.07785467128027682,
+      "grad_norm": 1.046875,
+      "kd_loss": 0.01046097930520773,
+      "learning_rate": 8.575383449917103e-06,
+      "loss": 0.044,
+      "step": 270,
+      "student_loss": 0.0009966753423213959,
+      "teacher_loss": 0.0006801315466873348
+    },
+    {
+      "epoch": 0.07929642445213379,
+      "grad_norm": 1.515625,
+      "kd_loss": 0.01713527925312519,
+      "learning_rate": 8.518316157871232e-06,
+      "loss": 0.0403,
+      "step": 275,
+      "student_loss": 0.04822665825486183,
+      "teacher_loss": 0.03450855612754822
+    },
+    {
+      "epoch": 0.08073817762399077,
+      "grad_norm": 1.3828125,
+      "kd_loss": 0.021968362852931023,
+      "learning_rate": 8.460326248389825e-06,
+      "loss": 0.0401,
+      "step": 280,
+      "student_loss": 0.0006340977270156145,
+      "teacher_loss": 0.0001483594678575173
+    },
+    {
+      "epoch": 0.08217993079584775,
+      "grad_norm": 1.3203125,
+      "kd_loss": 0.01131309662014246,
+      "learning_rate": 8.401428928321607e-06,
+      "loss": 0.0435,
+      "step": 285,
+      "student_loss": 0.0005278023309074342,
+      "teacher_loss": 0.0004103762039449066
+    },
+    {
+      "epoch": 0.08362168396770472,
+      "grad_norm": 1.1015625,
+      "kd_loss": 0.00958277191966772,
+      "learning_rate": 8.341639642468002e-06,
+      "loss": 0.0469,
+      "step": 290,
+      "student_loss": 0.005627856124192476,
+      "teacher_loss": 0.0034064538776874542
+    },
+    {
+      "epoch": 0.0850634371395617,
+      "grad_norm": 1.140625,
+      "kd_loss": 0.009735080413520336,
+      "learning_rate": 8.280974069532999e-06,
+      "loss": 0.0409,
+      "step": 295,
+      "student_loss": 0.000509344507008791,
+      "teacher_loss": 0.0004550877492874861
+    },
+    {
+      "epoch": 0.08650519031141868,
+      "grad_norm": 1.09375,
+      "kd_loss": 0.031678151339292526,
+      "learning_rate": 8.219448118011687e-06,
+      "loss": 0.0379,
+      "step": 300,
+      "student_loss": 0.016466177999973297,
+      "teacher_loss": 0.002865313785150647
+    },
+    {
+      "epoch": 0.08794694348327567,
+      "grad_norm": 1.1015625,
+      "kd_loss": 0.013346894644200802,
+      "learning_rate": 8.157077922018537e-06,
+      "loss": 0.0353,
+      "step": 305,
+      "student_loss": 0.009980602189898491,
+      "teacher_loss": 0.0014113991055637598
+    },
+    {
+      "epoch": 0.08938869665513265,
+      "grad_norm": 1.90625,
+      "kd_loss": 0.010920979082584381,
+      "learning_rate": 8.093879837056486e-06,
+      "loss": 0.0384,
+      "step": 310,
+      "student_loss": 0.00036570793599821627,
+      "teacher_loss": 0.0002939177502412349
+    },
+    {
+      "epoch": 0.09083044982698962,
+      "grad_norm": 1.0078125,
+      "kd_loss": 0.021986963227391243,
+      "learning_rate": 8.029870435728018e-06,
+      "loss": 0.0385,
+      "step": 315,
+      "student_loss": 0.01466396264731884,
+      "teacher_loss": 0.0008777049370110035
+    },
+    {
+      "epoch": 0.0922722029988466,
+      "grad_norm": 1.640625,
+      "kd_loss": 0.014081098139286041,
+      "learning_rate": 7.965066503389264e-06,
+      "loss": 0.0417,
+      "step": 320,
+      "student_loss": 0.0004964058171026409,
+      "teacher_loss": 0.0003025036712642759
+    },
+    {
+      "epoch": 0.09371395617070358,
+      "grad_norm": 1.2421875,
+      "kd_loss": 0.03542112559080124,
+      "learning_rate": 7.89948503374835e-06,
+      "loss": 0.0378,
+      "step": 325,
+      "student_loss": 0.01556178368628025,
+      "teacher_loss": 0.018082890659570694
+    },
+    {
+      "epoch": 0.09515570934256055,
+      "grad_norm": 1.40625,
+      "kd_loss": 0.04085119441151619,
+      "learning_rate": 7.833143224409076e-06,
+      "loss": 0.0394,
+      "step": 330,
+      "student_loss": 0.024770811200141907,
+      "teacher_loss": 0.0021320905070751905
+    },
+    {
+      "epoch": 0.09659746251441753,
+      "grad_norm": 1.0234375,
+      "kd_loss": 0.008477268740534782,
+      "learning_rate": 7.766058472361154e-06,
+      "loss": 0.0338,
+      "step": 335,
+      "student_loss": 0.0009084849734790623,
+      "teacher_loss": 0.0007285018800757825
+    },
+    {
+      "epoch": 0.09803921568627451,
+      "grad_norm": 1.28125,
+      "kd_loss": 0.014947460032999516,
+      "learning_rate": 7.698248369418146e-06,
+      "loss": 0.0388,
+      "step": 340,
+      "student_loss": 0.009875037707388401,
+      "teacher_loss": 0.00507500022649765
+    },
+    {
+      "epoch": 0.09948096885813149,
+      "grad_norm": 1.2421875,
+      "kd_loss": 0.019748909398913383,
+      "learning_rate": 7.629730697604314e-06,
+      "loss": 0.0437,
+      "step": 345,
+      "student_loss": 0.008698839694261551,
+      "teacher_loss": 0.00021470236242748797
+    },
+    {
+      "epoch": 0.10092272202998846,
+      "grad_norm": 1.453125,
+      "kd_loss": 0.038638580590486526,
+      "learning_rate": 7.560523424491595e-06,
+      "loss": 0.0333,
+      "step": 350,
+      "student_loss": 0.007182905916124582,
+      "teacher_loss": 0.0004611952172126621
+    },
+    {
+      "epoch": 0.10236447520184544,
+      "grad_norm": 1.4375,
+      "kd_loss": 0.008461177349090576,
+      "learning_rate": 7.490644698487909e-06,
+      "loss": 0.0405,
+      "step": 355,
+      "student_loss": 0.0004199718532618135,
+      "teacher_loss": 0.00038222281727939844
+    },
+    {
+      "epoch": 0.10380622837370242,
+      "grad_norm": 1.1796875,
+      "kd_loss": 0.008598582819104195,
+      "learning_rate": 7.420112844078066e-06,
+      "loss": 0.0396,
+      "step": 360,
+      "student_loss": 0.00045404830598272383,
+      "teacher_loss": 0.0003997418680228293
+    },
+    {
+      "epoch": 0.1052479815455594,
+      "grad_norm": 1.78125,
+      "kd_loss": 0.018130140379071236,
+      "learning_rate": 7.348946357018479e-06,
+      "loss": 0.0425,
+      "step": 365,
+      "student_loss": 0.06869062036275864,
+      "teacher_loss": 0.027944643050432205
+    },
+    {
+      "epoch": 0.10668973471741638,
+      "grad_norm": 1.03125,
+      "kd_loss": 0.0350988432765007,
+      "learning_rate": 7.277163899486975e-06,
+      "loss": 0.0447,
+      "step": 370,
+      "student_loss": 0.015085455030202866,
+      "teacher_loss": 0.0004648211761377752
+    },
+    {
+      "epoch": 0.10813148788927336,
+      "grad_norm": 1.0703125,
+      "kd_loss": 0.01613399013876915,
+      "learning_rate": 7.204784295188959e-06,
+      "loss": 0.0365,
+      "step": 375,
+      "student_loss": 0.03554360568523407,
+      "teacher_loss": 0.021264519542455673
+    },
+    {
+      "epoch": 0.10957324106113034,
+      "grad_norm": 1.296875,
+      "kd_loss": 0.010999550111591816,
+      "learning_rate": 7.1318265244212305e-06,
+      "loss": 0.0381,
+      "step": 380,
+      "student_loss": 0.0004269553755875677,
+      "teacher_loss": 0.0003071910759899765
+    },
+    {
+      "epoch": 0.11101499423298732,
+      "grad_norm": 0.875,
+      "kd_loss": 0.015028773806989193,
+      "learning_rate": 7.05830971909472e-06,
+      "loss": 0.0349,
+      "step": 385,
+      "student_loss": 0.0005910908803343773,
+      "teacher_loss": 0.0003781717678066343
+    },
+    {
+      "epoch": 0.11245674740484429,
+      "grad_norm": 1.25,
+      "kd_loss": 0.010998338460922241,
+      "learning_rate": 6.9842531577174865e-06,
+      "loss": 0.033,
+      "step": 390,
+      "student_loss": 0.00025347189512103796,
+      "teacher_loss": 0.00023755666916258633
+    },
+    {
+      "epoch": 0.11389850057670127,
+      "grad_norm": 1.390625,
+      "kd_loss": 0.010839108377695084,
+      "learning_rate": 6.9096762603392595e-06,
+      "loss": 0.0393,
+      "step": 395,
+      "student_loss": 0.00046008970821276307,
+      "teacher_loss": 0.00034296512603759766
+    },
+    {
+      "epoch": 0.11534025374855825,
+      "grad_norm": 2.40625,
+      "kd_loss": 0.015689171850681305,
+      "learning_rate": 6.834598583458862e-06,
+      "loss": 0.0333,
+      "step": 400,
+      "student_loss": 0.0004951858427375555,
+      "teacher_loss": 0.0002840181696228683
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 1000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 200,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoints/codi1.5b_a1.0_b1.0_g1.0_ls2/checkpoint-600/added_tokens.json

@@ -0,0 +1,35 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|action_sep|>": 151670,
+  "<|arg_sep|>": 151671,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|call_sep|>": 151666,
+  "<|end_of_text|>": 151673,
+  "<|endoftext|>": 151643,
+  "<|exception_sep|>": 151669,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|frame_sep|>": 151672,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|latent_end|>": 151675,
+  "<|latent_start|>": 151674,
+  "<|line_sep|>": 151667,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|return_sep|>": 151668,
+  "<|trace_context_start|>": 151665,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

checkpoints/codi1.5b_a1.0_b1.0_g1.0_ls2/checkpoint-600/chat_template.jinja

@@ -0,0 +1,54 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
+    {%- endif %}
+    {{- "\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>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\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" }}
+{%- else %}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
+    {%- else %}
+        {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role }}
+        {%- if message.content %}
+            {{- '\n' + message.content }}
+        {%- endif %}
+        {%- for tool_call in message.tool_calls %}
+            {%- if tool_call.function is defined %}
+                {%- set tool_call = tool_call.function %}
+            {%- endif %}
+            {{- '\n<tool_call>\n{"name": "' }}
+            {{- tool_call.name }}
+            {{- '", "arguments": ' }}
+            {{- tool_call.arguments | tojson }}
+            {{- '}\n</tool_call>' }}
+        {%- endfor %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}

checkpoints/codi1.5b_a1.0_b1.0_g1.0_ls2/checkpoint-600/config.json

@@ -0,0 +1,58 @@
+{
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "dtype": "bfloat16",
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 1536,
+  "initializer_range": 0.02,
+  "intermediate_size": 8960,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 2,
+  "pad_token_id": 151643,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "transformers_version": "4.57.6",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151676
+}

checkpoints/codi1.5b_a1.0_b1.0_g1.0_ls2/checkpoint-600/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7448e9232596f2baf886f818457931ae5d797620a7cab584453a45dfe3ae64a5
+size 3096275515

checkpoints/codi1.5b_a1.0_b1.0_g1.0_ls2/checkpoint-600/special_tokens_map.json

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

checkpoints/codi1.5b_a1.0_b1.0_g1.0_ls2/checkpoint-600/thought_projector.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d6ca7d2abfac84407f2a77a3ef77cdfbd0a7e0c484f220f0e4616bbfd040b71
+size 9445953

checkpoints/codi1.5b_a1.0_b1.0_g1.0_ls2/checkpoint-600/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83a790d654474f5dfe225f889afd0210313eb1083f942671f2c4b8e95a1c922b
+size 11424004

checkpoints/codi1.5b_a1.0_b1.0_g1.0_ls2/checkpoint-600/tokenizer_config.json

@@ -0,0 +1,295 @@
+{
+  "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
+    },
+    "151665": {
+      "content": "<|trace_context_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151666": {
+      "content": "<|call_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151667": {
+      "content": "<|line_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151668": {
+      "content": "<|return_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151669": {
+      "content": "<|exception_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151670": {
+      "content": "<|action_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151671": {
+      "content": "<|arg_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151672": {
+      "content": "<|frame_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151673": {
+      "content": "<|end_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151674": {
+      "content": "<|latent_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151675": {
+      "content": "<|latent_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "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,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoints/codi1.5b_a1.0_b1.0_g1.0_ls2/checkpoint-600/trainer_state.json

@@ -0,0 +1,1234 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.17301038062283736,
+  "eval_steps": 500,
+  "global_step": 600,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0014417531718569781,
+      "grad_norm": 52992.0,
+      "kd_loss": 0.3193017542362213,
+      "learning_rate": 1.3333333333333334e-06,
+      "loss": 0.473,
+      "step": 5,
+      "student_loss": 0.15727384388446808,
+      "teacher_loss": 0.0004137983196415007
+    },
+    {
+      "epoch": 0.0028835063437139563,
+      "grad_norm": 16121856.0,
+      "kd_loss": 0.3087984025478363,
+      "learning_rate": 3e-06,
+      "loss": 0.466,
+      "step": 10,
+      "student_loss": 0.2608874440193176,
+      "teacher_loss": 0.0007329508662223816
+    },
+    {
+      "epoch": 0.004325259515570935,
+      "grad_norm": 2240.0,
+      "kd_loss": 0.25935155153274536,
+      "learning_rate": 4.666666666666667e-06,
+      "loss": 0.4585,
+      "step": 15,
+      "student_loss": 0.1052168533205986,
+      "teacher_loss": 0.000609480426646769
+    },
+    {
+      "epoch": 0.0057670126874279125,
+      "grad_norm": 4194304.0,
+      "kd_loss": 0.25011566281318665,
+      "learning_rate": 6.333333333333333e-06,
+      "loss": 0.4707,
+      "step": 20,
+      "student_loss": 0.15271778404712677,
+      "teacher_loss": 0.0002972046786453575
+    },
+    {
+      "epoch": 0.00720876585928489,
+      "grad_norm": 41680896.0,
+      "kd_loss": 0.2633170485496521,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 0.4368,
+      "step": 25,
+      "student_loss": 0.09109362959861755,
+      "teacher_loss": 0.0009600125486031175
+    },
+    {
+      "epoch": 0.00865051903114187,
+      "grad_norm": 512.0,
+      "kd_loss": 0.2533612847328186,
+      "learning_rate": 9.666666666666667e-06,
+      "loss": 0.4187,
+      "step": 30,
+      "student_loss": 0.22675999999046326,
+      "teacher_loss": 0.00035076512722298503
+    },
+    {
+      "epoch": 0.010092272202998846,
+      "grad_norm": 48.75,
+      "kd_loss": 0.2179471105337143,
+      "learning_rate": 9.99958042442916e-06,
+      "loss": 0.3713,
+      "step": 35,
+      "student_loss": 0.09486500918865204,
+      "teacher_loss": 0.00026503618573769927
+    },
+    {
+      "epoch": 0.011534025374855825,
+      "grad_norm": 10.0,
+      "kd_loss": 0.17874062061309814,
+      "learning_rate": 9.997876019358083e-06,
+      "loss": 0.2647,
+      "step": 40,
+      "student_loss": 0.07879351079463959,
+      "teacher_loss": 0.05543303117156029
+    },
+    {
+      "epoch": 0.012975778546712802,
+      "grad_norm": 4.9375,
+      "kd_loss": 0.19365739822387695,
+      "learning_rate": 9.99486100792044e-06,
+      "loss": 0.1686,
+      "step": 45,
+      "student_loss": 0.07774724811315536,
+      "teacher_loss": 0.0008653572876937687
+    },
+    {
+      "epoch": 0.01441753171856978,
+      "grad_norm": 3.359375,
+      "kd_loss": 0.06108914315700531,
+      "learning_rate": 9.990536180750724e-06,
+      "loss": 0.1396,
+      "step": 50,
+      "student_loss": 0.008677379228174686,
+      "teacher_loss": 0.005272893700748682
+    },
+    {
+      "epoch": 0.015859284890426758,
+      "grad_norm": 3.71875,
+      "kd_loss": 0.04330182075500488,
+      "learning_rate": 9.984902671959911e-06,
+      "loss": 0.1065,
+      "step": 55,
+      "student_loss": 0.001041711075231433,
+      "teacher_loss": 0.0005072589847259223
+    },
+    {
+      "epoch": 0.01730103806228374,
+      "grad_norm": 4.125,
+      "kd_loss": 0.03823668882250786,
+      "learning_rate": 9.97796195883804e-06,
+      "loss": 0.0862,
+      "step": 60,
+      "student_loss": 0.0209807138890028,
+      "teacher_loss": 0.0038409351836889982
+    },
+    {
+      "epoch": 0.018742791234140715,
+      "grad_norm": 10.1875,
+      "kd_loss": 0.03922531381249428,
+      "learning_rate": 9.969715861466839e-06,
+      "loss": 0.0844,
+      "step": 65,
+      "student_loss": 0.04678678512573242,
+      "teacher_loss": 0.05432586744427681
+    },
+    {
+      "epoch": 0.020184544405997693,
+      "grad_norm": 2.03125,
+      "kd_loss": 0.0549621656537056,
+      "learning_rate": 9.96016654224243e-06,
+      "loss": 0.0797,
+      "step": 70,
+      "student_loss": 0.016930116340517998,
+      "teacher_loss": 0.0029678302817046642
+    },
+    {
+      "epoch": 0.02162629757785467,
+      "grad_norm": 2.5625,
+      "kd_loss": 0.023080041632056236,
+      "learning_rate": 9.94931650530827e-06,
+      "loss": 0.0756,
+      "step": 75,
+      "student_loss": 0.002210108330473304,
+      "teacher_loss": 0.0013834249693900347
+    },
+    {
+      "epoch": 0.02306805074971165,
+      "grad_norm": 2.296875,
+      "kd_loss": 0.025744518265128136,
+      "learning_rate": 9.93716859589851e-06,
+      "loss": 0.0644,
+      "step": 80,
+      "student_loss": 0.0015430074417963624,
+      "teacher_loss": 0.000761081581003964
+    },
+    {
+      "epoch": 0.024509803921568627,
+      "grad_norm": 3.125,
+      "kd_loss": 0.023152953013777733,
+      "learning_rate": 9.923725999591846e-06,
+      "loss": 0.0609,
+      "step": 85,
+      "student_loss": 0.0187687948346138,
+      "teacher_loss": 0.011518553830683231
+    },
+    {
+      "epoch": 0.025951557093425604,
+      "grad_norm": 1.8359375,
+      "kd_loss": 0.06841632723808289,
+      "learning_rate": 9.908992241476189e-06,
+      "loss": 0.0622,
+      "step": 90,
+      "student_loss": 0.05537872016429901,
+      "teacher_loss": 0.011890009045600891
+    },
+    {
+      "epoch": 0.027393310265282585,
+      "grad_norm": 4.21875,
+      "kd_loss": 0.041227906942367554,
+      "learning_rate": 9.892971185224244e-06,
+      "loss": 0.0626,
+      "step": 95,
+      "student_loss": 0.009465624578297138,
+      "teacher_loss": 0.005057212430983782
+    },
+    {
+      "epoch": 0.02883506343713956,
+      "grad_norm": 1.8359375,
+      "kd_loss": 0.021006152033805847,
+      "learning_rate": 9.875667032080354e-06,
+      "loss": 0.0538,
+      "step": 100,
+      "student_loss": 0.0007415671134367585,
+      "teacher_loss": 0.0005348982522264123
+    },
+    {
+      "epoch": 0.03027681660899654,
+      "grad_norm": 1.6328125,
+      "kd_loss": 0.035115621984004974,
+      "learning_rate": 9.857084319758772e-06,
+      "loss": 0.0541,
+      "step": 105,
+      "student_loss": 0.005187581293284893,
+      "teacher_loss": 0.00030648778192698956
+    },
+    {
+      "epoch": 0.031718569780853516,
+      "grad_norm": 2.953125,
+      "kd_loss": 0.03037514165043831,
+      "learning_rate": 9.837227921253747e-06,
+      "loss": 0.06,
+      "step": 110,
+      "student_loss": 0.031953420490026474,
+      "teacher_loss": 0.0175339188426733
+    },
+    {
+      "epoch": 0.03316032295271049,
+      "grad_norm": 1.484375,
+      "kd_loss": 0.023421702906489372,
+      "learning_rate": 9.816103043561648e-06,
+      "loss": 0.0563,
+      "step": 115,
+      "student_loss": 0.0006847245967946947,
+      "teacher_loss": 0.0003864571626763791
+    },
+    {
+      "epoch": 0.03460207612456748,
+      "grad_norm": 1.8203125,
+      "kd_loss": 0.018447211012244225,
+      "learning_rate": 9.79371522631553e-06,
+      "loss": 0.0478,
+      "step": 120,
+      "student_loss": 0.0015498347347602248,
+      "teacher_loss": 0.0010675351368263364
+    },
+    {
+      "epoch": 0.036043829296424454,
+      "grad_norm": 1.96875,
+      "kd_loss": 0.05630031228065491,
+      "learning_rate": 9.770070340332457e-06,
+      "loss": 0.0527,
+      "step": 125,
+      "student_loss": 0.04758762940764427,
+      "teacher_loss": 0.0004967509885318577
+    },
+    {
+      "epoch": 0.03748558246828143,
+      "grad_norm": 1.859375,
+      "kd_loss": 0.018152693286538124,
+      "learning_rate": 9.745174586073982e-06,
+      "loss": 0.0518,
+      "step": 130,
+      "student_loss": 0.0008988101035356522,
+      "teacher_loss": 0.0007278143893927336
+    },
+    {
+      "epoch": 0.03892733564013841,
+      "grad_norm": 1.6640625,
+      "kd_loss": 0.030904680490493774,
+      "learning_rate": 9.719034492020183e-06,
+      "loss": 0.0526,
+      "step": 135,
+      "student_loss": 0.0127235297113657,
+      "teacher_loss": 0.0011665972415357828
+    },
+    {
+      "epoch": 0.040369088811995385,
+      "grad_norm": 1.1640625,
+      "kd_loss": 0.01759810373187065,
+      "learning_rate": 9.691656912957686e-06,
+      "loss": 0.0494,
+      "step": 140,
+      "student_loss": 0.0008300879271700978,
+      "teacher_loss": 0.0005129938363097608
+    },
+    {
+      "epoch": 0.04181084198385236,
+      "grad_norm": 1.0234375,
+      "kd_loss": 0.061179179698228836,
+      "learning_rate": 9.663049028182112e-06,
+      "loss": 0.0457,
+      "step": 145,
+      "student_loss": 0.04404008761048317,
+      "teacher_loss": 0.009324059821665287
+    },
+    {
+      "epoch": 0.04325259515570934,
+      "grad_norm": 1.15625,
+      "kd_loss": 0.01291500125080347,
+      "learning_rate": 9.633218339615433e-06,
+      "loss": 0.0455,
+      "step": 150,
+      "student_loss": 0.0008404091349802911,
+      "teacher_loss": 0.0008450732566416264
+    },
+    {
+      "epoch": 0.04469434832756632,
+      "grad_norm": 1.4921875,
+      "kd_loss": 0.017479021102190018,
+      "learning_rate": 9.602172669838721e-06,
+      "loss": 0.0575,
+      "step": 155,
+      "student_loss": 0.0009151780977845192,
+      "teacher_loss": 0.0006974826683290303
+    },
+    {
+      "epoch": 0.0461361014994233,
+      "grad_norm": 1.671875,
+      "kd_loss": 0.022708255797624588,
+      "learning_rate": 9.569920160040815e-06,
+      "loss": 0.0503,
+      "step": 160,
+      "student_loss": 0.07660368084907532,
+      "teacher_loss": 0.04039459675550461
+    },
+    {
+      "epoch": 0.04757785467128028,
+      "grad_norm": 1.0703125,
+      "kd_loss": 0.027437202632427216,
+      "learning_rate": 9.536469267883432e-06,
+      "loss": 0.0451,
+      "step": 165,
+      "student_loss": 0.0005943832220509648,
+      "teacher_loss": 0.005336699075996876
+    },
+    {
+      "epoch": 0.049019607843137254,
+      "grad_norm": 1.71875,
+      "kd_loss": 0.014546042308211327,
+      "learning_rate": 9.501828765283295e-06,
+      "loss": 0.0459,
+      "step": 170,
+      "student_loss": 0.0006958618760108948,
+      "teacher_loss": 0.0005218263831920922
+    },
+    {
+      "epoch": 0.05046136101499423,
+      "grad_norm": 1.4453125,
+      "kd_loss": 0.02377346158027649,
+      "learning_rate": 9.466007736111846e-06,
+      "loss": 0.0465,
+      "step": 175,
+      "student_loss": 0.003214897122234106,
+      "teacher_loss": 0.0006713470793329179
+    },
+    {
+      "epoch": 0.05190311418685121,
+      "grad_norm": 1.296875,
+      "kd_loss": 0.02517828531563282,
+      "learning_rate": 9.429015573813163e-06,
+      "loss": 0.0454,
+      "step": 180,
+      "student_loss": 0.0007039233460091054,
+      "teacher_loss": 0.0003641469811554998
+    },
+    {
+      "epoch": 0.05334486735870819,
+      "grad_norm": 1.25,
+      "kd_loss": 0.029188504442572594,
+      "learning_rate": 9.390861978940687e-06,
+      "loss": 0.0473,
+      "step": 185,
+      "student_loss": 0.04238048940896988,
+      "teacher_loss": 0.00033479384728707373
+    },
+    {
+      "epoch": 0.05478662053056517,
+      "grad_norm": 1.484375,
+      "kd_loss": 0.03749082237482071,
+      "learning_rate": 9.351556956613423e-06,
+      "loss": 0.0436,
+      "step": 190,
+      "student_loss": 0.010270334780216217,
+      "teacher_loss": 0.0024021982681006193
+    },
+    {
+      "epoch": 0.056228373702422146,
+      "grad_norm": 2.0,
+      "kd_loss": 0.030336912721395493,
+      "learning_rate": 9.31111081389227e-06,
+      "loss": 0.0442,
+      "step": 195,
+      "student_loss": 0.010534510016441345,
+      "teacher_loss": 0.0003890562220476568
+    },
+    {
+      "epoch": 0.05767012687427912,
+      "grad_norm": 0.921875,
+      "kd_loss": 0.026554003357887268,
+      "learning_rate": 9.269534157077177e-06,
+      "loss": 0.0497,
+      "step": 200,
+      "student_loss": 0.0034760867711156607,
+      "teacher_loss": 0.00022423896007239819
+    },
+    {
+      "epoch": 0.0591118800461361,
+      "grad_norm": 1.9140625,
+      "kd_loss": 0.023410219699144363,
+      "learning_rate": 9.226837888925813e-06,
+      "loss": 0.0471,
+      "step": 205,
+      "student_loss": 0.03611442819237709,
+      "teacher_loss": 0.027781842276453972
+    },
+    {
+      "epoch": 0.06055363321799308,
+      "grad_norm": 1.7578125,
+      "kd_loss": 0.022867349907755852,
+      "learning_rate": 9.183033205794525e-06,
+      "loss": 0.0428,
+      "step": 210,
+      "student_loss": 0.001971556106582284,
+      "teacher_loss": 0.0009746765717864037
+    },
+    {
+      "epoch": 0.061995386389850055,
+      "grad_norm": 1.0234375,
+      "kd_loss": 0.028235338628292084,
+      "learning_rate": 9.13813159470227e-06,
+      "loss": 0.0449,
+      "step": 215,
+      "student_loss": 0.0009558866149745882,
+      "teacher_loss": 0.0004049334966111928
+    },
+    {
+      "epoch": 0.06343713956170703,
+      "grad_norm": 1.4296875,
+      "kd_loss": 0.03134317323565483,
+      "learning_rate": 9.092144830318357e-06,
+      "loss": 0.0438,
+      "step": 220,
+      "student_loss": 0.048195730894804,
+      "teacher_loss": 0.009161758236587048
+    },
+    {
+      "epoch": 0.06487889273356401,
+      "grad_norm": 1.1328125,
+      "kd_loss": 0.014049015007913113,
+      "learning_rate": 9.045084971874738e-06,
+      "loss": 0.0487,
+      "step": 225,
+      "student_loss": 0.05373133346438408,
+      "teacher_loss": 0.0009734037448652089
+    },
+    {
+      "epoch": 0.06632064590542099,
+      "grad_norm": 1.7265625,
+      "kd_loss": 0.021539395675063133,
+      "learning_rate": 8.99696436000368e-06,
+      "loss": 0.0384,
+      "step": 230,
+      "student_loss": 0.0008717047749087214,
+      "teacher_loss": 0.0028650674503296614
+    },
+    {
+      "epoch": 0.06776239907727798,
+      "grad_norm": 1.0390625,
+      "kd_loss": 0.045927971601486206,
+      "learning_rate": 8.947795613501658e-06,
+      "loss": 0.0397,
+      "step": 235,
+      "student_loss": 0.012143217958509922,
+      "teacher_loss": 0.0006723064580000937
+    },
+    {
+      "epoch": 0.06920415224913495,
+      "grad_norm": 0.78125,
+      "kd_loss": 0.01626853086054325,
+      "learning_rate": 8.897591626020284e-06,
+      "loss": 0.0425,
+      "step": 240,
+      "student_loss": 0.0004826921212952584,
+      "teacher_loss": 0.0003007515915669501
+    },
+    {
+      "epoch": 0.07064590542099193,
+      "grad_norm": 1.078125,
+      "kd_loss": 0.010876834392547607,
+      "learning_rate": 8.846365562685178e-06,
+      "loss": 0.0379,
+      "step": 245,
+      "student_loss": 0.00123109039850533,
+      "teacher_loss": 0.0017208561766892672
+    },
+    {
+      "epoch": 0.07208765859284891,
+      "grad_norm": 1.6484375,
+      "kd_loss": 0.012208702974021435,
+      "learning_rate": 8.794130856643635e-06,
+      "loss": 0.0402,
+      "step": 250,
+      "student_loss": 0.0006701876409351826,
+      "teacher_loss": 0.00039402375114150345
+    },
+    {
+      "epoch": 0.07352941176470588,
+      "grad_norm": 3.859375,
+      "kd_loss": 0.010964477434754372,
+      "learning_rate": 8.74090120554202e-06,
+      "loss": 0.0428,
+      "step": 255,
+      "student_loss": 0.0004243800649419427,
+      "teacher_loss": 0.0003773768839892
+    },
+    {
+      "epoch": 0.07497116493656286,
+      "grad_norm": 2.015625,
+      "kd_loss": 0.018098091706633568,
+      "learning_rate": 8.686690567933803e-06,
+      "loss": 0.0436,
+      "step": 260,
+      "student_loss": 0.040437813848257065,
+      "teacher_loss": 0.032756391912698746
+    },
+    {
+      "epoch": 0.07641291810841984,
+      "grad_norm": 1.125,
+      "kd_loss": 0.011841603554785252,
+      "learning_rate": 8.63151315961915e-06,
+      "loss": 0.0412,
+      "step": 265,
+      "student_loss": 0.0006605261587537825,
+      "teacher_loss": 0.0004997120704501867
+    },
+    {
+      "epoch": 0.07785467128027682,
+      "grad_norm": 1.046875,
+      "kd_loss": 0.01046097930520773,
+      "learning_rate": 8.575383449917103e-06,
+      "loss": 0.044,
+      "step": 270,
+      "student_loss": 0.0009966753423213959,
+      "teacher_loss": 0.0006801315466873348
+    },
+    {
+      "epoch": 0.07929642445213379,
+      "grad_norm": 1.515625,
+      "kd_loss": 0.01713527925312519,
+      "learning_rate": 8.518316157871232e-06,
+      "loss": 0.0403,
+      "step": 275,
+      "student_loss": 0.04822665825486183,
+      "teacher_loss": 0.03450855612754822
+    },
+    {
+      "epoch": 0.08073817762399077,
+      "grad_norm": 1.3828125,
+      "kd_loss": 0.021968362852931023,
+      "learning_rate": 8.460326248389825e-06,
+      "loss": 0.0401,
+      "step": 280,
+      "student_loss": 0.0006340977270156145,
+      "teacher_loss": 0.0001483594678575173
+    },
+    {
+      "epoch": 0.08217993079584775,
+      "grad_norm": 1.3203125,
+      "kd_loss": 0.01131309662014246,
+      "learning_rate": 8.401428928321607e-06,
+      "loss": 0.0435,
+      "step": 285,
+      "student_loss": 0.0005278023309074342,
+      "teacher_loss": 0.0004103762039449066
+    },
+    {
+      "epoch": 0.08362168396770472,
+      "grad_norm": 1.1015625,
+      "kd_loss": 0.00958277191966772,
+      "learning_rate": 8.341639642468002e-06,
+      "loss": 0.0469,
+      "step": 290,
+      "student_loss": 0.005627856124192476,
+      "teacher_loss": 0.0034064538776874542
+    },
+    {
+      "epoch": 0.0850634371395617,
+      "grad_norm": 1.140625,
+      "kd_loss": 0.009735080413520336,
+      "learning_rate": 8.280974069532999e-06,
+      "loss": 0.0409,
+      "step": 295,
+      "student_loss": 0.000509344507008791,
+      "teacher_loss": 0.0004550877492874861
+    },
+    {
+      "epoch": 0.08650519031141868,
+      "grad_norm": 1.09375,
+      "kd_loss": 0.031678151339292526,
+      "learning_rate": 8.219448118011687e-06,
+      "loss": 0.0379,
+      "step": 300,
+      "student_loss": 0.016466177999973297,
+      "teacher_loss": 0.002865313785150647
+    },
+    {
+      "epoch": 0.08794694348327567,
+      "grad_norm": 1.1015625,
+      "kd_loss": 0.013346894644200802,
+      "learning_rate": 8.157077922018537e-06,
+      "loss": 0.0353,
+      "step": 305,
+      "student_loss": 0.009980602189898491,
+      "teacher_loss": 0.0014113991055637598
+    },
+    {
+      "epoch": 0.08938869665513265,
+      "grad_norm": 1.90625,
+      "kd_loss": 0.010920979082584381,
+      "learning_rate": 8.093879837056486e-06,
+      "loss": 0.0384,
+      "step": 310,
+      "student_loss": 0.00036570793599821627,
+      "teacher_loss": 0.0002939177502412349
+    },
+    {
+      "epoch": 0.09083044982698962,
+      "grad_norm": 1.0078125,
+      "kd_loss": 0.021986963227391243,
+      "learning_rate": 8.029870435728018e-06,
+      "loss": 0.0385,
+      "step": 315,
+      "student_loss": 0.01466396264731884,
+      "teacher_loss": 0.0008777049370110035
+    },
+    {
+      "epoch": 0.0922722029988466,
+      "grad_norm": 1.640625,
+      "kd_loss": 0.014081098139286041,
+      "learning_rate": 7.965066503389264e-06,
+      "loss": 0.0417,
+      "step": 320,
+      "student_loss": 0.0004964058171026409,
+      "teacher_loss": 0.0003025036712642759
+    },
+    {
+      "epoch": 0.09371395617070358,
+      "grad_norm": 1.2421875,
+      "kd_loss": 0.03542112559080124,
+      "learning_rate": 7.89948503374835e-06,
+      "loss": 0.0378,
+      "step": 325,
+      "student_loss": 0.01556178368628025,
+      "teacher_loss": 0.018082890659570694
+    },
+    {
+      "epoch": 0.09515570934256055,
+      "grad_norm": 1.40625,
+      "kd_loss": 0.04085119441151619,
+      "learning_rate": 7.833143224409076e-06,
+      "loss": 0.0394,
+      "step": 330,
+      "student_loss": 0.024770811200141907,
+      "teacher_loss": 0.0021320905070751905
+    },
+    {
+      "epoch": 0.09659746251441753,
+      "grad_norm": 1.0234375,
+      "kd_loss": 0.008477268740534782,
+      "learning_rate": 7.766058472361154e-06,
+      "loss": 0.0338,
+      "step": 335,
+      "student_loss": 0.0009084849734790623,
+      "teacher_loss": 0.0007285018800757825
+    },
+    {
+      "epoch": 0.09803921568627451,
+      "grad_norm": 1.28125,
+      "kd_loss": 0.014947460032999516,
+      "learning_rate": 7.698248369418146e-06,
+      "loss": 0.0388,
+      "step": 340,
+      "student_loss": 0.009875037707388401,
+      "teacher_loss": 0.00507500022649765
+    },
+    {
+      "epoch": 0.09948096885813149,
+      "grad_norm": 1.2421875,
+      "kd_loss": 0.019748909398913383,
+      "learning_rate": 7.629730697604314e-06,
+      "loss": 0.0437,
+      "step": 345,
+      "student_loss": 0.008698839694261551,
+      "teacher_loss": 0.00021470236242748797
+    },
+    {
+      "epoch": 0.10092272202998846,
+      "grad_norm": 1.453125,
+      "kd_loss": 0.038638580590486526,
+      "learning_rate": 7.560523424491595e-06,
+      "loss": 0.0333,
+      "step": 350,
+      "student_loss": 0.007182905916124582,
+      "teacher_loss": 0.0004611952172126621
+    },
+    {
+      "epoch": 0.10236447520184544,
+      "grad_norm": 1.4375,
+      "kd_loss": 0.008461177349090576,
+      "learning_rate": 7.490644698487909e-06,
+      "loss": 0.0405,
+      "step": 355,
+      "student_loss": 0.0004199718532618135,
+      "teacher_loss": 0.00038222281727939844
+    },
+    {
+      "epoch": 0.10380622837370242,
+      "grad_norm": 1.1796875,
+      "kd_loss": 0.008598582819104195,
+      "learning_rate": 7.420112844078066e-06,
+      "loss": 0.0396,
+      "step": 360,
+      "student_loss": 0.00045404830598272383,
+      "teacher_loss": 0.0003997418680228293
+    },
+    {
+      "epoch": 0.1052479815455594,
+      "grad_norm": 1.78125,
+      "kd_loss": 0.018130140379071236,
+      "learning_rate": 7.348946357018479e-06,
+      "loss": 0.0425,
+      "step": 365,
+      "student_loss": 0.06869062036275864,
+      "teacher_loss": 0.027944643050432205
+    },
+    {
+      "epoch": 0.10668973471741638,
+      "grad_norm": 1.03125,
+      "kd_loss": 0.0350988432765007,
+      "learning_rate": 7.277163899486975e-06,
+      "loss": 0.0447,
+      "step": 370,
+      "student_loss": 0.015085455030202866,
+      "teacher_loss": 0.0004648211761377752
+    },
+    {
+      "epoch": 0.10813148788927336,
+      "grad_norm": 1.0703125,
+      "kd_loss": 0.01613399013876915,
+      "learning_rate": 7.204784295188959e-06,
+      "loss": 0.0365,
+      "step": 375,
+      "student_loss": 0.03554360568523407,
+      "teacher_loss": 0.021264519542455673
+    },
+    {
+      "epoch": 0.10957324106113034,
+      "grad_norm": 1.296875,
+      "kd_loss": 0.010999550111591816,
+      "learning_rate": 7.1318265244212305e-06,
+      "loss": 0.0381,
+      "step": 380,
+      "student_loss": 0.0004269553755875677,
+      "teacher_loss": 0.0003071910759899765
+    },
+    {
+      "epoch": 0.11101499423298732,
+      "grad_norm": 0.875,
+      "kd_loss": 0.015028773806989193,
+      "learning_rate": 7.05830971909472e-06,
+      "loss": 0.0349,
+      "step": 385,
+      "student_loss": 0.0005910908803343773,
+      "teacher_loss": 0.0003781717678066343
+    },
+    {
+      "epoch": 0.11245674740484429,
+      "grad_norm": 1.25,
+      "kd_loss": 0.010998338460922241,
+      "learning_rate": 6.9842531577174865e-06,
+      "loss": 0.033,
+      "step": 390,
+      "student_loss": 0.00025347189512103796,
+      "teacher_loss": 0.00023755666916258633
+    },
+    {
+      "epoch": 0.11389850057670127,
+      "grad_norm": 1.390625,
+      "kd_loss": 0.010839108377695084,
+      "learning_rate": 6.9096762603392595e-06,
+      "loss": 0.0393,
+      "step": 395,
+      "student_loss": 0.00046008970821276307,
+      "teacher_loss": 0.00034296512603759766
+    },
+    {
+      "epoch": 0.11534025374855825,
+      "grad_norm": 2.40625,
+      "kd_loss": 0.015689171850681305,
+      "learning_rate": 6.834598583458862e-06,
+      "loss": 0.0333,
+      "step": 400,
+      "student_loss": 0.0004951858427375555,
+      "teacher_loss": 0.0002840181696228683
+    },
+    {
+      "epoch": 0.11678200692041522,
+      "grad_norm": 1.328125,
+      "kd_loss": 0.014689328148961067,
+      "learning_rate": 6.7590398148958625e-06,
+      "loss": 0.0425,
+      "step": 405,
+      "student_loss": 0.005328211933374405,
+      "teacher_loss": 0.0002102136058965698
+    },
+    {
+      "epoch": 0.1182237600922722,
+      "grad_norm": 1.4609375,
+      "kd_loss": 0.026721687987446785,
+      "learning_rate": 6.6830197686277945e-06,
+      "loss": 0.0417,
+      "step": 410,
+      "student_loss": 0.015544440597295761,
+      "teacher_loss": 0.00868156086653471
+    },
+    {
+      "epoch": 0.11966551326412918,
+      "grad_norm": 1.1640625,
+      "kd_loss": 0.0165933258831501,
+      "learning_rate": 6.6065583795942625e-06,
+      "loss": 0.0409,
+      "step": 415,
+      "student_loss": 0.0018743074033409357,
+      "teacher_loss": 0.002361958846449852
+    },
+    {
+      "epoch": 0.12110726643598616,
+      "grad_norm": 1.34375,
+      "kd_loss": 0.02428903616964817,
+      "learning_rate": 6.52967569846937e-06,
+      "loss": 0.0376,
+      "step": 420,
+      "student_loss": 0.05027158558368683,
+      "teacher_loss": 0.022369280457496643
+    },
+    {
+      "epoch": 0.12254901960784313,
+      "grad_norm": 1.171875,
+      "kd_loss": 0.00989749375730753,
+      "learning_rate": 6.452391886403767e-06,
+      "loss": 0.0366,
+      "step": 425,
+      "student_loss": 0.001526529318653047,
+      "teacher_loss": 0.001954666106030345
+    },
+    {
+      "epoch": 0.12399077277970011,
+      "grad_norm": 1.40625,
+      "kd_loss": 0.025572113692760468,
+      "learning_rate": 6.374727209737743e-06,
+      "loss": 0.0457,
+      "step": 430,
+      "student_loss": 0.05225735530257225,
+      "teacher_loss": 0.06261400878429413
+    },
+    {
+      "epoch": 0.1254325259515571,
+      "grad_norm": 1.1953125,
+      "kd_loss": 0.009243296459317207,
+      "learning_rate": 6.296702034686726e-06,
+      "loss": 0.0351,
+      "step": 435,
+      "student_loss": 0.0006208799313753843,
+      "teacher_loss": 0.0005131844663992524
+    },
+    {
+      "epoch": 0.12687427912341406,
+      "grad_norm": 1.140625,
+      "kd_loss": 0.025882720947265625,
+      "learning_rate": 6.218336822000598e-06,
+      "loss": 0.0366,
+      "step": 440,
+      "student_loss": 0.022235309705138206,
+      "teacher_loss": 0.005665617063641548
+    },
+    {
+      "epoch": 0.12831603229527105,
+      "grad_norm": 1.5546875,
+      "kd_loss": 0.020934544503688812,
+      "learning_rate": 6.139652121598219e-06,
+      "loss": 0.0381,
+      "step": 445,
+      "student_loss": 0.02492375858128071,
+      "teacher_loss": 0.01704920269548893
+    },
+    {
+      "epoch": 0.12975778546712802,
+      "grad_norm": 1.078125,
+      "kd_loss": 0.021503543481230736,
+      "learning_rate": 6.060668567178561e-06,
+      "loss": 0.039,
+      "step": 450,
+      "student_loss": 0.0008401675149798393,
+      "teacher_loss": 0.0007966886623762548
+    },
+    {
+      "epoch": 0.131199538638985,
+      "grad_norm": 0.99609375,
+      "kd_loss": 0.011403748765587807,
+      "learning_rate": 5.981406870809889e-06,
+      "loss": 0.0383,
+      "step": 455,
+      "student_loss": 0.0014924939023330808,
+      "teacher_loss": 0.000647007254883647
+    },
+    {
+      "epoch": 0.13264129181084197,
+      "grad_norm": 1.515625,
+      "kd_loss": 0.013661489821970463,
+      "learning_rate": 5.9018878174983674e-06,
+      "loss": 0.0329,
+      "step": 460,
+      "student_loss": 0.0015512986574321985,
+      "teacher_loss": 0.0012551237596198916
+    },
+    {
+      "epoch": 0.13408304498269896,
+      "grad_norm": 1.265625,
+      "kd_loss": 0.020031817257404327,
+      "learning_rate": 5.822132259737565e-06,
+      "loss": 0.0399,
+      "step": 465,
+      "student_loss": 0.0005617028218694031,
+      "teacher_loss": 0.0006807463942095637
+    },
+    {
+      "epoch": 0.13552479815455595,
+      "grad_norm": 1.171875,
+      "kd_loss": 0.012775675393640995,
+      "learning_rate": 5.742161112040237e-06,
+      "loss": 0.0377,
+      "step": 470,
+      "student_loss": 0.00029168292530812323,
+      "teacher_loss": 0.00020419349311850965
+    },
+    {
+      "epoch": 0.13696655132641292,
+      "grad_norm": 0.87109375,
+      "kd_loss": 0.016445137560367584,
+      "learning_rate": 5.661995345453867e-06,
+      "loss": 0.0315,
+      "step": 475,
+      "student_loss": 0.0005847346619702876,
+      "teacher_loss": 0.0003634036984294653
+    },
+    {
+      "epoch": 0.1384083044982699,
+      "grad_norm": 0.95703125,
+      "kd_loss": 0.014534696005284786,
+      "learning_rate": 5.581655982061367e-06,
+      "loss": 0.0466,
+      "step": 480,
+      "student_loss": 0.0203537754714489,
+      "teacher_loss": 0.014939186163246632
+    },
+    {
+      "epoch": 0.13985005767012687,
+      "grad_norm": 1.1640625,
+      "kd_loss": 0.008392157033085823,
+      "learning_rate": 5.501164089468406e-06,
+      "loss": 0.0357,
+      "step": 485,
+      "student_loss": 0.0004224316217005253,
+      "teacher_loss": 0.00044211489148437977
+    },
+    {
+      "epoch": 0.14129181084198386,
+      "grad_norm": 1.8984375,
+      "kd_loss": 0.014247741550207138,
+      "learning_rate": 5.4205407752787884e-06,
+      "loss": 0.0428,
+      "step": 490,
+      "student_loss": 0.019939009100198746,
+      "teacher_loss": 0.009562309831380844
+    },
+    {
+      "epoch": 0.14273356401384082,
+      "grad_norm": 1.828125,
+      "kd_loss": 0.026821549981832504,
+      "learning_rate": 5.339807181559359e-06,
+      "loss": 0.0484,
+      "step": 495,
+      "student_loss": 0.01085620652884245,
+      "teacher_loss": 0.001887582358904183
+    },
+    {
+      "epoch": 0.14417531718569782,
+      "grad_norm": 1.03125,
+      "kd_loss": 0.011890986934304237,
+      "learning_rate": 5.258984479295853e-06,
+      "loss": 0.0366,
+      "step": 500,
+      "student_loss": 0.0007122078677639365,
+      "teacher_loss": 0.0006097567966207862
+    },
+    {
+      "epoch": 0.14561707035755478,
+      "grad_norm": 1.0,
+      "kd_loss": 0.01012763474136591,
+      "learning_rate": 5.1780938628411795e-06,
+      "loss": 0.0433,
+      "step": 505,
+      "student_loss": 0.0004120942030567676,
+      "teacher_loss": 0.00030555034754797816
+    },
+    {
+      "epoch": 0.14705882352941177,
+      "grad_norm": 1.90625,
+      "kd_loss": 0.010170744732022285,
+      "learning_rate": 5.097156544357567e-06,
+      "loss": 0.0382,
+      "step": 510,
+      "student_loss": 0.0002881335385609418,
+      "teacher_loss": 0.000244438968366012
+    },
+    {
+      "epoch": 0.14850057670126873,
+      "grad_norm": 1.359375,
+      "kd_loss": 0.0138414166867733,
+      "learning_rate": 5.016193748254045e-06,
+      "loss": 0.031,
+      "step": 515,
+      "student_loss": 0.005790602881461382,
+      "teacher_loss": 0.0001912783191073686
+    },
+    {
+      "epoch": 0.14994232987312572,
+      "grad_norm": 1.9921875,
+      "kd_loss": 0.03539569675922394,
+      "learning_rate": 4.935226705620699e-06,
+      "loss": 0.0397,
+      "step": 520,
+      "student_loss": 0.04242030531167984,
+      "teacher_loss": 0.011500299908220768
+    },
+    {
+      "epoch": 0.1513840830449827,
+      "grad_norm": 0.67578125,
+      "kd_loss": 0.018779262900352478,
+      "learning_rate": 4.8542766486612035e-06,
+      "loss": 0.0403,
+      "step": 525,
+      "student_loss": 0.00041962284012697637,
+      "teacher_loss": 0.00021298698266036808
+    },
+    {
+      "epoch": 0.15282583621683968,
+      "grad_norm": 1.2421875,
+      "kd_loss": 0.01180377509444952,
+      "learning_rate": 4.773364805125025e-06,
+      "loss": 0.0351,
+      "step": 530,
+      "student_loss": 0.00039459849358536303,
+      "teacher_loss": 0.0003135094593744725
+    },
+    {
+      "epoch": 0.15426758938869667,
+      "grad_norm": 0.96484375,
+      "kd_loss": 0.022030461579561234,
+      "learning_rate": 4.6925123927408265e-06,
+      "loss": 0.0343,
+      "step": 535,
+      "student_loss": 0.000637000659480691,
+      "teacher_loss": 0.00034665301791392267
+    },
+    {
+      "epoch": 0.15570934256055363,
+      "grad_norm": 1.234375,
+      "kd_loss": 0.01367215160280466,
+      "learning_rate": 4.611740613652485e-06,
+      "loss": 0.0333,
+      "step": 540,
+      "student_loss": 0.0006559583125635982,
+      "teacher_loss": 0.0003204621316399425
+    },
+    {
+      "epoch": 0.15715109573241062,
+      "grad_norm": 2.234375,
+      "kd_loss": 0.00888274796307087,
+      "learning_rate": 4.531070648859186e-06,
+      "loss": 0.0319,
+      "step": 545,
+      "student_loss": 0.01682436652481556,
+      "teacher_loss": 0.013372495770454407
+    },
+    {
+      "epoch": 0.15859284890426759,
+      "grad_norm": 1.640625,
+      "kd_loss": 0.026771951466798782,
+      "learning_rate": 4.450523652661086e-06,
+      "loss": 0.0306,
+      "step": 550,
+      "student_loss": 0.0001725157053442672,
+      "teacher_loss": 0.012681440450251102
+    },
+    {
+      "epoch": 0.16003460207612458,
+      "grad_norm": 1.1015625,
+      "kd_loss": 0.03767453879117966,
+      "learning_rate": 4.370120747111956e-06,
+      "loss": 0.0381,
+      "step": 555,
+      "student_loss": 0.009898228570818901,
+      "teacher_loss": 0.0022960191126912832
+    },
+    {
+      "epoch": 0.16147635524798154,
+      "grad_norm": 1.734375,
+      "kd_loss": 0.0351857915520668,
+      "learning_rate": 4.289883016480291e-06,
+      "loss": 0.0381,
+      "step": 560,
+      "student_loss": 0.027657803148031235,
+      "teacher_loss": 0.00034597894409671426
+    },
+    {
+      "epoch": 0.16291810841983853,
+      "grad_norm": 1.4296875,
+      "kd_loss": 0.019546959549188614,
+      "learning_rate": 4.209831501720328e-06,
+      "loss": 0.0346,
+      "step": 565,
+      "student_loss": 0.028599649667739868,
+      "teacher_loss": 0.018787631765007973
+    },
+    {
+      "epoch": 0.1643598615916955,
+      "grad_norm": 1.5625,
+      "kd_loss": 0.020644016563892365,
+      "learning_rate": 4.129987194954421e-06,
+      "loss": 0.0405,
+      "step": 570,
+      "student_loss": 0.010047786869108677,
+      "teacher_loss": 0.006790643557906151
+    },
+    {
+      "epoch": 0.16580161476355249,
+      "grad_norm": 1.4921875,
+      "kd_loss": 0.01332971639931202,
+      "learning_rate": 4.050371033968216e-06,
+      "loss": 0.0376,
+      "step": 575,
+      "student_loss": 0.0004119194345548749,
+      "teacher_loss": 0.00025748086045496166
+    },
+    {
+      "epoch": 0.16724336793540945,
+      "grad_norm": 1.3515625,
+      "kd_loss": 0.012037251144647598,
+      "learning_rate": 3.9710038967200825e-06,
+      "loss": 0.0342,
+      "step": 580,
+      "student_loss": 0.0030028573237359524,
+      "teacher_loss": 0.0012405890738591552
+    },
+    {
+      "epoch": 0.16868512110726644,
+      "grad_norm": 0.88671875,
+      "kd_loss": 0.01703016459941864,
+      "learning_rate": 3.89190659586623e-06,
+      "loss": 0.032,
+      "step": 585,
+      "student_loss": 0.0007975402986630797,
+      "teacher_loss": 0.0002710323315113783
+    },
+    {
+      "epoch": 0.1701268742791234,
+      "grad_norm": 1.1171875,
+      "kd_loss": 0.01272827759385109,
+      "learning_rate": 3.8130998733029517e-06,
+      "loss": 0.035,
+      "step": 590,
+      "student_loss": 0.000885407323949039,
+      "teacher_loss": 0.00043826864566653967
+    },
+    {
+      "epoch": 0.1715686274509804,
+      "grad_norm": 1.3828125,
+      "kd_loss": 0.009466774761676788,
+      "learning_rate": 3.734604394727419e-06,
+      "loss": 0.0345,
+      "step": 595,
+      "student_loss": 0.0005723866051994264,
+      "teacher_loss": 0.0005249618552625179
+    },
+    {
+      "epoch": 0.17301038062283736,
+      "grad_norm": 1.4765625,
+      "kd_loss": 0.020295076072216034,
+      "learning_rate": 3.656440744218464e-06,
+      "loss": 0.04,
+      "step": 600,
+      "student_loss": 0.04926498606801033,
+      "teacher_loss": 0.00894973799586296
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 1000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 200,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoints/codi1.5b_a1.0_b1.0_g1.0_ls2/checkpoint-800/added_tokens.json

@@ -0,0 +1,35 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|action_sep|>": 151670,
+  "<|arg_sep|>": 151671,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|call_sep|>": 151666,
+  "<|end_of_text|>": 151673,
+  "<|endoftext|>": 151643,
+  "<|exception_sep|>": 151669,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|frame_sep|>": 151672,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|latent_end|>": 151675,
+  "<|latent_start|>": 151674,
+  "<|line_sep|>": 151667,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|return_sep|>": 151668,
+  "<|trace_context_start|>": 151665,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

checkpoints/codi1.5b_a1.0_b1.0_g1.0_ls2/checkpoint-800/chat_template.jinja

@@ -0,0 +1,54 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
+    {%- endif %}
+    {{- "\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>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\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" }}
+{%- else %}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
+    {%- else %}
+        {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role }}
+        {%- if message.content %}
+            {{- '\n' + message.content }}
+        {%- endif %}
+        {%- for tool_call in message.tool_calls %}
+            {%- if tool_call.function is defined %}
+                {%- set tool_call = tool_call.function %}
+            {%- endif %}
+            {{- '\n<tool_call>\n{"name": "' }}
+            {{- tool_call.name }}
+            {{- '", "arguments": ' }}
+            {{- tool_call.arguments | tojson }}
+            {{- '}\n</tool_call>' }}
+        {%- endfor %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}

checkpoints/codi1.5b_a1.0_b1.0_g1.0_ls2/checkpoint-800/config.json

@@ -0,0 +1,58 @@
+{
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "dtype": "bfloat16",
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 1536,
+  "initializer_range": 0.02,
+  "intermediate_size": 8960,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 2,
+  "pad_token_id": 151643,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "transformers_version": "4.57.6",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151676
+}

checkpoints/codi1.5b_a1.0_b1.0_g1.0_ls2/checkpoint-800/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:660adf38ba4f7e0e04fe43e4f496edca9831d68d262d9fb06c3fa4aff27cad64
+size 3096275515