Upload 14 files

.gitattributes

@@ -34,3 +34,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 checkpoint-200/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-400/tokenizer.json filter=lfs diff=lfs merge=lfs -text

checkpoint-400/added_tokens.json

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

checkpoint-400/config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "Qwen/Qwen2.5-0.5B-Instruct",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 896,
+  "initializer_range": 0.02,
+  "intermediate_size": 4864,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 21,
+  "model_type": "qwen2",
+  "num_attention_heads": 14,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 2,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.48.3",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

checkpoint-400/generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.1,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.48.3"
+}

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

checkpoint-400/tokenizer_config.json

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

checkpoint-400/trainer_state.json

@@ -0,0 +1,3251 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.028019298291698407,
+  "eval_steps": 200,
+  "global_step": 400,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 7.004824572924602e-05,
+      "grad_norm": 6.222772121429443,
+      "learning_rate": 9.99930017513135e-05,
+      "loss": 1.1076,
+      "num_input_tokens_seen": 16384,
+      "step": 1
+    },
+    {
+      "epoch": 0.00014009649145849205,
+      "grad_norm": 6.042057037353516,
+      "learning_rate": 9.998600350262697e-05,
+      "loss": 1.1086,
+      "num_input_tokens_seen": 32768,
+      "step": 2
+    },
+    {
+      "epoch": 0.00021014473718773804,
+      "grad_norm": 7.119229316711426,
+      "learning_rate": 9.997900525394046e-05,
+      "loss": 1.4047,
+      "num_input_tokens_seen": 49152,
+      "step": 3
+    },
+    {
+      "epoch": 0.0002801929829169841,
+      "grad_norm": 7.133191108703613,
+      "learning_rate": 9.997200700525395e-05,
+      "loss": 1.3921,
+      "num_input_tokens_seen": 65536,
+      "step": 4
+    },
+    {
+      "epoch": 0.0003502412286462301,
+      "grad_norm": 6.1078338623046875,
+      "learning_rate": 9.996500875656743e-05,
+      "loss": 1.3171,
+      "num_input_tokens_seen": 81920,
+      "step": 5
+    },
+    {
+      "epoch": 0.0004202894743754761,
+      "grad_norm": 6.466420650482178,
+      "learning_rate": 9.995801050788092e-05,
+      "loss": 1.0732,
+      "num_input_tokens_seen": 97344,
+      "step": 6
+    },
+    {
+      "epoch": 0.0004903377201047221,
+      "grad_norm": 5.578189849853516,
+      "learning_rate": 9.99510122591944e-05,
+      "loss": 0.9929,
+      "num_input_tokens_seen": 113728,
+      "step": 7
+    },
+    {
+      "epoch": 0.0005603859658339682,
+      "grad_norm": 7.197720527648926,
+      "learning_rate": 9.994401401050789e-05,
+      "loss": 1.2512,
+      "num_input_tokens_seen": 129528,
+      "step": 8
+    },
+    {
+      "epoch": 0.0006304342115632141,
+      "grad_norm": 6.618913650512695,
+      "learning_rate": 9.993701576182136e-05,
+      "loss": 1.3495,
+      "num_input_tokens_seen": 145704,
+      "step": 9
+    },
+    {
+      "epoch": 0.0007004824572924602,
+      "grad_norm": 6.955508232116699,
+      "learning_rate": 9.993001751313485e-05,
+      "loss": 1.1823,
+      "num_input_tokens_seen": 161664,
+      "step": 10
+    },
+    {
+      "epoch": 0.0007705307030217062,
+      "grad_norm": 6.6807074546813965,
+      "learning_rate": 9.992301926444835e-05,
+      "loss": 1.1693,
+      "num_input_tokens_seen": 177960,
+      "step": 11
+    },
+    {
+      "epoch": 0.0008405789487509522,
+      "grad_norm": 6.784447193145752,
+      "learning_rate": 9.991602101576183e-05,
+      "loss": 1.3744,
+      "num_input_tokens_seen": 194344,
+      "step": 12
+    },
+    {
+      "epoch": 0.0009106271944801982,
+      "grad_norm": 6.7418437004089355,
+      "learning_rate": 9.990902276707532e-05,
+      "loss": 1.22,
+      "num_input_tokens_seen": 210728,
+      "step": 13
+    },
+    {
+      "epoch": 0.0009806754402094443,
+      "grad_norm": 6.43395471572876,
+      "learning_rate": 9.990202451838879e-05,
+      "loss": 1.1772,
+      "num_input_tokens_seen": 227112,
+      "step": 14
+    },
+    {
+      "epoch": 0.0010507236859386903,
+      "grad_norm": 6.09422492980957,
+      "learning_rate": 9.989502626970228e-05,
+      "loss": 1.195,
+      "num_input_tokens_seen": 243496,
+      "step": 15
+    },
+    {
+      "epoch": 0.0011207719316679364,
+      "grad_norm": 6.238271236419678,
+      "learning_rate": 9.988802802101577e-05,
+      "loss": 1.2623,
+      "num_input_tokens_seen": 259744,
+      "step": 16
+    },
+    {
+      "epoch": 0.0011908201773971822,
+      "grad_norm": 6.56187629699707,
+      "learning_rate": 9.988102977232926e-05,
+      "loss": 1.2721,
+      "num_input_tokens_seen": 276128,
+      "step": 17
+    },
+    {
+      "epoch": 0.0012608684231264283,
+      "grad_norm": 6.818358898162842,
+      "learning_rate": 9.987403152364275e-05,
+      "loss": 1.2649,
+      "num_input_tokens_seen": 292512,
+      "step": 18
+    },
+    {
+      "epoch": 0.0013309166688556743,
+      "grad_norm": 5.950352191925049,
+      "learning_rate": 9.986703327495622e-05,
+      "loss": 1.0024,
+      "num_input_tokens_seen": 308632,
+      "step": 19
+    },
+    {
+      "epoch": 0.0014009649145849204,
+      "grad_norm": 6.387479305267334,
+      "learning_rate": 9.986003502626971e-05,
+      "loss": 1.2783,
+      "num_input_tokens_seen": 325016,
+      "step": 20
+    },
+    {
+      "epoch": 0.0014710131603141664,
+      "grad_norm": 6.187346458435059,
+      "learning_rate": 9.985303677758318e-05,
+      "loss": 1.1701,
+      "num_input_tokens_seen": 341384,
+      "step": 21
+    },
+    {
+      "epoch": 0.0015410614060434125,
+      "grad_norm": 5.371951103210449,
+      "learning_rate": 9.984603852889667e-05,
+      "loss": 1.0483,
+      "num_input_tokens_seen": 357768,
+      "step": 22
+    },
+    {
+      "epoch": 0.0016111096517726585,
+      "grad_norm": 6.2206807136535645,
+      "learning_rate": 9.983904028021016e-05,
+      "loss": 1.2516,
+      "num_input_tokens_seen": 374152,
+      "step": 23
+    },
+    {
+      "epoch": 0.0016811578975019044,
+      "grad_norm": 6.121264457702637,
+      "learning_rate": 9.983204203152365e-05,
+      "loss": 1.1506,
+      "num_input_tokens_seen": 390536,
+      "step": 24
+    },
+    {
+      "epoch": 0.0017512061432311504,
+      "grad_norm": 6.353756904602051,
+      "learning_rate": 9.982504378283714e-05,
+      "loss": 1.3118,
+      "num_input_tokens_seen": 406920,
+      "step": 25
+    },
+    {
+      "epoch": 0.0018212543889603965,
+      "grad_norm": 6.270686149597168,
+      "learning_rate": 9.981804553415061e-05,
+      "loss": 1.0883,
+      "num_input_tokens_seen": 422728,
+      "step": 26
+    },
+    {
+      "epoch": 0.0018913026346896425,
+      "grad_norm": 6.117632865905762,
+      "learning_rate": 9.98110472854641e-05,
+      "loss": 1.3346,
+      "num_input_tokens_seen": 439112,
+      "step": 27
+    },
+    {
+      "epoch": 0.0019613508804188886,
+      "grad_norm": 6.429015159606934,
+      "learning_rate": 9.980404903677759e-05,
+      "loss": 1.2494,
+      "num_input_tokens_seen": 455144,
+      "step": 28
+    },
+    {
+      "epoch": 0.0020313991261481346,
+      "grad_norm": 6.4467620849609375,
+      "learning_rate": 9.979705078809107e-05,
+      "loss": 1.3335,
+      "num_input_tokens_seen": 470360,
+      "step": 29
+    },
+    {
+      "epoch": 0.0021014473718773807,
+      "grad_norm": 6.57926082611084,
+      "learning_rate": 9.979005253940455e-05,
+      "loss": 1.2126,
+      "num_input_tokens_seen": 486120,
+      "step": 30
+    },
+    {
+      "epoch": 0.0021714956176066267,
+      "grad_norm": 5.650569915771484,
+      "learning_rate": 9.978305429071804e-05,
+      "loss": 1.1363,
+      "num_input_tokens_seen": 501896,
+      "step": 31
+    },
+    {
+      "epoch": 0.0022415438633358728,
+      "grad_norm": 6.380292892456055,
+      "learning_rate": 9.977605604203153e-05,
+      "loss": 1.2251,
+      "num_input_tokens_seen": 517752,
+      "step": 32
+    },
+    {
+      "epoch": 0.002311592109065119,
+      "grad_norm": 5.704173564910889,
+      "learning_rate": 9.976905779334502e-05,
+      "loss": 1.1685,
+      "num_input_tokens_seen": 534136,
+      "step": 33
+    },
+    {
+      "epoch": 0.0023816403547943644,
+      "grad_norm": 5.342978000640869,
+      "learning_rate": 9.97620595446585e-05,
+      "loss": 1.2012,
+      "num_input_tokens_seen": 550216,
+      "step": 34
+    },
+    {
+      "epoch": 0.0024516886005236105,
+      "grad_norm": 5.7014241218566895,
+      "learning_rate": 9.975506129597198e-05,
+      "loss": 1.2342,
+      "num_input_tokens_seen": 566600,
+      "step": 35
+    },
+    {
+      "epoch": 0.0025217368462528565,
+      "grad_norm": 6.26229190826416,
+      "learning_rate": 9.974806304728546e-05,
+      "loss": 1.2041,
+      "num_input_tokens_seen": 582984,
+      "step": 36
+    },
+    {
+      "epoch": 0.0025917850919821026,
+      "grad_norm": 6.583463191986084,
+      "learning_rate": 9.974106479859896e-05,
+      "loss": 1.3021,
+      "num_input_tokens_seen": 598968,
+      "step": 37
+    },
+    {
+      "epoch": 0.0026618333377113486,
+      "grad_norm": 5.58498477935791,
+      "learning_rate": 9.973406654991245e-05,
+      "loss": 1.1622,
+      "num_input_tokens_seen": 614840,
+      "step": 38
+    },
+    {
+      "epoch": 0.0027318815834405947,
+      "grad_norm": 5.906906604766846,
+      "learning_rate": 9.972706830122592e-05,
+      "loss": 1.1971,
+      "num_input_tokens_seen": 631224,
+      "step": 39
+    },
+    {
+      "epoch": 0.0028019298291698407,
+      "grad_norm": 5.962359428405762,
+      "learning_rate": 9.972007005253941e-05,
+      "loss": 1.1326,
+      "num_input_tokens_seen": 647000,
+      "step": 40
+    },
+    {
+      "epoch": 0.002871978074899087,
+      "grad_norm": 6.447500705718994,
+      "learning_rate": 9.971307180385289e-05,
+      "loss": 1.0905,
+      "num_input_tokens_seen": 662480,
+      "step": 41
+    },
+    {
+      "epoch": 0.002942026320628333,
+      "grad_norm": 5.7290520668029785,
+      "learning_rate": 9.970607355516638e-05,
+      "loss": 1.3585,
+      "num_input_tokens_seen": 678480,
+      "step": 42
+    },
+    {
+      "epoch": 0.003012074566357579,
+      "grad_norm": 6.063445568084717,
+      "learning_rate": 9.969907530647987e-05,
+      "loss": 1.2841,
+      "num_input_tokens_seen": 694256,
+      "step": 43
+    },
+    {
+      "epoch": 0.003082122812086825,
+      "grad_norm": 5.302809238433838,
+      "learning_rate": 9.969207705779335e-05,
+      "loss": 1.1168,
+      "num_input_tokens_seen": 710152,
+      "step": 44
+    },
+    {
+      "epoch": 0.003152171057816071,
+      "grad_norm": 5.634128093719482,
+      "learning_rate": 9.968507880910684e-05,
+      "loss": 1.0609,
+      "num_input_tokens_seen": 726184,
+      "step": 45
+    },
+    {
+      "epoch": 0.003222219303545317,
+      "grad_norm": 5.652642726898193,
+      "learning_rate": 9.967808056042032e-05,
+      "loss": 1.2228,
+      "num_input_tokens_seen": 742520,
+      "step": 46
+    },
+    {
+      "epoch": 0.0032922675492745627,
+      "grad_norm": 5.340751647949219,
+      "learning_rate": 9.96710823117338e-05,
+      "loss": 1.0595,
+      "num_input_tokens_seen": 758904,
+      "step": 47
+    },
+    {
+      "epoch": 0.0033623157950038087,
+      "grad_norm": 5.422239780426025,
+      "learning_rate": 9.966408406304728e-05,
+      "loss": 1.1161,
+      "num_input_tokens_seen": 775040,
+      "step": 48
+    },
+    {
+      "epoch": 0.0034323640407330548,
+      "grad_norm": 5.29241418838501,
+      "learning_rate": 9.965708581436077e-05,
+      "loss": 1.0255,
+      "num_input_tokens_seen": 790856,
+      "step": 49
+    },
+    {
+      "epoch": 0.003502412286462301,
+      "grad_norm": 5.146270275115967,
+      "learning_rate": 9.965008756567426e-05,
+      "loss": 0.9762,
+      "num_input_tokens_seen": 807064,
+      "step": 50
+    },
+    {
+      "epoch": 0.003572460532191547,
+      "grad_norm": 5.825758457183838,
+      "learning_rate": 9.964308931698775e-05,
+      "loss": 1.2108,
+      "num_input_tokens_seen": 823448,
+      "step": 51
+    },
+    {
+      "epoch": 0.003642508777920793,
+      "grad_norm": 6.179538726806641,
+      "learning_rate": 9.963609106830124e-05,
+      "loss": 1.322,
+      "num_input_tokens_seen": 838888,
+      "step": 52
+    },
+    {
+      "epoch": 0.003712557023650039,
+      "grad_norm": 6.464454174041748,
+      "learning_rate": 9.962909281961471e-05,
+      "loss": 1.5077,
+      "num_input_tokens_seen": 855272,
+      "step": 53
+    },
+    {
+      "epoch": 0.003782605269379285,
+      "grad_norm": 5.4227294921875,
+      "learning_rate": 9.96220945709282e-05,
+      "loss": 1.2679,
+      "num_input_tokens_seen": 871656,
+      "step": 54
+    },
+    {
+      "epoch": 0.003852653515108531,
+      "grad_norm": 5.949041366577148,
+      "learning_rate": 9.961509632224169e-05,
+      "loss": 1.3618,
+      "num_input_tokens_seen": 888040,
+      "step": 55
+    },
+    {
+      "epoch": 0.003922701760837777,
+      "grad_norm": 6.050904750823975,
+      "learning_rate": 9.960809807355516e-05,
+      "loss": 1.3155,
+      "num_input_tokens_seen": 904400,
+      "step": 56
+    },
+    {
+      "epoch": 0.003992750006567023,
+      "grad_norm": 6.048308849334717,
+      "learning_rate": 9.960109982486866e-05,
+      "loss": 1.3131,
+      "num_input_tokens_seen": 919952,
+      "step": 57
+    },
+    {
+      "epoch": 0.004062798252296269,
+      "grad_norm": 5.683863162994385,
+      "learning_rate": 9.959410157618214e-05,
+      "loss": 1.1692,
+      "num_input_tokens_seen": 936336,
+      "step": 58
+    },
+    {
+      "epoch": 0.004132846498025515,
+      "grad_norm": 5.449287414550781,
+      "learning_rate": 9.958710332749563e-05,
+      "loss": 1.0613,
+      "num_input_tokens_seen": 952152,
+      "step": 59
+    },
+    {
+      "epoch": 0.004202894743754761,
+      "grad_norm": 5.31496524810791,
+      "learning_rate": 9.958010507880912e-05,
+      "loss": 0.9605,
+      "num_input_tokens_seen": 967824,
+      "step": 60
+    },
+    {
+      "epoch": 0.004272942989484007,
+      "grad_norm": 5.57105016708374,
+      "learning_rate": 9.957310683012259e-05,
+      "loss": 1.1701,
+      "num_input_tokens_seen": 983864,
+      "step": 61
+    },
+    {
+      "epoch": 0.004342991235213253,
+      "grad_norm": 5.3456830978393555,
+      "learning_rate": 9.956610858143608e-05,
+      "loss": 1.0995,
+      "num_input_tokens_seen": 1000248,
+      "step": 62
+    },
+    {
+      "epoch": 0.004413039480942499,
+      "grad_norm": 5.453295707702637,
+      "learning_rate": 9.955911033274957e-05,
+      "loss": 1.2413,
+      "num_input_tokens_seen": 1016632,
+      "step": 63
+    },
+    {
+      "epoch": 0.0044830877266717455,
+      "grad_norm": 4.975449562072754,
+      "learning_rate": 9.955211208406306e-05,
+      "loss": 1.0961,
+      "num_input_tokens_seen": 1033016,
+      "step": 64
+    },
+    {
+      "epoch": 0.004553135972400991,
+      "grad_norm": 5.542137145996094,
+      "learning_rate": 9.954511383537655e-05,
+      "loss": 1.1171,
+      "num_input_tokens_seen": 1049400,
+      "step": 65
+    },
+    {
+      "epoch": 0.004623184218130238,
+      "grad_norm": 5.213950157165527,
+      "learning_rate": 9.953811558669002e-05,
+      "loss": 1.2228,
+      "num_input_tokens_seen": 1065784,
+      "step": 66
+    },
+    {
+      "epoch": 0.004693232463859483,
+      "grad_norm": 5.496099948883057,
+      "learning_rate": 9.953111733800351e-05,
+      "loss": 1.1529,
+      "num_input_tokens_seen": 1082168,
+      "step": 67
+    },
+    {
+      "epoch": 0.004763280709588729,
+      "grad_norm": 5.64145565032959,
+      "learning_rate": 9.952411908931698e-05,
+      "loss": 1.2301,
+      "num_input_tokens_seen": 1098024,
+      "step": 68
+    },
+    {
+      "epoch": 0.004833328955317975,
+      "grad_norm": 5.566709995269775,
+      "learning_rate": 9.951712084063047e-05,
+      "loss": 1.2679,
+      "num_input_tokens_seen": 1114408,
+      "step": 69
+    },
+    {
+      "epoch": 0.004903377201047221,
+      "grad_norm": 6.443673133850098,
+      "learning_rate": 9.951012259194396e-05,
+      "loss": 1.2313,
+      "num_input_tokens_seen": 1130792,
+      "step": 70
+    },
+    {
+      "epoch": 0.0049734254467764675,
+      "grad_norm": 5.882962226867676,
+      "learning_rate": 9.950312434325745e-05,
+      "loss": 1.4304,
+      "num_input_tokens_seen": 1147176,
+      "step": 71
+    },
+    {
+      "epoch": 0.005043473692505713,
+      "grad_norm": 6.0052666664123535,
+      "learning_rate": 9.949612609457094e-05,
+      "loss": 1.3027,
+      "num_input_tokens_seen": 1160968,
+      "step": 72
+    },
+    {
+      "epoch": 0.0051135219382349596,
+      "grad_norm": 5.260256767272949,
+      "learning_rate": 9.948912784588441e-05,
+      "loss": 1.1526,
+      "num_input_tokens_seen": 1177352,
+      "step": 73
+    },
+    {
+      "epoch": 0.005183570183964205,
+      "grad_norm": 5.641814708709717,
+      "learning_rate": 9.94821295971979e-05,
+      "loss": 1.0666,
+      "num_input_tokens_seen": 1193032,
+      "step": 74
+    },
+    {
+      "epoch": 0.005253618429693452,
+      "grad_norm": 5.121115207672119,
+      "learning_rate": 9.947513134851138e-05,
+      "loss": 1.2404,
+      "num_input_tokens_seen": 1208952,
+      "step": 75
+    },
+    {
+      "epoch": 0.005323666675422697,
+      "grad_norm": 5.63930082321167,
+      "learning_rate": 9.946813309982487e-05,
+      "loss": 1.5127,
+      "num_input_tokens_seen": 1225000,
+      "step": 76
+    },
+    {
+      "epoch": 0.005393714921151944,
+      "grad_norm": 4.880716800689697,
+      "learning_rate": 9.946113485113837e-05,
+      "loss": 1.1484,
+      "num_input_tokens_seen": 1241384,
+      "step": 77
+    },
+    {
+      "epoch": 0.005463763166881189,
+      "grad_norm": 5.59611177444458,
+      "learning_rate": 9.945413660245184e-05,
+      "loss": 1.1678,
+      "num_input_tokens_seen": 1257680,
+      "step": 78
+    },
+    {
+      "epoch": 0.005533811412610436,
+      "grad_norm": 5.052026271820068,
+      "learning_rate": 9.944713835376533e-05,
+      "loss": 1.2207,
+      "num_input_tokens_seen": 1274064,
+      "step": 79
+    },
+    {
+      "epoch": 0.0056038596583396815,
+      "grad_norm": 5.285096168518066,
+      "learning_rate": 9.944014010507881e-05,
+      "loss": 1.1457,
+      "num_input_tokens_seen": 1290448,
+      "step": 80
+    },
+    {
+      "epoch": 0.005673907904068927,
+      "grad_norm": 5.4286580085754395,
+      "learning_rate": 9.94331418563923e-05,
+      "loss": 1.3047,
+      "num_input_tokens_seen": 1306832,
+      "step": 81
+    },
+    {
+      "epoch": 0.005743956149798174,
+      "grad_norm": 5.937953472137451,
+      "learning_rate": 9.942614360770578e-05,
+      "loss": 1.4353,
+      "num_input_tokens_seen": 1323216,
+      "step": 82
+    },
+    {
+      "epoch": 0.005814004395527419,
+      "grad_norm": 5.129006385803223,
+      "learning_rate": 9.941914535901927e-05,
+      "loss": 1.1434,
+      "num_input_tokens_seen": 1339408,
+      "step": 83
+    },
+    {
+      "epoch": 0.005884052641256666,
+      "grad_norm": 5.179675102233887,
+      "learning_rate": 9.941214711033276e-05,
+      "loss": 1.2452,
+      "num_input_tokens_seen": 1355792,
+      "step": 84
+    },
+    {
+      "epoch": 0.005954100886985911,
+      "grad_norm": 4.912832736968994,
+      "learning_rate": 9.940514886164624e-05,
+      "loss": 1.1255,
+      "num_input_tokens_seen": 1372176,
+      "step": 85
+    },
+    {
+      "epoch": 0.006024149132715158,
+      "grad_norm": 5.190899848937988,
+      "learning_rate": 9.939815061295973e-05,
+      "loss": 1.2543,
+      "num_input_tokens_seen": 1388560,
+      "step": 86
+    },
+    {
+      "epoch": 0.006094197378444403,
+      "grad_norm": 5.1751275062561035,
+      "learning_rate": 9.939115236427321e-05,
+      "loss": 1.3145,
+      "num_input_tokens_seen": 1404944,
+      "step": 87
+    },
+    {
+      "epoch": 0.00616424562417365,
+      "grad_norm": 5.450705528259277,
+      "learning_rate": 9.938415411558669e-05,
+      "loss": 1.2844,
+      "num_input_tokens_seen": 1421328,
+      "step": 88
+    },
+    {
+      "epoch": 0.0062342938699028955,
+      "grad_norm": 5.593935012817383,
+      "learning_rate": 9.937715586690018e-05,
+      "loss": 1.3284,
+      "num_input_tokens_seen": 1437464,
+      "step": 89
+    },
+    {
+      "epoch": 0.006304342115632142,
+      "grad_norm": 5.156428813934326,
+      "learning_rate": 9.937015761821367e-05,
+      "loss": 1.1682,
+      "num_input_tokens_seen": 1452952,
+      "step": 90
+    },
+    {
+      "epoch": 0.006374390361361388,
+      "grad_norm": 4.673638820648193,
+      "learning_rate": 9.936315936952715e-05,
+      "loss": 1.004,
+      "num_input_tokens_seen": 1469336,
+      "step": 91
+    },
+    {
+      "epoch": 0.006444438607090634,
+      "grad_norm": 4.996700763702393,
+      "learning_rate": 9.935616112084064e-05,
+      "loss": 1.087,
+      "num_input_tokens_seen": 1485448,
+      "step": 92
+    },
+    {
+      "epoch": 0.00651448685281988,
+      "grad_norm": 4.817474365234375,
+      "learning_rate": 9.934916287215412e-05,
+      "loss": 1.151,
+      "num_input_tokens_seen": 1501472,
+      "step": 93
+    },
+    {
+      "epoch": 0.006584535098549125,
+      "grad_norm": 5.400479316711426,
+      "learning_rate": 9.934216462346761e-05,
+      "loss": 1.3144,
+      "num_input_tokens_seen": 1516424,
+      "step": 94
+    },
+    {
+      "epoch": 0.006654583344278372,
+      "grad_norm": 5.232216835021973,
+      "learning_rate": 9.933516637478108e-05,
+      "loss": 1.0019,
+      "num_input_tokens_seen": 1532792,
+      "step": 95
+    },
+    {
+      "epoch": 0.006724631590007617,
+      "grad_norm": 5.392521381378174,
+      "learning_rate": 9.932816812609457e-05,
+      "loss": 1.3195,
+      "num_input_tokens_seen": 1548600,
+      "step": 96
+    },
+    {
+      "epoch": 0.006794679835736864,
+      "grad_norm": 5.5280866622924805,
+      "learning_rate": 9.932116987740806e-05,
+      "loss": 1.283,
+      "num_input_tokens_seen": 1564088,
+      "step": 97
+    },
+    {
+      "epoch": 0.0068647280814661095,
+      "grad_norm": 4.963179588317871,
+      "learning_rate": 9.931417162872155e-05,
+      "loss": 1.2716,
+      "num_input_tokens_seen": 1580040,
+      "step": 98
+    },
+    {
+      "epoch": 0.006934776327195356,
+      "grad_norm": 4.920302391052246,
+      "learning_rate": 9.930717338003504e-05,
+      "loss": 1.088,
+      "num_input_tokens_seen": 1595880,
+      "step": 99
+    },
+    {
+      "epoch": 0.007004824572924602,
+      "grad_norm": 4.935486793518066,
+      "learning_rate": 9.930017513134851e-05,
+      "loss": 1.0122,
+      "num_input_tokens_seen": 1611864,
+      "step": 100
+    },
+    {
+      "epoch": 0.007074872818653848,
+      "grad_norm": 5.099087238311768,
+      "learning_rate": 9.9293176882662e-05,
+      "loss": 1.1605,
+      "num_input_tokens_seen": 1627472,
+      "step": 101
+    },
+    {
+      "epoch": 0.007144921064383094,
+      "grad_norm": 5.3764328956604,
+      "learning_rate": 9.928617863397548e-05,
+      "loss": 1.2225,
+      "num_input_tokens_seen": 1643856,
+      "step": 102
+    },
+    {
+      "epoch": 0.00721496931011234,
+      "grad_norm": 5.281564712524414,
+      "learning_rate": 9.927918038528898e-05,
+      "loss": 1.1483,
+      "num_input_tokens_seen": 1660240,
+      "step": 103
+    },
+    {
+      "epoch": 0.007285017555841586,
+      "grad_norm": 5.395167827606201,
+      "learning_rate": 9.927218213660247e-05,
+      "loss": 1.6014,
+      "num_input_tokens_seen": 1676624,
+      "step": 104
+    },
+    {
+      "epoch": 0.007355065801570832,
+      "grad_norm": 5.322319507598877,
+      "learning_rate": 9.926518388791594e-05,
+      "loss": 1.0933,
+      "num_input_tokens_seen": 1693008,
+      "step": 105
+    },
+    {
+      "epoch": 0.007425114047300078,
+      "grad_norm": 5.301229953765869,
+      "learning_rate": 9.925818563922943e-05,
+      "loss": 1.1998,
+      "num_input_tokens_seen": 1708424,
+      "step": 106
+    },
+    {
+      "epoch": 0.0074951622930293236,
+      "grad_norm": 4.958597183227539,
+      "learning_rate": 9.92511873905429e-05,
+      "loss": 1.3285,
+      "num_input_tokens_seen": 1724808,
+      "step": 107
+    },
+    {
+      "epoch": 0.00756521053875857,
+      "grad_norm": 4.3913960456848145,
+      "learning_rate": 9.924418914185639e-05,
+      "loss": 0.9017,
+      "num_input_tokens_seen": 1740752,
+      "step": 108
+    },
+    {
+      "epoch": 0.007635258784487816,
+      "grad_norm": 5.401021480560303,
+      "learning_rate": 9.923719089316988e-05,
+      "loss": 1.3646,
+      "num_input_tokens_seen": 1755176,
+      "step": 109
+    },
+    {
+      "epoch": 0.007705307030217062,
+      "grad_norm": 4.894444942474365,
+      "learning_rate": 9.923019264448337e-05,
+      "loss": 0.9955,
+      "num_input_tokens_seen": 1771560,
+      "step": 110
+    },
+    {
+      "epoch": 0.007775355275946308,
+      "grad_norm": 4.878688335418701,
+      "learning_rate": 9.922319439579686e-05,
+      "loss": 1.1766,
+      "num_input_tokens_seen": 1787944,
+      "step": 111
+    },
+    {
+      "epoch": 0.007845403521675554,
+      "grad_norm": 4.9379777908325195,
+      "learning_rate": 9.921619614711033e-05,
+      "loss": 1.1631,
+      "num_input_tokens_seen": 1803568,
+      "step": 112
+    },
+    {
+      "epoch": 0.0079154517674048,
+      "grad_norm": 5.101811408996582,
+      "learning_rate": 9.920919789842382e-05,
+      "loss": 1.2165,
+      "num_input_tokens_seen": 1819952,
+      "step": 113
+    },
+    {
+      "epoch": 0.007985500013134045,
+      "grad_norm": 5.32574987411499,
+      "learning_rate": 9.920219964973731e-05,
+      "loss": 1.3012,
+      "num_input_tokens_seen": 1835296,
+      "step": 114
+    },
+    {
+      "epoch": 0.008055548258863293,
+      "grad_norm": 5.2391180992126465,
+      "learning_rate": 9.919520140105079e-05,
+      "loss": 1.2451,
+      "num_input_tokens_seen": 1851224,
+      "step": 115
+    },
+    {
+      "epoch": 0.008125596504592538,
+      "grad_norm": 4.865017890930176,
+      "learning_rate": 9.918820315236427e-05,
+      "loss": 1.1683,
+      "num_input_tokens_seen": 1867608,
+      "step": 116
+    },
+    {
+      "epoch": 0.008195644750321784,
+      "grad_norm": 4.943136215209961,
+      "learning_rate": 9.918120490367776e-05,
+      "loss": 1.31,
+      "num_input_tokens_seen": 1883696,
+      "step": 117
+    },
+    {
+      "epoch": 0.00826569299605103,
+      "grad_norm": 4.769871711730957,
+      "learning_rate": 9.917420665499125e-05,
+      "loss": 1.1212,
+      "num_input_tokens_seen": 1900080,
+      "step": 118
+    },
+    {
+      "epoch": 0.008335741241780275,
+      "grad_norm": 4.785780429840088,
+      "learning_rate": 9.916720840630474e-05,
+      "loss": 1.2415,
+      "num_input_tokens_seen": 1916464,
+      "step": 119
+    },
+    {
+      "epoch": 0.008405789487509523,
+      "grad_norm": 4.802333831787109,
+      "learning_rate": 9.916021015761822e-05,
+      "loss": 1.0513,
+      "num_input_tokens_seen": 1932848,
+      "step": 120
+    },
+    {
+      "epoch": 0.008475837733238768,
+      "grad_norm": 5.22212553024292,
+      "learning_rate": 9.91532119089317e-05,
+      "loss": 1.2574,
+      "num_input_tokens_seen": 1949232,
+      "step": 121
+    },
+    {
+      "epoch": 0.008545885978968014,
+      "grad_norm": 5.104204177856445,
+      "learning_rate": 9.914621366024518e-05,
+      "loss": 1.0436,
+      "num_input_tokens_seen": 1964184,
+      "step": 122
+    },
+    {
+      "epoch": 0.00861593422469726,
+      "grad_norm": 5.11055326461792,
+      "learning_rate": 9.913921541155868e-05,
+      "loss": 1.1939,
+      "num_input_tokens_seen": 1980568,
+      "step": 123
+    },
+    {
+      "epoch": 0.008685982470426507,
+      "grad_norm": 4.784866809844971,
+      "learning_rate": 9.913221716287216e-05,
+      "loss": 1.2056,
+      "num_input_tokens_seen": 1996952,
+      "step": 124
+    },
+    {
+      "epoch": 0.008756030716155752,
+      "grad_norm": 4.763037204742432,
+      "learning_rate": 9.912521891418564e-05,
+      "loss": 1.1403,
+      "num_input_tokens_seen": 2013336,
+      "step": 125
+    },
+    {
+      "epoch": 0.008826078961884998,
+      "grad_norm": 4.813408851623535,
+      "learning_rate": 9.911822066549913e-05,
+      "loss": 1.1897,
+      "num_input_tokens_seen": 2029720,
+      "step": 126
+    },
+    {
+      "epoch": 0.008896127207614244,
+      "grad_norm": 4.79008674621582,
+      "learning_rate": 9.911122241681261e-05,
+      "loss": 1.2315,
+      "num_input_tokens_seen": 2046104,
+      "step": 127
+    },
+    {
+      "epoch": 0.008966175453343491,
+      "grad_norm": 4.843508720397949,
+      "learning_rate": 9.91042241681261e-05,
+      "loss": 1.0883,
+      "num_input_tokens_seen": 2061592,
+      "step": 128
+    },
+    {
+      "epoch": 0.009036223699072737,
+      "grad_norm": 4.917592525482178,
+      "learning_rate": 9.909722591943959e-05,
+      "loss": 1.2512,
+      "num_input_tokens_seen": 2077792,
+      "step": 129
+    },
+    {
+      "epoch": 0.009106271944801982,
+      "grad_norm": 4.9154133796691895,
+      "learning_rate": 9.909022767075307e-05,
+      "loss": 1.3284,
+      "num_input_tokens_seen": 2094176,
+      "step": 130
+    },
+    {
+      "epoch": 0.009176320190531228,
+      "grad_norm": 5.2125420570373535,
+      "learning_rate": 9.908322942206656e-05,
+      "loss": 1.3469,
+      "num_input_tokens_seen": 2110480,
+      "step": 131
+    },
+    {
+      "epoch": 0.009246368436260475,
+      "grad_norm": 4.715712547302246,
+      "learning_rate": 9.907623117338004e-05,
+      "loss": 1.0844,
+      "num_input_tokens_seen": 2126864,
+      "step": 132
+    },
+    {
+      "epoch": 0.009316416681989721,
+      "grad_norm": 4.805694580078125,
+      "learning_rate": 9.906923292469353e-05,
+      "loss": 1.069,
+      "num_input_tokens_seen": 2142848,
+      "step": 133
+    },
+    {
+      "epoch": 0.009386464927718966,
+      "grad_norm": 4.961355209350586,
+      "learning_rate": 9.9062234676007e-05,
+      "loss": 1.3387,
+      "num_input_tokens_seen": 2159232,
+      "step": 134
+    },
+    {
+      "epoch": 0.009456513173448212,
+      "grad_norm": 4.582219123840332,
+      "learning_rate": 9.905523642732049e-05,
+      "loss": 1.2013,
+      "num_input_tokens_seen": 2175616,
+      "step": 135
+    },
+    {
+      "epoch": 0.009526561419177458,
+      "grad_norm": 5.195998191833496,
+      "learning_rate": 9.904823817863398e-05,
+      "loss": 1.2552,
+      "num_input_tokens_seen": 2191872,
+      "step": 136
+    },
+    {
+      "epoch": 0.009596609664906705,
+      "grad_norm": 4.934189319610596,
+      "learning_rate": 9.904123992994747e-05,
+      "loss": 1.2961,
+      "num_input_tokens_seen": 2208208,
+      "step": 137
+    },
+    {
+      "epoch": 0.00966665791063595,
+      "grad_norm": 4.981037616729736,
+      "learning_rate": 9.903424168126096e-05,
+      "loss": 1.1546,
+      "num_input_tokens_seen": 2224592,
+      "step": 138
+    },
+    {
+      "epoch": 0.009736706156365196,
+      "grad_norm": 5.469496250152588,
+      "learning_rate": 9.902724343257443e-05,
+      "loss": 1.3833,
+      "num_input_tokens_seen": 2240976,
+      "step": 139
+    },
+    {
+      "epoch": 0.009806754402094442,
+      "grad_norm": 4.889583587646484,
+      "learning_rate": 9.902024518388792e-05,
+      "loss": 1.2095,
+      "num_input_tokens_seen": 2257360,
+      "step": 140
+    },
+    {
+      "epoch": 0.00987680264782369,
+      "grad_norm": 4.532052516937256,
+      "learning_rate": 9.901324693520141e-05,
+      "loss": 1.143,
+      "num_input_tokens_seen": 2272848,
+      "step": 141
+    },
+    {
+      "epoch": 0.009946850893552935,
+      "grad_norm": 5.278079032897949,
+      "learning_rate": 9.900624868651488e-05,
+      "loss": 1.2849,
+      "num_input_tokens_seen": 2289232,
+      "step": 142
+    },
+    {
+      "epoch": 0.01001689913928218,
+      "grad_norm": 4.549891948699951,
+      "learning_rate": 9.899925043782839e-05,
+      "loss": 1.0482,
+      "num_input_tokens_seen": 2305424,
+      "step": 143
+    },
+    {
+      "epoch": 0.010086947385011426,
+      "grad_norm": 4.7777180671691895,
+      "learning_rate": 9.899225218914186e-05,
+      "loss": 1.1926,
+      "num_input_tokens_seen": 2320968,
+      "step": 144
+    },
+    {
+      "epoch": 0.010156995630740673,
+      "grad_norm": 4.320313453674316,
+      "learning_rate": 9.898525394045535e-05,
+      "loss": 1.0468,
+      "num_input_tokens_seen": 2337352,
+      "step": 145
+    },
+    {
+      "epoch": 0.010227043876469919,
+      "grad_norm": 4.915202617645264,
+      "learning_rate": 9.897825569176882e-05,
+      "loss": 1.1326,
+      "num_input_tokens_seen": 2353064,
+      "step": 146
+    },
+    {
+      "epoch": 0.010297092122199165,
+      "grad_norm": 4.569783687591553,
+      "learning_rate": 9.897125744308231e-05,
+      "loss": 0.8586,
+      "num_input_tokens_seen": 2369128,
+      "step": 147
+    },
+    {
+      "epoch": 0.01036714036792841,
+      "grad_norm": 4.591664791107178,
+      "learning_rate": 9.89642591943958e-05,
+      "loss": 1.1369,
+      "num_input_tokens_seen": 2385512,
+      "step": 148
+    },
+    {
+      "epoch": 0.010437188613657656,
+      "grad_norm": 4.913016319274902,
+      "learning_rate": 9.895726094570929e-05,
+      "loss": 1.1564,
+      "num_input_tokens_seen": 2401208,
+      "step": 149
+    },
+    {
+      "epoch": 0.010507236859386903,
+      "grad_norm": 4.908018112182617,
+      "learning_rate": 9.895026269702278e-05,
+      "loss": 1.1247,
+      "num_input_tokens_seen": 2417592,
+      "step": 150
+    },
+    {
+      "epoch": 0.010577285105116149,
+      "grad_norm": 4.536910057067871,
+      "learning_rate": 9.894326444833625e-05,
+      "loss": 1.014,
+      "num_input_tokens_seen": 2433976,
+      "step": 151
+    },
+    {
+      "epoch": 0.010647333350845395,
+      "grad_norm": 4.899227142333984,
+      "learning_rate": 9.893626619964974e-05,
+      "loss": 1.0418,
+      "num_input_tokens_seen": 2448072,
+      "step": 152
+    },
+    {
+      "epoch": 0.01071738159657464,
+      "grad_norm": 4.600861072540283,
+      "learning_rate": 9.892926795096323e-05,
+      "loss": 1.0459,
+      "num_input_tokens_seen": 2464240,
+      "step": 153
+    },
+    {
+      "epoch": 0.010787429842303888,
+      "grad_norm": 4.707681179046631,
+      "learning_rate": 9.89222697022767e-05,
+      "loss": 1.0859,
+      "num_input_tokens_seen": 2480624,
+      "step": 154
+    },
+    {
+      "epoch": 0.010857478088033133,
+      "grad_norm": 4.748518466949463,
+      "learning_rate": 9.89152714535902e-05,
+      "loss": 1.0608,
+      "num_input_tokens_seen": 2497008,
+      "step": 155
+    },
+    {
+      "epoch": 0.010927526333762379,
+      "grad_norm": 4.794179439544678,
+      "learning_rate": 9.890827320490368e-05,
+      "loss": 1.2243,
+      "num_input_tokens_seen": 2513392,
+      "step": 156
+    },
+    {
+      "epoch": 0.010997574579491624,
+      "grad_norm": 4.593925476074219,
+      "learning_rate": 9.890127495621717e-05,
+      "loss": 1.1002,
+      "num_input_tokens_seen": 2529776,
+      "step": 157
+    },
+    {
+      "epoch": 0.011067622825220872,
+      "grad_norm": 4.318257808685303,
+      "learning_rate": 9.889427670753066e-05,
+      "loss": 0.9561,
+      "num_input_tokens_seen": 2546160,
+      "step": 158
+    },
+    {
+      "epoch": 0.011137671070950117,
+      "grad_norm": 4.631777286529541,
+      "learning_rate": 9.888727845884414e-05,
+      "loss": 1.1553,
+      "num_input_tokens_seen": 2562544,
+      "step": 159
+    },
+    {
+      "epoch": 0.011207719316679363,
+      "grad_norm": 4.896609783172607,
+      "learning_rate": 9.888028021015762e-05,
+      "loss": 1.1779,
+      "num_input_tokens_seen": 2578088,
+      "step": 160
+    },
+    {
+      "epoch": 0.011277767562408609,
+      "grad_norm": 4.3978681564331055,
+      "learning_rate": 9.88732819614711e-05,
+      "loss": 1.1778,
+      "num_input_tokens_seen": 2594416,
+      "step": 161
+    },
+    {
+      "epoch": 0.011347815808137854,
+      "grad_norm": 4.82927942276001,
+      "learning_rate": 9.886628371278459e-05,
+      "loss": 1.0339,
+      "num_input_tokens_seen": 2609776,
+      "step": 162
+    },
+    {
+      "epoch": 0.011417864053867102,
+      "grad_norm": 4.413319110870361,
+      "learning_rate": 9.885928546409809e-05,
+      "loss": 1.0992,
+      "num_input_tokens_seen": 2626160,
+      "step": 163
+    },
+    {
+      "epoch": 0.011487912299596347,
+      "grad_norm": 4.626354694366455,
+      "learning_rate": 9.885228721541156e-05,
+      "loss": 1.1948,
+      "num_input_tokens_seen": 2642464,
+      "step": 164
+    },
+    {
+      "epoch": 0.011557960545325593,
+      "grad_norm": 4.328434467315674,
+      "learning_rate": 9.884528896672505e-05,
+      "loss": 1.1493,
+      "num_input_tokens_seen": 2658528,
+      "step": 165
+    },
+    {
+      "epoch": 0.011628008791054838,
+      "grad_norm": 4.57839822769165,
+      "learning_rate": 9.883829071803853e-05,
+      "loss": 1.0775,
+      "num_input_tokens_seen": 2674912,
+      "step": 166
+    },
+    {
+      "epoch": 0.011698057036784086,
+      "grad_norm": 5.103973865509033,
+      "learning_rate": 9.883129246935202e-05,
+      "loss": 1.2458,
+      "num_input_tokens_seen": 2690792,
+      "step": 167
+    },
+    {
+      "epoch": 0.011768105282513331,
+      "grad_norm": 4.558016300201416,
+      "learning_rate": 9.88242942206655e-05,
+      "loss": 1.0122,
+      "num_input_tokens_seen": 2705616,
+      "step": 168
+    },
+    {
+      "epoch": 0.011838153528242577,
+      "grad_norm": 4.811260223388672,
+      "learning_rate": 9.8817295971979e-05,
+      "loss": 1.2989,
+      "num_input_tokens_seen": 2721704,
+      "step": 169
+    },
+    {
+      "epoch": 0.011908201773971823,
+      "grad_norm": 4.726966857910156,
+      "learning_rate": 9.881029772329248e-05,
+      "loss": 1.176,
+      "num_input_tokens_seen": 2738088,
+      "step": 170
+    },
+    {
+      "epoch": 0.01197825001970107,
+      "grad_norm": 4.874902725219727,
+      "learning_rate": 9.880329947460596e-05,
+      "loss": 1.2586,
+      "num_input_tokens_seen": 2754040,
+      "step": 171
+    },
+    {
+      "epoch": 0.012048298265430316,
+      "grad_norm": 4.379549980163574,
+      "learning_rate": 9.879630122591945e-05,
+      "loss": 1.1771,
+      "num_input_tokens_seen": 2770424,
+      "step": 172
+    },
+    {
+      "epoch": 0.012118346511159561,
+      "grad_norm": 4.455331802368164,
+      "learning_rate": 9.878930297723292e-05,
+      "loss": 1.0714,
+      "num_input_tokens_seen": 2786808,
+      "step": 173
+    },
+    {
+      "epoch": 0.012188394756888807,
+      "grad_norm": 4.42273473739624,
+      "learning_rate": 9.878230472854641e-05,
+      "loss": 1.1798,
+      "num_input_tokens_seen": 2803176,
+      "step": 174
+    },
+    {
+      "epoch": 0.012258443002618052,
+      "grad_norm": 4.4078874588012695,
+      "learning_rate": 9.87753064798599e-05,
+      "loss": 1.1672,
+      "num_input_tokens_seen": 2819448,
+      "step": 175
+    },
+    {
+      "epoch": 0.0123284912483473,
+      "grad_norm": 4.79048490524292,
+      "learning_rate": 9.876830823117339e-05,
+      "loss": 1.3331,
+      "num_input_tokens_seen": 2835832,
+      "step": 176
+    },
+    {
+      "epoch": 0.012398539494076545,
+      "grad_norm": 4.212133884429932,
+      "learning_rate": 9.876130998248688e-05,
+      "loss": 1.0007,
+      "num_input_tokens_seen": 2851776,
+      "step": 177
+    },
+    {
+      "epoch": 0.012468587739805791,
+      "grad_norm": 5.7587738037109375,
+      "learning_rate": 9.875431173380035e-05,
+      "loss": 1.4729,
+      "num_input_tokens_seen": 2867896,
+      "step": 178
+    },
+    {
+      "epoch": 0.012538635985535037,
+      "grad_norm": 4.3469462394714355,
+      "learning_rate": 9.874731348511384e-05,
+      "loss": 0.957,
+      "num_input_tokens_seen": 2884280,
+      "step": 179
+    },
+    {
+      "epoch": 0.012608684231264284,
+      "grad_norm": 4.584625244140625,
+      "learning_rate": 9.874031523642733e-05,
+      "loss": 1.0753,
+      "num_input_tokens_seen": 2899208,
+      "step": 180
+    },
+    {
+      "epoch": 0.01267873247699353,
+      "grad_norm": 4.544627666473389,
+      "learning_rate": 9.87333169877408e-05,
+      "loss": 1.1706,
+      "num_input_tokens_seen": 2915416,
+      "step": 181
+    },
+    {
+      "epoch": 0.012748780722722775,
+      "grad_norm": 4.8749237060546875,
+      "learning_rate": 9.872631873905429e-05,
+      "loss": 1.3382,
+      "num_input_tokens_seen": 2931360,
+      "step": 182
+    },
+    {
+      "epoch": 0.01281882896845202,
+      "grad_norm": 4.593903541564941,
+      "learning_rate": 9.871932049036778e-05,
+      "loss": 1.1588,
+      "num_input_tokens_seen": 2947744,
+      "step": 183
+    },
+    {
+      "epoch": 0.012888877214181268,
+      "grad_norm": 4.478219509124756,
+      "learning_rate": 9.871232224168127e-05,
+      "loss": 1.1013,
+      "num_input_tokens_seen": 2963664,
+      "step": 184
+    },
+    {
+      "epoch": 0.012958925459910514,
+      "grad_norm": 5.028106212615967,
+      "learning_rate": 9.870532399299476e-05,
+      "loss": 1.3223,
+      "num_input_tokens_seen": 2980048,
+      "step": 185
+    },
+    {
+      "epoch": 0.01302897370563976,
+      "grad_norm": 4.866946697235107,
+      "learning_rate": 9.869832574430823e-05,
+      "loss": 1.2376,
+      "num_input_tokens_seen": 2995992,
+      "step": 186
+    },
+    {
+      "epoch": 0.013099021951369005,
+      "grad_norm": 4.421341419219971,
+      "learning_rate": 9.869132749562172e-05,
+      "loss": 1.2252,
+      "num_input_tokens_seen": 3012000,
+      "step": 187
+    },
+    {
+      "epoch": 0.01316907019709825,
+      "grad_norm": 4.88083028793335,
+      "learning_rate": 9.86843292469352e-05,
+      "loss": 1.2951,
+      "num_input_tokens_seen": 3028384,
+      "step": 188
+    },
+    {
+      "epoch": 0.013239118442827498,
+      "grad_norm": 4.654318809509277,
+      "learning_rate": 9.86773309982487e-05,
+      "loss": 1.2839,
+      "num_input_tokens_seen": 3044768,
+      "step": 189
+    },
+    {
+      "epoch": 0.013309166688556744,
+      "grad_norm": 4.626763820648193,
+      "learning_rate": 9.867033274956219e-05,
+      "loss": 1.2389,
+      "num_input_tokens_seen": 3061152,
+      "step": 190
+    },
+    {
+      "epoch": 0.01337921493428599,
+      "grad_norm": 4.178484916687012,
+      "learning_rate": 9.866333450087566e-05,
+      "loss": 1.1186,
+      "num_input_tokens_seen": 3077056,
+      "step": 191
+    },
+    {
+      "epoch": 0.013449263180015235,
+      "grad_norm": 4.755034923553467,
+      "learning_rate": 9.865633625218915e-05,
+      "loss": 1.0594,
+      "num_input_tokens_seen": 3093400,
+      "step": 192
+    },
+    {
+      "epoch": 0.013519311425744482,
+      "grad_norm": 4.437506198883057,
+      "learning_rate": 9.864933800350263e-05,
+      "loss": 1.2078,
+      "num_input_tokens_seen": 3109784,
+      "step": 193
+    },
+    {
+      "epoch": 0.013589359671473728,
+      "grad_norm": 5.140488624572754,
+      "learning_rate": 9.864233975481611e-05,
+      "loss": 1.4312,
+      "num_input_tokens_seen": 3124976,
+      "step": 194
+    },
+    {
+      "epoch": 0.013659407917202973,
+      "grad_norm": 4.72155237197876,
+      "learning_rate": 9.86353415061296e-05,
+      "loss": 1.1752,
+      "num_input_tokens_seen": 3140632,
+      "step": 195
+    },
+    {
+      "epoch": 0.013729456162932219,
+      "grad_norm": 4.914645671844482,
+      "learning_rate": 9.862834325744309e-05,
+      "loss": 1.2464,
+      "num_input_tokens_seen": 3156616,
+      "step": 196
+    },
+    {
+      "epoch": 0.013799504408661466,
+      "grad_norm": 4.23387336730957,
+      "learning_rate": 9.862134500875658e-05,
+      "loss": 0.9722,
+      "num_input_tokens_seen": 3172840,
+      "step": 197
+    },
+    {
+      "epoch": 0.013869552654390712,
+      "grad_norm": 4.659370422363281,
+      "learning_rate": 9.861434676007005e-05,
+      "loss": 1.1981,
+      "num_input_tokens_seen": 3188584,
+      "step": 198
+    },
+    {
+      "epoch": 0.013939600900119958,
+      "grad_norm": 4.580902576446533,
+      "learning_rate": 9.860734851138354e-05,
+      "loss": 1.1913,
+      "num_input_tokens_seen": 3204432,
+      "step": 199
+    },
+    {
+      "epoch": 0.014009649145849203,
+      "grad_norm": 4.208237648010254,
+      "learning_rate": 9.860035026269702e-05,
+      "loss": 1.2056,
+      "num_input_tokens_seen": 3220816,
+      "step": 200
+    },
+    {
+      "epoch": 0.014009649145849203,
+      "eval_loss": 1.2226407527923584,
+      "eval_runtime": 0.3992,
+      "eval_samples_per_second": 2.505,
+      "eval_steps_per_second": 2.505,
+      "num_input_tokens_seen": 3220816,
+      "step": 200
+    },
+    {
+      "epoch": 0.014079697391578449,
+      "grad_norm": 4.526260852813721,
+      "learning_rate": 9.85933520140105e-05,
+      "loss": 1.0488,
+      "num_input_tokens_seen": 3237200,
+      "step": 201
+    },
+    {
+      "epoch": 0.014149745637307696,
+      "grad_norm": 4.46895170211792,
+      "learning_rate": 9.8586353765324e-05,
+      "loss": 1.1101,
+      "num_input_tokens_seen": 3253336,
+      "step": 202
+    },
+    {
+      "epoch": 0.014219793883036942,
+      "grad_norm": 4.367347717285156,
+      "learning_rate": 9.857935551663748e-05,
+      "loss": 1.0425,
+      "num_input_tokens_seen": 3269632,
+      "step": 203
+    },
+    {
+      "epoch": 0.014289842128766187,
+      "grad_norm": 4.860860347747803,
+      "learning_rate": 9.857235726795097e-05,
+      "loss": 1.4068,
+      "num_input_tokens_seen": 3285432,
+      "step": 204
+    },
+    {
+      "epoch": 0.014359890374495433,
+      "grad_norm": 4.336480617523193,
+      "learning_rate": 9.856535901926445e-05,
+      "loss": 1.2579,
+      "num_input_tokens_seen": 3301632,
+      "step": 205
+    },
+    {
+      "epoch": 0.01442993862022468,
+      "grad_norm": 4.587873458862305,
+      "learning_rate": 9.855836077057794e-05,
+      "loss": 1.1508,
+      "num_input_tokens_seen": 3318016,
+      "step": 206
+    },
+    {
+      "epoch": 0.014499986865953926,
+      "grad_norm": 4.719262599945068,
+      "learning_rate": 9.855136252189142e-05,
+      "loss": 1.0208,
+      "num_input_tokens_seen": 3333168,
+      "step": 207
+    },
+    {
+      "epoch": 0.014570035111683172,
+      "grad_norm": 4.419138431549072,
+      "learning_rate": 9.85443642732049e-05,
+      "loss": 1.2576,
+      "num_input_tokens_seen": 3349384,
+      "step": 208
+    },
+    {
+      "epoch": 0.014640083357412417,
+      "grad_norm": 4.3150835037231445,
+      "learning_rate": 9.85373660245184e-05,
+      "loss": 1.1786,
+      "num_input_tokens_seen": 3365768,
+      "step": 209
+    },
+    {
+      "epoch": 0.014710131603141665,
+      "grad_norm": 4.5917649269104,
+      "learning_rate": 9.853036777583188e-05,
+      "loss": 1.2821,
+      "num_input_tokens_seen": 3382152,
+      "step": 210
+    },
+    {
+      "epoch": 0.01478017984887091,
+      "grad_norm": 4.9094343185424805,
+      "learning_rate": 9.852336952714537e-05,
+      "loss": 1.2415,
+      "num_input_tokens_seen": 3397896,
+      "step": 211
+    },
+    {
+      "epoch": 0.014850228094600156,
+      "grad_norm": 4.394861698150635,
+      "learning_rate": 9.851637127845885e-05,
+      "loss": 1.1776,
+      "num_input_tokens_seen": 3414280,
+      "step": 212
+    },
+    {
+      "epoch": 0.014920276340329401,
+      "grad_norm": 4.196374416351318,
+      "learning_rate": 9.850937302977233e-05,
+      "loss": 1.065,
+      "num_input_tokens_seen": 3430584,
+      "step": 213
+    },
+    {
+      "epoch": 0.014990324586058647,
+      "grad_norm": 4.728682518005371,
+      "learning_rate": 9.850237478108582e-05,
+      "loss": 1.2686,
+      "num_input_tokens_seen": 3446968,
+      "step": 214
+    },
+    {
+      "epoch": 0.015060372831787894,
+      "grad_norm": 4.291411876678467,
+      "learning_rate": 9.84953765323993e-05,
+      "loss": 1.1877,
+      "num_input_tokens_seen": 3462568,
+      "step": 215
+    },
+    {
+      "epoch": 0.01513042107751714,
+      "grad_norm": 4.405060768127441,
+      "learning_rate": 9.84883782837128e-05,
+      "loss": 1.2873,
+      "num_input_tokens_seen": 3478952,
+      "step": 216
+    },
+    {
+      "epoch": 0.015200469323246386,
+      "grad_norm": 4.254365921020508,
+      "learning_rate": 9.848138003502628e-05,
+      "loss": 1.1062,
+      "num_input_tokens_seen": 3495304,
+      "step": 217
+    },
+    {
+      "epoch": 0.015270517568975631,
+      "grad_norm": 4.741672039031982,
+      "learning_rate": 9.847438178633976e-05,
+      "loss": 1.1983,
+      "num_input_tokens_seen": 3511688,
+      "step": 218
+    },
+    {
+      "epoch": 0.015340565814704879,
+      "grad_norm": 4.352742671966553,
+      "learning_rate": 9.846738353765325e-05,
+      "loss": 1.2028,
+      "num_input_tokens_seen": 3528072,
+      "step": 219
+    },
+    {
+      "epoch": 0.015410614060434124,
+      "grad_norm": 4.996603488922119,
+      "learning_rate": 9.846038528896672e-05,
+      "loss": 1.1561,
+      "num_input_tokens_seen": 3542904,
+      "step": 220
+    },
+    {
+      "epoch": 0.01548066230616337,
+      "grad_norm": 4.911815166473389,
+      "learning_rate": 9.845338704028021e-05,
+      "loss": 1.3375,
+      "num_input_tokens_seen": 3558352,
+      "step": 221
+    },
+    {
+      "epoch": 0.015550710551892616,
+      "grad_norm": 4.638419151306152,
+      "learning_rate": 9.84463887915937e-05,
+      "loss": 1.1963,
+      "num_input_tokens_seen": 3574736,
+      "step": 222
+    },
+    {
+      "epoch": 0.015620758797621863,
+      "grad_norm": 4.323521614074707,
+      "learning_rate": 9.843939054290719e-05,
+      "loss": 1.1224,
+      "num_input_tokens_seen": 3591120,
+      "step": 223
+    },
+    {
+      "epoch": 0.01569080704335111,
+      "grad_norm": 4.466544151306152,
+      "learning_rate": 9.843239229422068e-05,
+      "loss": 1.3988,
+      "num_input_tokens_seen": 3607392,
+      "step": 224
+    },
+    {
+      "epoch": 0.015760855289080354,
+      "grad_norm": 4.476973533630371,
+      "learning_rate": 9.842539404553415e-05,
+      "loss": 1.184,
+      "num_input_tokens_seen": 3623776,
+      "step": 225
+    },
+    {
+      "epoch": 0.0158309035348096,
+      "grad_norm": 4.648625373840332,
+      "learning_rate": 9.841839579684764e-05,
+      "loss": 1.1768,
+      "num_input_tokens_seen": 3640008,
+      "step": 226
+    },
+    {
+      "epoch": 0.015900951780538845,
+      "grad_norm": 4.364476203918457,
+      "learning_rate": 9.841139754816112e-05,
+      "loss": 1.0208,
+      "num_input_tokens_seen": 3656392,
+      "step": 227
+    },
+    {
+      "epoch": 0.01597100002626809,
+      "grad_norm": 4.3054633140563965,
+      "learning_rate": 9.84043992994746e-05,
+      "loss": 1.1215,
+      "num_input_tokens_seen": 3672392,
+      "step": 228
+    },
+    {
+      "epoch": 0.016041048271997337,
+      "grad_norm": 4.83436918258667,
+      "learning_rate": 9.83974010507881e-05,
+      "loss": 1.2284,
+      "num_input_tokens_seen": 3688776,
+      "step": 229
+    },
+    {
+      "epoch": 0.016111096517726586,
+      "grad_norm": 4.447519779205322,
+      "learning_rate": 9.839040280210158e-05,
+      "loss": 1.1765,
+      "num_input_tokens_seen": 3705080,
+      "step": 230
+    },
+    {
+      "epoch": 0.01618114476345583,
+      "grad_norm": 4.269217491149902,
+      "learning_rate": 9.838340455341507e-05,
+      "loss": 1.0466,
+      "num_input_tokens_seen": 3721464,
+      "step": 231
+    },
+    {
+      "epoch": 0.016251193009185077,
+      "grad_norm": 4.41223669052124,
+      "learning_rate": 9.837640630472854e-05,
+      "loss": 1.2098,
+      "num_input_tokens_seen": 3737184,
+      "step": 232
+    },
+    {
+      "epoch": 0.016321241254914323,
+      "grad_norm": 4.632737159729004,
+      "learning_rate": 9.836940805604203e-05,
+      "loss": 1.1562,
+      "num_input_tokens_seen": 3753192,
+      "step": 233
+    },
+    {
+      "epoch": 0.016391289500643568,
+      "grad_norm": 4.379425525665283,
+      "learning_rate": 9.836240980735552e-05,
+      "loss": 1.1219,
+      "num_input_tokens_seen": 3767976,
+      "step": 234
+    },
+    {
+      "epoch": 0.016461337746372814,
+      "grad_norm": 4.28551721572876,
+      "learning_rate": 9.835541155866901e-05,
+      "loss": 1.0259,
+      "num_input_tokens_seen": 3784008,
+      "step": 235
+    },
+    {
+      "epoch": 0.01653138599210206,
+      "grad_norm": 4.642453670501709,
+      "learning_rate": 9.83484133099825e-05,
+      "loss": 1.1684,
+      "num_input_tokens_seen": 3800000,
+      "step": 236
+    },
+    {
+      "epoch": 0.016601434237831305,
+      "grad_norm": 4.367178440093994,
+      "learning_rate": 9.834141506129597e-05,
+      "loss": 1.2877,
+      "num_input_tokens_seen": 3816384,
+      "step": 237
+    },
+    {
+      "epoch": 0.01667148248356055,
+      "grad_norm": 4.5724005699157715,
+      "learning_rate": 9.833441681260946e-05,
+      "loss": 1.1814,
+      "num_input_tokens_seen": 3830328,
+      "step": 238
+    },
+    {
+      "epoch": 0.0167415307292898,
+      "grad_norm": 4.318159580230713,
+      "learning_rate": 9.832741856392295e-05,
+      "loss": 1.1143,
+      "num_input_tokens_seen": 3846712,
+      "step": 239
+    },
+    {
+      "epoch": 0.016811578975019045,
+      "grad_norm": 4.408501625061035,
+      "learning_rate": 9.832042031523643e-05,
+      "loss": 1.1508,
+      "num_input_tokens_seen": 3861776,
+      "step": 240
+    },
+    {
+      "epoch": 0.01688162722074829,
+      "grad_norm": 4.20060920715332,
+      "learning_rate": 9.831342206654991e-05,
+      "loss": 1.209,
+      "num_input_tokens_seen": 3877736,
+      "step": 241
+    },
+    {
+      "epoch": 0.016951675466477537,
+      "grad_norm": 4.431649208068848,
+      "learning_rate": 9.83064238178634e-05,
+      "loss": 1.2458,
+      "num_input_tokens_seen": 3893320,
+      "step": 242
+    },
+    {
+      "epoch": 0.017021723712206782,
+      "grad_norm": 4.000490188598633,
+      "learning_rate": 9.829942556917689e-05,
+      "loss": 1.0274,
+      "num_input_tokens_seen": 3909704,
+      "step": 243
+    },
+    {
+      "epoch": 0.017091771957936028,
+      "grad_norm": 4.703495025634766,
+      "learning_rate": 9.829242732049038e-05,
+      "loss": 1.1711,
+      "num_input_tokens_seen": 3925808,
+      "step": 244
+    },
+    {
+      "epoch": 0.017161820203665273,
+      "grad_norm": 4.639338970184326,
+      "learning_rate": 9.828542907180386e-05,
+      "loss": 1.3046,
+      "num_input_tokens_seen": 3942192,
+      "step": 245
+    },
+    {
+      "epoch": 0.01723186844939452,
+      "grad_norm": 4.414276599884033,
+      "learning_rate": 9.827843082311734e-05,
+      "loss": 1.271,
+      "num_input_tokens_seen": 3958528,
+      "step": 246
+    },
+    {
+      "epoch": 0.017301916695123768,
+      "grad_norm": 4.404853820800781,
+      "learning_rate": 9.827143257443082e-05,
+      "loss": 1.0693,
+      "num_input_tokens_seen": 3974912,
+      "step": 247
+    },
+    {
+      "epoch": 0.017371964940853014,
+      "grad_norm": 4.519491195678711,
+      "learning_rate": 9.826443432574431e-05,
+      "loss": 1.2894,
+      "num_input_tokens_seen": 3991296,
+      "step": 248
+    },
+    {
+      "epoch": 0.01744201318658226,
+      "grad_norm": 4.261727809906006,
+      "learning_rate": 9.825743607705781e-05,
+      "loss": 1.2059,
+      "num_input_tokens_seen": 4006544,
+      "step": 249
+    },
+    {
+      "epoch": 0.017512061432311505,
+      "grad_norm": 4.102485656738281,
+      "learning_rate": 9.825043782837129e-05,
+      "loss": 0.9365,
+      "num_input_tokens_seen": 4022320,
+      "step": 250
+    },
+    {
+      "epoch": 0.01758210967804075,
+      "grad_norm": 4.804764270782471,
+      "learning_rate": 9.824343957968477e-05,
+      "loss": 1.3344,
+      "num_input_tokens_seen": 4037048,
+      "step": 251
+    },
+    {
+      "epoch": 0.017652157923769996,
+      "grad_norm": 4.130600452423096,
+      "learning_rate": 9.823644133099825e-05,
+      "loss": 1.2349,
+      "num_input_tokens_seen": 4053432,
+      "step": 252
+    },
+    {
+      "epoch": 0.017722206169499242,
+      "grad_norm": 4.234742641448975,
+      "learning_rate": 9.822944308231174e-05,
+      "loss": 1.1371,
+      "num_input_tokens_seen": 4069816,
+      "step": 253
+    },
+    {
+      "epoch": 0.017792254415228487,
+      "grad_norm": 4.754928112030029,
+      "learning_rate": 9.822244483362521e-05,
+      "loss": 1.5168,
+      "num_input_tokens_seen": 4085864,
+      "step": 254
+    },
+    {
+      "epoch": 0.017862302660957733,
+      "grad_norm": 4.542768478393555,
+      "learning_rate": 9.821544658493871e-05,
+      "loss": 1.1943,
+      "num_input_tokens_seen": 4102240,
+      "step": 255
+    },
+    {
+      "epoch": 0.017932350906686982,
+      "grad_norm": 4.411310195922852,
+      "learning_rate": 9.82084483362522e-05,
+      "loss": 1.2694,
+      "num_input_tokens_seen": 4118544,
+      "step": 256
+    },
+    {
+      "epoch": 0.018002399152416228,
+      "grad_norm": 4.205377101898193,
+      "learning_rate": 9.820145008756568e-05,
+      "loss": 1.1581,
+      "num_input_tokens_seen": 4134928,
+      "step": 257
+    },
+    {
+      "epoch": 0.018072447398145473,
+      "grad_norm": 4.451165199279785,
+      "learning_rate": 9.819445183887917e-05,
+      "loss": 1.089,
+      "num_input_tokens_seen": 4150848,
+      "step": 258
+    },
+    {
+      "epoch": 0.01814249564387472,
+      "grad_norm": 4.366336822509766,
+      "learning_rate": 9.818745359019264e-05,
+      "loss": 1.1767,
+      "num_input_tokens_seen": 4167184,
+      "step": 259
+    },
+    {
+      "epoch": 0.018212543889603965,
+      "grad_norm": 4.394649982452393,
+      "learning_rate": 9.818045534150613e-05,
+      "loss": 1.0741,
+      "num_input_tokens_seen": 4183376,
+      "step": 260
+    },
+    {
+      "epoch": 0.01828259213533321,
+      "grad_norm": 4.344518184661865,
+      "learning_rate": 9.817345709281962e-05,
+      "loss": 1.2282,
+      "num_input_tokens_seen": 4199760,
+      "step": 261
+    },
+    {
+      "epoch": 0.018352640381062456,
+      "grad_norm": 4.403041362762451,
+      "learning_rate": 9.816645884413311e-05,
+      "loss": 1.2317,
+      "num_input_tokens_seen": 4215816,
+      "step": 262
+    },
+    {
+      "epoch": 0.0184226886267917,
+      "grad_norm": 4.715320110321045,
+      "learning_rate": 9.81594605954466e-05,
+      "loss": 1.3074,
+      "num_input_tokens_seen": 4231504,
+      "step": 263
+    },
+    {
+      "epoch": 0.01849273687252095,
+      "grad_norm": 4.5754265785217285,
+      "learning_rate": 9.815246234676007e-05,
+      "loss": 1.253,
+      "num_input_tokens_seen": 4247888,
+      "step": 264
+    },
+    {
+      "epoch": 0.018562785118250196,
+      "grad_norm": 4.2346930503845215,
+      "learning_rate": 9.814546409807356e-05,
+      "loss": 1.1727,
+      "num_input_tokens_seen": 4264248,
+      "step": 265
+    },
+    {
+      "epoch": 0.018632833363979442,
+      "grad_norm": 4.186713218688965,
+      "learning_rate": 9.813846584938705e-05,
+      "loss": 1.2693,
+      "num_input_tokens_seen": 4280632,
+      "step": 266
+    },
+    {
+      "epoch": 0.018702881609708687,
+      "grad_norm": 4.6356706619262695,
+      "learning_rate": 9.813146760070052e-05,
+      "loss": 1.3755,
+      "num_input_tokens_seen": 4296648,
+      "step": 267
+    },
+    {
+      "epoch": 0.018772929855437933,
+      "grad_norm": 4.466466903686523,
+      "learning_rate": 9.812446935201401e-05,
+      "loss": 1.283,
+      "num_input_tokens_seen": 4311408,
+      "step": 268
+    },
+    {
+      "epoch": 0.01884297810116718,
+      "grad_norm": 4.3369140625,
+      "learning_rate": 9.81174711033275e-05,
+      "loss": 1.1555,
+      "num_input_tokens_seen": 4326736,
+      "step": 269
+    },
+    {
+      "epoch": 0.018913026346896424,
+      "grad_norm": 4.434782028198242,
+      "learning_rate": 9.811047285464099e-05,
+      "loss": 1.2859,
+      "num_input_tokens_seen": 4343120,
+      "step": 270
+    },
+    {
+      "epoch": 0.01898307459262567,
+      "grad_norm": 4.346708297729492,
+      "learning_rate": 9.810347460595448e-05,
+      "loss": 1.1421,
+      "num_input_tokens_seen": 4359504,
+      "step": 271
+    },
+    {
+      "epoch": 0.019053122838354915,
+      "grad_norm": 4.529878616333008,
+      "learning_rate": 9.809647635726795e-05,
+      "loss": 1.2654,
+      "num_input_tokens_seen": 4375888,
+      "step": 272
+    },
+    {
+      "epoch": 0.019123171084084165,
+      "grad_norm": 4.051745891571045,
+      "learning_rate": 9.808947810858144e-05,
+      "loss": 1.1469,
+      "num_input_tokens_seen": 4392224,
+      "step": 273
+    },
+    {
+      "epoch": 0.01919321932981341,
+      "grad_norm": 4.403522491455078,
+      "learning_rate": 9.808247985989492e-05,
+      "loss": 1.233,
+      "num_input_tokens_seen": 4408608,
+      "step": 274
+    },
+    {
+      "epoch": 0.019263267575542656,
+      "grad_norm": 4.166261196136475,
+      "learning_rate": 9.807548161120842e-05,
+      "loss": 1.1697,
+      "num_input_tokens_seen": 4424992,
+      "step": 275
+    },
+    {
+      "epoch": 0.0193333158212719,
+      "grad_norm": 4.29187536239624,
+      "learning_rate": 9.806848336252191e-05,
+      "loss": 1.0503,
+      "num_input_tokens_seen": 4441376,
+      "step": 276
+    },
+    {
+      "epoch": 0.019403364067001147,
+      "grad_norm": 4.4056172370910645,
+      "learning_rate": 9.806148511383538e-05,
+      "loss": 1.1965,
+      "num_input_tokens_seen": 4457760,
+      "step": 277
+    },
+    {
+      "epoch": 0.019473412312730393,
+      "grad_norm": 4.355875015258789,
+      "learning_rate": 9.805448686514887e-05,
+      "loss": 1.1024,
+      "num_input_tokens_seen": 4474144,
+      "step": 278
+    },
+    {
+      "epoch": 0.019543460558459638,
+      "grad_norm": 4.46420955657959,
+      "learning_rate": 9.804748861646235e-05,
+      "loss": 1.203,
+      "num_input_tokens_seen": 4488912,
+      "step": 279
+    },
+    {
+      "epoch": 0.019613508804188884,
+      "grad_norm": 4.48052453994751,
+      "learning_rate": 9.804049036777583e-05,
+      "loss": 1.2089,
+      "num_input_tokens_seen": 4505296,
+      "step": 280
+    },
+    {
+      "epoch": 0.01968355704991813,
+      "grad_norm": 4.458749294281006,
+      "learning_rate": 9.803349211908932e-05,
+      "loss": 1.1557,
+      "num_input_tokens_seen": 4520576,
+      "step": 281
+    },
+    {
+      "epoch": 0.01975360529564738,
+      "grad_norm": 4.551771640777588,
+      "learning_rate": 9.802649387040281e-05,
+      "loss": 1.1671,
+      "num_input_tokens_seen": 4536960,
+      "step": 282
+    },
+    {
+      "epoch": 0.019823653541376624,
+      "grad_norm": 4.038064956665039,
+      "learning_rate": 9.80194956217163e-05,
+      "loss": 1.1562,
+      "num_input_tokens_seen": 4553344,
+      "step": 283
+    },
+    {
+      "epoch": 0.01989370178710587,
+      "grad_norm": 4.647075653076172,
+      "learning_rate": 9.801249737302978e-05,
+      "loss": 1.3069,
+      "num_input_tokens_seen": 4568928,
+      "step": 284
+    },
+    {
+      "epoch": 0.019963750032835115,
+      "grad_norm": 4.258941650390625,
+      "learning_rate": 9.800549912434326e-05,
+      "loss": 1.0349,
+      "num_input_tokens_seen": 4585312,
+      "step": 285
+    },
+    {
+      "epoch": 0.02003379827856436,
+      "grad_norm": 4.348769664764404,
+      "learning_rate": 9.799850087565674e-05,
+      "loss": 1.1163,
+      "num_input_tokens_seen": 4601696,
+      "step": 286
+    },
+    {
+      "epoch": 0.020103846524293607,
+      "grad_norm": 4.105901718139648,
+      "learning_rate": 9.799150262697023e-05,
+      "loss": 1.0313,
+      "num_input_tokens_seen": 4617312,
+      "step": 287
+    },
+    {
+      "epoch": 0.020173894770022852,
+      "grad_norm": 4.079495429992676,
+      "learning_rate": 9.798450437828372e-05,
+      "loss": 1.0828,
+      "num_input_tokens_seen": 4633696,
+      "step": 288
+    },
+    {
+      "epoch": 0.020243943015752098,
+      "grad_norm": 4.03472375869751,
+      "learning_rate": 9.79775061295972e-05,
+      "loss": 0.9475,
+      "num_input_tokens_seen": 4650080,
+      "step": 289
+    },
+    {
+      "epoch": 0.020313991261481347,
+      "grad_norm": 4.077049732208252,
+      "learning_rate": 9.797050788091069e-05,
+      "loss": 1.1323,
+      "num_input_tokens_seen": 4666328,
+      "step": 290
+    },
+    {
+      "epoch": 0.020384039507210593,
+      "grad_norm": 4.086606025695801,
+      "learning_rate": 9.796350963222417e-05,
+      "loss": 1.1218,
+      "num_input_tokens_seen": 4682256,
+      "step": 291
+    },
+    {
+      "epoch": 0.020454087752939838,
+      "grad_norm": 4.296900749206543,
+      "learning_rate": 9.795651138353766e-05,
+      "loss": 1.2964,
+      "num_input_tokens_seen": 4698640,
+      "step": 292
+    },
+    {
+      "epoch": 0.020524135998669084,
+      "grad_norm": 4.040759086608887,
+      "learning_rate": 9.794951313485115e-05,
+      "loss": 1.1077,
+      "num_input_tokens_seen": 4714928,
+      "step": 293
+    },
+    {
+      "epoch": 0.02059418424439833,
+      "grad_norm": 3.8260273933410645,
+      "learning_rate": 9.794251488616462e-05,
+      "loss": 0.9667,
+      "num_input_tokens_seen": 4731312,
+      "step": 294
+    },
+    {
+      "epoch": 0.020664232490127575,
+      "grad_norm": 4.294517993927002,
+      "learning_rate": 9.793551663747811e-05,
+      "loss": 1.2704,
+      "num_input_tokens_seen": 4747544,
+      "step": 295
+    },
+    {
+      "epoch": 0.02073428073585682,
+      "grad_norm": 4.206037521362305,
+      "learning_rate": 9.79285183887916e-05,
+      "loss": 1.1593,
+      "num_input_tokens_seen": 4763928,
+      "step": 296
+    },
+    {
+      "epoch": 0.020804328981586066,
+      "grad_norm": 4.147867202758789,
+      "learning_rate": 9.792152014010509e-05,
+      "loss": 1.1256,
+      "num_input_tokens_seen": 4780312,
+      "step": 297
+    },
+    {
+      "epoch": 0.020874377227315312,
+      "grad_norm": 4.23718786239624,
+      "learning_rate": 9.791452189141857e-05,
+      "loss": 1.2353,
+      "num_input_tokens_seen": 4796384,
+      "step": 298
+    },
+    {
+      "epoch": 0.02094442547304456,
+      "grad_norm": 4.172685146331787,
+      "learning_rate": 9.790752364273205e-05,
+      "loss": 1.1868,
+      "num_input_tokens_seen": 4812768,
+      "step": 299
+    },
+    {
+      "epoch": 0.021014473718773807,
+      "grad_norm": 4.167289733886719,
+      "learning_rate": 9.790052539404554e-05,
+      "loss": 1.0606,
+      "num_input_tokens_seen": 4829152,
+      "step": 300
+    },
+    {
+      "epoch": 0.021084521964503052,
+      "grad_norm": 4.096963882446289,
+      "learning_rate": 9.789352714535903e-05,
+      "loss": 1.0557,
+      "num_input_tokens_seen": 4845384,
+      "step": 301
+    },
+    {
+      "epoch": 0.021154570210232298,
+      "grad_norm": 4.223779678344727,
+      "learning_rate": 9.788652889667252e-05,
+      "loss": 1.1485,
+      "num_input_tokens_seen": 4861768,
+      "step": 302
+    },
+    {
+      "epoch": 0.021224618455961543,
+      "grad_norm": 3.8243472576141357,
+      "learning_rate": 9.7879530647986e-05,
+      "loss": 1.004,
+      "num_input_tokens_seen": 4878152,
+      "step": 303
+    },
+    {
+      "epoch": 0.02129466670169079,
+      "grad_norm": 4.092590808868408,
+      "learning_rate": 9.787253239929948e-05,
+      "loss": 1.0211,
+      "num_input_tokens_seen": 4894536,
+      "step": 304
+    },
+    {
+      "epoch": 0.021364714947420035,
+      "grad_norm": 4.42412805557251,
+      "learning_rate": 9.786553415061297e-05,
+      "loss": 0.9915,
+      "num_input_tokens_seen": 4910320,
+      "step": 305
+    },
+    {
+      "epoch": 0.02143476319314928,
+      "grad_norm": 4.488316535949707,
+      "learning_rate": 9.785853590192644e-05,
+      "loss": 1.1782,
+      "num_input_tokens_seen": 4926704,
+      "step": 306
+    },
+    {
+      "epoch": 0.021504811438878526,
+      "grad_norm": 4.110256195068359,
+      "learning_rate": 9.785153765323993e-05,
+      "loss": 1.102,
+      "num_input_tokens_seen": 4943088,
+      "step": 307
+    },
+    {
+      "epoch": 0.021574859684607775,
+      "grad_norm": 4.246950149536133,
+      "learning_rate": 9.784453940455342e-05,
+      "loss": 1.067,
+      "num_input_tokens_seen": 4958736,
+      "step": 308
+    },
+    {
+      "epoch": 0.02164490793033702,
+      "grad_norm": 4.175214767456055,
+      "learning_rate": 9.783754115586691e-05,
+      "loss": 1.0638,
+      "num_input_tokens_seen": 4975120,
+      "step": 309
+    },
+    {
+      "epoch": 0.021714956176066266,
+      "grad_norm": 4.427795886993408,
+      "learning_rate": 9.78305429071804e-05,
+      "loss": 1.1347,
+      "num_input_tokens_seen": 4991504,
+      "step": 310
+    },
+    {
+      "epoch": 0.021785004421795512,
+      "grad_norm": 4.158191204071045,
+      "learning_rate": 9.782354465849387e-05,
+      "loss": 1.1662,
+      "num_input_tokens_seen": 5007152,
+      "step": 311
+    },
+    {
+      "epoch": 0.021855052667524758,
+      "grad_norm": 4.184347629547119,
+      "learning_rate": 9.781654640980736e-05,
+      "loss": 1.0791,
+      "num_input_tokens_seen": 5023536,
+      "step": 312
+    },
+    {
+      "epoch": 0.021925100913254003,
+      "grad_norm": 3.8506295680999756,
+      "learning_rate": 9.780954816112084e-05,
+      "loss": 1.0615,
+      "num_input_tokens_seen": 5039728,
+      "step": 313
+    },
+    {
+      "epoch": 0.02199514915898325,
+      "grad_norm": 4.310062408447266,
+      "learning_rate": 9.780254991243432e-05,
+      "loss": 1.1363,
+      "num_input_tokens_seen": 5056008,
+      "step": 314
+    },
+    {
+      "epoch": 0.022065197404712494,
+      "grad_norm": 4.215006351470947,
+      "learning_rate": 9.779555166374781e-05,
+      "loss": 1.1715,
+      "num_input_tokens_seen": 5072096,
+      "step": 315
+    },
+    {
+      "epoch": 0.022135245650441743,
+      "grad_norm": 4.219073295593262,
+      "learning_rate": 9.77885534150613e-05,
+      "loss": 1.219,
+      "num_input_tokens_seen": 5088432,
+      "step": 316
+    },
+    {
+      "epoch": 0.02220529389617099,
+      "grad_norm": 4.319522857666016,
+      "learning_rate": 9.778155516637479e-05,
+      "loss": 1.3085,
+      "num_input_tokens_seen": 5104240,
+      "step": 317
+    },
+    {
+      "epoch": 0.022275342141900235,
+      "grad_norm": 4.118961334228516,
+      "learning_rate": 9.777455691768827e-05,
+      "loss": 1.0926,
+      "num_input_tokens_seen": 5120624,
+      "step": 318
+    },
+    {
+      "epoch": 0.02234539038762948,
+      "grad_norm": 4.195051193237305,
+      "learning_rate": 9.776755866900175e-05,
+      "loss": 1.0894,
+      "num_input_tokens_seen": 5137008,
+      "step": 319
+    },
+    {
+      "epoch": 0.022415438633358726,
+      "grad_norm": 4.114197254180908,
+      "learning_rate": 9.776056042031524e-05,
+      "loss": 1.1897,
+      "num_input_tokens_seen": 5153272,
+      "step": 320
+    },
+    {
+      "epoch": 0.02248548687908797,
+      "grad_norm": 4.014908313751221,
+      "learning_rate": 9.775356217162872e-05,
+      "loss": 1.0932,
+      "num_input_tokens_seen": 5169472,
+      "step": 321
+    },
+    {
+      "epoch": 0.022555535124817217,
+      "grad_norm": 4.190642356872559,
+      "learning_rate": 9.774656392294222e-05,
+      "loss": 1.1413,
+      "num_input_tokens_seen": 5185856,
+      "step": 322
+    },
+    {
+      "epoch": 0.022625583370546463,
+      "grad_norm": 4.562993049621582,
+      "learning_rate": 9.77395656742557e-05,
+      "loss": 1.2865,
+      "num_input_tokens_seen": 5202240,
+      "step": 323
+    },
+    {
+      "epoch": 0.02269563161627571,
+      "grad_norm": 4.607022762298584,
+      "learning_rate": 9.773256742556918e-05,
+      "loss": 1.1465,
+      "num_input_tokens_seen": 5218168,
+      "step": 324
+    },
+    {
+      "epoch": 0.022765679862004957,
+      "grad_norm": 3.956439256668091,
+      "learning_rate": 9.772556917688267e-05,
+      "loss": 1.028,
+      "num_input_tokens_seen": 5234368,
+      "step": 325
+    },
+    {
+      "epoch": 0.022835728107734203,
+      "grad_norm": 4.20713472366333,
+      "learning_rate": 9.771857092819615e-05,
+      "loss": 1.2332,
+      "num_input_tokens_seen": 5249808,
+      "step": 326
+    },
+    {
+      "epoch": 0.02290577635346345,
+      "grad_norm": 4.4092864990234375,
+      "learning_rate": 9.771157267950964e-05,
+      "loss": 1.104,
+      "num_input_tokens_seen": 5266120,
+      "step": 327
+    },
+    {
+      "epoch": 0.022975824599192694,
+      "grad_norm": 4.529845237731934,
+      "learning_rate": 9.770457443082312e-05,
+      "loss": 1.3475,
+      "num_input_tokens_seen": 5282504,
+      "step": 328
+    },
+    {
+      "epoch": 0.02304587284492194,
+      "grad_norm": 4.221986293792725,
+      "learning_rate": 9.769757618213661e-05,
+      "loss": 1.4115,
+      "num_input_tokens_seen": 5298344,
+      "step": 329
+    },
+    {
+      "epoch": 0.023115921090651186,
+      "grad_norm": 4.29000186920166,
+      "learning_rate": 9.76905779334501e-05,
+      "loss": 1.2855,
+      "num_input_tokens_seen": 5314728,
+      "step": 330
+    },
+    {
+      "epoch": 0.02318596933638043,
+      "grad_norm": 4.426812648773193,
+      "learning_rate": 9.768357968476358e-05,
+      "loss": 1.514,
+      "num_input_tokens_seen": 5330816,
+      "step": 331
+    },
+    {
+      "epoch": 0.023256017582109677,
+      "grad_norm": 4.210752964019775,
+      "learning_rate": 9.767658143607706e-05,
+      "loss": 1.0854,
+      "num_input_tokens_seen": 5346552,
+      "step": 332
+    },
+    {
+      "epoch": 0.023326065827838922,
+      "grad_norm": 4.216427326202393,
+      "learning_rate": 9.766958318739054e-05,
+      "loss": 1.1573,
+      "num_input_tokens_seen": 5362936,
+      "step": 333
+    },
+    {
+      "epoch": 0.02339611407356817,
+      "grad_norm": 4.132325649261475,
+      "learning_rate": 9.766258493870403e-05,
+      "loss": 1.0942,
+      "num_input_tokens_seen": 5379320,
+      "step": 334
+    },
+    {
+      "epoch": 0.023466162319297417,
+      "grad_norm": 4.277027130126953,
+      "learning_rate": 9.765558669001752e-05,
+      "loss": 1.1227,
+      "num_input_tokens_seen": 5395704,
+      "step": 335
+    },
+    {
+      "epoch": 0.023536210565026663,
+      "grad_norm": 4.228096961975098,
+      "learning_rate": 9.7648588441331e-05,
+      "loss": 1.1094,
+      "num_input_tokens_seen": 5412088,
+      "step": 336
+    },
+    {
+      "epoch": 0.02360625881075591,
+      "grad_norm": 4.194522380828857,
+      "learning_rate": 9.76415901926445e-05,
+      "loss": 1.2066,
+      "num_input_tokens_seen": 5428472,
+      "step": 337
+    },
+    {
+      "epoch": 0.023676307056485154,
+      "grad_norm": 4.336326599121094,
+      "learning_rate": 9.763459194395797e-05,
+      "loss": 1.2251,
+      "num_input_tokens_seen": 5444856,
+      "step": 338
+    },
+    {
+      "epoch": 0.0237463553022144,
+      "grad_norm": 4.2723307609558105,
+      "learning_rate": 9.762759369527146e-05,
+      "loss": 1.0927,
+      "num_input_tokens_seen": 5460304,
+      "step": 339
+    },
+    {
+      "epoch": 0.023816403547943645,
+      "grad_norm": 4.190036773681641,
+      "learning_rate": 9.762059544658493e-05,
+      "loss": 1.2036,
+      "num_input_tokens_seen": 5476688,
+      "step": 340
+    },
+    {
+      "epoch": 0.02388645179367289,
+      "grad_norm": 4.477560043334961,
+      "learning_rate": 9.761359719789842e-05,
+      "loss": 1.362,
+      "num_input_tokens_seen": 5493072,
+      "step": 341
+    },
+    {
+      "epoch": 0.02395650003940214,
+      "grad_norm": 4.160232067108154,
+      "learning_rate": 9.760659894921192e-05,
+      "loss": 1.1602,
+      "num_input_tokens_seen": 5509456,
+      "step": 342
+    },
+    {
+      "epoch": 0.024026548285131386,
+      "grad_norm": 3.857335090637207,
+      "learning_rate": 9.75996007005254e-05,
+      "loss": 1.0963,
+      "num_input_tokens_seen": 5525840,
+      "step": 343
+    },
+    {
+      "epoch": 0.02409659653086063,
+      "grad_norm": 4.141246318817139,
+      "learning_rate": 9.759260245183889e-05,
+      "loss": 1.2009,
+      "num_input_tokens_seen": 5541888,
+      "step": 344
+    },
+    {
+      "epoch": 0.024166644776589877,
+      "grad_norm": 4.50364875793457,
+      "learning_rate": 9.758560420315236e-05,
+      "loss": 1.1483,
+      "num_input_tokens_seen": 5557848,
+      "step": 345
+    },
+    {
+      "epoch": 0.024236693022319122,
+      "grad_norm": 4.3343353271484375,
+      "learning_rate": 9.757860595446585e-05,
+      "loss": 1.3594,
+      "num_input_tokens_seen": 5573504,
+      "step": 346
+    },
+    {
+      "epoch": 0.024306741268048368,
+      "grad_norm": 4.050408363342285,
+      "learning_rate": 9.757160770577934e-05,
+      "loss": 1.0563,
+      "num_input_tokens_seen": 5589544,
+      "step": 347
+    },
+    {
+      "epoch": 0.024376789513777614,
+      "grad_norm": 4.051811695098877,
+      "learning_rate": 9.756460945709283e-05,
+      "loss": 1.0288,
+      "num_input_tokens_seen": 5605368,
+      "step": 348
+    },
+    {
+      "epoch": 0.02444683775950686,
+      "grad_norm": 4.365113258361816,
+      "learning_rate": 9.755761120840632e-05,
+      "loss": 1.3054,
+      "num_input_tokens_seen": 5621752,
+      "step": 349
+    },
+    {
+      "epoch": 0.024516886005236105,
+      "grad_norm": 4.0057501792907715,
+      "learning_rate": 9.755061295971979e-05,
+      "loss": 1.1302,
+      "num_input_tokens_seen": 5638136,
+      "step": 350
+    },
+    {
+      "epoch": 0.024586934250965354,
+      "grad_norm": 4.254896640777588,
+      "learning_rate": 9.754361471103328e-05,
+      "loss": 1.0495,
+      "num_input_tokens_seen": 5653168,
+      "step": 351
+    },
+    {
+      "epoch": 0.0246569824966946,
+      "grad_norm": 3.8119771480560303,
+      "learning_rate": 9.753661646234677e-05,
+      "loss": 1.0349,
+      "num_input_tokens_seen": 5669504,
+      "step": 352
+    },
+    {
+      "epoch": 0.024727030742423845,
+      "grad_norm": 4.5082621574401855,
+      "learning_rate": 9.752961821366024e-05,
+      "loss": 1.2537,
+      "num_input_tokens_seen": 5685168,
+      "step": 353
+    },
+    {
+      "epoch": 0.02479707898815309,
+      "grad_norm": 4.392731189727783,
+      "learning_rate": 9.752261996497373e-05,
+      "loss": 1.2534,
+      "num_input_tokens_seen": 5701240,
+      "step": 354
+    },
+    {
+      "epoch": 0.024867127233882336,
+      "grad_norm": 4.293395519256592,
+      "learning_rate": 9.751562171628722e-05,
+      "loss": 1.2774,
+      "num_input_tokens_seen": 5717624,
+      "step": 355
+    },
+    {
+      "epoch": 0.024937175479611582,
+      "grad_norm": 4.64813756942749,
+      "learning_rate": 9.750862346760071e-05,
+      "loss": 1.2795,
+      "num_input_tokens_seen": 5733104,
+      "step": 356
+    },
+    {
+      "epoch": 0.025007223725340828,
+      "grad_norm": 4.5166778564453125,
+      "learning_rate": 9.75016252189142e-05,
+      "loss": 1.1301,
+      "num_input_tokens_seen": 5749488,
+      "step": 357
+    },
+    {
+      "epoch": 0.025077271971070073,
+      "grad_norm": 3.894291400909424,
+      "learning_rate": 9.749462697022767e-05,
+      "loss": 0.901,
+      "num_input_tokens_seen": 5765872,
+      "step": 358
+    },
+    {
+      "epoch": 0.02514732021679932,
+      "grad_norm": 4.10056209564209,
+      "learning_rate": 9.748762872154116e-05,
+      "loss": 1.0529,
+      "num_input_tokens_seen": 5780856,
+      "step": 359
+    },
+    {
+      "epoch": 0.025217368462528568,
+      "grad_norm": 4.6277666091918945,
+      "learning_rate": 9.748063047285464e-05,
+      "loss": 1.3649,
+      "num_input_tokens_seen": 5796856,
+      "step": 360
+    },
+    {
+      "epoch": 0.025287416708257814,
+      "grad_norm": 4.029720306396484,
+      "learning_rate": 9.747363222416813e-05,
+      "loss": 0.8863,
+      "num_input_tokens_seen": 5812176,
+      "step": 361
+    },
+    {
+      "epoch": 0.02535746495398706,
+      "grad_norm": 3.7772202491760254,
+      "learning_rate": 9.746663397548161e-05,
+      "loss": 1.0448,
+      "num_input_tokens_seen": 5828064,
+      "step": 362
+    },
+    {
+      "epoch": 0.025427513199716305,
+      "grad_norm": 4.379861354827881,
+      "learning_rate": 9.74596357267951e-05,
+      "loss": 1.3274,
+      "num_input_tokens_seen": 5843680,
+      "step": 363
+    },
+    {
+      "epoch": 0.02549756144544555,
+      "grad_norm": 4.254587173461914,
+      "learning_rate": 9.745263747810859e-05,
+      "loss": 1.1502,
+      "num_input_tokens_seen": 5859024,
+      "step": 364
+    },
+    {
+      "epoch": 0.025567609691174796,
+      "grad_norm": 4.271276473999023,
+      "learning_rate": 9.744563922942207e-05,
+      "loss": 1.2785,
+      "num_input_tokens_seen": 5874320,
+      "step": 365
+    },
+    {
+      "epoch": 0.02563765793690404,
+      "grad_norm": 4.224324703216553,
+      "learning_rate": 9.743864098073555e-05,
+      "loss": 1.0926,
+      "num_input_tokens_seen": 5890704,
+      "step": 366
+    },
+    {
+      "epoch": 0.025707706182633287,
+      "grad_norm": 4.289444446563721,
+      "learning_rate": 9.743164273204903e-05,
+      "loss": 1.1913,
+      "num_input_tokens_seen": 5906016,
+      "step": 367
+    },
+    {
+      "epoch": 0.025777754428362536,
+      "grad_norm": 4.280707359313965,
+      "learning_rate": 9.742464448336253e-05,
+      "loss": 1.2238,
+      "num_input_tokens_seen": 5921784,
+      "step": 368
+    },
+    {
+      "epoch": 0.025847802674091782,
+      "grad_norm": 4.554803848266602,
+      "learning_rate": 9.741764623467602e-05,
+      "loss": 1.2491,
+      "num_input_tokens_seen": 5938072,
+      "step": 369
+    },
+    {
+      "epoch": 0.025917850919821028,
+      "grad_norm": 4.677784442901611,
+      "learning_rate": 9.74106479859895e-05,
+      "loss": 1.2387,
+      "num_input_tokens_seen": 5954456,
+      "step": 370
+    },
+    {
+      "epoch": 0.025987899165550273,
+      "grad_norm": 4.268225193023682,
+      "learning_rate": 9.740364973730298e-05,
+      "loss": 1.2983,
+      "num_input_tokens_seen": 5970664,
+      "step": 371
+    },
+    {
+      "epoch": 0.02605794741127952,
+      "grad_norm": 4.361818790435791,
+      "learning_rate": 9.739665148861646e-05,
+      "loss": 1.199,
+      "num_input_tokens_seen": 5987048,
+      "step": 372
+    },
+    {
+      "epoch": 0.026127995657008764,
+      "grad_norm": 3.9990735054016113,
+      "learning_rate": 9.738965323992995e-05,
+      "loss": 1.0777,
+      "num_input_tokens_seen": 6003432,
+      "step": 373
+    },
+    {
+      "epoch": 0.02619804390273801,
+      "grad_norm": 3.992142915725708,
+      "learning_rate": 9.738265499124344e-05,
+      "loss": 1.0443,
+      "num_input_tokens_seen": 6019816,
+      "step": 374
+    },
+    {
+      "epoch": 0.026268092148467256,
+      "grad_norm": 4.270167827606201,
+      "learning_rate": 9.737565674255693e-05,
+      "loss": 1.1764,
+      "num_input_tokens_seen": 6036200,
+      "step": 375
+    },
+    {
+      "epoch": 0.0263381403941965,
+      "grad_norm": 4.362086296081543,
+      "learning_rate": 9.736865849387041e-05,
+      "loss": 1.2735,
+      "num_input_tokens_seen": 6052120,
+      "step": 376
+    },
+    {
+      "epoch": 0.02640818863992575,
+      "grad_norm": 3.6900475025177,
+      "learning_rate": 9.736166024518389e-05,
+      "loss": 0.8729,
+      "num_input_tokens_seen": 6068264,
+      "step": 377
+    },
+    {
+      "epoch": 0.026478236885654996,
+      "grad_norm": 3.8281285762786865,
+      "learning_rate": 9.735466199649738e-05,
+      "loss": 1.1096,
+      "num_input_tokens_seen": 6084504,
+      "step": 378
+    },
+    {
+      "epoch": 0.02654828513138424,
+      "grad_norm": 3.9335553646087646,
+      "learning_rate": 9.734766374781087e-05,
+      "loss": 1.0763,
+      "num_input_tokens_seen": 6100592,
+      "step": 379
+    },
+    {
+      "epoch": 0.026618333377113487,
+      "grad_norm": 4.332645416259766,
+      "learning_rate": 9.734066549912434e-05,
+      "loss": 1.1751,
+      "num_input_tokens_seen": 6116976,
+      "step": 380
+    },
+    {
+      "epoch": 0.026688381622842733,
+      "grad_norm": 4.160863399505615,
+      "learning_rate": 9.733366725043783e-05,
+      "loss": 1.0778,
+      "num_input_tokens_seen": 6133360,
+      "step": 381
+    },
+    {
+      "epoch": 0.02675842986857198,
+      "grad_norm": 4.388178825378418,
+      "learning_rate": 9.732666900175132e-05,
+      "loss": 1.2214,
+      "num_input_tokens_seen": 6149744,
+      "step": 382
+    },
+    {
+      "epoch": 0.026828478114301224,
+      "grad_norm": 4.354910373687744,
+      "learning_rate": 9.73196707530648e-05,
+      "loss": 1.4115,
+      "num_input_tokens_seen": 6166048,
+      "step": 383
+    },
+    {
+      "epoch": 0.02689852636003047,
+      "grad_norm": 4.058071613311768,
+      "learning_rate": 9.73126725043783e-05,
+      "loss": 1.0934,
+      "num_input_tokens_seen": 6181840,
+      "step": 384
+    },
+    {
+      "epoch": 0.026968574605759715,
+      "grad_norm": 4.060855865478516,
+      "learning_rate": 9.730567425569177e-05,
+      "loss": 1.1395,
+      "num_input_tokens_seen": 6198224,
+      "step": 385
+    },
+    {
+      "epoch": 0.027038622851488964,
+      "grad_norm": 4.316681385040283,
+      "learning_rate": 9.729867600700526e-05,
+      "loss": 1.1052,
+      "num_input_tokens_seen": 6214608,
+      "step": 386
+    },
+    {
+      "epoch": 0.02710867109721821,
+      "grad_norm": 4.322516918182373,
+      "learning_rate": 9.729167775831873e-05,
+      "loss": 1.2512,
+      "num_input_tokens_seen": 6230992,
+      "step": 387
+    },
+    {
+      "epoch": 0.027178719342947456,
+      "grad_norm": 4.090857028961182,
+      "learning_rate": 9.728467950963224e-05,
+      "loss": 1.0772,
+      "num_input_tokens_seen": 6246760,
+      "step": 388
+    },
+    {
+      "epoch": 0.0272487675886767,
+      "grad_norm": 4.0143961906433105,
+      "learning_rate": 9.727768126094571e-05,
+      "loss": 1.0578,
+      "num_input_tokens_seen": 6261968,
+      "step": 389
+    },
+    {
+      "epoch": 0.027318815834405947,
+      "grad_norm": 4.911194324493408,
+      "learning_rate": 9.72706830122592e-05,
+      "loss": 1.3016,
+      "num_input_tokens_seen": 6276664,
+      "step": 390
+    },
+    {
+      "epoch": 0.027388864080135192,
+      "grad_norm": 4.057498931884766,
+      "learning_rate": 9.726368476357269e-05,
+      "loss": 1.026,
+      "num_input_tokens_seen": 6293048,
+      "step": 391
+    },
+    {
+      "epoch": 0.027458912325864438,
+      "grad_norm": 3.9827401638031006,
+      "learning_rate": 9.725668651488616e-05,
+      "loss": 1.136,
+      "num_input_tokens_seen": 6309432,
+      "step": 392
+    },
+    {
+      "epoch": 0.027528960571593684,
+      "grad_norm": 4.640822887420654,
+      "learning_rate": 9.724968826619965e-05,
+      "loss": 1.2823,
+      "num_input_tokens_seen": 6325568,
+      "step": 393
+    },
+    {
+      "epoch": 0.027599008817322933,
+      "grad_norm": 4.372538089752197,
+      "learning_rate": 9.724269001751314e-05,
+      "loss": 1.0354,
+      "num_input_tokens_seen": 6341952,
+      "step": 394
+    },
+    {
+      "epoch": 0.02766905706305218,
+      "grad_norm": 4.018289566040039,
+      "learning_rate": 9.723569176882663e-05,
+      "loss": 1.029,
+      "num_input_tokens_seen": 6358336,
+      "step": 395
+    },
+    {
+      "epoch": 0.027739105308781424,
+      "grad_norm": 4.440858364105225,
+      "learning_rate": 9.722869352014012e-05,
+      "loss": 1.2272,
+      "num_input_tokens_seen": 6374680,
+      "step": 396
+    },
+    {
+      "epoch": 0.02780915355451067,
+      "grad_norm": 4.246788024902344,
+      "learning_rate": 9.722169527145359e-05,
+      "loss": 1.0161,
+      "num_input_tokens_seen": 6390672,
+      "step": 397
+    },
+    {
+      "epoch": 0.027879201800239915,
+      "grad_norm": 4.27274751663208,
+      "learning_rate": 9.721469702276708e-05,
+      "loss": 1.293,
+      "num_input_tokens_seen": 6407056,
+      "step": 398
+    },
+    {
+      "epoch": 0.02794925004596916,
+      "grad_norm": 4.171760559082031,
+      "learning_rate": 9.720769877408056e-05,
+      "loss": 1.2766,
+      "num_input_tokens_seen": 6423440,
+      "step": 399
+    },
+    {
+      "epoch": 0.028019298291698407,
+      "grad_norm": 4.174622535705566,
+      "learning_rate": 9.720070052539405e-05,
+      "loss": 1.049,
+      "num_input_tokens_seen": 6439824,
+      "step": 400
+    },
+    {
+      "epoch": 0.028019298291698407,
+      "eval_loss": 1.1994441747665405,
+      "eval_runtime": 0.2131,
+      "eval_samples_per_second": 4.693,
+      "eval_steps_per_second": 4.693,
+      "num_input_tokens_seen": 6439824,
+      "step": 400
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 14275,
+  "num_input_tokens_seen": 6439824,
+  "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": 1.3828805107273728e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}