Upload 13 files

.gitattributes

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

adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "/root/autodl-tmp/Qwen2.5-14B-scipy",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "o_proj",
+    "down_proj",
+    "k_proj",
+    "v_proj",
+    "gate_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

added_tokens.json

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

all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 0.9985022466300549,
+    "num_input_tokens_seen": 18683616,
+    "total_flos": 1.599323192678744e+18,
+    "train_loss": 2.4129163398742675,
+    "train_runtime": 18708.0864,
+    "train_samples_per_second": 0.214,
+    "train_steps_per_second": 0.013
+}

special_tokens_map.json

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

tokenizer.json

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

tokenizer_config.json

@@ -0,0 +1,208 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 0.9985022466300549,
+    "num_input_tokens_seen": 18683616,
+    "total_flos": 1.599323192678744e+18,
+    "train_loss": 2.4129163398742675,
+    "train_runtime": 18708.0864,
+    "train_samples_per_second": 0.214,
+    "train_steps_per_second": 0.013
+}

trainer_log.jsonl

@@ -0,0 +1,177 @@
+{"current_steps": 2, "total_steps": 250, "loss": 2.4965, "learning_rate": 0.00029995262839249497, "epoch": 0.00798801797304044, "percentage": 0.8, "elapsed_time": "0:02:45", "remaining_time": "5:41:52", "throughput": 981.74, "total_tokens": 162400}
+{"current_steps": 4, "total_steps": 250, "loss": 2.4769, "learning_rate": 0.00029981054349090264, "epoch": 0.01597603594608088, "percentage": 1.6, "elapsed_time": "0:05:22", "remaining_time": "5:30:17", "throughput": 983.22, "total_tokens": 316832}
+{"current_steps": 6, "total_steps": 250, "loss": 2.4562, "learning_rate": 0.00029957383503909204, "epoch": 0.023964053919121316, "percentage": 2.4, "elapsed_time": "0:07:39", "remaining_time": "5:11:29", "throughput": 993.45, "total_tokens": 456560}
+{"current_steps": 8, "total_steps": 250, "loss": 2.5164, "learning_rate": 0.000299242652547195, "epoch": 0.03195207189216176, "percentage": 3.2, "elapsed_time": "0:10:15", "remaining_time": "5:10:32", "throughput": 994.0, "total_tokens": 612256}
+{"current_steps": 10, "total_steps": 250, "loss": 2.4843, "learning_rate": 0.0002988172051971717, "epoch": 0.0399400898652022, "percentage": 4.0, "elapsed_time": "0:13:00", "remaining_time": "5:12:09", "throughput": 992.51, "total_tokens": 774544}
+{"current_steps": 12, "total_steps": 250, "loss": 2.5155, "learning_rate": 0.0002982977617106871, "epoch": 0.04792810783824263, "percentage": 4.8, "elapsed_time": "0:15:49", "remaining_time": "5:13:56", "throughput": 989.39, "total_tokens": 939664}
+{"current_steps": 14, "total_steps": 250, "loss": 2.4476, "learning_rate": 0.0002976846501793808, "epoch": 0.05591612581128307, "percentage": 5.6, "elapsed_time": "0:18:19", "remaining_time": "5:09:00", "throughput": 992.34, "total_tokens": 1091408}
+{"current_steps": 16, "total_steps": 250, "loss": 2.4053, "learning_rate": 0.000296978257857637, "epoch": 0.06390414378432352, "percentage": 6.4, "elapsed_time": "0:21:01", "remaining_time": "5:07:35", "throughput": 992.14, "total_tokens": 1251968}
+{"current_steps": 18, "total_steps": 250, "loss": 2.4275, "learning_rate": 0.0002961790309179866, "epoch": 0.07189216175736396, "percentage": 7.2, "elapsed_time": "0:23:45", "remaining_time": "5:06:15", "throughput": 991.55, "total_tokens": 1413632}
+{"current_steps": 20, "total_steps": 250, "loss": 2.4095, "learning_rate": 0.00029528747416929463, "epoch": 0.0798801797304044, "percentage": 8.0, "elapsed_time": "0:26:12", "remaining_time": "5:01:22", "throughput": 993.12, "total_tokens": 1561616}
+{"current_steps": 22, "total_steps": 250, "loss": 2.4703, "learning_rate": 0.0002943041507379128, "epoch": 0.08786819770344484, "percentage": 8.8, "elapsed_time": "0:28:31", "remaining_time": "4:55:41", "throughput": 994.26, "total_tokens": 1702048}
+{"current_steps": 24, "total_steps": 250, "loss": 2.4129, "learning_rate": 0.0002932296817119964, "epoch": 0.09585621567648527, "percentage": 9.6, "elapsed_time": "0:30:55", "remaining_time": "4:51:16", "throughput": 995.28, "total_tokens": 1847168}
+{"current_steps": 26, "total_steps": 250, "loss": 2.4276, "learning_rate": 0.00029206474574921165, "epoch": 0.1038442336495257, "percentage": 10.4, "elapsed_time": "0:33:33", "remaining_time": "4:49:06", "throughput": 994.66, "total_tokens": 2002624}
+{"current_steps": 28, "total_steps": 250, "loss": 2.4062, "learning_rate": 0.0002908100786480811, "epoch": 0.11183225162256615, "percentage": 11.2, "elapsed_time": "0:36:18", "remaining_time": "4:47:50", "throughput": 992.99, "total_tokens": 2162992}
+{"current_steps": 30, "total_steps": 250, "loss": 2.4229, "learning_rate": 0.00028946647288323766, "epoch": 0.11982026959560658, "percentage": 12.0, "elapsed_time": "0:38:38", "remaining_time": "4:43:19", "throughput": 994.15, "total_tokens": 2304544}
+{"current_steps": 32, "total_steps": 250, "loss": 2.4247, "learning_rate": 0.00028803477710488055, "epoch": 0.12780828756864704, "percentage": 12.8, "elapsed_time": "0:40:56", "remaining_time": "4:38:57", "throughput": 994.88, "total_tokens": 2444336}
+{"current_steps": 34, "total_steps": 250, "loss": 2.4517, "learning_rate": 0.00028651589560274934, "epoch": 0.13579630554168748, "percentage": 13.6, "elapsed_time": "0:43:33", "remaining_time": "4:36:42", "throughput": 994.44, "total_tokens": 2598848}
+{"current_steps": 36, "total_steps": 250, "loss": 2.3632, "learning_rate": 0.00028491078773495564, "epoch": 0.14378432351472792, "percentage": 14.4, "elapsed_time": "0:45:59", "remaining_time": "4:33:26", "throughput": 994.78, "total_tokens": 2745520}
+{"current_steps": 38, "total_steps": 250, "loss": 2.5248, "learning_rate": 0.00028322046732203165, "epoch": 0.15177234148776836, "percentage": 15.2, "elapsed_time": "0:48:50", "remaining_time": "4:32:31", "throughput": 994.03, "total_tokens": 2913392}
+{"current_steps": 40, "total_steps": 250, "loss": 2.4143, "learning_rate": 0.0002814460020065795, "epoch": 0.1597603594608088, "percentage": 16.0, "elapsed_time": "0:51:10", "remaining_time": "4:28:40", "throughput": 994.48, "total_tokens": 3053600}
+{"current_steps": 42, "total_steps": 250, "loss": 2.4045, "learning_rate": 0.00027958851257892526, "epoch": 0.16774837743384924, "percentage": 16.8, "elapsed_time": "0:53:33", "remaining_time": "4:25:15", "throughput": 995.5, "total_tokens": 3199248}
+{"current_steps": 44, "total_steps": 250, "loss": 2.4382, "learning_rate": 0.00027764917226920377, "epoch": 0.17573639540688968, "percentage": 17.6, "elapsed_time": "0:55:35", "remaining_time": "4:20:15", "throughput": 996.71, "total_tokens": 3324464}
+{"current_steps": 46, "total_steps": 250, "loss": 2.4288, "learning_rate": 0.00027562920600632127, "epoch": 0.18372441337993012, "percentage": 18.4, "elapsed_time": "0:58:20", "remaining_time": "4:18:45", "throughput": 995.47, "total_tokens": 3485088}
+{"current_steps": 48, "total_steps": 250, "loss": 2.4689, "learning_rate": 0.0002735298896442641, "epoch": 0.19171243135297053, "percentage": 19.2, "elapsed_time": "1:00:49", "remaining_time": "4:16:00", "throughput": 995.96, "total_tokens": 3635152}
+{"current_steps": 50, "total_steps": 250, "loss": 2.395, "learning_rate": 0.0002713525491562421, "epoch": 0.19970044932601097, "percentage": 20.0, "elapsed_time": "1:03:21", "remaining_time": "4:13:27", "throughput": 996.16, "total_tokens": 3787152}
+{"current_steps": 52, "total_steps": 250, "loss": 2.3901, "learning_rate": 0.0002690985597971753, "epoch": 0.2076884672990514, "percentage": 20.8, "elapsed_time": "1:05:43", "remaining_time": "4:10:17", "throughput": 996.8, "total_tokens": 3931280}
+{"current_steps": 54, "total_steps": 250, "loss": 2.3819, "learning_rate": 0.0002667693452350535, "epoch": 0.21567648527209185, "percentage": 21.6, "elapsed_time": "1:08:16", "remaining_time": "4:07:49", "throughput": 996.81, "total_tokens": 4083536}
+{"current_steps": 56, "total_steps": 250, "loss": 2.444, "learning_rate": 0.0002643663766517172, "epoch": 0.2236645032451323, "percentage": 22.4, "elapsed_time": "1:10:53", "remaining_time": "4:05:36", "throughput": 996.6, "total_tokens": 4239440}
+{"current_steps": 58, "total_steps": 250, "loss": 2.3407, "learning_rate": 0.00026189117181362733, "epoch": 0.23165252121817273, "percentage": 23.2, "elapsed_time": "1:12:59", "remaining_time": "4:01:36", "throughput": 997.68, "total_tokens": 4369008}
+{"current_steps": 60, "total_steps": 250, "loss": 2.4137, "learning_rate": 0.0002593452941132117, "epoch": 0.23964053919121317, "percentage": 24.0, "elapsed_time": "1:15:35", "remaining_time": "3:59:23", "throughput": 997.73, "total_tokens": 4525680}
+{"current_steps": 62, "total_steps": 250, "loss": 2.3727, "learning_rate": 0.0002567303515813928, "epoch": 0.2476285571642536, "percentage": 24.8, "elapsed_time": "1:18:14", "remaining_time": "3:57:15", "throughput": 997.62, "total_tokens": 4683360}
+{"current_steps": 64, "total_steps": 250, "loss": 2.4705, "learning_rate": 0.0002540479958719207, "epoch": 0.2556165751372941, "percentage": 25.6, "elapsed_time": "1:20:45", "remaining_time": "3:54:43", "throughput": 997.47, "total_tokens": 4833520}
+{"current_steps": 66, "total_steps": 250, "loss": 2.2845, "learning_rate": 0.00025129992121815365, "epoch": 0.2636045931103345, "percentage": 26.4, "elapsed_time": "1:23:05", "remaining_time": "3:51:37", "throughput": 997.89, "total_tokens": 4974480}
+{"current_steps": 68, "total_steps": 250, "loss": 2.3124, "learning_rate": 0.00024848786336294346, "epoch": 0.27159261108337496, "percentage": 27.2, "elapsed_time": "1:25:07", "remaining_time": "3:47:49", "throughput": 998.48, "total_tokens": 5099616}
+{"current_steps": 70, "total_steps": 250, "loss": 2.4011, "learning_rate": 0.0002456135984623034, "epoch": 0.2795806290564154, "percentage": 28.0, "elapsed_time": "1:27:30", "remaining_time": "3:45:00", "throughput": 998.89, "total_tokens": 5244416}
+{"current_steps": 72, "total_steps": 250, "loss": 2.3147, "learning_rate": 0.00024267894196355015, "epoch": 0.28756864702945584, "percentage": 28.8, "elapsed_time": "1:29:56", "remaining_time": "3:42:20", "throughput": 999.22, "total_tokens": 5392128}
+{"current_steps": 74, "total_steps": 250, "loss": 2.3653, "learning_rate": 0.00023968574745862782, "epoch": 0.2955566650024963, "percentage": 29.6, "elapsed_time": "1:32:29", "remaining_time": "3:39:57", "throughput": 999.29, "total_tokens": 5545216}
+{"current_steps": 76, "total_steps": 250, "loss": 2.361, "learning_rate": 0.0002366359055133401, "epoch": 0.3035446829755367, "percentage": 30.4, "elapsed_time": "1:35:19", "remaining_time": "3:38:15", "throughput": 998.62, "total_tokens": 5712080}
+{"current_steps": 78, "total_steps": 250, "loss": 2.3499, "learning_rate": 0.0002335313424732282, "epoch": 0.31153270094857716, "percentage": 31.2, "elapsed_time": "1:37:47", "remaining_time": "3:35:38", "throughput": 998.56, "total_tokens": 5858800}
+{"current_steps": 80, "total_steps": 250, "loss": 2.3515, "learning_rate": 0.00023037401924684946, "epoch": 0.3195207189216176, "percentage": 32.0, "elapsed_time": "1:40:19", "remaining_time": "3:33:11", "throughput": 998.25, "total_tokens": 6008784}
+{"current_steps": 82, "total_steps": 250, "loss": 2.398, "learning_rate": 0.00022716593006722594, "epoch": 0.32750873689465804, "percentage": 32.8, "elapsed_time": "1:42:45", "remaining_time": "3:30:32", "throughput": 998.34, "total_tokens": 6155536}
+{"current_steps": 84, "total_steps": 250, "loss": 2.3678, "learning_rate": 0.00022390910123224373, "epoch": 0.3354967548676985, "percentage": 33.6, "elapsed_time": "1:45:17", "remaining_time": "3:28:03", "throughput": 998.33, "total_tokens": 6306576}
+{"current_steps": 86, "total_steps": 250, "loss": 2.4406, "learning_rate": 0.0002206055898247999, "epoch": 0.3434847728407389, "percentage": 34.4, "elapsed_time": "1:48:04", "remaining_time": "3:26:04", "throughput": 997.91, "total_tokens": 6470448}
+{"current_steps": 88, "total_steps": 250, "loss": 2.3589, "learning_rate": 0.00021725748241350486, "epoch": 0.35147279081377936, "percentage": 35.2, "elapsed_time": "1:50:29", "remaining_time": "3:23:23", "throughput": 998.17, "total_tokens": 6616864}
+{"current_steps": 90, "total_steps": 250, "loss": 2.3573, "learning_rate": 0.00021386689373476087, "epoch": 0.3594608087868198, "percentage": 36.0, "elapsed_time": "1:53:25", "remaining_time": "3:21:38", "throughput": 997.21, "total_tokens": 6786448}
+{"current_steps": 92, "total_steps": 250, "loss": 2.3993, "learning_rate": 0.0002104359653570494, "epoch": 0.36744882675986024, "percentage": 36.8, "elapsed_time": "1:56:18", "remaining_time": "3:19:44", "throughput": 996.64, "total_tokens": 6954720}
+{"current_steps": 94, "total_steps": 250, "loss": 2.4304, "learning_rate": 0.00020696686432827017, "epoch": 0.3754368447329007, "percentage": 37.6, "elapsed_time": "1:58:36", "remaining_time": "3:16:50", "throughput": 996.85, "total_tokens": 7094208}
+{"current_steps": 96, "total_steps": 250, "loss": 2.3126, "learning_rate": 0.00020346178180698758, "epoch": 0.38342486270594106, "percentage": 38.4, "elapsed_time": "2:00:44", "remaining_time": "3:13:41", "throughput": 997.64, "total_tokens": 7227440}
+{"current_steps": 98, "total_steps": 250, "loss": 2.3727, "learning_rate": 0.000199922931678448, "epoch": 0.3914128806789815, "percentage": 39.2, "elapsed_time": "2:02:55", "remaining_time": "3:10:40", "throughput": 998.19, "total_tokens": 7362608}
+{"current_steps": 100, "total_steps": 250, "loss": 2.3292, "learning_rate": 0.0001963525491562421, "epoch": 0.39940089865202194, "percentage": 40.0, "elapsed_time": "2:05:28", "remaining_time": "3:08:13", "throughput": 998.17, "total_tokens": 7515024}
+{"current_steps": 102, "total_steps": 250, "loss": 2.3322, "learning_rate": 0.0001927528893704964, "epoch": 0.4073889166250624, "percentage": 40.8, "elapsed_time": "2:08:06", "remaining_time": "3:05:52", "throughput": 997.94, "total_tokens": 7670624}
+{"current_steps": 2, "total_steps": 250, "loss": 2.5021, "learning_rate": 4.99921047320825e-05, "epoch": 0.00798801797304044, "percentage": 0.8, "elapsed_time": "0:02:44", "remaining_time": "5:40:03", "throughput": 986.97, "total_tokens": 162400}
+{"current_steps": 4, "total_steps": 250, "loss": 2.5086, "learning_rate": 4.996842391515044e-05, "epoch": 0.01597603594608088, "percentage": 1.6, "elapsed_time": "0:05:21", "remaining_time": "5:29:17", "throughput": 986.19, "total_tokens": 316832}
+{"current_steps": 6, "total_steps": 250, "loss": 2.4884, "learning_rate": 4.992897250651535e-05, "epoch": 0.023964053919121316, "percentage": 2.4, "elapsed_time": "0:07:38", "remaining_time": "5:10:49", "throughput": 995.56, "total_tokens": 456560}
+{"current_steps": 8, "total_steps": 250, "loss": 2.5476, "learning_rate": 4.987377542453251e-05, "epoch": 0.03195207189216176, "percentage": 3.2, "elapsed_time": "0:10:15", "remaining_time": "5:10:04", "throughput": 995.49, "total_tokens": 612256}
+{"current_steps": 10, "total_steps": 250, "loss": 2.5127, "learning_rate": 4.980286753286195e-05, "epoch": 0.0399400898652022, "percentage": 4.0, "elapsed_time": "0:12:59", "remaining_time": "5:11:42", "throughput": 993.92, "total_tokens": 774544}
+{"current_steps": 12, "total_steps": 250, "loss": 2.5413, "learning_rate": 4.971629361844785e-05, "epoch": 0.04792810783824263, "percentage": 4.8, "elapsed_time": "0:15:48", "remaining_time": "5:13:33", "throughput": 990.58, "total_tokens": 939664}
+{"current_steps": 14, "total_steps": 250, "loss": 2.4724, "learning_rate": 4.9614108363230135e-05, "epoch": 0.05591612581128307, "percentage": 5.6, "elapsed_time": "0:18:18", "remaining_time": "5:08:42", "throughput": 993.26, "total_tokens": 1091408}
+{"current_steps": 16, "total_steps": 250, "loss": 2.4269, "learning_rate": 4.949637630960617e-05, "epoch": 0.06390414378432352, "percentage": 6.4, "elapsed_time": "0:21:00", "remaining_time": "5:07:17", "throughput": 993.1, "total_tokens": 1251968}
+{"current_steps": 18, "total_steps": 250, "loss": 2.4497, "learning_rate": 4.9363171819664434e-05, "epoch": 0.07189216175736396, "percentage": 7.2, "elapsed_time": "0:23:44", "remaining_time": "5:05:58", "throughput": 992.44, "total_tokens": 1413632}
+{"current_steps": 20, "total_steps": 250, "loss": 2.4304, "learning_rate": 4.9214579028215776e-05, "epoch": 0.0798801797304044, "percentage": 8.0, "elapsed_time": "0:26:11", "remaining_time": "5:01:08", "throughput": 993.94, "total_tokens": 1561616}
+{"current_steps": 22, "total_steps": 250, "loss": 2.4962, "learning_rate": 4.905069178965215e-05, "epoch": 0.08786819770344484, "percentage": 8.8, "elapsed_time": "0:28:30", "remaining_time": "4:55:28", "throughput": 994.99, "total_tokens": 1702048}
+{"current_steps": 24, "total_steps": 250, "loss": 2.4427, "learning_rate": 4.887161361866608e-05, "epoch": 0.09585621567648527, "percentage": 9.6, "elapsed_time": "0:30:54", "remaining_time": "4:51:03", "throughput": 996.03, "total_tokens": 1847168}
+{"current_steps": 26, "total_steps": 250, "loss": 2.4515, "learning_rate": 4.867745762486861e-05, "epoch": 0.1038442336495257, "percentage": 10.4, "elapsed_time": "0:33:31", "remaining_time": "4:48:53", "throughput": 995.39, "total_tokens": 2002624}
+{"current_steps": 28, "total_steps": 250, "loss": 2.4309, "learning_rate": 4.846834644134686e-05, "epoch": 0.11183225162256615, "percentage": 11.2, "elapsed_time": "0:36:16", "remaining_time": "4:47:38", "throughput": 993.66, "total_tokens": 2162992}
+{"current_steps": 30, "total_steps": 250, "loss": 2.4502, "learning_rate": 4.8244412147206284e-05, "epoch": 0.11982026959560658, "percentage": 12.0, "elapsed_time": "0:38:36", "remaining_time": "4:43:07", "throughput": 994.83, "total_tokens": 2304544}
+{"current_steps": 32, "total_steps": 250, "loss": 2.4509, "learning_rate": 4.800579618414676e-05, "epoch": 0.12780828756864704, "percentage": 12.8, "elapsed_time": "0:40:55", "remaining_time": "4:38:45", "throughput": 995.62, "total_tokens": 2444336}
+{"current_steps": 34, "total_steps": 250, "loss": 2.4778, "learning_rate": 4.775264926712489e-05, "epoch": 0.13579630554168748, "percentage": 13.6, "elapsed_time": "0:43:31", "remaining_time": "4:36:32", "throughput": 995.05, "total_tokens": 2598848}
+{"current_steps": 36, "total_steps": 250, "loss": 2.3898, "learning_rate": 4.7485131289159276e-05, "epoch": 0.14378432351472792, "percentage": 14.4, "elapsed_time": "0:45:58", "remaining_time": "4:33:14", "throughput": 995.46, "total_tokens": 2745520}
+{"current_steps": 38, "total_steps": 250, "loss": 2.5515, "learning_rate": 4.720341122033862e-05, "epoch": 0.15177234148776836, "percentage": 15.2, "elapsed_time": "0:48:48", "remaining_time": "4:32:19", "throughput": 994.72, "total_tokens": 2913392}
+{"current_steps": 40, "total_steps": 250, "loss": 2.4457, "learning_rate": 4.690766700109659e-05, "epoch": 0.1597603594608088, "percentage": 16.0, "elapsed_time": "0:51:08", "remaining_time": "4:28:28", "throughput": 995.22, "total_tokens": 3053600}
+{"current_steps": 42, "total_steps": 250, "loss": 2.4336, "learning_rate": 4.659808542982088e-05, "epoch": 0.16774837743384924, "percentage": 16.8, "elapsed_time": "0:53:31", "remaining_time": "4:25:06", "throughput": 996.09, "total_tokens": 3199248}
+{"current_steps": 44, "total_steps": 250, "loss": 2.4655, "learning_rate": 4.6274862044867304e-05, "epoch": 0.17573639540688968, "percentage": 17.6, "elapsed_time": "0:55:32", "remaining_time": "4:20:03", "throughput": 997.5, "total_tokens": 3324464}
+{"current_steps": 46, "total_steps": 250, "loss": 2.4566, "learning_rate": 4.593820100105355e-05, "epoch": 0.18372441337993012, "percentage": 18.4, "elapsed_time": "0:58:18", "remaining_time": "4:18:34", "throughput": 996.21, "total_tokens": 3485088}
+{"current_steps": 48, "total_steps": 250, "loss": 2.4912, "learning_rate": 4.558831494071069e-05, "epoch": 0.19171243135297053, "percentage": 19.2, "elapsed_time": "1:00:47", "remaining_time": "4:15:48", "throughput": 996.69, "total_tokens": 3635152}
+{"current_steps": 50, "total_steps": 250, "loss": 2.4185, "learning_rate": 4.522542485937369e-05, "epoch": 0.19970044932601097, "percentage": 20.0, "elapsed_time": "1:03:19", "remaining_time": "4:13:16", "throughput": 996.88, "total_tokens": 3787152}
+{"current_steps": 52, "total_steps": 250, "loss": 2.4221, "learning_rate": 4.484975996619589e-05, "epoch": 0.2076884672990514, "percentage": 20.8, "elapsed_time": "1:05:41", "remaining_time": "4:10:06", "throughput": 997.5, "total_tokens": 3931280}
+{"current_steps": 54, "total_steps": 250, "loss": 2.4091, "learning_rate": 4.4461557539175594e-05, "epoch": 0.21567648527209185, "percentage": 21.6, "elapsed_time": "1:08:13", "remaining_time": "4:07:38", "throughput": 997.5, "total_tokens": 4083536}
+{"current_steps": 56, "total_steps": 250, "loss": 2.4697, "learning_rate": 4.40610627752862e-05, "epoch": 0.2236645032451323, "percentage": 22.4, "elapsed_time": "1:10:50", "remaining_time": "4:05:26", "throughput": 997.29, "total_tokens": 4239440}
+{"current_steps": 58, "total_steps": 250, "loss": 2.3675, "learning_rate": 4.3648528635604556e-05, "epoch": 0.23165252121817273, "percentage": 23.2, "elapsed_time": "1:12:56", "remaining_time": "4:01:26", "throughput": 998.36, "total_tokens": 4369008}
+{"current_steps": 60, "total_steps": 250, "loss": 2.4421, "learning_rate": 4.3224215685535294e-05, "epoch": 0.23964053919121317, "percentage": 24.0, "elapsed_time": "1:15:33", "remaining_time": "3:59:14", "throughput": 998.36, "total_tokens": 4525680}
+{"current_steps": 62, "total_steps": 250, "loss": 2.3973, "learning_rate": 4.278839193023214e-05, "epoch": 0.2476285571642536, "percentage": 24.8, "elapsed_time": "1:18:11", "remaining_time": "3:57:06", "throughput": 998.23, "total_tokens": 4683360}
+{"current_steps": 64, "total_steps": 250, "loss": 2.5022, "learning_rate": 4.234133264532012e-05, "epoch": 0.2556165751372941, "percentage": 25.6, "elapsed_time": "1:20:42", "remaining_time": "3:54:34", "throughput": 998.06, "total_tokens": 4833520}
+{"current_steps": 66, "total_steps": 250, "loss": 2.3089, "learning_rate": 4.188332020302561e-05, "epoch": 0.2636045931103345, "percentage": 26.4, "elapsed_time": "1:23:02", "remaining_time": "3:51:29", "throughput": 998.46, "total_tokens": 4974480}
+{"current_steps": 68, "total_steps": 250, "loss": 2.3378, "learning_rate": 4.1414643893823914e-05, "epoch": 0.27159261108337496, "percentage": 27.2, "elapsed_time": "1:25:04", "remaining_time": "3:47:42", "throughput": 999.02, "total_tokens": 5099616}
+{"current_steps": 70, "total_steps": 250, "loss": 2.4277, "learning_rate": 4.093559974371725e-05, "epoch": 0.2795806290564154, "percentage": 28.0, "elapsed_time": "1:27:27", "remaining_time": "3:44:53", "throughput": 999.43, "total_tokens": 5244416}
+{"current_steps": 72, "total_steps": 250, "loss": 2.3468, "learning_rate": 4.044649032725836e-05, "epoch": 0.28756864702945584, "percentage": 28.8, "elapsed_time": "1:29:53", "remaining_time": "3:42:13", "throughput": 999.76, "total_tokens": 5392128}
+{"current_steps": 74, "total_steps": 250, "loss": 2.3907, "learning_rate": 3.9947624576437975e-05, "epoch": 0.2955566650024963, "percentage": 29.6, "elapsed_time": "1:32:26", "remaining_time": "3:39:51", "throughput": 999.79, "total_tokens": 5545216}
+{"current_steps": 76, "total_steps": 250, "loss": 2.3878, "learning_rate": 3.943931758555669e-05, "epoch": 0.3035446829755367, "percentage": 30.4, "elapsed_time": "1:35:17", "remaining_time": "3:38:09", "throughput": 999.1, "total_tokens": 5712080}
+{"current_steps": 78, "total_steps": 250, "loss": 2.3853, "learning_rate": 3.8921890412204705e-05, "epoch": 0.31153270094857716, "percentage": 31.2, "elapsed_time": "1:37:44", "remaining_time": "3:35:31", "throughput": 999.04, "total_tokens": 5858800}
+{"current_steps": 80, "total_steps": 250, "loss": 2.3765, "learning_rate": 3.8395669874474915e-05, "epoch": 0.3195207189216176, "percentage": 32.0, "elapsed_time": "1:40:15", "remaining_time": "3:33:03", "throughput": 998.81, "total_tokens": 6008784}
+{"current_steps": 82, "total_steps": 250, "loss": 2.4277, "learning_rate": 3.786098834453766e-05, "epoch": 0.32750873689465804, "percentage": 32.8, "elapsed_time": "1:42:43", "remaining_time": "3:30:26", "throughput": 998.78, "total_tokens": 6155536}
+{"current_steps": 84, "total_steps": 250, "loss": 2.3935, "learning_rate": 3.731818353870729e-05, "epoch": 0.3354967548676985, "percentage": 33.6, "elapsed_time": "1:45:14", "remaining_time": "3:27:58", "throughput": 998.76, "total_tokens": 6306576}
+{"current_steps": 86, "total_steps": 250, "loss": 2.4679, "learning_rate": 3.6767598304133324e-05, "epoch": 0.3434847728407389, "percentage": 34.4, "elapsed_time": "1:48:00", "remaining_time": "3:25:58", "throughput": 998.38, "total_tokens": 6470448}
+{"current_steps": 88, "total_steps": 250, "loss": 2.3868, "learning_rate": 3.6209580402250815e-05, "epoch": 0.35147279081377936, "percentage": 35.2, "elapsed_time": "1:50:25", "remaining_time": "3:23:17", "throughput": 998.63, "total_tokens": 6616864}
+{"current_steps": 90, "total_steps": 250, "loss": 2.3859, "learning_rate": 3.564448228912682e-05, "epoch": 0.3594608087868198, "percentage": 36.0, "elapsed_time": "1:53:22", "remaining_time": "3:21:33", "throughput": 997.62, "total_tokens": 6786448}
+{"current_steps": 92, "total_steps": 250, "loss": 2.4216, "learning_rate": 3.507266089284157e-05, "epoch": 0.36744882675986024, "percentage": 36.8, "elapsed_time": "1:56:14", "remaining_time": "3:19:38", "throughput": 997.13, "total_tokens": 6954720}
+{"current_steps": 94, "total_steps": 250, "loss": 2.4611, "learning_rate": 3.4494477388045035e-05, "epoch": 0.3754368447329007, "percentage": 37.6, "elapsed_time": "1:58:33", "remaining_time": "3:16:44", "throughput": 997.32, "total_tokens": 7094208}
+{"current_steps": 96, "total_steps": 250, "loss": 2.3384, "learning_rate": 3.3910296967831266e-05, "epoch": 0.38342486270594106, "percentage": 38.4, "elapsed_time": "2:00:41", "remaining_time": "3:13:36", "throughput": 998.11, "total_tokens": 7227440}
+{"current_steps": 98, "total_steps": 250, "loss": 2.4074, "learning_rate": 3.332048861307467e-05, "epoch": 0.3914128806789815, "percentage": 39.2, "elapsed_time": "2:02:52", "remaining_time": "3:10:34", "throughput": 998.66, "total_tokens": 7362608}
+{"current_steps": 100, "total_steps": 250, "loss": 2.3572, "learning_rate": 3.272542485937369e-05, "epoch": 0.39940089865202194, "percentage": 40.0, "elapsed_time": "2:05:25", "remaining_time": "3:08:07", "throughput": 998.63, "total_tokens": 7515024}
+{"current_steps": 102, "total_steps": 250, "loss": 2.3579, "learning_rate": 3.21254815617494e-05, "epoch": 0.4073889166250624, "percentage": 40.8, "elapsed_time": "2:08:02", "remaining_time": "3:05:47", "throughput": 998.41, "total_tokens": 7670624}
+{"current_steps": 104, "total_steps": 250, "loss": 2.3728, "learning_rate": 3.152103765724743e-05, "epoch": 0.4153769345981028, "percentage": 41.6, "elapsed_time": "2:10:28", "remaining_time": "3:03:09", "throughput": 998.66, "total_tokens": 7817648}
+{"current_steps": 106, "total_steps": 250, "loss": 2.2712, "learning_rate": 3.091247492559312e-05, "epoch": 0.42336495257114326, "percentage": 42.4, "elapsed_time": "2:12:58", "remaining_time": "3:00:38", "throughput": 998.75, "total_tokens": 7968432}
+{"current_steps": 108, "total_steps": 250, "loss": 2.4054, "learning_rate": 3.0300177748051373e-05, "epoch": 0.4313529705441837, "percentage": 43.2, "elapsed_time": "2:15:40", "remaining_time": "2:58:23", "throughput": 998.38, "total_tokens": 8127312}
+{"current_steps": 110, "total_steps": 250, "loss": 2.3966, "learning_rate": 2.9684532864643122e-05, "epoch": 0.43934098851722414, "percentage": 44.0, "elapsed_time": "2:18:08", "remaining_time": "2:55:49", "throughput": 998.32, "total_tokens": 8275008}
+{"current_steps": 112, "total_steps": 250, "loss": 2.4478, "learning_rate": 2.9065929129872094e-05, "epoch": 0.4473290064902646, "percentage": 44.8, "elapsed_time": "2:20:40", "remaining_time": "2:53:19", "throughput": 998.23, "total_tokens": 8425536}
+{"current_steps": 114, "total_steps": 250, "loss": 2.4386, "learning_rate": 2.844475726711595e-05, "epoch": 0.455317024463305, "percentage": 45.6, "elapsed_time": "2:23:09", "remaining_time": "2:50:46", "throughput": 998.21, "total_tokens": 8573776}
+{"current_steps": 116, "total_steps": 250, "loss": 2.4176, "learning_rate": 2.782140962183704e-05, "epoch": 0.46330504243634546, "percentage": 46.4, "elapsed_time": "2:25:44", "remaining_time": "2:48:21", "throughput": 998.29, "total_tokens": 8729200}
+{"current_steps": 118, "total_steps": 250, "loss": 2.3505, "learning_rate": 2.7196279913768584e-05, "epoch": 0.4712930604093859, "percentage": 47.2, "elapsed_time": "2:28:21", "remaining_time": "2:45:57", "throughput": 998.13, "total_tokens": 8884720}
+{"current_steps": 120, "total_steps": 250, "loss": 2.3867, "learning_rate": 2.656976298823284e-05, "epoch": 0.47928107838242634, "percentage": 48.0, "elapsed_time": "2:30:54", "remaining_time": "2:43:28", "throughput": 997.88, "total_tokens": 9035088}
+{"current_steps": 122, "total_steps": 250, "loss": 2.4321, "learning_rate": 2.594225456674837e-05, "epoch": 0.4872690963554668, "percentage": 48.8, "elapsed_time": "2:33:28", "remaining_time": "2:41:00", "throughput": 997.87, "total_tokens": 9188528}
+{"current_steps": 124, "total_steps": 250, "loss": 2.4392, "learning_rate": 2.531415099708382e-05, "epoch": 0.4952571143285072, "percentage": 49.6, "elapsed_time": "2:36:15", "remaining_time": "2:38:47", "throughput": 997.54, "total_tokens": 9352752}
+{"current_steps": 126, "total_steps": 250, "loss": 2.4005, "learning_rate": 2.4685849002916183e-05, "epoch": 0.5032451323015477, "percentage": 50.4, "elapsed_time": "2:38:40", "remaining_time": "2:36:09", "throughput": 997.62, "total_tokens": 9497840}
+{"current_steps": 128, "total_steps": 250, "loss": 2.309, "learning_rate": 2.4057745433251635e-05, "epoch": 0.5112331502745882, "percentage": 51.2, "elapsed_time": "2:41:16", "remaining_time": "2:33:43", "throughput": 997.73, "total_tokens": 9654816}
+{"current_steps": 130, "total_steps": 250, "loss": 2.522, "learning_rate": 2.3430237011767167e-05, "epoch": 0.5192211682476285, "percentage": 52.0, "elapsed_time": "2:43:59", "remaining_time": "2:31:22", "throughput": 997.5, "total_tokens": 9814944}
+{"current_steps": 132, "total_steps": 250, "loss": 2.4151, "learning_rate": 2.280372008623142e-05, "epoch": 0.527209186220669, "percentage": 52.8, "elapsed_time": "2:46:14", "remaining_time": "2:28:36", "throughput": 997.77, "total_tokens": 9951952}
+{"current_steps": 134, "total_steps": 250, "loss": 2.3723, "learning_rate": 2.217859037816296e-05, "epoch": 0.5351972041937094, "percentage": 53.6, "elapsed_time": "2:48:58", "remaining_time": "2:26:16", "throughput": 997.45, "total_tokens": 10112272}
+{"current_steps": 136, "total_steps": 250, "loss": 2.416, "learning_rate": 2.155524273288405e-05, "epoch": 0.5431852221667499, "percentage": 54.4, "elapsed_time": "2:51:51", "remaining_time": "2:24:03", "throughput": 997.06, "total_tokens": 10281344}
+{"current_steps": 138, "total_steps": 250, "loss": 2.5335, "learning_rate": 2.0934070870127912e-05, "epoch": 0.5511732401397903, "percentage": 55.2, "elapsed_time": "2:53:55", "remaining_time": "2:21:09", "throughput": 997.52, "total_tokens": 10409584}
+{"current_steps": 140, "total_steps": 250, "loss": 2.4946, "learning_rate": 2.031546713535688e-05, "epoch": 0.5591612581128308, "percentage": 56.0, "elapsed_time": "2:56:43", "remaining_time": "2:18:51", "throughput": 997.17, "total_tokens": 10573840}
+{"current_steps": 142, "total_steps": 250, "loss": 2.3169, "learning_rate": 1.969982225194864e-05, "epoch": 0.5671492760858712, "percentage": 56.8, "elapsed_time": "2:59:20", "remaining_time": "2:16:23", "throughput": 997.15, "total_tokens": 10729760}
+{"current_steps": 144, "total_steps": 250, "loss": 2.3797, "learning_rate": 1.908752507440689e-05, "epoch": 0.5751372940589117, "percentage": 57.6, "elapsed_time": "3:01:52", "remaining_time": "2:13:52", "throughput": 997.18, "total_tokens": 10881664}
+{"current_steps": 146, "total_steps": 250, "loss": 2.4498, "learning_rate": 1.8478962342752583e-05, "epoch": 0.5831253120319521, "percentage": 58.4, "elapsed_time": "3:04:25", "remaining_time": "2:11:22", "throughput": 997.2, "total_tokens": 11034352}
+{"current_steps": 148, "total_steps": 250, "loss": 2.3818, "learning_rate": 1.7874518438250597e-05, "epoch": 0.5911133300049926, "percentage": 59.2, "elapsed_time": "3:06:45", "remaining_time": "2:08:42", "throughput": 997.38, "total_tokens": 11175952}
+{"current_steps": 150, "total_steps": 250, "loss": 2.3818, "learning_rate": 1.7274575140626318e-05, "epoch": 0.5991013479780329, "percentage": 60.0, "elapsed_time": "3:09:00", "remaining_time": "2:06:00", "throughput": 997.69, "total_tokens": 11314112}
+{"current_steps": 152, "total_steps": 250, "loss": 2.4073, "learning_rate": 1.6679511386925337e-05, "epoch": 0.6070893659510734, "percentage": 60.8, "elapsed_time": "3:11:51", "remaining_time": "2:03:42", "throughput": 997.38, "total_tokens": 11481792}
+{"current_steps": 154, "total_steps": 250, "loss": 2.3467, "learning_rate": 1.6089703032168733e-05, "epoch": 0.6150773839241138, "percentage": 61.6, "elapsed_time": "3:14:44", "remaining_time": "2:01:23", "throughput": 996.97, "total_tokens": 11649040}
+{"current_steps": 156, "total_steps": 250, "loss": 2.4047, "learning_rate": 1.5505522611954975e-05, "epoch": 0.6230654018971543, "percentage": 62.4, "elapsed_time": "3:17:07", "remaining_time": "1:58:46", "throughput": 996.99, "total_tokens": 11791488}
+{"current_steps": 158, "total_steps": 250, "loss": 2.2998, "learning_rate": 1.4927339107158437e-05, "epoch": 0.6310534198701947, "percentage": 63.2, "elapsed_time": "3:19:38", "remaining_time": "1:56:14", "throughput": 996.81, "total_tokens": 11940144}
+{"current_steps": 160, "total_steps": 250, "loss": 2.383, "learning_rate": 1.4355517710873184e-05, "epoch": 0.6390414378432352, "percentage": 64.0, "elapsed_time": "3:22:16", "remaining_time": "1:53:46", "throughput": 996.79, "total_tokens": 12097648}
+{"current_steps": 162, "total_steps": 250, "loss": 2.3525, "learning_rate": 1.3790419597749199e-05, "epoch": 0.6470294558162756, "percentage": 64.8, "elapsed_time": "3:24:53", "remaining_time": "1:51:17", "throughput": 996.74, "total_tokens": 12253152}
+{"current_steps": 164, "total_steps": 250, "loss": 2.4133, "learning_rate": 1.3232401695866687e-05, "epoch": 0.6550174737893161, "percentage": 65.6, "elapsed_time": "3:27:33", "remaining_time": "1:48:50", "throughput": 996.51, "total_tokens": 12410080}
+{"current_steps": 166, "total_steps": 250, "loss": 2.3677, "learning_rate": 1.2681816461292715e-05, "epoch": 0.6630054917623565, "percentage": 66.4, "elapsed_time": "3:29:44", "remaining_time": "1:46:08", "throughput": 996.82, "total_tokens": 12544848}
+{"current_steps": 168, "total_steps": 250, "loss": 2.4215, "learning_rate": 1.2139011655462337e-05, "epoch": 0.670993509735397, "percentage": 67.2, "elapsed_time": "3:32:22", "remaining_time": "1:43:39", "throughput": 996.77, "total_tokens": 12701808}
+{"current_steps": 170, "total_steps": 250, "loss": 2.3162, "learning_rate": 1.1604330125525079e-05, "epoch": 0.6789815277084373, "percentage": 68.0, "elapsed_time": "3:34:48", "remaining_time": "1:41:05", "throughput": 996.68, "total_tokens": 12845840}
+{"current_steps": 172, "total_steps": 250, "loss": 2.4129, "learning_rate": 1.107810958779531e-05, "epoch": 0.6869695456814778, "percentage": 68.8, "elapsed_time": "3:37:09", "remaining_time": "1:38:28", "throughput": 996.83, "total_tokens": 12988144}
+{"current_steps": 174, "total_steps": 250, "loss": 2.4046, "learning_rate": 1.0560682414443315e-05, "epoch": 0.6949575636545182, "percentage": 69.6, "elapsed_time": "3:39:29", "remaining_time": "1:35:51", "throughput": 997.02, "total_tokens": 13129808}
+{"current_steps": 176, "total_steps": 250, "loss": 2.3596, "learning_rate": 1.0052375423562038e-05, "epoch": 0.7029455816275587, "percentage": 70.4, "elapsed_time": "3:41:47", "remaining_time": "1:33:15", "throughput": 997.1, "total_tokens": 13269264}
+{"current_steps": 178, "total_steps": 250, "loss": 2.3047, "learning_rate": 9.553509672741645e-06, "epoch": 0.7109335996005991, "percentage": 71.2, "elapsed_time": "3:44:16", "remaining_time": "1:30:43", "throughput": 997.07, "total_tokens": 13417184}
+{"current_steps": 180, "total_steps": 250, "loss": 2.4177, "learning_rate": 9.064400256282757e-06, "epoch": 0.7189216175736396, "percentage": 72.0, "elapsed_time": "3:46:41", "remaining_time": "1:28:09", "throughput": 997.03, "total_tokens": 13561008}
+{"current_steps": 182, "total_steps": 250, "loss": 2.4451, "learning_rate": 8.585356106176094e-06, "epoch": 0.72690963554668, "percentage": 72.8, "elapsed_time": "3:49:05", "remaining_time": "1:25:35", "throughput": 997.19, "total_tokens": 13706976}
+{"current_steps": 184, "total_steps": 250, "loss": 2.3997, "learning_rate": 8.116679796974388e-06, "epoch": 0.7348976535197205, "percentage": 73.6, "elapsed_time": "3:51:09", "remaining_time": "1:22:55", "throughput": 997.55, "total_tokens": 13835936}
+{"current_steps": 186, "total_steps": 250, "loss": 2.412, "learning_rate": 7.65866735467988e-06, "epoch": 0.7428856714927609, "percentage": 74.4, "elapsed_time": "3:53:11", "remaining_time": "1:20:14", "throughput": 997.91, "total_tokens": 13962144}
+{"current_steps": 188, "total_steps": 250, "loss": 2.4054, "learning_rate": 7.211608069767867e-06, "epoch": 0.7508736894658014, "percentage": 75.2, "elapsed_time": "3:56:02", "remaining_time": "1:17:50", "throughput": 997.61, "total_tokens": 14128800}
+{"current_steps": 190, "total_steps": 250, "loss": 2.4417, "learning_rate": 6.775784314464717e-06, "epoch": 0.7588617074388417, "percentage": 76.0, "elapsed_time": "3:58:32", "remaining_time": "1:15:19", "throughput": 997.62, "total_tokens": 14278288}
+{"current_steps": 192, "total_steps": 250, "loss": 2.3358, "learning_rate": 6.3514713643954475e-06, "epoch": 0.7668497254118821, "percentage": 76.8, "elapsed_time": "4:01:04", "remaining_time": "1:12:49", "throughput": 997.64, "total_tokens": 14429936}
+{"current_steps": 194, "total_steps": 250, "loss": 2.5089, "learning_rate": 5.9389372247138e-06, "epoch": 0.7748377433849226, "percentage": 77.6, "elapsed_time": "4:03:18", "remaining_time": "1:10:14", "throughput": 997.85, "total_tokens": 14567552}
+{"current_steps": 196, "total_steps": 250, "loss": 2.4246, "learning_rate": 5.538442460824417e-06, "epoch": 0.782825761357963, "percentage": 78.4, "elapsed_time": "4:05:33", "remaining_time": "1:07:39", "throughput": 998.01, "total_tokens": 14704528}
+{"current_steps": 198, "total_steps": 250, "loss": 2.369, "learning_rate": 5.150240033804116e-06, "epoch": 0.7908137793310035, "percentage": 79.2, "elapsed_time": "4:07:52", "remaining_time": "1:05:05", "throughput": 998.23, "total_tokens": 14846192}
+{"current_steps": 200, "total_steps": 250, "loss": 2.4204, "learning_rate": 4.7745751406263165e-06, "epoch": 0.7988017973040439, "percentage": 80.0, "elapsed_time": "4:10:19", "remaining_time": "1:02:34", "throughput": 998.28, "total_tokens": 14993936}
+{"current_steps": 202, "total_steps": 250, "loss": 2.3141, "learning_rate": 4.411685059289314e-06, "epoch": 0.8067898152770844, "percentage": 80.8, "elapsed_time": "4:12:39", "remaining_time": "1:00:02", "throughput": 998.43, "total_tokens": 15136240}
+{"current_steps": 204, "total_steps": 250, "loss": 2.3841, "learning_rate": 4.061798998946459e-06, "epoch": 0.8147778332501248, "percentage": 81.6, "elapsed_time": "4:14:57", "remaining_time": "0:57:29", "throughput": 998.54, "total_tokens": 15274672}
+{"current_steps": 206, "total_steps": 250, "loss": 2.3653, "learning_rate": 3.725137955132707e-06, "epoch": 0.8227658512231653, "percentage": 82.4, "elapsed_time": "4:17:18", "remaining_time": "0:54:57", "throughput": 998.67, "total_tokens": 15417920}
+{"current_steps": 208, "total_steps": 250, "loss": 2.4382, "learning_rate": 3.4019145701791184e-06, "epoch": 0.8307538691962056, "percentage": 83.2, "elapsed_time": "4:19:37", "remaining_time": "0:52:25", "throughput": 998.73, "total_tokens": 15557920}
+{"current_steps": 210, "total_steps": 250, "loss": 2.4455, "learning_rate": 3.092332998903416e-06, "epoch": 0.8387418871692461, "percentage": 84.0, "elapsed_time": "4:21:42", "remaining_time": "0:49:50", "throughput": 999.09, "total_tokens": 15687968}
+{"current_steps": 212, "total_steps": 250, "loss": 2.4322, "learning_rate": 2.7965887796613884e-06, "epoch": 0.8467299051422865, "percentage": 84.8, "elapsed_time": "4:24:17", "remaining_time": "0:47:22", "throughput": 999.1, "total_tokens": 15843072}
+{"current_steps": 214, "total_steps": 250, "loss": 2.4433, "learning_rate": 2.514868710840723e-06, "epoch": 0.854717923115327, "percentage": 85.6, "elapsed_time": "4:26:59", "remaining_time": "0:44:54", "throughput": 998.92, "total_tokens": 16002112}
+{"current_steps": 216, "total_steps": 250, "loss": 2.4399, "learning_rate": 2.2473507328751086e-06, "epoch": 0.8627059410883674, "percentage": 86.4, "elapsed_time": "4:29:08", "remaining_time": "0:42:21", "throughput": 999.17, "total_tokens": 16135328}
+{"current_steps": 218, "total_steps": 250, "loss": 2.378, "learning_rate": 1.9942038158532407e-06, "epoch": 0.8706939590614079, "percentage": 87.2, "elapsed_time": "4:31:49", "remaining_time": "0:39:54", "throughput": 999.01, "total_tokens": 16293008}
+{"current_steps": 220, "total_steps": 250, "loss": 2.3874, "learning_rate": 1.7555878527937164e-06, "epoch": 0.8786819770344483, "percentage": 88.0, "elapsed_time": "4:34:16", "remaining_time": "0:37:24", "throughput": 999.09, "total_tokens": 16441024}
+{"current_steps": 222, "total_steps": 250, "loss": 2.4028, "learning_rate": 1.5316535586531483e-06, "epoch": 0.8866699950074888, "percentage": 88.8, "elapsed_time": "4:36:40", "remaining_time": "0:34:53", "throughput": 999.21, "total_tokens": 16587616}
+{"current_steps": 224, "total_steps": 250, "loss": 2.3372, "learning_rate": 1.3225423751313942e-06, "epoch": 0.8946580129805292, "percentage": 89.6, "elapsed_time": "4:39:02", "remaining_time": "0:32:23", "throughput": 999.27, "total_tokens": 16730800}
+{"current_steps": 226, "total_steps": 250, "loss": 2.4288, "learning_rate": 1.1283863813339263e-06, "epoch": 0.9026460309535697, "percentage": 90.4, "elapsed_time": "4:41:37", "remaining_time": "0:29:54", "throughput": 999.31, "total_tokens": 16886144}
+{"current_steps": 228, "total_steps": 250, "loss": 2.3483, "learning_rate": 9.493082103478517e-07, "epoch": 0.91063404892661, "percentage": 91.2, "elapsed_time": "4:44:13", "remaining_time": "0:27:25", "throughput": 999.16, "total_tokens": 17038816}
+{"current_steps": 230, "total_steps": 250, "loss": 2.4648, "learning_rate": 7.854209717842231e-07, "epoch": 0.9186220668996505, "percentage": 92.0, "elapsed_time": "4:46:23", "remaining_time": "0:24:54", "throughput": 999.34, "total_tokens": 17171792}
+{"current_steps": 232, "total_steps": 250, "loss": 2.4327, "learning_rate": 6.368281803355691e-07, "epoch": 0.9266100848726909, "percentage": 92.8, "elapsed_time": "4:48:56", "remaining_time": "0:22:25", "throughput": 999.34, "total_tokens": 17324752}
+{"current_steps": 234, "total_steps": 250, "loss": 2.3037, "learning_rate": 5.036236903938285e-07, "epoch": 0.9345981028457314, "percentage": 93.6, "elapsed_time": "4:51:39", "remaining_time": "0:19:56", "throughput": 999.16, "total_tokens": 17485168}
+{"current_steps": 236, "total_steps": 250, "loss": 2.4094, "learning_rate": 3.8589163676986674e-07, "epoch": 0.9425861208187718, "percentage": 94.4, "elapsed_time": "4:54:08", "remaining_time": "0:17:26", "throughput": 999.11, "total_tokens": 17632832}
+{"current_steps": 238, "total_steps": 250, "loss": 2.3348, "learning_rate": 2.8370638155215123e-07, "epoch": 0.9505741387918123, "percentage": 95.2, "elapsed_time": "4:56:39", "remaining_time": "0:14:57", "throughput": 999.03, "total_tokens": 17781744}
+{"current_steps": 240, "total_steps": 250, "loss": 2.3979, "learning_rate": 1.9713246713805588e-07, "epoch": 0.9585621567648527, "percentage": 96.0, "elapsed_time": "4:59:44", "remaining_time": "0:12:29", "throughput": 998.58, "total_tokens": 17959392}
+{"current_steps": 242, "total_steps": 250, "loss": 2.346, "learning_rate": 1.2622457546749567e-07, "epoch": 0.9665501747378932, "percentage": 96.8, "elapsed_time": "5:02:29", "remaining_time": "0:09:59", "throughput": 998.47, "total_tokens": 18121744}
+{"current_steps": 244, "total_steps": 250, "loss": 2.4486, "learning_rate": 7.102749348465165e-08, "epoch": 0.9745381927109336, "percentage": 97.6, "elapsed_time": "5:05:03", "remaining_time": "0:07:30", "throughput": 998.39, "total_tokens": 18273856}
+{"current_steps": 246, "total_steps": 250, "loss": 2.3959, "learning_rate": 3.157608484956332e-08, "epoch": 0.982526210683974, "percentage": 98.4, "elapsed_time": "5:07:14", "remaining_time": "0:04:59", "throughput": 998.56, "total_tokens": 18407456}
+{"current_steps": 248, "total_steps": 250, "loss": 2.4287, "learning_rate": 7.895267917501504e-09, "epoch": 0.9905142286570144, "percentage": 99.2, "elapsed_time": "5:09:43", "remaining_time": "0:02:29", "throughput": 998.52, "total_tokens": 18555776}
+{"current_steps": 250, "total_steps": 250, "loss": 2.4911, "learning_rate": 0.0, "epoch": 0.9985022466300549, "percentage": 100.0, "elapsed_time": "5:11:44", "remaining_time": "0:00:00", "throughput": 998.87, "total_tokens": 18683616}
+{"current_steps": 250, "total_steps": 250, "epoch": 0.9985022466300549, "percentage": 100.0, "elapsed_time": "5:11:48", "remaining_time": "0:00:00", "throughput": 998.69, "total_tokens": 18683616}

trainer_state.json

@@ -0,0 +1,1043 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9985022466300549,
+  "eval_steps": 500,
+  "global_step": 250,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.00798801797304044,
+      "grad_norm": 0.02341790311038494,
+      "learning_rate": 4.99921047320825e-05,
+      "loss": 2.5021,
+      "num_input_tokens_seen": 162400,
+      "step": 2
+    },
+    {
+      "epoch": 0.01597603594608088,
+      "grad_norm": 0.030116591602563858,
+      "learning_rate": 4.996842391515044e-05,
+      "loss": 2.5086,
+      "num_input_tokens_seen": 316832,
+      "step": 4
+    },
+    {
+      "epoch": 0.023964053919121316,
+      "grad_norm": 0.03529619425535202,
+      "learning_rate": 4.992897250651535e-05,
+      "loss": 2.4884,
+      "num_input_tokens_seen": 456560,
+      "step": 6
+    },
+    {
+      "epoch": 0.03195207189216176,
+      "grad_norm": 0.028305748477578163,
+      "learning_rate": 4.987377542453251e-05,
+      "loss": 2.5476,
+      "num_input_tokens_seen": 612256,
+      "step": 8
+    },
+    {
+      "epoch": 0.0399400898652022,
+      "grad_norm": 0.02712586335837841,
+      "learning_rate": 4.980286753286195e-05,
+      "loss": 2.5127,
+      "num_input_tokens_seen": 774544,
+      "step": 10
+    },
+    {
+      "epoch": 0.04792810783824263,
+      "grad_norm": 0.029004713520407677,
+      "learning_rate": 4.971629361844785e-05,
+      "loss": 2.5413,
+      "num_input_tokens_seen": 939664,
+      "step": 12
+    },
+    {
+      "epoch": 0.05591612581128307,
+      "grad_norm": 0.02819664776325226,
+      "learning_rate": 4.9614108363230135e-05,
+      "loss": 2.4724,
+      "num_input_tokens_seen": 1091408,
+      "step": 14
+    },
+    {
+      "epoch": 0.06390414378432352,
+      "grad_norm": 0.025089334696531296,
+      "learning_rate": 4.949637630960617e-05,
+      "loss": 2.4269,
+      "num_input_tokens_seen": 1251968,
+      "step": 16
+    },
+    {
+      "epoch": 0.07189216175736396,
+      "grad_norm": 0.027914991602301598,
+      "learning_rate": 4.9363171819664434e-05,
+      "loss": 2.4497,
+      "num_input_tokens_seen": 1413632,
+      "step": 18
+    },
+    {
+      "epoch": 0.0798801797304044,
+      "grad_norm": 0.029010389000177383,
+      "learning_rate": 4.9214579028215776e-05,
+      "loss": 2.4304,
+      "num_input_tokens_seen": 1561616,
+      "step": 20
+    },
+    {
+      "epoch": 0.08786819770344484,
+      "grad_norm": 0.032729391008615494,
+      "learning_rate": 4.905069178965215e-05,
+      "loss": 2.4962,
+      "num_input_tokens_seen": 1702048,
+      "step": 22
+    },
+    {
+      "epoch": 0.09585621567648527,
+      "grad_norm": 0.034885670989751816,
+      "learning_rate": 4.887161361866608e-05,
+      "loss": 2.4427,
+      "num_input_tokens_seen": 1847168,
+      "step": 24
+    },
+    {
+      "epoch": 0.1038442336495257,
+      "grad_norm": 0.028687166050076485,
+      "learning_rate": 4.867745762486861e-05,
+      "loss": 2.4515,
+      "num_input_tokens_seen": 2002624,
+      "step": 26
+    },
+    {
+      "epoch": 0.11183225162256615,
+      "grad_norm": 0.02790650725364685,
+      "learning_rate": 4.846834644134686e-05,
+      "loss": 2.4309,
+      "num_input_tokens_seen": 2162992,
+      "step": 28
+    },
+    {
+      "epoch": 0.11982026959560658,
+      "grad_norm": 0.0356418751180172,
+      "learning_rate": 4.8244412147206284e-05,
+      "loss": 2.4502,
+      "num_input_tokens_seen": 2304544,
+      "step": 30
+    },
+    {
+      "epoch": 0.12780828756864704,
+      "grad_norm": 0.03653424605727196,
+      "learning_rate": 4.800579618414676e-05,
+      "loss": 2.4509,
+      "num_input_tokens_seen": 2444336,
+      "step": 32
+    },
+    {
+      "epoch": 0.13579630554168748,
+      "grad_norm": 0.03637837618589401,
+      "learning_rate": 4.775264926712489e-05,
+      "loss": 2.4778,
+      "num_input_tokens_seen": 2598848,
+      "step": 34
+    },
+    {
+      "epoch": 0.14378432351472792,
+      "grad_norm": 0.03624645993113518,
+      "learning_rate": 4.7485131289159276e-05,
+      "loss": 2.3898,
+      "num_input_tokens_seen": 2745520,
+      "step": 36
+    },
+    {
+      "epoch": 0.15177234148776836,
+      "grad_norm": 0.039211999624967575,
+      "learning_rate": 4.720341122033862e-05,
+      "loss": 2.5515,
+      "num_input_tokens_seen": 2913392,
+      "step": 38
+    },
+    {
+      "epoch": 0.1597603594608088,
+      "grad_norm": 0.04233478382229805,
+      "learning_rate": 4.690766700109659e-05,
+      "loss": 2.4457,
+      "num_input_tokens_seen": 3053600,
+      "step": 40
+    },
+    {
+      "epoch": 0.16774837743384924,
+      "grad_norm": 0.03884820267558098,
+      "learning_rate": 4.659808542982088e-05,
+      "loss": 2.4336,
+      "num_input_tokens_seen": 3199248,
+      "step": 42
+    },
+    {
+      "epoch": 0.17573639540688968,
+      "grad_norm": 0.04048454761505127,
+      "learning_rate": 4.6274862044867304e-05,
+      "loss": 2.4655,
+      "num_input_tokens_seen": 3324464,
+      "step": 44
+    },
+    {
+      "epoch": 0.18372441337993012,
+      "grad_norm": 0.034897685050964355,
+      "learning_rate": 4.593820100105355e-05,
+      "loss": 2.4566,
+      "num_input_tokens_seen": 3485088,
+      "step": 46
+    },
+    {
+      "epoch": 0.19171243135297053,
+      "grad_norm": 0.04081996530294418,
+      "learning_rate": 4.558831494071069e-05,
+      "loss": 2.4912,
+      "num_input_tokens_seen": 3635152,
+      "step": 48
+    },
+    {
+      "epoch": 0.19970044932601097,
+      "grad_norm": 0.03764244541525841,
+      "learning_rate": 4.522542485937369e-05,
+      "loss": 2.4185,
+      "num_input_tokens_seen": 3787152,
+      "step": 50
+    },
+    {
+      "epoch": 0.2076884672990514,
+      "grad_norm": 0.04559960216283798,
+      "learning_rate": 4.484975996619589e-05,
+      "loss": 2.4221,
+      "num_input_tokens_seen": 3931280,
+      "step": 52
+    },
+    {
+      "epoch": 0.21567648527209185,
+      "grad_norm": 0.03996207192540169,
+      "learning_rate": 4.4461557539175594e-05,
+      "loss": 2.4091,
+      "num_input_tokens_seen": 4083536,
+      "step": 54
+    },
+    {
+      "epoch": 0.2236645032451323,
+      "grad_norm": 0.042057909071445465,
+      "learning_rate": 4.40610627752862e-05,
+      "loss": 2.4697,
+      "num_input_tokens_seen": 4239440,
+      "step": 56
+    },
+    {
+      "epoch": 0.23165252121817273,
+      "grad_norm": 0.04598196595907211,
+      "learning_rate": 4.3648528635604556e-05,
+      "loss": 2.3675,
+      "num_input_tokens_seen": 4369008,
+      "step": 58
+    },
+    {
+      "epoch": 0.23964053919121317,
+      "grad_norm": 0.03921639174222946,
+      "learning_rate": 4.3224215685535294e-05,
+      "loss": 2.4421,
+      "num_input_tokens_seen": 4525680,
+      "step": 60
+    },
+    {
+      "epoch": 0.2476285571642536,
+      "grad_norm": 0.03894852474331856,
+      "learning_rate": 4.278839193023214e-05,
+      "loss": 2.3973,
+      "num_input_tokens_seen": 4683360,
+      "step": 62
+    },
+    {
+      "epoch": 0.2556165751372941,
+      "grad_norm": 0.048196952790021896,
+      "learning_rate": 4.234133264532012e-05,
+      "loss": 2.5022,
+      "num_input_tokens_seen": 4833520,
+      "step": 64
+    },
+    {
+      "epoch": 0.2636045931103345,
+      "grad_norm": 0.03995994105935097,
+      "learning_rate": 4.188332020302561e-05,
+      "loss": 2.3089,
+      "num_input_tokens_seen": 4974480,
+      "step": 66
+    },
+    {
+      "epoch": 0.27159261108337496,
+      "grad_norm": 0.047357227653265,
+      "learning_rate": 4.1414643893823914e-05,
+      "loss": 2.3378,
+      "num_input_tokens_seen": 5099616,
+      "step": 68
+    },
+    {
+      "epoch": 0.2795806290564154,
+      "grad_norm": 0.046735942363739014,
+      "learning_rate": 4.093559974371725e-05,
+      "loss": 2.4277,
+      "num_input_tokens_seen": 5244416,
+      "step": 70
+    },
+    {
+      "epoch": 0.28756864702945584,
+      "grad_norm": 0.04764910414814949,
+      "learning_rate": 4.044649032725836e-05,
+      "loss": 2.3468,
+      "num_input_tokens_seen": 5392128,
+      "step": 72
+    },
+    {
+      "epoch": 0.2955566650024963,
+      "grad_norm": 0.04130158573389053,
+      "learning_rate": 3.9947624576437975e-05,
+      "loss": 2.3907,
+      "num_input_tokens_seen": 5545216,
+      "step": 74
+    },
+    {
+      "epoch": 0.3035446829755367,
+      "grad_norm": 0.048350926488637924,
+      "learning_rate": 3.943931758555669e-05,
+      "loss": 2.3878,
+      "num_input_tokens_seen": 5712080,
+      "step": 76
+    },
+    {
+      "epoch": 0.31153270094857716,
+      "grad_norm": 0.052576858550310135,
+      "learning_rate": 3.8921890412204705e-05,
+      "loss": 2.3853,
+      "num_input_tokens_seen": 5858800,
+      "step": 78
+    },
+    {
+      "epoch": 0.3195207189216176,
+      "grad_norm": 0.04666517302393913,
+      "learning_rate": 3.8395669874474915e-05,
+      "loss": 2.3765,
+      "num_input_tokens_seen": 6008784,
+      "step": 80
+    },
+    {
+      "epoch": 0.32750873689465804,
+      "grad_norm": 0.045086730271577835,
+      "learning_rate": 3.786098834453766e-05,
+      "loss": 2.4277,
+      "num_input_tokens_seen": 6155536,
+      "step": 82
+    },
+    {
+      "epoch": 0.3354967548676985,
+      "grad_norm": 0.0495474711060524,
+      "learning_rate": 3.731818353870729e-05,
+      "loss": 2.3935,
+      "num_input_tokens_seen": 6306576,
+      "step": 84
+    },
+    {
+      "epoch": 0.3434847728407389,
+      "grad_norm": 0.0486772395670414,
+      "learning_rate": 3.6767598304133324e-05,
+      "loss": 2.4679,
+      "num_input_tokens_seen": 6470448,
+      "step": 86
+    },
+    {
+      "epoch": 0.35147279081377936,
+      "grad_norm": 0.05734413489699364,
+      "learning_rate": 3.6209580402250815e-05,
+      "loss": 2.3868,
+      "num_input_tokens_seen": 6616864,
+      "step": 88
+    },
+    {
+      "epoch": 0.3594608087868198,
+      "grad_norm": 0.04023748263716698,
+      "learning_rate": 3.564448228912682e-05,
+      "loss": 2.3859,
+      "num_input_tokens_seen": 6786448,
+      "step": 90
+    },
+    {
+      "epoch": 0.36744882675986024,
+      "grad_norm": 0.04801137000322342,
+      "learning_rate": 3.507266089284157e-05,
+      "loss": 2.4216,
+      "num_input_tokens_seen": 6954720,
+      "step": 92
+    },
+    {
+      "epoch": 0.3754368447329007,
+      "grad_norm": 0.05846545100212097,
+      "learning_rate": 3.4494477388045035e-05,
+      "loss": 2.4611,
+      "num_input_tokens_seen": 7094208,
+      "step": 94
+    },
+    {
+      "epoch": 0.38342486270594106,
+      "grad_norm": 0.04973718896508217,
+      "learning_rate": 3.3910296967831266e-05,
+      "loss": 2.3384,
+      "num_input_tokens_seen": 7227440,
+      "step": 96
+    },
+    {
+      "epoch": 0.3914128806789815,
+      "grad_norm": 0.0684569925069809,
+      "learning_rate": 3.332048861307467e-05,
+      "loss": 2.4074,
+      "num_input_tokens_seen": 7362608,
+      "step": 98
+    },
+    {
+      "epoch": 0.39940089865202194,
+      "grad_norm": 0.05771000683307648,
+      "learning_rate": 3.272542485937369e-05,
+      "loss": 2.3572,
+      "num_input_tokens_seen": 7515024,
+      "step": 100
+    },
+    {
+      "epoch": 0.4073889166250624,
+      "grad_norm": 0.043234046548604965,
+      "learning_rate": 3.21254815617494e-05,
+      "loss": 2.3579,
+      "num_input_tokens_seen": 7670624,
+      "step": 102
+    },
+    {
+      "epoch": 0.4153769345981028,
+      "grad_norm": 0.06148277968168259,
+      "learning_rate": 3.152103765724743e-05,
+      "loss": 2.3728,
+      "num_input_tokens_seen": 7817648,
+      "step": 104
+    },
+    {
+      "epoch": 0.42336495257114326,
+      "grad_norm": 0.04587692394852638,
+      "learning_rate": 3.091247492559312e-05,
+      "loss": 2.2712,
+      "num_input_tokens_seen": 7968432,
+      "step": 106
+    },
+    {
+      "epoch": 0.4313529705441837,
+      "grad_norm": 0.05067060887813568,
+      "learning_rate": 3.0300177748051373e-05,
+      "loss": 2.4054,
+      "num_input_tokens_seen": 8127312,
+      "step": 108
+    },
+    {
+      "epoch": 0.43934098851722414,
+      "grad_norm": 0.04505151882767677,
+      "learning_rate": 2.9684532864643122e-05,
+      "loss": 2.3966,
+      "num_input_tokens_seen": 8275008,
+      "step": 110
+    },
+    {
+      "epoch": 0.4473290064902646,
+      "grad_norm": 0.058195654302835464,
+      "learning_rate": 2.9065929129872094e-05,
+      "loss": 2.4478,
+      "num_input_tokens_seen": 8425536,
+      "step": 112
+    },
+    {
+      "epoch": 0.455317024463305,
+      "grad_norm": 0.05548926442861557,
+      "learning_rate": 2.844475726711595e-05,
+      "loss": 2.4386,
+      "num_input_tokens_seen": 8573776,
+      "step": 114
+    },
+    {
+      "epoch": 0.46330504243634546,
+      "grad_norm": 0.05548759549856186,
+      "learning_rate": 2.782140962183704e-05,
+      "loss": 2.4176,
+      "num_input_tokens_seen": 8729200,
+      "step": 116
+    },
+    {
+      "epoch": 0.4712930604093859,
+      "grad_norm": 0.05361337587237358,
+      "learning_rate": 2.7196279913768584e-05,
+      "loss": 2.3505,
+      "num_input_tokens_seen": 8884720,
+      "step": 118
+    },
+    {
+      "epoch": 0.47928107838242634,
+      "grad_norm": 0.05254572257399559,
+      "learning_rate": 2.656976298823284e-05,
+      "loss": 2.3867,
+      "num_input_tokens_seen": 9035088,
+      "step": 120
+    },
+    {
+      "epoch": 0.4872690963554668,
+      "grad_norm": 0.051810409873723984,
+      "learning_rate": 2.594225456674837e-05,
+      "loss": 2.4321,
+      "num_input_tokens_seen": 9188528,
+      "step": 122
+    },
+    {
+      "epoch": 0.4952571143285072,
+      "grad_norm": 0.05497866868972778,
+      "learning_rate": 2.531415099708382e-05,
+      "loss": 2.4392,
+      "num_input_tokens_seen": 9352752,
+      "step": 124
+    },
+    {
+      "epoch": 0.5032451323015477,
+      "grad_norm": 0.06646806746721268,
+      "learning_rate": 2.4685849002916183e-05,
+      "loss": 2.4005,
+      "num_input_tokens_seen": 9497840,
+      "step": 126
+    },
+    {
+      "epoch": 0.5112331502745882,
+      "grad_norm": 0.05319731682538986,
+      "learning_rate": 2.4057745433251635e-05,
+      "loss": 2.309,
+      "num_input_tokens_seen": 9654816,
+      "step": 128
+    },
+    {
+      "epoch": 0.5192211682476285,
+      "grad_norm": 0.07142467051744461,
+      "learning_rate": 2.3430237011767167e-05,
+      "loss": 2.522,
+      "num_input_tokens_seen": 9814944,
+      "step": 130
+    },
+    {
+      "epoch": 0.527209186220669,
+      "grad_norm": 0.06771399825811386,
+      "learning_rate": 2.280372008623142e-05,
+      "loss": 2.4151,
+      "num_input_tokens_seen": 9951952,
+      "step": 132
+    },
+    {
+      "epoch": 0.5351972041937094,
+      "grad_norm": 0.062045566737651825,
+      "learning_rate": 2.217859037816296e-05,
+      "loss": 2.3723,
+      "num_input_tokens_seen": 10112272,
+      "step": 134
+    },
+    {
+      "epoch": 0.5431852221667499,
+      "grad_norm": 0.05891815572977066,
+      "learning_rate": 2.155524273288405e-05,
+      "loss": 2.416,
+      "num_input_tokens_seen": 10281344,
+      "step": 136
+    },
+    {
+      "epoch": 0.5511732401397903,
+      "grad_norm": 0.06526540219783783,
+      "learning_rate": 2.0934070870127912e-05,
+      "loss": 2.5335,
+      "num_input_tokens_seen": 10409584,
+      "step": 138
+    },
+    {
+      "epoch": 0.5591612581128308,
+      "grad_norm": 0.0685892105102539,
+      "learning_rate": 2.031546713535688e-05,
+      "loss": 2.4946,
+      "num_input_tokens_seen": 10573840,
+      "step": 140
+    },
+    {
+      "epoch": 0.5671492760858712,
+      "grad_norm": 0.05832570418715477,
+      "learning_rate": 1.969982225194864e-05,
+      "loss": 2.3169,
+      "num_input_tokens_seen": 10729760,
+      "step": 142
+    },
+    {
+      "epoch": 0.5751372940589117,
+      "grad_norm": 0.05707252770662308,
+      "learning_rate": 1.908752507440689e-05,
+      "loss": 2.3797,
+      "num_input_tokens_seen": 10881664,
+      "step": 144
+    },
+    {
+      "epoch": 0.5831253120319521,
+      "grad_norm": 0.05318214371800423,
+      "learning_rate": 1.8478962342752583e-05,
+      "loss": 2.4498,
+      "num_input_tokens_seen": 11034352,
+      "step": 146
+    },
+    {
+      "epoch": 0.5911133300049926,
+      "grad_norm": 0.06147105619311333,
+      "learning_rate": 1.7874518438250597e-05,
+      "loss": 2.3818,
+      "num_input_tokens_seen": 11175952,
+      "step": 148
+    },
+    {
+      "epoch": 0.5991013479780329,
+      "grad_norm": 0.05764273181557655,
+      "learning_rate": 1.7274575140626318e-05,
+      "loss": 2.3818,
+      "num_input_tokens_seen": 11314112,
+      "step": 150
+    },
+    {
+      "epoch": 0.6070893659510734,
+      "grad_norm": 0.05358808860182762,
+      "learning_rate": 1.6679511386925337e-05,
+      "loss": 2.4073,
+      "num_input_tokens_seen": 11481792,
+      "step": 152
+    },
+    {
+      "epoch": 0.6150773839241138,
+      "grad_norm": 0.05264300853013992,
+      "learning_rate": 1.6089703032168733e-05,
+      "loss": 2.3467,
+      "num_input_tokens_seen": 11649040,
+      "step": 154
+    },
+    {
+      "epoch": 0.6230654018971543,
+      "grad_norm": 0.060223497450351715,
+      "learning_rate": 1.5505522611954975e-05,
+      "loss": 2.4047,
+      "num_input_tokens_seen": 11791488,
+      "step": 156
+    },
+    {
+      "epoch": 0.6310534198701947,
+      "grad_norm": 0.0639820247888565,
+      "learning_rate": 1.4927339107158437e-05,
+      "loss": 2.2998,
+      "num_input_tokens_seen": 11940144,
+      "step": 158
+    },
+    {
+      "epoch": 0.6390414378432352,
+      "grad_norm": 0.053195178508758545,
+      "learning_rate": 1.4355517710873184e-05,
+      "loss": 2.383,
+      "num_input_tokens_seen": 12097648,
+      "step": 160
+    },
+    {
+      "epoch": 0.6470294558162756,
+      "grad_norm": 0.059055812656879425,
+      "learning_rate": 1.3790419597749199e-05,
+      "loss": 2.3525,
+      "num_input_tokens_seen": 12253152,
+      "step": 162
+    },
+    {
+      "epoch": 0.6550174737893161,
+      "grad_norm": 0.07648273557424545,
+      "learning_rate": 1.3232401695866687e-05,
+      "loss": 2.4133,
+      "num_input_tokens_seen": 12410080,
+      "step": 164
+    },
+    {
+      "epoch": 0.6630054917623565,
+      "grad_norm": 0.06658945977687836,
+      "learning_rate": 1.2681816461292715e-05,
+      "loss": 2.3677,
+      "num_input_tokens_seen": 12544848,
+      "step": 166
+    },
+    {
+      "epoch": 0.670993509735397,
+      "grad_norm": 0.06263954192399979,
+      "learning_rate": 1.2139011655462337e-05,
+      "loss": 2.4215,
+      "num_input_tokens_seen": 12701808,
+      "step": 168
+    },
+    {
+      "epoch": 0.6789815277084373,
+      "grad_norm": 0.0712100937962532,
+      "learning_rate": 1.1604330125525079e-05,
+      "loss": 2.3162,
+      "num_input_tokens_seen": 12845840,
+      "step": 170
+    },
+    {
+      "epoch": 0.6869695456814778,
+      "grad_norm": 0.06635987758636475,
+      "learning_rate": 1.107810958779531e-05,
+      "loss": 2.4129,
+      "num_input_tokens_seen": 12988144,
+      "step": 172
+    },
+    {
+      "epoch": 0.6949575636545182,
+      "grad_norm": 0.07223087549209595,
+      "learning_rate": 1.0560682414443315e-05,
+      "loss": 2.4046,
+      "num_input_tokens_seen": 13129808,
+      "step": 174
+    },
+    {
+      "epoch": 0.7029455816275587,
+      "grad_norm": 0.08978503942489624,
+      "learning_rate": 1.0052375423562038e-05,
+      "loss": 2.3596,
+      "num_input_tokens_seen": 13269264,
+      "step": 176
+    },
+    {
+      "epoch": 0.7109335996005991,
+      "grad_norm": 0.06082882732152939,
+      "learning_rate": 9.553509672741645e-06,
+      "loss": 2.3047,
+      "num_input_tokens_seen": 13417184,
+      "step": 178
+    },
+    {
+      "epoch": 0.7189216175736396,
+      "grad_norm": 0.07053129374980927,
+      "learning_rate": 9.064400256282757e-06,
+      "loss": 2.4177,
+      "num_input_tokens_seen": 13561008,
+      "step": 180
+    },
+    {
+      "epoch": 0.72690963554668,
+      "grad_norm": 0.0724414512515068,
+      "learning_rate": 8.585356106176094e-06,
+      "loss": 2.4451,
+      "num_input_tokens_seen": 13706976,
+      "step": 182
+    },
+    {
+      "epoch": 0.7348976535197205,
+      "grad_norm": 0.07262030243873596,
+      "learning_rate": 8.116679796974388e-06,
+      "loss": 2.3997,
+      "num_input_tokens_seen": 13835936,
+      "step": 184
+    },
+    {
+      "epoch": 0.7428856714927609,
+      "grad_norm": 0.07069452106952667,
+      "learning_rate": 7.65866735467988e-06,
+      "loss": 2.412,
+      "num_input_tokens_seen": 13962144,
+      "step": 186
+    },
+    {
+      "epoch": 0.7508736894658014,
+      "grad_norm": 0.053225237876176834,
+      "learning_rate": 7.211608069767867e-06,
+      "loss": 2.4054,
+      "num_input_tokens_seen": 14128800,
+      "step": 188
+    },
+    {
+      "epoch": 0.7588617074388417,
+      "grad_norm": 0.05883209779858589,
+      "learning_rate": 6.775784314464717e-06,
+      "loss": 2.4417,
+      "num_input_tokens_seen": 14278288,
+      "step": 190
+    },
+    {
+      "epoch": 0.7668497254118821,
+      "grad_norm": 0.0630330890417099,
+      "learning_rate": 6.3514713643954475e-06,
+      "loss": 2.3358,
+      "num_input_tokens_seen": 14429936,
+      "step": 192
+    },
+    {
+      "epoch": 0.7748377433849226,
+      "grad_norm": 0.06319437175989151,
+      "learning_rate": 5.9389372247138e-06,
+      "loss": 2.5089,
+      "num_input_tokens_seen": 14567552,
+      "step": 194
+    },
+    {
+      "epoch": 0.782825761357963,
+      "grad_norm": 0.0682671070098877,
+      "learning_rate": 5.538442460824417e-06,
+      "loss": 2.4246,
+      "num_input_tokens_seen": 14704528,
+      "step": 196
+    },
+    {
+      "epoch": 0.7908137793310035,
+      "grad_norm": 0.06514116376638412,
+      "learning_rate": 5.150240033804116e-06,
+      "loss": 2.369,
+      "num_input_tokens_seen": 14846192,
+      "step": 198
+    },
+    {
+      "epoch": 0.7988017973040439,
+      "grad_norm": 0.05886775627732277,
+      "learning_rate": 4.7745751406263165e-06,
+      "loss": 2.4204,
+      "num_input_tokens_seen": 14993936,
+      "step": 200
+    },
+    {
+      "epoch": 0.8067898152770844,
+      "grad_norm": 0.06780359148979187,
+      "learning_rate": 4.411685059289314e-06,
+      "loss": 2.3141,
+      "num_input_tokens_seen": 15136240,
+      "step": 202
+    },
+    {
+      "epoch": 0.8147778332501248,
+      "grad_norm": 0.06595364212989807,
+      "learning_rate": 4.061798998946459e-06,
+      "loss": 2.3841,
+      "num_input_tokens_seen": 15274672,
+      "step": 204
+    },
+    {
+      "epoch": 0.8227658512231653,
+      "grad_norm": 0.06310597062110901,
+      "learning_rate": 3.725137955132707e-06,
+      "loss": 2.3653,
+      "num_input_tokens_seen": 15417920,
+      "step": 206
+    },
+    {
+      "epoch": 0.8307538691962056,
+      "grad_norm": 0.06177780404686928,
+      "learning_rate": 3.4019145701791184e-06,
+      "loss": 2.4382,
+      "num_input_tokens_seen": 15557920,
+      "step": 208
+    },
+    {
+      "epoch": 0.8387418871692461,
+      "grad_norm": 0.0720074325799942,
+      "learning_rate": 3.092332998903416e-06,
+      "loss": 2.4455,
+      "num_input_tokens_seen": 15687968,
+      "step": 210
+    },
+    {
+      "epoch": 0.8467299051422865,
+      "grad_norm": 0.05820966139435768,
+      "learning_rate": 2.7965887796613884e-06,
+      "loss": 2.4322,
+      "num_input_tokens_seen": 15843072,
+      "step": 212
+    },
+    {
+      "epoch": 0.854717923115327,
+      "grad_norm": 0.07062980532646179,
+      "learning_rate": 2.514868710840723e-06,
+      "loss": 2.4433,
+      "num_input_tokens_seen": 16002112,
+      "step": 214
+    },
+    {
+      "epoch": 0.8627059410883674,
+      "grad_norm": 0.07145073264837265,
+      "learning_rate": 2.2473507328751086e-06,
+      "loss": 2.4399,
+      "num_input_tokens_seen": 16135328,
+      "step": 216
+    },
+    {
+      "epoch": 0.8706939590614079,
+      "grad_norm": 0.06476866453886032,
+      "learning_rate": 1.9942038158532407e-06,
+      "loss": 2.378,
+      "num_input_tokens_seen": 16293008,
+      "step": 218
+    },
+    {
+      "epoch": 0.8786819770344483,
+      "grad_norm": 0.05755852535367012,
+      "learning_rate": 1.7555878527937164e-06,
+      "loss": 2.3874,
+      "num_input_tokens_seen": 16441024,
+      "step": 220
+    },
+    {
+      "epoch": 0.8866699950074888,
+      "grad_norm": 0.059895843267440796,
+      "learning_rate": 1.5316535586531483e-06,
+      "loss": 2.4028,
+      "num_input_tokens_seen": 16587616,
+      "step": 222
+    },
+    {
+      "epoch": 0.8946580129805292,
+      "grad_norm": 0.055422358214855194,
+      "learning_rate": 1.3225423751313942e-06,
+      "loss": 2.3372,
+      "num_input_tokens_seen": 16730800,
+      "step": 224
+    },
+    {
+      "epoch": 0.9026460309535697,
+      "grad_norm": 0.06502599269151688,
+      "learning_rate": 1.1283863813339263e-06,
+      "loss": 2.4288,
+      "num_input_tokens_seen": 16886144,
+      "step": 226
+    },
+    {
+      "epoch": 0.91063404892661,
+      "grad_norm": 0.06254018843173981,
+      "learning_rate": 9.493082103478517e-07,
+      "loss": 2.3483,
+      "num_input_tokens_seen": 17038816,
+      "step": 228
+    },
+    {
+      "epoch": 0.9186220668996505,
+      "grad_norm": 0.08103015273809433,
+      "learning_rate": 7.854209717842231e-07,
+      "loss": 2.4648,
+      "num_input_tokens_seen": 17171792,
+      "step": 230
+    },
+    {
+      "epoch": 0.9266100848726909,
+      "grad_norm": 0.06423594057559967,
+      "learning_rate": 6.368281803355691e-07,
+      "loss": 2.4327,
+      "num_input_tokens_seen": 17324752,
+      "step": 232
+    },
+    {
+      "epoch": 0.9345981028457314,
+      "grad_norm": 0.06621188670396805,
+      "learning_rate": 5.036236903938285e-07,
+      "loss": 2.3037,
+      "num_input_tokens_seen": 17485168,
+      "step": 234
+    },
+    {
+      "epoch": 0.9425861208187718,
+      "grad_norm": 0.06229124590754509,
+      "learning_rate": 3.8589163676986674e-07,
+      "loss": 2.4094,
+      "num_input_tokens_seen": 17632832,
+      "step": 236
+    },
+    {
+      "epoch": 0.9505741387918123,
+      "grad_norm": 0.07828541845083237,
+      "learning_rate": 2.8370638155215123e-07,
+      "loss": 2.3348,
+      "num_input_tokens_seen": 17781744,
+      "step": 238
+    },
+    {
+      "epoch": 0.9585621567648527,
+      "grad_norm": 0.049717940390110016,
+      "learning_rate": 1.9713246713805588e-07,
+      "loss": 2.3979,
+      "num_input_tokens_seen": 17959392,
+      "step": 240
+    },
+    {
+      "epoch": 0.9665501747378932,
+      "grad_norm": 0.06252018362283707,
+      "learning_rate": 1.2622457546749567e-07,
+      "loss": 2.346,
+      "num_input_tokens_seen": 18121744,
+      "step": 242
+    },
+    {
+      "epoch": 0.9745381927109336,
+      "grad_norm": 0.06641443818807602,
+      "learning_rate": 7.102749348465165e-08,
+      "loss": 2.4486,
+      "num_input_tokens_seen": 18273856,
+      "step": 244
+    },
+    {
+      "epoch": 0.982526210683974,
+      "grad_norm": 0.052787262946367264,
+      "learning_rate": 3.157608484956332e-08,
+      "loss": 2.3959,
+      "num_input_tokens_seen": 18407456,
+      "step": 246
+    },
+    {
+      "epoch": 0.9905142286570144,
+      "grad_norm": 0.058858100324869156,
+      "learning_rate": 7.895267917501504e-09,
+      "loss": 2.4287,
+      "num_input_tokens_seen": 18555776,
+      "step": 248
+    },
+    {
+      "epoch": 0.9985022466300549,
+      "grad_norm": 0.07202674448490143,
+      "learning_rate": 0.0,
+      "loss": 2.4911,
+      "num_input_tokens_seen": 18683616,
+      "step": 250
+    },
+    {
+      "epoch": 0.9985022466300549,
+      "num_input_tokens_seen": 18683616,
+      "step": 250,
+      "total_flos": 1.599323192678744e+18,
+      "train_loss": 2.4129163398742675,
+      "train_runtime": 18708.0864,
+      "train_samples_per_second": 0.214,
+      "train_steps_per_second": 0.013
+    }
+  ],
+  "logging_steps": 2,
+  "max_steps": 250,
+  "num_input_tokens_seen": 18683616,
+  "num_train_epochs": 1,
+  "save_steps": 1000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.599323192678744e+18,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d83dfded8f6f28abb3b96317b9a8d68c218c87cbec77be722fe4ea54ebd69b6d
+size 5432