Training in progress, epoch 1

.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 +1,32 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen3-0.6B",
+  "bias": "none",
+  "eva_config": null,
+  "exclude_modules": null,
+  "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_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:908a8a6f10f9921ad3a7796e10152a67cb21b17f8151567c21bffffac7fbd040
+size 18365064

added_tokens.json

@@ -0,0 +1,28 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|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
+}

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:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
+size 11422654

tokenizer_config.json

@@ -0,0 +1,241 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "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\\n' }}\n    {%- endif %}\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    {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n    {%- set index = (messages|length - 1) - loop.index0 %}\n    {%- if ns.multi_step_tool and message.role == \"user\" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}\n        {%- set ns.multi_step_tool = false %}\n        {%- set ns.last_query_index = index %}\n    {%- endif %}\n{%- endfor %}\n{%- for message in messages %}\n    {%- if message.content is string %}\n        {%- set content = message.content %}\n    {%- else %}\n        {%- set content = '' %}\n    {%- endif %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n        {{- '<|im_start|>' + message.role + '\\n' + content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {%- set reasoning_content = '' %}\n        {%- if message.reasoning_content is string %}\n            {%- set reasoning_content = message.reasoning_content %}\n        {%- else %}\n            {%- if '</think>' in content %}\n                {%- set reasoning_content = content.split('</think>')[0].rstrip('\\n').split('<think>')[-1].lstrip('\\n') %}\n                {%- set content = content.split('</think>')[-1].lstrip('\\n') %}\n            {%- endif %}\n        {%- endif %}\n        {%- if loop.index0 > ns.last_query_index %}\n            {%- if loop.last or (not loop.last and reasoning_content) %}\n                {{- '<|im_start|>' + message.role + '\\n<think>\\n' + reasoning_content.strip('\\n') + '\\n</think>\\n\\n' + content.lstrip('\\n') }}\n            {%- else %}\n                {{- '<|im_start|>' + message.role + '\\n' + content }}\n            {%- endif %}\n        {%- else %}\n            {{- '<|im_start|>' + message.role + '\\n' + content }}\n        {%- endif %}\n        {%- if message.tool_calls %}\n            {%- for tool_call in message.tool_calls %}\n                {%- if (loop.first and content) or (not loop.first) %}\n                    {{- '\\n' }}\n                {%- endif %}\n                {%- if tool_call.function %}\n                    {%- set tool_call = tool_call.function %}\n                {%- endif %}\n                {{- '<tool_call>\\n{\"name\": \"' }}\n                {{- tool_call.name }}\n                {{- '\", \"arguments\": ' }}\n                {%- if tool_call.arguments is string %}\n                    {{- tool_call.arguments }}\n                {%- else %}\n                    {{- tool_call.arguments | tojson }}\n                {%- endif %}\n                {{- '}\\n</tool_call>' }}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- 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    {%- if enable_thinking is defined and enable_thinking is false %}\n        {{- '<think>\\n\\n</think>\\n\\n' }}\n    {%- endif %}\n{%- endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_log.jsonl

@@ -0,0 +1,135 @@
+{"current_steps": 10, "total_steps": 20130, "loss": 4.1082, "lr": 0.0004999997533920029, "epoch": 0.007450176941702366, "percentage": 0.05, "elapsed_time": "0:00:20", "remaining_time": "11:24:49"}
+{"current_steps": 20, "total_steps": 20130, "loss": 0.791, "lr": 0.0004999989009205385, "epoch": 0.014900353883404731, "percentage": 0.1, "elapsed_time": "0:00:40", "remaining_time": "11:19:13"}
+{"current_steps": 30, "total_steps": 20130, "loss": 0.7219, "lr": 0.0004999974395431395, "epoch": 0.022350530825107098, "percentage": 0.15, "elapsed_time": "0:01:00", "remaining_time": "11:17:13"}
+{"current_steps": 40, "total_steps": 20130, "loss": 0.5207, "lr": 0.0004999953692633653, "epoch": 0.029800707766809462, "percentage": 0.2, "elapsed_time": "0:01:19", "remaining_time": "11:03:27"}
+{"current_steps": 50, "total_steps": 20130, "loss": 0.4734, "lr": 0.0004999926900862584, "epoch": 0.03725088470851183, "percentage": 0.25, "elapsed_time": "0:01:38", "remaining_time": "11:02:35"}
+{"current_steps": 60, "total_steps": 20130, "loss": 0.4561, "lr": 0.0004999894020183443, "epoch": 0.044701061650214195, "percentage": 0.3, "elapsed_time": "0:01:58", "remaining_time": "11:00:52"}
+{"current_steps": 70, "total_steps": 20130, "loss": 0.3621, "lr": 0.0004999855050676314, "epoch": 0.05215123859191656, "percentage": 0.35, "elapsed_time": "0:02:17", "remaining_time": "10:57:48"}
+{"current_steps": 80, "total_steps": 20130, "loss": 0.4021, "lr": 0.0004999809992436114, "epoch": 0.059601415533618925, "percentage": 0.4, "elapsed_time": "0:02:37", "remaining_time": "10:56:14"}
+{"current_steps": 90, "total_steps": 20130, "loss": 0.3726, "lr": 0.0004999758845572588, "epoch": 0.06705159247532129, "percentage": 0.45, "elapsed_time": "0:02:56", "remaining_time": "10:56:19"}
+{"current_steps": 100, "total_steps": 20130, "loss": 0.4157, "lr": 0.0004999701610210309, "epoch": 0.07450176941702366, "percentage": 0.5, "elapsed_time": "0:03:15", "remaining_time": "10:53:21"}
+{"current_steps": 110, "total_steps": 20130, "loss": 0.3503, "lr": 0.0004999638286488685, "epoch": 0.08195194635872602, "percentage": 0.55, "elapsed_time": "0:03:34", "remaining_time": "10:52:08"}
+{"current_steps": 120, "total_steps": 20130, "loss": 0.3882, "lr": 0.0004999568874561947, "epoch": 0.08940212330042839, "percentage": 0.6, "elapsed_time": "0:03:54", "remaining_time": "10:51:21"}
+{"current_steps": 130, "total_steps": 20130, "loss": 0.3906, "lr": 0.0004999493374599157, "epoch": 0.09685230024213075, "percentage": 0.65, "elapsed_time": "0:04:13", "remaining_time": "10:51:11"}
+{"current_steps": 140, "total_steps": 20130, "loss": 0.3112, "lr": 0.0004999411786784206, "epoch": 0.10430247718383312, "percentage": 0.7, "elapsed_time": "0:04:32", "remaining_time": "10:48:22"}
+{"current_steps": 150, "total_steps": 20130, "loss": 0.3528, "lr": 0.0004999324111315813, "epoch": 0.11175265412553548, "percentage": 0.75, "elapsed_time": "0:04:52", "remaining_time": "10:49:05"}
+{"current_steps": 160, "total_steps": 20130, "loss": 0.3425, "lr": 0.0004999230348407522, "epoch": 0.11920283106723785, "percentage": 0.79, "elapsed_time": "0:05:12", "remaining_time": "10:49:41"}
+{"current_steps": 170, "total_steps": 20130, "loss": 0.3274, "lr": 0.0004999130498287706, "epoch": 0.12665300800894022, "percentage": 0.84, "elapsed_time": "0:05:32", "remaining_time": "10:51:23"}
+{"current_steps": 180, "total_steps": 20130, "loss": 0.3293, "lr": 0.0004999024561199562, "epoch": 0.13410318495064258, "percentage": 0.89, "elapsed_time": "0:05:53", "remaining_time": "10:53:25"}
+{"current_steps": 190, "total_steps": 20130, "loss": 0.4148, "lr": 0.0004998912537401116, "epoch": 0.14155336189234494, "percentage": 0.94, "elapsed_time": "0:06:13", "remaining_time": "10:53:23"}
+{"current_steps": 200, "total_steps": 20130, "loss": 0.3709, "lr": 0.0004998794427165216, "epoch": 0.14900353883404732, "percentage": 0.99, "elapsed_time": "0:06:33", "remaining_time": "10:53:36"}
+{"current_steps": 210, "total_steps": 20130, "loss": 0.3316, "lr": 0.0004998670230779536, "epoch": 0.15645371577574968, "percentage": 1.04, "elapsed_time": "0:06:53", "remaining_time": "10:53:03"}
+{"current_steps": 220, "total_steps": 20130, "loss": 0.4145, "lr": 0.0004998539948546572, "epoch": 0.16390389271745204, "percentage": 1.09, "elapsed_time": "0:07:13", "remaining_time": "10:53:51"}
+{"current_steps": 230, "total_steps": 20130, "loss": 0.3417, "lr": 0.0004998403580783645, "epoch": 0.1713540696591544, "percentage": 1.14, "elapsed_time": "0:07:33", "remaining_time": "10:53:20"}
+{"current_steps": 240, "total_steps": 20130, "loss": 0.3383, "lr": 0.0004998261127822895, "epoch": 0.17880424660085678, "percentage": 1.19, "elapsed_time": "0:07:53", "remaining_time": "10:53:23"}
+{"current_steps": 250, "total_steps": 20130, "loss": 0.3045, "lr": 0.0004998112590011287, "epoch": 0.18625442354255914, "percentage": 1.24, "elapsed_time": "0:08:12", "remaining_time": "10:53:17"}
+{"current_steps": 260, "total_steps": 20130, "loss": 0.1849, "lr": 0.0004997957967710605, "epoch": 0.1937046004842615, "percentage": 1.29, "elapsed_time": "0:08:31", "remaining_time": "10:51:49"}
+{"current_steps": 270, "total_steps": 20130, "loss": 0.2341, "lr": 0.0004997797261297452, "epoch": 0.20115477742596385, "percentage": 1.34, "elapsed_time": "0:08:51", "remaining_time": "10:51:12"}
+{"current_steps": 280, "total_steps": 20130, "loss": 0.2934, "lr": 0.0004997630471163249, "epoch": 0.20860495436766624, "percentage": 1.39, "elapsed_time": "0:09:09", "remaining_time": "10:49:48"}
+{"current_steps": 290, "total_steps": 20130, "loss": 0.2906, "lr": 0.0004997457597714237, "epoch": 0.2160551313093686, "percentage": 1.44, "elapsed_time": "0:09:29", "remaining_time": "10:49:09"}
+{"current_steps": 300, "total_steps": 20130, "loss": 0.317, "lr": 0.0004997278641371473, "epoch": 0.22350530825107096, "percentage": 1.49, "elapsed_time": "0:09:49", "remaining_time": "10:49:02"}
+{"current_steps": 310, "total_steps": 20130, "loss": 0.238, "lr": 0.0004997093602570828, "epoch": 0.23095548519277334, "percentage": 1.54, "elapsed_time": "0:10:07", "remaining_time": "10:47:45"}
+{"current_steps": 320, "total_steps": 20130, "loss": 0.2804, "lr": 0.0004996902481762991, "epoch": 0.2384056621344757, "percentage": 1.59, "elapsed_time": "0:10:26", "remaining_time": "10:46:49"}
+{"current_steps": 330, "total_steps": 20130, "loss": 0.2827, "lr": 0.0004996705279413459, "epoch": 0.24585583907617806, "percentage": 1.64, "elapsed_time": "0:10:45", "remaining_time": "10:45:33"}
+{"current_steps": 340, "total_steps": 20130, "loss": 0.3027, "lr": 0.0004996501996002548, "epoch": 0.25330601601788044, "percentage": 1.69, "elapsed_time": "0:11:04", "remaining_time": "10:45:00"}
+{"current_steps": 350, "total_steps": 20130, "loss": 0.2972, "lr": 0.0004996292632025379, "epoch": 0.2607561929595828, "percentage": 1.74, "elapsed_time": "0:11:24", "remaining_time": "10:44:53"}
+{"current_steps": 360, "total_steps": 20130, "loss": 0.2931, "lr": 0.0004996077187991889, "epoch": 0.26820636990128516, "percentage": 1.79, "elapsed_time": "0:11:43", "remaining_time": "10:44:08"}
+{"current_steps": 370, "total_steps": 20130, "loss": 0.24, "lr": 0.0004995855664426819, "epoch": 0.2756565468429875, "percentage": 1.84, "elapsed_time": "0:12:02", "remaining_time": "10:42:58"}
+{"current_steps": 380, "total_steps": 20130, "loss": 0.3056, "lr": 0.0004995628061869722, "epoch": 0.2831067237846899, "percentage": 1.89, "elapsed_time": "0:12:22", "remaining_time": "10:43:04"}
+{"current_steps": 390, "total_steps": 20130, "loss": 0.2745, "lr": 0.0004995394380874951, "epoch": 0.29055690072639223, "percentage": 1.94, "elapsed_time": "0:12:40", "remaining_time": "10:41:44"}
+{"current_steps": 400, "total_steps": 20130, "loss": 0.3092, "lr": 0.000499515462201167, "epoch": 0.29800707766809464, "percentage": 1.99, "elapsed_time": "0:13:00", "remaining_time": "10:41:31"}
+{"current_steps": 410, "total_steps": 20130, "loss": 0.3076, "lr": 0.0004994908785863843, "epoch": 0.305457254609797, "percentage": 2.04, "elapsed_time": "0:13:20", "remaining_time": "10:41:18"}
+{"current_steps": 420, "total_steps": 20130, "loss": 0.2699, "lr": 0.0004994656873030238, "epoch": 0.31290743155149936, "percentage": 2.09, "elapsed_time": "0:13:38", "remaining_time": "10:40:24"}
+{"current_steps": 430, "total_steps": 20130, "loss": 0.2555, "lr": 0.0004994398884124421, "epoch": 0.3203576084932017, "percentage": 2.14, "elapsed_time": "0:13:57", "remaining_time": "10:39:22"}
+{"current_steps": 440, "total_steps": 20130, "loss": 0.2408, "lr": 0.000499413481977476, "epoch": 0.3278077854349041, "percentage": 2.19, "elapsed_time": "0:14:16", "remaining_time": "10:38:52"}
+{"current_steps": 450, "total_steps": 20130, "loss": 0.2823, "lr": 0.0004993864680624418, "epoch": 0.33525796237660643, "percentage": 2.24, "elapsed_time": "0:14:35", "remaining_time": "10:37:51"}
+{"current_steps": 460, "total_steps": 20130, "loss": 0.278, "lr": 0.0004993588467331357, "epoch": 0.3427081393183088, "percentage": 2.29, "elapsed_time": "0:14:54", "remaining_time": "10:37:18"}
+{"current_steps": 470, "total_steps": 20130, "loss": 0.271, "lr": 0.000499330618056833, "epoch": 0.35015831626001115, "percentage": 2.33, "elapsed_time": "0:15:12", "remaining_time": "10:36:23"}
+{"current_steps": 480, "total_steps": 20130, "loss": 0.288, "lr": 0.0004993017821022885, "epoch": 0.35760849320171356, "percentage": 2.38, "elapsed_time": "0:15:33", "remaining_time": "10:36:46"}
+{"current_steps": 490, "total_steps": 20130, "loss": 0.3049, "lr": 0.000499272338939736, "epoch": 0.3650586701434159, "percentage": 2.43, "elapsed_time": "0:15:52", "remaining_time": "10:36:05"}
+{"current_steps": 500, "total_steps": 20130, "loss": 0.2526, "lr": 0.0004992422886408883, "epoch": 0.3725088470851183, "percentage": 2.48, "elapsed_time": "0:16:11", "remaining_time": "10:35:53"}
+{"current_steps": 510, "total_steps": 20130, "loss": 0.2451, "lr": 0.0004992116312789371, "epoch": 0.37995902402682064, "percentage": 2.53, "elapsed_time": "0:16:30", "remaining_time": "10:35:24"}
+{"current_steps": 520, "total_steps": 20130, "loss": 0.2576, "lr": 0.0004991803669285522, "epoch": 0.387409200968523, "percentage": 2.58, "elapsed_time": "0:16:49", "remaining_time": "10:34:38"}
+{"current_steps": 530, "total_steps": 20130, "loss": 0.3265, "lr": 0.0004991484956658824, "epoch": 0.39485937791022535, "percentage": 2.63, "elapsed_time": "0:17:09", "remaining_time": "10:34:18"}
+{"current_steps": 540, "total_steps": 20130, "loss": 0.2558, "lr": 0.0004991160175685544, "epoch": 0.4023095548519277, "percentage": 2.68, "elapsed_time": "0:17:28", "remaining_time": "10:33:53"}
+{"current_steps": 550, "total_steps": 20130, "loss": 0.2817, "lr": 0.0004990829327156728, "epoch": 0.4097597317936301, "percentage": 2.73, "elapsed_time": "0:17:48", "remaining_time": "10:33:49"}
+{"current_steps": 560, "total_steps": 20130, "loss": 0.1873, "lr": 0.0004990492411878205, "epoch": 0.4172099087353325, "percentage": 2.78, "elapsed_time": "0:18:06", "remaining_time": "10:33:00"}
+{"current_steps": 570, "total_steps": 20130, "loss": 0.242, "lr": 0.0004990149430670575, "epoch": 0.42466008567703484, "percentage": 2.83, "elapsed_time": "0:18:26", "remaining_time": "10:32:46"}
+{"current_steps": 580, "total_steps": 20130, "loss": 0.2487, "lr": 0.0004989800384369216, "epoch": 0.4321102626187372, "percentage": 2.88, "elapsed_time": "0:18:45", "remaining_time": "10:32:03"}
+{"current_steps": 590, "total_steps": 20130, "loss": 0.271, "lr": 0.0004989445273824276, "epoch": 0.43956043956043955, "percentage": 2.93, "elapsed_time": "0:19:03", "remaining_time": "10:31:13"}
+{"current_steps": 600, "total_steps": 20130, "loss": 0.2535, "lr": 0.0004989084099900677, "epoch": 0.4470106165021419, "percentage": 2.98, "elapsed_time": "0:19:22", "remaining_time": "10:30:34"}
+{"current_steps": 610, "total_steps": 20130, "loss": 0.2101, "lr": 0.0004988716863478104, "epoch": 0.45446079344384427, "percentage": 3.03, "elapsed_time": "0:19:40", "remaining_time": "10:29:46"}
+{"current_steps": 620, "total_steps": 20130, "loss": 0.2584, "lr": 0.0004988343565451011, "epoch": 0.4619109703855467, "percentage": 3.08, "elapsed_time": "0:19:59", "remaining_time": "10:29:17"}
+{"current_steps": 630, "total_steps": 20130, "loss": 0.2352, "lr": 0.0004987964206728618, "epoch": 0.46936114732724904, "percentage": 3.13, "elapsed_time": "0:20:19", "remaining_time": "10:28:59"}
+{"current_steps": 640, "total_steps": 20130, "loss": 0.2284, "lr": 0.0004987578788234901, "epoch": 0.4768113242689514, "percentage": 3.18, "elapsed_time": "0:20:38", "remaining_time": "10:28:26"}
+{"current_steps": 650, "total_steps": 20130, "loss": 0.215, "lr": 0.00049871873109086, "epoch": 0.48426150121065376, "percentage": 3.23, "elapsed_time": "0:20:57", "remaining_time": "10:28:13"}
+{"current_steps": 660, "total_steps": 20130, "loss": 0.2403, "lr": 0.0004986789775703211, "epoch": 0.4917116781523561, "percentage": 3.28, "elapsed_time": "0:21:17", "remaining_time": "10:28:02"}
+{"current_steps": 670, "total_steps": 20130, "loss": 0.2382, "lr": 0.0004986386183586985, "epoch": 0.49916185509405847, "percentage": 3.33, "elapsed_time": "0:21:36", "remaining_time": "10:27:32"}
+{"current_steps": 680, "total_steps": 20130, "loss": 0.2182, "lr": 0.0004985976535542922, "epoch": 0.5066120320357609, "percentage": 3.38, "elapsed_time": "0:21:55", "remaining_time": "10:27:04"}
+{"current_steps": 690, "total_steps": 20130, "loss": 0.2583, "lr": 0.0004985560832568779, "epoch": 0.5140622089774632, "percentage": 3.43, "elapsed_time": "0:22:15", "remaining_time": "10:26:57"}
+{"current_steps": 700, "total_steps": 20130, "loss": 0.2634, "lr": 0.0004985139075677052, "epoch": 0.5215123859191656, "percentage": 3.48, "elapsed_time": "0:22:34", "remaining_time": "10:26:46"}
+{"current_steps": 710, "total_steps": 20130, "loss": 0.2244, "lr": 0.0004984711265894991, "epoch": 0.528962562860868, "percentage": 3.53, "elapsed_time": "0:22:53", "remaining_time": "10:26:21"}
+{"current_steps": 720, "total_steps": 20130, "loss": 0.1873, "lr": 0.0004984277404264581, "epoch": 0.5364127398025703, "percentage": 3.58, "elapsed_time": "0:23:12", "remaining_time": "10:25:43"}
+{"current_steps": 730, "total_steps": 20130, "loss": 0.2576, "lr": 0.0004983837491842551, "epoch": 0.5438629167442727, "percentage": 3.63, "elapsed_time": "0:23:31", "remaining_time": "10:25:18"}
+{"current_steps": 740, "total_steps": 20130, "loss": 0.2407, "lr": 0.0004983391529700368, "epoch": 0.551313093685975, "percentage": 3.68, "elapsed_time": "0:23:50", "remaining_time": "10:24:43"}
+{"current_steps": 750, "total_steps": 20130, "loss": 0.2284, "lr": 0.0004982939518924233, "epoch": 0.5587632706276774, "percentage": 3.73, "elapsed_time": "0:24:09", "remaining_time": "10:24:25"}
+{"current_steps": 760, "total_steps": 20130, "loss": 0.2071, "lr": 0.0004982481460615077, "epoch": 0.5662134475693797, "percentage": 3.78, "elapsed_time": "0:24:29", "remaining_time": "10:24:11"}
+{"current_steps": 770, "total_steps": 20130, "loss": 0.2534, "lr": 0.0004982017355888564, "epoch": 0.5736636245110821, "percentage": 3.83, "elapsed_time": "0:24:48", "remaining_time": "10:23:51"}
+{"current_steps": 780, "total_steps": 20130, "loss": 0.2488, "lr": 0.0004981547205875083, "epoch": 0.5811138014527845, "percentage": 3.87, "elapsed_time": "0:25:09", "remaining_time": "10:24:01"}
+{"current_steps": 790, "total_steps": 20130, "loss": 0.2324, "lr": 0.0004981071011719748, "epoch": 0.5885639783944868, "percentage": 3.92, "elapsed_time": "0:25:28", "remaining_time": "10:23:34"}
+{"current_steps": 800, "total_steps": 20130, "loss": 0.2131, "lr": 0.0004980588774582393, "epoch": 0.5960141553361893, "percentage": 3.97, "elapsed_time": "0:25:47", "remaining_time": "10:23:09"}
+{"current_steps": 810, "total_steps": 20130, "loss": 0.1603, "lr": 0.0004980100495637572, "epoch": 0.6034643322778916, "percentage": 4.02, "elapsed_time": "0:26:05", "remaining_time": "10:22:30"}
+{"current_steps": 820, "total_steps": 20130, "loss": 0.2185, "lr": 0.0004979606176074555, "epoch": 0.610914509219594, "percentage": 4.07, "elapsed_time": "0:26:26", "remaining_time": "10:22:30"}
+{"current_steps": 830, "total_steps": 20130, "loss": 0.1855, "lr": 0.0004979105817097321, "epoch": 0.6183646861612964, "percentage": 4.12, "elapsed_time": "0:26:45", "remaining_time": "10:22:14"}
+{"current_steps": 840, "total_steps": 20130, "loss": 0.1871, "lr": 0.0004978599419924565, "epoch": 0.6258148631029987, "percentage": 4.17, "elapsed_time": "0:27:04", "remaining_time": "10:21:54"}
+{"current_steps": 850, "total_steps": 20130, "loss": 0.197, "lr": 0.0004978086985789683, "epoch": 0.6332650400447011, "percentage": 4.22, "elapsed_time": "0:27:23", "remaining_time": "10:21:22"}
+{"current_steps": 860, "total_steps": 20130, "loss": 0.2128, "lr": 0.0004977568515940778, "epoch": 0.6407152169864034, "percentage": 4.27, "elapsed_time": "0:27:42", "remaining_time": "10:20:57"}
+{"current_steps": 870, "total_steps": 20130, "loss": 0.2379, "lr": 0.0004977044011640654, "epoch": 0.6481653939281058, "percentage": 4.32, "elapsed_time": "0:28:01", "remaining_time": "10:20:29"}
+{"current_steps": 880, "total_steps": 20130, "loss": 0.1691, "lr": 0.0004976513474166809, "epoch": 0.6556155708698082, "percentage": 4.37, "elapsed_time": "0:28:20", "remaining_time": "10:19:56"}
+{"current_steps": 890, "total_steps": 20130, "loss": 0.1505, "lr": 0.0004975976904811441, "epoch": 0.6630657478115105, "percentage": 4.42, "elapsed_time": "0:28:39", "remaining_time": "10:19:24"}
+{"current_steps": 900, "total_steps": 20130, "loss": 0.2142, "lr": 0.0004975434304881436, "epoch": 0.6705159247532129, "percentage": 4.47, "elapsed_time": "0:28:58", "remaining_time": "10:19:01"}
+{"current_steps": 910, "total_steps": 20130, "loss": 0.2357, "lr": 0.0004974885675698369, "epoch": 0.6779661016949152, "percentage": 4.52, "elapsed_time": "0:29:17", "remaining_time": "10:18:46"}
+{"current_steps": 920, "total_steps": 20130, "loss": 0.2738, "lr": 0.0004974331018598499, "epoch": 0.6854162786366176, "percentage": 4.57, "elapsed_time": "0:29:37", "remaining_time": "10:18:26"}
+{"current_steps": 930, "total_steps": 20130, "loss": 0.1878, "lr": 0.000497377033493277, "epoch": 0.6928664555783199, "percentage": 4.62, "elapsed_time": "0:29:56", "remaining_time": "10:18:05"}
+{"current_steps": 940, "total_steps": 20130, "loss": 0.2238, "lr": 0.0004973203626066801, "epoch": 0.7003166325200223, "percentage": 4.67, "elapsed_time": "0:30:14", "remaining_time": "10:17:26"}
+{"current_steps": 950, "total_steps": 20130, "loss": 0.2441, "lr": 0.0004972630893380889, "epoch": 0.7077668094617248, "percentage": 4.72, "elapsed_time": "0:30:35", "remaining_time": "10:17:28"}
+{"current_steps": 960, "total_steps": 20130, "loss": 0.1506, "lr": 0.000497205213827, "epoch": 0.7152169864034271, "percentage": 4.77, "elapsed_time": "0:30:54", "remaining_time": "10:17:13"}
+{"current_steps": 970, "total_steps": 20130, "loss": 0.208, "lr": 0.000497146736214377, "epoch": 0.7226671633451295, "percentage": 4.82, "elapsed_time": "0:31:13", "remaining_time": "10:16:54"}
+{"current_steps": 980, "total_steps": 20130, "loss": 0.3225, "lr": 0.0004970876566426501, "epoch": 0.7301173402868318, "percentage": 4.87, "elapsed_time": "0:31:34", "remaining_time": "10:17:02"}
+{"current_steps": 990, "total_steps": 20130, "loss": 0.2272, "lr": 0.0004970279752557154, "epoch": 0.7375675172285342, "percentage": 4.92, "elapsed_time": "0:31:54", "remaining_time": "10:16:52"}
+{"current_steps": 1000, "total_steps": 20130, "loss": 0.2082, "lr": 0.0004969676921989351, "epoch": 0.7450176941702366, "percentage": 4.97, "elapsed_time": "0:32:12", "remaining_time": "10:16:13"}
+{"current_steps": 1010, "total_steps": 20130, "loss": 0.2107, "lr": 0.0004969068076191366, "epoch": 0.7524678711119389, "percentage": 5.02, "elapsed_time": "0:32:32", "remaining_time": "10:15:53"}
+{"current_steps": 1020, "total_steps": 20130, "loss": 0.2396, "lr": 0.0004968453216646124, "epoch": 0.7599180480536413, "percentage": 5.07, "elapsed_time": "0:32:51", "remaining_time": "10:15:30"}
+{"current_steps": 1030, "total_steps": 20130, "loss": 0.2244, "lr": 0.00049678323448512, "epoch": 0.7673682249953436, "percentage": 5.12, "elapsed_time": "0:33:10", "remaining_time": "10:15:11"}
+{"current_steps": 1040, "total_steps": 20130, "loss": 0.1832, "lr": 0.0004967205462318809, "epoch": 0.774818401937046, "percentage": 5.17, "elapsed_time": "0:33:29", "remaining_time": "10:14:46"}
+{"current_steps": 1050, "total_steps": 20130, "loss": 0.2101, "lr": 0.0004966572570575808, "epoch": 0.7822685788787483, "percentage": 5.22, "elapsed_time": "0:33:48", "remaining_time": "10:14:23"}
+{"current_steps": 1060, "total_steps": 20130, "loss": 0.1465, "lr": 0.000496593367116369, "epoch": 0.7897187558204507, "percentage": 5.27, "elapsed_time": "0:34:07", "remaining_time": "10:13:56"}
+{"current_steps": 1070, "total_steps": 20130, "loss": 0.2099, "lr": 0.0004965288765638582, "epoch": 0.7971689327621531, "percentage": 5.32, "elapsed_time": "0:34:27", "remaining_time": "10:13:44"}
+{"current_steps": 1080, "total_steps": 20130, "loss": 0.2134, "lr": 0.0004964637855571236, "epoch": 0.8046191097038554, "percentage": 5.37, "elapsed_time": "0:34:46", "remaining_time": "10:13:18"}
+{"current_steps": 1090, "total_steps": 20130, "loss": 0.1729, "lr": 0.0004963980942547032, "epoch": 0.8120692866455579, "percentage": 5.41, "elapsed_time": "0:35:05", "remaining_time": "10:13:03"}
+{"current_steps": 1100, "total_steps": 20130, "loss": 0.2303, "lr": 0.000496331802816597, "epoch": 0.8195194635872602, "percentage": 5.46, "elapsed_time": "0:35:24", "remaining_time": "10:12:37"}
+{"current_steps": 1110, "total_steps": 20130, "loss": 0.2057, "lr": 0.0004962649114042667, "epoch": 0.8269696405289626, "percentage": 5.51, "elapsed_time": "0:35:44", "remaining_time": "10:12:26"}
+{"current_steps": 1120, "total_steps": 20130, "loss": 0.1329, "lr": 0.0004961974201806352, "epoch": 0.834419817470665, "percentage": 5.56, "elapsed_time": "0:36:03", "remaining_time": "10:12:02"}
+{"current_steps": 1130, "total_steps": 20130, "loss": 0.2025, "lr": 0.0004961293293100867, "epoch": 0.8418699944123673, "percentage": 5.61, "elapsed_time": "0:36:22", "remaining_time": "10:11:41"}
+{"current_steps": 1140, "total_steps": 20130, "loss": 0.2331, "lr": 0.0004960606389584654, "epoch": 0.8493201713540697, "percentage": 5.66, "elapsed_time": "0:36:41", "remaining_time": "10:11:12"}
+{"current_steps": 1150, "total_steps": 20130, "loss": 0.149, "lr": 0.0004959913492930761, "epoch": 0.856770348295772, "percentage": 5.71, "elapsed_time": "0:37:00", "remaining_time": "10:10:49"}
+{"current_steps": 1160, "total_steps": 20130, "loss": 0.2372, "lr": 0.0004959214604826831, "epoch": 0.8642205252374744, "percentage": 5.76, "elapsed_time": "0:37:20", "remaining_time": "10:10:37"}
+{"current_steps": 1170, "total_steps": 20130, "loss": 0.1854, "lr": 0.0004958509726975098, "epoch": 0.8716707021791767, "percentage": 5.81, "elapsed_time": "0:37:40", "remaining_time": "10:10:28"}
+{"current_steps": 1180, "total_steps": 20130, "loss": 0.1851, "lr": 0.0004957798861092387, "epoch": 0.8791208791208791, "percentage": 5.86, "elapsed_time": "0:37:59", "remaining_time": "10:10:11"}
+{"current_steps": 1190, "total_steps": 20130, "loss": 0.2057, "lr": 0.0004957082008910109, "epoch": 0.8865710560625815, "percentage": 5.91, "elapsed_time": "0:38:18", "remaining_time": "10:09:44"}
+{"current_steps": 1200, "total_steps": 20130, "loss": 0.2082, "lr": 0.0004956359172174254, "epoch": 0.8940212330042838, "percentage": 5.96, "elapsed_time": "0:38:37", "remaining_time": "10:09:13"}
+{"current_steps": 1210, "total_steps": 20130, "loss": 0.2018, "lr": 0.0004955630352645388, "epoch": 0.9014714099459862, "percentage": 6.01, "elapsed_time": "0:38:55", "remaining_time": "10:08:43"}
+{"current_steps": 1220, "total_steps": 20130, "loss": 0.2061, "lr": 0.0004954895552098646, "epoch": 0.9089215868876885, "percentage": 6.06, "elapsed_time": "0:39:15", "remaining_time": "10:08:37"}
+{"current_steps": 1230, "total_steps": 20130, "loss": 0.1489, "lr": 0.0004954154772323738, "epoch": 0.9163717638293909, "percentage": 6.11, "elapsed_time": "0:39:34", "remaining_time": "10:08:12"}
+{"current_steps": 1240, "total_steps": 20130, "loss": 0.1876, "lr": 0.0004953408015124928, "epoch": 0.9238219407710934, "percentage": 6.16, "elapsed_time": "0:39:53", "remaining_time": "10:07:44"}
+{"current_steps": 1250, "total_steps": 20130, "loss": 0.2055, "lr": 0.0004952655282321047, "epoch": 0.9312721177127957, "percentage": 6.21, "elapsed_time": "0:40:13", "remaining_time": "10:07:28"}
+{"current_steps": 1260, "total_steps": 20130, "loss": 0.1605, "lr": 0.0004951896575745477, "epoch": 0.9387222946544981, "percentage": 6.26, "elapsed_time": "0:40:31", "remaining_time": "10:06:57"}
+{"current_steps": 1270, "total_steps": 20130, "loss": 0.2025, "lr": 0.0004951131897246147, "epoch": 0.9461724715962004, "percentage": 6.31, "elapsed_time": "0:40:51", "remaining_time": "10:06:39"}
+{"current_steps": 1280, "total_steps": 20130, "loss": 0.1798, "lr": 0.0004950361248685538, "epoch": 0.9536226485379028, "percentage": 6.36, "elapsed_time": "0:41:10", "remaining_time": "10:06:23"}
+{"current_steps": 1290, "total_steps": 20130, "loss": 0.2297, "lr": 0.0004949584631940664, "epoch": 0.9610728254796052, "percentage": 6.41, "elapsed_time": "0:41:29", "remaining_time": "10:06:03"}
+{"current_steps": 1300, "total_steps": 20130, "loss": 0.1549, "lr": 0.0004948802048903083, "epoch": 0.9685230024213075, "percentage": 6.46, "elapsed_time": "0:41:48", "remaining_time": "10:05:39"}
+{"current_steps": 1310, "total_steps": 20130, "loss": 0.1567, "lr": 0.0004948013501478881, "epoch": 0.9759731793630099, "percentage": 6.51, "elapsed_time": "0:42:08", "remaining_time": "10:05:20"}
+{"current_steps": 1320, "total_steps": 20130, "loss": 0.1901, "lr": 0.000494721899158867, "epoch": 0.9834233563047122, "percentage": 6.56, "elapsed_time": "0:42:27", "remaining_time": "10:04:57"}
+{"current_steps": 1330, "total_steps": 20130, "loss": 0.1949, "lr": 0.0004946418521167585, "epoch": 0.9908735332464146, "percentage": 6.61, "elapsed_time": "0:42:46", "remaining_time": "10:04:39"}
+{"current_steps": 1340, "total_steps": 20130, "loss": 0.1607, "lr": 0.000494561209216528, "epoch": 0.9983237101881169, "percentage": 6.66, "elapsed_time": "0:43:06", "remaining_time": "10:04:34"}
+{"current_steps": 1343, "total_steps": 20130, "eval_loss": 0.31036314368247986, "epoch": 1.0, "percentage": 6.67, "elapsed_time": "0:43:48", "remaining_time": "10:12:46"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02a562b2b3e1fc9072d6fcae3bd05f8b6cfe952269cf7cd2eb6251bbbd92368a
+size 5752