Training in progress, step 1000

.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

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
+}

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "Qwen/Qwen2.5-Coder-1.5B-Instruct",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 1536,
+  "initializer_range": 0.02,
+  "intermediate_size": 8960,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 2,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": 32768,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.49.0",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5570d2f4f3fe0154cc0d20647018db706f6ae75d0a33c3b23b8d828f83df039
+size 3087467144

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 +1,209 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_log.jsonl

@@ -0,0 +1,101 @@
+{"current_steps": 10, "total_steps": 166628, "loss": 0.6105, "lr": 1.2002640580927805e-08, "epoch": 0.00012002784646037881, "percentage": 0.01, "elapsed_time": "0:00:54", "remaining_time": "10 days, 13:03:08"}
+{"current_steps": 20, "total_steps": 166628, "loss": 0.6215, "lr": 2.400528116185561e-08, "epoch": 0.00024005569292075762, "percentage": 0.01, "elapsed_time": "0:01:34", "remaining_time": "9 days, 2:57:44"}
+{"current_steps": 30, "total_steps": 166628, "loss": 0.6288, "lr": 3.600792174278341e-08, "epoch": 0.0003600835393811364, "percentage": 0.02, "elapsed_time": "0:02:22", "remaining_time": "9 days, 3:06:37"}
+{"current_steps": 40, "total_steps": 166628, "loss": 0.6191, "lr": 4.801056232371122e-08, "epoch": 0.00048011138584151523, "percentage": 0.02, "elapsed_time": "0:03:00", "remaining_time": "8 days, 16:50:03"}
+{"current_steps": 50, "total_steps": 166628, "loss": 0.6403, "lr": 6.001320290463902e-08, "epoch": 0.000600139232301894, "percentage": 0.03, "elapsed_time": "0:03:38", "remaining_time": "8 days, 9:45:40"}
+{"current_steps": 60, "total_steps": 166628, "loss": 0.6238, "lr": 7.201584348556683e-08, "epoch": 0.0007201670787622728, "percentage": 0.04, "elapsed_time": "0:04:26", "remaining_time": "8 days, 13:13:07"}
+{"current_steps": 70, "total_steps": 166628, "loss": 0.6153, "lr": 8.401848406649463e-08, "epoch": 0.0008401949252226517, "percentage": 0.04, "elapsed_time": "0:05:17", "remaining_time": "8 days, 17:40:59"}
+{"current_steps": 80, "total_steps": 166628, "loss": 0.6052, "lr": 9.602112464742244e-08, "epoch": 0.0009602227716830305, "percentage": 0.05, "elapsed_time": "0:06:16", "remaining_time": "9 days, 1:59:54"}
+{"current_steps": 90, "total_steps": 166628, "loss": 0.5754, "lr": 1.0802376522835025e-07, "epoch": 0.0010802506181434093, "percentage": 0.05, "elapsed_time": "0:06:56", "remaining_time": "8 days, 21:55:20"}
+{"current_steps": 100, "total_steps": 166628, "loss": 0.5553, "lr": 1.2002640580927805e-07, "epoch": 0.001200278464603788, "percentage": 0.06, "elapsed_time": "0:07:50", "remaining_time": "9 days, 1:40:43"}
+{"current_steps": 110, "total_steps": 166628, "loss": 0.5569, "lr": 1.3202904639020585e-07, "epoch": 0.0013203063110641669, "percentage": 0.07, "elapsed_time": "0:08:36", "remaining_time": "9 days, 1:10:40"}
+{"current_steps": 120, "total_steps": 166628, "loss": 0.5361, "lr": 1.4403168697113365e-07, "epoch": 0.0014403341575245456, "percentage": 0.07, "elapsed_time": "0:09:20", "remaining_time": "9 days, 0:08:29"}
+{"current_steps": 130, "total_steps": 166628, "loss": 0.4994, "lr": 1.5603432755206145e-07, "epoch": 0.0015603620039849244, "percentage": 0.08, "elapsed_time": "0:09:58", "remaining_time": "8 days, 20:54:56"}
+{"current_steps": 140, "total_steps": 166628, "loss": 0.4816, "lr": 1.6803696813298926e-07, "epoch": 0.0016803898504453034, "percentage": 0.08, "elapsed_time": "0:10:48", "remaining_time": "8 days, 22:19:06"}
+{"current_steps": 150, "total_steps": 166628, "loss": 0.4141, "lr": 1.8003960871391706e-07, "epoch": 0.0018004176969056822, "percentage": 0.09, "elapsed_time": "0:11:37", "remaining_time": "8 days, 22:54:27"}
+{"current_steps": 160, "total_steps": 166628, "loss": 0.405, "lr": 1.9204224929484489e-07, "epoch": 0.001920445543366061, "percentage": 0.1, "elapsed_time": "0:12:20", "remaining_time": "8 days, 21:59:04"}
+{"current_steps": 170, "total_steps": 166628, "loss": 0.3405, "lr": 2.040448898757727e-07, "epoch": 0.00204047338982644, "percentage": 0.1, "elapsed_time": "0:13:03", "remaining_time": "8 days, 21:03:25"}
+{"current_steps": 180, "total_steps": 166628, "loss": 0.3295, "lr": 2.160475304567005e-07, "epoch": 0.0021605012362868187, "percentage": 0.11, "elapsed_time": "0:13:39", "remaining_time": "8 days, 18:23:16"}
+{"current_steps": 190, "total_steps": 166628, "loss": 0.3121, "lr": 2.280501710376283e-07, "epoch": 0.0022805290827471974, "percentage": 0.11, "elapsed_time": "0:14:23", "remaining_time": "8 days, 18:00:53"}
+{"current_steps": 200, "total_steps": 166628, "loss": 0.3089, "lr": 2.400528116185561e-07, "epoch": 0.002400556929207576, "percentage": 0.12, "elapsed_time": "0:15:06", "remaining_time": "8 days, 17:34:46"}
+{"current_steps": 210, "total_steps": 166628, "loss": 0.2922, "lr": 2.520554521994839e-07, "epoch": 0.002520584775667955, "percentage": 0.13, "elapsed_time": "0:16:14", "remaining_time": "8 days, 22:36:10"}
+{"current_steps": 220, "total_steps": 166628, "loss": 0.3005, "lr": 2.640580927804117e-07, "epoch": 0.0026406126221283337, "percentage": 0.13, "elapsed_time": "0:17:01", "remaining_time": "8 days, 22:39:47"}
+{"current_steps": 230, "total_steps": 166628, "loss": 0.2631, "lr": 2.760607333613395e-07, "epoch": 0.0027606404685887125, "percentage": 0.14, "elapsed_time": "0:17:40", "remaining_time": "8 days, 21:06:02"}
+{"current_steps": 240, "total_steps": 166628, "loss": 0.2677, "lr": 2.880633739422673e-07, "epoch": 0.0028806683150490913, "percentage": 0.14, "elapsed_time": "0:18:30", "remaining_time": "8 days, 21:46:02"}
+{"current_steps": 250, "total_steps": 166628, "loss": 0.2569, "lr": 3.000660145231951e-07, "epoch": 0.00300069616150947, "percentage": 0.15, "elapsed_time": "0:19:04", "remaining_time": "8 days, 19:33:51"}
+{"current_steps": 260, "total_steps": 166628, "loss": 0.257, "lr": 3.120686551041229e-07, "epoch": 0.003120724007969849, "percentage": 0.16, "elapsed_time": "0:19:49", "remaining_time": "8 days, 19:24:51"}
+{"current_steps": 270, "total_steps": 166628, "loss": 0.2646, "lr": 3.240712956850507e-07, "epoch": 0.003240751854430228, "percentage": 0.16, "elapsed_time": "0:20:52", "remaining_time": "8 days, 22:18:14"}
+{"current_steps": 280, "total_steps": 166628, "loss": 0.2304, "lr": 3.360739362659785e-07, "epoch": 0.0033607797008906068, "percentage": 0.17, "elapsed_time": "0:21:35", "remaining_time": "8 days, 21:46:38"}
+{"current_steps": 290, "total_steps": 166628, "loss": 0.2231, "lr": 3.480765768469063e-07, "epoch": 0.0034808075473509855, "percentage": 0.17, "elapsed_time": "0:22:08", "remaining_time": "8 days, 19:36:41"}
+{"current_steps": 300, "total_steps": 166628, "loss": 0.2314, "lr": 3.600792174278341e-07, "epoch": 0.0036008353938113643, "percentage": 0.18, "elapsed_time": "0:22:43", "remaining_time": "8 days, 18:03:24"}
+{"current_steps": 310, "total_steps": 166628, "loss": 0.2308, "lr": 3.720818580087619e-07, "epoch": 0.003720863240271743, "percentage": 0.19, "elapsed_time": "0:23:22", "remaining_time": "8 days, 16:57:34"}
+{"current_steps": 320, "total_steps": 166628, "loss": 0.2461, "lr": 3.8408449858968977e-07, "epoch": 0.003840891086732122, "percentage": 0.19, "elapsed_time": "0:24:18", "remaining_time": "8 days, 18:34:06"}
+{"current_steps": 330, "total_steps": 166628, "loss": 0.2284, "lr": 3.960871391706176e-07, "epoch": 0.003960918933192501, "percentage": 0.2, "elapsed_time": "0:25:02", "remaining_time": "8 days, 18:21:46"}
+{"current_steps": 340, "total_steps": 166628, "loss": 0.2153, "lr": 4.080897797515454e-07, "epoch": 0.00408094677965288, "percentage": 0.2, "elapsed_time": "0:25:48", "remaining_time": "8 days, 18:21:20"}
+{"current_steps": 350, "total_steps": 166628, "loss": 0.2049, "lr": 4.200924203324732e-07, "epoch": 0.004200974626113258, "percentage": 0.21, "elapsed_time": "0:26:35", "remaining_time": "8 days, 18:31:14"}
+{"current_steps": 360, "total_steps": 166628, "loss": 0.203, "lr": 4.32095060913401e-07, "epoch": 0.004321002472573637, "percentage": 0.22, "elapsed_time": "0:27:19", "remaining_time": "8 days, 18:21:44"}
+{"current_steps": 370, "total_steps": 166628, "loss": 0.2269, "lr": 4.440977014943288e-07, "epoch": 0.004441030319034016, "percentage": 0.22, "elapsed_time": "0:28:07", "remaining_time": "8 days, 18:41:24"}
+{"current_steps": 380, "total_steps": 166628, "loss": 0.1951, "lr": 4.561003420752566e-07, "epoch": 0.004561058165494395, "percentage": 0.23, "elapsed_time": "0:28:52", "remaining_time": "8 days, 18:29:11"}
+{"current_steps": 390, "total_steps": 166628, "loss": 0.1955, "lr": 4.681029826561844e-07, "epoch": 0.004681086011954773, "percentage": 0.23, "elapsed_time": "0:29:33", "remaining_time": "8 days, 17:59:14"}
+{"current_steps": 400, "total_steps": 166628, "loss": 0.1988, "lr": 4.801056232371122e-07, "epoch": 0.004801113858415152, "percentage": 0.24, "elapsed_time": "0:30:20", "remaining_time": "8 days, 18:06:24"}
+{"current_steps": 410, "total_steps": 166628, "loss": 0.2013, "lr": 4.9210826381804e-07, "epoch": 0.004921141704875531, "percentage": 0.25, "elapsed_time": "0:31:00", "remaining_time": "8 days, 17:28:33"}
+{"current_steps": 420, "total_steps": 166628, "loss": 0.1936, "lr": 5.041109043989678e-07, "epoch": 0.00504116955133591, "percentage": 0.25, "elapsed_time": "0:31:49", "remaining_time": "8 days, 17:53:44"}
+{"current_steps": 430, "total_steps": 166628, "loss": 0.1858, "lr": 5.161135449798956e-07, "epoch": 0.005161197397796289, "percentage": 0.26, "elapsed_time": "0:32:29", "remaining_time": "8 days, 17:16:13"}
+{"current_steps": 440, "total_steps": 166628, "loss": 0.181, "lr": 5.281161855608234e-07, "epoch": 0.0052812252442566675, "percentage": 0.26, "elapsed_time": "0:33:13", "remaining_time": "8 days, 17:06:23"}
+{"current_steps": 450, "total_steps": 166628, "loss": 0.1793, "lr": 5.401188261417512e-07, "epoch": 0.005401253090717047, "percentage": 0.27, "elapsed_time": "0:33:54", "remaining_time": "8 days, 16:43:23"}
+{"current_steps": 460, "total_steps": 166628, "loss": 0.2124, "lr": 5.52121466722679e-07, "epoch": 0.005521280937177425, "percentage": 0.28, "elapsed_time": "0:34:50", "remaining_time": "8 days, 17:48:04"}
+{"current_steps": 470, "total_steps": 166628, "loss": 0.1752, "lr": 5.641241073036068e-07, "epoch": 0.005641308783637804, "percentage": 0.28, "elapsed_time": "0:35:32", "remaining_time": "8 days, 17:25:00"}
+{"current_steps": 480, "total_steps": 166628, "loss": 0.1806, "lr": 5.761267478845346e-07, "epoch": 0.0057613366300981825, "percentage": 0.29, "elapsed_time": "0:36:12", "remaining_time": "8 days, 16:52:47"}
+{"current_steps": 490, "total_steps": 166628, "loss": 0.1748, "lr": 5.881293884654624e-07, "epoch": 0.005881364476558562, "percentage": 0.29, "elapsed_time": "0:36:52", "remaining_time": "8 days, 16:23:02"}
+{"current_steps": 500, "total_steps": 166628, "loss": 0.187, "lr": 6.001320290463902e-07, "epoch": 0.00600139232301894, "percentage": 0.3, "elapsed_time": "0:37:38", "remaining_time": "8 days, 16:26:59"}
+{"current_steps": 510, "total_steps": 166628, "loss": 0.1776, "lr": 6.12134669627318e-07, "epoch": 0.006121420169479319, "percentage": 0.31, "elapsed_time": "0:38:23", "remaining_time": "8 days, 16:24:30"}
+{"current_steps": 520, "total_steps": 166628, "loss": 0.151, "lr": 6.241373102082458e-07, "epoch": 0.006241448015939698, "percentage": 0.31, "elapsed_time": "0:38:58", "remaining_time": "8 days, 15:29:40"}
+{"current_steps": 530, "total_steps": 166628, "loss": 0.1553, "lr": 6.361399507891737e-07, "epoch": 0.006361475862400077, "percentage": 0.32, "elapsed_time": "0:39:42", "remaining_time": "8 days, 15:23:25"}
+{"current_steps": 540, "total_steps": 166628, "loss": 0.1681, "lr": 6.481425913701014e-07, "epoch": 0.006481503708860456, "percentage": 0.32, "elapsed_time": "0:40:27", "remaining_time": "8 days, 15:21:16"}
+{"current_steps": 550, "total_steps": 166628, "loss": 0.1532, "lr": 6.601452319510293e-07, "epoch": 0.006601531555320834, "percentage": 0.33, "elapsed_time": "0:41:04", "remaining_time": "8 days, 14:43:08"}
+{"current_steps": 560, "total_steps": 166628, "loss": 0.1609, "lr": 6.72147872531957e-07, "epoch": 0.0067215594017812135, "percentage": 0.34, "elapsed_time": "0:41:56", "remaining_time": "8 days, 15:15:30"}
+{"current_steps": 570, "total_steps": 166628, "loss": 0.1475, "lr": 6.841505131128849e-07, "epoch": 0.006841587248241592, "percentage": 0.34, "elapsed_time": "0:42:47", "remaining_time": "8 days, 15:46:09"}
+{"current_steps": 580, "total_steps": 166628, "loss": 0.1375, "lr": 6.961531536938126e-07, "epoch": 0.006961615094701971, "percentage": 0.35, "elapsed_time": "0:43:23", "remaining_time": "8 days, 15:02:16"}
+{"current_steps": 590, "total_steps": 166628, "loss": 0.1569, "lr": 7.081557942747405e-07, "epoch": 0.007081642941162349, "percentage": 0.35, "elapsed_time": "0:44:05", "remaining_time": "8 days, 14:46:51"}
+{"current_steps": 600, "total_steps": 166628, "loss": 0.1716, "lr": 7.201584348556682e-07, "epoch": 0.007201670787622729, "percentage": 0.36, "elapsed_time": "0:44:49", "remaining_time": "8 days, 14:45:22"}
+{"current_steps": 610, "total_steps": 166628, "loss": 0.161, "lr": 7.321610754365961e-07, "epoch": 0.007321698634083107, "percentage": 0.37, "elapsed_time": "0:45:28", "remaining_time": "8 days, 14:16:18"}
+{"current_steps": 620, "total_steps": 166628, "loss": 0.1617, "lr": 7.441637160175238e-07, "epoch": 0.007441726480543486, "percentage": 0.37, "elapsed_time": "0:46:12", "remaining_time": "8 days, 14:10:57"}
+{"current_steps": 630, "total_steps": 166628, "loss": 0.156, "lr": 7.561663565984517e-07, "epoch": 0.0075617543270038645, "percentage": 0.38, "elapsed_time": "0:46:57", "remaining_time": "8 days, 14:14:29"}
+{"current_steps": 640, "total_steps": 166628, "loss": 0.166, "lr": 7.681689971793795e-07, "epoch": 0.007681782173464244, "percentage": 0.38, "elapsed_time": "0:47:49", "remaining_time": "8 days, 14:45:03"}
+{"current_steps": 650, "total_steps": 166628, "loss": 0.1291, "lr": 7.801716377603073e-07, "epoch": 0.007801810019924623, "percentage": 0.39, "elapsed_time": "0:48:24", "remaining_time": "8 days, 14:03:04"}
+{"current_steps": 660, "total_steps": 166628, "loss": 0.1541, "lr": 7.921742783412351e-07, "epoch": 0.007921837866385001, "percentage": 0.4, "elapsed_time": "0:49:00", "remaining_time": "8 days, 13:24:42"}
+{"current_steps": 670, "total_steps": 166628, "loss": 0.1457, "lr": 8.04176918922163e-07, "epoch": 0.00804186571284538, "percentage": 0.4, "elapsed_time": "0:49:45", "remaining_time": "8 days, 13:25:08"}
+{"current_steps": 680, "total_steps": 166628, "loss": 0.1642, "lr": 8.161795595030908e-07, "epoch": 0.00816189355930576, "percentage": 0.41, "elapsed_time": "0:50:29", "remaining_time": "8 days, 13:22:24"}
+{"current_steps": 690, "total_steps": 166628, "loss": 0.1378, "lr": 8.281822000840186e-07, "epoch": 0.008281921405766137, "percentage": 0.41, "elapsed_time": "0:51:12", "remaining_time": "8 days, 13:13:08"}
+{"current_steps": 700, "total_steps": 166628, "loss": 0.1539, "lr": 8.401848406649464e-07, "epoch": 0.008401949252226516, "percentage": 0.42, "elapsed_time": "0:51:56", "remaining_time": "8 days, 13:13:08"}
+{"current_steps": 710, "total_steps": 166628, "loss": 0.1329, "lr": 8.521874812458742e-07, "epoch": 0.008521977098686895, "percentage": 0.43, "elapsed_time": "0:52:31", "remaining_time": "8 days, 12:34:04"}
+{"current_steps": 720, "total_steps": 166628, "loss": 0.1586, "lr": 8.64190121826802e-07, "epoch": 0.008642004945147275, "percentage": 0.43, "elapsed_time": "0:53:17", "remaining_time": "8 days, 12:41:07"}
+{"current_steps": 730, "total_steps": 166628, "loss": 0.151, "lr": 8.761927624077298e-07, "epoch": 0.008762032791607652, "percentage": 0.44, "elapsed_time": "0:54:05", "remaining_time": "8 days, 12:52:27"}
+{"current_steps": 740, "total_steps": 166628, "loss": 0.1505, "lr": 8.881954029886576e-07, "epoch": 0.008882060638068031, "percentage": 0.44, "elapsed_time": "0:54:46", "remaining_time": "8 days, 12:40:20"}
+{"current_steps": 750, "total_steps": 166628, "loss": 0.1421, "lr": 9.001980435695854e-07, "epoch": 0.00900208848452841, "percentage": 0.45, "elapsed_time": "0:55:30", "remaining_time": "8 days, 12:36:59"}
+{"current_steps": 760, "total_steps": 166628, "loss": 0.149, "lr": 9.122006841505132e-07, "epoch": 0.00912211633098879, "percentage": 0.46, "elapsed_time": "0:56:16", "remaining_time": "8 days, 12:43:31"}
+{"current_steps": 770, "total_steps": 166628, "loss": 0.1715, "lr": 9.24203324731441e-07, "epoch": 0.009242144177449169, "percentage": 0.46, "elapsed_time": "0:57:19", "remaining_time": "8 days, 13:47:50"}
+{"current_steps": 780, "total_steps": 166628, "loss": 0.1477, "lr": 9.362059653123688e-07, "epoch": 0.009362172023909546, "percentage": 0.47, "elapsed_time": "0:58:04", "remaining_time": "8 days, 13:48:47"}
+{"current_steps": 790, "total_steps": 166628, "loss": 0.1446, "lr": 9.482086058932966e-07, "epoch": 0.009482199870369926, "percentage": 0.47, "elapsed_time": "0:58:55", "remaining_time": "8 days, 14:09:31"}
+{"current_steps": 800, "total_steps": 166628, "loss": 0.1493, "lr": 9.602112464742244e-07, "epoch": 0.009602227716830305, "percentage": 0.48, "elapsed_time": "0:59:53", "remaining_time": "8 days, 14:56:00"}
+{"current_steps": 810, "total_steps": 166628, "loss": 0.1379, "lr": 9.72213887055152e-07, "epoch": 0.009722255563290684, "percentage": 0.49, "elapsed_time": "1:00:39", "remaining_time": "8 days, 14:56:08"}
+{"current_steps": 820, "total_steps": 166628, "loss": 0.1441, "lr": 9.8421652763608e-07, "epoch": 0.009842283409751061, "percentage": 0.49, "elapsed_time": "1:01:27", "remaining_time": "8 days, 15:06:48"}
+{"current_steps": 830, "total_steps": 166628, "loss": 0.1431, "lr": 9.962191682170077e-07, "epoch": 0.00996231125621144, "percentage": 0.5, "elapsed_time": "1:02:15", "remaining_time": "8 days, 15:17:08"}
+{"current_steps": 840, "total_steps": 166628, "loss": 0.1326, "lr": 1.0082218087979356e-06, "epoch": 0.01008233910267182, "percentage": 0.5, "elapsed_time": "1:02:55", "remaining_time": "8 days, 14:57:42"}
+{"current_steps": 850, "total_steps": 166628, "loss": 0.1429, "lr": 1.0202244493788635e-06, "epoch": 0.010202366949132199, "percentage": 0.51, "elapsed_time": "1:03:40", "remaining_time": "8 days, 14:58:01"}
+{"current_steps": 860, "total_steps": 166628, "loss": 0.112, "lr": 1.0322270899597912e-06, "epoch": 0.010322394795592578, "percentage": 0.52, "elapsed_time": "1:04:25", "remaining_time": "8 days, 14:58:15"}
+{"current_steps": 870, "total_steps": 166628, "loss": 0.1337, "lr": 1.044229730540719e-06, "epoch": 0.010442422642052956, "percentage": 0.52, "elapsed_time": "1:05:01", "remaining_time": "8 days, 14:29:57"}
+{"current_steps": 880, "total_steps": 166628, "loss": 0.1354, "lr": 1.0562323711216468e-06, "epoch": 0.010562450488513335, "percentage": 0.53, "elapsed_time": "1:05:46", "remaining_time": "8 days, 14:28:20"}
+{"current_steps": 890, "total_steps": 166628, "loss": 0.1337, "lr": 1.0682350117025747e-06, "epoch": 0.010682478334973714, "percentage": 0.53, "elapsed_time": "1:06:25", "remaining_time": "8 days, 14:10:19"}
+{"current_steps": 900, "total_steps": 166628, "loss": 0.1109, "lr": 1.0802376522835024e-06, "epoch": 0.010802506181434093, "percentage": 0.54, "elapsed_time": "1:07:06", "remaining_time": "8 days, 13:56:04"}
+{"current_steps": 910, "total_steps": 166628, "loss": 0.1346, "lr": 1.0922402928644303e-06, "epoch": 0.01092253402789447, "percentage": 0.55, "elapsed_time": "1:07:51", "remaining_time": "8 days, 13:57:36"}
+{"current_steps": 920, "total_steps": 166628, "loss": 0.1323, "lr": 1.104242933445358e-06, "epoch": 0.01104256187435485, "percentage": 0.55, "elapsed_time": "1:08:39", "remaining_time": "8 days, 14:05:19"}
+{"current_steps": 930, "total_steps": 166628, "loss": 0.1395, "lr": 1.116245574026286e-06, "epoch": 0.01116258972081523, "percentage": 0.56, "elapsed_time": "1:09:29", "remaining_time": "8 days, 14:20:53"}
+{"current_steps": 940, "total_steps": 166628, "loss": 0.1579, "lr": 1.1282482146072136e-06, "epoch": 0.011282617567275608, "percentage": 0.56, "elapsed_time": "1:10:32", "remaining_time": "8 days, 15:15:11"}
+{"current_steps": 950, "total_steps": 166628, "loss": 0.1358, "lr": 1.1402508551881415e-06, "epoch": 0.011402645413735986, "percentage": 0.57, "elapsed_time": "1:11:12", "remaining_time": "8 days, 14:59:09"}
+{"current_steps": 960, "total_steps": 166628, "loss": 0.1345, "lr": 1.1522534957690692e-06, "epoch": 0.011522673260196365, "percentage": 0.58, "elapsed_time": "1:11:57", "remaining_time": "8 days, 14:56:55"}
+{"current_steps": 970, "total_steps": 166628, "loss": 0.1418, "lr": 1.1642561363499971e-06, "epoch": 0.011642701106656744, "percentage": 0.58, "elapsed_time": "1:12:47", "remaining_time": "8 days, 15:12:21"}
+{"current_steps": 980, "total_steps": 166628, "loss": 0.1388, "lr": 1.1762587769309248e-06, "epoch": 0.011762728953117123, "percentage": 0.59, "elapsed_time": "1:13:34", "remaining_time": "8 days, 15:17:38"}
+{"current_steps": 990, "total_steps": 166628, "loss": 0.1202, "lr": 1.1882614175118527e-06, "epoch": 0.011882756799577503, "percentage": 0.59, "elapsed_time": "1:14:14", "remaining_time": "8 days, 15:02:21"}
+{"current_steps": 1000, "total_steps": 166628, "loss": 0.1193, "lr": 1.2002640580927804e-06, "epoch": 0.01200278464603788, "percentage": 0.6, "elapsed_time": "1:15:04", "remaining_time": "8 days, 15:15:17"}
+{"current_steps": 1010, "total_steps": 166628, "loss": 0.1231, "lr": 1.2122666986737083e-06, "epoch": 0.01212281249249826, "percentage": 0.61, "elapsed_time": "1:16:04", "remaining_time": "8 days, 15:54:41"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13befb8e966c1bf28eb7bb63c0c75dcf03bd294b306fcada6d5cb543c4e351c1
+size 7800