Model save

.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

README.md

@@ -0,0 +1,58 @@
+---
+library_name: transformers
+tags:
+- llama-factory
+- generated_from_trainer
+model-index:
+- name: subset_with_verbose_native_1.5b
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# subset_with_verbose_native_1.5b
+
+This model was trained from scratch on an unknown dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 2e-05
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 4
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 256
+- total_eval_batch_size: 32
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 2.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.50.0
+- Pytorch 2.6.0+cu124
+- Datasets 3.4.1
+- Tokenizers 0.21.0

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 +1,28 @@
+{
+  "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": "4.50.0",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.1,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.50.0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d81ed070e9308642019ed29326b5b791f2d931494615f27cc982f594bf31054
+size 3554214752

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 +1,64 @@
+{"current_steps": 10, "total_steps": 630, "loss": 0.6217, "lr": 3.1746031746031746e-06, "epoch": 0.03169572107765452, "percentage": 1.59, "elapsed_time": "0:04:53", "remaining_time": "5:03:36"}
+{"current_steps": 20, "total_steps": 630, "loss": 0.2821, "lr": 6.349206349206349e-06, "epoch": 0.06339144215530904, "percentage": 3.17, "elapsed_time": "0:09:45", "remaining_time": "4:57:38"}
+{"current_steps": 30, "total_steps": 630, "loss": 0.0935, "lr": 9.523809523809525e-06, "epoch": 0.09508716323296355, "percentage": 4.76, "elapsed_time": "0:14:38", "remaining_time": "4:52:46"}
+{"current_steps": 40, "total_steps": 630, "loss": 0.0607, "lr": 1.2698412698412699e-05, "epoch": 0.12678288431061807, "percentage": 6.35, "elapsed_time": "0:19:33", "remaining_time": "4:48:26"}
+{"current_steps": 50, "total_steps": 630, "loss": 0.0491, "lr": 1.5873015873015872e-05, "epoch": 0.15847860538827258, "percentage": 7.94, "elapsed_time": "0:24:27", "remaining_time": "4:43:41"}
+{"current_steps": 60, "total_steps": 630, "loss": 0.0413, "lr": 1.904761904761905e-05, "epoch": 0.1901743264659271, "percentage": 9.52, "elapsed_time": "0:29:21", "remaining_time": "4:38:54"}
+{"current_steps": 70, "total_steps": 630, "loss": 0.0375, "lr": 1.9992479525042305e-05, "epoch": 0.2218700475435816, "percentage": 11.11, "elapsed_time": "0:34:13", "remaining_time": "4:33:50"}
+{"current_steps": 80, "total_steps": 630, "loss": 0.0335, "lr": 1.99556717736037e-05, "epoch": 0.25356576862123614, "percentage": 12.7, "elapsed_time": "0:39:05", "remaining_time": "4:28:42"}
+{"current_steps": 90, "total_steps": 630, "loss": 0.0312, "lr": 1.9888308262251286e-05, "epoch": 0.28526148969889065, "percentage": 14.29, "elapsed_time": "0:43:56", "remaining_time": "4:23:41"}
+{"current_steps": 100, "total_steps": 630, "loss": 0.0293, "lr": 1.9790595741802757e-05, "epoch": 0.31695721077654515, "percentage": 15.87, "elapsed_time": "0:48:50", "remaining_time": "4:18:53"}
+{"current_steps": 110, "total_steps": 630, "loss": 0.0279, "lr": 1.966283410968174e-05, "epoch": 0.3486529318541997, "percentage": 17.46, "elapsed_time": "0:53:46", "remaining_time": "4:14:11"}
+{"current_steps": 120, "total_steps": 630, "loss": 0.027, "lr": 1.9505415489478293e-05, "epoch": 0.3803486529318542, "percentage": 19.05, "elapsed_time": "0:58:42", "remaining_time": "4:09:30"}
+{"current_steps": 130, "total_steps": 630, "loss": 0.0272, "lr": 1.931882302745057e-05, "epoch": 0.4120443740095087, "percentage": 20.63, "elapsed_time": "1:03:36", "remaining_time": "4:04:39"}
+{"current_steps": 140, "total_steps": 630, "loss": 0.0259, "lr": 1.9103629409661468e-05, "epoch": 0.4437400950871632, "percentage": 22.22, "elapsed_time": "1:08:35", "remaining_time": "4:00:03"}
+{"current_steps": 150, "total_steps": 630, "loss": 0.0242, "lr": 1.8860495104301346e-05, "epoch": 0.4754358161648177, "percentage": 23.81, "elapsed_time": "1:13:27", "remaining_time": "3:55:03"}
+{"current_steps": 160, "total_steps": 630, "loss": 0.0252, "lr": 1.8590166334591533e-05, "epoch": 0.5071315372424723, "percentage": 25.4, "elapsed_time": "1:18:23", "remaining_time": "3:50:15"}
+{"current_steps": 170, "total_steps": 630, "loss": 0.0236, "lr": 1.8293472788490096e-05, "epoch": 0.5388272583201268, "percentage": 26.98, "elapsed_time": "1:23:15", "remaining_time": "3:45:18"}
+{"current_steps": 180, "total_steps": 630, "loss": 0.0233, "lr": 1.7971325072229227e-05, "epoch": 0.5705229793977813, "percentage": 28.57, "elapsed_time": "1:28:07", "remaining_time": "3:40:19"}
+{"current_steps": 190, "total_steps": 630, "loss": 0.023, "lr": 1.7624711915499767e-05, "epoch": 0.6022187004754358, "percentage": 30.16, "elapsed_time": "1:33:07", "remaining_time": "3:35:40"}
+{"current_steps": 200, "total_steps": 630, "loss": 0.0224, "lr": 1.72546971368607e-05, "epoch": 0.6339144215530903, "percentage": 31.75, "elapsed_time": "1:38:03", "remaining_time": "3:30:50"}
+{"current_steps": 210, "total_steps": 630, "loss": 0.0218, "lr": 1.686241637868734e-05, "epoch": 0.6656101426307448, "percentage": 33.33, "elapsed_time": "1:42:58", "remaining_time": "3:25:56"}
+{"current_steps": 220, "total_steps": 630, "loss": 0.0213, "lr": 1.6449073621679128e-05, "epoch": 0.6973058637083994, "percentage": 34.92, "elapsed_time": "1:47:51", "remaining_time": "3:21:01"}
+{"current_steps": 230, "total_steps": 630, "loss": 0.0206, "lr": 1.601593748962485e-05, "epoch": 0.7290015847860539, "percentage": 36.51, "elapsed_time": "1:52:46", "remaining_time": "3:16:07"}
+{"current_steps": 240, "total_steps": 630, "loss": 0.0211, "lr": 1.5564337355766412e-05, "epoch": 0.7606973058637084, "percentage": 38.1, "elapsed_time": "1:57:41", "remaining_time": "3:11:15"}
+{"current_steps": 250, "total_steps": 630, "loss": 0.0216, "lr": 1.5095659262711588e-05, "epoch": 0.7923930269413629, "percentage": 39.68, "elapsed_time": "2:02:38", "remaining_time": "3:06:24"}
+{"current_steps": 260, "total_steps": 630, "loss": 0.0207, "lr": 1.4611341668418199e-05, "epoch": 0.8240887480190174, "percentage": 41.27, "elapsed_time": "2:07:35", "remaining_time": "3:01:34"}
+{"current_steps": 270, "total_steps": 630, "loss": 0.0198, "lr": 1.4112871031306118e-05, "epoch": 0.8557844690966719, "percentage": 42.86, "elapsed_time": "2:12:30", "remaining_time": "2:56:40"}
+{"current_steps": 280, "total_steps": 630, "loss": 0.0202, "lr": 1.3601777248047105e-05, "epoch": 0.8874801901743264, "percentage": 44.44, "elapsed_time": "2:17:27", "remaining_time": "2:51:49"}
+{"current_steps": 290, "total_steps": 630, "loss": 0.0198, "lr": 1.3079628958034856e-05, "epoch": 0.919175911251981, "percentage": 46.03, "elapsed_time": "2:22:24", "remaining_time": "2:46:57"}
+{"current_steps": 300, "total_steps": 630, "loss": 0.0199, "lr": 1.2548028728946548e-05, "epoch": 0.9508716323296355, "percentage": 47.62, "elapsed_time": "2:27:21", "remaining_time": "2:42:05"}
+{"current_steps": 310, "total_steps": 630, "loss": 0.0196, "lr": 1.2008608138172393e-05, "epoch": 0.9825673534072901, "percentage": 49.21, "elapsed_time": "2:32:13", "remaining_time": "2:37:08"}
+{"current_steps": 320, "total_steps": 630, "loss": 0.0192, "lr": 1.1463022765209089e-05, "epoch": 1.012678288431062, "percentage": 50.79, "elapsed_time": "2:36:52", "remaining_time": "2:31:58"}
+{"current_steps": 330, "total_steps": 630, "loss": 0.0172, "lr": 1.0912947110386484e-05, "epoch": 1.0443740095087164, "percentage": 52.38, "elapsed_time": "2:41:47", "remaining_time": "2:27:04"}
+{"current_steps": 340, "total_steps": 630, "loss": 0.0185, "lr": 1.0360069455522765e-05, "epoch": 1.076069730586371, "percentage": 53.97, "elapsed_time": "2:46:44", "remaining_time": "2:22:13"}
+{"current_steps": 350, "total_steps": 630, "loss": 0.0171, "lr": 9.806086682281759e-06, "epoch": 1.1077654516640254, "percentage": 55.56, "elapsed_time": "2:51:39", "remaining_time": "2:17:19"}
+{"current_steps": 360, "total_steps": 630, "loss": 0.0182, "lr": 9.252699064135759e-06, "epoch": 1.13946117274168, "percentage": 57.14, "elapsed_time": "2:56:36", "remaining_time": "2:12:27"}
+{"current_steps": 370, "total_steps": 630, "loss": 0.018, "lr": 8.701605047918277e-06, "epoch": 1.1711568938193344, "percentage": 58.73, "elapsed_time": "3:01:34", "remaining_time": "2:07:35"}
+{"current_steps": 380, "total_steps": 630, "loss": 0.018, "lr": 8.154496040983073e-06, "epoch": 1.202852614896989, "percentage": 60.32, "elapsed_time": "3:06:34", "remaining_time": "2:02:45"}
+{"current_steps": 390, "total_steps": 630, "loss": 0.0177, "lr": 7.613051219968624e-06, "epoch": 1.2345483359746434, "percentage": 61.9, "elapsed_time": "3:11:28", "remaining_time": "1:57:49"}
+{"current_steps": 400, "total_steps": 630, "loss": 0.0168, "lr": 7.0789323771008775e-06, "epoch": 1.266244057052298, "percentage": 63.49, "elapsed_time": "3:16:23", "remaining_time": "1:52:55"}
+{"current_steps": 410, "total_steps": 630, "loss": 0.0178, "lr": 6.553778819851927e-06, "epoch": 1.2979397781299524, "percentage": 65.08, "elapsed_time": "3:21:19", "remaining_time": "1:48:01"}
+{"current_steps": 420, "total_steps": 630, "loss": 0.0167, "lr": 6.039202339608432e-06, "epoch": 1.329635499207607, "percentage": 66.67, "elapsed_time": "3:26:12", "remaining_time": "1:43:06"}
+{"current_steps": 430, "total_steps": 630, "loss": 0.016, "lr": 5.536782264791942e-06, "epoch": 1.3613312202852614, "percentage": 68.25, "elapsed_time": "3:31:06", "remaining_time": "1:38:11"}
+{"current_steps": 440, "total_steps": 630, "loss": 0.0169, "lr": 5.048060613613887e-06, "epoch": 1.393026941362916, "percentage": 69.84, "elapsed_time": "3:36:05", "remaining_time": "1:33:18"}
+{"current_steps": 450, "total_steps": 630, "loss": 0.0167, "lr": 4.5745373613424075e-06, "epoch": 1.4247226624405704, "percentage": 71.43, "elapsed_time": "3:40:57", "remaining_time": "1:28:23"}
+{"current_steps": 460, "total_steps": 630, "loss": 0.0164, "lr": 4.117665836606549e-06, "epoch": 1.456418383518225, "percentage": 73.02, "elapsed_time": "3:45:53", "remaining_time": "1:23:28"}
+{"current_steps": 470, "total_steps": 630, "loss": 0.0166, "lr": 3.6788482608674824e-06, "epoch": 1.4881141045958794, "percentage": 74.6, "elapsed_time": "3:50:52", "remaining_time": "1:18:35"}
+{"current_steps": 480, "total_steps": 630, "loss": 0.017, "lr": 3.2594314447468457e-06, "epoch": 1.519809825673534, "percentage": 76.19, "elapsed_time": "3:55:46", "remaining_time": "1:13:40"}
+{"current_steps": 490, "total_steps": 630, "loss": 0.0162, "lr": 2.8607026544210115e-06, "epoch": 1.5515055467511885, "percentage": 77.78, "elapsed_time": "4:00:37", "remaining_time": "1:08:45"}
+{"current_steps": 500, "total_steps": 630, "loss": 0.0174, "lr": 2.4838856607680185e-06, "epoch": 1.583201267828843, "percentage": 79.37, "elapsed_time": "4:05:34", "remaining_time": "1:03:51"}
+{"current_steps": 510, "total_steps": 630, "loss": 0.0159, "lr": 2.130136983393112e-06, "epoch": 1.6148969889064975, "percentage": 80.95, "elapsed_time": "4:10:29", "remaining_time": "0:58:56"}
+{"current_steps": 520, "total_steps": 630, "loss": 0.0166, "lr": 1.8005423410605772e-06, "epoch": 1.6465927099841522, "percentage": 82.54, "elapsed_time": "4:15:30", "remaining_time": "0:54:02"}
+{"current_steps": 530, "total_steps": 630, "loss": 0.016, "lr": 1.4961133194262101e-06, "epoch": 1.6782884310618067, "percentage": 84.13, "elapsed_time": "4:20:22", "remaining_time": "0:49:07"}
+{"current_steps": 540, "total_steps": 630, "loss": 0.0156, "lr": 1.2177842662977136e-06, "epoch": 1.7099841521394612, "percentage": 85.71, "elapsed_time": "4:25:18", "remaining_time": "0:44:13"}
+{"current_steps": 550, "total_steps": 630, "loss": 0.0157, "lr": 9.664094239520372e-07, "epoch": 1.7416798732171157, "percentage": 87.3, "elapsed_time": "4:30:11", "remaining_time": "0:39:18"}
+{"current_steps": 560, "total_steps": 630, "loss": 0.0166, "lr": 7.427603073110967e-07, "epoch": 1.7733755942947702, "percentage": 88.89, "elapsed_time": "4:35:10", "remaining_time": "0:34:23"}
+{"current_steps": 570, "total_steps": 630, "loss": 0.0158, "lr": 5.475233360227516e-07, "epoch": 1.8050713153724247, "percentage": 90.48, "elapsed_time": "4:40:06", "remaining_time": "0:29:29"}
+{"current_steps": 580, "total_steps": 630, "loss": 0.0157, "lr": 3.8129772771456797e-07, "epoch": 1.8367670364500792, "percentage": 92.06, "elapsed_time": "4:45:00", "remaining_time": "0:24:34"}
+{"current_steps": 590, "total_steps": 630, "loss": 0.0166, "lr": 2.445936588863806e-07, "epoch": 1.8684627575277337, "percentage": 93.65, "elapsed_time": "4:49:52", "remaining_time": "0:19:39"}
+{"current_steps": 600, "total_steps": 630, "loss": 0.0159, "lr": 1.3783069908621772e-07, "epoch": 1.9001584786053882, "percentage": 95.24, "elapsed_time": "4:54:48", "remaining_time": "0:14:44"}
+{"current_steps": 610, "total_steps": 630, "loss": 0.0164, "lr": 6.13365231753571e-08, "epoch": 1.931854199683043, "percentage": 96.83, "elapsed_time": "4:59:42", "remaining_time": "0:09:49"}
+{"current_steps": 620, "total_steps": 630, "loss": 0.0159, "lr": 1.5345905634827073e-08, "epoch": 1.9635499207606975, "percentage": 98.41, "elapsed_time": "5:04:35", "remaining_time": "0:04:54"}
+{"current_steps": 630, "total_steps": 630, "loss": 0.016, "lr": 0.0, "epoch": 1.995245641838352, "percentage": 100.0, "elapsed_time": "5:09:31", "remaining_time": "0:00:00"}
+{"current_steps": 630, "total_steps": 630, "epoch": 1.995245641838352, "percentage": 100.0, "elapsed_time": "5:09:43", "remaining_time": "0:00:00"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1538dffcec333abd11c3402348d7f813ea6b8e7e86fe3b78bde2b8f969f7834c
+size 7544