Add files using upload-large-folder tool

.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 +1,63 @@
+---
+library_name: peft
+license: other
+base_model: Qwen/Qwen2.5-14B-Instruct
+tags:
+- llama-factory
+- lora
+- generated_from_trainer
+model-index:
+- name: omni_training_less_than_5
+  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. -->
+
+# omni_training_less_than_5
+
+This model is a fine-tuned version of [Qwen/Qwen2.5-14B-Instruct](https://huggingface.co/Qwen/Qwen2.5-14B-Instruct) on the omni_training_less_than_5 dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.7308
+
+## 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: 0.0001
+- train_batch_size: 2
+- eval_batch_size: 1
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 4
+- total_train_batch_size: 8
+- total_eval_batch_size: 4
+- optimizer: Use 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
+
+- PEFT 0.12.0
+- Transformers 4.46.1
+- Pytorch 2.5.1+cu124
+- Datasets 3.1.0
+- Tokenizers 0.20.3

adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-14B-Instruct",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "gate_proj",
+    "q_proj",
+    "up_proj",
+    "k_proj",
+    "o_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:a16e04a6a4be274ef21044caf2572f11049dc7fc5e3aaab52509e8c825f7a979
+size 68902296

added_tokens.json

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

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 2.0,
+    "eval_loss": 0.7307779788970947,
+    "eval_runtime": 1.5534,
+    "eval_samples_per_second": 1.288,
+    "eval_steps_per_second": 0.644,
+    "total_flos": 167148584435712.0,
+    "train_loss": 0.7704400447281924,
+    "train_runtime": 273.3504,
+    "train_samples_per_second": 1.266,
+    "train_steps_per_second": 0.161
+}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 2.0,
+    "eval_loss": 0.7307779788970947,
+    "eval_runtime": 1.5534,
+    "eval_samples_per_second": 1.288,
+    "eval_steps_per_second": 0.644
+}

special_tokens_map.json

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

tokenizer.json

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

tokenizer_config.json

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

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.0,
+    "total_flos": 167148584435712.0,
+    "train_loss": 0.7704400447281924,
+    "train_runtime": 273.3504,
+    "train_samples_per_second": 1.266,
+    "train_steps_per_second": 0.161
+}

trainer_log.jsonl

@@ -0,0 +1,45 @@
+{"current_steps": 1, "total_steps": 44, "loss": 0.8818, "lr": 2e-05, "epoch": 0.045454545454545456, "percentage": 2.27, "elapsed_time": "0:00:08", "remaining_time": "0:05:57"}
+{"current_steps": 2, "total_steps": 44, "loss": 0.876, "lr": 4e-05, "epoch": 0.09090909090909091, "percentage": 4.55, "elapsed_time": "0:00:18", "remaining_time": "0:06:31"}
+{"current_steps": 3, "total_steps": 44, "loss": 1.2233, "lr": 6e-05, "epoch": 0.13636363636363635, "percentage": 6.82, "elapsed_time": "0:00:24", "remaining_time": "0:05:31"}
+{"current_steps": 4, "total_steps": 44, "loss": 1.019, "lr": 8e-05, "epoch": 0.18181818181818182, "percentage": 9.09, "elapsed_time": "0:00:29", "remaining_time": "0:04:57"}
+{"current_steps": 5, "total_steps": 44, "loss": 0.7696, "lr": 0.0001, "epoch": 0.22727272727272727, "percentage": 11.36, "elapsed_time": "0:00:35", "remaining_time": "0:04:35"}
+{"current_steps": 6, "total_steps": 44, "loss": 0.9575, "lr": 9.983786540671051e-05, "epoch": 0.2727272727272727, "percentage": 13.64, "elapsed_time": "0:00:40", "remaining_time": "0:04:19"}
+{"current_steps": 7, "total_steps": 44, "loss": 0.8849, "lr": 9.935251313189564e-05, "epoch": 0.3181818181818182, "percentage": 15.91, "elapsed_time": "0:00:46", "remaining_time": "0:04:06"}
+{"current_steps": 8, "total_steps": 44, "loss": 0.8554, "lr": 9.85470908713026e-05, "epoch": 0.36363636363636365, "percentage": 18.18, "elapsed_time": "0:00:52", "remaining_time": "0:03:54"}
+{"current_steps": 9, "total_steps": 44, "loss": 0.7842, "lr": 9.742682209735727e-05, "epoch": 0.4090909090909091, "percentage": 20.45, "elapsed_time": "0:00:57", "remaining_time": "0:03:44"}
+{"current_steps": 10, "total_steps": 44, "loss": 0.7777, "lr": 9.599897218294122e-05, "epoch": 0.45454545454545453, "percentage": 22.73, "elapsed_time": "0:01:03", "remaining_time": "0:03:35"}
+{"current_steps": 11, "total_steps": 44, "loss": 0.7611, "lr": 9.42728012826605e-05, "epoch": 0.5, "percentage": 25.0, "elapsed_time": "0:01:08", "remaining_time": "0:03:26"}
+{"current_steps": 12, "total_steps": 44, "loss": 0.7816, "lr": 9.225950427718975e-05, "epoch": 0.5454545454545454, "percentage": 27.27, "elapsed_time": "0:01:14", "remaining_time": "0:03:18"}
+{"current_steps": 13, "total_steps": 44, "loss": 0.7748, "lr": 8.997213817017507e-05, "epoch": 0.5909090909090909, "percentage": 29.55, "elapsed_time": "0:01:20", "remaining_time": "0:03:11"}
+{"current_steps": 14, "total_steps": 44, "loss": 0.7604, "lr": 8.742553740855506e-05, "epoch": 0.6363636363636364, "percentage": 31.82, "elapsed_time": "0:01:25", "remaining_time": "0:03:03"}
+{"current_steps": 15, "total_steps": 44, "loss": 0.7948, "lr": 8.463621767547998e-05, "epoch": 0.6818181818181818, "percentage": 34.09, "elapsed_time": "0:01:31", "remaining_time": "0:02:56"}
+{"current_steps": 16, "total_steps": 44, "loss": 0.7387, "lr": 8.162226877976887e-05, "epoch": 0.7272727272727273, "percentage": 36.36, "elapsed_time": "0:01:37", "remaining_time": "0:02:49"}
+{"current_steps": 17, "total_steps": 44, "loss": 0.8671, "lr": 7.840323733655778e-05, "epoch": 0.7727272727272727, "percentage": 38.64, "elapsed_time": "0:01:42", "remaining_time": "0:02:42"}
+{"current_steps": 18, "total_steps": 44, "loss": 0.6836, "lr": 7.500000000000001e-05, "epoch": 0.8181818181818182, "percentage": 40.91, "elapsed_time": "0:01:48", "remaining_time": "0:02:36"}
+{"current_steps": 19, "total_steps": 44, "loss": 0.7574, "lr": 7.143462807015271e-05, "epoch": 0.8636363636363636, "percentage": 43.18, "elapsed_time": "0:01:53", "remaining_time": "0:02:29"}
+{"current_steps": 20, "total_steps": 44, "loss": 0.6944, "lr": 6.773024435212678e-05, "epoch": 0.9090909090909091, "percentage": 45.45, "elapsed_time": "0:01:59", "remaining_time": "0:02:23"}
+{"current_steps": 21, "total_steps": 44, "loss": 0.7105, "lr": 6.391087319582264e-05, "epoch": 0.9545454545454546, "percentage": 47.73, "elapsed_time": "0:02:05", "remaining_time": "0:02:17"}
+{"current_steps": 22, "total_steps": 44, "loss": 0.7271, "lr": 6.0001284688802226e-05, "epoch": 1.0, "percentage": 50.0, "elapsed_time": "0:02:10", "remaining_time": "0:02:10"}
+{"current_steps": 23, "total_steps": 44, "loss": 0.7422, "lr": 5.602683401276615e-05, "epoch": 1.0454545454545454, "percentage": 52.27, "elapsed_time": "0:02:16", "remaining_time": "0:02:04"}
+{"current_steps": 24, "total_steps": 44, "loss": 0.7493, "lr": 5.201329700547076e-05, "epoch": 1.0909090909090908, "percentage": 54.55, "elapsed_time": "0:02:22", "remaining_time": "0:01:58"}
+{"current_steps": 25, "total_steps": 44, "loss": 0.7524, "lr": 4.798670299452926e-05, "epoch": 1.1363636363636362, "percentage": 56.82, "elapsed_time": "0:02:27", "remaining_time": "0:01:52"}
+{"current_steps": 26, "total_steps": 44, "loss": 0.7569, "lr": 4.397316598723385e-05, "epoch": 1.1818181818181819, "percentage": 59.09, "elapsed_time": "0:02:33", "remaining_time": "0:01:46"}
+{"current_steps": 27, "total_steps": 44, "loss": 0.74, "lr": 3.9998715311197785e-05, "epoch": 1.2272727272727273, "percentage": 61.36, "elapsed_time": "0:02:38", "remaining_time": "0:01:40"}
+{"current_steps": 28, "total_steps": 44, "loss": 0.7329, "lr": 3.608912680417737e-05, "epoch": 1.2727272727272727, "percentage": 63.64, "elapsed_time": "0:02:44", "remaining_time": "0:01:34"}
+{"current_steps": 29, "total_steps": 44, "loss": 0.6354, "lr": 3.226975564787322e-05, "epoch": 1.3181818181818181, "percentage": 65.91, "elapsed_time": "0:02:50", "remaining_time": "0:01:28"}
+{"current_steps": 30, "total_steps": 44, "loss": 0.686, "lr": 2.8565371929847284e-05, "epoch": 1.3636363636363638, "percentage": 68.18, "elapsed_time": "0:02:55", "remaining_time": "0:01:22"}
+{"current_steps": 31, "total_steps": 44, "loss": 0.7447, "lr": 2.500000000000001e-05, "epoch": 1.4090909090909092, "percentage": 70.45, "elapsed_time": "0:03:01", "remaining_time": "0:01:16"}
+{"current_steps": 32, "total_steps": 44, "loss": 0.679, "lr": 2.1596762663442218e-05, "epoch": 1.4545454545454546, "percentage": 72.73, "elapsed_time": "0:03:06", "remaining_time": "0:01:10"}
+{"current_steps": 33, "total_steps": 44, "loss": 0.716, "lr": 1.837773122023114e-05, "epoch": 1.5, "percentage": 75.0, "elapsed_time": "0:03:12", "remaining_time": "0:01:04"}
+{"current_steps": 34, "total_steps": 44, "loss": 0.7334, "lr": 1.536378232452003e-05, "epoch": 1.5454545454545454, "percentage": 77.27, "elapsed_time": "0:03:18", "remaining_time": "0:00:58"}
+{"current_steps": 35, "total_steps": 44, "loss": 0.684, "lr": 1.257446259144494e-05, "epoch": 1.5909090909090908, "percentage": 79.55, "elapsed_time": "0:03:23", "remaining_time": "0:00:52"}
+{"current_steps": 36, "total_steps": 44, "loss": 0.7261, "lr": 1.0027861829824952e-05, "epoch": 1.6363636363636362, "percentage": 81.82, "elapsed_time": "0:03:29", "remaining_time": "0:00:46"}
+{"current_steps": 37, "total_steps": 44, "loss": 0.7938, "lr": 7.740495722810271e-06, "epoch": 1.6818181818181817, "percentage": 84.09, "elapsed_time": "0:03:34", "remaining_time": "0:00:40"}
+{"current_steps": 38, "total_steps": 44, "loss": 0.7025, "lr": 5.727198717339511e-06, "epoch": 1.7272727272727273, "percentage": 86.36, "elapsed_time": "0:03:40", "remaining_time": "0:00:34"}
+{"current_steps": 39, "total_steps": 44, "loss": 0.7592, "lr": 4.001027817058789e-06, "epoch": 1.7727272727272727, "percentage": 88.64, "elapsed_time": "0:03:46", "remaining_time": "0:00:28"}
+{"current_steps": 40, "total_steps": 44, "loss": 0.7231, "lr": 2.573177902642726e-06, "epoch": 1.8181818181818183, "percentage": 90.91, "elapsed_time": "0:03:51", "remaining_time": "0:00:23"}
+{"current_steps": 41, "total_steps": 44, "loss": 0.6872, "lr": 1.4529091286973995e-06, "epoch": 1.8636363636363638, "percentage": 93.18, "elapsed_time": "0:03:57", "remaining_time": "0:00:17"}
+{"current_steps": 42, "total_steps": 44, "loss": 0.696, "lr": 6.474868681043578e-07, "epoch": 1.9090909090909092, "percentage": 95.45, "elapsed_time": "0:04:03", "remaining_time": "0:00:11"}
+{"current_steps": 43, "total_steps": 44, "loss": 0.6727, "lr": 1.6213459328950352e-07, "epoch": 1.9545454545454546, "percentage": 97.73, "elapsed_time": "0:04:08", "remaining_time": "0:00:05"}
+{"current_steps": 44, "total_steps": 44, "loss": 0.7056, "lr": 0.0, "epoch": 2.0, "percentage": 100.0, "elapsed_time": "0:04:14", "remaining_time": "0:00:00"}
+{"current_steps": 44, "total_steps": 44, "epoch": 2.0, "percentage": 100.0, "elapsed_time": "0:04:33", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,350 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 200,
+  "global_step": 44,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.045454545454545456,
+      "grad_norm": 0.20162349585089198,
+      "learning_rate": 2e-05,
+      "loss": 0.8818,
+      "step": 1
+    },
+    {
+      "epoch": 0.09090909090909091,
+      "grad_norm": 0.1953500581220745,
+      "learning_rate": 4e-05,
+      "loss": 0.876,
+      "step": 2
+    },
+    {
+      "epoch": 0.13636363636363635,
+      "grad_norm": 0.5228028889794835,
+      "learning_rate": 6e-05,
+      "loss": 1.2233,
+      "step": 3
+    },
+    {
+      "epoch": 0.18181818181818182,
+      "grad_norm": 0.3168539123432193,
+      "learning_rate": 8e-05,
+      "loss": 1.019,
+      "step": 4
+    },
+    {
+      "epoch": 0.22727272727272727,
+      "grad_norm": 0.2448592330495161,
+      "learning_rate": 0.0001,
+      "loss": 0.7696,
+      "step": 5
+    },
+    {
+      "epoch": 0.2727272727272727,
+      "grad_norm": 0.5022417968409909,
+      "learning_rate": 9.983786540671051e-05,
+      "loss": 0.9575,
+      "step": 6
+    },
+    {
+      "epoch": 0.3181818181818182,
+      "grad_norm": 0.3690185930765724,
+      "learning_rate": 9.935251313189564e-05,
+      "loss": 0.8849,
+      "step": 7
+    },
+    {
+      "epoch": 0.36363636363636365,
+      "grad_norm": 0.3481259765917461,
+      "learning_rate": 9.85470908713026e-05,
+      "loss": 0.8554,
+      "step": 8
+    },
+    {
+      "epoch": 0.4090909090909091,
+      "grad_norm": 0.2491302807616705,
+      "learning_rate": 9.742682209735727e-05,
+      "loss": 0.7842,
+      "step": 9
+    },
+    {
+      "epoch": 0.45454545454545453,
+      "grad_norm": 0.2553944608600153,
+      "learning_rate": 9.599897218294122e-05,
+      "loss": 0.7777,
+      "step": 10
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.16006256910442612,
+      "learning_rate": 9.42728012826605e-05,
+      "loss": 0.7611,
+      "step": 11
+    },
+    {
+      "epoch": 0.5454545454545454,
+      "grad_norm": 0.15558254774359165,
+      "learning_rate": 9.225950427718975e-05,
+      "loss": 0.7816,
+      "step": 12
+    },
+    {
+      "epoch": 0.5909090909090909,
+      "grad_norm": 0.18832677655086638,
+      "learning_rate": 8.997213817017507e-05,
+      "loss": 0.7748,
+      "step": 13
+    },
+    {
+      "epoch": 0.6363636363636364,
+      "grad_norm": 0.09681390727181982,
+      "learning_rate": 8.742553740855506e-05,
+      "loss": 0.7604,
+      "step": 14
+    },
+    {
+      "epoch": 0.6818181818181818,
+      "grad_norm": 0.07979864307427108,
+      "learning_rate": 8.463621767547998e-05,
+      "loss": 0.7948,
+      "step": 15
+    },
+    {
+      "epoch": 0.7272727272727273,
+      "grad_norm": 0.0751068874132372,
+      "learning_rate": 8.162226877976887e-05,
+      "loss": 0.7387,
+      "step": 16
+    },
+    {
+      "epoch": 0.7727272727272727,
+      "grad_norm": 0.09818843566208878,
+      "learning_rate": 7.840323733655778e-05,
+      "loss": 0.8671,
+      "step": 17
+    },
+    {
+      "epoch": 0.8181818181818182,
+      "grad_norm": 0.12433711342571083,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 0.6836,
+      "step": 18
+    },
+    {
+      "epoch": 0.8636363636363636,
+      "grad_norm": 0.09336807665626587,
+      "learning_rate": 7.143462807015271e-05,
+      "loss": 0.7574,
+      "step": 19
+    },
+    {
+      "epoch": 0.9090909090909091,
+      "grad_norm": 0.10857087455570018,
+      "learning_rate": 6.773024435212678e-05,
+      "loss": 0.6944,
+      "step": 20
+    },
+    {
+      "epoch": 0.9545454545454546,
+      "grad_norm": 0.09987180851168877,
+      "learning_rate": 6.391087319582264e-05,
+      "loss": 0.7105,
+      "step": 21
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.12403936967122979,
+      "learning_rate": 6.0001284688802226e-05,
+      "loss": 0.7271,
+      "step": 22
+    },
+    {
+      "epoch": 1.0454545454545454,
+      "grad_norm": 0.11169323633585997,
+      "learning_rate": 5.602683401276615e-05,
+      "loss": 0.7422,
+      "step": 23
+    },
+    {
+      "epoch": 1.0909090909090908,
+      "grad_norm": 0.08664401280752744,
+      "learning_rate": 5.201329700547076e-05,
+      "loss": 0.7493,
+      "step": 24
+    },
+    {
+      "epoch": 1.1363636363636362,
+      "grad_norm": 0.08676810328328194,
+      "learning_rate": 4.798670299452926e-05,
+      "loss": 0.7524,
+      "step": 25
+    },
+    {
+      "epoch": 1.1818181818181819,
+      "grad_norm": 0.08590933006332456,
+      "learning_rate": 4.397316598723385e-05,
+      "loss": 0.7569,
+      "step": 26
+    },
+    {
+      "epoch": 1.2272727272727273,
+      "grad_norm": 0.08858606445370859,
+      "learning_rate": 3.9998715311197785e-05,
+      "loss": 0.74,
+      "step": 27
+    },
+    {
+      "epoch": 1.2727272727272727,
+      "grad_norm": 0.07666247259553818,
+      "learning_rate": 3.608912680417737e-05,
+      "loss": 0.7329,
+      "step": 28
+    },
+    {
+      "epoch": 1.3181818181818181,
+      "grad_norm": 0.07618604122498249,
+      "learning_rate": 3.226975564787322e-05,
+      "loss": 0.6354,
+      "step": 29
+    },
+    {
+      "epoch": 1.3636363636363638,
+      "grad_norm": 0.08140024777764204,
+      "learning_rate": 2.8565371929847284e-05,
+      "loss": 0.686,
+      "step": 30
+    },
+    {
+      "epoch": 1.4090909090909092,
+      "grad_norm": 0.08978876050933346,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.7447,
+      "step": 31
+    },
+    {
+      "epoch": 1.4545454545454546,
+      "grad_norm": 0.0716318283002434,
+      "learning_rate": 2.1596762663442218e-05,
+      "loss": 0.679,
+      "step": 32
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 0.10585147220057532,
+      "learning_rate": 1.837773122023114e-05,
+      "loss": 0.716,
+      "step": 33
+    },
+    {
+      "epoch": 1.5454545454545454,
+      "grad_norm": 0.08349343850144146,
+      "learning_rate": 1.536378232452003e-05,
+      "loss": 0.7334,
+      "step": 34
+    },
+    {
+      "epoch": 1.5909090909090908,
+      "grad_norm": 0.07246804816219393,
+      "learning_rate": 1.257446259144494e-05,
+      "loss": 0.684,
+      "step": 35
+    },
+    {
+      "epoch": 1.6363636363636362,
+      "grad_norm": 0.08656458135317226,
+      "learning_rate": 1.0027861829824952e-05,
+      "loss": 0.7261,
+      "step": 36
+    },
+    {
+      "epoch": 1.6818181818181817,
+      "grad_norm": 0.07432309009864736,
+      "learning_rate": 7.740495722810271e-06,
+      "loss": 0.7938,
+      "step": 37
+    },
+    {
+      "epoch": 1.7272727272727273,
+      "grad_norm": 0.06644380159937287,
+      "learning_rate": 5.727198717339511e-06,
+      "loss": 0.7025,
+      "step": 38
+    },
+    {
+      "epoch": 1.7727272727272727,
+      "grad_norm": 0.07589928426253979,
+      "learning_rate": 4.001027817058789e-06,
+      "loss": 0.7592,
+      "step": 39
+    },
+    {
+      "epoch": 1.8181818181818183,
+      "grad_norm": 0.1400960157888807,
+      "learning_rate": 2.573177902642726e-06,
+      "loss": 0.7231,
+      "step": 40
+    },
+    {
+      "epoch": 1.8636363636363638,
+      "grad_norm": 0.07387468065399092,
+      "learning_rate": 1.4529091286973995e-06,
+      "loss": 0.6872,
+      "step": 41
+    },
+    {
+      "epoch": 1.9090909090909092,
+      "grad_norm": 0.0855342727329305,
+      "learning_rate": 6.474868681043578e-07,
+      "loss": 0.696,
+      "step": 42
+    },
+    {
+      "epoch": 1.9545454545454546,
+      "grad_norm": 0.0985088722005277,
+      "learning_rate": 1.6213459328950352e-07,
+      "loss": 0.6727,
+      "step": 43
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.07968270308548887,
+      "learning_rate": 0.0,
+      "loss": 0.7056,
+      "step": 44
+    },
+    {
+      "epoch": 2.0,
+      "step": 44,
+      "total_flos": 167148584435712.0,
+      "train_loss": 0.7704400447281924,
+      "train_runtime": 273.3504,
+      "train_samples_per_second": 1.266,
+      "train_steps_per_second": 0.161
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 44,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 167148584435712.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ecc80db74aacbbe132f654f49994d63c9f8651b65cf58b6dfdd357f0b975c2da
+size 7224