初始化项目，由ModelHub XC社区提供模型

Model: lldois/v38_v29_r3_aggressive_lr7e7_ep10
Source: Original Platform

.gitattributes

@@ -0,0 +1,36 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz 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
+license: other
+base_model: lldois/v29_v19_user_world_guard_lr8e7_ep018
+tags:
+- llama-factory
+- full
+- generated_from_trainer
+model-index:
+- name: v38_v29_r3_aggressive_lr7e7_ep10
+  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. -->
+
+# v38_v29_r3_aggressive_lr7e7_ep10
+
+This model is a fine-tuned version of [lldois/v29_v19_user_world_guard_lr8e7_ep018](https://huggingface.co/lldois/v29_v19_user_world_guard_lr8e7_ep018) on the exp_v38_r3_aggressive 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: 7e-07
+- train_batch_size: 1
+- eval_batch_size: 8
+- seed: 202607188
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 4
+- 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_steps: 0.03
+- num_epochs: 1.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 5.6.0
+- Pytorch 2.7.1+cu126
+- Datasets 4.0.0
+- Tokenizers 0.22.2

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "total_flos": 2.197680639479255e+17,
+    "train_loss": 2.143569690286467,
+    "train_runtime": 3558.7051,
+    "train_samples_per_second": 0.518,
+    "train_steps_per_second": 0.13
+}

chat_template.jinja

@@ -0,0 +1,89 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# 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>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\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" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- 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>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if message.content is string %}
+        {%- set content = message.content %}
+    {%- else %}
+        {%- set content = '' %}
+    {%- endif %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in content %}
+                {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+                {%- set content = content.split('</think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

config.json

@@ -0,0 +1,63 @@
+{
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": null,
+  "dtype": "bfloat16",
+  "eos_token_id": 151645,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 40960,
+  "max_window_layers": 28,
+  "model_type": "qwen3",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 8,
+  "pad_token_id": 151643,
+  "rms_norm_eps": 1e-06,
+  "rope_parameters": {
+    "rope_theta": 1000000,
+    "rope_type": "default"
+  },
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "transformers_version": "5.6.0",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 176253
+}

experiment_recipe.json

@@ -0,0 +1,72 @@
+{
+  "created_at": "2026-07-15 00:59:15",
+  "name": "v38_v29_r3_aggressive_lr7e7_ep10",
+  "base": "/home/ll/llm4rec/experiments/outputs/v29_v19_user_world_guard_lr8e7_ep018",
+  "dataset": "v38_r3_aggressive",
+  "dataset_manifest": {
+    "name": "v38_r3_aggressive",
+    "path": "/home/ll/llm4rec/experiments/data/v38_r3_aggressive.jsonl",
+    "records": 80000,
+    "bytes": 305394286,
+    "sha256": "1b53237ca7e35d4c0019b89966b7eec83e6945b643ddc0fe86ed057d90f7b81c",
+    "requested_components": {
+      "general": 20000,
+      "r0": 8000,
+      "r3_think": 20000,
+      "r3_direct": 22000,
+      "old_rec": 4000,
+      "old_user": 3000,
+      "old_item": 3000
+    },
+    "groups": {
+      "r3": 42000,
+      "general": 20000,
+      "old_item": 3000,
+      "old_user": 3000,
+      "old_rec": 4000,
+      "r0": 8000
+    },
+    "variants": {
+      "profile_goods_direct": 5026,
+      "profile_goods_cot": 4597,
+      "official_general_cot": 10049,
+      "profile_video/video_cot": 6131,
+      "profile_video/video_direct": 6741,
+      "original_competition": 4883,
+      "profile_live_direct": 5061,
+      "user_logic_json_strict": 411,
+      "official_general_direct": 9951,
+      "user_strict_array": 503,
+      "caption_to_sid_direct": 3936,
+      "profile_live_cot": 4541,
+      "profile_video/ad_direct": 5172,
+      "rec_no_think_direct_final": 2005,
+      "profile_video/ad_cot": 4731,
+      "sid_to_caption_cot": 2069,
+      "user_extra_no_think_logic": 204,
+      "item_short_think": 516,
+      "item_no_think_direct_final": 555,
+      "sid_to_caption_direct": 1995,
+      "user_array_json_strict": 514,
+      "user_strict_logic": 409
+    },
+    "routes": {
+      "no_think": 43837,
+      "think": 36163
+    },
+    "target_leakage": 0,
+    "seed": 202607155
+  },
+  "learning_rate": "7.0e-7",
+  "epochs": 1.0,
+  "stages": null,
+  "note": "Highest R3 share, trained on real temporal holdouts from official user profiles with target leakage blocked.",
+  "cot_policy": "Preserve meaningful CoT for /think and pure final outputs for /no_think.",
+  "checkpoint_policy": "save_strategy=no; only the final model is retained.",
+  "script": "/home/ll/llm4rec/experiments/run_v34_v43.py",
+  "script_sha256": "fbf01773c61579cf6159f64442fc0c8902714c84ed23b488bc9a6236a154f402",
+  "configs": [
+    "/home/ll/llm4rec/experiments/configs/v38_v29_r3_aggressive_lr7e7_ep10.yaml"
+  ],
+  "reproduce": "/home/ll/llm4rec/demo/LLaMA-Factory/.venv/bin/python /home/ll/llm4rec/experiments/run_v34_v43.py --single v38_v29_r3_aggressive_lr7e7_ep10 --gpu <gpu>"
+}

generation_config.json

@@ -0,0 +1,12 @@
+{
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "temperature": 0.6,
+  "top_k": 20,
+  "top_p": 0.95,
+  "transformers_version": "5.6.0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0304112cb98f02c71547e168b4f355cb192930d83890e8c1d85cf62605c0b894
+size 1602902832

runs/Jul15_03-02-30_ubuntu-System-Product-Name/events.out.tfevents.1784055750.ubuntu-System-Product-Name.1382577.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5509c00f555f2dc5cce1d125c200662963b799533e37944910794506e462d142
+size 15960

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd4d15f596979aecbc11ba12668cb21c9fb8452ce1235cd9d7878cc950170421
+size 16016554

tokenizer_config.json

@@ -0,0 +1,16 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "is_local": true,
+  "local_files_only": false,
+  "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": 1.0,
+    "total_flos": 2.197680639479255e+17,
+    "train_loss": 2.143569690286467,
+    "train_runtime": 3558.7051,
+    "train_samples_per_second": 0.518,
+    "train_steps_per_second": 0.13
+}

trainer_log.jsonl

@@ -0,0 +1,47 @@
+{"current_steps": 10, "total_steps": 461, "loss": 2.309475326538086, "lr": 4.5000000000000003e-07, "epoch": 0.021715526601520086, "percentage": 2.17, "elapsed_time": "0:01:17", "remaining_time": "0:58:09"}
+{"current_steps": 20, "total_steps": 461, "loss": 2.2500890731811523, "lr": 6.997839182620514e-07, "epoch": 0.04343105320304017, "percentage": 4.34, "elapsed_time": "0:02:36", "remaining_time": "0:57:21"}
+{"current_steps": 30, "total_steps": 461, "loss": 2.348200798034668, "lr": 6.980568648741917e-07, "epoch": 0.06514657980456026, "percentage": 6.51, "elapsed_time": "0:03:52", "remaining_time": "0:55:35"}
+{"current_steps": 40, "total_steps": 461, "loss": 1.9902046203613282, "lr": 6.946112854013265e-07, "epoch": 0.08686210640608034, "percentage": 8.68, "elapsed_time": "0:05:10", "remaining_time": "0:54:23"}
+{"current_steps": 50, "total_steps": 461, "loss": 2.356439399719238, "lr": 6.894641923457209e-07, "epoch": 0.10857763300760044, "percentage": 10.85, "elapsed_time": "0:06:25", "remaining_time": "0:52:48"}
+{"current_steps": 60, "total_steps": 461, "loss": 2.275517463684082, "lr": 6.826409994100501e-07, "epoch": 0.13029315960912052, "percentage": 13.02, "elapsed_time": "0:07:41", "remaining_time": "0:51:26"}
+{"current_steps": 70, "total_steps": 461, "loss": 1.863471221923828, "lr": 6.74175396017585e-07, "epoch": 0.15200868621064062, "percentage": 15.18, "elapsed_time": "0:09:01", "remaining_time": "0:50:24"}
+{"current_steps": 80, "total_steps": 461, "loss": 2.199751091003418, "lr": 6.641091809711172e-07, "epoch": 0.1737242128121607, "percentage": 17.35, "elapsed_time": "0:10:21", "remaining_time": "0:49:21"}
+{"current_steps": 90, "total_steps": 461, "loss": 2.2227617263793946, "lr": 6.52492056071934e-07, "epoch": 0.19543973941368079, "percentage": 19.52, "elapsed_time": "0:11:39", "remaining_time": "0:48:04"}
+{"current_steps": 100, "total_steps": 461, "loss": 2.2083740234375, "lr": 6.393813807178434e-07, "epoch": 0.21715526601520088, "percentage": 21.69, "elapsed_time": "0:12:54", "remaining_time": "0:46:34"}
+{"current_steps": 110, "total_steps": 461, "loss": 2.2678974151611326, "lr": 6.248418886919186e-07, "epoch": 0.23887079261672095, "percentage": 23.86, "elapsed_time": "0:14:10", "remaining_time": "0:45:14"}
+{"current_steps": 120, "total_steps": 461, "loss": 2.0732358932495116, "lr": 6.089453685403166e-07, "epoch": 0.26058631921824105, "percentage": 26.03, "elapsed_time": "0:15:29", "remaining_time": "0:44:01"}
+{"current_steps": 130, "total_steps": 461, "loss": 2.0399072647094725, "lr": 5.917703091172979e-07, "epoch": 0.28230184581976114, "percentage": 28.2, "elapsed_time": "0:16:45", "remaining_time": "0:42:39"}
+{"current_steps": 140, "total_steps": 461, "loss": 2.0727848052978515, "lr": 5.73401512047564e-07, "epoch": 0.30401737242128124, "percentage": 30.37, "elapsed_time": "0:18:03", "remaining_time": "0:41:23"}
+{"current_steps": 150, "total_steps": 461, "loss": 2.0733610153198243, "lr": 5.539296730193784e-07, "epoch": 0.3257328990228013, "percentage": 32.54, "elapsed_time": "0:19:20", "remaining_time": "0:40:06"}
+{"current_steps": 160, "total_steps": 461, "loss": 2.1352399826049804, "lr": 5.334509339758256e-07, "epoch": 0.3474484256243214, "percentage": 34.71, "elapsed_time": "0:20:37", "remaining_time": "0:38:48"}
+{"current_steps": 170, "total_steps": 461, "loss": 2.003406524658203, "lr": 5.120664084152621e-07, "epoch": 0.3691639522258415, "percentage": 36.88, "elapsed_time": "0:21:54", "remaining_time": "0:37:30"}
+{"current_steps": 180, "total_steps": 461, "loss": 2.21402530670166, "lr": 4.898816821447787e-07, "epoch": 0.39087947882736157, "percentage": 39.05, "elapsed_time": "0:23:13", "remaining_time": "0:36:15"}
+{"current_steps": 190, "total_steps": 461, "loss": 2.0832319259643555, "lr": 4.6700629195170006e-07, "epoch": 0.41259500542888167, "percentage": 41.21, "elapsed_time": "0:24:32", "remaining_time": "0:35:00"}
+{"current_steps": 200, "total_steps": 461, "loss": 2.305379295349121, "lr": 4.43553184767171e-07, "epoch": 0.43431053203040176, "percentage": 43.38, "elapsed_time": "0:25:50", "remaining_time": "0:33:42"}
+{"current_steps": 210, "total_steps": 461, "loss": 2.1995058059692383, "lr": 4.1963815999220493e-07, "epoch": 0.4560260586319218, "percentage": 45.55, "elapsed_time": "0:27:06", "remaining_time": "0:32:24"}
+{"current_steps": 220, "total_steps": 461, "loss": 2.07507266998291, "lr": 3.953792977397001e-07, "epoch": 0.4777415852334419, "percentage": 47.72, "elapsed_time": "0:28:22", "remaining_time": "0:31:04"}
+{"current_steps": 230, "total_steps": 461, "loss": 1.987565040588379, "lr": 3.708963758154715e-07, "epoch": 0.499457111834962, "percentage": 49.89, "elapsed_time": "0:29:40", "remaining_time": "0:29:48"}
+{"current_steps": 240, "total_steps": 461, "loss": 1.974489974975586, "lr": 3.463102783169471e-07, "epoch": 0.5211726384364821, "percentage": 52.06, "elapsed_time": "0:31:00", "remaining_time": "0:28:33"}
+{"current_steps": 250, "total_steps": 461, "loss": 2.0915807723999023, "lr": 3.217423987695643e-07, "epoch": 0.5428881650380022, "percentage": 54.23, "elapsed_time": "0:32:14", "remaining_time": "0:27:12"}
+{"current_steps": 260, "total_steps": 461, "loss": 2.112474060058594, "lr": 2.9731404074787175e-07, "epoch": 0.5646036916395223, "percentage": 56.4, "elapsed_time": "0:33:31", "remaining_time": "0:25:54"}
+{"current_steps": 270, "total_steps": 461, "loss": 2.2007789611816406, "lr": 2.73145818940763e-07, "epoch": 0.5863192182410424, "percentage": 58.57, "elapsed_time": "0:34:48", "remaining_time": "0:24:37"}
+{"current_steps": 280, "total_steps": 461, "loss": 2.275239181518555, "lr": 2.4935706361807427e-07, "epoch": 0.6080347448425625, "percentage": 60.74, "elapsed_time": "0:36:02", "remaining_time": "0:23:18"}
+{"current_steps": 290, "total_steps": 461, "loss": 2.0178400039672852, "lr": 2.2606523143898274e-07, "epoch": 0.6297502714440825, "percentage": 62.91, "elapsed_time": "0:37:17", "remaining_time": "0:21:59"}
+{"current_steps": 300, "total_steps": 461, "loss": 2.1944948196411134, "lr": 2.033853255113336e-07, "epoch": 0.6514657980456026, "percentage": 65.08, "elapsed_time": "0:38:35", "remaining_time": "0:20:42"}
+{"current_steps": 310, "total_steps": 461, "loss": 2.111407661437988, "lr": 1.8142932756534272e-07, "epoch": 0.6731813246471227, "percentage": 67.25, "elapsed_time": "0:39:52", "remaining_time": "0:19:25"}
+{"current_steps": 320, "total_steps": 461, "loss": 2.0520841598510744, "lr": 1.603056450453112e-07, "epoch": 0.6948968512486428, "percentage": 69.41, "elapsed_time": "0:41:08", "remaining_time": "0:18:07"}
+{"current_steps": 330, "total_steps": 461, "loss": 1.9921758651733399, "lr": 1.401185758493289e-07, "epoch": 0.7166123778501629, "percentage": 71.58, "elapsed_time": "0:42:26", "remaining_time": "0:16:50"}
+{"current_steps": 340, "total_steps": 461, "loss": 2.2591268539428713, "lr": 1.2096779335980598e-07, "epoch": 0.738327904451683, "percentage": 73.75, "elapsed_time": "0:43:44", "remaining_time": "0:15:33"}
+{"current_steps": 350, "total_steps": 461, "loss": 2.3327383041381835, "lr": 1.0294785430748916e-07, "epoch": 0.760043431053203, "percentage": 75.92, "elapsed_time": "0:44:59", "remaining_time": "0:14:16"}
+{"current_steps": 360, "total_steps": 461, "loss": 2.176487350463867, "lr": 8.6147731898877e-08, "epoch": 0.7817589576547231, "percentage": 78.09, "elapsed_time": "0:46:17", "remaining_time": "0:12:59"}
+{"current_steps": 370, "total_steps": 461, "loss": 2.1322710037231447, "lr": 7.065037651220986e-08, "epoch": 0.8034744842562432, "percentage": 80.26, "elapsed_time": "0:47:32", "remaining_time": "0:11:41"}
+{"current_steps": 380, "total_steps": 461, "loss": 2.1231149673461913, "lr": 5.653230613109414e-08, "epoch": 0.8251900108577633, "percentage": 82.43, "elapsed_time": "0:48:50", "remaining_time": "0:10:24"}
+{"current_steps": 390, "total_steps": 461, "loss": 2.1640350341796877, "lr": 4.38632285379887e-08, "epoch": 0.8469055374592834, "percentage": 84.6, "elapsed_time": "0:50:10", "remaining_time": "0:09:08"}
+{"current_steps": 400, "total_steps": 461, "loss": 2.0533117294311523, "lr": 3.27056971329667e-08, "epoch": 0.8686210640608035, "percentage": 86.77, "elapsed_time": "0:51:28", "remaining_time": "0:07:50"}
+{"current_steps": 410, "total_steps": 461, "loss": 2.199868011474609, "lr": 2.3114802077145063e-08, "epoch": 0.8903365906623235, "percentage": 88.94, "elapsed_time": "0:52:44", "remaining_time": "0:06:33"}
+{"current_steps": 420, "total_steps": 461, "loss": 2.2271245956420898, "lr": 1.5137898285755707e-08, "epoch": 0.9120521172638436, "percentage": 91.11, "elapsed_time": "0:54:03", "remaining_time": "0:05:16"}
+{"current_steps": 430, "total_steps": 461, "loss": 2.0086801528930662, "lr": 8.814371613888839e-09, "epoch": 0.9337676438653637, "percentage": 93.28, "elapsed_time": "0:55:24", "remaining_time": "0:03:59"}
+{"current_steps": 440, "total_steps": 461, "loss": 1.9937088012695312, "lr": 4.175444389363636e-09, "epoch": 0.9554831704668838, "percentage": 95.44, "elapsed_time": "0:56:44", "remaining_time": "0:02:42"}
+{"current_steps": 450, "total_steps": 461, "loss": 2.1526458740234373, "lr": 1.2440212529050531e-09, "epoch": 0.9771986970684039, "percentage": 97.61, "elapsed_time": "0:57:59", "remaining_time": "0:01:25"}
+{"current_steps": 460, "total_steps": 461, "loss": 2.2378005981445312, "lr": 3.4576066788472026e-11, "epoch": 0.998914223669924, "percentage": 99.78, "elapsed_time": "0:59:14", "remaining_time": "0:00:07"}
+{"current_steps": 461, "total_steps": 461, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "0:59:18", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,365 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 461,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.021715526601520086,
+      "grad_norm": 5.0625,
+      "learning_rate": 4.5000000000000003e-07,
+      "loss": 2.309475326538086,
+      "step": 10
+    },
+    {
+      "epoch": 0.04343105320304017,
+      "grad_norm": 9.6875,
+      "learning_rate": 6.997839182620514e-07,
+      "loss": 2.2500890731811523,
+      "step": 20
+    },
+    {
+      "epoch": 0.06514657980456026,
+      "grad_norm": 7.90625,
+      "learning_rate": 6.980568648741917e-07,
+      "loss": 2.348200798034668,
+      "step": 30
+    },
+    {
+      "epoch": 0.08686210640608034,
+      "grad_norm": 5.34375,
+      "learning_rate": 6.946112854013265e-07,
+      "loss": 1.9902046203613282,
+      "step": 40
+    },
+    {
+      "epoch": 0.10857763300760044,
+      "grad_norm": 14.75,
+      "learning_rate": 6.894641923457209e-07,
+      "loss": 2.356439399719238,
+      "step": 50
+    },
+    {
+      "epoch": 0.13029315960912052,
+      "grad_norm": 7.25,
+      "learning_rate": 6.826409994100501e-07,
+      "loss": 2.275517463684082,
+      "step": 60
+    },
+    {
+      "epoch": 0.15200868621064062,
+      "grad_norm": 7.9375,
+      "learning_rate": 6.74175396017585e-07,
+      "loss": 1.863471221923828,
+      "step": 70
+    },
+    {
+      "epoch": 0.1737242128121607,
+      "grad_norm": 13.125,
+      "learning_rate": 6.641091809711172e-07,
+      "loss": 2.199751091003418,
+      "step": 80
+    },
+    {
+      "epoch": 0.19543973941368079,
+      "grad_norm": 13.75,
+      "learning_rate": 6.52492056071934e-07,
+      "loss": 2.2227617263793946,
+      "step": 90
+    },
+    {
+      "epoch": 0.21715526601520088,
+      "grad_norm": 7.875,
+      "learning_rate": 6.393813807178434e-07,
+      "loss": 2.2083740234375,
+      "step": 100
+    },
+    {
+      "epoch": 0.23887079261672095,
+      "grad_norm": 16.625,
+      "learning_rate": 6.248418886919186e-07,
+      "loss": 2.2678974151611326,
+      "step": 110
+    },
+    {
+      "epoch": 0.26058631921824105,
+      "grad_norm": 11.6875,
+      "learning_rate": 6.089453685403166e-07,
+      "loss": 2.0732358932495116,
+      "step": 120
+    },
+    {
+      "epoch": 0.28230184581976114,
+      "grad_norm": 12.9375,
+      "learning_rate": 5.917703091172979e-07,
+      "loss": 2.0399072647094725,
+      "step": 130
+    },
+    {
+      "epoch": 0.30401737242128124,
+      "grad_norm": 9.3125,
+      "learning_rate": 5.73401512047564e-07,
+      "loss": 2.0727848052978515,
+      "step": 140
+    },
+    {
+      "epoch": 0.3257328990228013,
+      "grad_norm": 24.25,
+      "learning_rate": 5.539296730193784e-07,
+      "loss": 2.0733610153198243,
+      "step": 150
+    },
+    {
+      "epoch": 0.3474484256243214,
+      "grad_norm": 5.0625,
+      "learning_rate": 5.334509339758256e-07,
+      "loss": 2.1352399826049804,
+      "step": 160
+    },
+    {
+      "epoch": 0.3691639522258415,
+      "grad_norm": 7.5,
+      "learning_rate": 5.120664084152621e-07,
+      "loss": 2.003406524658203,
+      "step": 170
+    },
+    {
+      "epoch": 0.39087947882736157,
+      "grad_norm": 5.875,
+      "learning_rate": 4.898816821447787e-07,
+      "loss": 2.21402530670166,
+      "step": 180
+    },
+    {
+      "epoch": 0.41259500542888167,
+      "grad_norm": 12.1875,
+      "learning_rate": 4.6700629195170006e-07,
+      "loss": 2.0832319259643555,
+      "step": 190
+    },
+    {
+      "epoch": 0.43431053203040176,
+      "grad_norm": 11.4375,
+      "learning_rate": 4.43553184767171e-07,
+      "loss": 2.305379295349121,
+      "step": 200
+    },
+    {
+      "epoch": 0.4560260586319218,
+      "grad_norm": 7.71875,
+      "learning_rate": 4.1963815999220493e-07,
+      "loss": 2.1995058059692383,
+      "step": 210
+    },
+    {
+      "epoch": 0.4777415852334419,
+      "grad_norm": 9.8125,
+      "learning_rate": 3.953792977397001e-07,
+      "loss": 2.07507266998291,
+      "step": 220
+    },
+    {
+      "epoch": 0.499457111834962,
+      "grad_norm": 8.625,
+      "learning_rate": 3.708963758154715e-07,
+      "loss": 1.987565040588379,
+      "step": 230
+    },
+    {
+      "epoch": 0.5211726384364821,
+      "grad_norm": 17.125,
+      "learning_rate": 3.463102783169471e-07,
+      "loss": 1.974489974975586,
+      "step": 240
+    },
+    {
+      "epoch": 0.5428881650380022,
+      "grad_norm": 5.90625,
+      "learning_rate": 3.217423987695643e-07,
+      "loss": 2.0915807723999023,
+      "step": 250
+    },
+    {
+      "epoch": 0.5646036916395223,
+      "grad_norm": 7.78125,
+      "learning_rate": 2.9731404074787175e-07,
+      "loss": 2.112474060058594,
+      "step": 260
+    },
+    {
+      "epoch": 0.5863192182410424,
+      "grad_norm": 21.625,
+      "learning_rate": 2.73145818940763e-07,
+      "loss": 2.2007789611816406,
+      "step": 270
+    },
+    {
+      "epoch": 0.6080347448425625,
+      "grad_norm": 13.8125,
+      "learning_rate": 2.4935706361807427e-07,
+      "loss": 2.275239181518555,
+      "step": 280
+    },
+    {
+      "epoch": 0.6297502714440825,
+      "grad_norm": 8.6875,
+      "learning_rate": 2.2606523143898274e-07,
+      "loss": 2.0178400039672852,
+      "step": 290
+    },
+    {
+      "epoch": 0.6514657980456026,
+      "grad_norm": 6.21875,
+      "learning_rate": 2.033853255113336e-07,
+      "loss": 2.1944948196411134,
+      "step": 300
+    },
+    {
+      "epoch": 0.6731813246471227,
+      "grad_norm": 18.75,
+      "learning_rate": 1.8142932756534272e-07,
+      "loss": 2.111407661437988,
+      "step": 310
+    },
+    {
+      "epoch": 0.6948968512486428,
+      "grad_norm": 14.875,
+      "learning_rate": 1.603056450453112e-07,
+      "loss": 2.0520841598510744,
+      "step": 320
+    },
+    {
+      "epoch": 0.7166123778501629,
+      "grad_norm": 4.0,
+      "learning_rate": 1.401185758493289e-07,
+      "loss": 1.9921758651733399,
+      "step": 330
+    },
+    {
+      "epoch": 0.738327904451683,
+      "grad_norm": 10.125,
+      "learning_rate": 1.2096779335980598e-07,
+      "loss": 2.2591268539428713,
+      "step": 340
+    },
+    {
+      "epoch": 0.760043431053203,
+      "grad_norm": 18.375,
+      "learning_rate": 1.0294785430748916e-07,
+      "loss": 2.3327383041381835,
+      "step": 350
+    },
+    {
+      "epoch": 0.7817589576547231,
+      "grad_norm": 6.65625,
+      "learning_rate": 8.6147731898877e-08,
+      "loss": 2.176487350463867,
+      "step": 360
+    },
+    {
+      "epoch": 0.8034744842562432,
+      "grad_norm": 7.03125,
+      "learning_rate": 7.065037651220986e-08,
+      "loss": 2.1322710037231447,
+      "step": 370
+    },
+    {
+      "epoch": 0.8251900108577633,
+      "grad_norm": 10.0625,
+      "learning_rate": 5.653230613109414e-08,
+      "loss": 2.1231149673461913,
+      "step": 380
+    },
+    {
+      "epoch": 0.8469055374592834,
+      "grad_norm": 4.96875,
+      "learning_rate": 4.38632285379887e-08,
+      "loss": 2.1640350341796877,
+      "step": 390
+    },
+    {
+      "epoch": 0.8686210640608035,
+      "grad_norm": 7.3125,
+      "learning_rate": 3.27056971329667e-08,
+      "loss": 2.0533117294311523,
+      "step": 400
+    },
+    {
+      "epoch": 0.8903365906623235,
+      "grad_norm": 8.5625,
+      "learning_rate": 2.3114802077145063e-08,
+      "loss": 2.199868011474609,
+      "step": 410
+    },
+    {
+      "epoch": 0.9120521172638436,
+      "grad_norm": 7.5625,
+      "learning_rate": 1.5137898285755707e-08,
+      "loss": 2.2271245956420898,
+      "step": 420
+    },
+    {
+      "epoch": 0.9337676438653637,
+      "grad_norm": 5.71875,
+      "learning_rate": 8.814371613888839e-09,
+      "loss": 2.0086801528930662,
+      "step": 430
+    },
+    {
+      "epoch": 0.9554831704668838,
+      "grad_norm": 5.21875,
+      "learning_rate": 4.175444389363636e-09,
+      "loss": 1.9937088012695312,
+      "step": 440
+    },
+    {
+      "epoch": 0.9771986970684039,
+      "grad_norm": 12.0625,
+      "learning_rate": 1.2440212529050531e-09,
+      "loss": 2.1526458740234373,
+      "step": 450
+    },
+    {
+      "epoch": 0.998914223669924,
+      "grad_norm": 8.75,
+      "learning_rate": 3.4576066788472026e-11,
+      "loss": 2.2378005981445312,
+      "step": 460
+    },
+    {
+      "epoch": 1.0,
+      "step": 461,
+      "total_flos": 2.197680639479255e+17,
+      "train_loss": 2.143569690286467,
+      "train_runtime": 3558.7051,
+      "train_samples_per_second": 0.518,
+      "train_steps_per_second": 0.13
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 461,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": false,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.197680639479255e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f49e2d2efc6cb169731684579c9ba9fe378b56bbc943f20a164e4e8a8739062
+size 6033