初始化项目，由ModelHub XC社区提供模型

Model: lldois/v28_v26_no_template_product_world_lr12e6_ep022 Source: Original Platform
2026-07-23 13:24:13 +08:00
commit 439e83e703
17 changed files with 2773 additions and 0 deletions
--- a/.gitattributes
+++ b/.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
--- a/README.md
+++ b/README.md
@@ -0,0 +1,58 @@
+---
+library_name: transformers
+license: other
+base_model: lldois/v26_v21_product_rec_rebalance_lr22e6_ep032
+tags:
+- llama-factory
+- full
+- generated_from_trainer
+model-index:
+- name: v28_v26_no_template_product_world_lr12e6_ep022
+  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. -->
+
+# v28_v26_no_template_product_world_lr12e6_ep022
+
+This model is a fine-tuned version of [lldois/v26_v21_product_rec_rebalance_lr22e6_ep032](https://huggingface.co/lldois/v26_v21_product_rec_rebalance_lr22e6_ep032) on the exp_v26_no_template_product_world 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: 1.2e-06
+- train_batch_size: 1
+- eval_batch_size: 8
+- seed: 202607281
+- 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: 0.02
+- num_epochs: 0.22
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 5.6.0
+- Pytorch 2.7.1+cu126
+- Datasets 4.0.0
+- Tokenizers 0.22.2
--- a/all_results.json
+++ b/all_results.json
@@ -0,0 +1,8 @@
+{
+    "epoch": 0.22123893805309736,
+    "total_flos": 2.3544070748841984e+16,
+    "train_loss": 1.5697357273101806,
+    "train_runtime": 430.9822,
+    "train_samples_per_second": 0.461,
+    "train_steps_per_second": 0.116
+}
--- a/chat_template.jinja
+++ b/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 %}
--- a/config.json
+++ b/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
+}
--- a/experiment_recipe.json
+++ b/experiment_recipe.json
@@ -0,0 +1,65 @@
+{
+  "created_at": "2026-07-12 04:25:55",
+  "run": {
+    "name": "v28_v26_no_template_product_world_lr12e6_ep022",
+    "dataset": "v26_no_template_product_world",
+    "model_path": "/home/ll/llm4rec/experiments/outputs/v26_v21_product_rec_rebalance_lr22e6_ep032",
+    "lr": "1.2e-6",
+    "epochs": 0.22,
+    "warmup": 0.02,
+    "scheduler": "cosine",
+    "seed": 202607281,
+    "note": "v26 continuation. Remove repeated synthetic short-think templates, keep low-update CoT/no-think route supervision, add mild product/video rec replay plus item and user guards. Goal: keep v26 speed/user1/rec1 while recovering rec2/world.",
+    "config": "/home/ll/llm4rec/experiments/configs/v28_v26_no_template_product_world_lr12e6_ep022.yaml"
+  },
+  "dataset_manifest": {
+    "name": "v26_no_template_product_world",
+    "path": "/home/ll/llm4rec/experiments/data/v26_no_template_product_world.jsonl",
+    "records": 21886,
+    "groups": {
+      "item": 8397,
+      "rec": 10689,
+      "user": 2800
+    },
+    "variants": {
+      "item_short_think": 2792,
+      "item_compact_cot": 2800,
+      "rec_cot_pattern_clean": 4000,
+      "user_extra_no_think_logic": 483,
+      "rec_no_think_direct_final": 6689,
+      "item_no_think_direct_final": 2805,
+      "user_strict_array": 1269,
+      "user_strict_logic": 1048
+    },
+    "sha256": "e3ca534de9f823184f2688db713a110fcaf10f98e17a534183e096a6bca88d18",
+    "seed": 202607111
+  },
+  "dataset_recipe": "v26 continuation: drop repeated synthetic short-think templates, keep cleaned original CoT and route-specific no-think final answers, add mild product/video repair, item replay, and user JSON guard.",
+  "cot_policy": "Preserve /think reasoning supervision and do not use v7_final_only as a CoT training base. For /no_think prompts, train pure final answers without generated <think> tags. This is route-specific behavior, not global CoT removal.",
+  "raw_counts": {
+    "rec": 19204,
+    "item": 10384,
+    "user": 2892
+  },
+  "eval_observations": {
+    "v07": "best local score so far: total=0.8978, eval_time≈47.3min; fast final outputs likely help.",
+    "v15": "best CoT-preserving score so far: total=0.8778, eval_time≈70.1min; logs show repeated tokens, JSON shell errors, prompt leakage, and verbose /no_think outputs.",
+    "v19": "best CoT-native continuation so far: total=0.8855, eval_time≈48.1min; user1 and rec4 improved but world dropped.",
+    "v20": "v7 final-only continuation with CoT restore failed as a CoT route: total=0.8527, item fell to 0.1840; do not use v7 as future CoT base.",
+    "v22": "scratch official-base 3 epoch clean CoT underperformed: total=0.8217; item/world preserved but user and rec2 are weak.",
+    "v23": "scratch official-base 5 epoch low-LR guard failed badly: total=0.6990; item/user collapse suggests long scratch SFT is not viable with current data mix.",
+    "v24": "v15 light repair is best among v22-v24 but still only total=0.8364; user2 improves but rec/world do not recover.",
+    "v25": "v19 product-heavy repair did not beat v19: total=0.8793. Logs show heavy repeated product tokens and repeated short-think phrases; avoid this over-sampling pattern.",
+    "v26": "best latest batch and fastest eval: total=0.8804, eval_time≈45.7min, best user1/rec1. It is useful as a base, but rec2/world dropped.",
+    "v27": "v12 product/ad repair kept user2/world relatively better but was slow and template-heavy: total=0.8563, eval_time≈70.6min. Do not continue this exact direction.",
+    "v16": "CoT pattern rewrite failed: total=0.7912; logs show malformed user JSON and fragmented recommendation reasoning.",
+    "v18": "low-LR mixed replay from v12 failed: total=0.8340; item/world dropped and rec outputs mixed text/itemic/think tags."
+  },
+  "script": "/home/ll/llm4rec/experiments/run_experiments.py",
+  "script_sha256": "7375c7a06ae5221c98bc2135819e0999d80e2b2098543ac9a5c56c352bd693d3",
+  "deadline": "none",
+  "reproduce": {
+    "prepare_command": "EXPERIMENT_PREPARE_ONLY=1 python3 experiments/run_experiments.py",
+    "train_command": "CUDA_VISIBLE_DEVICES=<gpu> bash -lc 'source /home/ll/llm4rec/demo/LLaMA-Factory/.venv/bin/activate && llamafactory-cli train /home/ll/llm4rec/experiments/configs/v28_v26_no_template_product_world_lr12e6_ep022.yaml'"
+  }
+}
--- a/generation_config.json
+++ b/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"
+}
--- a/model.safetensors
+++ b/model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05cb7d56f868f19bf3298e29c6b903cc9698d8962afb1be3c04423ccb2a28c25
+size 1602902832
--- a/runs/Jul12_04-26-29_ubuntu-System-Product-Name/events.out.tfevents.1783801589.ubuntu-System-Product-Name.776848.0
+++ b/runs/Jul12_04-26-29_ubuntu-System-Product-Name/events.out.tfevents.1783801589.ubuntu-System-Product-Name.776848.0
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d971c752da4a5fbe1b2123ef2a6a95c3e2f5beacc67e94e89240f160b8e628c
+size 8396
--- a/tokenizer.json
+++ b/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd4d15f596979aecbc11ba12668cb21c9fb8452ce1235cd9d7878cc950170421
+size 16016554
--- a/tokenizer_config.json
+++ b/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
+}
--- a/train.log
+++ b/train.log
--- a/train_results.json
+++ b/train_results.json
@@ -0,0 +1,8 @@
+{
+    "epoch": 0.22123893805309736,
+    "total_flos": 2.3544070748841984e+16,
+    "train_loss": 1.5697357273101806,
+    "train_runtime": 430.9822,
+    "train_samples_per_second": 0.461,
+    "train_steps_per_second": 0.116
+}
--- a/trainer_log.jsonl
+++ b/trainer_log.jsonl
@@ -0,0 +1,11 @@
+{"current_steps": 5, "total_steps": 50, "loss": 1.6575153350830079, "lr": 1.1889354941946392e-06, "epoch": 0.022123893805309734, "percentage": 10.0, "elapsed_time": "0:00:45", "remaining_time": "0:06:53"}
+{"current_steps": 10, "total_steps": 50, "loss": 1.5272085189819335, "lr": 1.1227912224740335e-06, "epoch": 0.04424778761061947, "percentage": 20.0, "elapsed_time": "0:01:33", "remaining_time": "0:06:14"}
+{"current_steps": 15, "total_steps": 50, "loss": 1.5009249687194823, "lr": 1.00338053415679e-06, "epoch": 0.06637168141592921, "percentage": 30.0, "elapsed_time": "0:02:20", "remaining_time": "0:05:28"}
+{"current_steps": 20, "total_steps": 50, "loss": 1.4947051048278808, "lr": 8.428700058734362e-07, "epoch": 0.08849557522123894, "percentage": 40.0, "elapsed_time": "0:03:07", "remaining_time": "0:04:40"}
+{"current_steps": 25, "total_steps": 50, "loss": 1.6262493133544922, "lr": 6.57613815544609e-07, "epoch": 0.11061946902654868, "percentage": 50.0, "elapsed_time": "0:03:49", "remaining_time": "0:03:49"}
+{"current_steps": 30, "total_steps": 50, "loss": 1.6392818450927735, "lr": 4.6648743962621137e-07, "epoch": 0.13274336283185842, "percentage": 60.0, "elapsed_time": "0:04:28", "remaining_time": "0:02:58"}
+{"current_steps": 35, "total_steps": 50, "loss": 1.5571434020996093, "lr": 2.8896445901368497e-07, "epoch": 0.15486725663716813, "percentage": 70.0, "elapsed_time": "0:05:09", "remaining_time": "0:02:12"}
+{"current_steps": 40, "total_steps": 50, "loss": 1.5264162063598632, "lr": 1.4313242497851934e-07, "epoch": 0.17699115044247787, "percentage": 80.0, "elapsed_time": "0:05:51", "remaining_time": "0:01:27"}
+{"current_steps": 45, "total_steps": 50, "loss": 1.5222594261169433, "lr": 4.3849945592387015e-08, "epoch": 0.19911504424778761, "percentage": 90.0, "elapsed_time": "0:06:29", "remaining_time": "0:00:43"}
+{"current_steps": 50, "total_steps": 50, "loss": 1.6456531524658202, "lr": 1.2327643497981987e-09, "epoch": 0.22123893805309736, "percentage": 100.0, "elapsed_time": "0:07:10", "remaining_time": "0:00:00"}
+{"current_steps": 50, "total_steps": 50, "epoch": 0.22123893805309736, "percentage": 100.0, "elapsed_time": "0:07:10", "remaining_time": "0:00:00"}
--- a/trainer_state.json
+++ b/trainer_state.json
@@ -0,0 +1,113 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.22123893805309736,
+  "eval_steps": 500,
+  "global_step": 50,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.022123893805309734,
+      "grad_norm": 15.9375,
+      "learning_rate": 1.1889354941946392e-06,
+      "loss": 1.6575153350830079,
+      "step": 5
+    },
+    {
+      "epoch": 0.04424778761061947,
+      "grad_norm": 11.6875,
+      "learning_rate": 1.1227912224740335e-06,
+      "loss": 1.5272085189819335,
+      "step": 10
+    },
+    {
+      "epoch": 0.06637168141592921,
+      "grad_norm": 9.5625,
+      "learning_rate": 1.00338053415679e-06,
+      "loss": 1.5009249687194823,
+      "step": 15
+    },
+    {
+      "epoch": 0.08849557522123894,
+      "grad_norm": 10.6875,
+      "learning_rate": 8.428700058734362e-07,
+      "loss": 1.4947051048278808,
+      "step": 20
+    },
+    {
+      "epoch": 0.11061946902654868,
+      "grad_norm": 12.1875,
+      "learning_rate": 6.57613815544609e-07,
+      "loss": 1.6262493133544922,
+      "step": 25
+    },
+    {
+      "epoch": 0.13274336283185842,
+      "grad_norm": 12.75,
+      "learning_rate": 4.6648743962621137e-07,
+      "loss": 1.6392818450927735,
+      "step": 30
+    },
+    {
+      "epoch": 0.15486725663716813,
+      "grad_norm": 21.875,
+      "learning_rate": 2.8896445901368497e-07,
+      "loss": 1.5571434020996093,
+      "step": 35
+    },
+    {
+      "epoch": 0.17699115044247787,
+      "grad_norm": 11.75,
+      "learning_rate": 1.4313242497851934e-07,
+      "loss": 1.5264162063598632,
+      "step": 40
+    },
+    {
+      "epoch": 0.19911504424778761,
+      "grad_norm": 23.5,
+      "learning_rate": 4.3849945592387015e-08,
+      "loss": 1.5222594261169433,
+      "step": 45
+    },
+    {
+      "epoch": 0.22123893805309736,
+      "grad_norm": 10.625,
+      "learning_rate": 1.2327643497981987e-09,
+      "loss": 1.6456531524658202,
+      "step": 50
+    },
+    {
+      "epoch": 0.22123893805309736,
+      "step": 50,
+      "total_flos": 2.3544070748841984e+16,
+      "train_loss": 1.5697357273101806,
+      "train_runtime": 430.9822,
+      "train_samples_per_second": 0.461,
+      "train_steps_per_second": 0.116
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 50,
+  "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": 2.3544070748841984e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}
--- a/training_args.bin
+++ b/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:516b40e85e43f9bd475ffb07ac9717fac1c30c11ebd2c1aede0b2fa779b8fe83
+size 6097
--- a/training_loss.png
+++ b/training_loss.png