Upload folder using huggingface_hub

.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 +1,209 @@
+---
+base_model: Qwen/Qwen2.5-7B-Instruct
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen2.5-7B-Instruct
+- lora
+- sft
+- transformers
+- trl
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.18.1

adapter_config.json

@@ -0,0 +1,46 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-7B-Instruct",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "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": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "gate_proj",
+    "down_proj",
+    "k_proj",
+    "q_proj",
+    "up_proj",
+    "v_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:905509c9527dab0b81a8730bf9b2aaef71432a69998dde791c66b29dac2b0f8d
+size 80792880

chat_template.jinja

@@ -0,0 +1,54 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
+    {%- endif %}
+    {{- "\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>" }}
+    {%- 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' }}
+    {%- else %}
+        {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role }}
+        {%- if message.content %}
+            {{- '\n' + message.content }}
+        {%- endif %}
+        {%- for tool_call in message.tool_calls %}
+            {%- if tool_call.function is defined %}
+                {%- set tool_call = tool_call.function %}
+            {%- endif %}
+            {{- '\n<tool_call>\n{"name": "' }}
+            {{- tool_call.name }}
+            {{- '", "arguments": ' }}
+            {{- tool_call.arguments | tojson }}
+            {{- '}\n</tool_call>' }}
+        {%- endfor %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.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' }}
+{%- endif %}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25c87b4e1ec0d66ea5f77af5ddd775cf9d13a677c494db051605458541bd1157
+size 161816251

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2378a2c3197ef96f2307fb74417b2247392b2cf52a4603f984e139ce954330a4
+size 14645

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8803f022c60b184179e5954b1ae91f861d29fe5bf97935a67825796df543f419
+size 1465

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fd169731d2cbde95e10bf356d66d5997fd885dd8dbb6fb4684da3f23b2585d8
+size 11421892

tokenizer_config.json

@@ -0,0 +1,29 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_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|>"
+  ],
+  "is_local": false,
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_state.json

@@ -0,0 +1,374 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 345,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 1.6703570872545241,
+      "epoch": 0.087527352297593,
+      "grad_norm": 0.65625,
+      "learning_rate": 0.00019478260869565218,
+      "loss": 2.0278825759887695,
+      "mean_token_accuracy": 0.612476097419858,
+      "num_tokens": 18728.0,
+      "step": 10
+    },
+    {
+      "entropy": 1.2492346689105034,
+      "epoch": 0.175054704595186,
+      "grad_norm": 0.75,
+      "learning_rate": 0.0001889855072463768,
+      "loss": 1.2333297729492188,
+      "mean_token_accuracy": 0.7266808465123177,
+      "num_tokens": 37328.0,
+      "step": 20
+    },
+    {
+      "entropy": 1.1282426938414574,
+      "epoch": 0.26258205689277897,
+      "grad_norm": 0.6796875,
+      "learning_rate": 0.00018318840579710147,
+      "loss": 1.1297640800476074,
+      "mean_token_accuracy": 0.7533167637884617,
+      "num_tokens": 56036.0,
+      "step": 30
+    },
+    {
+      "entropy": 0.9922276919707655,
+      "epoch": 0.350109409190372,
+      "grad_norm": 0.640625,
+      "learning_rate": 0.0001773913043478261,
+      "loss": 1.033622646331787,
+      "mean_token_accuracy": 0.7703150801360608,
+      "num_tokens": 75072.0,
+      "step": 40
+    },
+    {
+      "entropy": 1.0213249990716577,
+      "epoch": 0.437636761487965,
+      "grad_norm": 0.53125,
+      "learning_rate": 0.00017159420289855073,
+      "loss": 1.042306900024414,
+      "mean_token_accuracy": 0.7690192483365536,
+      "num_tokens": 93505.0,
+      "step": 50
+    },
+    {
+      "entropy": 0.9650674186646938,
+      "epoch": 0.5251641137855579,
+      "grad_norm": 0.56640625,
+      "learning_rate": 0.00016579710144927536,
+      "loss": 1.0220633506774903,
+      "mean_token_accuracy": 0.7742902040481567,
+      "num_tokens": 112039.0,
+      "step": 60
+    },
+    {
+      "entropy": 1.0567748602479696,
+      "epoch": 0.612691466083151,
+      "grad_norm": 0.59765625,
+      "learning_rate": 0.00016,
+      "loss": 1.0543122291564941,
+      "mean_token_accuracy": 0.7587149851024151,
+      "num_tokens": 131322.0,
+      "step": 70
+    },
+    {
+      "entropy": 0.9168455514125526,
+      "epoch": 0.700218818380744,
+      "grad_norm": 0.6328125,
+      "learning_rate": 0.00015420289855072464,
+      "loss": 0.95663423538208,
+      "mean_token_accuracy": 0.78614791482687,
+      "num_tokens": 149646.0,
+      "step": 80
+    },
+    {
+      "entropy": 0.9514417068101466,
+      "epoch": 0.787746170678337,
+      "grad_norm": 0.68359375,
+      "learning_rate": 0.00014840579710144927,
+      "loss": 0.9753911972045899,
+      "mean_token_accuracy": 0.781362334638834,
+      "num_tokens": 168182.0,
+      "step": 90
+    },
+    {
+      "entropy": 0.9971431667916477,
+      "epoch": 0.87527352297593,
+      "grad_norm": 0.6015625,
+      "learning_rate": 0.00014260869565217393,
+      "loss": 1.0196686744689942,
+      "mean_token_accuracy": 0.7682865738868714,
+      "num_tokens": 187221.0,
+      "step": 100
+    },
+    {
+      "entropy": 0.9537320947274566,
+      "epoch": 0.962800875273523,
+      "grad_norm": 0.515625,
+      "learning_rate": 0.00013681159420289856,
+      "loss": 0.9510069847106933,
+      "mean_token_accuracy": 0.782170583307743,
+      "num_tokens": 205633.0,
+      "step": 110
+    },
+    {
+      "entropy": 0.907145096643551,
+      "epoch": 1.0437636761487965,
+      "grad_norm": 0.484375,
+      "learning_rate": 0.00013101449275362319,
+      "loss": 0.9373687744140625,
+      "mean_token_accuracy": 0.7886275141625791,
+      "num_tokens": 222954.0,
+      "step": 120
+    },
+    {
+      "entropy": 0.8457014967687428,
+      "epoch": 1.1312910284463895,
+      "grad_norm": 0.6328125,
+      "learning_rate": 0.00012521739130434784,
+      "loss": 0.8454959869384766,
+      "mean_token_accuracy": 0.7963103860616684,
+      "num_tokens": 241678.0,
+      "step": 130
+    },
+    {
+      "entropy": 0.8462455681525171,
+      "epoch": 1.2188183807439825,
+      "grad_norm": 0.703125,
+      "learning_rate": 0.00011942028985507247,
+      "loss": 0.8574352264404297,
+      "mean_token_accuracy": 0.8001780763268471,
+      "num_tokens": 260144.0,
+      "step": 140
+    },
+    {
+      "entropy": 0.8343841714784503,
+      "epoch": 1.3063457330415755,
+      "grad_norm": 0.703125,
+      "learning_rate": 0.00011362318840579711,
+      "loss": 0.8432804107666015,
+      "mean_token_accuracy": 0.7991413235664367,
+      "num_tokens": 279020.0,
+      "step": 150
+    },
+    {
+      "entropy": 0.7861125588417053,
+      "epoch": 1.3938730853391685,
+      "grad_norm": 0.7578125,
+      "learning_rate": 0.00010782608695652174,
+      "loss": 0.8140290260314942,
+      "mean_token_accuracy": 0.8104772590100765,
+      "num_tokens": 297696.0,
+      "step": 160
+    },
+    {
+      "entropy": 0.8265796534717083,
+      "epoch": 1.4814004376367615,
+      "grad_norm": 0.7421875,
+      "learning_rate": 0.00010202898550724637,
+      "loss": 0.8296893119812012,
+      "mean_token_accuracy": 0.8040477402508259,
+      "num_tokens": 315741.0,
+      "step": 170
+    },
+    {
+      "entropy": 0.7689724578522146,
+      "epoch": 1.5689277899343543,
+      "grad_norm": 0.80859375,
+      "learning_rate": 9.623188405797103e-05,
+      "loss": 0.7881460189819336,
+      "mean_token_accuracy": 0.808928444236517,
+      "num_tokens": 334515.0,
+      "step": 180
+    },
+    {
+      "entropy": 0.7925019094720482,
+      "epoch": 1.6564551422319473,
+      "grad_norm": 0.7890625,
+      "learning_rate": 9.043478260869566e-05,
+      "loss": 0.8049691200256348,
+      "mean_token_accuracy": 0.8096396245062352,
+      "num_tokens": 352933.0,
+      "step": 190
+    },
+    {
+      "entropy": 0.7968289134092629,
+      "epoch": 1.7439824945295404,
+      "grad_norm": 0.859375,
+      "learning_rate": 8.463768115942029e-05,
+      "loss": 0.8357898712158203,
+      "mean_token_accuracy": 0.8038821592926979,
+      "num_tokens": 371642.0,
+      "step": 200
+    },
+    {
+      "entropy": 0.8211181129328906,
+      "epoch": 1.8315098468271334,
+      "grad_norm": 0.80078125,
+      "learning_rate": 7.884057971014493e-05,
+      "loss": 0.8084160804748535,
+      "mean_token_accuracy": 0.8103035606443882,
+      "num_tokens": 390297.0,
+      "step": 210
+    },
+    {
+      "entropy": 0.8177960739005357,
+      "epoch": 1.9190371991247264,
+      "grad_norm": 0.73828125,
+      "learning_rate": 7.304347826086957e-05,
+      "loss": 0.8264873504638672,
+      "mean_token_accuracy": 0.8067296646535397,
+      "num_tokens": 409295.0,
+      "step": 220
+    },
+    {
+      "entropy": 0.8154785256530788,
+      "epoch": 2.0,
+      "grad_norm": 1.6171875,
+      "learning_rate": 6.72463768115942e-05,
+      "loss": 0.82596435546875,
+      "mean_token_accuracy": 0.8030677026993519,
+      "num_tokens": 426750.0,
+      "step": 230
+    },
+    {
+      "entropy": 0.6059559936635196,
+      "epoch": 2.087527352297593,
+      "grad_norm": 1.6796875,
+      "learning_rate": 6.144927536231884e-05,
+      "loss": 0.6000402450561524,
+      "mean_token_accuracy": 0.8544376268982887,
+      "num_tokens": 445112.0,
+      "step": 240
+    },
+    {
+      "entropy": 0.6742822146276012,
+      "epoch": 2.175054704595186,
+      "grad_norm": 0.9453125,
+      "learning_rate": 5.565217391304348e-05,
+      "loss": 0.6495694160461426,
+      "mean_token_accuracy": 0.8368013821542263,
+      "num_tokens": 464055.0,
+      "step": 250
+    },
+    {
+      "entropy": 0.6670764476526528,
+      "epoch": 2.262582056892779,
+      "grad_norm": 1.21875,
+      "learning_rate": 4.985507246376812e-05,
+      "loss": 0.6383417129516602,
+      "mean_token_accuracy": 0.8340263485908508,
+      "num_tokens": 483243.0,
+      "step": 260
+    },
+    {
+      "entropy": 0.6482093236874789,
+      "epoch": 2.350109409190372,
+      "grad_norm": 1.0390625,
+      "learning_rate": 4.405797101449275e-05,
+      "loss": 0.6531811237335206,
+      "mean_token_accuracy": 0.8335508003830909,
+      "num_tokens": 501911.0,
+      "step": 270
+    },
+    {
+      "entropy": 0.6858879348263145,
+      "epoch": 2.437636761487965,
+      "grad_norm": 1.0546875,
+      "learning_rate": 3.8260869565217395e-05,
+      "loss": 0.6682425498962402,
+      "mean_token_accuracy": 0.8321790546178818,
+      "num_tokens": 520579.0,
+      "step": 280
+    },
+    {
+      "entropy": 0.6361387457232922,
+      "epoch": 2.525164113785558,
+      "grad_norm": 1.1171875,
+      "learning_rate": 3.246376811594203e-05,
+      "loss": 0.628416633605957,
+      "mean_token_accuracy": 0.8387672163546085,
+      "num_tokens": 539205.0,
+      "step": 290
+    },
+    {
+      "entropy": 0.6545329387299716,
+      "epoch": 2.612691466083151,
+      "grad_norm": 1.015625,
+      "learning_rate": 2.6666666666666667e-05,
+      "loss": 0.6523668766021729,
+      "mean_token_accuracy": 0.8395993508398533,
+      "num_tokens": 557726.0,
+      "step": 300
+    },
+    {
+      "entropy": 0.5724413711111993,
+      "epoch": 2.700218818380744,
+      "grad_norm": 1.09375,
+      "learning_rate": 2.0869565217391303e-05,
+      "loss": 0.5660404682159423,
+      "mean_token_accuracy": 0.860739403963089,
+      "num_tokens": 575763.0,
+      "step": 310
+    },
+    {
+      "entropy": 0.6278647107072175,
+      "epoch": 2.787746170678337,
+      "grad_norm": 1.0859375,
+      "learning_rate": 1.5072463768115944e-05,
+      "loss": 0.6288604736328125,
+      "mean_token_accuracy": 0.8464278854429722,
+      "num_tokens": 594054.0,
+      "step": 320
+    },
+    {
+      "entropy": 0.6267774282023311,
+      "epoch": 2.87527352297593,
+      "grad_norm": 1.03125,
+      "learning_rate": 9.27536231884058e-06,
+      "loss": 0.6052563190460205,
+      "mean_token_accuracy": 0.8475193127989769,
+      "num_tokens": 613053.0,
+      "step": 330
+    },
+    {
+      "entropy": 0.6937473515979946,
+      "epoch": 2.962800875273523,
+      "grad_norm": 1.0625,
+      "learning_rate": 3.4782608695652175e-06,
+      "loss": 0.6603917121887207,
+      "mean_token_accuracy": 0.8315372362732887,
+      "num_tokens": 632039.0,
+      "step": 340
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 345,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "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": 2.7311532200064e+16,
+  "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:acf8d3195dc34bcdb1bf0acfadc9cedc73d801254e6a1b033f85be1d3d33ea4d
+size 5649