Upload fine-tuned Qwen LoRA for semantic bridging

.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 +1,210 @@
+---
+base_model: unsloth/Qwen2.5-7B-Instruct
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:unsloth/Qwen2.5-7B-Instruct
+- lora
+- sft
+- transformers
+- trl
+- unsloth
+---
+
+# 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 +1,50 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": {
+    "base_model_class": "Qwen2ForCausalLM",
+    "parent_library": "transformers.models.qwen2.modeling_qwen2",
+    "unsloth_fixed": true
+  },
+  "base_model_name_or_path": "unsloth/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": [
+    "down_proj",
+    "q_proj",
+    "k_proj",
+    "v_proj",
+    "o_proj",
+    "up_proj",
+    "gate_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:b103037fd6002829cef903f5aedada1774f09ed884ccb80c35320f7e98f5c829
+size 161533192

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
+}

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:fe448597dfe3dcc3b9bdfe36b69ff5ee3e68c1c01b851572f5cf10368148d390
+size 323291451

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:625ded86a61f4bd564579a1aacbbbc47367c15b5b6a32f6b059b143fa14bc08f
+size 14645

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90e22e6c80a3769a7e9b9925714def0741d4c710e0acfb48f70bfb66c77c3ab6
+size 1465

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": "<|vision_pad|>",
+    "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,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 32768,
+  "pad_token": "<|vision_pad|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_state.json

@@ -0,0 +1,859 @@
+{
+  "best_global_step": 800,
+  "best_metric": 0.44239288568496704,
+  "best_model_checkpoint": "./qwen_semantic_bridge_v2_full/checkpoint-800",
+  "epoch": 5.975609756097561,
+  "eval_steps": 25,
+  "global_step": 800,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.075046904315197,
+      "grad_norm": 1.53766667842865,
+      "learning_rate": 2.6865671641791044e-06,
+      "loss": 2.4791,
+      "step": 10
+    },
+    {
+      "epoch": 0.150093808630394,
+      "grad_norm": 1.524065613746643,
+      "learning_rate": 5.671641791044776e-06,
+      "loss": 2.4315,
+      "step": 20
+    },
+    {
+      "epoch": 0.18761726078799248,
+      "eval_loss": 2.34097957611084,
+      "eval_runtime": 5.5956,
+      "eval_samples_per_second": 20.194,
+      "eval_steps_per_second": 5.183,
+      "step": 25
+    },
+    {
+      "epoch": 0.225140712945591,
+      "grad_norm": 1.4025851488113403,
+      "learning_rate": 8.656716417910449e-06,
+      "loss": 2.3807,
+      "step": 30
+    },
+    {
+      "epoch": 0.300187617260788,
+      "grad_norm": 0.9802243709564209,
+      "learning_rate": 1.164179104477612e-05,
+      "loss": 2.1459,
+      "step": 40
+    },
+    {
+      "epoch": 0.37523452157598497,
+      "grad_norm": 0.9669085144996643,
+      "learning_rate": 1.4626865671641794e-05,
+      "loss": 1.9016,
+      "step": 50
+    },
+    {
+      "epoch": 0.37523452157598497,
+      "eval_loss": 1.7425719499588013,
+      "eval_runtime": 5.053,
+      "eval_samples_per_second": 22.363,
+      "eval_steps_per_second": 5.739,
+      "step": 50
+    },
+    {
+      "epoch": 0.450281425891182,
+      "grad_norm": 1.1177589893341064,
+      "learning_rate": 1.761194029850746e-05,
+      "loss": 1.596,
+      "step": 60
+    },
+    {
+      "epoch": 0.525328330206379,
+      "grad_norm": 0.5461925864219666,
+      "learning_rate": 2.0597014925373135e-05,
+      "loss": 1.2615,
+      "step": 70
+    },
+    {
+      "epoch": 0.5628517823639775,
+      "eval_loss": 1.0852540731430054,
+      "eval_runtime": 5.0653,
+      "eval_samples_per_second": 22.308,
+      "eval_steps_per_second": 5.725,
+      "step": 75
+    },
+    {
+      "epoch": 0.600375234521576,
+      "grad_norm": 0.5370538830757141,
+      "learning_rate": 2.3582089552238806e-05,
+      "loss": 1.1037,
+      "step": 80
+    },
+    {
+      "epoch": 0.6754221388367729,
+      "grad_norm": 0.4297517240047455,
+      "learning_rate": 2.656716417910448e-05,
+      "loss": 0.989,
+      "step": 90
+    },
+    {
+      "epoch": 0.7504690431519699,
+      "grad_norm": 0.5314680933952332,
+      "learning_rate": 2.955223880597015e-05,
+      "loss": 0.9507,
+      "step": 100
+    },
+    {
+      "epoch": 0.7504690431519699,
+      "eval_loss": 0.9193022847175598,
+      "eval_runtime": 5.0765,
+      "eval_samples_per_second": 22.259,
+      "eval_steps_per_second": 5.713,
+      "step": 100
+    },
+    {
+      "epoch": 0.8255159474671669,
+      "grad_norm": 0.4320300221443176,
+      "learning_rate": 3.253731343283582e-05,
+      "loss": 0.9321,
+      "step": 110
+    },
+    {
+      "epoch": 0.900562851782364,
+      "grad_norm": 0.44459468126296997,
+      "learning_rate": 3.5522388059701495e-05,
+      "loss": 0.8909,
+      "step": 120
+    },
+    {
+      "epoch": 0.9380863039399625,
+      "eval_loss": 0.847252368927002,
+      "eval_runtime": 5.0816,
+      "eval_samples_per_second": 22.237,
+      "eval_steps_per_second": 5.707,
+      "step": 125
+    },
+    {
+      "epoch": 0.975609756097561,
+      "grad_norm": 0.4286046326160431,
+      "learning_rate": 3.850746268656716e-05,
+      "loss": 0.8575,
+      "step": 130
+    },
+    {
+      "epoch": 1.0450281425891181,
+      "grad_norm": 0.4913986921310425,
+      "learning_rate": 4.149253731343284e-05,
+      "loss": 0.859,
+      "step": 140
+    },
+    {
+      "epoch": 1.1200750469043153,
+      "grad_norm": 0.47017258405685425,
+      "learning_rate": 4.447761194029851e-05,
+      "loss": 0.8314,
+      "step": 150
+    },
+    {
+      "epoch": 1.1200750469043153,
+      "eval_loss": 0.8092061877250671,
+      "eval_runtime": 5.0731,
+      "eval_samples_per_second": 22.274,
+      "eval_steps_per_second": 5.716,
+      "step": 150
+    },
+    {
+      "epoch": 1.1951219512195121,
+      "grad_norm": 0.4936457574367523,
+      "learning_rate": 4.7462686567164185e-05,
+      "loss": 0.8098,
+      "step": 160
+    },
+    {
+      "epoch": 1.2701688555347093,
+      "grad_norm": 0.46496817469596863,
+      "learning_rate": 5.044776119402985e-05,
+      "loss": 0.7836,
+      "step": 170
+    },
+    {
+      "epoch": 1.3076923076923077,
+      "eval_loss": 0.7787837982177734,
+      "eval_runtime": 5.0698,
+      "eval_samples_per_second": 22.289,
+      "eval_steps_per_second": 5.72,
+      "step": 175
+    },
+    {
+      "epoch": 1.3452157598499062,
+      "grad_norm": 0.48638296127319336,
+      "learning_rate": 5.343283582089552e-05,
+      "loss": 0.7835,
+      "step": 180
+    },
+    {
+      "epoch": 1.4202626641651033,
+      "grad_norm": 0.49088621139526367,
+      "learning_rate": 5.64179104477612e-05,
+      "loss": 0.7774,
+      "step": 190
+    },
+    {
+      "epoch": 1.4953095684803002,
+      "grad_norm": 0.49398818612098694,
+      "learning_rate": 5.940298507462687e-05,
+      "loss": 0.77,
+      "step": 200
+    },
+    {
+      "epoch": 1.4953095684803002,
+      "eval_loss": 0.7553061842918396,
+      "eval_runtime": 5.0675,
+      "eval_samples_per_second": 22.299,
+      "eval_steps_per_second": 5.723,
+      "step": 200
+    },
+    {
+      "epoch": 1.5703564727954973,
+      "grad_norm": 0.5628990530967712,
+      "learning_rate": 6.238805970149254e-05,
+      "loss": 0.7582,
+      "step": 210
+    },
+    {
+      "epoch": 1.6454033771106942,
+      "grad_norm": 0.49695977568626404,
+      "learning_rate": 6.537313432835821e-05,
+      "loss": 0.7592,
+      "step": 220
+    },
+    {
+      "epoch": 1.6829268292682928,
+      "eval_loss": 0.7301478385925293,
+      "eval_runtime": 5.0727,
+      "eval_samples_per_second": 22.276,
+      "eval_steps_per_second": 5.717,
+      "step": 225
+    },
+    {
+      "epoch": 1.720450281425891,
+      "grad_norm": 0.4944610595703125,
+      "learning_rate": 6.835820895522388e-05,
+      "loss": 0.7329,
+      "step": 230
+    },
+    {
+      "epoch": 1.7954971857410882,
+      "grad_norm": 0.4966571033000946,
+      "learning_rate": 7.134328358208956e-05,
+      "loss": 0.7303,
+      "step": 240
+    },
+    {
+      "epoch": 1.8705440900562853,
+      "grad_norm": 0.5113062858581543,
+      "learning_rate": 7.432835820895523e-05,
+      "loss": 0.7082,
+      "step": 250
+    },
+    {
+      "epoch": 1.8705440900562853,
+      "eval_loss": 0.7024827003479004,
+      "eval_runtime": 5.0682,
+      "eval_samples_per_second": 22.296,
+      "eval_steps_per_second": 5.722,
+      "step": 250
+    },
+    {
+      "epoch": 1.9455909943714822,
+      "grad_norm": 0.5686495900154114,
+      "learning_rate": 7.731343283582089e-05,
+      "loss": 0.7017,
+      "step": 260
+    },
+    {
+      "epoch": 2.0150093808630394,
+      "grad_norm": 0.5748053193092346,
+      "learning_rate": 8.029850746268657e-05,
+      "loss": 0.6874,
+      "step": 270
+    },
+    {
+      "epoch": 2.052532833020638,
+      "eval_loss": 0.6817129850387573,
+      "eval_runtime": 5.0735,
+      "eval_samples_per_second": 22.273,
+      "eval_steps_per_second": 5.716,
+      "step": 275
+    },
+    {
+      "epoch": 2.0900562851782363,
+      "grad_norm": 0.5935199856758118,
+      "learning_rate": 8.328358208955225e-05,
+      "loss": 0.6522,
+      "step": 280
+    },
+    {
+      "epoch": 2.1651031894934336,
+      "grad_norm": 0.5952720046043396,
+      "learning_rate": 8.626865671641792e-05,
+      "loss": 0.6259,
+      "step": 290
+    },
+    {
+      "epoch": 2.2401500938086305,
+      "grad_norm": 0.6446412205696106,
+      "learning_rate": 8.925373134328359e-05,
+      "loss": 0.6171,
+      "step": 300
+    },
+    {
+      "epoch": 2.2401500938086305,
+      "eval_loss": 0.6408159136772156,
+      "eval_runtime": 5.0734,
+      "eval_samples_per_second": 22.273,
+      "eval_steps_per_second": 5.716,
+      "step": 300
+    },
+    {
+      "epoch": 2.3151969981238274,
+      "grad_norm": 0.722795307636261,
+      "learning_rate": 9.223880597014926e-05,
+      "loss": 0.6128,
+      "step": 310
+    },
+    {
+      "epoch": 2.3902439024390243,
+      "grad_norm": 0.6945660710334778,
+      "learning_rate": 9.522388059701492e-05,
+      "loss": 0.6027,
+      "step": 320
+    },
+    {
+      "epoch": 2.427767354596623,
+      "eval_loss": 0.6130869388580322,
+      "eval_runtime": 5.075,
+      "eval_samples_per_second": 22.266,
+      "eval_steps_per_second": 5.714,
+      "step": 325
+    },
+    {
+      "epoch": 2.465290806754221,
+      "grad_norm": 0.7010583877563477,
+      "learning_rate": 9.82089552238806e-05,
+      "loss": 0.5824,
+      "step": 330
+    },
+    {
+      "epoch": 2.5403377110694185,
+      "grad_norm": 0.7590329051017761,
+      "learning_rate": 9.999990255427757e-05,
+      "loss": 0.5626,
+      "step": 340
+    },
+    {
+      "epoch": 2.6153846153846154,
+      "grad_norm": 0.8965818881988525,
+      "learning_rate": 9.99988062942623e-05,
+      "loss": 0.5603,
+      "step": 350
+    },
+    {
+      "epoch": 2.6153846153846154,
+      "eval_loss": 0.5764831304550171,
+      "eval_runtime": 5.073,
+      "eval_samples_per_second": 22.275,
+      "eval_steps_per_second": 5.717,
+      "step": 350
+    },
+    {
+      "epoch": 2.6904315196998123,
+      "grad_norm": 0.7385474443435669,
+      "learning_rate": 9.999649199387416e-05,
+      "loss": 0.5426,
+      "step": 360
+    },
+    {
+      "epoch": 2.7654784240150097,
+      "grad_norm": 0.8265758156776428,
+      "learning_rate": 9.999295970949272e-05,
+      "loss": 0.5248,
+      "step": 370
+    },
+    {
+      "epoch": 2.803001876172608,
+      "eval_loss": 0.5394740104675293,
+      "eval_runtime": 5.0664,
+      "eval_samples_per_second": 22.304,
+      "eval_steps_per_second": 5.724,
+      "step": 375
+    },
+    {
+      "epoch": 2.8405253283302065,
+      "grad_norm": 0.7400410771369934,
+      "learning_rate": 9.998820952716934e-05,
+      "loss": 0.5078,
+      "step": 380
+    },
+    {
+      "epoch": 2.9155722326454034,
+      "grad_norm": 0.7278188467025757,
+      "learning_rate": 9.998224156262505e-05,
+      "loss": 0.4944,
+      "step": 390
+    },
+    {
+      "epoch": 2.9906191369606003,
+      "grad_norm": 0.7803333401679993,
+      "learning_rate": 9.997505596124777e-05,
+      "loss": 0.4893,
+      "step": 400
+    },
+    {
+      "epoch": 2.9906191369606003,
+      "eval_loss": 0.49963781237602234,
+      "eval_runtime": 5.0779,
+      "eval_samples_per_second": 22.253,
+      "eval_steps_per_second": 5.711,
+      "step": 400
+    },
+    {
+      "epoch": 3.0600375234521575,
+      "grad_norm": 0.8603639602661133,
+      "learning_rate": 9.996665289808871e-05,
+      "loss": 0.431,
+      "step": 410
+    },
+    {
+      "epoch": 3.1350844277673544,
+      "grad_norm": 0.70228511095047,
+      "learning_rate": 9.995703257785818e-05,
+      "loss": 0.408,
+      "step": 420
+    },
+    {
+      "epoch": 3.172607879924953,
+      "eval_loss": 0.4856467545032501,
+      "eval_runtime": 5.0713,
+      "eval_samples_per_second": 22.282,
+      "eval_steps_per_second": 5.719,
+      "step": 425
+    },
+    {
+      "epoch": 3.2101313320825517,
+      "grad_norm": 0.7288469672203064,
+      "learning_rate": 9.994619523492054e-05,
+      "loss": 0.3959,
+      "step": 430
+    },
+    {
+      "epoch": 3.2851782363977486,
+      "grad_norm": 0.7244749665260315,
+      "learning_rate": 9.993414113328852e-05,
+      "loss": 0.3995,
+      "step": 440
+    },
+    {
+      "epoch": 3.3602251407129455,
+      "grad_norm": 0.7007831931114197,
+      "learning_rate": 9.992087056661677e-05,
+      "loss": 0.3999,
+      "step": 450
+    },
+    {
+      "epoch": 3.3602251407129455,
+      "eval_loss": 0.474253386259079,
+      "eval_runtime": 5.0675,
+      "eval_samples_per_second": 22.299,
+      "eval_steps_per_second": 5.723,
+      "step": 450
+    },
+    {
+      "epoch": 3.4352720450281424,
+      "grad_norm": 0.8084601759910583,
+      "learning_rate": 9.990638385819472e-05,
+      "loss": 0.3819,
+      "step": 460
+    },
+    {
+      "epoch": 3.5103189493433398,
+      "grad_norm": 0.726610541343689,
+      "learning_rate": 9.989068136093873e-05,
+      "loss": 0.3869,
+      "step": 470
+    },
+    {
+      "epoch": 3.547842401500938,
+      "eval_loss": 0.46386292576789856,
+      "eval_runtime": 5.0699,
+      "eval_samples_per_second": 22.288,
+      "eval_steps_per_second": 5.72,
+      "step": 475
+    },
+    {
+      "epoch": 3.5853658536585367,
+      "grad_norm": 0.7002731561660767,
+      "learning_rate": 9.987376345738344e-05,
+      "loss": 0.3953,
+      "step": 480
+    },
+    {
+      "epoch": 3.6604127579737336,
+      "grad_norm": 0.6399222016334534,
+      "learning_rate": 9.985563055967248e-05,
+      "loss": 0.397,
+      "step": 490
+    },
+    {
+      "epoch": 3.7354596622889304,
+      "grad_norm": 0.8647626042366028,
+      "learning_rate": 9.983628310954843e-05,
+      "loss": 0.3868,
+      "step": 500
+    },
+    {
+      "epoch": 3.7354596622889304,
+      "eval_loss": 0.45724615454673767,
+      "eval_runtime": 5.072,
+      "eval_samples_per_second": 22.279,
+      "eval_steps_per_second": 5.718,
+      "step": 500
+    },
+    {
+      "epoch": 3.8105065666041273,
+      "grad_norm": 0.8007352948188782,
+      "learning_rate": 9.981572157834203e-05,
+      "loss": 0.3833,
+      "step": 510
+    },
+    {
+      "epoch": 3.8855534709193247,
+      "grad_norm": 0.7353331446647644,
+      "learning_rate": 9.979394646696078e-05,
+      "loss": 0.3873,
+      "step": 520
+    },
+    {
+      "epoch": 3.9230769230769234,
+      "eval_loss": 0.44937819242477417,
+      "eval_runtime": 5.0648,
+      "eval_samples_per_second": 22.311,
+      "eval_steps_per_second": 5.726,
+      "step": 525
+    },
+    {
+      "epoch": 3.9606003752345216,
+      "grad_norm": 0.725788950920105,
+      "learning_rate": 9.977095830587659e-05,
+      "loss": 0.3809,
+      "step": 530
+    },
+    {
+      "epoch": 4.030018761726079,
+      "grad_norm": 0.6748231053352356,
+      "learning_rate": 9.974675765511304e-05,
+      "loss": 0.346,
+      "step": 540
+    },
+    {
+      "epoch": 4.105065666041276,
+      "grad_norm": 0.7276281714439392,
+      "learning_rate": 9.972134510423157e-05,
+      "loss": 0.3137,
+      "step": 550
+    },
+    {
+      "epoch": 4.105065666041276,
+      "eval_loss": 0.4566233158111572,
+      "eval_runtime": 5.0603,
+      "eval_samples_per_second": 22.331,
+      "eval_steps_per_second": 5.731,
+      "step": 550
+    },
+    {
+      "epoch": 4.1801125703564725,
+      "grad_norm": 0.7759580612182617,
+      "learning_rate": 9.969472127231723e-05,
+      "loss": 0.3049,
+      "step": 560
+    },
+    {
+      "epoch": 4.25515947467167,
+      "grad_norm": 0.7065677642822266,
+      "learning_rate": 9.966688680796356e-05,
+      "loss": 0.3057,
+      "step": 570
+    },
+    {
+      "epoch": 4.2926829268292686,
+      "eval_loss": 0.4608473777770996,
+      "eval_runtime": 5.0627,
+      "eval_samples_per_second": 22.32,
+      "eval_steps_per_second": 5.728,
+      "step": 575
+    },
+    {
+      "epoch": 4.330206378986867,
+      "grad_norm": 0.746277391910553,
+      "learning_rate": 9.963784238925675e-05,
+      "loss": 0.3042,
+      "step": 580
+    },
+    {
+      "epoch": 4.405253283302064,
+      "grad_norm": 0.8283698558807373,
+      "learning_rate": 9.960758872375922e-05,
+      "loss": 0.312,
+      "step": 590
+    },
+    {
+      "epoch": 4.480300187617261,
+      "grad_norm": 0.7889224290847778,
+      "learning_rate": 9.957612654849225e-05,
+      "loss": 0.3153,
+      "step": 600
+    },
+    {
+      "epoch": 4.480300187617261,
+      "eval_loss": 0.45748454332351685,
+      "eval_runtime": 5.0739,
+      "eval_samples_per_second": 22.271,
+      "eval_steps_per_second": 5.715,
+      "step": 600
+    },
+    {
+      "epoch": 4.5553470919324575,
+      "grad_norm": 0.7301938533782959,
+      "learning_rate": 9.954345662991813e-05,
+      "loss": 0.3169,
+      "step": 610
+    },
+    {
+      "epoch": 4.630393996247655,
+      "grad_norm": 0.7097094655036926,
+      "learning_rate": 9.950957976392148e-05,
+      "loss": 0.313,
+      "step": 620
+    },
+    {
+      "epoch": 4.6679174484052535,
+      "eval_loss": 0.45044615864753723,
+      "eval_runtime": 5.0663,
+      "eval_samples_per_second": 22.304,
+      "eval_steps_per_second": 5.724,
+      "step": 625
+    },
+    {
+      "epoch": 4.705440900562852,
+      "grad_norm": 0.6627222895622253,
+      "learning_rate": 9.947449677578982e-05,
+      "loss": 0.311,
+      "step": 630
+    },
+    {
+      "epoch": 4.780487804878049,
+      "grad_norm": 0.831093966960907,
+      "learning_rate": 9.943820852019344e-05,
+      "loss": 0.3187,
+      "step": 640
+    },
+    {
+      "epoch": 4.855534709193246,
+      "grad_norm": 0.8561496734619141,
+      "learning_rate": 9.940071588116468e-05,
+      "loss": 0.317,
+      "step": 650
+    },
+    {
+      "epoch": 4.855534709193246,
+      "eval_loss": 0.4430959224700928,
+      "eval_runtime": 5.0752,
+      "eval_samples_per_second": 22.265,
+      "eval_steps_per_second": 5.714,
+      "step": 650
+    },
+    {
+      "epoch": 4.930581613508442,
+      "grad_norm": 0.7869876623153687,
+      "learning_rate": 9.936201977207631e-05,
+      "loss": 0.3165,
+      "step": 660
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 2.4095470905303955,
+      "learning_rate": 9.932212113561927e-05,
+      "loss": 0.3139,
+      "step": 670
+    },
+    {
+      "epoch": 5.037523452157599,
+      "eval_loss": 0.4734329581260681,
+      "eval_runtime": 5.0708,
+      "eval_samples_per_second": 22.285,
+      "eval_steps_per_second": 5.719,
+      "step": 675
+    },
+    {
+      "epoch": 5.075046904315197,
+      "grad_norm": 0.8977411985397339,
+      "learning_rate": 9.92810209437798e-05,
+      "loss": 0.2374,
+      "step": 680
+    },
+    {
+      "epoch": 5.150093808630394,
+      "grad_norm": 0.8467944860458374,
+      "learning_rate": 9.923872019781564e-05,
+      "loss": 0.2397,
+      "step": 690
+    },
+    {
+      "epoch": 5.225140712945591,
+      "grad_norm": 0.8776218295097351,
+      "learning_rate": 9.919521992823173e-05,
+      "loss": 0.2371,
+      "step": 700
+    },
+    {
+      "epoch": 5.225140712945591,
+      "eval_loss": 0.46672776341438293,
+      "eval_runtime": 5.0617,
+      "eval_samples_per_second": 22.324,
+      "eval_steps_per_second": 5.729,
+      "step": 700
+    },
+    {
+      "epoch": 5.300187617260788,
+      "grad_norm": 0.8390938639640808,
+      "learning_rate": 9.915052119475505e-05,
+      "loss": 0.2487,
+      "step": 710
+    },
+    {
+      "epoch": 5.375234521575985,
+      "grad_norm": 0.8848443627357483,
+      "learning_rate": 9.910462508630885e-05,
+      "loss": 0.2393,
+      "step": 720
+    },
+    {
+      "epoch": 5.412757973733584,
+      "eval_loss": 0.4665623605251312,
+      "eval_runtime": 5.0722,
+      "eval_samples_per_second": 22.278,
+      "eval_steps_per_second": 5.717,
+      "step": 725
+    },
+    {
+      "epoch": 5.450281425891182,
+      "grad_norm": 0.8097019195556641,
+      "learning_rate": 9.905753272098608e-05,
+      "loss": 0.2439,
+      "step": 730
+    },
+    {
+      "epoch": 5.525328330206379,
+      "grad_norm": 0.7588761448860168,
+      "learning_rate": 9.900924524602218e-05,
+      "loss": 0.2477,
+      "step": 740
+    },
+    {
+      "epoch": 5.600375234521576,
+      "grad_norm": 0.8408402800559998,
+      "learning_rate": 9.895976383776711e-05,
+      "loss": 0.2484,
+      "step": 750
+    },
+    {
+      "epoch": 5.600375234521576,
+      "eval_loss": 0.4602144956588745,
+      "eval_runtime": 5.0743,
+      "eval_samples_per_second": 22.269,
+      "eval_steps_per_second": 5.715,
+      "step": 750
+    },
+    {
+      "epoch": 5.6754221388367725,
+      "grad_norm": 0.8723646402359009,
+      "learning_rate": 9.890908970165669e-05,
+      "loss": 0.2533,
+      "step": 760
+    },
+    {
+      "epoch": 5.75046904315197,
+      "grad_norm": 0.6956503391265869,
+      "learning_rate": 9.88572240721833e-05,
+      "loss": 0.253,
+      "step": 770
+    },
+    {
+      "epoch": 5.7879924953095685,
+      "eval_loss": 0.450476735830307,
+      "eval_runtime": 5.0627,
+      "eval_samples_per_second": 22.32,
+      "eval_steps_per_second": 5.728,
+      "step": 775
+    },
+    {
+      "epoch": 5.825515947467167,
+      "grad_norm": 0.9172329306602478,
+      "learning_rate": 9.880416821286569e-05,
+      "loss": 0.2522,
+      "step": 780
+    },
+    {
+      "epoch": 5.900562851782364,
+      "grad_norm": 0.7848353981971741,
+      "learning_rate": 9.87499234162183e-05,
+      "loss": 0.2493,
+      "step": 790
+    },
+    {
+      "epoch": 5.975609756097561,
+      "grad_norm": 0.7720503211021423,
+      "learning_rate": 9.869449100371973e-05,
+      "loss": 0.2574,
+      "step": 800
+    },
+    {
+      "epoch": 5.975609756097561,
+      "eval_loss": 0.44239288568496704,
+      "eval_runtime": 5.0788,
+      "eval_samples_per_second": 22.249,
+      "eval_steps_per_second": 5.71,
+      "step": 800
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 6700,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 50,
+  "save_steps": 25,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 15,
+        "early_stopping_threshold": 0.0
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 0
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.5747343525279846e+17,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c75eb897625f755a32c2ad327d10501b47edde097461d3541cb6a487f7c8e5f
+size 6225