Upload folder using huggingface_hub

.gitattributes

@@ -60,3 +60,4 @@ punctuation/decoder_model/checkpoint-150/tokenizer.json filter=lfs diff=lfs merg
 punctuation/decoder_model/checkpoint-250/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 punctuation/decoder_model/checkpoint-300/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 punctuation/decoder_model/checkpoint-321/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+punctuation/encoder_model/checkpoint-214/tokenizer.json filter=lfs diff=lfs merge=lfs -text

punctuation/encoder_model/adapter_config.json

@@ -29,12 +29,12 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "o_proj",
+    "down_proj",
     "up_proj",
-    "q_proj",
+    "o_proj",
     "gate_proj",
     "k_proj",
-    "down_proj",
+    "q_proj",
     "v_proj"
   ],
   "target_parameters": null,

punctuation/encoder_model/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b50ac9618daa165da5413da4d66b62b262c2e567e95015d81a835a4ceef20d2
+oid sha256:f7cf45a94316d08e93f301379da4ce0ec282d37e7a5b55eadcbc380629c75d92
 size 295488936

punctuation/encoder_model/checkpoint-200/adapter_config.json

@@ -29,12 +29,12 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "o_proj",
+    "down_proj",
     "up_proj",
-    "q_proj",
+    "o_proj",
     "gate_proj",
     "k_proj",
-    "down_proj",
+    "q_proj",
     "v_proj"
   ],
   "target_parameters": null,

punctuation/encoder_model/checkpoint-200/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:29d5f6c14b40397e4a66513dfe0fa551137f8f14a3d11c79383735f71e0dc736
+oid sha256:f7cf45a94316d08e93f301379da4ce0ec282d37e7a5b55eadcbc380629c75d92
 size 295488936

punctuation/encoder_model/checkpoint-200/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:31b0bc9789592a73091646b6f6af64c0216adb2977442a830cd1502303107b1f
+oid sha256:7b024f37d0aa96b5f09f7fae31f8eae186d78580f48fe5c6e13f72f48e30d661
 size 591203178

punctuation/encoder_model/checkpoint-200/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:753fb53af3b3a6f6058224b229b73ca4eca90c611c58d0195328b8c8ac108bbf
+oid sha256:d804dbdc272ca810da862ca26dd16070271bf0838ecf3232d213924c843c09cc
 size 14244

punctuation/encoder_model/checkpoint-200/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da963d3b7106f3b4c395d03ef6897e64220165c23480563310345c76ab7b120d
+oid sha256:bbea466a7f26547df5a49469ed5be6093303fca4dbcdd92604cbf551ce72600a
 size 1064

punctuation/encoder_model/checkpoint-200/trainer_state.json

@@ -1,7 +1,7 @@
 {
-  "best_global_step": 50,
-  "best_metric": 0.5,
-  "best_model_checkpoint": "./models/punctuation/encoder_model/checkpoint-50",
+  "best_global_step": 200,
+  "best_metric": 1.0,
+  "best_model_checkpoint": "./models/punctuation/encoder_model/checkpoint-200",
   "epoch": 1.8752941176470588,
   "eval_steps": 50,
   "global_step": 200,
@@ -11,178 +11,178 @@
   "log_history": [
     {
       "epoch": 0.09411764705882353,
-      "grad_norm": 0.2591496407985687,
-      "learning_rate": 0.0001,
-      "loss": 1.0255,
+      "grad_norm": 0.36188849806785583,
+      "learning_rate": 8.181818181818183e-05,
+      "loss": 1.1219,
       "step": 10
     },
     {
       "epoch": 0.18823529411764706,
-      "grad_norm": 0.23840643465518951,
-      "learning_rate": 0.0001,
-      "loss": 0.8799,
+      "grad_norm": 0.2508435845375061,
+      "learning_rate": 0.00017272727272727275,
+      "loss": 0.9281,
       "step": 20
     },
     {
       "epoch": 0.2823529411764706,
-      "grad_norm": 0.2382705807685852,
-      "learning_rate": 0.0001,
-      "loss": 0.8393,
+      "grad_norm": 0.2157556265592575,
+      "learning_rate": 0.00019934477790194445,
+      "loss": 0.852,
       "step": 30
     },
     {
       "epoch": 0.3764705882352941,
-      "grad_norm": 0.26509279012680054,
-      "learning_rate": 0.0001,
-      "loss": 0.8444,
+      "grad_norm": 0.25683870911598206,
+      "learning_rate": 0.0001961561797682962,
+      "loss": 0.844,
       "step": 40
     },
     {
       "epoch": 0.47058823529411764,
-      "grad_norm": 0.26330241560935974,
-      "learning_rate": 0.0001,
-      "loss": 0.8232,
+      "grad_norm": 0.26627957820892334,
+      "learning_rate": 0.00019039892931234435,
+      "loss": 0.8168,
       "step": 50
     },
     {
       "epoch": 0.47058823529411764,
-      "eval_loss": 0.8152285814285278,
-      "eval_model_preparation_time": 0.0135,
-      "eval_runtime": 4.0525,
-      "eval_samples_per_second": 24.676,
-      "eval_steps_per_second": 12.338,
+      "eval_loss": 0.8057724237442017,
+      "eval_model_preparation_time": 0.0129,
+      "eval_runtime": 3.824,
+      "eval_samples_per_second": 26.15,
+      "eval_steps_per_second": 13.075,
       "step": 50
     },
     {
       "epoch": 0.5647058823529412,
-      "grad_norm": 0.2532142400741577,
-      "learning_rate": 0.0001,
-      "loss": 0.8123,
+      "grad_norm": 0.228170707821846,
+      "learning_rate": 0.00018222682189897752,
+      "loss": 0.8023,
       "step": 60
     },
     {
       "epoch": 0.6588235294117647,
-      "grad_norm": 0.2938081622123718,
-      "learning_rate": 0.0001,
-      "loss": 0.7956,
+      "grad_norm": 0.26517826318740845,
+      "learning_rate": 0.0001718581617779698,
+      "loss": 0.7858,
       "step": 70
     },
     {
       "epoch": 0.7529411764705882,
-      "grad_norm": 0.2652847170829773,
-      "learning_rate": 0.0001,
-      "loss": 0.7741,
+      "grad_norm": 0.22760385274887085,
+      "learning_rate": 0.00015956993044924334,
+      "loss": 0.7632,
       "step": 80
     },
     {
       "epoch": 0.8470588235294118,
-      "grad_norm": 0.257866770029068,
-      "learning_rate": 0.0001,
-      "loss": 0.7907,
+      "grad_norm": 0.2228352576494217,
+      "learning_rate": 0.00014569038756304207,
+      "loss": 0.7788,
       "step": 90
     },
     {
       "epoch": 0.9411764705882353,
-      "grad_norm": 0.29850393533706665,
-      "learning_rate": 0.0001,
-      "loss": 0.7763,
+      "grad_norm": 0.25218382477760315,
+      "learning_rate": 0.00013059030200965536,
+      "loss": 0.7637,
       "step": 100
     },
     {
       "epoch": 0.9411764705882353,
-      "eval_loss": 0.7670149207115173,
-      "eval_model_preparation_time": 0.0135,
-      "eval_runtime": 4.0483,
-      "eval_samples_per_second": 24.702,
-      "eval_steps_per_second": 12.351,
+      "eval_loss": 0.753893256187439,
+      "eval_model_preparation_time": 0.0129,
+      "eval_runtime": 3.8121,
+      "eval_samples_per_second": 26.232,
+      "eval_steps_per_second": 13.116,
       "step": 100
     },
     {
       "epoch": 1.0282352941176471,
-      "grad_norm": 0.277658611536026,
-      "learning_rate": 0.0001,
-      "loss": 0.7689,
+      "grad_norm": 0.23036813735961914,
+      "learning_rate": 0.00011467304744553618,
+      "loss": 0.7508,
       "step": 110
     },
     {
       "epoch": 1.1223529411764706,
-      "grad_norm": 0.30186522006988525,
-      "learning_rate": 0.0001,
-      "loss": 0.7235,
+      "grad_norm": 0.25190669298171997,
+      "learning_rate": 9.836382683735132e-05,
+      "loss": 0.6933,
       "step": 120
     },
     {
       "epoch": 1.2164705882352942,
-      "grad_norm": 0.32689717411994934,
-      "learning_rate": 0.0001,
-      "loss": 0.7106,
+      "grad_norm": 0.27167296409606934,
+      "learning_rate": 8.209831387233676e-05,
+      "loss": 0.6799,
       "step": 130
     },
     {
       "epoch": 1.3105882352941176,
-      "grad_norm": 0.3532510995864868,
-      "learning_rate": 0.0001,
-      "loss": 0.6671,
+      "grad_norm": 0.29528751969337463,
+      "learning_rate": 6.6311014660778e-05,
+      "loss": 0.6377,
       "step": 140
     },
     {
       "epoch": 1.4047058823529412,
-      "grad_norm": 0.3470897376537323,
-      "learning_rate": 0.0001,
-      "loss": 0.6976,
+      "grad_norm": 0.2657102346420288,
+      "learning_rate": 5.142366062836599e-05,
+      "loss": 0.6636,
       "step": 150
     },
     {
       "epoch": 1.4047058823529412,
-      "eval_loss": 0.7519224286079407,
-      "eval_model_preparation_time": 0.0135,
-      "eval_runtime": 4.0317,
-      "eval_samples_per_second": 24.804,
-      "eval_steps_per_second": 12.402,
+      "eval_loss": 0.7372229099273682,
+      "eval_model_preparation_time": 0.0129,
+      "eval_runtime": 3.8052,
+      "eval_samples_per_second": 26.28,
+      "eval_steps_per_second": 13.14,
       "step": 150
     },
     {
       "epoch": 1.4988235294117647,
-      "grad_norm": 0.3563544452190399,
-      "learning_rate": 0.0001,
-      "loss": 0.6853,
+      "grad_norm": 0.27975210547447205,
+      "learning_rate": 3.783394266299228e-05,
+      "loss": 0.6498,
       "step": 160
     },
     {
       "epoch": 1.592941176470588,
-      "grad_norm": 0.3066166043281555,
-      "learning_rate": 0.0001,
-      "loss": 0.664,
+      "grad_norm": 0.2573317587375641,
+      "learning_rate": 2.5904887464504114e-05,
+      "loss": 0.6343,
       "step": 170
     },
     {
       "epoch": 1.6870588235294117,
-      "grad_norm": 0.352414071559906,
-      "learning_rate": 0.0001,
-      "loss": 0.6849,
+      "grad_norm": 0.2996138036251068,
+      "learning_rate": 1.595515989055618e-05,
+      "loss": 0.6505,
       "step": 180
     },
     {
       "epoch": 1.7811764705882354,
-      "grad_norm": 0.3295493721961975,
-      "learning_rate": 0.0001,
-      "loss": 0.683,
+      "grad_norm": 0.2739143669605255,
+      "learning_rate": 8.250550355250875e-06,
+      "loss": 0.6494,
       "step": 190
     },
     {
       "epoch": 1.8752941176470588,
-      "grad_norm": 0.3805347681045532,
-      "learning_rate": 0.0001,
-      "loss": 0.6574,
+      "grad_norm": 0.3023104965686798,
+      "learning_rate": 2.996874680545603e-06,
+      "loss": 0.6241,
       "step": 200
     },
     {
       "epoch": 1.8752941176470588,
-      "eval_loss": 0.732289731502533,
-      "eval_model_preparation_time": 0.0135,
-      "eval_runtime": 4.0681,
-      "eval_samples_per_second": 24.581,
-      "eval_steps_per_second": 12.291,
+      "eval_loss": 0.7298660278320312,
+      "eval_model_preparation_time": 0.0129,
+      "eval_runtime": 3.8044,
+      "eval_samples_per_second": 26.286,
+      "eval_steps_per_second": 13.143,
       "step": 200
     }
   ],

punctuation/encoder_model/checkpoint-200/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9fe3eebf03936502ce0d736fbdd8fab243fcbd8afa4264316711d934cc5852d7
+oid sha256:1c183af3b7bc95584398a77bc592fe53fb18d26a136f103466b442a82eaa4ecb
 size 5496

punctuation/encoder_model/checkpoint-214/README.md

@@ -0,0 +1,207 @@
+---
+base_model: deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B
+- lora
+- transformers
+---
+
+# 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

punctuation/encoder_model/checkpoint-214/adapter_config.json

@@ -0,0 +1,46 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B",
+  "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": 128,
+  "lora_bias": false,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "up_proj",
+    "o_proj",
+    "gate_proj",
+    "k_proj",
+    "q_proj",
+    "v_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

punctuation/encoder_model/checkpoint-214/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72171cf42b8ed83736415ec23bdb8a3c1eb09700f5675e9d3172744a0bfbb03a
+size 295488936

punctuation/encoder_model/checkpoint-214/chat_template.jinja

@@ -0,0 +1 @@
+{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<｜User｜>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<｜Assistant｜><｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\n' + '```json' + '\n' + tool['function']['arguments'] + '\n' + '```' + '<｜tool▁call▁end｜>'}}{%- set ns.is_first = true -%}{%- else %}{{'\n' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\n' + '```json' + '\n' + tool['function']['arguments'] + '\n' + '```' + '<｜tool▁call▁end｜>'}}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>' + message['content'] + '<｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '</think>' in content %}{% set content = content.split('</think>')[-1] %}{% endif %}{{'<｜Assistant｜>' + content + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\n<｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<｜Assistant｜><think>\n'}}{% endif %}

punctuation/encoder_model/checkpoint-214/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58ab12279dd2d06323288284b5ac5a526f5f136bc2d2d43e6b930bc0540feafa
+size 591203178

punctuation/encoder_model/checkpoint-214/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3bdc3aee4efd4ac2905a76ab7222a5376e21922247e2849b9e98734f3360f985
+size 14244

punctuation/encoder_model/checkpoint-214/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:802f115045aeeb27907b881b744440b538c2582f39dcf8d05da0ddabad9a975b
+size 1064

punctuation/encoder_model/checkpoint-214/special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<｜begin▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<｜end▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<｜end▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

punctuation/encoder_model/checkpoint-214/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1f3503dade503303f354be26edaf4223708fa1ca2e84c4daf306b5d7c40ce23
+size 11423058

punctuation/encoder_model/checkpoint-214/tokenizer_config.json

@@ -0,0 +1,194 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<｜end▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<｜User｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151645": {
+      "content": "<｜Assistant｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151646": {
+      "content": "<｜begin▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|EOT|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151648": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151649": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "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
+    }
+  },
+  "bos_token": "<｜begin▁of▁sentence｜>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<｜end▁of▁sentence｜>",
+  "extra_special_tokens": {},
+  "legacy": true,
+  "model_max_length": 16384,
+  "pad_token": "<｜end▁of▁sentence｜>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizerFast",
+  "unk_token": null,
+  "use_default_system_prompt": false
+}

punctuation/encoder_model/checkpoint-214/trainer_state.json

@@ -0,0 +1,217 @@
+{
+  "best_global_step": 200,
+  "best_metric": 1.0,
+  "best_model_checkpoint": "./models/punctuation/encoder_model/checkpoint-200",
+  "epoch": 2.0,
+  "eval_steps": 50,
+  "global_step": 214,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.09411764705882353,
+      "grad_norm": 0.36188849806785583,
+      "learning_rate": 8.181818181818183e-05,
+      "loss": 1.1219,
+      "step": 10
+    },
+    {
+      "epoch": 0.18823529411764706,
+      "grad_norm": 0.2508435845375061,
+      "learning_rate": 0.00017272727272727275,
+      "loss": 0.9281,
+      "step": 20
+    },
+    {
+      "epoch": 0.2823529411764706,
+      "grad_norm": 0.2157556265592575,
+      "learning_rate": 0.00019934477790194445,
+      "loss": 0.852,
+      "step": 30
+    },
+    {
+      "epoch": 0.3764705882352941,
+      "grad_norm": 0.25683870911598206,
+      "learning_rate": 0.0001961561797682962,
+      "loss": 0.844,
+      "step": 40
+    },
+    {
+      "epoch": 0.47058823529411764,
+      "grad_norm": 0.26627957820892334,
+      "learning_rate": 0.00019039892931234435,
+      "loss": 0.8168,
+      "step": 50
+    },
+    {
+      "epoch": 0.47058823529411764,
+      "eval_loss": 0.8057724237442017,
+      "eval_model_preparation_time": 0.0129,
+      "eval_runtime": 3.824,
+      "eval_samples_per_second": 26.15,
+      "eval_steps_per_second": 13.075,
+      "step": 50
+    },
+    {
+      "epoch": 0.5647058823529412,
+      "grad_norm": 0.228170707821846,
+      "learning_rate": 0.00018222682189897752,
+      "loss": 0.8023,
+      "step": 60
+    },
+    {
+      "epoch": 0.6588235294117647,
+      "grad_norm": 0.26517826318740845,
+      "learning_rate": 0.0001718581617779698,
+      "loss": 0.7858,
+      "step": 70
+    },
+    {
+      "epoch": 0.7529411764705882,
+      "grad_norm": 0.22760385274887085,
+      "learning_rate": 0.00015956993044924334,
+      "loss": 0.7632,
+      "step": 80
+    },
+    {
+      "epoch": 0.8470588235294118,
+      "grad_norm": 0.2228352576494217,
+      "learning_rate": 0.00014569038756304207,
+      "loss": 0.7788,
+      "step": 90
+    },
+    {
+      "epoch": 0.9411764705882353,
+      "grad_norm": 0.25218382477760315,
+      "learning_rate": 0.00013059030200965536,
+      "loss": 0.7637,
+      "step": 100
+    },
+    {
+      "epoch": 0.9411764705882353,
+      "eval_loss": 0.753893256187439,
+      "eval_model_preparation_time": 0.0129,
+      "eval_runtime": 3.8121,
+      "eval_samples_per_second": 26.232,
+      "eval_steps_per_second": 13.116,
+      "step": 100
+    },
+    {
+      "epoch": 1.0282352941176471,
+      "grad_norm": 0.23036813735961914,
+      "learning_rate": 0.00011467304744553618,
+      "loss": 0.7508,
+      "step": 110
+    },
+    {
+      "epoch": 1.1223529411764706,
+      "grad_norm": 0.25190669298171997,
+      "learning_rate": 9.836382683735132e-05,
+      "loss": 0.6933,
+      "step": 120
+    },
+    {
+      "epoch": 1.2164705882352942,
+      "grad_norm": 0.27167296409606934,
+      "learning_rate": 8.209831387233676e-05,
+      "loss": 0.6799,
+      "step": 130
+    },
+    {
+      "epoch": 1.3105882352941176,
+      "grad_norm": 0.29528751969337463,
+      "learning_rate": 6.6311014660778e-05,
+      "loss": 0.6377,
+      "step": 140
+    },
+    {
+      "epoch": 1.4047058823529412,
+      "grad_norm": 0.2657102346420288,
+      "learning_rate": 5.142366062836599e-05,
+      "loss": 0.6636,
+      "step": 150
+    },
+    {
+      "epoch": 1.4047058823529412,
+      "eval_loss": 0.7372229099273682,
+      "eval_model_preparation_time": 0.0129,
+      "eval_runtime": 3.8052,
+      "eval_samples_per_second": 26.28,
+      "eval_steps_per_second": 13.14,
+      "step": 150
+    },
+    {
+      "epoch": 1.4988235294117647,
+      "grad_norm": 0.27975210547447205,
+      "learning_rate": 3.783394266299228e-05,
+      "loss": 0.6498,
+      "step": 160
+    },
+    {
+      "epoch": 1.592941176470588,
+      "grad_norm": 0.2573317587375641,
+      "learning_rate": 2.5904887464504114e-05,
+      "loss": 0.6343,
+      "step": 170
+    },
+    {
+      "epoch": 1.6870588235294117,
+      "grad_norm": 0.2996138036251068,
+      "learning_rate": 1.595515989055618e-05,
+      "loss": 0.6505,
+      "step": 180
+    },
+    {
+      "epoch": 1.7811764705882354,
+      "grad_norm": 0.2739143669605255,
+      "learning_rate": 8.250550355250875e-06,
+      "loss": 0.6494,
+      "step": 190
+    },
+    {
+      "epoch": 1.8752941176470588,
+      "grad_norm": 0.3023104965686798,
+      "learning_rate": 2.996874680545603e-06,
+      "loss": 0.6241,
+      "step": 200
+    },
+    {
+      "epoch": 1.8752941176470588,
+      "eval_loss": 0.7298660278320312,
+      "eval_model_preparation_time": 0.0129,
+      "eval_runtime": 3.8044,
+      "eval_samples_per_second": 26.286,
+      "eval_steps_per_second": 13.143,
+      "step": 200
+    },
+    {
+      "epoch": 1.9694117647058822,
+      "grad_norm": 0.30277180671691895,
+      "learning_rate": 3.3447606908196817e-07,
+      "loss": 0.6682,
+      "step": 210
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 214,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 50,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3.0957481606324224e+16,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

punctuation/encoder_model/checkpoint-214/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c183af3b7bc95584398a77bc592fe53fb18d26a136f103466b442a82eaa4ecb
+size 5496

punctuation/encoder_model/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9fe3eebf03936502ce0d736fbdd8fab243fcbd8afa4264316711d934cc5852d7
+oid sha256:1c183af3b7bc95584398a77bc592fe53fb18d26a136f103466b442a82eaa4ecb
 size 5496

punctuation/encoder_model/training_config.yaml

@@ -26,9 +26,9 @@ training:
   gradient_checkpointing: false
   greater_is_better: true
   group_by_length: true
-  learning_rate: 0.0001
+  learning_rate: 0.0002
   load_best_model_at_end: true
-  lr_scheduler: constant
+  lr_scheduler: cosine
   max_grad_norm: 1.0
   metric_for_best_model: eval_encoder_accuracy
   num_epochs: 2