Upload folder using huggingface_hub

adapter_config.json

@@ -19,8 +19,8 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v",
-    "q"
+    "q",
+    "v"
   ],
   "task_type": "SEQ_2_SEQ_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a6e5f9300115b502234b9a3c50a84141340484ddbc1273e7d7cbe0931f59913d
+oid sha256:faf0c6f35158f5c691bcbb6256383f248b329602cb928768a9904823ce59b414
 size 544841648

all_results.json

@@ -1,9 +1,9 @@
 {
     "epoch": 4.0,
-    "total_flos": 1.7759719053361152e+17,
-    "train_loss": 0.046144020387704134,
-    "train_runtime": 3194.9024,
-    "train_samples": 13065,
-    "train_samples_per_second": 16.357,
-    "train_steps_per_second": 8.179
+    "total_flos": 2.1310027172118528e+17,
+    "train_loss": 0.03533258935690139,
+    "train_runtime": 3211.4331,
+    "train_samples": 15678,
+    "train_samples_per_second": 19.528,
+    "train_steps_per_second": 9.764
 }

{checkpoint-26132 → checkpoint-30000}/adapter_config.json

@@ -19,8 +19,8 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v",
-    "q"
+    "q",
+    "v"
   ],
   "task_type": "SEQ_2_SEQ_LM",
   "use_dora": false,

{checkpoint-26132 → checkpoint-30000}/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a6e5f9300115b502234b9a3c50a84141340484ddbc1273e7d7cbe0931f59913d
+oid sha256:a68bfb48a7bbb9b102cb6f4c314afc6a90b9cb7e341f889f8a17267961f083bc
 size 544841648

{checkpoint-26132 → checkpoint-30000}/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:301692ff532b33ea77f7da2aa2ad44db4b9d8e31b24d1691502c615473022cba
+oid sha256:9a9ec4346447a76a26178d0b32ca679a0a563d6294dc712c2a004ec4ffccaa5f
 size 37990394

{checkpoint-26132 → checkpoint-30000}/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b7304b02b9c4ff8c8521d1dbe72cde0bf67010649b15b880dfc41c79fdb53fb
+oid sha256:55afcabd3d5e08c4755393aef9ad6682e369f41cce50f7de0acc76d339302d2f
 size 14244

{checkpoint-26132 → checkpoint-30000}/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c5013f058fe9364bbd6164da7faa4f27cf4e1e00c76966294c7ccc5abbc98033
+oid sha256:16543d21e85148e256c34e78bda77dffa4cedb47d0dcd6da5522d8eb941c02cf
 size 1064

checkpoint-30000/trainer_state.json

@@ -0,0 +1,75 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.827018752391887,
+  "eval_steps": 500,
+  "global_step": 30000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 3.8255547054322876,
+      "grad_norm": 2.0333640575408936,
+      "learning_rate": 4.4961546046144744e-08,
+      "loss": 0.8176,
+      "step": 5000
+    },
+    {
+      "epoch": 3.827018752391887,
+      "grad_norm": 1.769223928451538,
+      "learning_rate": 4.458473071611758e-08,
+      "loss": 0.4356,
+      "step": 10000
+    },
+    {
+      "epoch": 3.826530612244898,
+      "grad_norm": 2.0607104301452637,
+      "learning_rate": 4.47103688605431e-08,
+      "loss": 0.317,
+      "step": 15000
+    },
+    {
+      "epoch": 3.827018752391887,
+      "grad_norm": 2.4189670085906982,
+      "learning_rate": 4.458473071611758e-08,
+      "loss": 0.2652,
+      "step": 20000
+    },
+    {
+      "epoch": 3.826725853359865,
+      "grad_norm": 2.4704151153564453,
+      "learning_rate": 4.465835568881174e-08,
+      "loss": 0.2326,
+      "step": 25000
+    },
+    {
+      "epoch": 3.827018752391887,
+      "grad_norm": 2.8222293853759766,
+      "learning_rate": 4.458326483642939e-08,
+      "loss": 0.2139,
+      "step": 30000
+    }
+  ],
+  "logging_steps": 5000,
+  "max_steps": 31356,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 10000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.0387507640434688e+17,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

{checkpoint-26132 → checkpoint-30000}/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:976a262046bbf421089c599ad956b2892170853fd5b15cff0ebb12496b127106
+oid sha256:eca53f5cf57c5d05568c2f1ff04ccf0af2a3c76bc5e4cc2a0340633b3f32cc03
 size 5304

checkpoint-31356/README.md

@@ -0,0 +1,202 @@
+---
+base_model: google/flan-t5-xl
+library_name: peft
+---
+
+# 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 0.9.0

checkpoint-31356/adapter_config.json

@@ -0,0 +1,28 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "google/flan-t5-xl",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q",
+    "v"
+  ],
+  "task_type": "SEQ_2_SEQ_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-31356/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:faf0c6f35158f5c691bcbb6256383f248b329602cb928768a9904823ce59b414
+size 544841648

checkpoint-31356/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dba8425ed30e97b092f7d8cf34d7c388756ba3908435c578606a833e3abde3b2
+size 37990394

checkpoint-31356/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:686afead75d16a1358bba6b60ea770a65e95cc222890111643b7a7746f973aab
+size 14244

checkpoint-31356/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de01f13982a138d8badcfc8fda46cd84ddfcb48f9f4889809bbc3ea0bef1577e
+size 1064

{checkpoint-26132 → checkpoint-31356}/trainer_state.json

@@ -3,7 +3,7 @@
   "best_model_checkpoint": null,
   "epoch": 4.0,
   "eval_steps": 500,
-  "global_step": 26132,
+  "global_step": 31356,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -42,10 +42,17 @@
       "learning_rate": 4.465835568881174e-08,
       "loss": 0.2326,
       "step": 25000
+    },
+    {
+      "epoch": 3.827018752391887,
+      "grad_norm": 2.8222293853759766,
+      "learning_rate": 4.458326483642939e-08,
+      "loss": 0.2139,
+      "step": 30000
     }
   ],
   "logging_steps": 5000,
-  "max_steps": 26132,
+  "max_steps": 31356,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 4,
   "save_steps": 10000,
@@ -61,7 +68,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.7759719053361152e+17,
+  "total_flos": 2.1310027172118528e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null

checkpoint-31356/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eca53f5cf57c5d05568c2f1ff04ccf0af2a3c76bc5e4cc2a0340633b3f32cc03
+size 5304

runs/{Jul22_12-07-50_951d2b8164e7/events.out.tfevents.1721650148.951d2b8164e7.137.0 → Jul24_11-08-51_ed2d0ca52250/events.out.tfevents.1721819439.ed2d0ca52250.137.0}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:24b3a2dea23c0d395987ae304d86a85d4e2aa584310a198ea8afebc55fe88818
+oid sha256:dd793b8b63878e5ce571286764494d4dc1474a7246e630786d4fa3d30115f515
 size 6515

train_results.json

@@ -1,9 +1,9 @@
 {
     "epoch": 4.0,
-    "total_flos": 1.7759719053361152e+17,
-    "train_loss": 0.046144020387704134,
-    "train_runtime": 3194.9024,
-    "train_samples": 13065,
-    "train_samples_per_second": 16.357,
-    "train_steps_per_second": 8.179
+    "total_flos": 2.1310027172118528e+17,
+    "train_loss": 0.03533258935690139,
+    "train_runtime": 3211.4331,
+    "train_samples": 15678,
+    "train_samples_per_second": 19.528,
+    "train_steps_per_second": 9.764
 }

trainer_state.json

@@ -3,7 +3,7 @@
   "best_model_checkpoint": null,
   "epoch": 4.0,
   "eval_steps": 500,
-  "global_step": 26132,
+  "global_step": 31356,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -43,18 +43,25 @@
       "loss": 0.2326,
       "step": 25000
     },
+    {
+      "epoch": 3.827018752391887,
+      "grad_norm": 2.8222293853759766,
+      "learning_rate": 4.458326483642939e-08,
+      "loss": 0.2139,
+      "step": 30000
+    },
     {
       "epoch": 4.0,
-      "step": 26132,
-      "total_flos": 1.7759719053361152e+17,
-      "train_loss": 0.046144020387704134,
-      "train_runtime": 3194.9024,
-      "train_samples_per_second": 16.357,
-      "train_steps_per_second": 8.179
+      "step": 31356,
+      "total_flos": 2.1310027172118528e+17,
+      "train_loss": 0.03533258935690139,
+      "train_runtime": 3211.4331,
+      "train_samples_per_second": 19.528,
+      "train_steps_per_second": 9.764
     }
   ],
   "logging_steps": 5000,
-  "max_steps": 26132,
+  "max_steps": 31356,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 4,
   "save_steps": 10000,
@@ -70,7 +77,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.7759719053361152e+17,
+  "total_flos": 2.1310027172118528e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null