Upload folder using huggingface_hub

adapter_config.json

@@ -19,8 +19,8 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q",
-    "v"
+    "v",
+    "q"
   ],
   "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 sha256:3db87f701896489195a927e5c9dde21c995d3de94ee90397a91267637ea97711
+oid sha256:01dc76d47c630ee9a10ca60d96943f30917b2e8908c45fff0b061290b8242dfa
 size 544841648

all_results.json

@@ -1,9 +1,9 @@
 {
     "epoch": 4.0,
-    "total_flos": 5.356521585003725e+17,
-    "train_loss": 0.017390920542402186,
-    "train_runtime": 3545.4545,
-    "train_samples": 39396,
-    "train_samples_per_second": 44.447,
-    "train_steps_per_second": 22.223
+    "total_flos": 5.739774105826099e+17,
+    "train_loss": 0.015574026028710613,
+    "train_runtime": 3492.2371,
+    "train_samples": 42210,
+    "train_samples_per_second": 48.347,
+    "train_steps_per_second": 24.174
 }

{checkpoint-78792 → checkpoint-80000}/adapter_config.json

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

{checkpoint-78792 → checkpoint-80000}/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3db87f701896489195a927e5c9dde21c995d3de94ee90397a91267637ea97711
+oid sha256:8d3183b8ae6d643bfd8b634c5ccdc59cdcc5439ad8e422c57fe1844fe5382b10
 size 544841648

{checkpoint-78792 → checkpoint-80000}/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f4239286133abb6f49aad3ee2ea71120e40586fdff7016818259ec9555cbc88f
+oid sha256:f3f5b2da1476a5efa6ad4b9807f6b40a55a14454e2aa228082bcc5607ef9c122
 size 37990394

{checkpoint-78792 → checkpoint-80000}/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:40d188f8ecdaa0b550b15bd909cbf6af4c96aba25c804a4eb2925dc968a36347
+oid sha256:205eca22c5c8f2a2af54f50098e55859d90dfff6dbe070947a77895c34863282
 size 14244

{checkpoint-78792 → checkpoint-80000}/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3800369f654a2ebd0bbc0f4a716f8780d023112ba7cff4ffaf8ef138bd39a16b
+oid sha256:91f4b84f36dbacb4e6d59bfa7e3abffb360c19ee57057b40dd440e36df07328a
 size 1064

checkpoint-80000/trainer_state.json

@@ -0,0 +1,145 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.7905709547500592,
+  "eval_steps": 500,
+  "global_step": 80000,
+  "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
+    },
+    {
+      "epoch": 3.826809534222611,
+      "grad_norm": 1.4943372011184692,
+      "learning_rate": 4.4637321760694354e-08,
+      "loss": 0.198,
+      "step": 35000
+    },
+    {
+      "epoch": 3.827018752391887,
+      "grad_norm": 1.933853030204773,
+      "learning_rate": 4.458363129731462e-08,
+      "loss": 0.189,
+      "step": 40000
+    },
+    {
+      "epoch": 3.8268560251722086,
+      "grad_norm": 2.177536725997925,
+      "learning_rate": 4.462563563036998e-08,
+      "loss": 0.1828,
+      "step": 45000
+    },
+    {
+      "epoch": 3.827018752391887,
+      "grad_norm": 2.765676498413086,
+      "learning_rate": 4.45829716720587e-08,
+      "loss": 0.1762,
+      "step": 50000
+    },
+    {
+      "epoch": 3.9090262970859984,
+      "grad_norm": 2.2480595111846924,
+      "learning_rate": 2.3447088347896174e-08,
+      "loss": 0.2188,
+      "step": 55000
+    },
+    {
+      "epoch": 3.8767202946307426,
+      "grad_norm": 1.3450602293014526,
+      "learning_rate": 3.177352206494588e-08,
+      "loss": 0.2161,
+      "step": 60000
+    },
+    {
+      "epoch": 3.849798625918029,
+      "grad_norm": 1.3951970338821411,
+      "learning_rate": 3.871223801309743e-08,
+      "loss": 0.2069,
+      "step": 65000
+    },
+    {
+      "epoch": 3.827018752391887,
+      "grad_norm": 1.839920997619629,
+      "learning_rate": 4.458284603136581e-08,
+      "loss": 0.2588,
+      "step": 70000
+    },
+    {
+      "epoch": 3.8074931465123365,
+      "grad_norm": 1.9440021514892578,
+      "learning_rate": 4.961532422672319e-08,
+      "loss": 0.2477,
+      "step": 75000
+    },
+    {
+      "epoch": 3.7905709547500592,
+      "grad_norm": 3.082991361618042,
+      "learning_rate": 5.397682171773297e-08,
+      "loss": 0.2357,
+      "step": 80000
+    }
+  ],
+  "logging_steps": 5000,
+  "max_steps": 84420,
+  "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": 5.4388790744776704e+17,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

{checkpoint-78792 → checkpoint-80000}/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a0028a00e0bcd56d48c072639a7305c99d8e69f0b3902a8942073cab0eb1638c
+oid sha256:33f6e66c85f7c72f9e44879c2a7e4580c13742beb3d4a77e00c08dce8c8244e4
 size 5304

checkpoint-84420/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-84420/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": [
+    "v",
+    "q"
+  ],
+  "task_type": "SEQ_2_SEQ_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-84420/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01dc76d47c630ee9a10ca60d96943f30917b2e8908c45fff0b061290b8242dfa
+size 544841648

checkpoint-84420/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:508ccba39be04c7b8623afdce7e1ec37094317a076db1cef006de9423b9e9314
+size 37990394

checkpoint-84420/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52f24ab11cbb521b9e9ef016d7234a7c8f29f07dc9ad940e606b3ce717b92f44
+size 14244

checkpoint-84420/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63fc22c6d8ff9e9c381706a3aa000b0c6395d7c6d6550ec9021d55dc2c8f0357
+size 1064

{checkpoint-78792 → checkpoint-84420}/trainer_state.json

@@ -3,7 +3,7 @@
   "best_model_checkpoint": null,
   "epoch": 4.0,
   "eval_steps": 500,
-  "global_step": 78792,
+  "global_step": 84420,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -112,10 +112,17 @@
       "learning_rate": 4.961532422672319e-08,
       "loss": 0.2477,
       "step": 75000
+    },
+    {
+      "epoch": 3.7905709547500592,
+      "grad_norm": 3.082991361618042,
+      "learning_rate": 5.397682171773297e-08,
+      "loss": 0.2357,
+      "step": 80000
     }
   ],
   "logging_steps": 5000,
-  "max_steps": 78792,
+  "max_steps": 84420,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 4,
   "save_steps": 10000,
@@ -131,7 +138,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.356521585003725e+17,
+  "total_flos": 5.739774105826099e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null

checkpoint-84420/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33f6e66c85f7c72f9e44879c2a7e4580c13742beb3d4a77e00c08dce8c8244e4
+size 5304

runs/{Aug21_16-45-59_6b771ec52587/events.out.tfevents.1724258878.6b771ec52587.136.0 → Aug22_11-32-24_6bed13c89f20/events.out.tfevents.1724326675.6bed13c89f20.135.0}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:340a5adc2213c03feb9d0ca38742af09051b894ba2f3893409ecd82018f6b90e
+oid sha256:a086e47217cfcfc9ea9578bdc27640a9f8e274367012065be775a07c797b356b
 size 6515

train_results.json

@@ -1,9 +1,9 @@
 {
     "epoch": 4.0,
-    "total_flos": 5.356521585003725e+17,
-    "train_loss": 0.017390920542402186,
-    "train_runtime": 3545.4545,
-    "train_samples": 39396,
-    "train_samples_per_second": 44.447,
-    "train_steps_per_second": 22.223
+    "total_flos": 5.739774105826099e+17,
+    "train_loss": 0.015574026028710613,
+    "train_runtime": 3492.2371,
+    "train_samples": 42210,
+    "train_samples_per_second": 48.347,
+    "train_steps_per_second": 24.174
 }

trainer_state.json

@@ -3,7 +3,7 @@
   "best_model_checkpoint": null,
   "epoch": 4.0,
   "eval_steps": 500,
-  "global_step": 78792,
+  "global_step": 84420,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -113,18 +113,25 @@
       "loss": 0.2477,
       "step": 75000
     },
+    {
+      "epoch": 3.7905709547500592,
+      "grad_norm": 3.082991361618042,
+      "learning_rate": 5.397682171773297e-08,
+      "loss": 0.2357,
+      "step": 80000
+    },
     {
       "epoch": 4.0,
-      "step": 78792,
-      "total_flos": 5.356521585003725e+17,
-      "train_loss": 0.017390920542402186,
-      "train_runtime": 3545.4545,
-      "train_samples_per_second": 44.447,
-      "train_steps_per_second": 22.223
+      "step": 84420,
+      "total_flos": 5.739774105826099e+17,
+      "train_loss": 0.015574026028710613,
+      "train_runtime": 3492.2371,
+      "train_samples_per_second": 48.347,
+      "train_steps_per_second": 24.174
     }
   ],
   "logging_steps": 5000,
-  "max_steps": 78792,
+  "max_steps": 84420,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 4,
   "save_steps": 10000,
@@ -140,7 +147,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.356521585003725e+17,
+  "total_flos": 5.739774105826099e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null