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 sha256:4720cb70541162b17e25483934f5390d358dcb851854cadce950bf3a98cb0560
+oid sha256:4f4fdaa80279a5e919dc4429dde8012463191cc6d1a982dd3eaddee4af96eb3c
 size 544841648

all_results.json

@@ -1,9 +1,9 @@
 {
     "epoch": 4.0,
-    "total_flos": 3.55220884094976e+17,
-    "train_loss": 0.017499278579869583,
-    "train_runtime": 3192.4272,
-    "train_samples": 26130,
-    "train_samples_per_second": 32.74,
-    "train_steps_per_second": 16.37
+    "total_flos": 3.8254470258622464e+17,
+    "train_loss": 0.015788240303955946,
+    "train_runtime": 2477.3699,
+    "train_samples": 28140,
+    "train_samples_per_second": 45.435,
+    "train_steps_per_second": 22.718
 }

checkpoint-50000/adapter_model.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:443abd9be21c7b656d989061bda3008cb130bbcf4495f34291bde2cd208ba9b8
-size 544841648

checkpoint-50000/optimizer.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:94a66fb07a5f591f16726734f59000a572d5ec3206ba3507a45b33b92255e925
-size 37990394

checkpoint-50000/rng_state.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:abea384ff6bd16a94d871a738111b171e9c39bb3f6ba3508ad163c3ab27de48f
-size 14244

checkpoint-50000/trainer_state.json

@@ -1,103 +0,0 @@
-{
-  "best_metric": null,
-  "best_model_checkpoint": null,
-  "epoch": 3.827018752391887,
-  "eval_steps": 500,
-  "global_step": 50000,
-  "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
-    }
-  ],
-  "logging_steps": 5000,
-  "max_steps": 52260,
-  "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": 3.3986278107316224e+17,
-  "train_batch_size": 2,
-  "trial_name": null,
-  "trial_params": null
-}

checkpoint-52260/README.md

@@ -1,202 +0,0 @@
----
-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-52260/adapter_config.json

@@ -1,28 +0,0 @@
-{
-  "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-52260/scheduler.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:3d6946b56ba520a4c42e25c4183e61c20310a5159a418d48ae2c263affdea73a
-size 1064

checkpoint-52260/training_args.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:0a1733802abcab0de0abb290e8fdb2e08aa4244d9df7398b939c16c173aa1312
-size 5304

{checkpoint-50000 → checkpoint-56280}/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-52260 → checkpoint-56280}/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4720cb70541162b17e25483934f5390d358dcb851854cadce950bf3a98cb0560
+oid sha256:4f4fdaa80279a5e919dc4429dde8012463191cc6d1a982dd3eaddee4af96eb3c
 size 544841648

{checkpoint-52260 → checkpoint-56280}/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb7381fdf10cc3dc14ed9252ae8081bd5d5e25584189ea63bbc1b763112169f5
+oid sha256:0837cdf6c98996fe13904f3c067562d53bef89cdf5cd6bfdd6802104ef7652b4
 size 37990394

{checkpoint-52260 → checkpoint-56280}/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0959fba3c9fb8317395cc59ecaca85c2c69a10520140117202d7c071aa41eacd
+oid sha256:35f6420e75e12f77b1e05ef197bbd742b0542f9ee8e5cd6c5a49edcc211516a5
 size 14244

{checkpoint-50000 → checkpoint-56280}/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:18122420ac5ddf63c73a761b98c0cc8f149b9ea242b4795404ad9cef5b5a7c78
+oid sha256:025092508d689d03772052fd1d5943c92acbca0df75ca25e6d77a9b8690adfc8
 size 1064

{checkpoint-52260 → checkpoint-56280}/trainer_state.json

@@ -3,7 +3,7 @@
   "best_model_checkpoint": null,
   "epoch": 4.0,
   "eval_steps": 500,
-  "global_step": 52260,
+  "global_step": 56280,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -77,10 +77,17 @@
       "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
     }
   ],
   "logging_steps": 5000,
-  "max_steps": 52260,
+  "max_steps": 56280,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 4,
   "save_steps": 10000,
@@ -96,7 +103,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.55220884094976e+17,
+  "total_flos": 3.8254470258622464e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null

{checkpoint-50000 → checkpoint-56280}/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a1733802abcab0de0abb290e8fdb2e08aa4244d9df7398b939c16c173aa1312
+oid sha256:dde3e76c68960f29d8dcd8b585e7fa7dacc620895b260d003b92d999fa18fa8e
 size 5304

runs/{Aug20_11-52-47_fb34deda2d26/events.out.tfevents.1724154850.fb34deda2d26.137.0 → Aug21_09-41-51_3a6a8a11d0c1/events.out.tfevents.1724233400.3a6a8a11d0c1.138.0}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6ce5dbb26b1c798781d4170ccbc22de812292b941bce16a5c0d9c3cd2a563d8e
+oid sha256:6c4617f1df51a6e36fb16b2c5baf9b5f0d2a4eeb6f8b41a097abe807ff470b19
 size 6515

train_results.json

@@ -1,9 +1,9 @@
 {
     "epoch": 4.0,
-    "total_flos": 3.55220884094976e+17,
-    "train_loss": 0.017499278579869583,
-    "train_runtime": 3192.4272,
-    "train_samples": 26130,
-    "train_samples_per_second": 32.74,
-    "train_steps_per_second": 16.37
+    "total_flos": 3.8254470258622464e+17,
+    "train_loss": 0.015788240303955946,
+    "train_runtime": 2477.3699,
+    "train_samples": 28140,
+    "train_samples_per_second": 45.435,
+    "train_steps_per_second": 22.718
 }

trainer_state.json

@@ -3,7 +3,7 @@
   "best_model_checkpoint": null,
   "epoch": 4.0,
   "eval_steps": 500,
-  "global_step": 52260,
+  "global_step": 56280,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -78,18 +78,25 @@
       "loss": 0.1762,
       "step": 50000
     },
+    {
+      "epoch": 3.9090262970859984,
+      "grad_norm": 2.2480595111846924,
+      "learning_rate": 2.3447088347896174e-08,
+      "loss": 0.2188,
+      "step": 55000
+    },
     {
       "epoch": 4.0,
-      "step": 52260,
-      "total_flos": 3.55220884094976e+17,
-      "train_loss": 0.017499278579869583,
-      "train_runtime": 3192.4272,
-      "train_samples_per_second": 32.74,
-      "train_steps_per_second": 16.37
+      "step": 56280,
+      "total_flos": 3.8254470258622464e+17,
+      "train_loss": 0.015788240303955946,
+      "train_runtime": 2477.3699,
+      "train_samples_per_second": 45.435,
+      "train_steps_per_second": 22.718
     }
   ],
   "logging_steps": 5000,
-  "max_steps": 52260,
+  "max_steps": 56280,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 4,
   "save_steps": 10000,
@@ -105,7 +112,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.55220884094976e+17,
+  "total_flos": 3.8254470258622464e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null