Upload folder using huggingface_hub

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f4fdaa80279a5e919dc4429dde8012463191cc6d1a982dd3eaddee4af96eb3c
+oid sha256:16080c215e4b00d9d4c530725509ca38c91a2fc3d597eaaee95f9be5142cabf9
 size 544841648

all_results.json

@@ -1,9 +1,9 @@
 {
     "epoch": 4.0,
-    "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
+    "total_flos": 4.2083890061574144e+17,
+    "train_loss": 0.019547846163706376,
+    "train_runtime": 3481.2518,
+    "train_samples": 30954,
+    "train_samples_per_second": 35.567,
+    "train_steps_per_second": 17.783
 }

{checkpoint-56280 → checkpoint-60000}/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f4fdaa80279a5e919dc4429dde8012463191cc6d1a982dd3eaddee4af96eb3c
+oid sha256:fdb8131978b6d0b677d1beb8d9954db0d4c23648922a56c18c355d340e42a66e
 size 544841648

{checkpoint-56280 → checkpoint-60000}/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0837cdf6c98996fe13904f3c067562d53bef89cdf5cd6bfdd6802104ef7652b4
+oid sha256:eff4e303a739fe88c4aff79f94208b42abfb67c67a338f8f79eb9368caa034fa
 size 37990394

{checkpoint-56280 → checkpoint-60000}/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:35f6420e75e12f77b1e05ef197bbd742b0542f9ee8e5cd6c5a49edcc211516a5
+oid sha256:8635a03f2144ebe0ee83cceb2859c7b2f4fea62a8486bcaf70c19a119b1f9457
 size 14244

{checkpoint-56280 → checkpoint-60000}/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:025092508d689d03772052fd1d5943c92acbca0df75ca25e6d77a9b8690adfc8
+oid sha256:f01b464a8c417dce0640b0ecf6efffb7eea74085be43d062534201690c89fa6b
 size 1064

checkpoint-60000/trainer_state.json

@@ -0,0 +1,117 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.8767202946307426,
+  "eval_steps": 500,
+  "global_step": 60000,
+  "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
+    }
+  ],
+  "logging_steps": 5000,
+  "max_steps": 61908,
+  "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": 4.078690148725555e+17,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

{checkpoint-56280 → checkpoint-60000}/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dde3e76c68960f29d8dcd8b585e7fa7dacc620895b260d003b92d999fa18fa8e
+oid sha256:390d0eac7a16c61b5c708efab78a271e240b3582131c2d386df68f6e311469e5
 size 5304

checkpoint-61908/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-61908/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-61908/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16080c215e4b00d9d4c530725509ca38c91a2fc3d597eaaee95f9be5142cabf9
+size 544841648

checkpoint-61908/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e0851c667cf84d8d0e2e92d2a45f291e1df7c03b28dbec830f965651939a4e5
+size 37990394

checkpoint-61908/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:acf2407379b7316d635d65352a31db23979129de27f5ecf0a2893ecb9dbcb58d
+size 14244

checkpoint-61908/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfa2dc300e715c86dd76acf004431e9917f7fdb7d060c87475c0c2bda84b4d52
+size 1064

{checkpoint-56280 → checkpoint-61908}/trainer_state.json

@@ -3,7 +3,7 @@
   "best_model_checkpoint": null,
   "epoch": 4.0,
   "eval_steps": 500,
-  "global_step": 56280,
+  "global_step": 61908,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -84,10 +84,17 @@
       "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
     }
   ],
   "logging_steps": 5000,
-  "max_steps": 56280,
+  "max_steps": 61908,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 4,
   "save_steps": 10000,
@@ -103,7 +110,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.8254470258622464e+17,
+  "total_flos": 4.2083890061574144e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null

checkpoint-61908/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:390d0eac7a16c61b5c708efab78a271e240b3582131c2d386df68f6e311469e5
+size 5304

runs/{Aug21_09-41-51_3a6a8a11d0c1/events.out.tfevents.1724233400.3a6a8a11d0c1.138.0 → Aug21_10-42-57_63410d948620/events.out.tfevents.1724237060.63410d948620.135.0}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6c4617f1df51a6e36fb16b2c5baf9b5f0d2a4eeb6f8b41a097abe807ff470b19
+oid sha256:ee6c367290145e3bc7e228764a6d5be98cb4809340aac59f5124c8e8660fccf1
 size 6515

train_results.json

@@ -1,9 +1,9 @@
 {
     "epoch": 4.0,
-    "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
+    "total_flos": 4.2083890061574144e+17,
+    "train_loss": 0.019547846163706376,
+    "train_runtime": 3481.2518,
+    "train_samples": 30954,
+    "train_samples_per_second": 35.567,
+    "train_steps_per_second": 17.783
 }

trainer_state.json

@@ -3,7 +3,7 @@
   "best_model_checkpoint": null,
   "epoch": 4.0,
   "eval_steps": 500,
-  "global_step": 56280,
+  "global_step": 61908,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -85,18 +85,25 @@
       "loss": 0.2188,
       "step": 55000
     },
+    {
+      "epoch": 3.8767202946307426,
+      "grad_norm": 1.3450602293014526,
+      "learning_rate": 3.177352206494588e-08,
+      "loss": 0.2161,
+      "step": 60000
+    },
     {
       "epoch": 4.0,
-      "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
+      "step": 61908,
+      "total_flos": 4.2083890061574144e+17,
+      "train_loss": 0.019547846163706376,
+      "train_runtime": 3481.2518,
+      "train_samples_per_second": 35.567,
+      "train_steps_per_second": 17.783
     }
   ],
   "logging_steps": 5000,
-  "max_steps": 56280,
+  "max_steps": 61908,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 4,
   "save_steps": 10000,
@@ -112,7 +119,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.8254470258622464e+17,
+  "total_flos": 4.2083890061574144e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null