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:ba73d0b6ff0c6e95ca0d641879751d7120f2482f5cac2cde9f5c4e830d08799a
+oid sha256:777be92c024d57eed800fe41145a2cf03e611655a585dc70211b79289bedbeea
 size 544841648

all_results.json

@@ -1,9 +1,9 @@
 {
     "epoch": 4.0,
-    "total_flos": 2.4866224852598784e+17,
-    "train_loss": 0.028278429242836262,
-    "train_runtime": 3203.7786,
-    "train_samples": 18291,
-    "train_samples_per_second": 22.837,
-    "train_steps_per_second": 11.419
+    "total_flos": 2.8417630571495424e+17,
+    "train_loss": 0.023514361843221542,
+    "train_runtime": 3204.5387,
+    "train_samples": 20904,
+    "train_samples_per_second": 26.093,
+    "train_steps_per_second": 13.046
 }

{checkpoint-36584 → checkpoint-40000}/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-36584 → checkpoint-40000}/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba73d0b6ff0c6e95ca0d641879751d7120f2482f5cac2cde9f5c4e830d08799a
+oid sha256:627cba15472ca8277f36b88d2333dc5205ca2de4f188a7125cda4392b68034f4
 size 544841648

{checkpoint-36584 → checkpoint-40000}/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:57bcbbe8f97923b5d84118393ff0e1baa39e477b32d728f67a85fc455c0647b4
+oid sha256:8d176de87dfc31840ccfe406c428a662718065c6c3f19d6ffaf36cb3c3b8b4b0
 size 37990394

{checkpoint-36584 → checkpoint-40000}/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:103bee0ff85c12256490f8b6a3db30e00a8a167d1950b19c24bc508ba48afbfc
+oid sha256:1d71b25f85283f230ffa08c3d781b73e9e197d3bc9ee88d63d025bf024fdfc05
 size 14244

{checkpoint-36584 → checkpoint-40000}/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b12114cfb4c012a87d41b854b98b90ba9555f72060579c6d13a750853ef0c0b
+oid sha256:82ea00907a4ff30a8447b0f013ef4e580baf03980df7a17fca266a73545f4992
 size 1064

checkpoint-40000/trainer_state.json

@@ -0,0 +1,89 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.827018752391887,
+  "eval_steps": 500,
+  "global_step": 40000,
+  "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
+    }
+  ],
+  "logging_steps": 5000,
+  "max_steps": 41808,
+  "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": 2.7187060190969856e+17,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

{checkpoint-36584 → checkpoint-40000}/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a5eefa45d6db9e220a39ae5c1b5dceb275f5f479c5020c91f4267d7a4674828
+oid sha256:ad6ee3e9a803770c7514b8a1baa94e39c48707ea955a5f11b3ad463ca733e8ba
 size 5304

checkpoint-41808/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-41808/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-41808/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:777be92c024d57eed800fe41145a2cf03e611655a585dc70211b79289bedbeea
+size 544841648

checkpoint-41808/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fbe5175d687e769372cec249e2931e803d59d6ac6cf4b74ec92e2e9691244bf5
+size 37990394

checkpoint-41808/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:340f22c16d5e679faefe66fc111ef224cb7b7e91e5b2d0951a46a4961fabe627
+size 14244

checkpoint-41808/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:498bd368172c6bc9e689a6ffcd26fe9653c056dc3ea404b2fcbc3eac9d9ce616
+size 1064

{checkpoint-36584 → checkpoint-41808}/trainer_state.json

@@ -3,7 +3,7 @@
   "best_model_checkpoint": null,
   "epoch": 4.0,
   "eval_steps": 500,
-  "global_step": 36584,
+  "global_step": 41808,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -56,10 +56,17 @@
       "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
     }
   ],
   "logging_steps": 5000,
-  "max_steps": 36584,
+  "max_steps": 41808,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 4,
   "save_steps": 10000,
@@ -75,7 +82,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.4866224852598784e+17,
+  "total_flos": 2.8417630571495424e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null

checkpoint-41808/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad6ee3e9a803770c7514b8a1baa94e39c48707ea955a5f11b3ad463ca733e8ba
+size 5304

runs/{Jul25_11-31-08_5eea225c3324/events.out.tfevents.1721907159.5eea225c3324.138.0 → Jul29_15-14-39_6418d5428a51/events.out.tfevents.1722266164.6418d5428a51.136.0}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:391c21e03e372742fc71946752485872b12578910275430b3e5b311583dfde92
+oid sha256:a1ee3aebdc18826aac9e877a44f73abeaa9b005f99bf100a8e6aca13c17671df
 size 6515

train_results.json

@@ -1,9 +1,9 @@
 {
     "epoch": 4.0,
-    "total_flos": 2.4866224852598784e+17,
-    "train_loss": 0.028278429242836262,
-    "train_runtime": 3203.7786,
-    "train_samples": 18291,
-    "train_samples_per_second": 22.837,
-    "train_steps_per_second": 11.419
+    "total_flos": 2.8417630571495424e+17,
+    "train_loss": 0.023514361843221542,
+    "train_runtime": 3204.5387,
+    "train_samples": 20904,
+    "train_samples_per_second": 26.093,
+    "train_steps_per_second": 13.046
 }

trainer_state.json

@@ -3,7 +3,7 @@
   "best_model_checkpoint": null,
   "epoch": 4.0,
   "eval_steps": 500,
-  "global_step": 36584,
+  "global_step": 41808,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -57,18 +57,25 @@
       "loss": 0.198,
       "step": 35000
     },
+    {
+      "epoch": 3.827018752391887,
+      "grad_norm": 1.933853030204773,
+      "learning_rate": 4.458363129731462e-08,
+      "loss": 0.189,
+      "step": 40000
+    },
     {
       "epoch": 4.0,
-      "step": 36584,
-      "total_flos": 2.4866224852598784e+17,
-      "train_loss": 0.028278429242836262,
-      "train_runtime": 3203.7786,
-      "train_samples_per_second": 22.837,
-      "train_steps_per_second": 11.419
+      "step": 41808,
+      "total_flos": 2.8417630571495424e+17,
+      "train_loss": 0.023514361843221542,
+      "train_runtime": 3204.5387,
+      "train_samples_per_second": 26.093,
+      "train_steps_per_second": 13.046
     }
   ],
   "logging_steps": 5000,
-  "max_steps": 36584,
+  "max_steps": 41808,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 4,
   "save_steps": 10000,
@@ -84,7 +91,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.4866224852598784e+17,
+  "total_flos": 2.8417630571495424e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null