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 sha256:1c8cb1b7f478b3f1162c568eaacec794bbbda87c97dc7ecbd0b0bb55b88beafa
+oid sha256:be94a4f0f91667bca6db4128038f7aef8c95cf882def6649f583e59bc60e1197
 size 544841648

all_results.json

@@ -1,9 +1,9 @@
 {
     "epoch": 4.0,
-    "total_flos": 3.551619884777472e+16,
-    "train_loss": 0.801731087729141,
-    "train_runtime": 3202.2645,
-    "train_samples": 2613,
-    "train_samples_per_second": 3.264,
-    "train_steps_per_second": 1.633
+    "total_flos": 176151436984320.0,
+    "train_loss": 1.4319358553205217,
+    "train_runtime": 18.5979,
+    "train_samples": 13,
+    "train_samples_per_second": 2.796,
+    "train_steps_per_second": 1.506
 }

{checkpoint-5000 → checkpoint-28}/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-5228 → checkpoint-28}/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c8cb1b7f478b3f1162c568eaacec794bbbda87c97dc7ecbd0b0bb55b88beafa
+oid sha256:be94a4f0f91667bca6db4128038f7aef8c95cf882def6649f583e59bc60e1197
 size 544841648

{checkpoint-5228 → checkpoint-28}/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e41d07b183736dec3fc6e5734e5d74642afbf3d67ec6ff6186a518dd0c158901
+oid sha256:237484bf2ac3f65aafcb20b5743bf6bd3c1c1319966528a7bb64e50db8fa0b9e
 size 37990394

{checkpoint-5228 → checkpoint-28}/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:213c91bf46374887cf60c732956b5f92721324cb72eaf839c3b0d66538a580fe
+oid sha256:ec7e2b5a6196fca337c8bbaa2e63ce336abdbdbf731991872374ab9a46a8bc68
 size 14244

{checkpoint-5000 → checkpoint-28}/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a1ba951a3f17b4ac4b60e9325a788bb9a7a7e583fa728251aa238398c6dc66d
+oid sha256:b4ca939c39349627ebbc4f461efada993c34387eeab65975e53a7d0b481e126f
 size 1064

{checkpoint-5228 → checkpoint-28}/trainer_state.json

@@ -3,52 +3,16 @@
   "best_model_checkpoint": null,
   "epoch": 4.0,
   "eval_steps": 500,
-  "global_step": 5228,
+  "global_step": 28,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
-  "log_history": [
-    {
-      "epoch": 0.7651109410864575,
-      "grad_norm": 2.158221483230591,
-      "learning_rate": 8.337605994872807e-07,
-      "loss": 1.2573,
-      "step": 1000
-    },
-    {
-      "epoch": 1.5302218821729152,
-      "grad_norm": 2.2398524284362793,
-      "learning_rate": 6.365608361269966e-07,
-      "loss": 0.9101,
-      "step": 2000
-    },
-    {
-      "epoch": 2.295332823259373,
-      "grad_norm": 1.444738507270813,
-      "learning_rate": 4.3936107276671263e-07,
-      "loss": 0.7317,
-      "step": 3000
-    },
-    {
-      "epoch": 3.06044376434583,
-      "grad_norm": 1.4855622053146362,
-      "learning_rate": 2.421613094064287e-07,
-      "loss": 0.6212,
-      "step": 4000
-    },
-    {
-      "epoch": 3.8255547054322876,
-      "grad_norm": 2.0333640575408936,
-      "learning_rate": 4.4961546046144744e-08,
-      "loss": 0.5799,
-      "step": 5000
-    }
-  ],
-  "logging_steps": 1000,
-  "max_steps": 5228,
+  "log_history": [],
+  "logging_steps": 5000,
+  "max_steps": 28,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 4,
-  "save_steps": 1000,
+  "save_steps": 10000,
   "stateful_callbacks": {
     "TrainerControl": {
       "args": {
@@ -61,7 +25,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.551619884777472e+16,
+  "total_flos": 176151436984320.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null

{checkpoint-5000 → checkpoint-28}/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c44cd3c0bbdfd294377644249b74e963378130fe594b1ff91d44e99290e66b88
+oid sha256:274b9f1a1ad8e1eb1c51caa0738e6220891d47ad84b6cd90ffe695266d18b3e4
 size 5304

checkpoint-5000/adapter_model.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:e4c0d2cef7b01e2e2fcbc0316985aaaaf01f8b97395668c749895c501518a449
-size 544841648

checkpoint-5000/optimizer.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:44a6ef226fa286221fc3f72b2fb8aebe7e62cf574f7a3044f631f07b526711c2
-size 37990394

checkpoint-5000/rng_state.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:ee3d3cf2c902e0610827e446108ac632ab9869a70055760c6c41bf09f33c25c1
-size 14244

checkpoint-5000/trainer_state.json

@@ -1,68 +0,0 @@
-{
-  "best_metric": null,
-  "best_model_checkpoint": null,
-  "epoch": 3.8255547054322876,
-  "eval_steps": 500,
-  "global_step": 5000,
-  "is_hyper_param_search": false,
-  "is_local_process_zero": true,
-  "is_world_process_zero": true,
-  "log_history": [
-    {
-      "epoch": 0.7651109410864575,
-      "grad_norm": 2.158221483230591,
-      "learning_rate": 8.337605994872807e-07,
-      "loss": 1.2573,
-      "step": 1000
-    },
-    {
-      "epoch": 1.5302218821729152,
-      "grad_norm": 2.2398524284362793,
-      "learning_rate": 6.365608361269966e-07,
-      "loss": 0.9101,
-      "step": 2000
-    },
-    {
-      "epoch": 2.295332823259373,
-      "grad_norm": 1.444738507270813,
-      "learning_rate": 4.3936107276671263e-07,
-      "loss": 0.7317,
-      "step": 3000
-    },
-    {
-      "epoch": 3.06044376434583,
-      "grad_norm": 1.4855622053146362,
-      "learning_rate": 2.421613094064287e-07,
-      "loss": 0.6212,
-      "step": 4000
-    },
-    {
-      "epoch": 3.8255547054322876,
-      "grad_norm": 2.0333640575408936,
-      "learning_rate": 4.4961546046144744e-08,
-      "loss": 0.5799,
-      "step": 5000
-    }
-  ],
-  "logging_steps": 1000,
-  "max_steps": 5228,
-  "num_input_tokens_seen": 0,
-  "num_train_epochs": 4,
-  "save_steps": 1000,
-  "stateful_callbacks": {
-    "TrainerControl": {
-      "args": {
-        "should_epoch_stop": false,
-        "should_evaluate": false,
-        "should_log": false,
-        "should_save": true,
-        "should_training_stop": false
-      },
-      "attributes": {}
-    }
-  },
-  "total_flos": 3.397166128594944e+16,
-  "train_batch_size": 2,
-  "trial_name": null,
-  "trial_params": null
-}

checkpoint-5228/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-5228/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-5228/training_args.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:c44cd3c0bbdfd294377644249b74e963378130fe594b1ff91d44e99290e66b88
-size 5304

runs/Jul19_10-44-41_6a32a2c667bd/events.out.tfevents.1721385983.6a32a2c667bd.133.0

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:438b32ebc9b059995af8b3cb3383a85f32b1f44aa052ed7cecbbf564f4cffeff
-size 7345

checkpoint-5228/scheduler.pt → runs/Jul19_11-45-36_1ab95903c376/events.out.tfevents.1721389670.1ab95903c376.208.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37674dec2d637bf9ef2346da110360c6c5b445fd074c64bf85ac1e369e26a3b1
-size 1064
+oid sha256:a895b106a2a1eebd44881060ebf6de87cba33f6e75fbc4af07ccbf6757b4ac02
+size 6254

train_results.json

@@ -1,9 +1,9 @@
 {
     "epoch": 4.0,
-    "total_flos": 3.551619884777472e+16,
-    "train_loss": 0.801731087729141,
-    "train_runtime": 3202.2645,
-    "train_samples": 2613,
-    "train_samples_per_second": 3.264,
-    "train_steps_per_second": 1.633
+    "total_flos": 176151436984320.0,
+    "train_loss": 1.4319358553205217,
+    "train_runtime": 18.5979,
+    "train_samples": 13,
+    "train_samples_per_second": 2.796,
+    "train_steps_per_second": 1.506
 }

trainer_state.json

@@ -3,61 +3,26 @@
   "best_model_checkpoint": null,
   "epoch": 4.0,
   "eval_steps": 500,
-  "global_step": 5228,
+  "global_step": 28,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
-    {
-      "epoch": 0.7651109410864575,
-      "grad_norm": 2.158221483230591,
-      "learning_rate": 8.337605994872807e-07,
-      "loss": 1.2573,
-      "step": 1000
-    },
-    {
-      "epoch": 1.5302218821729152,
-      "grad_norm": 2.2398524284362793,
-      "learning_rate": 6.365608361269966e-07,
-      "loss": 0.9101,
-      "step": 2000
-    },
-    {
-      "epoch": 2.295332823259373,
-      "grad_norm": 1.444738507270813,
-      "learning_rate": 4.3936107276671263e-07,
-      "loss": 0.7317,
-      "step": 3000
-    },
-    {
-      "epoch": 3.06044376434583,
-      "grad_norm": 1.4855622053146362,
-      "learning_rate": 2.421613094064287e-07,
-      "loss": 0.6212,
-      "step": 4000
-    },
-    {
-      "epoch": 3.8255547054322876,
-      "grad_norm": 2.0333640575408936,
-      "learning_rate": 4.4961546046144744e-08,
-      "loss": 0.5799,
-      "step": 5000
-    },
     {
       "epoch": 4.0,
-      "step": 5228,
-      "total_flos": 3.551619884777472e+16,
-      "train_loss": 0.801731087729141,
-      "train_runtime": 3202.2645,
-      "train_samples_per_second": 3.264,
-      "train_steps_per_second": 1.633
+      "step": 28,
+      "total_flos": 176151436984320.0,
+      "train_loss": 1.4319358553205217,
+      "train_runtime": 18.5979,
+      "train_samples_per_second": 2.796,
+      "train_steps_per_second": 1.506
     }
   ],
-  "logging_steps": 1000,
-  "max_steps": 5228,
+  "logging_steps": 5000,
+  "max_steps": 28,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 4,
-  "save_steps": 1000,
+  "save_steps": 10000,
   "stateful_callbacks": {
     "TrainerControl": {
       "args": {
@@ -70,7 +35,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.551619884777472e+16,
+  "total_flos": 176151436984320.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null