Upload folder using huggingface_hub

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:466bf124f9b1c991c876134a7bfd74d3f4ce4e0dd047e6733995c13db93a8d0f
+oid sha256:dc1be0342fdcae1afa6818332380b9151c2d3449cf64bcda2c40b075aecb1c61
 size 544841648

all_results.json

@@ -1,9 +1,9 @@
 {
     "epoch": 4.0,
-    "total_flos": 6.504777309231514e+17,
-    "train_loss": 0.01301118949667816,
-    "train_runtime": 3469.6701,
-    "train_samples": 47838,
-    "train_samples_per_second": 55.15,
-    "train_steps_per_second": 27.575
+    "total_flos": 6.887547956822016e+17,
+    "train_loss": 0.01211053775515327,
+    "train_runtime": 3481.9111,
+    "train_samples": 50652,
+    "train_samples_per_second": 58.189,
+    "train_steps_per_second": 29.094
 }

{checkpoint-95676 → checkpoint-100000}/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:466bf124f9b1c991c876134a7bfd74d3f4ce4e0dd047e6733995c13db93a8d0f
+oid sha256:6a62f420fd99d3a2f45d35b38ceb0f322e57b7fdb3a5bff84e1ddf78f42a110f
 size 544841648

{checkpoint-95676 → checkpoint-100000}/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2190d93ffe97cdeab9dfd18cc5e755c33b576c75b37b4b14e0d90c3fb22a5b67
+oid sha256:a4f062394675a149fef90f2bd952248db6a9084701f5c8c7a12984b1c91010d5
 size 37990394

{checkpoint-95676 → checkpoint-100000}/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f1efd4d66a6b77b6a4fc2146d55bb7c2e5453fb2964197d291c271a73c7f201
+oid sha256:d3e0f311f72a1d66f22a5864dbb5ebbd5af29045d9e788168dc0716478759bc3
 size 14244

{checkpoint-95676 → checkpoint-100000}/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e6fcbdc36181bf92f5ee951e4e035bbfbe3b485bab5084267a313dd978bfdecd
+oid sha256:f8c9db79181d25e998519ee75c5a93ecf424b2747b05d5e05664b164d76f758a
 size 1064

checkpoint-100000/trainer_state.json

@@ -0,0 +1,173 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.948511411197978,
+  "eval_steps": 500,
+  "global_step": 100000,
+  "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
+    },
+    {
+      "epoch": 3.775764036958067,
+      "grad_norm": 2.4036500453948975,
+      "learning_rate": 5.77931445057587e-08,
+      "loss": 0.2354,
+      "step": 85000
+    },
+    {
+      "epoch": 3.997867803837953,
+      "grad_norm": 3.1487817764282227,
+      "learning_rate": 5.495386165365328e-10,
+      "loss": 0.2282,
+      "step": 90000
+    },
+    {
+      "epoch": 3.9717379489109077,
+      "grad_norm": 1.6769729852676392,
+      "learning_rate": 7.284090296859005e-09,
+      "loss": 0.2206,
+      "step": 95000
+    },
+    {
+      "epoch": 3.948511411197978,
+      "grad_norm": 1.3110090494155884,
+      "learning_rate": 1.3270373687209964e-08,
+      "loss": 0.2192,
+      "step": 100000
+    }
+  ],
+  "logging_steps": 5000,
+  "max_steps": 101304,
+  "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": 6.798778876290662e+17,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

{checkpoint-95676 → checkpoint-100000}/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aabc9cde5393ac30348fe7846fdbc1b2992bb5de6f1517ff78f1b18a9b9212af
+oid sha256:7bbe82e8282ac13b2b815601000df47cb98039e766dae69289ea8434ee2aec22
 size 5304

checkpoint-101304/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-101304/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": [
+    "q",
+    "v"
+  ],
+  "task_type": "SEQ_2_SEQ_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-101304/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc1be0342fdcae1afa6818332380b9151c2d3449cf64bcda2c40b075aecb1c61
+size 544841648

checkpoint-101304/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db02e67f41af07ecf9f4f9d209a02a02917fb8c5b19a546272d824ae3599d1d7
+size 37990394

checkpoint-101304/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:483df6c145bfaac8dc5aef51b3fae88915bf24e0f4badc89f7ac878efd346d30
+size 14244

checkpoint-101304/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0c8e75289bb354829142f17d2a239b40d81b328c1e57d81dc726ad262780a5f
+size 1064

{checkpoint-95676 → checkpoint-101304}/trainer_state.json

@@ -3,7 +3,7 @@
   "best_model_checkpoint": null,
   "epoch": 4.0,
   "eval_steps": 500,
-  "global_step": 95676,
+  "global_step": 101304,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -140,10 +140,17 @@
       "learning_rate": 7.284090296859005e-09,
       "loss": 0.2206,
       "step": 95000
+    },
+    {
+      "epoch": 3.948511411197978,
+      "grad_norm": 1.3110090494155884,
+      "learning_rate": 1.3270373687209964e-08,
+      "loss": 0.2192,
+      "step": 100000
     }
   ],
   "logging_steps": 5000,
-  "max_steps": 95676,
+  "max_steps": 101304,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 4,
   "save_steps": 10000,
@@ -159,7 +166,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.504777309231514e+17,
+  "total_flos": 6.887547956822016e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null

checkpoint-101304/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7bbe82e8282ac13b2b815601000df47cb98039e766dae69289ea8434ee2aec22
+size 5304

runs/{Aug22_14-13-43_77cb6af8ff2a/events.out.tfevents.1724336125.77cb6af8ff2a.137.0 → Aug22_15-56-17_fe884c7af436/events.out.tfevents.1724342271.fe884c7af436.137.0}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:681508b636b5f66eaec5b5341a1f258fead8b03447c5ddf608c98125cc75ca51
+oid sha256:8904ea0d365437d29be822cbd7cacc7539ef7036a58b89fe22a782c0444eebb7
 size 6515

train_results.json

@@ -1,9 +1,9 @@
 {
     "epoch": 4.0,
-    "total_flos": 6.504777309231514e+17,
-    "train_loss": 0.01301118949667816,
-    "train_runtime": 3469.6701,
-    "train_samples": 47838,
-    "train_samples_per_second": 55.15,
-    "train_steps_per_second": 27.575
+    "total_flos": 6.887547956822016e+17,
+    "train_loss": 0.01211053775515327,
+    "train_runtime": 3481.9111,
+    "train_samples": 50652,
+    "train_samples_per_second": 58.189,
+    "train_steps_per_second": 29.094
 }

trainer_state.json

@@ -3,7 +3,7 @@
   "best_model_checkpoint": null,
   "epoch": 4.0,
   "eval_steps": 500,
-  "global_step": 95676,
+  "global_step": 101304,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -141,18 +141,25 @@
       "loss": 0.2206,
       "step": 95000
     },
+    {
+      "epoch": 3.948511411197978,
+      "grad_norm": 1.3110090494155884,
+      "learning_rate": 1.3270373687209964e-08,
+      "loss": 0.2192,
+      "step": 100000
+    },
     {
       "epoch": 4.0,
-      "step": 95676,
-      "total_flos": 6.504777309231514e+17,
-      "train_loss": 0.01301118949667816,
-      "train_runtime": 3469.6701,
-      "train_samples_per_second": 55.15,
-      "train_steps_per_second": 27.575
+      "step": 101304,
+      "total_flos": 6.887547956822016e+17,
+      "train_loss": 0.01211053775515327,
+      "train_runtime": 3481.9111,
+      "train_samples_per_second": 58.189,
+      "train_steps_per_second": 29.094
     }
   ],
   "logging_steps": 5000,
-  "max_steps": 95676,
+  "max_steps": 101304,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 4,
   "save_steps": 10000,
@@ -168,7 +175,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.504777309231514e+17,
+  "total_flos": 6.887547956822016e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null