Upload folder using huggingface_hub

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c8cb1b7f478b3f1162c568eaacec794bbbda87c97dc7ecbd0b0bb55b88beafa
+oid sha256:ae0c989272aa37bed5660992a27bd0e38b617286a2c0299f319ffd11aef67794
 size 544841648

all_results.json

@@ -1,9 +1,9 @@
 {
     "epoch": 4.0,
-    "total_flos": 3.551619884777472e+16,
-    "train_loss": 0.8017316247637981,
-    "train_runtime": 3199.5912,
-    "train_samples": 2613,
-    "train_samples_per_second": 3.267,
-    "train_steps_per_second": 1.634
+    "total_flos": 7.103373623230464e+16,
+    "train_loss": 0.2151433927913393,
+    "train_runtime": 3218.1394,
+    "train_samples": 5226,
+    "train_samples_per_second": 6.496,
+    "train_steps_per_second": 3.248
 }

{checkpoint-5228 → checkpoint-10000}/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c8cb1b7f478b3f1162c568eaacec794bbbda87c97dc7ecbd0b0bb55b88beafa
+oid sha256:45828f14be9ac7523ce0bc1b95385f54d531b4c00a2a85a310e0f00a7ae81b01
 size 544841648

{checkpoint-5228 → checkpoint-10000}/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e41d07b183736dec3fc6e5734e5d74642afbf3d67ec6ff6186a518dd0c158901
+oid sha256:e44fd1346a37f7cdd4848cac7b600ed550dba658d7bb3d8a319c1f0538138552
 size 37990394

{checkpoint-5228 → checkpoint-10000}/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:213c91bf46374887cf60c732956b5f92721324cb72eaf839c3b0d66538a580fe
+oid sha256:b6b22f5b2dc5369bacb74c77bbb11c57b3a66753f22304f838d4dd48930aed14
 size 14244

{checkpoint-5228 → checkpoint-10000}/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37674dec2d637bf9ef2346da110360c6c5b445fd074c64bf85ac1e369e26a3b1
+oid sha256:dbb27ee9f8deedbb9f17877c517210fec0d518e49c6f94e4473dcc8883e0b96b
 size 1064

checkpoint-10000/trainer_state.json

@@ -0,0 +1,47 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.827018752391887,
+  "eval_steps": 500,
+  "global_step": 10000,
+  "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
+    }
+  ],
+  "logging_steps": 5000,
+  "max_steps": 10452,
+  "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": 6.794707047481344e+16,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

{checkpoint-5228 → checkpoint-10000}/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:671f3882fdd89ec2cc5a4733cc312f920ed86868f5d84b24db44883bb2204031
+oid sha256:7e974b2b98eb93b0874e1a116adbb45ebb9f8f05551aececac46178c302244cf
 size 5304

checkpoint-10452/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-10452/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-10452/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae0c989272aa37bed5660992a27bd0e38b617286a2c0299f319ffd11aef67794
+size 544841648

checkpoint-10452/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4782517fc1a6fbcaeaee6f03a113ade8f5f2bd361d9bc295a912a489c47f0334
+size 37990394

checkpoint-10452/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8b8dac94b38b5124bb16e5fcea9b04fe79d64bb02a51e89c88f2817a3d5c719
+size 14244

runs/Jul19_11-51-39_c765cd0652b2/events.out.tfevents.1721390065.c765cd0652b2.134.0 → checkpoint-10452/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9939a3d11f2186280e1ffefd373fab7482488f4a536493ac2550346d86d8f87e
-size 6502
+oid sha256:0667ef615a914683037d5639ac8bbf8788bd85b34be4a62bd8291801d602dbe5
+size 1064

{checkpoint-5228 → checkpoint-10452}/trainer_state.json

@@ -3,7 +3,7 @@
   "best_model_checkpoint": null,
   "epoch": 4.0,
   "eval_steps": 500,
-  "global_step": 5228,
+  "global_step": 10452,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -14,10 +14,17 @@
       "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
     }
   ],
   "logging_steps": 5000,
-  "max_steps": 5228,
+  "max_steps": 10452,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 4,
   "save_steps": 10000,
@@ -33,7 +40,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.551619884777472e+16,
+  "total_flos": 7.103373623230464e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null

checkpoint-10452/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e974b2b98eb93b0874e1a116adbb45ebb9f8f05551aececac46178c302244cf
+size 5304

runs/Jul20_11-25-38_163758744bce/events.out.tfevents.1721474814.163758744bce.137.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f9cca22ef38de8a48c64a9ab2225be8325e0897f89461c4d3091162092b664d
+size 6504

train_results.json

@@ -1,9 +1,9 @@
 {
     "epoch": 4.0,
-    "total_flos": 3.551619884777472e+16,
-    "train_loss": 0.8017316247637981,
-    "train_runtime": 3199.5912,
-    "train_samples": 2613,
-    "train_samples_per_second": 3.267,
-    "train_steps_per_second": 1.634
+    "total_flos": 7.103373623230464e+16,
+    "train_loss": 0.2151433927913393,
+    "train_runtime": 3218.1394,
+    "train_samples": 5226,
+    "train_samples_per_second": 6.496,
+    "train_steps_per_second": 3.248
 }

trainer_state.json

@@ -3,7 +3,7 @@
   "best_model_checkpoint": null,
   "epoch": 4.0,
   "eval_steps": 500,
-  "global_step": 5228,
+  "global_step": 10452,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -15,18 +15,25 @@
       "loss": 0.8176,
       "step": 5000
     },
+    {
+      "epoch": 3.827018752391887,
+      "grad_norm": 1.769223928451538,
+      "learning_rate": 4.458473071611758e-08,
+      "loss": 0.4356,
+      "step": 10000
+    },
     {
       "epoch": 4.0,
-      "step": 5228,
-      "total_flos": 3.551619884777472e+16,
-      "train_loss": 0.8017316247637981,
-      "train_runtime": 3199.5912,
-      "train_samples_per_second": 3.267,
-      "train_steps_per_second": 1.634
+      "step": 10452,
+      "total_flos": 7.103373623230464e+16,
+      "train_loss": 0.2151433927913393,
+      "train_runtime": 3218.1394,
+      "train_samples_per_second": 6.496,
+      "train_steps_per_second": 3.248
     }
   ],
   "logging_steps": 5000,
-  "max_steps": 5228,
+  "max_steps": 10452,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 4,
   "save_steps": 10000,
@@ -42,7 +49,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.551619884777472e+16,
+  "total_flos": 7.103373623230464e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null