Upload folder using huggingface_hub

adapter_config.json

@@ -19,8 +19,8 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v",
-    "q"
+    "q",
+    "v"
   ],
   "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:e3be45dd8abc317aa8ff42b741eacb0123a5a033565afc07df2902fc2fa6ac99
+oid sha256:466bf124f9b1c991c876134a7bfd74d3f4ce4e0dd047e6733995c13db93a8d0f
 size 544841648

all_results.json

@@ -1,9 +1,9 @@
 {
     "epoch": 4.0,
-    "total_flos": 6.122186025566208e+17,
-    "train_loss": 0.014308358761716922,
-    "train_runtime": 3508.7748,
-    "train_samples": 45024,
-    "train_samples_per_second": 51.327,
-    "train_steps_per_second": 25.664
+    "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
 }

checkpoint-90000/adapter_model.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:66b03970b4a4588f9354c7cabad09a8483153ab5a2d5a7d29d1d51e614b77d7b
-size 544841648

checkpoint-90000/optimizer.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:bddae352015f21a80238c1a005fe12ae1d4b252ddd5e73c74e47209d4cfa7c62
-size 37990394

checkpoint-90000/rng_state.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:b96f8aabcfbcf630b4fef16f9d4efd81d1b5f285c31f369efd74dac1c348151e
-size 14244

checkpoint-90000/trainer_state.json

@@ -1,159 +0,0 @@
-{
-  "best_metric": null,
-  "best_model_checkpoint": null,
-  "epoch": 3.997867803837953,
-  "eval_steps": 500,
-  "global_step": 90000,
-  "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
-    }
-  ],
-  "logging_steps": 5000,
-  "max_steps": 90048,
-  "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": 6.118928027104051e+17,
-  "train_batch_size": 2,
-  "trial_name": null,
-  "trial_params": null
-}

checkpoint-90048/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-90048/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": [
-    "v",
-    "q"
-  ],
-  "task_type": "SEQ_2_SEQ_LM",
-  "use_dora": false,
-  "use_rslora": false
-}

checkpoint-90048/training_args.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:c8850b67ca01c3d55bcc6cb9e8a159f8cd518e7d06e5ed57488631e3b20371c1
-size 5304

{checkpoint-90000 → checkpoint-95676}/adapter_config.json

@@ -19,8 +19,8 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v",
-    "q"
+    "q",
+    "v"
   ],
   "task_type": "SEQ_2_SEQ_LM",
   "use_dora": false,

{checkpoint-90048 → checkpoint-95676}/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e3be45dd8abc317aa8ff42b741eacb0123a5a033565afc07df2902fc2fa6ac99
+oid sha256:466bf124f9b1c991c876134a7bfd74d3f4ce4e0dd047e6733995c13db93a8d0f
 size 544841648

{checkpoint-90048 → checkpoint-95676}/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3fa274fdb5443fa874d07e8b7b7183f18c593b74948bb080f070ebd1a729132c
+oid sha256:2190d93ffe97cdeab9dfd18cc5e755c33b576c75b37b4b14e0d90c3fb22a5b67
 size 37990394

{checkpoint-90048 → checkpoint-95676}/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:af3ef4d1229a3b36c3dd98bab713467d96bfe6c249371f1d34215d944404fc98
+oid sha256:6f1efd4d66a6b77b6a4fc2146d55bb7c2e5453fb2964197d291c271a73c7f201
 size 14244

{checkpoint-90000 → checkpoint-95676}/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:77b3234a42852c71493edd1a2525bc22131d98673e22ca240a357585f56973d1
+oid sha256:e6fcbdc36181bf92f5ee951e4e035bbfbe3b485bab5084267a313dd978bfdecd
 size 1064

{checkpoint-90048 → checkpoint-95676}/trainer_state.json

@@ -3,7 +3,7 @@
   "best_model_checkpoint": null,
   "epoch": 4.0,
   "eval_steps": 500,
-  "global_step": 90048,
+  "global_step": 95676,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -133,10 +133,17 @@
       "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
     }
   ],
   "logging_steps": 5000,
-  "max_steps": 90048,
+  "max_steps": 95676,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 4,
   "save_steps": 10000,
@@ -152,7 +159,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.122186025566208e+17,
+  "total_flos": 6.504777309231514e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null

{checkpoint-90000 → checkpoint-95676}/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c8850b67ca01c3d55bcc6cb9e8a159f8cd518e7d06e5ed57488631e3b20371c1
+oid sha256:aabc9cde5393ac30348fe7846fdbc1b2992bb5de6f1517ff78f1b18a9b9212af
 size 5304

runs/Aug22_12-59-48_de49dc81e364/events.out.tfevents.1724331920.de49dc81e364.137.0

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:417691d8b6d839eaf6c69e6cfc073a71786487286acd53d60695b11eb4211865
-size 6730

checkpoint-90048/scheduler.pt → runs/Aug22_14-13-43_77cb6af8ff2a/events.out.tfevents.1724336125.77cb6af8ff2a.137.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:56419b7d299481241cd162d532f3e5433f41e7df33d63974fb9ac66135687bd7
-size 1064
+oid sha256:681508b636b5f66eaec5b5341a1f258fead8b03447c5ddf608c98125cc75ca51
+size 6515

train_results.json

@@ -1,9 +1,9 @@
 {
     "epoch": 4.0,
-    "total_flos": 6.122186025566208e+17,
-    "train_loss": 0.014308358761716922,
-    "train_runtime": 3508.7748,
-    "train_samples": 45024,
-    "train_samples_per_second": 51.327,
-    "train_steps_per_second": 25.664
+    "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
 }

trainer_state.json

@@ -3,7 +3,7 @@
   "best_model_checkpoint": null,
   "epoch": 4.0,
   "eval_steps": 500,
-  "global_step": 90048,
+  "global_step": 95676,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -134,18 +134,25 @@
       "loss": 0.2282,
       "step": 90000
     },
+    {
+      "epoch": 3.9717379489109077,
+      "grad_norm": 1.6769729852676392,
+      "learning_rate": 7.284090296859005e-09,
+      "loss": 0.2206,
+      "step": 95000
+    },
     {
       "epoch": 4.0,
-      "step": 90048,
-      "total_flos": 6.122186025566208e+17,
-      "train_loss": 0.014308358761716922,
-      "train_runtime": 3508.7748,
-      "train_samples_per_second": 51.327,
-      "train_steps_per_second": 25.664
+      "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
     }
   ],
   "logging_steps": 5000,
-  "max_steps": 90048,
+  "max_steps": 95676,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 4,
   "save_steps": 10000,
@@ -161,7 +168,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.122186025566208e+17,
+  "total_flos": 6.504777309231514e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null