Upload folder using huggingface_hub

README.md

@@ -1,13 +1,28 @@
 ---
+language:
+- en
 license: other
 base_model: facebook/opt-125m
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - accuracy
 model-index:
 - name: opt-125m-qnli
-  results: []
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: GLUE QNLI
+      type: glue
+      args: qnli
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.8898041369211056
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -15,21 +30,43 @@ should probably proofread and complete it, then remove this comment. -->
 
 # opt-125m-qnli
 
-all results
-
-```json
-{
-    "epoch": 3.0,
-    "eval_accuracy": 0.8914515833790957,
-    "eval_loss": 0.45798125863075256,
-    "eval_runtime": 10.3414,
-    "eval_samples": 5463,
-    "eval_samples_per_second": 528.267,
-    "eval_steps_per_second": 66.045,
-    "train_loss": 0.22705664602662998,
-    "train_runtime": 1659.9582,
-    "train_samples": 104743,
-    "train_samples_per_second": 189.299,
-    "train_steps_per_second": 5.917
-}
-```
+This model is a fine-tuned version of [facebook/opt-125m](https://huggingface.co/facebook/opt-125m) on the GLUE QNLI dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.8470
+- Accuracy: 0.8898
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 2e-05
+- train_batch_size: 16
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 5.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.31.0
+- Pytorch 2.0.1+cu117
+- Datasets 2.18.0
+- Tokenizers 0.13.3

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 5.0,
+    "eval_accuracy": 0.8898041369211056,
+    "eval_loss": 0.8470191359519958,
+    "eval_runtime": 7.6332,
+    "eval_samples": 5463,
+    "eval_samples_per_second": 715.691,
+    "eval_steps_per_second": 89.478,
+    "train_loss": 0.17498792731636295,
+    "train_runtime": 1485.8355,
+    "train_samples": 104743,
+    "train_samples_per_second": 352.472,
+    "train_steps_per_second": 22.031
+}

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "./checkpoints/opt-125m-qnli",
+  "_name_or_path": "facebook/opt-125m",
   "_remove_final_layer_norm": false,
   "activation_dropout": 0.0,
   "activation_function": "relu",

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 5.0,
+    "eval_accuracy": 0.8898041369211056,
+    "eval_loss": 0.8470191359519958,
+    "eval_runtime": 7.6332,
+    "eval_samples": 5463,
+    "eval_samples_per_second": 715.691,
+    "eval_steps_per_second": 89.478
+}

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4411ed8239976be075052de78f2067bae972534060f68d04466efd24f5ced31b
-size 501026977
+oid sha256:f29da52c7d9ba82a7937368c3951711782870caa8dfeaf7977b9bb40c07d404a
+size 501029729

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 5.0,
+    "train_loss": 0.17498792731636295,
+    "train_runtime": 1485.8355,
+    "train_samples": 104743,
+    "train_samples_per_second": 352.472,
+    "train_steps_per_second": 22.031
+}

trainer_state.json

@@ -0,0 +1,415 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 5.0,
+  "global_step": 32735,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.9696960439896138e-05,
+      "loss": 0.5246,
+      "step": 500
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.939147701237208e-05,
+      "loss": 0.4485,
+      "step": 1000
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.9085993584848024e-05,
+      "loss": 0.4207,
+      "step": 1500
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.8781121124179017e-05,
+      "loss": 0.4384,
+      "step": 2000
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.8475637696654957e-05,
+      "loss": 0.3822,
+      "step": 2500
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.81701542691309e-05,
+      "loss": 0.3769,
+      "step": 3000
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 1.7864670841606844e-05,
+      "loss": 0.3714,
+      "step": 3500
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 1.7559187414082787e-05,
+      "loss": 0.3608,
+      "step": 4000
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 1.725370398655873e-05,
+      "loss": 0.3537,
+      "step": 4500
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 1.6948220559034674e-05,
+      "loss": 0.3474,
+      "step": 5000
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.6642737131510617e-05,
+      "loss": 0.3435,
+      "step": 5500
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 1.633725370398656e-05,
+      "loss": 0.3314,
+      "step": 6000
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 1.6031770276462503e-05,
+      "loss": 0.3333,
+      "step": 6500
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 1.5727508782648543e-05,
+      "loss": 0.2464,
+      "step": 7000
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 1.5422025355124486e-05,
+      "loss": 0.2316,
+      "step": 7500
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 1.511654192760043e-05,
+      "loss": 0.2186,
+      "step": 8000
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 1.4811058500076371e-05,
+      "loss": 0.2305,
+      "step": 8500
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 1.4505575072552316e-05,
+      "loss": 0.2255,
+      "step": 9000
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 1.4200091645028258e-05,
+      "loss": 0.2317,
+      "step": 9500
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 1.3894608217504203e-05,
+      "loss": 0.232,
+      "step": 10000
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 1.3589124789980144e-05,
+      "loss": 0.2429,
+      "step": 10500
+    },
+    {
+      "epoch": 1.68,
+      "learning_rate": 1.3283641362456088e-05,
+      "loss": 0.2359,
+      "step": 11000
+    },
+    {
+      "epoch": 1.76,
+      "learning_rate": 1.2978157934932032e-05,
+      "loss": 0.2305,
+      "step": 11500
+    },
+    {
+      "epoch": 1.83,
+      "learning_rate": 1.2672674507407974e-05,
+      "loss": 0.228,
+      "step": 12000
+    },
+    {
+      "epoch": 1.91,
+      "learning_rate": 1.2367191079883917e-05,
+      "loss": 0.2384,
+      "step": 12500
+    },
+    {
+      "epoch": 1.99,
+      "learning_rate": 1.2063540552925004e-05,
+      "loss": 0.2294,
+      "step": 13000
+    },
+    {
+      "epoch": 2.06,
+      "learning_rate": 1.1758057125400948e-05,
+      "loss": 0.1472,
+      "step": 13500
+    },
+    {
+      "epoch": 2.14,
+      "learning_rate": 1.1452573697876892e-05,
+      "loss": 0.1447,
+      "step": 14000
+    },
+    {
+      "epoch": 2.21,
+      "learning_rate": 1.1147090270352833e-05,
+      "loss": 0.1399,
+      "step": 14500
+    },
+    {
+      "epoch": 2.29,
+      "learning_rate": 1.0841606842828778e-05,
+      "loss": 0.138,
+      "step": 15000
+    },
+    {
+      "epoch": 2.37,
+      "learning_rate": 1.0536734382159768e-05,
+      "loss": 0.1519,
+      "step": 15500
+    },
+    {
+      "epoch": 2.44,
+      "learning_rate": 1.0231250954635711e-05,
+      "loss": 0.1533,
+      "step": 16000
+    },
+    {
+      "epoch": 2.52,
+      "learning_rate": 9.925767527111655e-06,
+      "loss": 0.158,
+      "step": 16500
+    },
+    {
+      "epoch": 2.6,
+      "learning_rate": 9.620284099587598e-06,
+      "loss": 0.1571,
+      "step": 17000
+    },
+    {
+      "epoch": 2.67,
+      "learning_rate": 9.314800672063541e-06,
+      "loss": 0.1497,
+      "step": 17500
+    },
+    {
+      "epoch": 2.75,
+      "learning_rate": 9.009317244539484e-06,
+      "loss": 0.1503,
+      "step": 18000
+    },
+    {
+      "epoch": 2.83,
+      "learning_rate": 8.703833817015428e-06,
+      "loss": 0.1616,
+      "step": 18500
+    },
+    {
+      "epoch": 2.9,
+      "learning_rate": 8.398350389491371e-06,
+      "loss": 0.1493,
+      "step": 19000
+    },
+    {
+      "epoch": 2.98,
+      "learning_rate": 8.093477928822362e-06,
+      "loss": 0.1485,
+      "step": 19500
+    },
+    {
+      "epoch": 3.05,
+      "learning_rate": 7.788605468153352e-06,
+      "loss": 0.0928,
+      "step": 20000
+    },
+    {
+      "epoch": 3.13,
+      "learning_rate": 7.483122040629296e-06,
+      "loss": 0.082,
+      "step": 20500
+    },
+    {
+      "epoch": 3.21,
+      "learning_rate": 7.178249579960288e-06,
+      "loss": 0.0805,
+      "step": 21000
+    },
+    {
+      "epoch": 3.28,
+      "learning_rate": 6.872766152436231e-06,
+      "loss": 0.0795,
+      "step": 21500
+    },
+    {
+      "epoch": 3.36,
+      "learning_rate": 6.567282724912174e-06,
+      "loss": 0.0754,
+      "step": 22000
+    },
+    {
+      "epoch": 3.44,
+      "learning_rate": 6.261799297388117e-06,
+      "loss": 0.0726,
+      "step": 22500
+    },
+    {
+      "epoch": 3.51,
+      "learning_rate": 5.95631586986406e-06,
+      "loss": 0.0742,
+      "step": 23000
+    },
+    {
+      "epoch": 3.59,
+      "learning_rate": 5.650832442340004e-06,
+      "loss": 0.0833,
+      "step": 23500
+    },
+    {
+      "epoch": 3.67,
+      "learning_rate": 5.345349014815947e-06,
+      "loss": 0.0761,
+      "step": 24000
+    },
+    {
+      "epoch": 3.74,
+      "learning_rate": 5.03986558729189e-06,
+      "loss": 0.0793,
+      "step": 24500
+    },
+    {
+      "epoch": 3.82,
+      "learning_rate": 4.734382159767833e-06,
+      "loss": 0.086,
+      "step": 25000
+    },
+    {
+      "epoch": 3.89,
+      "learning_rate": 4.428898732243776e-06,
+      "loss": 0.0743,
+      "step": 25500
+    },
+    {
+      "epoch": 3.97,
+      "learning_rate": 4.124026271574768e-06,
+      "loss": 0.0886,
+      "step": 26000
+    },
+    {
+      "epoch": 4.05,
+      "learning_rate": 3.81854284405071e-06,
+      "loss": 0.0454,
+      "step": 26500
+    },
+    {
+      "epoch": 4.12,
+      "learning_rate": 3.5130594165266534e-06,
+      "loss": 0.0271,
+      "step": 27000
+    },
+    {
+      "epoch": 4.2,
+      "learning_rate": 3.2081869558576453e-06,
+      "loss": 0.0328,
+      "step": 27500
+    },
+    {
+      "epoch": 4.28,
+      "learning_rate": 2.902703528333588e-06,
+      "loss": 0.032,
+      "step": 28000
+    },
+    {
+      "epoch": 4.35,
+      "learning_rate": 2.597220100809531e-06,
+      "loss": 0.0292,
+      "step": 28500
+    },
+    {
+      "epoch": 4.43,
+      "learning_rate": 2.2917366732854746e-06,
+      "loss": 0.0254,
+      "step": 29000
+    },
+    {
+      "epoch": 4.51,
+      "learning_rate": 1.9862532457614175e-06,
+      "loss": 0.0333,
+      "step": 29500
+    },
+    {
+      "epoch": 4.58,
+      "learning_rate": 1.6807698182373607e-06,
+      "loss": 0.0251,
+      "step": 30000
+    },
+    {
+      "epoch": 4.66,
+      "learning_rate": 1.375286390713304e-06,
+      "loss": 0.0316,
+      "step": 30500
+    },
+    {
+      "epoch": 4.73,
+      "learning_rate": 1.069802963189247e-06,
+      "loss": 0.022,
+      "step": 31000
+    },
+    {
+      "epoch": 4.81,
+      "learning_rate": 7.643195356651903e-07,
+      "loss": 0.0303,
+      "step": 31500
+    },
+    {
+      "epoch": 4.89,
+      "learning_rate": 4.594470749961815e-07,
+      "loss": 0.0252,
+      "step": 32000
+    },
+    {
+      "epoch": 4.96,
+      "learning_rate": 1.5396364747212466e-07,
+      "loss": 0.0332,
+      "step": 32500
+    },
+    {
+      "epoch": 5.0,
+      "step": 32735,
+      "total_flos": 3.421125693407232e+16,
+      "train_loss": 0.17498792731636295,
+      "train_runtime": 1485.8355,
+      "train_samples_per_second": 352.472,
+      "train_steps_per_second": 22.031
+    }
+  ],
+  "max_steps": 32735,
+  "num_train_epochs": 5,
+  "total_flos": 3.421125693407232e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32dd2d0a95a99deb7524e960f058e61a4bd693bdd404b5c89b2451803b1ce65b
+size 3963