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-rte
-  results: []
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: GLUE RTE
+      type: glue
+      args: rte
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.6425992779783394
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -15,10 +30,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # opt-125m-rte
 
-This model is a fine-tuned version of [facebook/opt-125m](https://huggingface.co/facebook/opt-125m) on an unknown dataset.
+This model is a fine-tuned version of [facebook/opt-125m](https://huggingface.co/facebook/opt-125m) on the GLUE RTE dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.7647
-- Accuracy: 0.6354
+- Loss: 3.2055
+- Accuracy: 0.6426
 
 ## Model description
 
@@ -37,24 +52,16 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 5e-05
-- train_batch_size: 16
-- eval_batch_size: 32
+- learning_rate: 2e-05
+- train_batch_size: 8
+- eval_batch_size: 8
 - seed: 42
-- gradient_accumulation_steps: 8
-- total_train_batch_size: 128
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 4
+- num_epochs: 5.0
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | Accuracy |
-|:-------------:|:-----:|:----:|:---------------:|:--------:|
-| No log        | 0.97  | 19   | 0.6622          | 0.6462   |
-| No log        | 2.0   | 39   | 0.6257          | 0.6390   |
-| No log        | 2.97  | 58   | 0.7573          | 0.6354   |
-| No log        | 3.9   | 76   | 0.7647          | 0.6354   |
 
 
 ### Framework versions

all_results.json

@@ -1,14 +1,14 @@
 {
-    "epoch": 3.9,
-    "eval_accuracy": 0.6353790613718412,
-    "eval_loss": 0.764682948589325,
-    "eval_runtime": 0.9007,
+    "epoch": 5.0,
+    "eval_accuracy": 0.6425992779783394,
+    "eval_loss": 3.205474376678467,
+    "eval_runtime": 0.5373,
     "eval_samples": 277,
-    "eval_samples_per_second": 307.546,
-    "eval_steps_per_second": 9.992,
-    "train_loss": 0.5004565590306332,
-    "train_runtime": 76.0596,
+    "eval_samples_per_second": 515.583,
+    "eval_steps_per_second": 65.146,
+    "train_loss": 0.3344010169689472,
+    "train_runtime": 98.9629,
     "train_samples": 2490,
-    "train_samples_per_second": 130.95,
-    "train_steps_per_second": 0.999
+    "train_samples_per_second": 125.805,
+    "train_steps_per_second": 15.763
 }

config.json

@@ -13,16 +13,16 @@
   "enable_bias": true,
   "eos_token_id": 2,
   "ffn_dim": 3072,
-  "finetuning_task": "text-classification",
+  "finetuning_task": "rte",
   "hidden_size": 768,
   "id2label": {
-    "0": "0",
-    "1": "1"
+    "0": "entailment",
+    "1": "not_entailment"
   },
   "init_std": 0.02,
   "label2id": {
-    "0": 0,
-    "1": 1
+    "entailment": 0,
+    "not_entailment": 1
   },
   "layer_norm_elementwise_affine": true,
   "layerdrop": 0.0,

eval_results.json

@@ -1,9 +1,9 @@
 {
-    "epoch": 3.9,
-    "eval_accuracy": 0.6353790613718412,
-    "eval_loss": 0.764682948589325,
-    "eval_runtime": 0.9007,
+    "epoch": 5.0,
+    "eval_accuracy": 0.6425992779783394,
+    "eval_loss": 3.205474376678467,
+    "eval_runtime": 0.5373,
     "eval_samples": 277,
-    "eval_samples_per_second": 307.546,
-    "eval_steps_per_second": 9.992
+    "eval_samples_per_second": 515.583,
+    "eval_steps_per_second": 65.146
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b82d4ef6934c862a4c85f3972c435695856da58933d1eab159f2e7ed760907a
+oid sha256:8cb641be82ca0f1ccfb4f61fe42542d9659f201169ff773b587f2a936c8dfb1a
 size 501029729

tokenizer.json

@@ -2,13 +2,13 @@
   "version": "1.0",
   "truncation": {
     "direction": "Right",
-    "max_length": 512,
+    "max_length": 128,
     "strategy": "LongestFirst",
     "stride": 0
   },
   "padding": {
     "strategy": {
-      "Fixed": 512
+      "Fixed": 128
     },
     "direction": "Right",
     "pad_to_multiple_of": null,

train_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 3.9,
-    "train_loss": 0.5004565590306332,
-    "train_runtime": 76.0596,
+    "epoch": 5.0,
+    "train_loss": 0.3344010169689472,
+    "train_runtime": 98.9629,
     "train_samples": 2490,
-    "train_samples_per_second": 130.95,
-    "train_steps_per_second": 0.999
+    "train_samples_per_second": 125.805,
+    "train_steps_per_second": 15.763
 }

trainer_state.json

@@ -1,61 +1,43 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 3.8974358974358974,
-  "global_step": 76,
+  "epoch": 5.0,
+  "global_step": 1560,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.97,
-      "eval_accuracy": 0.6462093862815884,
-      "eval_loss": 0.6622310280799866,
-      "eval_runtime": 0.8176,
-      "eval_samples_per_second": 338.782,
-      "eval_steps_per_second": 11.007,
-      "step": 19
+      "epoch": 1.6,
+      "learning_rate": 1.3589743589743592e-05,
+      "loss": 0.6095,
+      "step": 500
     },
     {
-      "epoch": 2.0,
-      "eval_accuracy": 0.6389891696750902,
-      "eval_loss": 0.6256995797157288,
-      "eval_runtime": 0.8184,
-      "eval_samples_per_second": 338.47,
-      "eval_steps_per_second": 10.997,
-      "step": 39
+      "epoch": 3.21,
+      "learning_rate": 7.17948717948718e-06,
+      "loss": 0.3272,
+      "step": 1000
     },
     {
-      "epoch": 2.97,
-      "eval_accuracy": 0.6353790613718412,
-      "eval_loss": 0.7572575807571411,
-      "eval_runtime": 0.8328,
-      "eval_samples_per_second": 332.625,
-      "eval_steps_per_second": 10.807,
-      "step": 58
+      "epoch": 4.81,
+      "learning_rate": 7.692307692307694e-07,
+      "loss": 0.0972,
+      "step": 1500
     },
     {
-      "epoch": 3.9,
-      "eval_accuracy": 0.6353790613718412,
-      "eval_loss": 0.764682948589325,
-      "eval_runtime": 0.817,
-      "eval_samples_per_second": 339.032,
-      "eval_steps_per_second": 11.015,
-      "step": 76
-    },
-    {
-      "epoch": 3.9,
-      "step": 76,
-      "total_flos": 2537191448248320.0,
-      "train_loss": 0.5004565590306332,
-      "train_runtime": 76.0596,
-      "train_samples_per_second": 130.95,
-      "train_steps_per_second": 0.999
+      "epoch": 5.0,
+      "step": 1560,
+      "total_flos": 813286136217600.0,
+      "train_loss": 0.3344010169689472,
+      "train_runtime": 98.9629,
+      "train_samples_per_second": 125.805,
+      "train_steps_per_second": 15.763
     }
   ],
-  "max_steps": 76,
-  "num_train_epochs": 4,
-  "total_flos": 2537191448248320.0,
+  "max_steps": 1560,
+  "num_train_epochs": 5,
+  "total_flos": 813286136217600.0,
   "trial_name": null,
   "trial_params": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:640c9076d2caaa9604b9af40e9338f27bfb15056397526f47595f15d4d0dd940
-size 4091
+oid sha256:2b7acb9d14b816ffeacb7e2beaba2d6037a7bff441ba00c7df1b155086660724
+size 3963