Upload folder using huggingface_hub

README.md

@@ -1,13 +1,28 @@
 ---
+language:
+- en
 license: other
 base_model: facebook/opt-350m
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - accuracy
 model-index:
 - name: opt-350m-rte
-  results: []
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: GLUE RTE
+      type: glue
+      args: rte
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.7111913357400722
 ---
 
 <!-- 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-350m-rte
 
-This model is a fine-tuned version of [facebook/opt-350m](https://huggingface.co/facebook/opt-350m) on an unknown dataset.
+This model is a fine-tuned version of [facebook/opt-350m](https://huggingface.co/facebook/opt-350m) on the GLUE RTE dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.7144
-- Accuracy: 0.6859
+- Loss: 2.1042
+- Accuracy: 0.7112
 
 ## 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: 32
+- 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   | 0.9919          | 0.4729   |
-| No log        | 2.0   | 39   | 0.6613          | 0.5848   |
-| No log        | 2.97  | 58   | 0.6972          | 0.6318   |
-| No log        | 3.9   | 76   | 0.7144          | 0.6859   |
 
 
 ### Framework versions

all_results.json

@@ -1,14 +1,14 @@
 {
-    "epoch": 3.9,
-    "eval_accuracy": 0.6859205776173285,
-    "eval_loss": 0.714410662651062,
-    "eval_runtime": 1.9726,
+    "epoch": 5.0,
+    "eval_accuracy": 0.7111913357400722,
+    "eval_loss": 2.1042087078094482,
+    "eval_runtime": 1.5849,
     "eval_samples": 277,
-    "eval_samples_per_second": 140.423,
-    "eval_steps_per_second": 4.562,
-    "train_loss": 0.8060256556460732,
-    "train_runtime": 205.3233,
+    "eval_samples_per_second": 174.772,
+    "eval_steps_per_second": 22.083,
+    "train_loss": 0.30048399705153245,
+    "train_runtime": 200.6393,
     "train_samples": 2490,
-    "train_samples_per_second": 48.509,
-    "train_steps_per_second": 0.37
+    "train_samples_per_second": 62.052,
+    "train_steps_per_second": 1.944
 }

config.json

@@ -13,16 +13,16 @@
   "enable_bias": true,
   "eos_token_id": 2,
   "ffn_dim": 4096,
-  "finetuning_task": "text-classification",
+  "finetuning_task": "rte",
   "hidden_size": 1024,
   "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": 0.6859205776173285,
-    "eval_loss": 0.714410662651062,
-    "eval_runtime": 1.9726,
+    "epoch": 5.0,
+    "eval_accuracy": 0.7111913357400722,
+    "eval_loss": 2.1042087078094482,
+    "eval_runtime": 1.5849,
     "eval_samples": 277,
-    "eval_samples_per_second": 140.423,
-    "eval_steps_per_second": 4.562
+    "eval_samples_per_second": 174.772,
+    "eval_steps_per_second": 22.083
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f0cbae03772046ad4f9f14f0c4f5ad4b6d6c2f6673e61f11d538cbb736445cc
+oid sha256:b358536980e2f2c0deac46a206a0542b52e165e42423a83c7316fe8553ef30c7
 size 1324921569

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": 0.8060256556460732,
-    "train_runtime": 205.3233,
+    "epoch": 5.0,
+    "train_loss": 0.30048399705153245,
+    "train_runtime": 200.6393,
     "train_samples": 2490,
-    "train_samples_per_second": 48.509,
-    "train_steps_per_second": 0.37
+    "train_samples_per_second": 62.052,
+    "train_steps_per_second": 1.944
 }

trainer_state.json

@@ -1,61 +1,25 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 3.8974358974358974,
-  "global_step": 76,
+  "epoch": 5.0,
+  "global_step": 390,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.97,
-      "eval_accuracy": 0.4729241877256318,
-      "eval_loss": 0.9918849468231201,
-      "eval_runtime": 1.9203,
-      "eval_samples_per_second": 144.25,
-      "eval_steps_per_second": 4.687,
-      "step": 19
-    },
-    {
-      "epoch": 2.0,
-      "eval_accuracy": 0.5848375451263538,
-      "eval_loss": 0.6613093018531799,
-      "eval_runtime": 1.9293,
-      "eval_samples_per_second": 143.576,
-      "eval_steps_per_second": 4.665,
-      "step": 39
-    },
-    {
-      "epoch": 2.97,
-      "eval_accuracy": 0.631768953068592,
-      "eval_loss": 0.6972018480300903,
-      "eval_runtime": 1.9423,
-      "eval_samples_per_second": 142.614,
-      "eval_steps_per_second": 4.634,
-      "step": 58
-    },
-    {
-      "epoch": 3.9,
-      "eval_accuracy": 0.6859205776173285,
-      "eval_loss": 0.714410662651062,
-      "eval_runtime": 1.9428,
-      "eval_samples_per_second": 142.575,
-      "eval_steps_per_second": 4.632,
-      "step": 76
-    },
-    {
-      "epoch": 3.9,
-      "step": 76,
-      "total_flos": 9048931298181120.0,
-      "train_loss": 0.8060256556460732,
-      "train_runtime": 205.3233,
-      "train_samples_per_second": 48.509,
-      "train_steps_per_second": 0.37
+      "epoch": 5.0,
+      "step": 390,
+      "total_flos": 2900597184921600.0,
+      "train_loss": 0.30048399705153245,
+      "train_runtime": 200.6393,
+      "train_samples_per_second": 62.052,
+      "train_steps_per_second": 1.944
     }
   ],
-  "max_steps": 76,
-  "num_train_epochs": 4,
-  "total_flos": 9048931298181120.0,
+  "max_steps": 390,
+  "num_train_epochs": 5,
+  "total_flos": 2900597184921600.0,
   "trial_name": null,
   "trial_params": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:95dff2048bf9a7a9cb3f3d470d5ca72f7a996d9a67bd7db6b0f00ffb636f00b4
-size 4091
+oid sha256:3b3b22874f2da3cca2923e809d12e9c08b60ee574321286e71bb5196c3407c8e
+size 3963