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-sst2
-  results: []
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: GLUE SST2
+      type: glue
+      args: sst2
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.9162844036697247
 ---
 
 <!-- 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-sst2
 
-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 SST2 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.3048
-- Accuracy: 0.9209
+- Loss: 0.4992
+- Accuracy: 0.9163
 
 ## Model description
 
@@ -37,24 +52,16 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 5e-05
+- learning_rate: 2e-05
 - train_batch_size: 16
-- eval_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 |
-|:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 0.2524        | 1.0   | 526  | 0.2183          | 0.9083   |
-| 0.1152        | 2.0   | 1052 | 0.2751          | 0.8945   |
-| 0.0647        | 3.0   | 1578 | 0.3214          | 0.9060   |
-| 0.0322        | 4.0   | 2104 | 0.3048          | 0.9209   |
 
 
 ### Framework versions

all_results.json

@@ -1,14 +1,14 @@
 {
-    "epoch": 4.0,
-    "eval_accuracy": 0.9208715596330275,
-    "eval_loss": 0.3048288822174072,
-    "eval_runtime": 5.4607,
+    "epoch": 5.0,
+    "eval_accuracy": 0.9162844036697247,
+    "eval_loss": 0.4992079436779022,
+    "eval_runtime": 2.3494,
     "eval_samples": 872,
-    "eval_samples_per_second": 159.688,
-    "eval_steps_per_second": 5.128,
-    "train_loss": 0.11159764983808133,
-    "train_runtime": 5170.0912,
+    "eval_samples_per_second": 371.153,
+    "eval_steps_per_second": 46.394,
+    "train_loss": 0.11896094931842595,
+    "train_runtime": 1931.7504,
     "train_samples": 67349,
-    "train_samples_per_second": 52.107,
-    "train_steps_per_second": 0.407
+    "train_samples_per_second": 174.321,
+    "train_steps_per_second": 10.897
 }

config.json

@@ -13,16 +13,16 @@
   "enable_bias": true,
   "eos_token_id": 2,
   "ffn_dim": 4096,
-  "finetuning_task": "text-classification",
+  "finetuning_task": "sst2",
   "hidden_size": 1024,
   "id2label": {
-    "0": "0",
-    "1": "1"
+    "0": "negative",
+    "1": "positive"
   },
   "init_std": 0.02,
   "label2id": {
-    "0": 0,
-    "1": 1
+    "negative": 0,
+    "positive": 1
   },
   "layer_norm_elementwise_affine": true,
   "layerdrop": 0.0,

eval_results.json

@@ -1,9 +1,9 @@
 {
-    "epoch": 4.0,
-    "eval_accuracy": 0.9208715596330275,
-    "eval_loss": 0.3048288822174072,
-    "eval_runtime": 5.4607,
+    "epoch": 5.0,
+    "eval_accuracy": 0.9162844036697247,
+    "eval_loss": 0.4992079436779022,
+    "eval_runtime": 2.3494,
     "eval_samples": 872,
-    "eval_samples_per_second": 159.688,
-    "eval_steps_per_second": 5.128
+    "eval_samples_per_second": 371.153,
+    "eval_steps_per_second": 46.394
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d2204106204e2d52b7ab1dadd2de53610134032ff4312dbbdbe5daecc11703a
+oid sha256:37726e48158d3b426745fef1baad4ec6bf28d101cab54c64329d83a0f6e77ad2
 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": 4.0,
-    "train_loss": 0.11159764983808133,
-    "train_runtime": 5170.0912,
+    "epoch": 5.0,
+    "train_loss": 0.11896094931842595,
+    "train_runtime": 1931.7504,
     "train_samples": 67349,
-    "train_samples_per_second": 52.107,
-    "train_steps_per_second": 0.407
+    "train_samples_per_second": 174.321,
+    "train_steps_per_second": 10.897
 }

trainer_state.json

@@ -1,85 +1,277 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 3.998099762470309,
-  "global_step": 2104,
+  "epoch": 5.0,
+  "global_step": 21050,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.95,
-      "learning_rate": 3.811787072243346e-05,
-      "loss": 0.2524,
+      "epoch": 0.12,
+      "learning_rate": 1.9527790973871736e-05,
+      "loss": 0.3444,
       "step": 500
     },
     {
-      "epoch": 1.0,
-      "eval_accuracy": 0.908256880733945,
-      "eval_loss": 0.21832765638828278,
-      "eval_runtime": 5.5594,
-      "eval_samples_per_second": 156.85,
-      "eval_steps_per_second": 5.036,
-      "step": 526
+      "epoch": 0.24,
+      "learning_rate": 1.905273159144893e-05,
+      "loss": 0.2812,
+      "step": 1000
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.857767220902613e-05,
+      "loss": 0.265,
+      "step": 1500
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.8102612826603327e-05,
+      "loss": 0.2375,
+      "step": 2000
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 1.7628503562945368e-05,
+      "loss": 0.2282,
+      "step": 2500
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 1.7153444180522567e-05,
+      "loss": 0.2192,
+      "step": 3000
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1.6678384798099765e-05,
+      "loss": 0.2187,
+      "step": 3500
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.620332541567696e-05,
+      "loss": 0.2216,
+      "step": 4000
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 1.5729216152019004e-05,
+      "loss": 0.1802,
+      "step": 4500
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 1.5254156769596201e-05,
+      "loss": 0.1474,
+      "step": 5000
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 1.4779097387173397e-05,
+      "loss": 0.144,
+      "step": 5500
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 1.4304038004750596e-05,
+      "loss": 0.1607,
+      "step": 6000
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 1.382897862232779e-05,
+      "loss": 0.1622,
+      "step": 6500
+    },
+    {
+      "epoch": 1.66,
+      "learning_rate": 1.3354869358669835e-05,
+      "loss": 0.1581,
+      "step": 7000
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 1.2879809976247033e-05,
+      "loss": 0.1535,
+      "step": 7500
     },
     {
       "epoch": 1.9,
-      "learning_rate": 2.6235741444866924e-05,
-      "loss": 0.1152,
-      "step": 1000
+      "learning_rate": 1.2404750593824228e-05,
+      "loss": 0.1528,
+      "step": 8000
+    },
+    {
+      "epoch": 2.02,
+      "learning_rate": 1.1929691211401427e-05,
+      "loss": 0.1475,
+      "step": 8500
+    },
+    {
+      "epoch": 2.14,
+      "learning_rate": 1.1455581947743468e-05,
+      "loss": 0.1033,
+      "step": 9000
+    },
+    {
+      "epoch": 2.26,
+      "learning_rate": 1.0981472684085512e-05,
+      "loss": 0.0884,
+      "step": 9500
     },
     {
-      "epoch": 2.0,
-      "eval_accuracy": 0.8944954128440367,
-      "eval_loss": 0.27505654096603394,
-      "eval_runtime": 5.5334,
-      "eval_samples_per_second": 157.59,
-      "eval_steps_per_second": 5.06,
-      "step": 1052
+      "epoch": 2.38,
+      "learning_rate": 1.0506413301662707e-05,
+      "loss": 0.102,
+      "step": 10000
+    },
+    {
+      "epoch": 2.49,
+      "learning_rate": 1.0031353919239906e-05,
+      "loss": 0.104,
+      "step": 10500
+    },
+    {
+      "epoch": 2.61,
+      "learning_rate": 9.556294536817104e-06,
+      "loss": 0.1026,
+      "step": 11000
+    },
+    {
+      "epoch": 2.73,
+      "learning_rate": 9.0812351543943e-06,
+      "loss": 0.1116,
+      "step": 11500
     },
     {
       "epoch": 2.85,
-      "learning_rate": 1.4353612167300381e-05,
-      "loss": 0.0647,
-      "step": 1500
+      "learning_rate": 8.606175771971497e-06,
+      "loss": 0.1002,
+      "step": 12000
+    },
+    {
+      "epoch": 2.97,
+      "learning_rate": 8.131116389548695e-06,
+      "loss": 0.0996,
+      "step": 12500
+    },
+    {
+      "epoch": 3.09,
+      "learning_rate": 7.656057007125892e-06,
+      "loss": 0.0686,
+      "step": 13000
+    },
+    {
+      "epoch": 3.21,
+      "learning_rate": 7.180997624703089e-06,
+      "loss": 0.0594,
+      "step": 13500
+    },
+    {
+      "epoch": 3.33,
+      "learning_rate": 6.7068883610451305e-06,
+      "loss": 0.0562,
+      "step": 14000
+    },
+    {
+      "epoch": 3.44,
+      "learning_rate": 6.231828978622329e-06,
+      "loss": 0.0523,
+      "step": 14500
+    },
+    {
+      "epoch": 3.56,
+      "learning_rate": 5.757719714964372e-06,
+      "loss": 0.0576,
+      "step": 15000
     },
     {
-      "epoch": 3.0,
-      "eval_accuracy": 0.9059633027522935,
-      "eval_loss": 0.3214015066623688,
-      "eval_runtime": 5.5423,
-      "eval_samples_per_second": 157.334,
-      "eval_steps_per_second": 5.052,
-      "step": 1578
+      "epoch": 3.68,
+      "learning_rate": 5.282660332541568e-06,
+      "loss": 0.067,
+      "step": 15500
     },
     {
       "epoch": 3.8,
-      "learning_rate": 2.4714828897338406e-06,
-      "loss": 0.0322,
-      "step": 2000
+      "learning_rate": 4.807600950118766e-06,
+      "loss": 0.0664,
+      "step": 16000
+    },
+    {
+      "epoch": 3.92,
+      "learning_rate": 4.332541567695962e-06,
+      "loss": 0.064,
+      "step": 16500
+    },
+    {
+      "epoch": 4.04,
+      "learning_rate": 3.857482185273159e-06,
+      "loss": 0.0441,
+      "step": 17000
+    },
+    {
+      "epoch": 4.16,
+      "learning_rate": 3.382422802850356e-06,
+      "loss": 0.0306,
+      "step": 17500
+    },
+    {
+      "epoch": 4.28,
+      "learning_rate": 2.9073634204275536e-06,
+      "loss": 0.0287,
+      "step": 18000
+    },
+    {
+      "epoch": 4.39,
+      "learning_rate": 2.4323040380047506e-06,
+      "loss": 0.0314,
+      "step": 18500
+    },
+    {
+      "epoch": 4.51,
+      "learning_rate": 1.957244655581948e-06,
+      "loss": 0.0304,
+      "step": 19000
+    },
+    {
+      "epoch": 4.63,
+      "learning_rate": 1.4821852731591448e-06,
+      "loss": 0.0281,
+      "step": 19500
+    },
+    {
+      "epoch": 4.75,
+      "learning_rate": 1.007125890736342e-06,
+      "loss": 0.0257,
+      "step": 20000
+    },
+    {
+      "epoch": 4.87,
+      "learning_rate": 5.320665083135392e-07,
+      "loss": 0.0385,
+      "step": 20500
     },
     {
-      "epoch": 4.0,
-      "eval_accuracy": 0.9208715596330275,
-      "eval_loss": 0.3048288822174072,
-      "eval_runtime": 5.5583,
-      "eval_samples_per_second": 156.883,
-      "eval_steps_per_second": 5.038,
-      "step": 2104
+      "epoch": 4.99,
+      "learning_rate": 5.700712589073635e-08,
+      "loss": 0.0246,
+      "step": 21000
     },
     {
-      "epoch": 4.0,
-      "step": 2104,
-      "total_flos": 2.509461556171899e+17,
-      "train_loss": 0.11159764983808133,
-      "train_runtime": 5170.0912,
-      "train_samples_per_second": 52.107,
-      "train_steps_per_second": 0.407
+      "epoch": 5.0,
+      "step": 21050,
+      "total_flos": 7.845474691055616e+16,
+      "train_loss": 0.11896094931842595,
+      "train_runtime": 1931.7504,
+      "train_samples_per_second": 174.321,
+      "train_steps_per_second": 10.897
     }
   ],
-  "max_steps": 2104,
-  "num_train_epochs": 4,
-  "total_flos": 2.509461556171899e+17,
+  "max_steps": 21050,
+  "num_train_epochs": 5,
+  "total_flos": 7.845474691055616e+16,
   "trial_name": null,
   "trial_params": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9752cf7949d252b7a2ad5051d46d30a99bdf5d8bb4459118ef0e45204d2fe42f
-size 4091
+oid sha256:c17f7b6288e5c516c6649e53ffc27e41d0f094d0f9700693ab9da2c8179b7af1
+size 3963