imdb_text_classification

README.md

@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.3574
+- Loss: 1.3371
 
 ## Model description
 
@@ -47,14 +47,14 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 0.2839        | 1.0   | 3125 | 0.2983          |
-| 0.1714        | 2.0   | 6250 | 0.3002          |
-| 0.0776        | 3.0   | 9375 | 0.3574          |
+| No log        | 1.0   | 43   | 1.5036          |
+| No log        | 2.0   | 86   | 1.4300          |
+| No log        | 3.0   | 129  | 1.3371          |
 
 
 ### Framework versions
 
 - Transformers 4.44.2
-- Pytorch 2.4.1+cu121
-- Datasets 3.0.1
+- Pytorch 2.5.0+cu121
+- Datasets 3.1.0
 - Tokenizers 0.19.1

config.json

@@ -8,7 +8,21 @@
   "dim": 768,
   "dropout": 0.1,
   "hidden_dim": 3072,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4"
+  },
   "initializer_range": 0.02,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4
+  },
   "max_position_embeddings": 512,
   "model_type": "distilbert",
   "n_heads": 12,

eval_results.json

@@ -1 +1 @@
-{"eval_loss": 0.35744309425354004, "eval_runtime": 110.9426, "eval_samples_per_second": 225.342, "eval_steps_per_second": 28.168, "epoch": 3.0}
+{"eval_loss": 1.337083101272583, "eval_runtime": 0.4518, "eval_samples_per_second": 221.35, "eval_steps_per_second": 28.776, "epoch": 3.0}

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:98e2ba2304a9c0e23b6d54aafae9cd5b556225b579729bb2196dc0a50534e357
-size 267832560
+oid sha256:0871f770a31e555116cd2754df361c124358a7a1b8adf3ff4f88fda3909c7968
+size 267841796

runs/Nov11_18-44-19_70e8903556eb/events.out.tfevents.1731350665.70e8903556eb.4587.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:914c63b2483cbc99790240013dd3ea2c8476e8b0fb1ed4d5b8b329d02b30e5b3
+size 4776

runs/Nov11_19-00-12_70e8903556eb/events.out.tfevents.1731351638.70e8903556eb.24415.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1667cdad5669ad262b5bdc9ebef82089e75854e3301c49f3c1763edc331cd3de
+size 4184

runs/Nov11_19-01-44_70e8903556eb/events.out.tfevents.1731351705.70e8903556eb.25559.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25f73c5e7957ef12ba95491f2a1fff2b0a48e3cdf59bf354efcfc3c019f8bdf6
+size 6163

runs/Nov11_19-01-44_70e8903556eb/events.out.tfevents.1731351729.70e8903556eb.25559.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97740b1e62bce229978f43c6a57a6258493c8a99c4016b38b25ed35e968c2e99
+size 359

trainer_state.json

@@ -3,173 +3,47 @@
   "best_model_checkpoint": null,
   "epoch": 3.0,
   "eval_steps": 500,
-  "global_step": 9375,
+  "global_step": 129,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
-    {
-      "epoch": 0.16,
-      "grad_norm": 25.028797149658203,
-      "learning_rate": 4.7333333333333336e-05,
-      "loss": 0.4107,
-      "step": 500
-    },
-    {
-      "epoch": 0.32,
-      "grad_norm": 6.398056507110596,
-      "learning_rate": 4.466666666666667e-05,
-      "loss": 0.3382,
-      "step": 1000
-    },
-    {
-      "epoch": 0.48,
-      "grad_norm": 17.56199073791504,
-      "learning_rate": 4.2e-05,
-      "loss": 0.3389,
-      "step": 1500
-    },
-    {
-      "epoch": 0.64,
-      "grad_norm": 32.491722106933594,
-      "learning_rate": 3.933333333333333e-05,
-      "loss": 0.3043,
-      "step": 2000
-    },
-    {
-      "epoch": 0.8,
-      "grad_norm": 12.640718460083008,
-      "learning_rate": 3.6666666666666666e-05,
-      "loss": 0.3006,
-      "step": 2500
-    },
-    {
-      "epoch": 0.96,
-      "grad_norm": 9.034324645996094,
-      "learning_rate": 3.4000000000000007e-05,
-      "loss": 0.2839,
-      "step": 3000
-    },
     {
       "epoch": 1.0,
-      "eval_loss": 0.29832616448402405,
-      "eval_runtime": 109.9495,
-      "eval_samples_per_second": 227.377,
-      "eval_steps_per_second": 28.422,
-      "step": 3125
-    },
-    {
-      "epoch": 1.12,
-      "grad_norm": 32.539512634277344,
-      "learning_rate": 3.1333333333333334e-05,
-      "loss": 0.2058,
-      "step": 3500
-    },
-    {
-      "epoch": 1.28,
-      "grad_norm": 2.0097203254699707,
-      "learning_rate": 2.8666666666666668e-05,
-      "loss": 0.182,
-      "step": 4000
-    },
-    {
-      "epoch": 1.44,
-      "grad_norm": 0.1602770835161209,
-      "learning_rate": 2.6000000000000002e-05,
-      "loss": 0.1614,
-      "step": 4500
-    },
-    {
-      "epoch": 1.6,
-      "grad_norm": 0.056532543152570724,
-      "learning_rate": 2.3333333333333336e-05,
-      "loss": 0.1726,
-      "step": 5000
-    },
-    {
-      "epoch": 1.76,
-      "grad_norm": 21.226852416992188,
-      "learning_rate": 2.0666666666666666e-05,
-      "loss": 0.1867,
-      "step": 5500
-    },
-    {
-      "epoch": 1.92,
-      "grad_norm": 14.321476936340332,
-      "learning_rate": 1.8e-05,
-      "loss": 0.1714,
-      "step": 6000
+      "eval_loss": 1.5036001205444336,
+      "eval_runtime": 0.459,
+      "eval_samples_per_second": 217.868,
+      "eval_steps_per_second": 28.323,
+      "step": 43
     },
     {
       "epoch": 2.0,
-      "eval_loss": 0.3002217710018158,
-      "eval_runtime": 110.1479,
-      "eval_samples_per_second": 226.968,
-      "eval_steps_per_second": 28.371,
-      "step": 6250
-    },
-    {
-      "epoch": 2.08,
-      "grad_norm": 0.014615637250244617,
-      "learning_rate": 1.5333333333333334e-05,
-      "loss": 0.1151,
-      "step": 6500
-    },
-    {
-      "epoch": 2.24,
-      "grad_norm": 0.2536245286464691,
-      "learning_rate": 1.2666666666666668e-05,
-      "loss": 0.074,
-      "step": 7000
-    },
-    {
-      "epoch": 2.4,
-      "grad_norm": 0.25840720534324646,
-      "learning_rate": 1e-05,
-      "loss": 0.0538,
-      "step": 7500
-    },
-    {
-      "epoch": 2.56,
-      "grad_norm": 0.008101879619061947,
-      "learning_rate": 7.333333333333334e-06,
-      "loss": 0.0659,
-      "step": 8000
-    },
-    {
-      "epoch": 2.7199999999999998,
-      "grad_norm": 0.056057158857584,
-      "learning_rate": 4.666666666666667e-06,
-      "loss": 0.0691,
-      "step": 8500
-    },
-    {
-      "epoch": 2.88,
-      "grad_norm": 0.04367438703775406,
-      "learning_rate": 2.0000000000000003e-06,
-      "loss": 0.0776,
-      "step": 9000
+      "eval_loss": 1.4299612045288086,
+      "eval_runtime": 0.4476,
+      "eval_samples_per_second": 223.397,
+      "eval_steps_per_second": 29.042,
+      "step": 86
     },
     {
       "epoch": 3.0,
-      "eval_loss": 0.35744309425354004,
-      "eval_runtime": 110.1571,
-      "eval_samples_per_second": 226.949,
-      "eval_steps_per_second": 28.369,
-      "step": 9375
+      "eval_loss": 1.337083101272583,
+      "eval_runtime": 0.4439,
+      "eval_samples_per_second": 225.292,
+      "eval_steps_per_second": 29.288,
+      "step": 129
     },
     {
       "epoch": 3.0,
-      "step": 9375,
-      "total_flos": 9935054899200000.0,
-      "train_loss": 0.18996990498860677,
-      "train_runtime": 1346.0972,
-      "train_samples_per_second": 55.717,
-      "train_steps_per_second": 6.965
+      "step": 129,
+      "total_flos": 135123975475200.0,
+      "train_loss": 1.5090400636658188,
+      "train_runtime": 22.4003,
+      "train_samples_per_second": 45.535,
+      "train_steps_per_second": 5.759
     }
   ],
   "logging_steps": 500,
-  "max_steps": 9375,
+  "max_steps": 129,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 500,
@@ -185,7 +59,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 9935054899200000.0,
+  "total_flos": 135123975475200.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ddbc9933bc9d68594c7d7df0830d5b3b8d87d71036ff60a78ef05041b18cdb90
+oid sha256:bd86464d6b1ab10996478262fc56c661ce2208553ecf94c1a9e299c7da21a91a
 size 5176