End of training

README.md

@@ -0,0 +1,68 @@
+---
+license: apache-2.0
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: flan-t5-small-twitter-sentiment-analysis
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# flan-t5-small-twitter-sentiment-analysis
+
+This model is a fine-tuned version of [google/flan-t5-small](https://huggingface.co/google/flan-t5-small) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1901
+- Accuracy: 0.8412
+
+## 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: 5e-05
+- train_batch_size: 64
+- eval_batch_size: 64
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 10.0
+
+### Training results
+
+| Training Loss | Epoch | Step  | Validation Loss | Accuracy |
+|:-------------:|:-----:|:-----:|:---------------:|:--------:|
+| 0.2136        | 1.0   | 1875  | 0.1923          | 0.8270   |
+| 0.1971        | 2.0   | 3750  | 0.1865          | 0.8367   |
+| 0.1883        | 3.0   | 5625  | 0.1830          | 0.8403   |
+| 0.1846        | 4.0   | 7500  | 0.1811          | 0.8415   |
+| 0.1753        | 5.0   | 9375  | 0.1793          | 0.8442   |
+| 0.1704        | 6.0   | 11250 | 0.1813          | 0.8433   |
+| 0.1689        | 7.0   | 13125 | 0.1815          | 0.8458   |
+| 0.1648        | 8.0   | 15000 | 0.1827          | 0.8461   |
+| 0.1661        | 9.0   | 16875 | 0.1821          | 0.8475   |
+| 0.1618        | 10.0  | 18750 | 0.1818          | 0.8471   |
+
+
+### Framework versions
+
+- Transformers 4.27.1
+- Pytorch 2.0.1
+- Datasets 2.9.0
+- Tokenizers 0.13.3

all_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 10.0,
+    "eval_accuracy": 0.8411722958805122,
+    "eval_loss": 0.1901138573884964,
+    "eval_runtime": 173.8619,
+    "eval_samples": 29997,
+    "eval_samples_per_second": 356.593,
+    "eval_steps_per_second": 5.573,
+    "gpu_memory": 17511,
+    "test_samples": 61998,
+    "train_loss": 0.18639904093424478,
+    "train_runtime": 5881.7351,
+    "train_samples": 119988,
+    "train_samples_per_second": 204.001,
+    "train_steps_per_second": 3.188
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 10.0,
+    "eval_accuracy": 0.8474514118078474,
+    "eval_loss": 0.18213823437690735,
+    "eval_runtime": 83.9027,
+    "eval_samples": 29997,
+    "eval_samples_per_second": 357.521,
+    "eval_steps_per_second": 5.59
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "decoder_start_token_id": 0,
+  "eos_token_id": 1,
+  "pad_token_id": 0,
+  "transformers_version": "4.27.1"
+}

logs/events.out.tfevents.1694842131.serverailab12gb-System-Product-Name.941915.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:29ab345df68b65644b2d7cf7963e1947fbd3fe1f7e31247dbea5a1e5117ff7fc
-size 14131
+oid sha256:f4af1d3e32c7621f3b4d69253c321faa162938fa8b7c52205c628467ad7d93d8
+size 14491

logs/events.out.tfevents.1694848096.serverailab12gb-System-Product-Name.941915.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:455ff0bc63f05d16e20549c777575907daf4ff2521cf8c9ae83102c2bc893518
+size 746

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:319c1d0e530f04db6cbb22353308956dd82806da901a9a3af5a5fd94666b9fe8
+oid sha256:5fda84ed28db082b99932e05688502f7ca546675f24102f32e8677857324f54e
 size 307910149

special_tokens_map.json

@@ -0,0 +1,107 @@
+{
+  "additional_special_tokens": [
+    "<extra_id_0>",
+    "<extra_id_1>",
+    "<extra_id_2>",
+    "<extra_id_3>",
+    "<extra_id_4>",
+    "<extra_id_5>",
+    "<extra_id_6>",
+    "<extra_id_7>",
+    "<extra_id_8>",
+    "<extra_id_9>",
+    "<extra_id_10>",
+    "<extra_id_11>",
+    "<extra_id_12>",
+    "<extra_id_13>",
+    "<extra_id_14>",
+    "<extra_id_15>",
+    "<extra_id_16>",
+    "<extra_id_17>",
+    "<extra_id_18>",
+    "<extra_id_19>",
+    "<extra_id_20>",
+    "<extra_id_21>",
+    "<extra_id_22>",
+    "<extra_id_23>",
+    "<extra_id_24>",
+    "<extra_id_25>",
+    "<extra_id_26>",
+    "<extra_id_27>",
+    "<extra_id_28>",
+    "<extra_id_29>",
+    "<extra_id_30>",
+    "<extra_id_31>",
+    "<extra_id_32>",
+    "<extra_id_33>",
+    "<extra_id_34>",
+    "<extra_id_35>",
+    "<extra_id_36>",
+    "<extra_id_37>",
+    "<extra_id_38>",
+    "<extra_id_39>",
+    "<extra_id_40>",
+    "<extra_id_41>",
+    "<extra_id_42>",
+    "<extra_id_43>",
+    "<extra_id_44>",
+    "<extra_id_45>",
+    "<extra_id_46>",
+    "<extra_id_47>",
+    "<extra_id_48>",
+    "<extra_id_49>",
+    "<extra_id_50>",
+    "<extra_id_51>",
+    "<extra_id_52>",
+    "<extra_id_53>",
+    "<extra_id_54>",
+    "<extra_id_55>",
+    "<extra_id_56>",
+    "<extra_id_57>",
+    "<extra_id_58>",
+    "<extra_id_59>",
+    "<extra_id_60>",
+    "<extra_id_61>",
+    "<extra_id_62>",
+    "<extra_id_63>",
+    "<extra_id_64>",
+    "<extra_id_65>",
+    "<extra_id_66>",
+    "<extra_id_67>",
+    "<extra_id_68>",
+    "<extra_id_69>",
+    "<extra_id_70>",
+    "<extra_id_71>",
+    "<extra_id_72>",
+    "<extra_id_73>",
+    "<extra_id_74>",
+    "<extra_id_75>",
+    "<extra_id_76>",
+    "<extra_id_77>",
+    "<extra_id_78>",
+    "<extra_id_79>",
+    "<extra_id_80>",
+    "<extra_id_81>",
+    "<extra_id_82>",
+    "<extra_id_83>",
+    "<extra_id_84>",
+    "<extra_id_85>",
+    "<extra_id_86>",
+    "<extra_id_87>",
+    "<extra_id_88>",
+    "<extra_id_89>",
+    "<extra_id_90>",
+    "<extra_id_91>",
+    "<extra_id_92>",
+    "<extra_id_93>",
+    "<extra_id_94>",
+    "<extra_id_95>",
+    "<extra_id_96>",
+    "<extra_id_97>",
+    "<extra_id_98>",
+    "<extra_id_99>"
+  ],
+  "eos_token": "</s>",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
+}

spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86
+size 791656

test_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 10.0,
+    "eval_accuracy": 0.8411722958805122,
+    "eval_loss": 0.1901138573884964,
+    "eval_runtime": 173.8619,
+    "eval_samples_per_second": 356.593,
+    "eval_steps_per_second": 5.573,
+    "test_samples": 61998
+}

tokenizer_config.json

@@ -0,0 +1,112 @@
+{
+  "additional_special_tokens": [
+    "<extra_id_0>",
+    "<extra_id_1>",
+    "<extra_id_2>",
+    "<extra_id_3>",
+    "<extra_id_4>",
+    "<extra_id_5>",
+    "<extra_id_6>",
+    "<extra_id_7>",
+    "<extra_id_8>",
+    "<extra_id_9>",
+    "<extra_id_10>",
+    "<extra_id_11>",
+    "<extra_id_12>",
+    "<extra_id_13>",
+    "<extra_id_14>",
+    "<extra_id_15>",
+    "<extra_id_16>",
+    "<extra_id_17>",
+    "<extra_id_18>",
+    "<extra_id_19>",
+    "<extra_id_20>",
+    "<extra_id_21>",
+    "<extra_id_22>",
+    "<extra_id_23>",
+    "<extra_id_24>",
+    "<extra_id_25>",
+    "<extra_id_26>",
+    "<extra_id_27>",
+    "<extra_id_28>",
+    "<extra_id_29>",
+    "<extra_id_30>",
+    "<extra_id_31>",
+    "<extra_id_32>",
+    "<extra_id_33>",
+    "<extra_id_34>",
+    "<extra_id_35>",
+    "<extra_id_36>",
+    "<extra_id_37>",
+    "<extra_id_38>",
+    "<extra_id_39>",
+    "<extra_id_40>",
+    "<extra_id_41>",
+    "<extra_id_42>",
+    "<extra_id_43>",
+    "<extra_id_44>",
+    "<extra_id_45>",
+    "<extra_id_46>",
+    "<extra_id_47>",
+    "<extra_id_48>",
+    "<extra_id_49>",
+    "<extra_id_50>",
+    "<extra_id_51>",
+    "<extra_id_52>",
+    "<extra_id_53>",
+    "<extra_id_54>",
+    "<extra_id_55>",
+    "<extra_id_56>",
+    "<extra_id_57>",
+    "<extra_id_58>",
+    "<extra_id_59>",
+    "<extra_id_60>",
+    "<extra_id_61>",
+    "<extra_id_62>",
+    "<extra_id_63>",
+    "<extra_id_64>",
+    "<extra_id_65>",
+    "<extra_id_66>",
+    "<extra_id_67>",
+    "<extra_id_68>",
+    "<extra_id_69>",
+    "<extra_id_70>",
+    "<extra_id_71>",
+    "<extra_id_72>",
+    "<extra_id_73>",
+    "<extra_id_74>",
+    "<extra_id_75>",
+    "<extra_id_76>",
+    "<extra_id_77>",
+    "<extra_id_78>",
+    "<extra_id_79>",
+    "<extra_id_80>",
+    "<extra_id_81>",
+    "<extra_id_82>",
+    "<extra_id_83>",
+    "<extra_id_84>",
+    "<extra_id_85>",
+    "<extra_id_86>",
+    "<extra_id_87>",
+    "<extra_id_88>",
+    "<extra_id_89>",
+    "<extra_id_90>",
+    "<extra_id_91>",
+    "<extra_id_92>",
+    "<extra_id_93>",
+    "<extra_id_94>",
+    "<extra_id_95>",
+    "<extra_id_96>",
+    "<extra_id_97>",
+    "<extra_id_98>",
+    "<extra_id_99>"
+  ],
+  "eos_token": "</s>",
+  "extra_ids": 100,
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sp_model_kwargs": {},
+  "special_tokens_map_file": "/home/younes_huggingface_co/.cache/huggingface/hub/models--google--t5-v1_1-small/snapshots/fb7e6cba609f7bab11c614294bc04f82f613c7b1/special_tokens_map.json",
+  "tokenizer_class": "T5Tokenizer",
+  "unk_token": "<unk>"
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 10.0,
+    "gpu_memory": 17511,
+    "train_loss": 0.18639904093424478,
+    "train_runtime": 5881.7351,
+    "train_samples": 119988,
+    "train_samples_per_second": 204.001,
+    "train_steps_per_second": 3.188
+}

trainer_state.json

@@ -0,0 +1,337 @@
+{
+  "best_metric": 0.8474514118078474,
+  "best_model_checkpoint": "save_model/flan-t5-small-twitter-sentiment-analysis/checkpoint-16875",
+  "epoch": 10.0,
+  "global_step": 18750,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.27,
+      "learning_rate": 4.866666666666667e-05,
+      "loss": 0.4402,
+      "step": 500
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 4.7333333333333336e-05,
+      "loss": 0.2228,
+      "step": 1000
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 0.2136,
+      "step": 1500
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8270493716038271,
+      "eval_loss": 0.19231748580932617,
+      "eval_runtime": 84.5141,
+      "eval_samples_per_second": 354.935,
+      "eval_steps_per_second": 5.549,
+      "step": 1875
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 4.466666666666667e-05,
+      "loss": 0.211,
+      "step": 2000
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 4.3333333333333334e-05,
+      "loss": 0.2042,
+      "step": 2500
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 4.2e-05,
+      "loss": 0.2022,
+      "step": 3000
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 4.066666666666667e-05,
+      "loss": 0.1971,
+      "step": 3500
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8367170050338367,
+      "eval_loss": 0.18650780618190765,
+      "eval_runtime": 84.5536,
+      "eval_samples_per_second": 354.769,
+      "eval_steps_per_second": 5.547,
+      "step": 3750
+    },
+    {
+      "epoch": 2.13,
+      "learning_rate": 3.933333333333333e-05,
+      "loss": 0.1966,
+      "step": 4000
+    },
+    {
+      "epoch": 2.4,
+      "learning_rate": 3.8e-05,
+      "loss": 0.1906,
+      "step": 4500
+    },
+    {
+      "epoch": 2.67,
+      "learning_rate": 3.6666666666666666e-05,
+      "loss": 0.1934,
+      "step": 5000
+    },
+    {
+      "epoch": 2.93,
+      "learning_rate": 3.5333333333333336e-05,
+      "loss": 0.1883,
+      "step": 5500
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8402506917358402,
+      "eval_loss": 0.18298229575157166,
+      "eval_runtime": 84.3321,
+      "eval_samples_per_second": 355.701,
+      "eval_steps_per_second": 5.561,
+      "step": 5625
+    },
+    {
+      "epoch": 3.2,
+      "learning_rate": 3.4000000000000007e-05,
+      "loss": 0.185,
+      "step": 6000
+    },
+    {
+      "epoch": 3.47,
+      "learning_rate": 3.266666666666667e-05,
+      "loss": 0.1811,
+      "step": 6500
+    },
+    {
+      "epoch": 3.73,
+      "learning_rate": 3.1333333333333334e-05,
+      "loss": 0.1845,
+      "step": 7000
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 3e-05,
+      "loss": 0.1846,
+      "step": 7500
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8415174850818415,
+      "eval_loss": 0.18108856678009033,
+      "eval_runtime": 84.5574,
+      "eval_samples_per_second": 354.753,
+      "eval_steps_per_second": 5.547,
+      "step": 7500
+    },
+    {
+      "epoch": 4.27,
+      "learning_rate": 2.8666666666666668e-05,
+      "loss": 0.1778,
+      "step": 8000
+    },
+    {
+      "epoch": 4.53,
+      "learning_rate": 2.733333333333333e-05,
+      "loss": 0.1788,
+      "step": 8500
+    },
+    {
+      "epoch": 4.8,
+      "learning_rate": 2.6000000000000002e-05,
+      "loss": 0.1753,
+      "step": 9000
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.8441510817748441,
+      "eval_loss": 0.1792929321527481,
+      "eval_runtime": 84.3334,
+      "eval_samples_per_second": 355.695,
+      "eval_steps_per_second": 5.561,
+      "step": 9375
+    },
+    {
+      "epoch": 5.07,
+      "learning_rate": 2.466666666666667e-05,
+      "loss": 0.1777,
+      "step": 9500
+    },
+    {
+      "epoch": 5.33,
+      "learning_rate": 2.3333333333333336e-05,
+      "loss": 0.1726,
+      "step": 10000
+    },
+    {
+      "epoch": 5.6,
+      "learning_rate": 2.2000000000000003e-05,
+      "loss": 0.1748,
+      "step": 10500
+    },
+    {
+      "epoch": 5.87,
+      "learning_rate": 2.0666666666666666e-05,
+      "loss": 0.1704,
+      "step": 11000
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.8432509917658433,
+      "eval_loss": 0.1813008189201355,
+      "eval_runtime": 84.0893,
+      "eval_samples_per_second": 356.728,
+      "eval_steps_per_second": 5.577,
+      "step": 11250
+    },
+    {
+      "epoch": 6.13,
+      "learning_rate": 1.9333333333333333e-05,
+      "loss": 0.1685,
+      "step": 11500
+    },
+    {
+      "epoch": 6.4,
+      "learning_rate": 1.8e-05,
+      "loss": 0.1696,
+      "step": 12000
+    },
+    {
+      "epoch": 6.67,
+      "learning_rate": 1.6666666666666667e-05,
+      "loss": 0.1699,
+      "step": 12500
+    },
+    {
+      "epoch": 6.93,
+      "learning_rate": 1.5333333333333334e-05,
+      "loss": 0.1689,
+      "step": 13000
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.8457845784578458,
+      "eval_loss": 0.1814945936203003,
+      "eval_runtime": 84.0394,
+      "eval_samples_per_second": 356.94,
+      "eval_steps_per_second": 5.581,
+      "step": 13125
+    },
+    {
+      "epoch": 7.2,
+      "learning_rate": 1.4000000000000001e-05,
+      "loss": 0.1705,
+      "step": 13500
+    },
+    {
+      "epoch": 7.47,
+      "learning_rate": 1.2666666666666668e-05,
+      "loss": 0.1661,
+      "step": 14000
+    },
+    {
+      "epoch": 7.73,
+      "learning_rate": 1.1333333333333334e-05,
+      "loss": 0.1651,
+      "step": 14500
+    },
+    {
+      "epoch": 8.0,
+      "learning_rate": 1e-05,
+      "loss": 0.1648,
+      "step": 15000
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.8461179451278461,
+      "eval_loss": 0.1826968640089035,
+      "eval_runtime": 83.8792,
+      "eval_samples_per_second": 357.621,
+      "eval_steps_per_second": 5.591,
+      "step": 15000
+    },
+    {
+      "epoch": 8.27,
+      "learning_rate": 8.666666666666668e-06,
+      "loss": 0.164,
+      "step": 15500
+    },
+    {
+      "epoch": 8.53,
+      "learning_rate": 7.333333333333334e-06,
+      "loss": 0.1635,
+      "step": 16000
+    },
+    {
+      "epoch": 8.8,
+      "learning_rate": 6e-06,
+      "loss": 0.1661,
+      "step": 16500
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.8474514118078474,
+      "eval_loss": 0.18213823437690735,
+      "eval_runtime": 84.2718,
+      "eval_samples_per_second": 355.955,
+      "eval_steps_per_second": 5.565,
+      "step": 16875
+    },
+    {
+      "epoch": 9.07,
+      "learning_rate": 4.666666666666667e-06,
+      "loss": 0.1606,
+      "step": 17000
+    },
+    {
+      "epoch": 9.33,
+      "learning_rate": 3.3333333333333333e-06,
+      "loss": 0.1636,
+      "step": 17500
+    },
+    {
+      "epoch": 9.6,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 0.1626,
+      "step": 18000
+    },
+    {
+      "epoch": 9.87,
+      "learning_rate": 6.666666666666667e-07,
+      "loss": 0.1618,
+      "step": 18500
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.847084708470847,
+      "eval_loss": 0.18182113766670227,
+      "eval_runtime": 84.3952,
+      "eval_samples_per_second": 355.435,
+      "eval_steps_per_second": 5.557,
+      "step": 18750
+    },
+    {
+      "epoch": 10.0,
+      "step": 18750,
+      "total_flos": 1.1152314939211776e+17,
+      "train_loss": 0.18639904093424478,
+      "train_runtime": 5881.7351,
+      "train_samples_per_second": 204.001,
+      "train_steps_per_second": 3.188
+    }
+  ],
+  "max_steps": 18750,
+  "num_train_epochs": 10,
+  "total_flos": 1.1152314939211776e+17,
+  "trial_name": null,
+  "trial_params": null
+}