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-lora
+  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-lora
+
+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: 0.2093
+- Accuracy: 0.8115
+
+## 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: 128
+- eval_batch_size: 128
+- 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 |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 0.2573        | 1.0   | 938  | 0.2270          | 0.7941   |
+| 0.2369        | 2.0   | 1876 | 0.2176          | 0.8057   |
+| 0.2286        | 3.0   | 2814 | 0.2132          | 0.8091   |
+| 0.2227        | 4.0   | 3752 | 0.2089          | 0.8122   |
+| 0.2204        | 5.0   | 4690 | 0.2083          | 0.8141   |
+| 0.2191        | 6.0   | 5628 | 0.2077          | 0.8143   |
+| 0.2183        | 7.0   | 6566 | 0.2048          | 0.8169   |
+| 0.2155        | 8.0   | 7504 | 0.2066          | 0.8156   |
+| 0.2164        | 9.0   | 8442 | 0.2047          | 0.8174   |
+| 0.2167        | 10.0  | 9380 | 0.2041          | 0.8177   |
+
+
+### 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": 0.8115100487112488,
+    "eval_loss": 0.2092970758676529,
+    "eval_runtime": 178.7127,
+    "eval_samples": 29997,
+    "eval_samples_per_second": 346.914,
+    "eval_steps_per_second": 2.714,
+    "gpu_memory": 19726,
+    "test_samples": 61998,
+    "train_loss": 0.22465838043928654,
+    "train_runtime": 5138.7739,
+    "train_samples": 119988,
+    "train_samples_per_second": 233.495,
+    "train_steps_per_second": 1.825
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 10.0,
+    "eval_accuracy": 0.8177151048438177,
+    "eval_loss": 0.2040574848651886,
+    "eval_runtime": 86.0001,
+    "eval_samples": 29997,
+    "eval_samples_per_second": 348.802,
+    "eval_steps_per_second": 2.733
+}

logs/events.out.tfevents.1695402211.serverailab12gb-System-Product-Name.12427.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c8b9fd21716ede26eab5d39688ecaab03bbd4fe9dde3884816bc3111405158b
-size 11134
+oid sha256:51e9413e41b309b737da4f0475424b25222f560086bd9870fcb6ac9717b8cb95
+size 11488

logs/events.out.tfevents.1695407436.serverailab12gb-System-Product-Name.12427.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b80ec44b5c2a4d08272f9b2a88a7dbaad264ce68c63ddac60f6dcd85957f8400
+size 734

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": 0.8115100487112488,
+    "eval_loss": 0.2092970758676529,
+    "eval_runtime": 178.7127,
+    "eval_samples_per_second": 346.914,
+    "eval_steps_per_second": 2.714,
+    "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": 19726,
+    "train_loss": 0.22465838043928654,
+    "train_runtime": 5138.7739,
+    "train_samples": 119988,
+    "train_samples_per_second": 233.495,
+    "train_steps_per_second": 1.825
+}

trainer_state.json

@@ -0,0 +1,223 @@
+{
+  "best_metric": 0.8177151048438177,
+  "best_model_checkpoint": "save_model/flan-t5-small-twitter-sentiment-analysis-lora/checkpoint-9380",
+  "epoch": 10.0,
+  "global_step": 9380,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.53,
+      "learning_rate": 4.7334754797441364e-05,
+      "loss": 0.2573,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7940794079407941,
+      "eval_loss": 0.22702552378177643,
+      "eval_runtime": 86.6302,
+      "eval_samples_per_second": 346.265,
+      "eval_steps_per_second": 2.713,
+      "step": 938
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 4.466950959488273e-05,
+      "loss": 0.2445,
+      "step": 1000
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 4.2004264392324094e-05,
+      "loss": 0.2369,
+      "step": 1500
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8056805680568057,
+      "eval_loss": 0.21760082244873047,
+      "eval_runtime": 86.3882,
+      "eval_samples_per_second": 347.235,
+      "eval_steps_per_second": 2.72,
+      "step": 1876
+    },
+    {
+      "epoch": 2.13,
+      "learning_rate": 3.9339019189765456e-05,
+      "loss": 0.2314,
+      "step": 2000
+    },
+    {
+      "epoch": 2.67,
+      "learning_rate": 3.6673773987206824e-05,
+      "loss": 0.2286,
+      "step": 2500
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8091142447578091,
+      "eval_loss": 0.2131662368774414,
+      "eval_runtime": 86.4294,
+      "eval_samples_per_second": 347.069,
+      "eval_steps_per_second": 2.719,
+      "step": 2814
+    },
+    {
+      "epoch": 3.2,
+      "learning_rate": 3.400852878464819e-05,
+      "loss": 0.2246,
+      "step": 3000
+    },
+    {
+      "epoch": 3.73,
+      "learning_rate": 3.1343283582089554e-05,
+      "loss": 0.2227,
+      "step": 3500
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8122478914558122,
+      "eval_loss": 0.20891216397285461,
+      "eval_runtime": 86.5057,
+      "eval_samples_per_second": 346.763,
+      "eval_steps_per_second": 2.717,
+      "step": 3752
+    },
+    {
+      "epoch": 4.26,
+      "learning_rate": 2.867803837953092e-05,
+      "loss": 0.223,
+      "step": 4000
+    },
+    {
+      "epoch": 4.8,
+      "learning_rate": 2.6012793176972285e-05,
+      "loss": 0.2204,
+      "step": 4500
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.8141480814748141,
+      "eval_loss": 0.2083190530538559,
+      "eval_runtime": 86.2794,
+      "eval_samples_per_second": 347.673,
+      "eval_steps_per_second": 2.724,
+      "step": 4690
+    },
+    {
+      "epoch": 5.33,
+      "learning_rate": 2.3347547974413646e-05,
+      "loss": 0.2216,
+      "step": 5000
+    },
+    {
+      "epoch": 5.86,
+      "learning_rate": 2.068230277185501e-05,
+      "loss": 0.2191,
+      "step": 5500
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.8143481014768144,
+      "eval_loss": 0.2076815366744995,
+      "eval_runtime": 86.2336,
+      "eval_samples_per_second": 347.858,
+      "eval_steps_per_second": 2.725,
+      "step": 5628
+    },
+    {
+      "epoch": 6.4,
+      "learning_rate": 1.8017057569296376e-05,
+      "loss": 0.2178,
+      "step": 6000
+    },
+    {
+      "epoch": 6.93,
+      "learning_rate": 1.535181236673774e-05,
+      "loss": 0.2183,
+      "step": 6500
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.8169150248358169,
+      "eval_loss": 0.204830601811409,
+      "eval_runtime": 86.2943,
+      "eval_samples_per_second": 347.613,
+      "eval_steps_per_second": 2.723,
+      "step": 6566
+    },
+    {
+      "epoch": 7.46,
+      "learning_rate": 1.2686567164179105e-05,
+      "loss": 0.2186,
+      "step": 7000
+    },
+    {
+      "epoch": 8.0,
+      "learning_rate": 1.002132196162047e-05,
+      "loss": 0.2155,
+      "step": 7500
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.8156148948228156,
+      "eval_loss": 0.206589013338089,
+      "eval_runtime": 86.3165,
+      "eval_samples_per_second": 347.523,
+      "eval_steps_per_second": 2.723,
+      "step": 7504
+    },
+    {
+      "epoch": 8.53,
+      "learning_rate": 7.356076759061833e-06,
+      "loss": 0.2164,
+      "step": 8000
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.8174150748408174,
+      "eval_loss": 0.20466509461402893,
+      "eval_runtime": 86.2755,
+      "eval_samples_per_second": 347.688,
+      "eval_steps_per_second": 2.724,
+      "step": 8442
+    },
+    {
+      "epoch": 9.06,
+      "learning_rate": 4.690831556503199e-06,
+      "loss": 0.2156,
+      "step": 8500
+    },
+    {
+      "epoch": 9.59,
+      "learning_rate": 2.025586353944563e-06,
+      "loss": 0.2167,
+      "step": 9000
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.8177151048438177,
+      "eval_loss": 0.2040574848651886,
+      "eval_runtime": 86.4923,
+      "eval_samples_per_second": 346.817,
+      "eval_steps_per_second": 2.717,
+      "step": 9380
+    },
+    {
+      "epoch": 10.0,
+      "step": 9380,
+      "total_flos": 1.1215726473904128e+17,
+      "train_loss": 0.22465838043928654,
+      "train_runtime": 5138.7739,
+      "train_samples_per_second": 233.495,
+      "train_steps_per_second": 1.825
+    }
+  ],
+  "max_steps": 9380,
+  "num_train_epochs": 10,
+  "total_flos": 1.1215726473904128e+17,
+  "trial_name": null,
+  "trial_params": null
+}