End of training

README.md

@@ -1,9 +1,8 @@
 ---
 license: apache-2.0
-library_name: peft
+base_model: google/flan-t5-small
 tags:
 - generated_from_trainer
-base_model: google/flan-t5-small
 model-index:
 - name: flan-small-sql
   results: []
@@ -16,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [google/flan-t5-small](https://huggingface.co/google/flan-t5-small) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.1380
+- Loss: 2.0431
 
 ## Model description
 
@@ -41,30 +40,15 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 10.0
+- num_epochs: 0.001
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss |
-|:-------------:|:-----:|:----:|:---------------:|
-| 0.4956        | 0.8   | 500  | 0.2179          |
-| 0.3076        | 1.6   | 1000 | 0.1833          |
-| 0.2707        | 2.4   | 1500 | 0.1702          |
-| 0.2439        | 3.2   | 2000 | 0.1608          |
-| 0.2295        | 4.0   | 2500 | 0.1565          |
-| 0.2163        | 4.8   | 3000 | 0.1502          |
-| 0.2058        | 5.6   | 3500 | 0.1501          |
-| 0.2009        | 6.4   | 4000 | 0.1458          |
-| 0.1898        | 7.2   | 4500 | 0.1427          |
-| 0.1874        | 8.0   | 5000 | 0.1428          |
-| 0.1792        | 8.8   | 5500 | 0.1390          |
-| 0.1757        | 9.6   | 6000 | 0.1386          |
 
 
 ### Framework versions
 
-- PEFT 0.7.1
-- Transformers 4.38.0
-- Pytorch 2.1.2+cu121
-- Datasets 2.17.0
-- Tokenizers 0.15.2
+- Transformers 4.36.0.dev0
+- Pytorch 2.1.0+cu118
+- Datasets 2.14.6
+- Tokenizers 0.14.1

adapter_config.json

@@ -19,8 +19,9 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q",
-    "v"
+    "v",
+    "q"
   ],
-  "task_type": "SEQ_2_SEQ_LM"
+  "task_type": "SEQ_2_SEQ_LM",
+  "use_rslora": false
 }

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a300d41e02bb949781fc8216dc693c26afaa57a55483ed09881bfa83438f6dc
+oid sha256:73d36a8bd1459a02f673c0ce7dde2ca37d3c20c69e509002c959ecb70c629af4
 size 2765880

all_results.json

@@ -1,11 +1,11 @@
 {
-    "epoch": 10.0,
-    "eval_loss": 0.1379527598619461,
-    "eval_runtime": 13.5172,
-    "eval_samples_per_second": 581.261,
-    "eval_steps_per_second": 36.398,
-    "train_loss": 0.23933088928222657,
-    "train_runtime": 648.1335,
-    "train_samples_per_second": 154.289,
-    "train_steps_per_second": 9.643
+    "epoch": 0.0,
+    "eval_loss": 2.043109178543091,
+    "eval_runtime": 12.8998,
+    "eval_samples_per_second": 609.078,
+    "eval_steps_per_second": 38.14,
+    "train_loss": 2.5783498287200928,
+    "train_runtime": 0.3238,
+    "train_samples_per_second": 30.88,
+    "train_steps_per_second": 3.088
 }

emissions.csv

@@ -0,0 +1,3 @@
+timestamp,experiment_id,project_name,duration,emissions,energy_consumed,country_name,country_iso_code,region,on_cloud,cloud_provider,cloud_region
+2024-02-24T00:05:40,16ea20c8-bcb1-453e-bce2-f6cb0599f084,codecarbon,0.3465697765350342,2.382074432305905e-05,6.453136242463374e-05,United States,USA,virginia,N,,
+2024-02-24T00:08:29,9fde16a4-8a69-4bb9-a34b-f48f907546a5,codecarbon,0.3421628475189209,2.3325881593192804e-05,6.319075922020199e-05,United States,USA,virginia,N,,

eval_results.json

@@ -1,7 +1,7 @@
 {
-    "epoch": 10.0,
-    "eval_loss": 0.1379527598619461,
-    "eval_runtime": 13.5172,
-    "eval_samples_per_second": 581.261,
-    "eval_steps_per_second": 36.398
+    "epoch": 0.0,
+    "eval_loss": 2.043109178543091,
+    "eval_runtime": 12.8998,
+    "eval_samples_per_second": 609.078,
+    "eval_steps_per_second": 38.14
 }

runs/Feb24_00-04-25_bd236bb80193/events.out.tfevents.1708733095.bd236bb80193.37.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14bd2e3ee3c5b4adde9589d9edd0fe5032b6ac6246666af865022bb732304326
+size 5342

runs/Feb24_00-05-16_bd236bb80193/events.out.tfevents.1708733139.bd236bb80193.413.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:056ffc6ba8d477c8d7a49b8aed88ea3551315eb633fbd72eae1b4520cb6024c1
+size 5691

runs/Feb24_00-05-16_bd236bb80193/events.out.tfevents.1708733153.bd236bb80193.413.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a923660a4f2cfd27f425ca843977587f67ee4cfd04b0c3883553ba83d9fb6df
+size 354

runs/Feb24_00-08-06_bd236bb80193/events.out.tfevents.1708733309.bd236bb80193.988.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:933752e60e1039ea736004287e5574a9b6b48e73fbfb2b69c188daa264b5bcd3
+size 5691

runs/Feb24_00-08-06_bd236bb80193/events.out.tfevents.1708733322.bd236bb80193.988.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb40150c9eef6df850249faccc4638b6810165c4ff7c89209825de66112280fa
+size 354

special_tokens_map.json

@@ -101,25 +101,7 @@
     "<extra_id_98>",
     "<extra_id_99>"
   ],
-  "eos_token": {
-    "content": "</s>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "pad_token": {
-    "content": "<pad>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "unk_token": {
-    "content": "<unk>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  }
+  "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

tokenizer.json

@@ -964,8 +964,7 @@
   "pre_tokenizer": {
     "type": "Metaspace",
     "replacement": "▁",
-    "add_prefix_space": true,
-    "prepend_scheme": "always"
+    "add_prefix_space": true
   },
   "post_processor": {
     "type": "TemplateProcessing",
@@ -1024,8 +1023,7 @@
   "decoder": {
     "type": "Metaspace",
     "replacement": "▁",
-    "add_prefix_space": true,
-    "prepend_scheme": "always"
+    "add_prefix_space": true
   },
   "model": {
     "type": "Unigram",

train_results.json

@@ -1,7 +1,7 @@
 {
-    "epoch": 10.0,
-    "train_loss": 0.23933088928222657,
-    "train_runtime": 648.1335,
-    "train_samples_per_second": 154.289,
-    "train_steps_per_second": 9.643
+    "epoch": 0.0,
+    "train_loss": 2.5783498287200928,
+    "train_runtime": 0.3238,
+    "train_samples_per_second": 30.88,
+    "train_steps_per_second": 3.088
 }

trainer_state.json

@@ -1,210 +1,28 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 10.0,
+  "epoch": 0.0016,
   "eval_steps": 500,
-  "global_step": 6250,
+  "global_step": 1,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.8,
-      "grad_norm": 0.5397563576698303,
-      "learning_rate": 0.00092,
-      "loss": 0.4956,
-      "step": 500
-    },
-    {
-      "epoch": 0.8,
-      "eval_loss": 0.2178906500339508,
-      "eval_runtime": 13.319,
-      "eval_samples_per_second": 589.908,
-      "eval_steps_per_second": 36.94,
-      "step": 500
-    },
-    {
-      "epoch": 1.6,
-      "grad_norm": 0.549730122089386,
-      "learning_rate": 0.00084,
-      "loss": 0.3076,
-      "step": 1000
-    },
-    {
-      "epoch": 1.6,
-      "eval_loss": 0.18326763808727264,
-      "eval_runtime": 13.3435,
-      "eval_samples_per_second": 588.825,
-      "eval_steps_per_second": 36.872,
-      "step": 1000
-    },
-    {
-      "epoch": 2.4,
-      "grad_norm": 0.5204197764396667,
-      "learning_rate": 0.00076,
-      "loss": 0.2707,
-      "step": 1500
-    },
-    {
-      "epoch": 2.4,
-      "eval_loss": 0.17023101449012756,
-      "eval_runtime": 13.2516,
-      "eval_samples_per_second": 592.91,
-      "eval_steps_per_second": 37.128,
-      "step": 1500
-    },
-    {
-      "epoch": 3.2,
-      "grad_norm": 0.3998057246208191,
-      "learning_rate": 0.00068,
-      "loss": 0.2439,
-      "step": 2000
-    },
-    {
-      "epoch": 3.2,
-      "eval_loss": 0.160837784409523,
-      "eval_runtime": 13.2287,
-      "eval_samples_per_second": 593.936,
-      "eval_steps_per_second": 37.192,
-      "step": 2000
-    },
-    {
-      "epoch": 4.0,
-      "grad_norm": 0.41501811146736145,
-      "learning_rate": 0.0006,
-      "loss": 0.2295,
-      "step": 2500
-    },
-    {
-      "epoch": 4.0,
-      "eval_loss": 0.15653032064437866,
-      "eval_runtime": 13.2124,
-      "eval_samples_per_second": 594.669,
-      "eval_steps_per_second": 37.238,
-      "step": 2500
-    },
-    {
-      "epoch": 4.8,
-      "grad_norm": 0.4228770136833191,
-      "learning_rate": 0.0005200000000000001,
-      "loss": 0.2163,
-      "step": 3000
-    },
-    {
-      "epoch": 4.8,
-      "eval_loss": 0.15016524493694305,
-      "eval_runtime": 13.3446,
-      "eval_samples_per_second": 588.779,
-      "eval_steps_per_second": 36.869,
-      "step": 3000
-    },
-    {
-      "epoch": 5.6,
-      "grad_norm": 0.48046761751174927,
-      "learning_rate": 0.00044,
-      "loss": 0.2058,
-      "step": 3500
-    },
-    {
-      "epoch": 5.6,
-      "eval_loss": 0.15010309219360352,
-      "eval_runtime": 13.3435,
-      "eval_samples_per_second": 588.824,
-      "eval_steps_per_second": 36.872,
-      "step": 3500
-    },
-    {
-      "epoch": 6.4,
-      "grad_norm": 0.3269839882850647,
-      "learning_rate": 0.00035999999999999997,
-      "loss": 0.2009,
-      "step": 4000
-    },
-    {
-      "epoch": 6.4,
-      "eval_loss": 0.1457582265138626,
-      "eval_runtime": 13.3297,
-      "eval_samples_per_second": 589.435,
-      "eval_steps_per_second": 36.91,
-      "step": 4000
-    },
-    {
-      "epoch": 7.2,
-      "grad_norm": 0.618806004524231,
-      "learning_rate": 0.00028000000000000003,
-      "loss": 0.1898,
-      "step": 4500
-    },
-    {
-      "epoch": 7.2,
-      "eval_loss": 0.14268401265144348,
-      "eval_runtime": 13.3194,
-      "eval_samples_per_second": 589.89,
-      "eval_steps_per_second": 36.939,
-      "step": 4500
-    },
-    {
-      "epoch": 8.0,
-      "grad_norm": 0.32574233412742615,
-      "learning_rate": 0.0002,
-      "loss": 0.1874,
-      "step": 5000
-    },
-    {
-      "epoch": 8.0,
-      "eval_loss": 0.14275924861431122,
-      "eval_runtime": 13.3109,
-      "eval_samples_per_second": 590.268,
-      "eval_steps_per_second": 36.962,
-      "step": 5000
-    },
-    {
-      "epoch": 8.8,
-      "grad_norm": 0.5372352600097656,
-      "learning_rate": 0.00012,
-      "loss": 0.1792,
-      "step": 5500
-    },
-    {
-      "epoch": 8.8,
-      "eval_loss": 0.13903391361236572,
-      "eval_runtime": 13.3118,
-      "eval_samples_per_second": 590.229,
-      "eval_steps_per_second": 36.96,
-      "step": 5500
-    },
-    {
-      "epoch": 9.6,
-      "grad_norm": 0.2961955964565277,
-      "learning_rate": 4e-05,
-      "loss": 0.1757,
-      "step": 6000
-    },
-    {
-      "epoch": 9.6,
-      "eval_loss": 0.13857147097587585,
-      "eval_runtime": 13.3572,
-      "eval_samples_per_second": 588.22,
-      "eval_steps_per_second": 36.834,
-      "step": 6000
-    },
-    {
-      "epoch": 10.0,
-      "step": 6250,
-      "total_flos": 3231326208000000.0,
-      "train_loss": 0.23933088928222657,
-      "train_runtime": 648.1335,
-      "train_samples_per_second": 154.289,
-      "train_steps_per_second": 9.643
+      "epoch": 0.0,
+      "step": 1,
+      "total_flos": 517012193280.0,
+      "train_loss": 2.5783498287200928,
+      "train_runtime": 0.3238,
+      "train_samples_per_second": 30.88,
+      "train_steps_per_second": 3.088
     }
   ],
   "logging_steps": 500,
-  "max_steps": 6250,
-  "num_input_tokens_seen": 0,
-  "num_train_epochs": 10,
+  "max_steps": 1,
+  "num_train_epochs": 1,
   "save_steps": 500,
-  "total_flos": 3231326208000000.0,
-  "train_batch_size": 16,
+  "total_flos": 517012193280.0,
   "trial_name": null,
   "trial_params": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de0a6dccc98d554d66a76fdbd912807ac60d3ab3c7edc5013d73b41ae0605b67
-size 5048
+oid sha256:aa8ecf515d6c00e0bde4f518167dadc8c68220a2f8351cd581c44d0e29e7c706
+size 4856