End of training

README.md

@@ -1,8 +1,9 @@
 ---
 license: apache-2.0
-base_model: google/flan-t5-small
+library_name: peft
 tags:
 - generated_from_trainer
+base_model: google/flan-t5-small
 model-index:
 - name: flan-base-sql
   results: []
@@ -15,7 +16,7 @@ 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: 0.1649
+- Loss: 2.0196
 
 ## Model description
 
@@ -38,24 +39,18 @@ The following hyperparameters were used during training:
 - train_batch_size: 16
 - eval_batch_size: 16
 - seed: 42
-- distributed_type: multi-GPU
-- num_devices: 8
-- total_train_batch_size: 128
-- total_eval_batch_size: 128
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 10.0
+- num_epochs: 0.0001
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss |
-|:-------------:|:-----:|:----:|:---------------:|
-| 0.4024        | 6.33  | 500  | 0.1728          |
 
 
 ### Framework versions
 
-- Transformers 4.36.0.dev0
-- Pytorch 2.1.0+cu118
-- Datasets 2.14.6
-- Tokenizers 0.14.1
+- PEFT 0.7.1
+- Transformers 4.38.0
+- Pytorch 2.1.2+cu121
+- Datasets 2.17.0
+- Tokenizers 0.15.2

adapter_config.json

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

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:41e5a6c074adf70a3081c0bd661b8d62426a9507595d7d7a2ec73bd4767e2067
+oid sha256:c0a437b988026fcdec3ff95b8370ab7dc9f9498d23bb52b7d853d82bd45c24a1
 size 2765880

all_results.json

@@ -1,11 +1,11 @@
 {
-    "epoch": 10.0,
-    "eval_loss": 0.16487877070903778,
-    "eval_runtime": 2.8546,
-    "eval_samples_per_second": 2752.375,
-    "eval_steps_per_second": 21.719,
-    "train_loss": 0.3472654608231557,
-    "train_runtime": 106.5441,
-    "train_samples_per_second": 938.578,
-    "train_steps_per_second": 7.415
+    "epoch": 0.02,
+    "eval_loss": 2.0195727348327637,
+    "eval_runtime": 13.0603,
+    "eval_samples_per_second": 601.592,
+    "eval_steps_per_second": 37.671,
+    "train_loss": 2.8207314014434814,
+    "train_runtime": 0.8917,
+    "train_samples_per_second": 0.112,
+    "train_steps_per_second": 1.121
 }

eval_results.json

@@ -1,7 +1,7 @@
 {
-    "epoch": 10.0,
-    "eval_loss": 0.16487877070903778,
-    "eval_runtime": 2.8546,
-    "eval_samples_per_second": 2752.375,
-    "eval_steps_per_second": 21.719
+    "epoch": 0.02,
+    "eval_loss": 2.0195727348327637,
+    "eval_runtime": 13.0603,
+    "eval_samples_per_second": 601.592,
+    "eval_steps_per_second": 37.671
 }

special_tokens_map.json

@@ -101,7 +101,25 @@
     "<extra_id_98>",
     "<extra_id_99>"
   ],
-  "eos_token": "</s>",
-  "pad_token": "<pad>",
-  "unk_token": "<unk>"
+  "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
+  }
 }

tokenizer.json

@@ -2,13 +2,13 @@
   "version": "1.0",
   "truncation": {
     "direction": "Right",
-    "max_length": 47,
+    "max_length": 46,
     "strategy": "LongestFirst",
     "stride": 0
   },
   "padding": {
     "strategy": {
-      "Fixed": 47
+      "Fixed": 46
     },
     "direction": "Right",
     "pad_to_multiple_of": null,
@@ -964,7 +964,8 @@
   "pre_tokenizer": {
     "type": "Metaspace",
     "replacement": "▁",
-    "add_prefix_space": true
+    "add_prefix_space": true,
+    "prepend_scheme": "always"
   },
   "post_processor": {
     "type": "TemplateProcessing",
@@ -1023,7 +1024,8 @@
   "decoder": {
     "type": "Metaspace",
     "replacement": "▁",
-    "add_prefix_space": true
+    "add_prefix_space": true,
+    "prepend_scheme": "always"
   },
   "model": {
     "type": "Unigram",

train_results.json

@@ -1,7 +1,7 @@
 {
-    "epoch": 10.0,
-    "train_loss": 0.3472654608231557,
-    "train_runtime": 106.5441,
-    "train_samples_per_second": 938.578,
-    "train_steps_per_second": 7.415
+    "epoch": 0.02,
+    "train_loss": 2.8207314014434814,
+    "train_runtime": 0.8917,
+    "train_samples_per_second": 0.112,
+    "train_steps_per_second": 1.121
 }

trainer_state.json

@@ -1,42 +1,30 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 10.0,
+  "epoch": 0.015873015873015872,
   "eval_steps": 500,
-  "global_step": 790,
+  "global_step": 1,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 6.33,
-      "learning_rate": 0.0003670886075949367,
-      "loss": 0.4024,
-      "step": 500
-    },
-    {
-      "epoch": 6.33,
-      "eval_loss": 0.17280669510364532,
-      "eval_runtime": 2.8781,
-      "eval_samples_per_second": 2729.968,
-      "eval_steps_per_second": 21.542,
-      "step": 500
-    },
-    {
-      "epoch": 10.0,
-      "step": 790,
-      "total_flos": 3267517032169472.0,
-      "train_loss": 0.3472654608231557,
-      "train_runtime": 106.5441,
-      "train_samples_per_second": 938.578,
-      "train_steps_per_second": 7.415
+      "epoch": 0.02,
+      "step": 1,
+      "total_flos": 517012193280.0,
+      "train_loss": 2.8207314014434814,
+      "train_runtime": 0.8917,
+      "train_samples_per_second": 0.112,
+      "train_steps_per_second": 1.121
     }
   ],
   "logging_steps": 500,
-  "max_steps": 790,
-  "num_train_epochs": 10,
+  "max_steps": 1,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
   "save_steps": 500,
-  "total_flos": 3267517032169472.0,
+  "total_flos": 517012193280.0,
+  "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:73516ab6f53c226d6a40128d334ce1313b9d34fdf37c818f3cb4ba28312154df
-size 4856
+oid sha256:4fc556c3de983d027da1ff74eb7ff292ea3fd4da4549339f39cafc1347592486
+size 5112