End of training

README.md

@@ -2,6 +2,8 @@
 license: apache-2.0
 tags:
 - generated_from_trainer
+datasets:
+- xlcost-text-to-code
 model-index:
 - name: flan-t5-xl-codeparrot-xlcost-text-to-code
   results: []
@@ -12,7 +14,18 @@ should probably proofread and complete it, then remove this comment. -->
 
 # flan-t5-xl-codeparrot-xlcost-text-to-code
 
-This model is a fine-tuned version of [google/flan-t5-xl](https://huggingface.co/google/flan-t5-xl) on an unknown dataset.
+This model is a fine-tuned version of [epinnock/flan-t5-xl-codeparrot-xlcost-text-to-code](https://huggingface.co/epinnock/flan-t5-xl-codeparrot-xlcost-text-to-code) on the xlcost-text-to-code dataset.
+It achieves the following results on the evaluation set:
+- eval_loss: 1.9876
+- eval_rouge1: 43.1227
+- eval_rouge2: 25.6539
+- eval_rougeL: 41.8635
+- eval_rougeLsum: 41.8883
+- eval_gen_len: 9.0445
+- eval_runtime: 1137.2469
+- eval_samples_per_second: 7.17
+- eval_steps_per_second: 0.897
+- step: 0
 
 ## Model description
 
@@ -33,9 +46,8 @@ More information needed
 The following hyperparameters were used during training:
 - learning_rate: 3e-05
 - train_batch_size: 6
-- eval_batch_size: 64
+- eval_batch_size: 8
 - seed: 42
-- distributed_type: multi-GPU
 - gradient_accumulation_steps: 24
 - total_train_batch_size: 144
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "google/flan-t5-xl",
+  "_name_or_path": "epinnock/flan-t5-xl-codeparrot-xlcost-text-to-code",
   "architectures": [
     "T5ForConditionalGeneration"
   ],

logs/events.out.tfevents.1675268686.n7boh0yjgo.2602.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e29ac3a3a4f50b91df243d0465d1e584914ccdf580bfd9c8cb777f11c3acf40
+size 532

logs/events.out.tfevents.1675268748.n7boh0yjgo.2602.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7667a2c8aadb974adef23d78562ff714b6e742287eadb92e9a509a883458bf99
+size 368

logs/events.out.tfevents.1675270112.n7boh0yjgo.2602.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11400ffbc8f9b2daaedd5c83126713694cab42fc9d01bf612a9e865c8c24ab42
+size 488

tokenizer.json

@@ -1,21 +1,7 @@
 {
   "version": "1.0",
-  "truncation": {
-    "direction": "Right",
-    "max_length": 250,
-    "strategy": "LongestFirst",
-    "stride": 0
-  },
-  "padding": {
-    "strategy": {
-      "Fixed": 250
-    },
-    "direction": "Right",
-    "pad_to_multiple_of": null,
-    "pad_id": 0,
-    "pad_type_id": 0,
-    "pad_token": "<pad>"
-  },
+  "truncation": null,
+  "padding": null,
   "added_tokens": [
     {
       "id": 0,

tokenizer_config.json

@@ -104,7 +104,7 @@
   "eos_token": "</s>",
   "extra_ids": 100,
   "model_max_length": 512,
-  "name_or_path": "google/flan-t5-xl",
+  "name_or_path": "epinnock/flan-t5-xl-codeparrot-xlcost-text-to-code",
   "pad_token": "<pad>",
   "sp_model_kwargs": {},
   "special_tokens_map_file": "/home/arthur_huggingface_co/.cache/huggingface/hub/models--google--t5-v1_1-small/snapshots/fb7e6cba609f7bab11c614294bc04f82f613c7b1/special_tokens_map.json",

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:83a1f644d6ee766a94a5f29d48dd5050dfbdbeb74ecd16b8d88aacb245558dff
+oid sha256:491e1d6ab27ed0a02576cb652b859006579b223f27eab55bbd954b8f42e1efc3
 size 3695