Training in progress, epoch 1

config.json

@@ -1,27 +1,34 @@
 {
-  "_name_or_path": "Salesforce/codet5-large",
+  "_name_or_path": "Salesforce/codet5-base",
   "architectures": [
     "T5ForConditionalGeneration"
   ],
   "bos_token_id": 1,
   "classifier_dropout": 0.0,
-  "d_ff": 4096,
+  "d_ff": 3072,
   "d_kv": 64,
-  "d_model": 1024,
+  "d_model": 768,
   "decoder_start_token_id": 0,
   "dense_act_fn": "relu",
   "dropout_rate": 0.1,
   "eos_token_id": 2,
   "feed_forward_proj": "relu",
+  "gradient_checkpointing": false,
+  "id2label": {
+    "0": "LABEL_0"
+  },
   "initializer_factor": 1.0,
   "is_encoder_decoder": true,
   "is_gated_act": false,
+  "label2id": {
+    "LABEL_0": 0
+  },
   "layer_norm_epsilon": 1e-06,
   "model_type": "t5",
   "n_positions": 512,
-  "num_decoder_layers": 24,
-  "num_heads": 16,
-  "num_layers": 24,
+  "num_decoder_layers": 12,
+  "num_heads": 12,
+  "num_layers": 12,
   "output_past": true,
   "pad_token_id": 0,
   "relative_attention_max_distance": 128,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:65d7cdb02fe27aeee39251489bbbe46a5d351bbf2e19ac0e962110e4b328e49f
-size 2950619856
+oid sha256:3282a9fcb084e437a7597680bb8c8f5e8255cafe919994f306fc05ed1985358b
+size 891558696

runs/Sep04_08-28-26_150f82326940/events.out.tfevents.1725438507.150f82326940.477.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef2d721a76b0e10b49ca19e257414257bcb4e22129db3f72ad9f30867c1d2b1b
+size 4184

tokenizer_config.json

@@ -954,6 +954,5 @@
   "pad_token": "</s>",
   "sep_token": "</s>",
   "tokenizer_class": "RobertaTokenizer",
-  "trim_offsets": true,
   "unk_token": "<unk>"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bfbf22f7f0d66894f58d2bb61806dcf1c488bdd5c6f58fdf12fdf56c60289280
+oid sha256:91a9ff0eb59ca66abc591eb4ba1dbdb71f5a4978c8e6cde5a9cef57e382b3f41
 size 5304