End of training

README.md

@@ -1,6 +1,6 @@
 ---
-license: apache-2.0
-base_model: codeparrot/codeparrot-small
+license: bsd-3-clause
+base_model: Salesforce/codegen-350M-mono
 tags:
 - generated_from_trainer
 model-index:
@@ -13,7 +13,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # PyLoomer_CodeParrot
 
-This model is a fine-tuned version of [codeparrot/codeparrot-small](https://huggingface.co/codeparrot/codeparrot-small) on an unknown dataset.
+This model is a fine-tuned version of [Salesforce/codegen-350M-mono](https://huggingface.co/Salesforce/codegen-350M-mono) on an unknown dataset.
 
 ## Model description
 
@@ -33,8 +33,8 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 0.0001
-- train_batch_size: 6
-- eval_batch_size: 6
+- train_batch_size: 2
+- eval_batch_size: 2
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear

adapter_config.json

@@ -1,6 +1,6 @@
 {
   "auto_mapping": null,
-  "base_model_name_or_path": "codeparrot/codeparrot-small",
+  "base_model_name_or_path": "Salesforce/codegen-350M-mono",
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,
@@ -14,7 +14,7 @@
   "r": 8,
   "revision": null,
   "target_modules": [
-    "c_attn"
+    "qkv_proj"
   ],
   "task_type": "CAUSAL_LM"
 }

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90bfa4ff95e678a3605aa40c2b742757b30e0f87a64cd36aa89c2ef065777237
-size 1188025
+oid sha256:a7fbfe3de320fee92686dae4ea51384102e7601e2b2c0241ebb5194094d82261
+size 2635433

added_tokens.json

@@ -1,7 +1,45 @@
 {
-  "<ASSISTANT_TASK:>": 32771,
-  "<END_TASK>": 32772,
-  "<SYSTEM_TASK:>": 32769,
-  "<USER_TASK:>": 32770,
-  "<|PAD|>": 32768
+  "\t\t": 50294,
+  "\t\t\t": 50293,
+  "\t\t\t\t": 50292,
+  "\t\t\t\t\t": 50291,
+  "\t\t\t\t\t\t": 50290,
+  "\t\t\t\t\t\t\t": 50289,
+  "\t\t\t\t\t\t\t\t": 50288,
+  "\t\t\t\t\t\t\t\t\t": 50287,
+  "  ": 50286,
+  "   ": 50285,
+  "    ": 50284,
+  "     ": 50283,
+  "      ": 50282,
+  "       ": 50281,
+  "        ": 50280,
+  "         ": 50279,
+  "          ": 50278,
+  "           ": 50277,
+  "            ": 50276,
+  "             ": 50275,
+  "              ": 50274,
+  "               ": 50273,
+  "                ": 50272,
+  "                 ": 50271,
+  "                  ": 50270,
+  "                   ": 50269,
+  "                    ": 50268,
+  "                     ": 50267,
+  "                      ": 50266,
+  "                       ": 50265,
+  "                        ": 50264,
+  "                         ": 50263,
+  "                          ": 50262,
+  "                           ": 50261,
+  "                            ": 50260,
+  "                             ": 50259,
+  "                              ": 50258,
+  "                               ": 50257,
+  "<ASSISTANT_TASK:>": 50298,
+  "<END_TASK>": 50299,
+  "<SYSTEM_TASK:>": 50296,
+  "<USER_TASK:>": 50297,
+  "<|PAD|>": 50295
 }

tokenizer_config.json

@@ -9,8 +9,8 @@
   "bos_token": "<|endoftext|>",
   "clean_up_tokenization_spaces": true,
   "eos_token": "<|endoftext|>",
-  "model_max_length": 5000,
+  "model_max_length": 2048,
   "pad_token": "<|PAD|>",
-  "tokenizer_class": "GPT2Tokenizer",
+  "tokenizer_class": "CodeGenTokenizer",
   "unk_token": "<|endoftext|>"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c972704e61d011e855ba280a4c3b5b3b8cab5d2aaf47fbbb2c732b43b8c895a0
+oid sha256:514277c1178436a679fc1c176f6553af2198dc0889010b1b9d9306673a3e8302
 size 3963