Bodnar485/EveDiablo_q150_epoch500

README.md

@@ -40,7 +40,7 @@ The following hyperparameters were used during training:
 - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 10
-- num_epochs: 1000
+- num_epochs: 250
 
 ### Framework versions
 

adapter_config.json

@@ -1,12 +1,12 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": null,
+  "base_model_name_or_path": "microsoft/DialoGPT-small",
   "bias": "none",
   "corda_config": null,
   "eva_config": null,
   "exclude_modules": null,
-  "fan_in_fan_out": false,
+  "fan_in_fan_out": true,
   "inference_mode": true,
   "init_lora_weights": true,
   "layer_replication": null,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8540c0ab74a669013e6238bbf75b9fd0d915691a21a4440cbd36822e0cfd7a75
-size 1183904
+oid sha256:b3c939e619acf5e34ced1870c40a84a3d62c26d16a8506c435a533c090938072
+size 309968192

tokenizer.json

@@ -1,7 +1,21 @@
 {
   "version": "1.0",
-  "truncation": null,
-  "padding": null,
+  "truncation": {
+    "direction": "Right",
+    "max_length": 64,
+    "strategy": "LongestFirst",
+    "stride": 0
+  },
+  "padding": {
+    "strategy": {
+      "Fixed": 64
+    },
+    "direction": "Right",
+    "pad_to_multiple_of": null,
+    "pad_id": 50257,
+    "pad_type_id": 0,
+    "pad_token": "[PAD]"
+  },
   "added_tokens": [
     {
       "id": 50256,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:59fa6bcff753d682e410f4f562860a89efaa5ff046eab6490dc3cf0b77e1879e
+oid sha256:c64987f690b54a7f83ffba85e215828b1f0bdfef275c865f774f7a64ca1bda79
 size 5304