End of training

README.md

@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [google/flan-t5-base](https://huggingface.co/google/flan-t5-base) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.1643
+- Loss: 2.3690
 
 ## Model description
 
@@ -47,11 +47,11 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| No log        | 1.0   | 495  | 2.1898          |
-| 2.5036        | 2.0   | 990  | 2.1677          |
-| 2.4433        | 3.0   | 1485 | 2.1651          |
-| 2.4366        | 4.0   | 1980 | 2.1646          |
-| 2.429         | 5.0   | 2475 | 2.1643          |
+| No log        | 1.0   | 495  | 2.3722          |
+| 2.5796        | 2.0   | 990  | 2.3708          |
+| 2.5828        | 3.0   | 1485 | 2.3707          |
+| 2.5714        | 4.0   | 1980 | 2.3701          |
+| 2.5735        | 5.0   | 2475 | 2.3690          |
 
 
 ### Framework versions

adapter_config.json

@@ -1,29 +1,17 @@
 {
-  "alpha_pattern": {},
   "auto_mapping": null,
   "base_model_name_or_path": "google/flan-t5-base",
-  "bias": "none",
-  "fan_in_fan_out": false,
   "inference_mode": true,
-  "init_lora_weights": true,
-  "layer_replication": null,
-  "layers_pattern": null,
-  "layers_to_transform": null,
-  "loftq_config": {},
-  "lora_alpha": 32,
-  "lora_dropout": 0.01,
-  "megatron_config": null,
-  "megatron_core": "megatron.core",
-  "modules_to_save": null,
-  "peft_type": "LORA",
-  "r": 8,
-  "rank_pattern": {},
+  "num_attention_heads": 12,
+  "num_layers": 12,
+  "num_transformer_submodules": 2,
+  "num_virtual_tokens": 10,
+  "peft_type": "PROMPT_TUNING",
+  "prompt_tuning_init": "RANDOM",
+  "prompt_tuning_init_text": null,
   "revision": null,
-  "target_modules": [
-    "v",
-    "q"
-  ],
   "task_type": "SEQ_2_SEQ_LM",
-  "use_dora": false,
-  "use_rslora": false
+  "token_dim": 768,
+  "tokenizer_kwargs": null,
+  "tokenizer_name_or_path": "google/flan-t5-base"
 }

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:885913014880b673efc89d8fae2a30e4aec23474b872f1520ead8a8a06f7d20d
-size 1789464
+oid sha256:c31651102ba4c854160dd450bba4fe5f0c34018aaf3a0cb1679b8de2db77c49c
+size 61560

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5cd4b1d44432aa9f52152cc40d801191e9b1b39f5f09c4b84aaad399d9ddd8dc
+oid sha256:5a577be0aea0688c3353fa26bf982d656c599ab56beceeafece1760076288a01
 size 5240