Finished training grade 4

README.md

@@ -13,11 +13,12 @@ model-index:
 should probably proofread and complete it, then remove this comment. -->
 
 [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/uds/Graded%20text%20simplification%20training/runs/npazoj3b)
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/uds/Graded%20text%20simplification%20training/runs/qel7fkh2)
 # text-simplification
 
 This model is a fine-tuned version of [openai-community/gpt2](https://huggingface.co/openai-community/gpt2) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6855
+- Loss: 0.7900
 
 ## Model description
 
@@ -48,11 +49,11 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 2.7433        | 1.0   | 235  | 0.8105          |
-| 0.828         | 2.0   | 470  | 0.7119          |
-| 0.7698        | 3.0   | 705  | 0.6963          |
-| 0.7587        | 4.0   | 940  | 0.6880          |
-| 0.753         | 5.0   | 1175 | 0.6855          |
+| 1.6926        | 1.0   | 587  | 0.8267          |
+| 0.8799        | 2.0   | 1174 | 0.7998          |
+| 0.8552        | 3.0   | 1761 | 0.7930          |
+| 0.846         | 4.0   | 2348 | 0.7905          |
+| 0.8424        | 5.0   | 2935 | 0.7900          |
 
 
 ### Framework versions

gpt2-grade-4-4module/adapter_config.json

@@ -0,0 +1,31 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": null,
+  "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": {},
+  "revision": null,
+  "target_modules": [
+    "lm_head",
+    "c_attn",
+    "c_fc",
+    "c_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

gpt2-grade-4-4module/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8ee8cecef40c94c0ebb2bfd422db4faf0d00e9b24a69c0c7939e7328d3d5441
+size 83582999

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a017bee5a001f1c54eb71efdea1d62bfff082fc4dc1dcf2a2215afc416a7663d
+oid sha256:359827dcd757afbec25603cf90a541779865d4e5e7a682c6e15e0a61a6131a06
 size 5240