Model save

README.md

@@ -14,6 +14,8 @@ should probably proofread and complete it, then remove this comment. -->
 # robust_llm_r2d2_tom-debug_pythia-14m_lora
 
 This model is a fine-tuned version of [EleutherAI/pythia-14m](https://huggingface.co/EleutherAI/pythia-14m) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 6.2327
 
 ## Model description
 
@@ -41,6 +43,13 @@ The following hyperparameters were used during training:
 - lr_scheduler_type: cosine
 - training_steps: 1
 
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 9.125         | 0.0   | 1    | 6.2329          |
+
+
 ### Framework versions
 
 - Transformers 4.37.2

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b6657d938dee44bb28d765adcb19d3a0c428e055ca6ceab9ed26c3a22b160691
+oid sha256:b3d46417fab125b3c2e4fab028940f6a27ec11dff0d062f4d87ef1d710e57395
 size 198216

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 0.0,
+    "eval_loss": 6.23274040222168,
+    "eval_runtime": 52.0876,
+    "eval_samples": 23110,
+    "eval_samples_per_second": 443.676,
+    "eval_steps_per_second": 55.464,
+    "train_loss": 9.125,
+    "train_runtime": 57.0654,
+    "train_samples": 207865,
+    "train_samples_per_second": 0.07,
+    "train_steps_per_second": 0.018
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.0,
+    "eval_loss": 6.23274040222168,
+    "eval_runtime": 52.0876,
+    "eval_samples": 23110,
+    "eval_samples_per_second": 443.676,
+    "eval_steps_per_second": 55.464
+}

runs/Feb05_19-16-43_r2d2-devbox-6vt8q/events.out.tfevents.1738783026.r2d2-devbox-6vt8q.6908.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:59e3b7f43701f40e1f7616cd19288c53505543fd63577e8075ae31aa797ace12
-size 4608
+oid sha256:f0744892dea0535e4e419a44eb564261de427a2f8ace0c67a8521e65da59e526
+size 5376

runs/Feb05_19-16-43_r2d2-devbox-6vt8q/events.out.tfevents.1738783135.r2d2-devbox-6vt8q.6908.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca59dceda4459acdf537c83649d3357e85e94f0562a8821a4efab636b865572b
+size 354

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.0,
+    "train_loss": 9.125,
+    "train_runtime": 57.0654,
+    "train_samples": 207865,
+    "train_samples_per_second": 0.07,
+    "train_steps_per_second": 0.018
+}

trainer_state.json

@@ -0,0 +1,44 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.9242981122635517e-05,
+  "eval_steps": 500,
+  "global_step": 1,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0,
+      "loss": 9.125,
+      "step": 1
+    },
+    {
+      "epoch": 0.0,
+      "eval_loss": 6.232901573181152,
+      "eval_runtime": 52.8258,
+      "eval_samples_per_second": 437.476,
+      "eval_steps_per_second": 54.689,
+      "step": 1
+    },
+    {
+      "epoch": 0.0,
+      "step": 1,
+      "total_flos": 379802615808.0,
+      "train_loss": 9.125,
+      "train_runtime": 57.0654,
+      "train_samples_per_second": 0.07,
+      "train_steps_per_second": 0.018
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 1,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "total_flos": 379802615808.0,
+  "train_batch_size": null,
+  "trial_name": null,
+  "trial_params": null
+}