Model save

README.md

@@ -1,5 +1,4 @@
 ---
-license: apache-2.0
 library_name: peft
 tags:
 - trl
@@ -7,7 +6,7 @@ tags:
 - generated_from_trainer
 datasets:
 - generator
-base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
+base_model: data/Tukan-1.1B-Chat-reasoning-sft-COLA_merged_0
 model-index:
 - name: Tukan-1.1B-Chat-reasoning-sft-COLA
   results: []
@@ -18,9 +17,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # Tukan-1.1B-Chat-reasoning-sft-COLA
 
-This model is a fine-tuned version of [TinyLlama/TinyLlama-1.1B-Chat-v1.0](https://huggingface.co/TinyLlama/TinyLlama-1.1B-Chat-v1.0) on the generator dataset.
+This model was trained from scratch on the generator dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.5464
+- Loss: 1.5414
 
 ## Model description
 

adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "TinyLlama/TinyLlama-1.1B-Chat-v1.0",
+  "base_model_name_or_path": "data/Tukan-1.1B-Chat-reasoning-sft-COLA_merged_0",
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:68b264ea9c5c8573c5bac38b0d63c8d49f62b4bc8f9b8b97dcb0cff3e141bf3a
+oid sha256:57448e5cb7a06f63d75e80343ec9dff64ed69de618f3355b139bf7ce1d2a649b
 size 26361536

all_results.json

@@ -1,13 +1,13 @@
 {
     "epoch": 0.95,
-    "eval_loss": 1.5464149713516235,
-    "eval_runtime": 1.3787,
+    "eval_loss": 1.541361689567566,
+    "eval_runtime": 1.365,
     "eval_samples": 36,
-    "eval_samples_per_second": 5.077,
-    "eval_steps_per_second": 2.176,
-    "train_loss": 1.5683434009552002,
-    "train_runtime": 86.2408,
+    "eval_samples_per_second": 5.128,
+    "eval_steps_per_second": 2.198,
+    "train_loss": 1.5626062154769897,
+    "train_runtime": 77.8859,
     "train_samples": 682,
-    "train_samples_per_second": 1.415,
-    "train_steps_per_second": 0.012
+    "train_samples_per_second": 1.566,
+    "train_steps_per_second": 0.013
 }

eval_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 0.95,
-    "eval_loss": 1.5464149713516235,
-    "eval_runtime": 1.3787,
+    "eval_loss": 1.541361689567566,
+    "eval_runtime": 1.365,
     "eval_samples": 36,
-    "eval_samples_per_second": 5.077,
-    "eval_steps_per_second": 2.176
+    "eval_samples_per_second": 5.128,
+    "eval_steps_per_second": 2.198
 }

runs/Jan21_18-49-28_98f107f1aa39/events.out.tfevents.1705863099.98f107f1aa39.101023.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bfc5a974ad8564f3e58f2769d1e202c406e6b1e728e8d9ad4b21f6ca693f6d4d
+size 5056

runs/Jan21_18-49-28_98f107f1aa39/events.out.tfevents.1705863178.98f107f1aa39.101023.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0b3f57672fd5497ae285e40cfa80891173e949bbfe7b2944ee4b4f369deb7d1
+size 354

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 0.95,
-    "train_loss": 1.5683434009552002,
-    "train_runtime": 86.2408,
+    "train_loss": 1.5626062154769897,
+    "train_runtime": 77.8859,
     "train_samples": 682,
-    "train_samples_per_second": 1.415,
-    "train_steps_per_second": 0.012
+    "train_samples_per_second": 1.566,
+    "train_steps_per_second": 0.013
 }

trainer_state.json

@@ -11,17 +11,17 @@
     {
       "epoch": 0.95,
       "learning_rate": 0.0,
-      "loss": 1.5683,
+      "loss": 1.5626,
       "step": 1
     },
     {
       "epoch": 0.95,
       "step": 1,
       "total_flos": 1535153516052480.0,
-      "train_loss": 1.5683434009552002,
-      "train_runtime": 86.2408,
-      "train_samples_per_second": 1.415,
-      "train_steps_per_second": 0.012
+      "train_loss": 1.5626062154769897,
+      "train_runtime": 77.8859,
+      "train_samples_per_second": 1.566,
+      "train_steps_per_second": 0.013
     }
   ],
   "logging_steps": 5,