End of training

README.md

@@ -2,7 +2,7 @@
 tags:
 - generated_from_trainer
 datasets:
-- category_cleaning
+- Displate/category_cleaning
 model-index:
 - name: category_cleaning
   results: []
@@ -13,7 +13,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # category_cleaning
 
-This model was trained from scratch on the category_cleaning dataset.
+This model was trained from scratch on the Displate/category_cleaning dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.2933
 
 ## Model description
 

all_results.json

@@ -1,11 +1,11 @@
 {
     "epoch": 3.0,
-    "eval_loss": 4.553551197052002,
-    "eval_runtime": 33.4667,
-    "eval_samples_per_second": 124.9,
-    "eval_steps_per_second": 1.972,
-    "train_loss": 2.093686363324016,
-    "train_runtime": 1371.5717,
-    "train_samples_per_second": 54.855,
-    "train_steps_per_second": 0.857
+    "eval_loss": 1.2932854890823364,
+    "eval_runtime": 0.1299,
+    "eval_samples_per_second": 92.356,
+    "eval_steps_per_second": 7.696,
+    "train_loss": 1.8652879397074382,
+    "train_runtime": 4.8165,
+    "train_samples_per_second": 46.715,
+    "train_steps_per_second": 1.246
 }

eval_results.json

@@ -1,7 +1,7 @@
 {
     "epoch": 3.0,
-    "eval_loss": 4.553551197052002,
-    "eval_runtime": 33.4667,
-    "eval_samples_per_second": 124.9,
-    "eval_steps_per_second": 1.972
+    "eval_loss": 1.2932854890823364,
+    "eval_runtime": 0.1299,
+    "eval_samples_per_second": 92.356,
+    "eval_steps_per_second": 7.696
 }

runs/Mar08_15-12-19_9da45c1bcf23/events.out.tfevents.1709910759.9da45c1bcf23.90608.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d5fcb8fbc14e0437b3156b642d4a0fd54e44da032e27cc38d7a9e763696bf637
+size 354

train_results.json

@@ -1,7 +1,7 @@
 {
     "epoch": 3.0,
-    "train_loss": 2.093686363324016,
-    "train_runtime": 1371.5717,
-    "train_samples_per_second": 54.855,
-    "train_steps_per_second": 0.857
+    "train_loss": 1.8652879397074382,
+    "train_runtime": 4.8165,
+    "train_samples_per_second": 46.715,
+    "train_steps_per_second": 1.246
 }

trainer_state.json

@@ -2,105 +2,28 @@
   "best_metric": null,
   "best_model_checkpoint": null,
   "epoch": 3.0,
-  "eval_steps": 200.0,
-  "global_step": 1176,
+  "eval_steps": 100,
+  "global_step": 6,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
-    {
-      "epoch": 0.26,
-      "grad_norm": 23.253705978393555,
-      "learning_rate": 4.5748299319727895e-05,
-      "loss": 3.0173,
-      "step": 100
-    },
-    {
-      "epoch": 0.51,
-      "grad_norm": 24.05482292175293,
-      "learning_rate": 4.149659863945579e-05,
-      "loss": 2.8146,
-      "step": 200
-    },
-    {
-      "epoch": 0.77,
-      "grad_norm": 19.086837768554688,
-      "learning_rate": 3.724489795918368e-05,
-      "loss": 2.7177,
-      "step": 300
-    },
-    {
-      "epoch": 1.02,
-      "grad_norm": 19.842321395874023,
-      "learning_rate": 3.2993197278911564e-05,
-      "loss": 2.6338,
-      "step": 400
-    },
-    {
-      "epoch": 1.28,
-      "grad_norm": 25.054931640625,
-      "learning_rate": 2.8741496598639456e-05,
-      "loss": 2.102,
-      "step": 500
-    },
-    {
-      "epoch": 1.53,
-      "grad_norm": 22.865522384643555,
-      "learning_rate": 2.448979591836735e-05,
-      "loss": 2.1015,
-      "step": 600
-    },
-    {
-      "epoch": 1.79,
-      "grad_norm": 25.445798873901367,
-      "learning_rate": 2.023809523809524e-05,
-      "loss": 2.0691,
-      "step": 700
-    },
-    {
-      "epoch": 2.04,
-      "grad_norm": 22.133098602294922,
-      "learning_rate": 1.5986394557823133e-05,
-      "loss": 1.9422,
-      "step": 800
-    },
-    {
-      "epoch": 2.3,
-      "grad_norm": 31.207412719726562,
-      "learning_rate": 1.1734693877551021e-05,
-      "loss": 1.4405,
-      "step": 900
-    },
-    {
-      "epoch": 2.55,
-      "grad_norm": 19.457901000976562,
-      "learning_rate": 7.482993197278912e-06,
-      "loss": 1.3896,
-      "step": 1000
-    },
-    {
-      "epoch": 2.81,
-      "grad_norm": 20.708255767822266,
-      "learning_rate": 3.231292517006803e-06,
-      "loss": 1.3735,
-      "step": 1100
-    },
     {
       "epoch": 3.0,
-      "step": 1176,
-      "total_flos": 4376310425967942.0,
-      "train_loss": 2.093686363324016,
-      "train_runtime": 1371.5717,
-      "train_samples_per_second": 54.855,
-      "train_steps_per_second": 0.857
+      "step": 6,
+      "total_flos": 13087574542350.0,
+      "train_loss": 1.8652879397074382,
+      "train_runtime": 4.8165,
+      "train_samples_per_second": 46.715,
+      "train_steps_per_second": 1.246
     }
   ],
   "logging_steps": 100,
-  "max_steps": 1176,
+  "max_steps": 6,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 500,
-  "total_flos": 4376310425967942.0,
+  "total_flos": 13087574542350.0,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null