End of training

README.md

@@ -1,7 +1,7 @@
 ---
 library_name: transformers
 license: apache-2.0
-base_model: HuggingFaceTB/SmolLM-135M
+base_model: HuggingFaceTB/SmolLM-360M
 tags:
 - trl
 - sft
@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # nature-buddy
 
-This model is a fine-tuned version of [HuggingFaceTB/SmolLM-135M](https://huggingface.co/HuggingFaceTB/SmolLM-135M) on the None dataset.
+This model is a fine-tuned version of [HuggingFaceTB/SmolLM-360M](https://huggingface.co/HuggingFaceTB/SmolLM-360M) on the None dataset.
 
 ## Model description
 

all_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 5.0,
-    "total_flos": 6581450258638848.0,
-    "train_loss": 0.5889826508769839,
-    "train_runtime": 806.0376,
-    "train_samples_per_second": 31.5,
-    "train_steps_per_second": 3.939
+    "total_flos": 1.94980087881216e+16,
+    "train_loss": 0.42690239373154526,
+    "train_runtime": 1498.3039,
+    "train_samples_per_second": 16.946,
+    "train_steps_per_second": 2.119
 }

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 5.0,
-    "total_flos": 6581450258638848.0,
-    "train_loss": 0.5889826508769839,
-    "train_runtime": 806.0376,
-    "train_samples_per_second": 31.5,
-    "train_steps_per_second": 3.939
+    "total_flos": 1.94980087881216e+16,
+    "train_loss": 0.42690239373154526,
+    "train_runtime": 1498.3039,
+    "train_samples_per_second": 16.946,
+    "train_steps_per_second": 2.119
 }

trainer_state.json

@@ -10,229 +10,229 @@
   "log_history": [
     {
       "epoch": 0.15748031496062992,
-      "grad_norm": 1.953125,
+      "grad_norm": 1.2890625,
       "learning_rate": 0.00031446540880503143,
-      "loss": 1.7301,
+      "loss": 1.5497,
       "step": 100
     },
     {
       "epoch": 0.31496062992125984,
-      "grad_norm": 1.1328125,
+      "grad_norm": 0.92578125,
       "learning_rate": 0.0004997720451762572,
-      "loss": 1.1137,
+      "loss": 0.9254,
       "step": 200
     },
     {
       "epoch": 0.47244094488188976,
-      "grad_norm": 1.28125,
+      "grad_norm": 0.90625,
       "learning_rate": 0.0004973084374349976,
-      "loss": 1.0141,
+      "loss": 0.8457,
       "step": 300
     },
     {
       "epoch": 0.6299212598425197,
-      "grad_norm": 1.078125,
+      "grad_norm": 0.734375,
       "learning_rate": 0.0004921639131931859,
-      "loss": 0.9538,
+      "loss": 0.7922,
       "step": 400
     },
     {
       "epoch": 0.7874015748031497,
-      "grad_norm": 0.9453125,
+      "grad_norm": 0.80078125,
       "learning_rate": 0.00048439424102900066,
-      "loss": 0.9061,
+      "loss": 0.7571,
       "step": 500
     },
     {
       "epoch": 0.9448818897637795,
-      "grad_norm": 1.0859375,
+      "grad_norm": 0.73828125,
       "learning_rate": 0.00047408364711169396,
-      "loss": 0.8785,
+      "loss": 0.7314,
       "step": 600
     },
     {
       "epoch": 1.1023622047244095,
-      "grad_norm": 0.83984375,
+      "grad_norm": 0.6484375,
       "learning_rate": 0.00046134390215823,
-      "loss": 0.7189,
+      "loss": 0.5663,
       "step": 700
     },
     {
       "epoch": 1.2598425196850394,
-      "grad_norm": 0.953125,
+      "grad_norm": 0.70703125,
       "learning_rate": 0.00044631310979666443,
-      "loss": 0.6703,
+      "loss": 0.5111,
       "step": 800
     },
     {
       "epoch": 1.4173228346456692,
-      "grad_norm": 0.9296875,
+      "grad_norm": 0.78125,
       "learning_rate": 0.0004291542094708612,
-      "loss": 0.6648,
+      "loss": 0.5099,
       "step": 900
     },
     {
       "epoch": 1.574803149606299,
-      "grad_norm": 1.2890625,
+      "grad_norm": 1.0078125,
       "learning_rate": 0.000410053210115622,
-      "loss": 0.6524,
+      "loss": 0.5007,
       "step": 1000
     },
     {
       "epoch": 1.7322834645669292,
-      "grad_norm": 1.03125,
+      "grad_norm": 0.828125,
       "learning_rate": 0.00038921717374985584,
-      "loss": 0.6622,
+      "loss": 0.5068,
       "step": 1100
     },
     {
       "epoch": 1.889763779527559,
-      "grad_norm": 0.96484375,
+      "grad_norm": 0.74609375,
       "learning_rate": 0.0003668719708463959,
-      "loss": 0.6379,
+      "loss": 0.4938,
       "step": 1200
     },
     {
       "epoch": 2.047244094488189,
-      "grad_norm": 1.0234375,
+      "grad_norm": 0.78515625,
       "learning_rate": 0.00034325983181110047,
-      "loss": 0.5745,
+      "loss": 0.4232,
       "step": 1300
     },
     {
       "epoch": 2.204724409448819,
-      "grad_norm": 1.0546875,
+      "grad_norm": 0.8515625,
       "learning_rate": 0.00031863672111412524,
-      "loss": 0.4619,
+      "loss": 0.2999,
       "step": 1400
     },
     {
       "epoch": 2.362204724409449,
-      "grad_norm": 1.203125,
+      "grad_norm": 0.921875,
       "learning_rate": 0.00029326956253877123,
-      "loss": 0.4808,
+      "loss": 0.3159,
       "step": 1500
     },
     {
       "epoch": 2.5196850393700787,
-      "grad_norm": 0.9921875,
+      "grad_norm": 0.79296875,
       "learning_rate": 0.00026743334562725617,
-      "loss": 0.4598,
+      "loss": 0.3034,
       "step": 1600
     },
     {
       "epoch": 2.677165354330709,
-      "grad_norm": 1.109375,
+      "grad_norm": 0.86328125,
       "learning_rate": 0.00024140814469062377,
-      "loss": 0.4687,
+      "loss": 0.3046,
       "step": 1700
     },
     {
       "epoch": 2.8346456692913384,
-      "grad_norm": 0.98046875,
+      "grad_norm": 0.84375,
       "learning_rate": 0.0002154760826978469,
-      "loss": 0.4703,
+      "loss": 0.3078,
       "step": 1800
     },
     {
       "epoch": 2.9921259842519685,
-      "grad_norm": 1.0625,
+      "grad_norm": 0.765625,
       "learning_rate": 0.00018991827295670777,
-      "loss": 0.4558,
+      "loss": 0.2941,
       "step": 1900
     },
     {
       "epoch": 3.1496062992125986,
-      "grad_norm": 1.046875,
+      "grad_norm": 0.7265625,
       "learning_rate": 0.00016501177173978493,
-      "loss": 0.3817,
+      "loss": 0.2171,
       "step": 2000
     },
     {
       "epoch": 3.3070866141732282,
-      "grad_norm": 1.0859375,
+      "grad_norm": 0.765625,
       "learning_rate": 0.00014102657489022886,
-      "loss": 0.3786,
+      "loss": 0.2132,
       "step": 2100
     },
     {
       "epoch": 3.4645669291338583,
-      "grad_norm": 0.8671875,
+      "grad_norm": 0.65234375,
       "learning_rate": 0.00011822269096524812,
-      "loss": 0.3779,
+      "loss": 0.2121,
       "step": 2200
     },
     {
       "epoch": 3.622047244094488,
-      "grad_norm": 1.328125,
+      "grad_norm": 0.84375,
       "learning_rate": 9.684732264553247e-05,
-      "loss": 0.3815,
+      "loss": 0.2142,
       "step": 2300
     },
     {
       "epoch": 3.779527559055118,
-      "grad_norm": 0.85546875,
+      "grad_norm": 0.66796875,
       "learning_rate": 7.713218696519558e-05,
-      "loss": 0.3859,
+      "loss": 0.2175,
       "step": 2400
     },
     {
       "epoch": 3.937007874015748,
-      "grad_norm": 1.0234375,
+      "grad_norm": 0.68359375,
       "learning_rate": 5.929100341195187e-05,
-      "loss": 0.3779,
+      "loss": 0.2124,
       "step": 2500
     },
     {
       "epoch": 4.094488188976378,
-      "grad_norm": 0.765625,
+      "grad_norm": 0.5390625,
       "learning_rate": 4.351717712746703e-05,
-      "loss": 0.3608,
+      "loss": 0.1979,
       "step": 2600
     },
     {
       "epoch": 4.251968503937007,
-      "grad_norm": 1.0546875,
+      "grad_norm": 0.67578125,
       "learning_rate": 2.9981702322862735e-05,
-      "loss": 0.3582,
+      "loss": 0.1953,
       "step": 2700
     },
     {
       "epoch": 4.409448818897638,
-      "grad_norm": 0.9375,
+      "grad_norm": 0.625,
       "learning_rate": 1.8831308637139e-05,
-      "loss": 0.3731,
+      "loss": 0.2015,
       "step": 2800
     },
     {
       "epoch": 4.566929133858268,
-      "grad_norm": 0.9296875,
+      "grad_norm": 0.58203125,
       "learning_rate": 1.0186870532686742e-05,
-      "loss": 0.3588,
+      "loss": 0.1981,
       "step": 2900
     },
     {
       "epoch": 4.724409448818898,
-      "grad_norm": 0.71875,
+      "grad_norm": 0.5,
       "learning_rate": 4.1420969706420505e-06,
-      "loss": 0.3537,
+      "loss": 0.19,
       "step": 3000
     },
     {
       "epoch": 4.881889763779528,
-      "grad_norm": 0.83203125,
+      "grad_norm": 0.55859375,
       "learning_rate": 7.625155704936715e-07,
-      "loss": 0.3614,
+      "loss": 0.1945,
       "step": 3100
     },
     {
       "epoch": 5.0,
       "step": 3175,
-      "total_flos": 6581450258638848.0,
-      "train_loss": 0.5889826508769839,
-      "train_runtime": 806.0376,
-      "train_samples_per_second": 31.5,
-      "train_steps_per_second": 3.939
+      "total_flos": 1.94980087881216e+16,
+      "train_loss": 0.42690239373154526,
+      "train_runtime": 1498.3039,
+      "train_samples_per_second": 16.946,
+      "train_steps_per_second": 2.119
     }
   ],
   "logging_steps": 100,
@@ -252,7 +252,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6581450258638848.0,
+  "total_flos": 1.94980087881216e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null