End of training

README.md

@@ -1,7 +1,7 @@
 ---
 library_name: transformers
 license: apache-2.0
-base_model: HuggingFaceTB/SmolLM-360M
+base_model: Qwen/Qwen2.5-0.5B
 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-360M](https://huggingface.co/HuggingFaceTB/SmolLM-360M) on the None dataset.
+This model is a fine-tuned version of [Qwen/Qwen2.5-0.5B](https://huggingface.co/Qwen/Qwen2.5-0.5B) on the None dataset.
 
 ## Model description
 

all_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 5.0,
-    "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
+    "total_flos": 2.254602634660147e+16,
+    "train_loss": 0.7783217168792965,
+    "train_runtime": 2040.3082,
+    "train_samples_per_second": 12.444,
+    "train_steps_per_second": 1.556
 }

generation_config.json

@@ -1,6 +1,6 @@
 {
-  "_from_model_config": true,
-  "bos_token_id": 0,
-  "eos_token_id": 0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "max_new_tokens": 2048,
   "transformers_version": "4.44.2"
 }

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 5.0,
-    "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
+    "total_flos": 2.254602634660147e+16,
+    "train_loss": 0.7783217168792965,
+    "train_runtime": 2040.3082,
+    "train_samples_per_second": 12.444,
+    "train_steps_per_second": 1.556
 }

trainer_state.json

@@ -10,229 +10,229 @@
   "log_history": [
     {
       "epoch": 0.15748031496062992,
-      "grad_norm": 1.2890625,
+      "grad_norm": 5.84375,
       "learning_rate": 0.00031446540880503143,
-      "loss": 1.5497,
+      "loss": 1.6016,
       "step": 100
     },
     {
       "epoch": 0.31496062992125984,
-      "grad_norm": 0.92578125,
+      "grad_norm": 2.90625,
       "learning_rate": 0.0004997720451762572,
-      "loss": 0.9254,
+      "loss": 2.0478,
       "step": 200
     },
     {
       "epoch": 0.47244094488188976,
-      "grad_norm": 0.90625,
+      "grad_norm": 3.0,
       "learning_rate": 0.0004973084374349976,
-      "loss": 0.8457,
+      "loss": 2.0072,
       "step": 300
     },
     {
       "epoch": 0.6299212598425197,
-      "grad_norm": 0.734375,
+      "grad_norm": 2.578125,
       "learning_rate": 0.0004921639131931859,
-      "loss": 0.7922,
+      "loss": 1.8507,
       "step": 400
     },
     {
       "epoch": 0.7874015748031497,
-      "grad_norm": 0.80078125,
+      "grad_norm": 1.6953125,
       "learning_rate": 0.00048439424102900066,
-      "loss": 0.7571,
+      "loss": 1.7019,
       "step": 500
     },
     {
       "epoch": 0.9448818897637795,
-      "grad_norm": 0.73828125,
+      "grad_norm": 2.6875,
       "learning_rate": 0.00047408364711169396,
-      "loss": 0.7314,
+      "loss": 1.5988,
       "step": 600
     },
     {
       "epoch": 1.1023622047244095,
-      "grad_norm": 0.6484375,
+      "grad_norm": 1.8203125,
       "learning_rate": 0.00046134390215823,
-      "loss": 0.5663,
+      "loss": 1.3103,
       "step": 700
     },
     {
       "epoch": 1.2598425196850394,
-      "grad_norm": 0.70703125,
+      "grad_norm": 1.671875,
       "learning_rate": 0.00044631310979666443,
-      "loss": 0.5111,
+      "loss": 1.237,
       "step": 800
     },
     {
       "epoch": 1.4173228346456692,
-      "grad_norm": 0.78125,
+      "grad_norm": 1.7421875,
       "learning_rate": 0.0004291542094708612,
-      "loss": 0.5099,
+      "loss": 1.2112,
       "step": 900
     },
     {
       "epoch": 1.574803149606299,
-      "grad_norm": 1.0078125,
+      "grad_norm": 2.28125,
       "learning_rate": 0.000410053210115622,
-      "loss": 0.5007,
+      "loss": 1.1948,
       "step": 1000
     },
     {
       "epoch": 1.7322834645669292,
-      "grad_norm": 0.828125,
+      "grad_norm": 1.5859375,
       "learning_rate": 0.00038921717374985584,
-      "loss": 0.5068,
+      "loss": 1.1666,
       "step": 1100
     },
     {
       "epoch": 1.889763779527559,
-      "grad_norm": 0.74609375,
+      "grad_norm": 1.59375,
       "learning_rate": 0.0003668719708463959,
-      "loss": 0.4938,
+      "loss": 1.1001,
       "step": 1200
     },
     {
       "epoch": 2.047244094488189,
-      "grad_norm": 0.78515625,
+      "grad_norm": 1.6171875,
       "learning_rate": 0.00034325983181110047,
-      "loss": 0.4232,
+      "loss": 0.9377,
       "step": 1300
     },
     {
       "epoch": 2.204724409448819,
-      "grad_norm": 0.8515625,
+      "grad_norm": 1.640625,
       "learning_rate": 0.00031863672111412524,
-      "loss": 0.2999,
+      "loss": 0.6561,
       "step": 1400
     },
     {
       "epoch": 2.362204724409449,
-      "grad_norm": 0.921875,
+      "grad_norm": 1.9296875,
       "learning_rate": 0.00029326956253877123,
-      "loss": 0.3159,
+      "loss": 0.6872,
       "step": 1500
     },
     {
       "epoch": 2.5196850393700787,
-      "grad_norm": 0.79296875,
+      "grad_norm": 1.5859375,
       "learning_rate": 0.00026743334562725617,
-      "loss": 0.3034,
+      "loss": 0.6448,
       "step": 1600
     },
     {
       "epoch": 2.677165354330709,
-      "grad_norm": 0.86328125,
+      "grad_norm": 1.6484375,
       "learning_rate": 0.00024140814469062377,
-      "loss": 0.3046,
+      "loss": 0.643,
       "step": 1700
     },
     {
       "epoch": 2.8346456692913384,
-      "grad_norm": 0.84375,
+      "grad_norm": 1.28125,
       "learning_rate": 0.0002154760826978469,
-      "loss": 0.3078,
+      "loss": 0.6216,
       "step": 1800
     },
     {
       "epoch": 2.9921259842519685,
-      "grad_norm": 0.765625,
+      "grad_norm": 1.625,
       "learning_rate": 0.00018991827295670777,
-      "loss": 0.2941,
+      "loss": 0.5788,
       "step": 1900
     },
     {
       "epoch": 3.1496062992125986,
-      "grad_norm": 0.7265625,
+      "grad_norm": 1.2890625,
       "learning_rate": 0.00016501177173978493,
-      "loss": 0.2171,
+      "loss": 0.2589,
       "step": 2000
     },
     {
       "epoch": 3.3070866141732282,
-      "grad_norm": 0.765625,
+      "grad_norm": 1.7734375,
       "learning_rate": 0.00014102657489022886,
-      "loss": 0.2132,
+      "loss": 0.2383,
       "step": 2100
     },
     {
       "epoch": 3.4645669291338583,
-      "grad_norm": 0.65234375,
+      "grad_norm": 1.1875,
       "learning_rate": 0.00011822269096524812,
-      "loss": 0.2121,
+      "loss": 0.2227,
       "step": 2200
     },
     {
       "epoch": 3.622047244094488,
-      "grad_norm": 0.84375,
+      "grad_norm": 1.46875,
       "learning_rate": 9.684732264553247e-05,
-      "loss": 0.2142,
+      "loss": 0.2168,
       "step": 2300
     },
     {
       "epoch": 3.779527559055118,
-      "grad_norm": 0.66796875,
+      "grad_norm": 1.0390625,
       "learning_rate": 7.713218696519558e-05,
-      "loss": 0.2175,
+      "loss": 0.2162,
       "step": 2400
     },
     {
       "epoch": 3.937007874015748,
-      "grad_norm": 0.68359375,
+      "grad_norm": 1.609375,
       "learning_rate": 5.929100341195187e-05,
-      "loss": 0.2124,
+      "loss": 0.1944,
       "step": 2500
     },
     {
       "epoch": 4.094488188976378,
-      "grad_norm": 0.5390625,
+      "grad_norm": 0.45703125,
       "learning_rate": 4.351717712746703e-05,
-      "loss": 0.1979,
+      "loss": 0.123,
       "step": 2600
     },
     {
       "epoch": 4.251968503937007,
-      "grad_norm": 0.67578125,
+      "grad_norm": 0.4609375,
       "learning_rate": 2.9981702322862735e-05,
-      "loss": 0.1953,
+      "loss": 0.0768,
       "step": 2700
     },
     {
       "epoch": 4.409448818897638,
-      "grad_norm": 0.625,
+      "grad_norm": 0.59375,
       "learning_rate": 1.8831308637139e-05,
-      "loss": 0.2015,
+      "loss": 0.0761,
       "step": 2800
     },
     {
       "epoch": 4.566929133858268,
-      "grad_norm": 0.58203125,
+      "grad_norm": 0.53515625,
       "learning_rate": 1.0186870532686742e-05,
-      "loss": 0.1981,
+      "loss": 0.0786,
       "step": 2900
     },
     {
       "epoch": 4.724409448818898,
-      "grad_norm": 0.5,
+      "grad_norm": 0.640625,
       "learning_rate": 4.1420969706420505e-06,
-      "loss": 0.19,
+      "loss": 0.0758,
       "step": 3000
     },
     {
       "epoch": 4.881889763779528,
-      "grad_norm": 0.55859375,
+      "grad_norm": 0.515625,
       "learning_rate": 7.625155704936715e-07,
-      "loss": 0.1945,
+      "loss": 0.0792,
       "step": 3100
     },
     {
       "epoch": 5.0,
       "step": 3175,
-      "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
+      "total_flos": 2.254602634660147e+16,
+      "train_loss": 0.7783217168792965,
+      "train_runtime": 2040.3082,
+      "train_samples_per_second": 12.444,
+      "train_steps_per_second": 1.556
     }
   ],
   "logging_steps": 100,
@@ -252,7 +252,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.94980087881216e+16,
+  "total_flos": 2.254602634660147e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null