Training in progress, epoch 3, checkpoint

checkpoint-11032/trainer_state.json

@@ -27,9 +27,9 @@
       "epoch": 0.36258158085569253,
       "eval_cosine_accuracy": 0.9711852073669434,
       "eval_loss": 0.3902958035469055,
-      "eval_runtime": 34.7826,
-      "eval_samples_per_second": 273.383,
-      "eval_steps_per_second": 1.092,
+      "eval_runtime": 34.6603,
+      "eval_samples_per_second": 274.348,
+      "eval_steps_per_second": 1.096,
       "step": 1000
     },
     {
@@ -43,9 +43,9 @@
       "epoch": 0.7251631617113851,
       "eval_cosine_accuracy": 0.9699232578277588,
       "eval_loss": 0.37875595688819885,
-      "eval_runtime": 34.4875,
-      "eval_samples_per_second": 275.723,
-      "eval_steps_per_second": 1.102,
+      "eval_runtime": 33.7082,
+      "eval_samples_per_second": 282.098,
+      "eval_steps_per_second": 1.127,
       "step": 2000
     },
     {
@@ -59,9 +59,9 @@
       "epoch": 1.0876811594202898,
       "eval_cosine_accuracy": 0.9716058373451233,
       "eval_loss": 0.3854234516620636,
-      "eval_runtime": 34.0163,
-      "eval_samples_per_second": 279.542,
-      "eval_steps_per_second": 1.117,
+      "eval_runtime": 34.2421,
+      "eval_samples_per_second": 277.699,
+      "eval_steps_per_second": 1.11,
       "step": 3000
     },
     {
@@ -75,9 +75,9 @@
       "epoch": 1.45,
       "eval_cosine_accuracy": 0.9708697199821472,
       "eval_loss": 0.3814031183719635,
-      "eval_runtime": 34.166,
-      "eval_samples_per_second": 278.318,
-      "eval_steps_per_second": 1.112,
+      "eval_runtime": 33.9647,
+      "eval_samples_per_second": 279.967,
+      "eval_steps_per_second": 1.119,
       "step": 4000
     },
     {
@@ -91,9 +91,9 @@
       "epoch": 1.8123188405797102,
       "eval_cosine_accuracy": 0.9710800051689148,
       "eval_loss": 0.38102903962135315,
-      "eval_runtime": 35.7406,
-      "eval_samples_per_second": 266.056,
-      "eval_steps_per_second": 1.063,
+      "eval_runtime": 34.858,
+      "eval_samples_per_second": 272.792,
+      "eval_steps_per_second": 1.09,
       "step": 5000
     },
     {
@@ -107,9 +107,9 @@
       "epoch": 2.17463768115942,
       "eval_cosine_accuracy": 0.9716058373451233,
       "eval_loss": 0.38304567337036133,
-      "eval_runtime": 34.6001,
-      "eval_samples_per_second": 274.826,
-      "eval_steps_per_second": 1.098,
+      "eval_runtime": 34.2523,
+      "eval_samples_per_second": 277.616,
+      "eval_steps_per_second": 1.109,
       "step": 6000
     },
     {
@@ -123,9 +123,9 @@
       "epoch": 2.5369565217391306,
       "eval_cosine_accuracy": 0.9721316695213318,
       "eval_loss": 0.3812798261642456,
-      "eval_runtime": 34.7347,
-      "eval_samples_per_second": 273.761,
-      "eval_steps_per_second": 1.094,
+      "eval_runtime": 33.9373,
+      "eval_samples_per_second": 280.193,
+      "eval_steps_per_second": 1.12,
       "step": 7000
     },
     {
@@ -139,9 +139,9 @@
       "epoch": 2.8992753623188405,
       "eval_cosine_accuracy": 0.9715006947517395,
       "eval_loss": 0.38419124484062195,
-      "eval_runtime": 33.8759,
-      "eval_samples_per_second": 280.701,
-      "eval_steps_per_second": 1.122,
+      "eval_runtime": 34.0546,
+      "eval_samples_per_second": 279.228,
+      "eval_steps_per_second": 1.116,
       "step": 8000
     },
     {
@@ -155,9 +155,9 @@
       "epoch": 3.261594202898551,
       "eval_cosine_accuracy": 0.9712903499603271,
       "eval_loss": 0.3847886919975281,
-      "eval_runtime": 33.958,
-      "eval_samples_per_second": 280.022,
-      "eval_steps_per_second": 1.119,
+      "eval_runtime": 34.006,
+      "eval_samples_per_second": 279.627,
+      "eval_steps_per_second": 1.117,
       "step": 9000
     },
     {
@@ -171,9 +171,9 @@
       "epoch": 3.623913043478261,
       "eval_cosine_accuracy": 0.970974862575531,
       "eval_loss": 0.3841721713542938,
-      "eval_runtime": 34.2368,
-      "eval_samples_per_second": 277.742,
-      "eval_steps_per_second": 1.11,
+      "eval_runtime": 33.9641,
+      "eval_samples_per_second": 279.972,
+      "eval_steps_per_second": 1.119,
       "step": 10000
     },
     {
@@ -187,9 +187,9 @@
       "epoch": 3.986231884057971,
       "eval_cosine_accuracy": 0.9705542325973511,
       "eval_loss": 0.38476327061653137,
-      "eval_runtime": 35.1285,
-      "eval_samples_per_second": 270.692,
-      "eval_steps_per_second": 1.082,
+      "eval_runtime": 34.6061,
+      "eval_samples_per_second": 274.778,
+      "eval_steps_per_second": 1.098,
       "step": 11000
     }
   ],

checkpoint-11032/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b41e05045f6aa7e498a4124fee16da5bd069671dc2554748b3f09072fd62ee83
+oid sha256:98354e6a6ec8411cdce0c11c2d3311243c8acedb0b90e2b2c87806e8519cdf4b
 size 5752