Training in progress, step 4000, checkpoint

checkpoint-4000/trainer_state.json

@@ -26,9 +26,9 @@
     {
       "epoch": 1.0,
       "eval_loss": 6.317445755004883,
-      "eval_runtime": 19.2809,
-      "eval_samples_per_second": 1306.732,
-      "eval_steps_per_second": 5.135,
+      "eval_runtime": 15.5824,
+      "eval_samples_per_second": 1616.887,
+      "eval_steps_per_second": 6.353,
       "step": 392
     },
     {
@@ -41,9 +41,9 @@
     {
       "epoch": 2.0,
       "eval_loss": 6.024065017700195,
-      "eval_runtime": 19.3681,
-      "eval_samples_per_second": 1300.85,
-      "eval_steps_per_second": 5.111,
+      "eval_runtime": 15.5591,
+      "eval_samples_per_second": 1619.314,
+      "eval_steps_per_second": 6.363,
       "step": 784
     },
     {
@@ -56,9 +56,9 @@
     {
       "epoch": 3.0,
       "eval_loss": 5.884053707122803,
-      "eval_runtime": 19.3497,
-      "eval_samples_per_second": 1302.088,
-      "eval_steps_per_second": 5.116,
+      "eval_runtime": 15.6179,
+      "eval_samples_per_second": 1613.212,
+      "eval_steps_per_second": 6.339,
       "step": 1176
     },
     {
@@ -71,9 +71,9 @@
     {
       "epoch": 4.0,
       "eval_loss": 5.788422584533691,
-      "eval_runtime": 19.3355,
-      "eval_samples_per_second": 1303.047,
-      "eval_steps_per_second": 5.12,
+      "eval_runtime": 15.5176,
+      "eval_samples_per_second": 1623.64,
+      "eval_steps_per_second": 6.38,
       "step": 1568
     },
     {
@@ -86,9 +86,9 @@
     {
       "epoch": 5.0,
       "eval_loss": 5.718640327453613,
-      "eval_runtime": 19.1626,
-      "eval_samples_per_second": 1314.803,
-      "eval_steps_per_second": 5.166,
+      "eval_runtime": 15.5828,
+      "eval_samples_per_second": 1616.851,
+      "eval_steps_per_second": 6.353,
       "step": 1960
     },
     {
@@ -101,9 +101,9 @@
     {
       "epoch": 6.0,
       "eval_loss": 5.6633148193359375,
-      "eval_runtime": 19.4816,
-      "eval_samples_per_second": 1293.269,
-      "eval_steps_per_second": 5.082,
+      "eval_runtime": 15.6437,
+      "eval_samples_per_second": 1610.551,
+      "eval_steps_per_second": 6.328,
       "step": 2352
     },
     {
@@ -116,9 +116,9 @@
     {
       "epoch": 7.0,
       "eval_loss": 5.620563507080078,
-      "eval_runtime": 19.2806,
-      "eval_samples_per_second": 1306.752,
-      "eval_steps_per_second": 5.135,
+      "eval_runtime": 15.5999,
+      "eval_samples_per_second": 1615.079,
+      "eval_steps_per_second": 6.346,
       "step": 2744
     },
     {
@@ -131,9 +131,9 @@
     {
       "epoch": 8.0,
       "eval_loss": 5.586855888366699,
-      "eval_runtime": 19.2672,
-      "eval_samples_per_second": 1307.661,
-      "eval_steps_per_second": 5.138,
+      "eval_runtime": 15.6428,
+      "eval_samples_per_second": 1610.644,
+      "eval_steps_per_second": 6.329,
       "step": 3136
     },
     {
@@ -146,9 +146,9 @@
     {
       "epoch": 9.0,
       "eval_loss": 5.562436580657959,
-      "eval_runtime": 19.4007,
-      "eval_samples_per_second": 1298.665,
-      "eval_steps_per_second": 5.103,
+      "eval_runtime": 15.5065,
+      "eval_samples_per_second": 1624.806,
+      "eval_steps_per_second": 6.384,
       "step": 3528
     },
     {
@@ -161,9 +161,9 @@
     {
       "epoch": 10.0,
       "eval_loss": 5.544801235198975,
-      "eval_runtime": 19.3033,
-      "eval_samples_per_second": 1305.215,
-      "eval_steps_per_second": 5.129,
+      "eval_runtime": 15.5961,
+      "eval_samples_per_second": 1615.463,
+      "eval_steps_per_second": 6.348,
       "step": 3920
     }
   ],

checkpoint-4000/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3aa067acc804b79ea56c8830addc6a7dc795994309c286a45aeb17ddcc8ec159
+oid sha256:52cf954a78a3d6fc682ff0c3b6ee4cda69040297e62c644ea0256038484a747a
 size 5905