Training in progress, step 500, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:80d69a236e68b6332db7d3cff5deaa06ec25ff0e5efa550677ce2f35df088680
+oid sha256:6974752fe7a3b14089ab2e7053fc764710e6d0ddbd1d7314081904519abc3ca2
 size 386379

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac6bc441453e9b4734e133be3c600607e5b3dee32b860836792368241f27642d
+oid sha256:3da8b0c6ec3a28101585919798344dd1a4d2e616af339b16dae843b9a7667d51
 size 1540661735

last-checkpoint/trainer_state.json

@@ -11,90 +11,90 @@
   "log_history": [
     {
       "epoch": 0.016666666666666666,
-      "grad_norm": 1325.952880859375,
+      "grad_norm": 769.3955078125,
       "learning_rate": 0.00013066666666666668,
-      "loss": 1512.93171875,
+      "loss": 2207.061875,
       "step": 50
     },
     {
       "epoch": 0.03333333333333333,
-      "grad_norm": 929.898681640625,
+      "grad_norm": 416.4177551269531,
       "learning_rate": 0.000264,
-      "loss": 1464.5940625,
+      "loss": 2157.63046875,
       "step": 100
     },
     {
       "epoch": 0.05,
-      "grad_norm": 747.4642333984375,
+      "grad_norm": 580.2691650390625,
       "learning_rate": 0.00039733333333333336,
-      "loss": 1415.48578125,
+      "loss": 2088.078125,
       "step": 150
     },
     {
       "epoch": 0.06666666666666667,
-      "grad_norm": 631.6712646484375,
+      "grad_norm": 518.3369140625,
       "learning_rate": 0.000399708326752494,
-      "loss": 1384.57703125,
+      "loss": 2027.68953125,
       "step": 200
     },
     {
       "epoch": 0.08333333333333333,
-      "grad_norm": 805.9771728515625,
+      "grad_norm": 343.1493225097656,
       "learning_rate": 0.0003988102673898103,
-      "loss": 1370.675,
+      "loss": 1981.4253125,
       "step": 250
     },
     {
       "epoch": 0.08333333333333333,
-      "eval_accuracy": 0.18672140762463343,
-      "eval_loss": 45.42939758300781,
-      "eval_runtime": 25.5972,
-      "eval_samples_per_second": 4.883,
-      "eval_steps_per_second": 0.156,
+      "eval_accuracy": 0.1509169110459433,
+      "eval_loss": 65.10028076171875,
+      "eval_runtime": 22.9136,
+      "eval_samples_per_second": 5.455,
+      "eval_steps_per_second": 0.175,
       "step": 250
     },
     {
       "epoch": 0.1,
-      "grad_norm": 653.5927124023438,
+      "grad_norm": 301.3949890136719,
       "learning_rate": 0.00039730842777928766,
-      "loss": 1365.14890625,
+      "loss": 1950.15375,
       "step": 300
     },
     {
       "epoch": 0.11666666666666667,
-      "grad_norm": 995.5695190429688,
+      "grad_norm": 479.62359619140625,
       "learning_rate": 0.0003952073689584629,
-      "loss": 1359.084375,
+      "loss": 1922.4278125,
       "step": 350
     },
     {
       "epoch": 0.13333333333333333,
-      "grad_norm": 825.2788696289062,
+      "grad_norm": 360.29132080078125,
       "learning_rate": 0.00039251347177392016,
-      "loss": 1355.68390625,
+      "loss": 1901.3628125,
       "step": 400
     },
     {
       "epoch": 0.15,
-      "grad_norm": 615.8878784179688,
+      "grad_norm": 334.61279296875,
       "learning_rate": 0.00038923491750286954,
-      "loss": 1353.1375,
+      "loss": 1883.4759375,
       "step": 450
     },
     {
       "epoch": 0.16666666666666666,
-      "grad_norm": 895.9261474609375,
+      "grad_norm": 390.5067443847656,
       "learning_rate": 0.00038538166300687717,
-      "loss": 1349.4459375,
+      "loss": 1868.25234375,
       "step": 500
     },
     {
       "epoch": 0.16666666666666666,
-      "eval_accuracy": 0.19390224828934507,
-      "eval_loss": 44.819725036621094,
-      "eval_runtime": 7.3949,
-      "eval_samples_per_second": 16.904,
-      "eval_steps_per_second": 0.541,
+      "eval_accuracy": 0.1607761485826002,
+      "eval_loss": 61.64983367919922,
+      "eval_runtime": 7.4283,
+      "eval_samples_per_second": 16.827,
+      "eval_steps_per_second": 0.538,
       "step": 500
     }
   ],

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cdf1bf7ff316b803830588f07fd42e9d70dbb919d664b54789baf8adc99f17cf
+oid sha256:bbabebbe458c541319860a962d07ff797d86a73d64992f9e2f64d3843d3ad153
 size 5265