Training in progress, step 1200, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce638fe074432886d0a23f98a8f165e69d1e6fee84a526cf594d00f8534028a1
+oid sha256:87399fda4401e43fddc5a839ada69ffdd168ab918f09d5782bc08b2a08c57590
 size 847599616

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0caa91a435695f3ccebbf12966391316e72dc5ad6f9cc2e90bacdd64a48fdc1c
+oid sha256:adf30444ff48bb3f968aa531132e86af74895e6dca092ef0b50a37cd281149ea
 size 1386414411

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2be637d2dd60e3cec1955d0241821cbcccd2af3688716d84100a306b44dad4a4
+oid sha256:3fc325c0f6e133b30ed7ac345224f75619e1ffa24494dab2a3e09b19384d35df
 size 14917

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b8d05de60c66749991154136b82121e270010e0cf03e7ae880dd38dcbbe6fd4a
+oid sha256:17d95b86c212e1cc1919367792abbcc28abe2eeeaccf2008cdfbf60e31bc1314
 size 14917

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f617c1b6753801a9d80064eb68997fd29d2b80564fcc110cff0fa781e09b8683
+oid sha256:dfdb9865d69d1265ac95b637888c2cf8ac3b8d1ad5a1b9e4f1da654c1dc9106a
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.42857142857142855,
+  "epoch": 0.5714285714285714,
   "eval_steps": 150,
-  "global_step": 900,
+  "global_step": 1200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -692,6 +692,234 @@
       "eval_samples_per_second": 19.572,
       "eval_steps_per_second": 2.466,
       "step": 900
+    },
+    {
+      "epoch": 0.43333333333333335,
+      "grad_norm": 9.677335739135742,
+      "learning_rate": 2.600034746917292e-06,
+      "loss": 17.079855346679686,
+      "step": 910
+    },
+    {
+      "epoch": 0.4380952380952381,
+      "grad_norm": 24.325902938842773,
+      "learning_rate": 2.569917770525538e-06,
+      "loss": 16.793905639648436,
+      "step": 920
+    },
+    {
+      "epoch": 0.44285714285714284,
+      "grad_norm": 32.768287658691406,
+      "learning_rate": 2.539659469727526e-06,
+      "loss": 17.420681762695313,
+      "step": 930
+    },
+    {
+      "epoch": 0.44761904761904764,
+      "grad_norm": 11.458124160766602,
+      "learning_rate": 2.509267347774807e-06,
+      "loss": 17.01726837158203,
+      "step": 940
+    },
+    {
+      "epoch": 0.4523809523809524,
+      "grad_norm": 47.37931442260742,
+      "learning_rate": 2.478748941103006e-06,
+      "loss": 16.992041015625,
+      "step": 950
+    },
+    {
+      "epoch": 0.45714285714285713,
+      "grad_norm": 16.12019157409668,
+      "learning_rate": 2.448111817462992e-06,
+      "loss": 17.042259216308594,
+      "step": 960
+    },
+    {
+      "epoch": 0.46190476190476193,
+      "grad_norm": 55.0360107421875,
+      "learning_rate": 2.417363574044275e-06,
+      "loss": 16.924298095703126,
+      "step": 970
+    },
+    {
+      "epoch": 0.4666666666666667,
+      "grad_norm": 8.713092803955078,
+      "learning_rate": 2.3865118355911064e-06,
+      "loss": 16.67218780517578,
+      "step": 980
+    },
+    {
+      "epoch": 0.4714285714285714,
+      "grad_norm": 30.71510887145996,
+      "learning_rate": 2.355564252511746e-06,
+      "loss": 16.627642822265624,
+      "step": 990
+    },
+    {
+      "epoch": 0.47619047619047616,
+      "grad_norm": 11.165261268615723,
+      "learning_rate": 2.3245284989813637e-06,
+      "loss": 16.885775756835937,
+      "step": 1000
+    },
+    {
+      "epoch": 0.48095238095238096,
+      "grad_norm": 33.494205474853516,
+      "learning_rate": 2.293412271039051e-06,
+      "loss": 16.8844970703125,
+      "step": 1010
+    },
+    {
+      "epoch": 0.4857142857142857,
+      "grad_norm": 16.44525909423828,
+      "learning_rate": 2.262223284679405e-06,
+      "loss": 16.938031005859376,
+      "step": 1020
+    },
+    {
+      "epoch": 0.49047619047619045,
+      "grad_norm": 56.29051208496094,
+      "learning_rate": 2.2309692739391725e-06,
+      "loss": 17.36894836425781,
+      "step": 1030
+    },
+    {
+      "epoch": 0.49523809523809526,
+      "grad_norm": 18.217512130737305,
+      "learning_rate": 2.1996579889794097e-06,
+      "loss": 16.765081787109374,
+      "step": 1040
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 12.565701484680176,
+      "learning_rate": 2.1682971941636525e-06,
+      "loss": 17.061727905273436,
+      "step": 1050
+    },
+    {
+      "epoch": 0.5,
+      "eval_accuracy": 0.06236220472440945,
+      "eval_loss": 16.80004119873047,
+      "eval_runtime": 25.3543,
+      "eval_samples_per_second": 19.721,
+      "eval_steps_per_second": 2.485,
+      "step": 1050
+    },
+    {
+      "epoch": 0.5047619047619047,
+      "grad_norm": 7.379430770874023,
+      "learning_rate": 2.1368946661325625e-06,
+      "loss": 17.065571594238282,
+      "step": 1060
+    },
+    {
+      "epoch": 0.5095238095238095,
+      "grad_norm": 33.2353515625,
+      "learning_rate": 2.1054581918755225e-06,
+      "loss": 16.781719970703126,
+      "step": 1070
+    },
+    {
+      "epoch": 0.5142857142857142,
+      "grad_norm": 5.199227809906006,
+      "learning_rate": 2.073995566799676e-06,
+      "loss": 16.9568115234375,
+      "step": 1080
+    },
+    {
+      "epoch": 0.5190476190476191,
+      "grad_norm": 21.680280685424805,
+      "learning_rate": 2.042514592796871e-06,
+      "loss": 16.72358856201172,
+      "step": 1090
+    },
+    {
+      "epoch": 0.5238095238095238,
+      "grad_norm": 19.837730407714844,
+      "learning_rate": 2.011023076309001e-06,
+      "loss": 16.884307861328125,
+      "step": 1100
+    },
+    {
+      "epoch": 0.5285714285714286,
+      "grad_norm": 12.718480110168457,
+      "learning_rate": 1.979528826392213e-06,
+      "loss": 16.639022827148438,
+      "step": 1110
+    },
+    {
+      "epoch": 0.5333333333333333,
+      "grad_norm": 16.71331787109375,
+      "learning_rate": 1.9480396527804736e-06,
+      "loss": 16.607608032226562,
+      "step": 1120
+    },
+    {
+      "epoch": 0.5380952380952381,
+      "grad_norm": 21.276140213012695,
+      "learning_rate": 1.916563363948959e-06,
+      "loss": 17.104000854492188,
+      "step": 1130
+    },
+    {
+      "epoch": 0.5428571428571428,
+      "grad_norm": 22.885112762451172,
+      "learning_rate": 1.8851077651777652e-06,
+      "loss": 16.868312072753906,
+      "step": 1140
+    },
+    {
+      "epoch": 0.5476190476190477,
+      "grad_norm": 38.87709426879883,
+      "learning_rate": 1.8536806566164048e-06,
+      "loss": 16.6172607421875,
+      "step": 1150
+    },
+    {
+      "epoch": 0.5523809523809524,
+      "grad_norm": 20.984086990356445,
+      "learning_rate": 1.8222898313495766e-06,
+      "loss": 16.41285400390625,
+      "step": 1160
+    },
+    {
+      "epoch": 0.5571428571428572,
+      "grad_norm": 18.480567932128906,
+      "learning_rate": 1.7909430734646932e-06,
+      "loss": 16.545147705078126,
+      "step": 1170
+    },
+    {
+      "epoch": 0.5619047619047619,
+      "grad_norm": 10.486381530761719,
+      "learning_rate": 1.7596481561216285e-06,
+      "loss": 16.698062133789062,
+      "step": 1180
+    },
+    {
+      "epoch": 0.5666666666666667,
+      "grad_norm": 28.246742248535156,
+      "learning_rate": 1.7284128396251875e-06,
+      "loss": 16.808547973632812,
+      "step": 1190
+    },
+    {
+      "epoch": 0.5714285714285714,
+      "grad_norm": 14.525625228881836,
+      "learning_rate": 1.6972448695007526e-06,
+      "loss": 16.164341735839844,
+      "step": 1200
+    },
+    {
+      "epoch": 0.5714285714285714,
+      "eval_accuracy": 0.05882677165354331,
+      "eval_loss": 16.66090965270996,
+      "eval_runtime": 25.3757,
+      "eval_samples_per_second": 19.704,
+      "eval_steps_per_second": 2.483,
+      "step": 1200
     }
   ],
   "logging_steps": 10,