Training in progress, step 10000, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc0c1563393d995412311cba1214a9520dca547b90b519de7f1ce0b2f94384a6
+oid sha256:c8dc9b7da6d26d633c2dd1a6298a08b45f5c5918ae1aaa6d997b662eb648987d
 size 386379

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3aa9b056f2e17085d4900f3271d88de35f6ac5194621790395f2e4f587a69232
+oid sha256:7e5109c5ab50d16612c916165b2f1b379e87b9655586367244ed0f35eed2e9a8
 size 1540661735

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e47a193d21ecc1ad99cf3d0b11067079c7e2eeed011077dd9d2eec110457c9c
+oid sha256:2650365deef6e7f360be9092deb581b50fcfc0981b456b54de45695f1dd87947
 size 14469

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:768ce36046f98e2d652c3d4e4715ee92969f1d46b33288d5213930731a801cf9
+oid sha256:d9300f32e301bd335f3fb5d2ba765ba95180c24ea46eaea685e58401c90015c1
 size 14469

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad69461fda5a7151f961131a57f67c28a9bf598350ae5d99ce95c8ec88ff78da
+oid sha256:f730639438ee8fcdcc1e1cb83751cf1eada38bbe0ef956dce2851ca931960b8a
 size 14469

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f092d919dcd7a979986c37fe2f4d5718eda679a575e6e71176605e3f28b4da3
+oid sha256:fe934d44769ac7e9a840b774edada5ec3bca8cf109f459667d3c8dc00da8820d
 size 14469

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7cfd234ef8e0bce0d28c2272f50bbffc1faa98bd25482e7a5eb6e1a7d18e6aab
+oid sha256:2b250b2b78856a4178b9411fc4c2c48db7ef90f84dc2088843965ef7dfde0aa6
 size 14469

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9277cfd5b2385bc7162ccde048b9e10c1f018201304953d47b48ffdd2baae832
+oid sha256:67ca67d6482b0321beff26f4299075e123e65721ad7171ad8e9b4413b619f027
 size 14469

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:110f59eb6a8f1b021131a112cdfbbed170d6a8d222fbcb0a48b72e3683fe424f
+oid sha256:f545309b770f4b9aabc99027a1da637fdad2e36ae6df1f09d6f3e87c09353442
 size 14469

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28db19b12e448a6216bc82ad0a8dc000f968411ed4a0fc53a441e099e33a6ca8
+oid sha256:7b930024c4c4916aafefd00a76494fc84038df46cd42e5e9dc314f9cb1f7dfe3
 size 14469

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4dc3ee7ff07df340dc973522b19f5110e955054f7179c9fdb7ad1c0dee99bc27
+oid sha256:82c259140dc729f7726e15f02d46430c5619fa08380b6000b04b9de5c5a519c4
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.32,
+  "epoch": 0.4,
   "eval_steps": 1000,
-  "global_step": 8000,
+  "global_step": 10000,
   "is_hyper_param_search": false,
   "is_local_process_zero": false,
   "is_world_process_zero": true,
@@ -640,6 +640,164 @@
       "eval_samples_per_second": 17.907,
       "eval_steps_per_second": 0.573,
       "step": 8000
+    },
+    {
+      "epoch": 0.324,
+      "grad_norm": 3.4113783836364746,
+      "learning_rate": 0.0030520091191551142,
+      "loss": 45.00322265625,
+      "step": 8100
+    },
+    {
+      "epoch": 0.328,
+      "grad_norm": 3.566800832748413,
+      "learning_rate": 0.003030543062602622,
+      "loss": 45.1212841796875,
+      "step": 8200
+    },
+    {
+      "epoch": 0.332,
+      "grad_norm": 3.9237873554229736,
+      "learning_rate": 0.003008914141089914,
+      "loss": 45.1877978515625,
+      "step": 8300
+    },
+    {
+      "epoch": 0.336,
+      "grad_norm": 4.103876113891602,
+      "learning_rate": 0.0029871257728083995,
+      "loss": 45.1942626953125,
+      "step": 8400
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 3.259410858154297,
+      "learning_rate": 0.0029651814011481333,
+      "loss": 44.929365234375,
+      "step": 8500
+    },
+    {
+      "epoch": 0.344,
+      "grad_norm": 3.518616199493408,
+      "learning_rate": 0.002943084494153631,
+      "loss": 44.5111328125,
+      "step": 8600
+    },
+    {
+      "epoch": 0.348,
+      "grad_norm": 3.544551372528076,
+      "learning_rate": 0.002920838543975789,
+      "loss": 44.8691015625,
+      "step": 8700
+    },
+    {
+      "epoch": 0.352,
+      "grad_norm": 3.5976264476776123,
+      "learning_rate": 0.0028984470663199887,
+      "loss": 44.924892578125,
+      "step": 8800
+    },
+    {
+      "epoch": 0.356,
+      "grad_norm": 3.3831348419189453,
+      "learning_rate": 0.0028759135998904796,
+      "loss": 44.773828125,
+      "step": 8900
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 3.3760013580322266,
+      "learning_rate": 0.002853241705831138,
+      "loss": 44.8477294921875,
+      "step": 9000
+    },
+    {
+      "epoch": 0.36,
+      "eval_accuracy": 0.2051945259042033,
+      "eval_loss": 44.57013702392578,
+      "eval_runtime": 7.2683,
+      "eval_samples_per_second": 17.198,
+      "eval_steps_per_second": 0.55,
+      "step": 9000
+    },
+    {
+      "epoch": 0.364,
+      "grad_norm": 2.7893764972686768,
+      "learning_rate": 0.0028304349671626613,
+      "loss": 44.7609765625,
+      "step": 9100
+    },
+    {
+      "epoch": 0.368,
+      "grad_norm": 3.8668603897094727,
+      "learning_rate": 0.002807496988216319,
+      "loss": 44.6481201171875,
+      "step": 9200
+    },
+    {
+      "epoch": 0.372,
+      "grad_norm": 3.4443302154541016,
+      "learning_rate": 0.002784431394064333,
+      "loss": 44.4382373046875,
+      "step": 9300
+    },
+    {
+      "epoch": 0.376,
+      "grad_norm": 3.2611913681030273,
+      "learning_rate": 0.0027612418299469746,
+      "loss": 44.3794384765625,
+      "step": 9400
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 2.5774736404418945,
+      "learning_rate": 0.0027379319606964806,
+      "loss": 44.4774462890625,
+      "step": 9500
+    },
+    {
+      "epoch": 0.384,
+      "grad_norm": 3.2907772064208984,
+      "learning_rate": 0.002714505470157871,
+      "loss": 44.4849267578125,
+      "step": 9600
+    },
+    {
+      "epoch": 0.388,
+      "grad_norm": 3.4475579261779785,
+      "learning_rate": 0.0026909660606067583,
+      "loss": 44.4125537109375,
+      "step": 9700
+    },
+    {
+      "epoch": 0.392,
+      "grad_norm": 4.186856269836426,
+      "learning_rate": 0.002667317452164251,
+      "loss": 44.404677734375,
+      "step": 9800
+    },
+    {
+      "epoch": 0.396,
+      "grad_norm": 3.1886963844299316,
+      "learning_rate": 0.0026435633822090316,
+      "loss": 44.2500146484375,
+      "step": 9900
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 3.3009133338928223,
+      "learning_rate": 0.002619707604786708,
+      "loss": 44.2538232421875,
+      "step": 10000
+    },
+    {
+      "epoch": 0.4,
+      "eval_accuracy": 0.20702737047898337,
+      "eval_loss": 44.112098693847656,
+      "eval_runtime": 7.3398,
+      "eval_samples_per_second": 17.03,
+      "eval_steps_per_second": 0.545,
+      "step": 10000
     }
   ],
   "logging_steps": 100,