Training in progress, step 4000, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:70a32488c42d94bc68537838fd59bace50bad9a491961be86f3738a6910755e4
+oid sha256:8d9744fca00a76a2b63dac0145112528d105510001811540108c40b285279761
 size 386379

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:47fd29bde813c33926e0c9c10cf9775d231d7930b7aa4abd47133c29f24ed7c5
+oid sha256:eda6f94a6ddf235700eba4f7ef325af055c1617aa52880aa4490a4d5390ce4cb
 size 1540661735

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a2a4adad934312ea001cd84349883cb6c15698df9bb6c090af6bf88181fb06b
+oid sha256:666c4ffc6f56dc33b9a78682d8f70b6048cb030ff6769652c67983bc0c55e9bb
 size 14469

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:649e8cc37e14e4911064da2b8cb9ef2ade87f6e78d1185d4b8e5b14453b1c83d
+oid sha256:b91a82f25eb2ba5e7ada463b6840a878d34219b311613ef51dfe56bd048532b9
 size 14469

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f6403efa0c30bbacae871a7df874ec4bbdb5b528b6d86d3b5609a837c3eb80b9
+oid sha256:ae6fc782ac05ca9ced39cd4e6262e90acfd0088a765c64bc05286563954690b6
 size 14469

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fedd614c5b3fb7e22cbb42e3d69fcde0d7a32f2e678c37f7c99bb5a167b975e8
+oid sha256:0cb48f272d3916d4dba504ddc3932b95ab25bac7736fe8342e16dc0cbc2a1adf
 size 14469

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f72141908b3038f5d527be0a4afe331900fd2cd98b763078b556a00ecca0eca1
+oid sha256:b090f294678dd201862ecf44cf91ce818a27b404a0eff4bef3b64dec57a7ecb8
 size 14469

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c958787b74a3aefeefe565a04ee3471c563655a4aa29b37f82c1b78d0c1b5a6c
+oid sha256:93564d987336a3da8adbded70bd5490c95a0d271364aab176adc5b13e849acb5
 size 14469

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a198a4edc5b0a0c0735b02620e42eae859d7b0a942bf7c1a21b08b1885eff98
+oid sha256:8dd028df69482d761eb10c87e2921b635a7522d6e0534c883e77e6c5389b6ff4
 size 14469

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1403f69e2c99c4fcaf2999db32c4368d388bb9ac696855db926ab4209f647997
+oid sha256:da0f84dd27aa055253dd988727f836725b299f77ef0700780966bcc8184785ad
 size 14469

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:19317e67cea234fe3e615230a11e75ee190fdec27b0f95904042181fcbf16742
+oid sha256:f9a8388b6b51fab4a30d39efc19f0e1fc13cb83c585b1bd7d347d801a2ccc8e7
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.08,
+  "epoch": 0.16,
   "eval_steps": 1000,
-  "global_step": 2000,
+  "global_step": 4000,
   "is_hyper_param_search": false,
   "is_local_process_zero": false,
   "is_world_process_zero": true,
@@ -166,6 +166,164 @@
       "eval_samples_per_second": 17.231,
       "eval_steps_per_second": 0.551,
       "step": 2000
+    },
+    {
+      "epoch": 0.084,
+      "grad_norm": 0.5317835807800293,
+      "learning_rate": 0.0039314280243790255,
+      "loss": 51.5766015625,
+      "step": 2100
+    },
+    {
+      "epoch": 0.088,
+      "grad_norm": 0.7677087187767029,
+      "learning_rate": 0.003924748298765388,
+      "loss": 51.459482421875,
+      "step": 2200
+    },
+    {
+      "epoch": 0.092,
+      "grad_norm": 0.8987520933151245,
+      "learning_rate": 0.003917764389788164,
+      "loss": 51.2251513671875,
+      "step": 2300
+    },
+    {
+      "epoch": 0.096,
+      "grad_norm": 0.8509472608566284,
+      "learning_rate": 0.003910477401170333,
+      "loss": 51.086318359375,
+      "step": 2400
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 1.0043303966522217,
+      "learning_rate": 0.003902888484532972,
+      "loss": 51.013447265625,
+      "step": 2500
+    },
+    {
+      "epoch": 0.104,
+      "grad_norm": 0.6577029228210449,
+      "learning_rate": 0.0038949988392132555,
+      "loss": 50.6555419921875,
+      "step": 2600
+    },
+    {
+      "epoch": 0.108,
+      "grad_norm": 0.9883126020431519,
+      "learning_rate": 0.0038868097120749187,
+      "loss": 50.6927490234375,
+      "step": 2700
+    },
+    {
+      "epoch": 0.112,
+      "grad_norm": 1.0359454154968262,
+      "learning_rate": 0.003878322397311201,
+      "loss": 50.8522021484375,
+      "step": 2800
+    },
+    {
+      "epoch": 0.116,
+      "grad_norm": 0.8272144198417664,
+      "learning_rate": 0.0038695382362403186,
+      "loss": 50.349677734375,
+      "step": 2900
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 0.7374610304832458,
+      "learning_rate": 0.0038604586170934807,
+      "loss": 49.932939453125,
+      "step": 3000
+    },
+    {
+      "epoch": 0.12,
+      "eval_accuracy": 0.16219354838709676,
+      "eval_loss": 50.10387420654297,
+      "eval_runtime": 7.1742,
+      "eval_samples_per_second": 17.424,
+      "eval_steps_per_second": 0.558,
+      "step": 3000
+    },
+    {
+      "epoch": 0.124,
+      "grad_norm": 1.0479457378387451,
+      "learning_rate": 0.0038510849747955015,
+      "loss": 49.958212890625,
+      "step": 3100
+    },
+    {
+      "epoch": 0.128,
+      "grad_norm": 1.4167745113372803,
+      "learning_rate": 0.0038414187907380216,
+      "loss": 49.9526025390625,
+      "step": 3200
+    },
+    {
+      "epoch": 0.132,
+      "grad_norm": 1.264487385749817,
+      "learning_rate": 0.0038314615925453986,
+      "loss": 49.983779296875,
+      "step": 3300
+    },
+    {
+      "epoch": 0.136,
+      "grad_norm": 1.5543415546417236,
+      "learning_rate": 0.003821214953833277,
+      "loss": 49.699599609375,
+      "step": 3400
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 1.4869952201843262,
+      "learning_rate": 0.0038106804939599037,
+      "loss": 49.46021484375,
+      "step": 3500
+    },
+    {
+      "epoch": 0.144,
+      "grad_norm": 1.2286678552627563,
+      "learning_rate": 0.003799859877770204,
+      "loss": 49.3774853515625,
+      "step": 3600
+    },
+    {
+      "epoch": 0.148,
+      "grad_norm": 2.0684049129486084,
+      "learning_rate": 0.003788754815332674,
+      "loss": 48.850126953125,
+      "step": 3700
+    },
+    {
+      "epoch": 0.152,
+      "grad_norm": 2.0739598274230957,
+      "learning_rate": 0.003777367061669124,
+      "loss": 48.7242919921875,
+      "step": 3800
+    },
+    {
+      "epoch": 0.156,
+      "grad_norm": 2.031198740005493,
+      "learning_rate": 0.0037656984164773206,
+      "loss": 48.9626513671875,
+      "step": 3900
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 1.9467569589614868,
+      "learning_rate": 0.003753750723846564,
+      "loss": 48.71037109375,
+      "step": 4000
+    },
+    {
+      "epoch": 0.16,
+      "eval_accuracy": 0.1748435972629521,
+      "eval_loss": 48.56401824951172,
+      "eval_runtime": 7.0573,
+      "eval_samples_per_second": 17.712,
+      "eval_steps_per_second": 0.567,
+      "step": 4000
     }
   ],
   "logging_steps": 100,