Training in progress, step 4000, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cee5801b782e9fa11728688160d98f08e40d7ce8b8147eaf7732d336677bcaf5
+oid sha256:7ebb38a924e948ebe7405d836c0326774ec3e803d6c16572a9234fd3887d27e5
 size 1600779

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f2d28589bd928752c7229e02d03a1390d159e98f1ad69e8957465a071d279f2a
+oid sha256:d391ca485a0db15ae264d0aafa0da7edc68c0f696b30fd294f28e503817b0a28
 size 621149155

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:799c2a9b233aca9b1649a975d8fc2d128798bc9a26769fb0f6cf72a67c9a46d2
+oid sha256:851f1a1d183e5897767447c672bcf8362d9ae2a4736cbb50b4e208139d171c19
 size 14469

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:89e9f7fe1ab29af6aa77e6004c57876d5313c9d3da26e9e11a0acfa75ab42122
+oid sha256:a7fa122671d1ef4d22de37e01b14987409ecd975ea71c5bf79191d6ce98cf8a3
 size 14469

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7fff2ccf7c72f15d3b76ddb019c26a4dca9d2e1f2ee32840db12f9fec2b95bea
+oid sha256:0836353fc5b4695271900d529f17e5c9bcc8f6b960c6c8ad2842449359842642
 size 14469

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:83a4e867fa1241d92d6bcf27766baa9f317570cbfb999ddb76e020d43ec7d4dc
+oid sha256:d85458cac81ee63dbddcc21880d9d5d65d2999a521682ced8bb92cd38533d72b
 size 14469

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f4acf2b09a1339e370773a0fd0c75b1d5891aee4c56e1dd818e17f835520caf
+oid sha256:5b61eff2b0a5194e1f7cf6b678cdf994e3194534b171d100afdd85158f083dbf
 size 14469

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7546ae9c1e6fa6e6426b888392672f7514267f83e14e93ef8fc7db13a5220a3b
+oid sha256:9e09f720647dea58d44bd8a7064bc267a53d19c77ef833401671fb959ec0bee3
 size 14469

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f84e63e29d923cc8c21554fe213de1a06f00b47198b99fe493dcf59f2ace055
+oid sha256:4fc874467b18473948fa002d73f9ced910bc93328612c168e89eefd3ff25af66
 size 14469

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b48f05a6fe6d1fbe948bd035323503b6cde575c8bc475d73338ea1f2101f32e
+oid sha256:e642abe2620703f2d27e2aefa3f96715c8ae63a82165f9e63e498f488c2c681d
 size 14469

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b716fb1dcbc77ddc6a0ae7c4c98d559e36f1986fff006ef6982bd75247833235
+oid sha256:76cf98a8cde877f1e49a9e4b884c4dce3d51bb4035429d464e74acc35ddca024
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.04,
+  "epoch": 0.08,
   "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": 35.816,
       "eval_steps_per_second": 0.573,
       "step": 2000
+    },
+    {
+      "epoch": 0.042,
+      "grad_norm": 3.47354793548584,
+      "learning_rate": 0.0016792,
+      "loss": 40.8328,
+      "step": 2100
+    },
+    {
+      "epoch": 0.044,
+      "grad_norm": 2.9095890522003174,
+      "learning_rate": 0.0017592,
+      "loss": 39.7859,
+      "step": 2200
+    },
+    {
+      "epoch": 0.046,
+      "grad_norm": 4.170510768890381,
+      "learning_rate": 0.0018392,
+      "loss": 40.0358,
+      "step": 2300
+    },
+    {
+      "epoch": 0.048,
+      "grad_norm": 9.68923282623291,
+      "learning_rate": 0.0019192,
+      "loss": 40.5113,
+      "step": 2400
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 4.442409992218018,
+      "learning_rate": 0.0019992,
+      "loss": 40.2312,
+      "step": 2500
+    },
+    {
+      "epoch": 0.052,
+      "grad_norm": 3.0799851417541504,
+      "learning_rate": 0.001999978563623903,
+      "loss": 39.559,
+      "step": 2600
+    },
+    {
+      "epoch": 0.054,
+      "grad_norm": 2.932781219482422,
+      "learning_rate": 0.0019999133871331223,
+      "loss": 39.2884,
+      "step": 2700
+    },
+    {
+      "epoch": 0.056,
+      "grad_norm": 3.138781785964966,
+      "learning_rate": 0.0019998044711915177,
+      "loss": 38.8602,
+      "step": 2800
+    },
+    {
+      "epoch": 0.058,
+      "grad_norm": 2.664058208465576,
+      "learning_rate": 0.0019996518205634257,
+      "loss": 37.9913,
+      "step": 2900
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 2.482013702392578,
+      "learning_rate": 0.0019994554419262797,
+      "loss": 37.4244,
+      "step": 3000
+    },
+    {
+      "epoch": 0.06,
+      "eval_accuracy": 0.2354109589041096,
+      "eval_loss": 38.45709991455078,
+      "eval_runtime": 3.1616,
+      "eval_samples_per_second": 39.537,
+      "eval_steps_per_second": 0.633,
+      "step": 3000
+    },
+    {
+      "epoch": 0.062,
+      "grad_norm": 3.9223365783691406,
+      "learning_rate": 0.001999215343870317,
+      "loss": 38.5841,
+      "step": 3100
+    },
+    {
+      "epoch": 0.064,
+      "grad_norm": 2.736224412918091,
+      "learning_rate": 0.0019989315368982054,
+      "loss": 38.4039,
+      "step": 3200
+    },
+    {
+      "epoch": 0.066,
+      "grad_norm": 2.4935879707336426,
+      "learning_rate": 0.0019986040334245797,
+      "loss": 38.2432,
+      "step": 3300
+    },
+    {
+      "epoch": 0.068,
+      "grad_norm": 3.567474842071533,
+      "learning_rate": 0.001998232847775504,
+      "loss": 38.0513,
+      "step": 3400
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 12.996139526367188,
+      "learning_rate": 0.0019978179961878404,
+      "loss": 37.0178,
+      "step": 3500
+    },
+    {
+      "epoch": 0.072,
+      "grad_norm": 3.0554473400115967,
+      "learning_rate": 0.001997359496808541,
+      "loss": 36.8567,
+      "step": 3600
+    },
+    {
+      "epoch": 0.074,
+      "grad_norm": 1.983723759651184,
+      "learning_rate": 0.001996857369693855,
+      "loss": 36.3819,
+      "step": 3700
+    },
+    {
+      "epoch": 0.076,
+      "grad_norm": 1.924381136894226,
+      "learning_rate": 0.0019963116368084486,
+      "loss": 36.6986,
+      "step": 3800
+    },
+    {
+      "epoch": 0.078,
+      "grad_norm": 1.8461555242538452,
+      "learning_rate": 0.001995722322024446,
+      "loss": 37.1027,
+      "step": 3900
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 2.570404529571533,
+      "learning_rate": 0.001995089451120385,
+      "loss": 36.6583,
+      "step": 4000
+    },
+    {
+      "epoch": 0.08,
+      "eval_accuracy": 0.2556536203522505,
+      "eval_loss": 36.39490509033203,
+      "eval_runtime": 3.1931,
+      "eval_samples_per_second": 39.147,
+      "eval_steps_per_second": 0.626,
+      "step": 4000
     }
   ],
   "logging_steps": 100,