Training in progress, step 8000, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f5c48459fa60b605303b0d27ace00ad2096e8131793c4adcbd8dbba3f7f05b68
+oid sha256:bc0c1563393d995412311cba1214a9520dca547b90b519de7f1ce0b2f94384a6
 size 386379

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:495659b2393af3017ab9e8e8f60326b39ab2d3fd0faffcb10f202cad46eb1273
+oid sha256:3aa9b056f2e17085d4900f3271d88de35f6ac5194621790395f2e4f587a69232
 size 1540661735

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ea3f206a9236577723633ea7c144cddc74c7390e88e7f9099912f6491fd80e8
+oid sha256:1e47a193d21ecc1ad99cf3d0b11067079c7e2eeed011077dd9d2eec110457c9c
 size 14469

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:867b8afafb899ee4f8d7e6052453cd8a741e4214d85da108553245a0b56d701a
+oid sha256:768ce36046f98e2d652c3d4e4715ee92969f1d46b33288d5213930731a801cf9
 size 14469

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:faa6fa2287aad321cbb22bbaedd456c7be2ae098ba9ca7cd858cc4c928c56651
+oid sha256:ad69461fda5a7151f961131a57f67c28a9bf598350ae5d99ce95c8ec88ff78da
 size 14469

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a6cb874a5313a6c9a2dbde4359bb963ad3cfd50cd3ad51a1fd10c71dd3508a77
+oid sha256:4f092d919dcd7a979986c37fe2f4d5718eda679a575e6e71176605e3f28b4da3
 size 14469

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea3314ca642931da1a5b28e60a20bd875be813361a002674a2f7f8ab48c9856e
+oid sha256:7cfd234ef8e0bce0d28c2272f50bbffc1faa98bd25482e7a5eb6e1a7d18e6aab
 size 14469

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c450d759f6f13b4b263f398164f48782614a20b556bf9dd81d5722276a593f27
+oid sha256:9277cfd5b2385bc7162ccde048b9e10c1f018201304953d47b48ffdd2baae832
 size 14469

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a758a18329b8c1b5690e207a82e38eddc070bca1b9e42028d9bae1a9e005081
+oid sha256:110f59eb6a8f1b021131a112cdfbbed170d6a8d222fbcb0a48b72e3683fe424f
 size 14469

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:69b890497b4e2dc118225b6da994942d04ab88dde8ff041fe55844b623ed290f
+oid sha256:28db19b12e448a6216bc82ad0a8dc000f968411ed4a0fc53a441e099e33a6ca8
 size 14469

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:888dd1fbf7803a02c8a29182dd5e65aa537b787d31363ffaf998bf1b2b7561ff
+oid sha256:4dc3ee7ff07df340dc973522b19f5110e955054f7179c9fdb7ad1c0dee99bc27
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.24,
+  "epoch": 0.32,
   "eval_steps": 1000,
-  "global_step": 6000,
+  "global_step": 8000,
   "is_hyper_param_search": false,
   "is_local_process_zero": false,
   "is_world_process_zero": true,
@@ -482,6 +482,164 @@
       "eval_samples_per_second": 16.662,
       "eval_steps_per_second": 0.533,
       "step": 6000
+    },
+    {
+      "epoch": 0.244,
+      "grad_norm": 3.177504062652588,
+      "learning_rate": 0.0034421101123303897,
+      "loss": 46.474375,
+      "step": 6100
+    },
+    {
+      "epoch": 0.248,
+      "grad_norm": 3.0214405059814453,
+      "learning_rate": 0.0034245757310132244,
+      "loss": 46.3790576171875,
+      "step": 6200
+    },
+    {
+      "epoch": 0.252,
+      "grad_norm": 2.933534860610962,
+      "learning_rate": 0.003406816212602642,
+      "loss": 46.0579736328125,
+      "step": 6300
+    },
+    {
+      "epoch": 0.256,
+      "grad_norm": 2.5542778968811035,
+      "learning_rate": 0.003388834363777341,
+      "loss": 46.0082861328125,
+      "step": 6400
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 3.1228818893432617,
+      "learning_rate": 0.0033706330263526692,
+      "loss": 46.218310546875,
+      "step": 6500
+    },
+    {
+      "epoch": 0.264,
+      "grad_norm": 3.096647262573242,
+      "learning_rate": 0.003352215076831515,
+      "loss": 46.06939453125,
+      "step": 6600
+    },
+    {
+      "epoch": 0.268,
+      "grad_norm": 3.2484421730041504,
+      "learning_rate": 0.0033335834259497076,
+      "loss": 46.158388671875,
+      "step": 6700
+    },
+    {
+      "epoch": 0.272,
+      "grad_norm": 3.035205841064453,
+      "learning_rate": 0.003314741018216011,
+      "loss": 45.9556396484375,
+      "step": 6800
+    },
+    {
+      "epoch": 0.276,
+      "grad_norm": 3.4140381813049316,
+      "learning_rate": 0.0032956908314467803,
+      "loss": 45.8059375,
+      "step": 6900
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 3.5898549556732178,
+      "learning_rate": 0.003276435876295352,
+      "loss": 45.785087890625,
+      "step": 7000
+    },
+    {
+      "epoch": 0.28,
+      "eval_accuracy": 0.2004613880742913,
+      "eval_loss": 45.5724983215332,
+      "eval_runtime": 7.1637,
+      "eval_samples_per_second": 17.449,
+      "eval_steps_per_second": 0.558,
+      "step": 7000
+    },
+    {
+      "epoch": 0.284,
+      "grad_norm": 3.6645097732543945,
+      "learning_rate": 0.0032569791957762473,
+      "loss": 45.450126953125,
+      "step": 7100
+    },
+    {
+      "epoch": 0.288,
+      "grad_norm": 3.449202060699463,
+      "learning_rate": 0.003237323864784261,
+      "loss": 45.6815869140625,
+      "step": 7200
+    },
+    {
+      "epoch": 0.292,
+      "grad_norm": 3.7189524173736572,
+      "learning_rate": 0.0032174729896085105,
+      "loss": 45.68208984375,
+      "step": 7300
+    },
+    {
+      "epoch": 0.296,
+      "grad_norm": 3.6789443492889404,
+      "learning_rate": 0.0031974297074415237,
+      "loss": 45.42337890625,
+      "step": 7400
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 4.174764633178711,
+      "learning_rate": 0.003177197185883444,
+      "loss": 45.540263671875,
+      "step": 7500
+    },
+    {
+      "epoch": 0.304,
+      "grad_norm": 3.5856988430023193,
+      "learning_rate": 0.0031567786224414272,
+      "loss": 45.4182177734375,
+      "step": 7600
+    },
+    {
+      "epoch": 0.308,
+      "grad_norm": 3.8331663608551025,
+      "learning_rate": 0.003136177244024319,
+      "loss": 45.5009228515625,
+      "step": 7700
+    },
+    {
+      "epoch": 0.312,
+      "grad_norm": 3.373854160308838,
+      "learning_rate": 0.003115396306432675,
+      "loss": 45.4340283203125,
+      "step": 7800
+    },
+    {
+      "epoch": 0.316,
+      "grad_norm": 3.256587028503418,
+      "learning_rate": 0.003094439093844223,
+      "loss": 45.136494140625,
+      "step": 7900
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 3.5598511695861816,
+      "learning_rate": 0.0030733089182948376,
+      "loss": 45.0095849609375,
+      "step": 8000
+    },
+    {
+      "epoch": 0.32,
+      "eval_accuracy": 0.2007086999022483,
+      "eval_loss": 45.0313720703125,
+      "eval_runtime": 6.9806,
+      "eval_samples_per_second": 17.907,
+      "eval_steps_per_second": 0.573,
+      "step": 8000
     }
   ],
   "logging_steps": 100,