Training in progress, step 8000, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c06f8bdb3470386515b85743f5f433fba520ab14f1b589e6f665e843ff544c6
+oid sha256:ebb0d1344d85e1fc40cd8989c7c6db8bce3a550c89c85b825448ecbec3b9d6c1
 size 1600779

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:47079a3c6b76024ae75741e62abdf81d9e0ad0f98cded6e05c983e0a05682bad
+oid sha256:2abc969de4ce645f9d76eb977581465612165dd82ab373f63378a5f647630661
 size 621149155

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d2a3ee2b9270eba0a2311f907ea53e1bec546e16e72a9c2fda6872be77c59c2f
+oid sha256:a2f17c67fa754158f3c03c5f9856c1aa1a0efb60e8b2ba7ff0933cd7e615deac
 size 14469

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b4ff89f8eafc39f075c9216838e6c051cd47ba4912a50dce51d8507d2b54554
+oid sha256:418ff55ed0dbe835354a2c0bf4053deea4eb6d628f7fb25addc88d7dd433e1a0
 size 14469

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:949e92b373ef785d8153838a856e7e94fcdbceccf0df94fac6b1428fba0aa52c
+oid sha256:7a35f8395aebcabd2d2ff704dcd0a2516f18acacf15eaa6f6de4d80c3f5a64ac
 size 14469

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:06a6a2db4cb588d8ce4130d4e05d07a9c55b5589d5cb162b1a3d954475ff88d3
+oid sha256:20538af5e8a8c67556fafaef54a8d5e99ae679aaa736d860c04c1a2e37c3c03c
 size 14469

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7088f74e466de020dfa05daf938b6e89670196138b802849a37053644f6497b8
+oid sha256:7766e34119d4055998fe3273163a12ee2907d627abe9c4714c8b112cc18d1fb5
 size 14469

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e94d95b4f9bc5f7112993c3b1fffc2e8c2ce3186f5ea05083591485e3d86055
+oid sha256:b86ea660b800de8c8f56b525f1c8ec70de64ab61f7f595cc6d7a9eec27f020ed
 size 14469

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:abab3cbb093f08eba5cc70d5ebf9d591bdbafc0cbf9d3444496ddf74c29c9cf8
+oid sha256:afea3cb817289360580454c91b5d591d50af9204d37e43c3818d916f106c73a9
 size 14469

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5972654a558bb8bded698917db31ad4f8203a51ad38c3abf88508a55e8574b82
+oid sha256:2f608549c3734c6d52376589878069a475672b0ca9e5e32be42d15b90c85b8d1
 size 14469

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb2a89a85e1c8ac7ee9b5678d857a4d99090faa37a24489f44839e0801dfe16a
+oid sha256:e9567d76a2efaa946d19913fd9fe6f6f70f6f7101d7dcb8866c09743534f2d4d
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.12,
+  "epoch": 0.16,
   "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": 37.972,
       "eval_steps_per_second": 0.608,
       "step": 6000
+    },
+    {
+      "epoch": 0.122,
+      "grad_norm": 1.9359498023986816,
+      "learning_rate": 0.0019718035350990712,
+      "loss": 35.0183,
+      "step": 6100
+    },
+    {
+      "epoch": 0.124,
+      "grad_norm": 1.7273503541946411,
+      "learning_rate": 0.0019702227914230566,
+      "loss": 34.6009,
+      "step": 6200
+    },
+    {
+      "epoch": 0.126,
+      "grad_norm": 4.945074081420898,
+      "learning_rate": 0.001968599607059059,
+      "loss": 34.7242,
+      "step": 6300
+    },
+    {
+      "epoch": 0.128,
+      "grad_norm": 1.6802929639816284,
+      "learning_rate": 0.0019669340530104207,
+      "loss": 34.5441,
+      "step": 6400
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 1.8048967123031616,
+      "learning_rate": 0.001965226202133872,
+      "loss": 34.3155,
+      "step": 6500
+    },
+    {
+      "epoch": 0.132,
+      "grad_norm": 1.656825065612793,
+      "learning_rate": 0.0019634761291363427,
+      "loss": 33.7591,
+      "step": 6600
+    },
+    {
+      "epoch": 0.134,
+      "grad_norm": 1.642227053642273,
+      "learning_rate": 0.0019616839105716954,
+      "loss": 33.6263,
+      "step": 6700
+    },
+    {
+      "epoch": 0.136,
+      "grad_norm": 1.531063199043274,
+      "learning_rate": 0.0019598496248373755,
+      "loss": 34.4644,
+      "step": 6800
+    },
+    {
+      "epoch": 0.138,
+      "grad_norm": 2.118232011795044,
+      "learning_rate": 0.001957973352170984,
+      "loss": 34.597,
+      "step": 6900
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 2.264650344848633,
+      "learning_rate": 0.001956055174646765,
+      "loss": 34.2066,
+      "step": 7000
+    },
+    {
+      "epoch": 0.14,
+      "eval_accuracy": 0.27988845401174167,
+      "eval_loss": 34.06083679199219,
+      "eval_runtime": 3.2263,
+      "eval_samples_per_second": 38.744,
+      "eval_steps_per_second": 0.62,
+      "step": 7000
+    },
+    {
+      "epoch": 0.142,
+      "grad_norm": 1.5203992128372192,
+      "learning_rate": 0.0019540951761720174,
+      "loss": 34.176,
+      "step": 7100
+    },
+    {
+      "epoch": 0.144,
+      "grad_norm": 1.5354284048080444,
+      "learning_rate": 0.0019520934424834247,
+      "loss": 33.8863,
+      "step": 7200
+    },
+    {
+      "epoch": 0.146,
+      "grad_norm": 1.9357357025146484,
+      "learning_rate": 0.0019500500611433025,
+      "loss": 33.6482,
+      "step": 7300
+    },
+    {
+      "epoch": 0.148,
+      "grad_norm": 1.6156283617019653,
+      "learning_rate": 0.0019479651215357707,
+      "loss": 33.4445,
+      "step": 7400
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 1.962512731552124,
+      "learning_rate": 0.0019458387148628417,
+      "loss": 33.8778,
+      "step": 7500
+    },
+    {
+      "epoch": 0.152,
+      "grad_norm": 1.920979380607605,
+      "learning_rate": 0.001943670934140432,
+      "loss": 34.0846,
+      "step": 7600
+    },
+    {
+      "epoch": 0.154,
+      "grad_norm": 1.5394798517227173,
+      "learning_rate": 0.0019414618741942936,
+      "loss": 33.9074,
+      "step": 7700
+    },
+    {
+      "epoch": 0.156,
+      "grad_norm": 1.8427844047546387,
+      "learning_rate": 0.0019392116316558638,
+      "loss": 33.8625,
+      "step": 7800
+    },
+    {
+      "epoch": 0.158,
+      "grad_norm": 1.5528762340545654,
+      "learning_rate": 0.001936920304958042,
+      "loss": 33.5134,
+      "step": 7900
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 2.177480936050415,
+      "learning_rate": 0.0019345879943308804,
+      "loss": 33.2939,
+      "step": 8000
+    },
+    {
+      "epoch": 0.16,
+      "eval_accuracy": 0.28487866927592953,
+      "eval_loss": 33.50783920288086,
+      "eval_runtime": 3.2372,
+      "eval_samples_per_second": 38.613,
+      "eval_steps_per_second": 0.618,
+      "step": 8000
     }
   ],
   "logging_steps": 100,