Training in progress, step 6000, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ebb38a924e948ebe7405d836c0326774ec3e803d6c16572a9234fd3887d27e5
+oid sha256:4c06f8bdb3470386515b85743f5f433fba520ab14f1b589e6f665e843ff544c6
 size 1600779

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d391ca485a0db15ae264d0aafa0da7edc68c0f696b30fd294f28e503817b0a28
+oid sha256:47079a3c6b76024ae75741e62abdf81d9e0ad0f98cded6e05c983e0a05682bad
 size 621149155

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:851f1a1d183e5897767447c672bcf8362d9ae2a4736cbb50b4e208139d171c19
+oid sha256:d2a3ee2b9270eba0a2311f907ea53e1bec546e16e72a9c2fda6872be77c59c2f
 size 14469

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a7fa122671d1ef4d22de37e01b14987409ecd975ea71c5bf79191d6ce98cf8a3
+oid sha256:1b4ff89f8eafc39f075c9216838e6c051cd47ba4912a50dce51d8507d2b54554
 size 14469

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0836353fc5b4695271900d529f17e5c9bcc8f6b960c6c8ad2842449359842642
+oid sha256:949e92b373ef785d8153838a856e7e94fcdbceccf0df94fac6b1428fba0aa52c
 size 14469

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d85458cac81ee63dbddcc21880d9d5d65d2999a521682ced8bb92cd38533d72b
+oid sha256:06a6a2db4cb588d8ce4130d4e05d07a9c55b5589d5cb162b1a3d954475ff88d3
 size 14469

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b61eff2b0a5194e1f7cf6b678cdf994e3194534b171d100afdd85158f083dbf
+oid sha256:7088f74e466de020dfa05daf938b6e89670196138b802849a37053644f6497b8
 size 14469

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e09f720647dea58d44bd8a7064bc267a53d19c77ef833401671fb959ec0bee3
+oid sha256:0e94d95b4f9bc5f7112993c3b1fffc2e8c2ce3186f5ea05083591485e3d86055
 size 14469

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4fc874467b18473948fa002d73f9ced910bc93328612c168e89eefd3ff25af66
+oid sha256:abab3cbb093f08eba5cc70d5ebf9d591bdbafc0cbf9d3444496ddf74c29c9cf8
 size 14469

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e642abe2620703f2d27e2aefa3f96715c8ae63a82165f9e63e498f488c2c681d
+oid sha256:5972654a558bb8bded698917db31ad4f8203a51ad38c3abf88508a55e8574b82
 size 14469

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:76cf98a8cde877f1e49a9e4b884c4dce3d51bb4035429d464e74acc35ddca024
+oid sha256:eb2a89a85e1c8ac7ee9b5678d857a4d99090faa37a24489f44839e0801dfe16a
 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": 0.12,
   "eval_steps": 1000,
-  "global_step": 4000,
+  "global_step": 6000,
   "is_hyper_param_search": false,
   "is_local_process_zero": false,
   "is_world_process_zero": true,
@@ -324,6 +324,164 @@
       "eval_samples_per_second": 39.147,
       "eval_steps_per_second": 0.626,
       "step": 4000
+    },
+    {
+      "epoch": 0.082,
+      "grad_norm": 17.625349044799805,
+      "learning_rate": 0.0019944130517800893,
+      "loss": 36.6922,
+      "step": 4100
+    },
+    {
+      "epoch": 0.084,
+      "grad_norm": 2.45036244392395,
+      "learning_rate": 0.001993693153591457,
+      "loss": 36.347,
+      "step": 4200
+    },
+    {
+      "epoch": 0.086,
+      "grad_norm": 3.7300970554351807,
+      "learning_rate": 0.0019929297880451674,
+      "loss": 35.9307,
+      "step": 4300
+    },
+    {
+      "epoch": 0.088,
+      "grad_norm": 1.9578310251235962,
+      "learning_rate": 0.0019921229885333023,
+      "loss": 35.2814,
+      "step": 4400
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 2.398409843444824,
+      "learning_rate": 0.001991272790347886,
+      "loss": 35.4533,
+      "step": 4500
+    },
+    {
+      "epoch": 0.092,
+      "grad_norm": 9.658867835998535,
+      "learning_rate": 0.0019903792306793415,
+      "loss": 36.307,
+      "step": 4600
+    },
+    {
+      "epoch": 0.094,
+      "grad_norm": 1.590939998626709,
+      "learning_rate": 0.001989442348614863,
+      "loss": 36.1738,
+      "step": 4700
+    },
+    {
+      "epoch": 0.096,
+      "grad_norm": 1.983271837234497,
+      "learning_rate": 0.0019884621851367075,
+      "loss": 35.8103,
+      "step": 4800
+    },
+    {
+      "epoch": 0.098,
+      "grad_norm": 2.5749049186706543,
+      "learning_rate": 0.001987438783120401,
+      "loss": 35.6467,
+      "step": 4900
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 2.067998170852661,
+      "learning_rate": 0.001986372187332862,
+      "loss": 35.323,
+      "step": 5000
+    },
+    {
+      "epoch": 0.1,
+      "eval_accuracy": 0.26483953033268104,
+      "eval_loss": 35.489601135253906,
+      "eval_runtime": 3.2889,
+      "eval_samples_per_second": 38.007,
+      "eval_steps_per_second": 0.608,
+      "step": 5000
+    },
+    {
+      "epoch": 0.102,
+      "grad_norm": 1.8774443864822388,
+      "learning_rate": 0.0019852624444304467,
+      "loss": 34.9978,
+      "step": 5100
+    },
+    {
+      "epoch": 0.104,
+      "grad_norm": 2.0262346267700195,
+      "learning_rate": 0.0019841096029569044,
+      "loss": 34.6675,
+      "step": 5200
+    },
+    {
+      "epoch": 0.106,
+      "grad_norm": 1.776671051979065,
+      "learning_rate": 0.0019829137133412556,
+      "loss": 35.4506,
+      "step": 5300
+    },
+    {
+      "epoch": 0.108,
+      "grad_norm": 1.751766324043274,
+      "learning_rate": 0.001981674827895587,
+      "loss": 35.3834,
+      "step": 5400
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 2.024419069290161,
+      "learning_rate": 0.00198039300081276,
+      "loss": 35.2425,
+      "step": 5500
+    },
+    {
+      "epoch": 0.112,
+      "grad_norm": 1.8287601470947266,
+      "learning_rate": 0.0019790682881640448,
+      "loss": 35.3261,
+      "step": 5600
+    },
+    {
+      "epoch": 0.114,
+      "grad_norm": 1.6531343460083008,
+      "learning_rate": 0.001977700747896664,
+      "loss": 34.8158,
+      "step": 5700
+    },
+    {
+      "epoch": 0.116,
+      "grad_norm": 2.180936098098755,
+      "learning_rate": 0.001976290439831259,
+      "loss": 34.4037,
+      "step": 5800
+    },
+    {
+      "epoch": 0.118,
+      "grad_norm": 1.750649094581604,
+      "learning_rate": 0.0019748374256592736,
+      "loss": 33.958,
+      "step": 5900
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 1.9409301280975342,
+      "learning_rate": 0.0019733417689402543,
+      "loss": 34.2086,
+      "step": 6000
+    },
+    {
+      "epoch": 0.12,
+      "eval_accuracy": 0.2734716242661448,
+      "eval_loss": 34.69782257080078,
+      "eval_runtime": 3.2919,
+      "eval_samples_per_second": 37.972,
+      "eval_steps_per_second": 0.608,
+      "step": 6000
     }
   ],
   "logging_steps": 100,