Training in progress, step 10000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b5b2537f5142e6fa774f5229435c8fe08d7962419f4ec779873d8e1778b6a5a
+oid sha256:172b83ee8c0c178fc631d554a3d8e1a9ee973cecb6292c8a65ea9cf6b9413a5f
 size 579824888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fde75f324a8d5912df33d74af3539f7d5c0a866216e75d10d52848057c5278fd
+oid sha256:4bb1ba220a967824aa67b3f408cb2411ac14a2a8f57c220950876c97a9607f93
 size 1159794763

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:231a1d74fdd644709c48076ea6500b1a4f8ca1620a6f210d62a4c539f1ee0b0f
+oid sha256:62b01f9ae52b370a3c5177e3cbec51226c2ec58f411c1ee0496cca95d179b183
 size 14645

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0182b4495f3c647cd51b29236a0c27e55ac1c8000e2e254b23fc4d917b1a56da
+oid sha256:687c619a9c245be775b1ee059ceaff574f576584c143ed02ddcab0296c87f35b
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.16,
+  "epoch": 0.2,
   "eval_steps": 1000,
-  "global_step": 8000,
+  "global_step": 10000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -640,6 +640,164 @@
       "eval_samples_per_second": 241.259,
       "eval_steps_per_second": 15.164,
       "step": 8000
+    },
+    {
+      "epoch": 0.162,
+      "grad_norm": 0.16548939049243927,
+      "learning_rate": 0.0009385625730561914,
+      "loss": 3.588617248535156,
+      "step": 8100
+    },
+    {
+      "epoch": 0.164,
+      "grad_norm": 0.16542939841747284,
+      "learning_rate": 0.0009370405468572831,
+      "loss": 3.590567626953125,
+      "step": 8200
+    },
+    {
+      "epoch": 0.166,
+      "grad_norm": 0.18206581473350525,
+      "learning_rate": 0.0009355011630568697,
+      "loss": 3.636882629394531,
+      "step": 8300
+    },
+    {
+      "epoch": 0.168,
+      "grad_norm": 0.2654706835746765,
+      "learning_rate": 0.0009339444827934676,
+      "loss": 3.6797540283203123,
+      "step": 8400
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 0.16825009882450104,
+      "learning_rate": 0.0009323705678925427,
+      "loss": 3.686376953125,
+      "step": 8500
+    },
+    {
+      "epoch": 0.172,
+      "grad_norm": 0.18937945365905762,
+      "learning_rate": 0.000930779480864057,
+      "loss": 3.6942425537109376,
+      "step": 8600
+    },
+    {
+      "epoch": 0.174,
+      "grad_norm": 0.19819994270801544,
+      "learning_rate": 0.0009291712848999833,
+      "loss": 3.6582196044921873,
+      "step": 8700
+    },
+    {
+      "epoch": 0.176,
+      "grad_norm": 0.1557057648897171,
+      "learning_rate": 0.0009275460438717975,
+      "loss": 3.6659271240234377,
+      "step": 8800
+    },
+    {
+      "epoch": 0.178,
+      "grad_norm": 0.16359280049800873,
+      "learning_rate": 0.0009259038223279413,
+      "loss": 3.66092529296875,
+      "step": 8900
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 0.17897452414035797,
+      "learning_rate": 0.0009242446854912575,
+      "loss": 3.6642529296875,
+      "step": 9000
+    },
+    {
+      "epoch": 0.18,
+      "eval_accuracy": 0.3497692697794326,
+      "eval_loss": 3.617546319961548,
+      "eval_runtime": 6.279,
+      "eval_samples_per_second": 309.124,
+      "eval_steps_per_second": 19.43,
+      "step": 9000
+    },
+    {
+      "epoch": 0.182,
+      "grad_norm": 0.20515520870685577,
+      "learning_rate": 0.0009225686992564015,
+      "loss": 3.6445053100585936,
+      "step": 9100
+    },
+    {
+      "epoch": 0.184,
+      "grad_norm": 0.16788582503795624,
+      "learning_rate": 0.0009208759301872229,
+      "loss": 3.657896728515625,
+      "step": 9200
+    },
+    {
+      "epoch": 0.186,
+      "grad_norm": 0.1988508403301239,
+      "learning_rate": 0.0009191664455141217,
+      "loss": 3.616723937988281,
+      "step": 9300
+    },
+    {
+      "epoch": 0.188,
+      "grad_norm": 0.1822570413351059,
+      "learning_rate": 0.0009174403131313792,
+      "loss": 3.6103390502929686,
+      "step": 9400
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 0.15679553151130676,
+      "learning_rate": 0.0009156976015944607,
+      "loss": 3.624302978515625,
+      "step": 9500
+    },
+    {
+      "epoch": 0.192,
+      "grad_norm": 0.15683937072753906,
+      "learning_rate": 0.0009139383801172929,
+      "loss": 3.6558917236328123,
+      "step": 9600
+    },
+    {
+      "epoch": 0.194,
+      "grad_norm": 0.1553466022014618,
+      "learning_rate": 0.0009121627185695152,
+      "loss": 3.6198284912109373,
+      "step": 9700
+    },
+    {
+      "epoch": 0.196,
+      "grad_norm": 0.14881721138954163,
+      "learning_rate": 0.0009103706874737043,
+      "loss": 3.60408203125,
+      "step": 9800
+    },
+    {
+      "epoch": 0.198,
+      "grad_norm": 0.1628589779138565,
+      "learning_rate": 0.0009085623580025737,
+      "loss": 3.6047940063476562,
+      "step": 9900
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.15589991211891174,
+      "learning_rate": 0.0009067378019761472,
+      "loss": 3.599223327636719,
+      "step": 10000
+    },
+    {
+      "epoch": 0.2,
+      "eval_accuracy": 0.3534593401629882,
+      "eval_loss": 3.579674005508423,
+      "eval_runtime": 6.3176,
+      "eval_samples_per_second": 307.239,
+      "eval_steps_per_second": 19.311,
+      "step": 10000
     }
   ],
   "logging_steps": 100,
@@ -659,7 +817,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.1359686934528e+17,
+  "total_flos": 3.919960866816e+17,
   "train_batch_size": 120,
   "trial_name": null,
   "trial_params": null