Training in progress, step 12000, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de0e6e5db5288feee0fefc4357eafb906c01848da238f0f1b9aac0e997510dec
+oid sha256:4bf78147f8e343a711c04d4bced1b1a3bee4e119ef0f393d9d961e3d7be9bbf4
 size 1442699

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:644b3d86f34c31a15e3fe76473fa14f4c704b8d59e60d78e4d6f10a6e753b1b8
+oid sha256:f11349bd4f131a5fba4fe75d7c08a58fc14a9f73c279ad7c85382a75c423a593
 size 499774435

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:86bc1651483ec7d90230200f2b53b997a19bb41b19e2710e0f81a67f62f0b352
+oid sha256:149d23a52063855ad630babdef2c6cdf6cb494879a59b9a4f1ccc02ef38dc56a
 size 14455

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:833776bf99a0597a4bf38df86be38e8ac151736eba1d084c9cbb84cab1caf4e9
+oid sha256:43ab2089bb2cb7b873a77ac8e24a3b3b2416ededca3811b6bb0922f61bea4c99
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.2,
+  "epoch": 0.24,
   "eval_steps": 1000,
-  "global_step": 10000,
+  "global_step": 12000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -798,6 +798,164 @@
       "eval_samples_per_second": 144.863,
       "eval_steps_per_second": 18.108,
       "step": 10000
+    },
+    {
+      "epoch": 0.202,
+      "grad_norm": 0.4188442528247833,
+      "learning_rate": 0.0018763385407335963,
+      "loss": 4.784246215820312,
+      "step": 10100
+    },
+    {
+      "epoch": 0.204,
+      "grad_norm": 0.24621133506298065,
+      "learning_rate": 0.001873133519711602,
+      "loss": 4.787679748535156,
+      "step": 10200
+    },
+    {
+      "epoch": 0.206,
+      "grad_norm": 0.5215740203857422,
+      "learning_rate": 0.0018698903050008956,
+      "loss": 4.709499206542969,
+      "step": 10300
+    },
+    {
+      "epoch": 0.208,
+      "grad_norm": 0.4617030918598175,
+      "learning_rate": 0.0018666090384701947,
+      "loss": 4.747078552246093,
+      "step": 10400
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 0.29167914390563965,
+      "learning_rate": 0.001863289863652727,
+      "loss": 4.661806945800781,
+      "step": 10500
+    },
+    {
+      "epoch": 0.212,
+      "grad_norm": 0.4101203680038452,
+      "learning_rate": 0.0018599329257399516,
+      "loss": 4.659268493652344,
+      "step": 10600
+    },
+    {
+      "epoch": 0.214,
+      "grad_norm": 0.31853312253952026,
+      "learning_rate": 0.0018565383715752083,
+      "loss": 4.701767272949219,
+      "step": 10700
+    },
+    {
+      "epoch": 0.216,
+      "grad_norm": 0.2906162440776825,
+      "learning_rate": 0.0018531063496472927,
+      "loss": 4.690833435058594,
+      "step": 10800
+    },
+    {
+      "epoch": 0.218,
+      "grad_norm": 0.3280249238014221,
+      "learning_rate": 0.0018496370100839622,
+      "loss": 4.6896670532226565,
+      "step": 10900
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 0.3699072301387787,
+      "learning_rate": 0.0018461305046453683,
+      "loss": 4.636054382324219,
+      "step": 11000
+    },
+    {
+      "epoch": 0.22,
+      "eval_accuracy": 0.2340371819960861,
+      "eval_loss": 4.797712326049805,
+      "eval_runtime": 6.7202,
+      "eval_samples_per_second": 148.805,
+      "eval_steps_per_second": 18.601,
+      "step": 11000
+    },
+    {
+      "epoch": 0.222,
+      "grad_norm": 0.24158497154712677,
+      "learning_rate": 0.0018425869867174187,
+      "loss": 4.711828002929687,
+      "step": 11100
+    },
+    {
+      "epoch": 0.224,
+      "grad_norm": 0.4193456172943115,
+      "learning_rate": 0.0018390066113050665,
+      "loss": 4.724891357421875,
+      "step": 11200
+    },
+    {
+      "epoch": 0.226,
+      "grad_norm": 0.3414510190486908,
+      "learning_rate": 0.0018353895350255317,
+      "loss": 4.649370727539062,
+      "step": 11300
+    },
+    {
+      "epoch": 0.228,
+      "grad_norm": 0.2959993779659271,
+      "learning_rate": 0.0018317359161014477,
+      "loss": 4.620471801757812,
+      "step": 11400
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 0.35871621966362,
+      "learning_rate": 0.001828045914353943,
+      "loss": 4.65095458984375,
+      "step": 11500
+    },
+    {
+      "epoch": 0.232,
+      "grad_norm": 0.8000448942184448,
+      "learning_rate": 0.0018243196911956476,
+      "loss": 4.606728210449218,
+      "step": 11600
+    },
+    {
+      "epoch": 0.234,
+      "grad_norm": 0.3677903115749359,
+      "learning_rate": 0.0018205574096236336,
+      "loss": 4.599508361816406,
+      "step": 11700
+    },
+    {
+      "epoch": 0.236,
+      "grad_norm": 0.5635560750961304,
+      "learning_rate": 0.0018167592342122857,
+      "loss": 4.591564331054688,
+      "step": 11800
+    },
+    {
+      "epoch": 0.238,
+      "grad_norm": 0.29384273290634155,
+      "learning_rate": 0.0018129253311061002,
+      "loss": 4.715082092285156,
+      "step": 11900
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 0.34943443536758423,
+      "learning_rate": 0.0018090558680124193,
+      "loss": 4.741492919921875,
+      "step": 12000
+    },
+    {
+      "epoch": 0.24,
+      "eval_accuracy": 0.24006849315068493,
+      "eval_loss": 4.731167316436768,
+      "eval_runtime": 6.7722,
+      "eval_samples_per_second": 147.662,
+      "eval_steps_per_second": 18.458,
+      "step": 12000
     }
   ],
   "logging_steps": 100,