Training in progress, step 6000, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b8c4f09e4df38c2b9a7b4ea1bb4b3bb55ce4048cf496c490994769c5b20d4a8
+oid sha256:bbdf201f2ca7db57b8feb7c3fd112ee2da171978edf625a10c49da7fb6425229
 size 1442699

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8be8ea274e8c78fb1a6aed38fc7b39f6a706b7c0fc47d551c8c41142e7ae8382
+oid sha256:5209572e45d9d97e930e13c4cbefc87684d2f813ab7698d7f8601f7281f9d968
 size 499774435

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:af971d84c55a6494396ed13d3bc14bba9e161e3dc5123551d9be42796da1c2be
+oid sha256:97cacdba2a01c848150f6f5acf2400fd2530701580557a29b8e2ae0aa198e156
 size 14455

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": true,
   "is_world_process_zero": true,
@@ -324,6 +324,164 @@
       "eval_samples_per_second": 151.355,
       "eval_steps_per_second": 18.919,
       "step": 4000
+    },
+    {
+      "epoch": 0.082,
+      "grad_norm": 0.5043853521347046,
+      "learning_rate": 0.0019944130517800893,
+      "loss": 5.239017944335938,
+      "step": 4100
+    },
+    {
+      "epoch": 0.084,
+      "grad_norm": 0.3757055699825287,
+      "learning_rate": 0.001993693153591457,
+      "loss": 5.197454833984375,
+      "step": 4200
+    },
+    {
+      "epoch": 0.086,
+      "grad_norm": 0.3453492820262909,
+      "learning_rate": 0.0019929297880451674,
+      "loss": 5.198365478515625,
+      "step": 4300
+    },
+    {
+      "epoch": 0.088,
+      "grad_norm": 0.4262433350086212,
+      "learning_rate": 0.0019921229885333023,
+      "loss": 5.171350708007813,
+      "step": 4400
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 0.40825143456459045,
+      "learning_rate": 0.001991272790347886,
+      "loss": 5.089209899902344,
+      "step": 4500
+    },
+    {
+      "epoch": 0.092,
+      "grad_norm": 0.4957910180091858,
+      "learning_rate": 0.0019903792306793415,
+      "loss": 5.19048828125,
+      "step": 4600
+    },
+    {
+      "epoch": 0.094,
+      "grad_norm": 0.3308526873588562,
+      "learning_rate": 0.001989442348614863,
+      "loss": 5.067187805175781,
+      "step": 4700
+    },
+    {
+      "epoch": 0.096,
+      "grad_norm": 0.8154045343399048,
+      "learning_rate": 0.0019884621851367075,
+      "loss": 4.980618591308594,
+      "step": 4800
+    },
+    {
+      "epoch": 0.098,
+      "grad_norm": 0.31783750653266907,
+      "learning_rate": 0.001987438783120401,
+      "loss": 5.060207214355469,
+      "step": 4900
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.3620655834674835,
+      "learning_rate": 0.001986372187332862,
+      "loss": 5.093417358398438,
+      "step": 5000
+    },
+    {
+      "epoch": 0.1,
+      "eval_accuracy": 0.2061839530332681,
+      "eval_loss": 5.202327251434326,
+      "eval_runtime": 6.6926,
+      "eval_samples_per_second": 149.419,
+      "eval_steps_per_second": 18.677,
+      "step": 5000
+    },
+    {
+      "epoch": 0.102,
+      "grad_norm": 0.5922824144363403,
+      "learning_rate": 0.0019852624444304467,
+      "loss": 5.105964965820313,
+      "step": 5100
+    },
+    {
+      "epoch": 0.104,
+      "grad_norm": 0.3136729598045349,
+      "learning_rate": 0.0019841096029569044,
+      "loss": 5.011907348632812,
+      "step": 5200
+    },
+    {
+      "epoch": 0.106,
+      "grad_norm": 0.5342575311660767,
+      "learning_rate": 0.0019829137133412556,
+      "loss": 5.081852111816406,
+      "step": 5300
+    },
+    {
+      "epoch": 0.108,
+      "grad_norm": 0.26439738273620605,
+      "learning_rate": 0.001981674827895587,
+      "loss": 4.994610595703125,
+      "step": 5400
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 0.37755730748176575,
+      "learning_rate": 0.00198039300081276,
+      "loss": 5.054569396972656,
+      "step": 5500
+    },
+    {
+      "epoch": 0.112,
+      "grad_norm": 0.2924644947052002,
+      "learning_rate": 0.0019790682881640448,
+      "loss": 4.945042419433594,
+      "step": 5600
+    },
+    {
+      "epoch": 0.114,
+      "grad_norm": 0.35851046442985535,
+      "learning_rate": 0.001977700747896664,
+      "loss": 4.959053039550781,
+      "step": 5700
+    },
+    {
+      "epoch": 0.116,
+      "grad_norm": 0.5607061386108398,
+      "learning_rate": 0.001976290439831259,
+      "loss": 5.00759521484375,
+      "step": 5800
+    },
+    {
+      "epoch": 0.118,
+      "grad_norm": 0.41018638014793396,
+      "learning_rate": 0.0019748374256592736,
+      "loss": 4.933994750976563,
+      "step": 5900
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 0.28882530331611633,
+      "learning_rate": 0.0019733417689402543,
+      "loss": 5.069781799316406,
+      "step": 6000
+    },
+    {
+      "epoch": 0.12,
+      "eval_accuracy": 0.21534050880626224,
+      "eval_loss": 5.081418037414551,
+      "eval_runtime": 6.8091,
+      "eval_samples_per_second": 146.862,
+      "eval_steps_per_second": 18.358,
+      "step": 6000
     }
   ],
   "logging_steps": 100,