Training in progress, step 8000, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bbdf201f2ca7db57b8feb7c3fd112ee2da171978edf625a10c49da7fb6425229
+oid sha256:fd74e6589d3e456165c757752a4ea537b0dce0f12a9239822f8f0b87e6fcab08
 size 1442699

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5209572e45d9d97e930e13c4cbefc87684d2f813ab7698d7f8601f7281f9d968
+oid sha256:5c0b03c00b2afb37434503ce30b41dc6f4cc779bf2123b15db0c1a37a46bde51
 size 499774435

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:97cacdba2a01c848150f6f5acf2400fd2530701580557a29b8e2ae0aa198e156
+oid sha256:6b43fdf0f4b166ccbde53eac22fd3e3b4db7ae9dc053939b2b5bbebd405317f8
 size 14455

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": true,
   "is_world_process_zero": true,
@@ -482,6 +482,164 @@
       "eval_samples_per_second": 146.862,
       "eval_steps_per_second": 18.358,
       "step": 6000
+    },
+    {
+      "epoch": 0.122,
+      "grad_norm": 0.3777143955230713,
+      "learning_rate": 0.0019718035350990712,
+      "loss": 5.025782775878906,
+      "step": 6100
+    },
+    {
+      "epoch": 0.124,
+      "grad_norm": 0.32341495156288147,
+      "learning_rate": 0.0019702227914230566,
+      "loss": 5.048944702148438,
+      "step": 6200
+    },
+    {
+      "epoch": 0.126,
+      "grad_norm": 0.6978408098220825,
+      "learning_rate": 0.001968599607059059,
+      "loss": 5.073916015625,
+      "step": 6300
+    },
+    {
+      "epoch": 0.128,
+      "grad_norm": 0.32388925552368164,
+      "learning_rate": 0.0019669340530104207,
+      "loss": 5.03993896484375,
+      "step": 6400
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 0.36633092164993286,
+      "learning_rate": 0.001965226202133872,
+      "loss": 5.047967529296875,
+      "step": 6500
+    },
+    {
+      "epoch": 0.132,
+      "grad_norm": 0.36229783296585083,
+      "learning_rate": 0.0019634761291363427,
+      "loss": 4.99884033203125,
+      "step": 6600
+    },
+    {
+      "epoch": 0.134,
+      "grad_norm": 0.26596584916114807,
+      "learning_rate": 0.0019616839105716954,
+      "loss": 4.971425476074219,
+      "step": 6700
+    },
+    {
+      "epoch": 0.136,
+      "grad_norm": 0.2571287751197815,
+      "learning_rate": 0.0019598496248373755,
+      "loss": 4.944924926757812,
+      "step": 6800
+    },
+    {
+      "epoch": 0.138,
+      "grad_norm": 0.33811017870903015,
+      "learning_rate": 0.001957973352170984,
+      "loss": 5.022549438476562,
+      "step": 6900
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 0.3483704924583435,
+      "learning_rate": 0.001956055174646765,
+      "loss": 4.955761108398438,
+      "step": 7000
+    },
+    {
+      "epoch": 0.14,
+      "eval_accuracy": 0.2182211350293542,
+      "eval_loss": 5.020055770874023,
+      "eval_runtime": 6.8173,
+      "eval_samples_per_second": 146.686,
+      "eval_steps_per_second": 18.336,
+      "step": 7000
+    },
+    {
+      "epoch": 0.142,
+      "grad_norm": 0.29454681277275085,
+      "learning_rate": 0.0019540951761720174,
+      "loss": 4.994992370605469,
+      "step": 7100
+    },
+    {
+      "epoch": 0.144,
+      "grad_norm": 0.7461824417114258,
+      "learning_rate": 0.0019520934424834247,
+      "loss": 4.95612060546875,
+      "step": 7200
+    },
+    {
+      "epoch": 0.146,
+      "grad_norm": 0.2770542502403259,
+      "learning_rate": 0.0019500500611433025,
+      "loss": 4.9815975952148435,
+      "step": 7300
+    },
+    {
+      "epoch": 0.148,
+      "grad_norm": 0.627005934715271,
+      "learning_rate": 0.0019479651215357707,
+      "loss": 4.982627563476562,
+      "step": 7400
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 0.5774574279785156,
+      "learning_rate": 0.0019458387148628417,
+      "loss": 4.9119635009765625,
+      "step": 7500
+    },
+    {
+      "epoch": 0.152,
+      "grad_norm": 0.6212947368621826,
+      "learning_rate": 0.001943670934140432,
+      "loss": 4.96866455078125,
+      "step": 7600
+    },
+    {
+      "epoch": 0.154,
+      "grad_norm": 0.4175465703010559,
+      "learning_rate": 0.0019414618741942936,
+      "loss": 4.972650146484375,
+      "step": 7700
+    },
+    {
+      "epoch": 0.156,
+      "grad_norm": 0.30829882621765137,
+      "learning_rate": 0.0019392116316558638,
+      "loss": 4.9120181274414065,
+      "step": 7800
+    },
+    {
+      "epoch": 0.158,
+      "grad_norm": 0.2758282423019409,
+      "learning_rate": 0.001936920304958042,
+      "loss": 4.90683837890625,
+      "step": 7900
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.30226844549179077,
+      "learning_rate": 0.0019345879943308804,
+      "loss": 4.854488220214844,
+      "step": 8000
+    },
+    {
+      "epoch": 0.16,
+      "eval_accuracy": 0.22608414872798435,
+      "eval_loss": 4.913477420806885,
+      "eval_runtime": 6.8714,
+      "eval_samples_per_second": 145.531,
+      "eval_steps_per_second": 18.191,
+      "step": 8000
     }
   ],
   "logging_steps": 100,