Training in progress, step 800, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e09283677180e00d442fe3b4ab19dcf7ff5412ba2b7458854f7b79bfeb5bb28
+oid sha256:daccdd81efc2a0a277293828fd500acae487f74c3c11e5a76a92dccead15b44b
 size 393799132

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a0ebf03042fa02beb3e8266a31815f5d456796b309a08eb95940ed1ba6323de
+oid sha256:d69e614d6fcf4d5b017f26a7472c93d63940795e5304612d66167e03f06b39bc
 size 112281209

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:38c24bcf45e53a4cc78a87451f451897ccd30442038e8997c70341d3d503f861
+oid sha256:d6fccf3bf444a367297314536bf77346f3099ed3337e36d16f64f387d1380e34
 size 14645

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ac41801a97e47677175a43c4edf9de5a5d83090675917774e24b53c8664713d
+oid sha256:2d2c1ab50908353d6abaf917148ad6bca8553e0ccba7d5dc41bd0aeedd20fc82
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2953e888fcadc989fed40774279f6b8f341c37014ceb7f5076d3ac543f58ccb8
+oid sha256:6ad74d36caff74e5320f9af0a9eec584d391d2f360825523f566a83179a17d80
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0035058401453755047,
+  "epoch": 0.00467445352716734,
   "eval_steps": 500,
-  "global_step": 600,
+  "global_step": 800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -428,6 +428,146 @@
       "learning_rate": 0.00019999995585589562,
       "loss": 39.09903564453125,
       "step": 600
+    },
+    {
+      "epoch": 0.0035642708144650965,
+      "grad_norm": 40.42493438720703,
+      "learning_rate": 0.0001999999528537353,
+      "loss": 39.420098876953126,
+      "step": 610
+    },
+    {
+      "epoch": 0.0036227014835546884,
+      "grad_norm": 65.23612976074219,
+      "learning_rate": 0.00019999994975281976,
+      "loss": 40.58140869140625,
+      "step": 620
+    },
+    {
+      "epoch": 0.0036811321526442797,
+      "grad_norm": 57.579830169677734,
+      "learning_rate": 0.00019999994655314898,
+      "loss": 40.40892639160156,
+      "step": 630
+    },
+    {
+      "epoch": 0.0037395628217338716,
+      "grad_norm": 70.6234359741211,
+      "learning_rate": 0.00019999994325472297,
+      "loss": 39.73567199707031,
+      "step": 640
+    },
+    {
+      "epoch": 0.0037979934908234634,
+      "grad_norm": 100.8598403930664,
+      "learning_rate": 0.0001999999398575417,
+      "loss": 38.62954406738281,
+      "step": 650
+    },
+    {
+      "epoch": 0.0038564241599130552,
+      "grad_norm": 69.65412902832031,
+      "learning_rate": 0.0001999999363616052,
+      "loss": 41.527337646484376,
+      "step": 660
+    },
+    {
+      "epoch": 0.003914854829002647,
+      "grad_norm": 73.54249572753906,
+      "learning_rate": 0.00019999993276691348,
+      "loss": 40.73309326171875,
+      "step": 670
+    },
+    {
+      "epoch": 0.0039732854980922385,
+      "grad_norm": 1597.5487060546875,
+      "learning_rate": 0.00019999992907346656,
+      "loss": 41.45749206542969,
+      "step": 680
+    },
+    {
+      "epoch": 0.00403171616718183,
+      "grad_norm": 81.58792114257812,
+      "learning_rate": 0.00019999992528126442,
+      "loss": 40.875448608398436,
+      "step": 690
+    },
+    {
+      "epoch": 0.004090146836271422,
+      "grad_norm": 96.45863342285156,
+      "learning_rate": 0.00019999992139030704,
+      "loss": 41.72288208007812,
+      "step": 700
+    },
+    {
+      "epoch": 0.004148577505361014,
+      "grad_norm": 115.86896514892578,
+      "learning_rate": 0.00019999991740059448,
+      "loss": 42.08210144042969,
+      "step": 710
+    },
+    {
+      "epoch": 0.004207008174450606,
+      "grad_norm": 94.17877197265625,
+      "learning_rate": 0.00019999991331212669,
+      "loss": 42.82060546875,
+      "step": 720
+    },
+    {
+      "epoch": 0.004265438843540198,
+      "grad_norm": 93.44184112548828,
+      "learning_rate": 0.00019999990912490372,
+      "loss": 43.04204406738281,
+      "step": 730
+    },
+    {
+      "epoch": 0.0043238695126297895,
+      "grad_norm": 119.51387786865234,
+      "learning_rate": 0.00019999990483892551,
+      "loss": 43.49368896484375,
+      "step": 740
+    },
+    {
+      "epoch": 0.004382300181719381,
+      "grad_norm": 2112.345703125,
+      "learning_rate": 0.00019999990045419213,
+      "loss": 42.52753601074219,
+      "step": 750
+    },
+    {
+      "epoch": 0.004440730850808972,
+      "grad_norm": 119.78974151611328,
+      "learning_rate": 0.00019999989597070357,
+      "loss": 43.43156433105469,
+      "step": 760
+    },
+    {
+      "epoch": 0.004499161519898564,
+      "grad_norm": 128.79014587402344,
+      "learning_rate": 0.00019999989138845984,
+      "loss": 44.296444702148435,
+      "step": 770
+    },
+    {
+      "epoch": 0.004557592188988156,
+      "grad_norm": 131.86851501464844,
+      "learning_rate": 0.00019999988670746087,
+      "loss": 43.5537841796875,
+      "step": 780
+    },
+    {
+      "epoch": 0.004616022858077748,
+      "grad_norm": 144.64266967773438,
+      "learning_rate": 0.00019999988192770677,
+      "loss": 44.307550048828126,
+      "step": 790
+    },
+    {
+      "epoch": 0.00467445352716734,
+      "grad_norm": 351.6954345703125,
+      "learning_rate": 0.0001999998770491975,
+      "loss": 44.655599975585936,
+      "step": 800
     }
   ],
   "logging_steps": 10,
@@ -447,7 +587,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4809381153761280.0,
+  "total_flos": 6418924487503872.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null