Training in progress, step 36000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eacd16009db792813323d990cfe5dae9dfaf2c1b2b6746f6ce4ee5c5abd05fa3
+oid sha256:d197cd9a3404a8c8f67910780423aecd5fdc3add3f182e0d82ab6682395c0006
 size 529337896

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:86b59222e117c9663552ff919bf9d06c38349de96bfd51727eb1c2c51c1eef72
+oid sha256:419fd2c3e0ba5d1952d3f93465eeb172ba6dac85f67c82c9eeb58a6bc214cded
 size 871247243

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:efa0171c7cd70527d3a922da6317b15994f35a839e2d8505c68b0fc08f030110
+oid sha256:6a202a832e7dde4f4f295f57293a1d0bb6e0f939cebe50d0b66fc7a8608bef7a
 size 14645

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dcc336e7edab566b72f19c8cdbf557762e0e53e457ed4985a87b74bd22371a59
+oid sha256:d525574f54acfd6c1c0d9e8a984a9fe4782c94abdc8722296a2554b91af7e0e9
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.68,
+  "epoch": 0.72,
   "eval_steps": 1000,
-  "global_step": 34000,
+  "global_step": 36000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2694,6 +2694,164 @@
       "eval_samples_per_second": 88.642,
       "eval_steps_per_second": 0.709,
       "step": 34000
+    },
+    {
+      "epoch": 0.682,
+      "grad_norm": 0.1495920717716217,
+      "learning_rate": 0.000503880797188073,
+      "loss": 3.2605,
+      "step": 34100
+    },
+    {
+      "epoch": 0.684,
+      "grad_norm": 0.16431903839111328,
+      "learning_rate": 0.0004981491600794544,
+      "loss": 3.2526,
+      "step": 34200
+    },
+    {
+      "epoch": 0.686,
+      "grad_norm": 0.1864980161190033,
+      "learning_rate": 0.0004924394755523447,
+      "loss": 3.2562,
+      "step": 34300
+    },
+    {
+      "epoch": 0.688,
+      "grad_norm": 0.1656457781791687,
+      "learning_rate": 0.0004867519933668425,
+      "loss": 3.2649,
+      "step": 34400
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 0.165181502699852,
+      "learning_rate": 0.0004810869623118437,
+      "loss": 3.257,
+      "step": 34500
+    },
+    {
+      "epoch": 0.692,
+      "grad_norm": 0.13930366933345795,
+      "learning_rate": 0.0004754446301941582,
+      "loss": 3.2525,
+      "step": 34600
+    },
+    {
+      "epoch": 0.694,
+      "grad_norm": 0.1519293636083603,
+      "learning_rate": 0.00046982524382767213,
+      "loss": 3.2596,
+      "step": 34700
+    },
+    {
+      "epoch": 0.696,
+      "grad_norm": 0.14039067924022675,
+      "learning_rate": 0.0004642290490225486,
+      "loss": 3.2582,
+      "step": 34800
+    },
+    {
+      "epoch": 0.698,
+      "grad_norm": 0.14533616602420807,
+      "learning_rate": 0.0004586562905744784,
+      "loss": 3.237,
+      "step": 34900
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 0.21432434022426605,
+      "learning_rate": 0.00045310721225396854,
+      "loss": 3.2596,
+      "step": 35000
+    },
+    {
+      "epoch": 0.7,
+      "eval_accuracy": 0.38947553816046965,
+      "eval_loss": 3.2606313228607178,
+      "eval_runtime": 10.6118,
+      "eval_samples_per_second": 94.235,
+      "eval_steps_per_second": 0.754,
+      "step": 35000
+    },
+    {
+      "epoch": 0.702,
+      "grad_norm": 0.15394216775894165,
+      "learning_rate": 0.00044758205679568163,
+      "loss": 3.2522,
+      "step": 35100
+    },
+    {
+      "epoch": 0.704,
+      "grad_norm": 0.14649616181850433,
+      "learning_rate": 0.00044208106588781694,
+      "loss": 3.2523,
+      "step": 35200
+    },
+    {
+      "epoch": 0.706,
+      "grad_norm": 0.13892528414726257,
+      "learning_rate": 0.00043660448016153656,
+      "loss": 3.2486,
+      "step": 35300
+    },
+    {
+      "epoch": 0.708,
+      "grad_norm": 0.16032464802265167,
+      "learning_rate": 0.0004311525391804426,
+      "loss": 3.2464,
+      "step": 35400
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 0.14114409685134888,
+      "learning_rate": 0.0004257254814300947,
+      "loss": 3.2546,
+      "step": 35500
+    },
+    {
+      "epoch": 0.712,
+      "grad_norm": 0.15264350175857544,
+      "learning_rate": 0.000420323544307581,
+      "loss": 3.2436,
+      "step": 35600
+    },
+    {
+      "epoch": 0.714,
+      "grad_norm": 0.21544255316257477,
+      "learning_rate": 0.0004149469641111302,
+      "loss": 3.2318,
+      "step": 35700
+    },
+    {
+      "epoch": 0.716,
+      "grad_norm": 0.16077803075313568,
+      "learning_rate": 0.00040959597602977806,
+      "loss": 3.2545,
+      "step": 35800
+    },
+    {
+      "epoch": 0.718,
+      "grad_norm": 0.14488866925239563,
+      "learning_rate": 0.00040427081413307864,
+      "loss": 3.2526,
+      "step": 35900
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 0.1400013417005539,
+      "learning_rate": 0.00039897171136086363,
+      "loss": 3.2217,
+      "step": 36000
+    },
+    {
+      "epoch": 0.72,
+      "eval_accuracy": 0.3897240704500978,
+      "eval_loss": 3.257254123687744,
+      "eval_runtime": 11.7287,
+      "eval_samples_per_second": 85.261,
+      "eval_steps_per_second": 0.682,
+      "step": 36000
     }
   ],
   "logging_steps": 100,