Training in progress, step 34000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e13225a7520c413144c7c1c355420a5c229ae4cb9ee2fc3ee9e6ec481a263534
+oid sha256:eacd16009db792813323d990cfe5dae9dfaf2c1b2b6746f6ce4ee5c5abd05fa3
 size 529337896

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc20992a7d2218d1b0875c85fb7d66067b2298850958dd0d9986500e15e7e571
+oid sha256:86b59222e117c9663552ff919bf9d06c38349de96bfd51727eb1c2c51c1eef72
 size 871247243

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:77b2a9c9cdb925b9023364da46617175730aa23d1c7044261e0928c3c8b3fa89
+oid sha256:efa0171c7cd70527d3a922da6317b15994f35a839e2d8505c68b0fc08f030110
 size 14645

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:39126e57e188afe7385c7c1c99d9aefd09279fe89a89d601c31fe9b0f88441d3
+oid sha256:dcc336e7edab566b72f19c8cdbf557762e0e53e457ed4985a87b74bd22371a59
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.64,
+  "epoch": 0.68,
   "eval_steps": 1000,
-  "global_step": 32000,
+  "global_step": 34000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2536,6 +2536,164 @@
       "eval_samples_per_second": 81.928,
       "eval_steps_per_second": 0.655,
       "step": 32000
+    },
+    {
+      "epoch": 0.642,
+      "grad_norm": 0.15901386737823486,
+      "learning_rate": 0.0006227308207857332,
+      "loss": 3.2593,
+      "step": 32100
+    },
+    {
+      "epoch": 0.644,
+      "grad_norm": 0.20247270166873932,
+      "learning_rate": 0.0006166139792108727,
+      "loss": 3.2716,
+      "step": 32200
+    },
+    {
+      "epoch": 0.646,
+      "grad_norm": 0.1866617053747177,
+      "learning_rate": 0.0006105139081825601,
+      "loss": 3.2867,
+      "step": 32300
+    },
+    {
+      "epoch": 0.648,
+      "grad_norm": 0.14510272443294525,
+      "learning_rate": 0.0006044308745376636,
+      "loss": 3.273,
+      "step": 32400
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 0.13237079977989197,
+      "learning_rate": 0.000598365144367781,
+      "loss": 3.2621,
+      "step": 32500
+    },
+    {
+      "epoch": 0.652,
+      "grad_norm": 0.15459007024765015,
+      "learning_rate": 0.0005923169830076003,
+      "loss": 3.2658,
+      "step": 32600
+    },
+    {
+      "epoch": 0.654,
+      "grad_norm": 0.13574740290641785,
+      "learning_rate": 0.0005862866550232925,
+      "loss": 3.2789,
+      "step": 32700
+    },
+    {
+      "epoch": 0.656,
+      "grad_norm": 0.15900640189647675,
+      "learning_rate": 0.0005802744242009394,
+      "loss": 3.2648,
+      "step": 32800
+    },
+    {
+      "epoch": 0.658,
+      "grad_norm": 0.18648633360862732,
+      "learning_rate": 0.000574280553534994,
+      "loss": 3.2575,
+      "step": 32900
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 0.15465696156024933,
+      "learning_rate": 0.0005683053052167772,
+      "loss": 3.2787,
+      "step": 33000
+    },
+    {
+      "epoch": 0.66,
+      "eval_accuracy": 0.3878962818003914,
+      "eval_loss": 3.276221513748169,
+      "eval_runtime": 11.2808,
+      "eval_samples_per_second": 88.646,
+      "eval_steps_per_second": 0.709,
+      "step": 33000
+    },
+    {
+      "epoch": 0.662,
+      "grad_norm": 0.15960443019866943,
+      "learning_rate": 0.000562348940623007,
+      "loss": 3.2866,
+      "step": 33100
+    },
+    {
+      "epoch": 0.664,
+      "grad_norm": 0.13718590140342712,
+      "learning_rate": 0.0005564117203043664,
+      "loss": 3.2549,
+      "step": 33200
+    },
+    {
+      "epoch": 0.666,
+      "grad_norm": 0.1479761153459549,
+      "learning_rate": 0.0005504939039741067,
+      "loss": 3.2697,
+      "step": 33300
+    },
+    {
+      "epoch": 0.668,
+      "grad_norm": 0.15424597263336182,
+      "learning_rate": 0.0005445957504966848,
+      "loss": 3.2743,
+      "step": 33400
+    },
+    {
+      "epoch": 0.67,
+      "grad_norm": 0.13904234766960144,
+      "learning_rate": 0.0005387175178764416,
+      "loss": 3.2551,
+      "step": 33500
+    },
+    {
+      "epoch": 0.672,
+      "grad_norm": 0.18515262007713318,
+      "learning_rate": 0.000532859463246314,
+      "loss": 3.2581,
+      "step": 33600
+    },
+    {
+      "epoch": 0.674,
+      "grad_norm": 0.1791761815547943,
+      "learning_rate": 0.0005270218428565896,
+      "loss": 3.2701,
+      "step": 33700
+    },
+    {
+      "epoch": 0.676,
+      "grad_norm": 0.17315128445625305,
+      "learning_rate": 0.0005212049120636959,
+      "loss": 3.2631,
+      "step": 33800
+    },
+    {
+      "epoch": 0.678,
+      "grad_norm": 0.1509447544813156,
+      "learning_rate": 0.000515408925319029,
+      "loss": 3.2592,
+      "step": 33900
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 0.1570684164762497,
+      "learning_rate": 0.0005096341361578265,
+      "loss": 3.2685,
+      "step": 34000
+    },
+    {
+      "epoch": 0.68,
+      "eval_accuracy": 0.3882113502935421,
+      "eval_loss": 3.2670066356658936,
+      "eval_runtime": 11.2814,
+      "eval_samples_per_second": 88.642,
+      "eval_steps_per_second": 0.709,
+      "step": 34000
     }
   ],
   "logging_steps": 100,