Training in progress, step 1800, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:19f020f57d4a61360034ec006ae66facade0f2d21653389e6f14602a4142a050
+oid sha256:7e3ce014c4ffdeb3ed2d1bb4f167ab2f28f0e06615589c0b4b8532fa2bda557a
 size 2558403928

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc606d36977ccbf3d4b122958eb1f61737f84fd18ecaaffc4930cc8fd07e9364
+oid sha256:d6bbd954c177e56d9e20277125d9cf6754fff55e598bb9de9bdec4e2cbe1afd8
 size 1313638993

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b62ca0429ec7faf1375b45507b4b6556f7e8ec80e94acc260c0727d9c01b414c
+oid sha256:1c51602986df284fcdbb1c3432b905ff86ef24e41fe8fb42533918ae0e10ec6f
 size 14645

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca372268f4fa9335030c0cb7aedb6cdba75f457da50e7a4034abb1a2d0843689
+oid sha256:fa0408efb69cab96d5bab9a1aaf44cedbc9fc8d34f4cef378d81605e5c026d5c
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa39772c5e0acad2bda0112b852159f96e3b408cefd615906b49c8dfa5e48e61
+oid sha256:020caa0fd59e7adabae53f0d39b914916a456345c07ea74ca27ee8ec408257e7
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.2,
+  "epoch": 1.44,
   "eval_steps": 500,
-  "global_step": 1500,
+  "global_step": 1800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1065,6 +1065,216 @@
       "learning_rate": 7.445598762092537e-05,
       "loss": 5.4473,
       "step": 1500
+    },
+    {
+      "epoch": 1.208,
+      "grad_norm": 7.027050495147705,
+      "learning_rate": 7.319053606355061e-05,
+      "loss": 5.1231,
+      "step": 1510
+    },
+    {
+      "epoch": 1.216,
+      "grad_norm": 6.161197662353516,
+      "learning_rate": 7.192969352016383e-05,
+      "loss": 5.1066,
+      "step": 1520
+    },
+    {
+      "epoch": 1.224,
+      "grad_norm": 5.8758745193481445,
+      "learning_rate": 7.067367675156758e-05,
+      "loss": 5.1743,
+      "step": 1530
+    },
+    {
+      "epoch": 1.232,
+      "grad_norm": 8.138237953186035,
+      "learning_rate": 6.942270168892959e-05,
+      "loss": 5.2096,
+      "step": 1540
+    },
+    {
+      "epoch": 1.24,
+      "grad_norm": 7.498131275177002,
+      "learning_rate": 6.817698339666066e-05,
+      "loss": 5.1718,
+      "step": 1550
+    },
+    {
+      "epoch": 1.248,
+      "grad_norm": 5.885447025299072,
+      "learning_rate": 6.693673603544097e-05,
+      "loss": 5.4034,
+      "step": 1560
+    },
+    {
+      "epoch": 1.256,
+      "grad_norm": 5.564108848571777,
+      "learning_rate": 6.570217282540247e-05,
+      "loss": 5.0762,
+      "step": 1570
+    },
+    {
+      "epoch": 1.264,
+      "grad_norm": 5.904695510864258,
+      "learning_rate": 6.447350600947236e-05,
+      "loss": 4.9994,
+      "step": 1580
+    },
+    {
+      "epoch": 1.272,
+      "grad_norm": 6.91570520401001,
+      "learning_rate": 6.325094681688503e-05,
+      "loss": 5.1286,
+      "step": 1590
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 5.768303394317627,
+      "learning_rate": 6.203470542686798e-05,
+      "loss": 4.975,
+      "step": 1600
+    },
+    {
+      "epoch": 1.288,
+      "grad_norm": 9.351409912109375,
+      "learning_rate": 6.082499093250831e-05,
+      "loss": 4.9613,
+      "step": 1610
+    },
+    {
+      "epoch": 1.296,
+      "grad_norm": 9.572948455810547,
+      "learning_rate": 5.962201130480618e-05,
+      "loss": 4.7479,
+      "step": 1620
+    },
+    {
+      "epoch": 1.304,
+      "grad_norm": 7.169508457183838,
+      "learning_rate": 5.842597335692067e-05,
+      "loss": 5.2066,
+      "step": 1630
+    },
+    {
+      "epoch": 1.312,
+      "grad_norm": 7.029344081878662,
+      "learning_rate": 5.7237082708615186e-05,
+      "loss": 4.7997,
+      "step": 1640
+    },
+    {
+      "epoch": 1.32,
+      "grad_norm": 6.824025630950928,
+      "learning_rate": 5.605554375090784e-05,
+      "loss": 4.6027,
+      "step": 1650
+    },
+    {
+      "epoch": 1.328,
+      "grad_norm": 12.187256813049316,
+      "learning_rate": 5.488155961093298e-05,
+      "loss": 5.03,
+      "step": 1660
+    },
+    {
+      "epoch": 1.336,
+      "grad_norm": 5.913212776184082,
+      "learning_rate": 5.3715332117020154e-05,
+      "loss": 4.7387,
+      "step": 1670
+    },
+    {
+      "epoch": 1.3439999999999999,
+      "grad_norm": 6.245068550109863,
+      "learning_rate": 5.2557061763996354e-05,
+      "loss": 5.0907,
+      "step": 1680
+    },
+    {
+      "epoch": 1.3519999999999999,
+      "grad_norm": 9.76169490814209,
+      "learning_rate": 5.140694767871733e-05,
+      "loss": 5.1469,
+      "step": 1690
+    },
+    {
+      "epoch": 1.3599999999999999,
+      "grad_norm": 10.653762817382812,
+      "learning_rate": 5.026518758583434e-05,
+      "loss": 4.9712,
+      "step": 1700
+    },
+    {
+      "epoch": 1.3679999999999999,
+      "grad_norm": 7.157083511352539,
+      "learning_rate": 4.9131977773801765e-05,
+      "loss": 4.6749,
+      "step": 1710
+    },
+    {
+      "epoch": 1.376,
+      "grad_norm": 8.09749698638916,
+      "learning_rate": 4.8007513061131736e-05,
+      "loss": 4.5003,
+      "step": 1720
+    },
+    {
+      "epoch": 1.384,
+      "grad_norm": 6.536433219909668,
+      "learning_rate": 4.6891986762901406e-05,
+      "loss": 4.2644,
+      "step": 1730
+    },
+    {
+      "epoch": 1.392,
+      "grad_norm": 7.866100311279297,
+      "learning_rate": 4.578559065751873e-05,
+      "loss": 4.721,
+      "step": 1740
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 5.806945323944092,
+      "learning_rate": 4.4688514953752515e-05,
+      "loss": 4.6537,
+      "step": 1750
+    },
+    {
+      "epoch": 1.408,
+      "grad_norm": 8.229887962341309,
+      "learning_rate": 4.360094825803203e-05,
+      "loss": 4.7068,
+      "step": 1760
+    },
+    {
+      "epoch": 1.416,
+      "grad_norm": 10.401880264282227,
+      "learning_rate": 4.25230775420224e-05,
+      "loss": 4.5295,
+      "step": 1770
+    },
+    {
+      "epoch": 1.424,
+      "grad_norm": 7.166602611541748,
+      "learning_rate": 4.145508811048089e-05,
+      "loss": 4.5715,
+      "step": 1780
+    },
+    {
+      "epoch": 1.432,
+      "grad_norm": 8.82656478881836,
+      "learning_rate": 4.039716356939981e-05,
+      "loss": 4.8924,
+      "step": 1790
+    },
+    {
+      "epoch": 1.44,
+      "grad_norm": 8.747090339660645,
+      "learning_rate": 3.9349485794441395e-05,
+      "loss": 4.5401,
+      "step": 1800
     }
   ],
   "logging_steps": 10,