Training in progress, step 1000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:56df8a1ec29b8cbb0c42a5264c1932a6249f0599e86f80aff848eb9853130cc0
+oid sha256:819f332804a581d3bba9599568c4b930cc17c3add617b442d1de87bc2c61522d
 size 3809184360

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:25722e7bf5fd0346d0d888862ebc90ce085ec4c8463a3f71bd2676c7fe82bedb
+oid sha256:758843891eea80d9773d542a9e0b754fa85102134de0c976e5a5692d56fcf5eb
 size 2457459557

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cdb8b30fd18ca6a24d25d627bd2e13a1e8f8cc7de78183781c4d89f29175eee0
+oid sha256:cba1622dcdafd049462e53ff248b7fef51550571b13d9c8fdcf0e035f1f9f15a
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c8b125c082de6f20d827ac9ce3a7228054a763972dd6779dfe18031391e49829
+oid sha256:1eff7a0a9bded1a7bd3fdba602c9613b8d890d63962a1be5e1c426de3b212f74
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.3,
+  "epoch": 0.4,
   "eval_steps": 500,
-  "global_step": 750,
+  "global_step": 1000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -533,6 +533,181 @@
       "learning_rate": 3.5383064516129035e-05,
       "loss": 0.8895,
       "step": 750
+    },
+    {
+      "epoch": 0.304,
+      "grad_norm": 23.548425674438477,
+      "learning_rate": 3.518145161290323e-05,
+      "loss": 0.8265,
+      "step": 760
+    },
+    {
+      "epoch": 0.308,
+      "grad_norm": 13.085064888000488,
+      "learning_rate": 3.497983870967742e-05,
+      "loss": 0.699,
+      "step": 770
+    },
+    {
+      "epoch": 0.312,
+      "grad_norm": 18.08486557006836,
+      "learning_rate": 3.477822580645161e-05,
+      "loss": 0.8628,
+      "step": 780
+    },
+    {
+      "epoch": 0.316,
+      "grad_norm": 19.6446590423584,
+      "learning_rate": 3.457661290322581e-05,
+      "loss": 0.7162,
+      "step": 790
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 12.074228286743164,
+      "learning_rate": 3.4375e-05,
+      "loss": 0.8185,
+      "step": 800
+    },
+    {
+      "epoch": 0.324,
+      "grad_norm": 23.04579734802246,
+      "learning_rate": 3.41733870967742e-05,
+      "loss": 0.7279,
+      "step": 810
+    },
+    {
+      "epoch": 0.328,
+      "grad_norm": 14.027397155761719,
+      "learning_rate": 3.397177419354839e-05,
+      "loss": 0.7416,
+      "step": 820
+    },
+    {
+      "epoch": 0.332,
+      "grad_norm": 14.763921737670898,
+      "learning_rate": 3.377016129032258e-05,
+      "loss": 0.7644,
+      "step": 830
+    },
+    {
+      "epoch": 0.336,
+      "grad_norm": 19.76808738708496,
+      "learning_rate": 3.3568548387096774e-05,
+      "loss": 0.8096,
+      "step": 840
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 18.55767059326172,
+      "learning_rate": 3.336693548387097e-05,
+      "loss": 0.7125,
+      "step": 850
+    },
+    {
+      "epoch": 0.344,
+      "grad_norm": 19.148754119873047,
+      "learning_rate": 3.3165322580645164e-05,
+      "loss": 0.7357,
+      "step": 860
+    },
+    {
+      "epoch": 0.348,
+      "grad_norm": 23.397655487060547,
+      "learning_rate": 3.296370967741936e-05,
+      "loss": 0.7064,
+      "step": 870
+    },
+    {
+      "epoch": 0.352,
+      "grad_norm": 35.228939056396484,
+      "learning_rate": 3.2762096774193553e-05,
+      "loss": 0.625,
+      "step": 880
+    },
+    {
+      "epoch": 0.356,
+      "grad_norm": 29.815994262695312,
+      "learning_rate": 3.256048387096775e-05,
+      "loss": 0.7508,
+      "step": 890
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 15.86763858795166,
+      "learning_rate": 3.2358870967741936e-05,
+      "loss": 0.6148,
+      "step": 900
+    },
+    {
+      "epoch": 0.364,
+      "grad_norm": 19.546428680419922,
+      "learning_rate": 3.215725806451613e-05,
+      "loss": 0.9258,
+      "step": 910
+    },
+    {
+      "epoch": 0.368,
+      "grad_norm": 31.96335220336914,
+      "learning_rate": 3.1955645161290326e-05,
+      "loss": 0.7065,
+      "step": 920
+    },
+    {
+      "epoch": 0.372,
+      "grad_norm": 17.415355682373047,
+      "learning_rate": 3.175403225806452e-05,
+      "loss": 0.6998,
+      "step": 930
+    },
+    {
+      "epoch": 0.376,
+      "grad_norm": 11.98726749420166,
+      "learning_rate": 3.1552419354838715e-05,
+      "loss": 0.8191,
+      "step": 940
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 13.42738151550293,
+      "learning_rate": 3.135080645161291e-05,
+      "loss": 0.7401,
+      "step": 950
+    },
+    {
+      "epoch": 0.384,
+      "grad_norm": 13.586627006530762,
+      "learning_rate": 3.11491935483871e-05,
+      "loss": 0.6598,
+      "step": 960
+    },
+    {
+      "epoch": 0.388,
+      "grad_norm": 10.619296073913574,
+      "learning_rate": 3.0947580645161286e-05,
+      "loss": 0.876,
+      "step": 970
+    },
+    {
+      "epoch": 0.392,
+      "grad_norm": 16.72213363647461,
+      "learning_rate": 3.074596774193548e-05,
+      "loss": 0.8656,
+      "step": 980
+    },
+    {
+      "epoch": 0.396,
+      "grad_norm": 13.87735366821289,
+      "learning_rate": 3.0544354838709676e-05,
+      "loss": 0.5487,
+      "step": 990
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 13.45494556427002,
+      "learning_rate": 3.034274193548387e-05,
+      "loss": 0.7243,
+      "step": 1000
     }
   ],
   "logging_steps": 10,
@@ -552,7 +727,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.3535660950272e+16,
+  "total_flos": 1.8015590195712e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null