Training in progress, step 750, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:17f1e891cbcbfebdb8fb05fb3584ed52b4d300c873323006bab56bff1a83e477
+oid sha256:9f773dc94967b7ee6e551db696f34227eb983340cfd6ce1fc1ae2d7d9ba5d943
 size 3826461296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f395dc9eec3233076c8a6eab517b6046c5f769c34f8cc42ea1aada63996b4194
+oid sha256:8632716595be573dc0ed32f03651903484a98a76acfa6f6710d2c042e6a3c5ea
 size 2479123301

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ff58b41c3672e659a0eb46d9ed11a0ca17415e7a2643a3ddfbaebb9f4e67f8f
+oid sha256:100000ea5d81ef450688ed224677c94deb5fa0928415e9497ab5b09006179386
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:06a53cb7201a63e56775adc37fbc436df78256e51be756e6ae4dae646e834711
+oid sha256:c8b125c082de6f20d827ac9ce3a7228054a763972dd6779dfe18031391e49829
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.2,
+  "epoch": 0.3,
   "eval_steps": 500,
-  "global_step": 500,
+  "global_step": 750,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -358,6 +358,181 @@
       "learning_rate": 4.0403225806451614e-05,
       "loss": 1.112,
       "step": 500
+    },
+    {
+      "epoch": 0.204,
+      "grad_norm": 17.082433700561523,
+      "learning_rate": 4.020161290322581e-05,
+      "loss": 0.9832,
+      "step": 510
+    },
+    {
+      "epoch": 0.208,
+      "grad_norm": 15.006577491760254,
+      "learning_rate": 4e-05,
+      "loss": 0.8085,
+      "step": 520
+    },
+    {
+      "epoch": 0.212,
+      "grad_norm": 23.60434913635254,
+      "learning_rate": 3.97983870967742e-05,
+      "loss": 1.2125,
+      "step": 530
+    },
+    {
+      "epoch": 0.216,
+      "grad_norm": 20.58735466003418,
+      "learning_rate": 3.959677419354839e-05,
+      "loss": 0.9544,
+      "step": 540
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 24.197471618652344,
+      "learning_rate": 3.939516129032259e-05,
+      "loss": 0.762,
+      "step": 550
+    },
+    {
+      "epoch": 0.224,
+      "grad_norm": 20.651039123535156,
+      "learning_rate": 3.9193548387096776e-05,
+      "loss": 0.9309,
+      "step": 560
+    },
+    {
+      "epoch": 0.228,
+      "grad_norm": 20.045127868652344,
+      "learning_rate": 3.901209677419355e-05,
+      "loss": 0.8862,
+      "step": 570
+    },
+    {
+      "epoch": 0.232,
+      "grad_norm": 18.766826629638672,
+      "learning_rate": 3.8810483870967744e-05,
+      "loss": 0.9722,
+      "step": 580
+    },
+    {
+      "epoch": 0.236,
+      "grad_norm": 28.41654396057129,
+      "learning_rate": 3.860887096774194e-05,
+      "loss": 1.0501,
+      "step": 590
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 14.174357414245605,
+      "learning_rate": 3.8407258064516134e-05,
+      "loss": 0.9859,
+      "step": 600
+    },
+    {
+      "epoch": 0.244,
+      "grad_norm": 18.710617065429688,
+      "learning_rate": 3.820564516129033e-05,
+      "loss": 1.0233,
+      "step": 610
+    },
+    {
+      "epoch": 0.248,
+      "grad_norm": 22.399860382080078,
+      "learning_rate": 3.800403225806452e-05,
+      "loss": 1.1186,
+      "step": 620
+    },
+    {
+      "epoch": 0.252,
+      "grad_norm": 18.62351417541504,
+      "learning_rate": 3.780241935483871e-05,
+      "loss": 1.1073,
+      "step": 630
+    },
+    {
+      "epoch": 0.256,
+      "grad_norm": 16.706384658813477,
+      "learning_rate": 3.7600806451612906e-05,
+      "loss": 0.9013,
+      "step": 640
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 14.72787857055664,
+      "learning_rate": 3.7399193548387094e-05,
+      "loss": 0.8391,
+      "step": 650
+    },
+    {
+      "epoch": 0.264,
+      "grad_norm": 17.56301498413086,
+      "learning_rate": 3.719758064516129e-05,
+      "loss": 0.9974,
+      "step": 660
+    },
+    {
+      "epoch": 0.268,
+      "grad_norm": 18.445892333984375,
+      "learning_rate": 3.6995967741935484e-05,
+      "loss": 0.9481,
+      "step": 670
+    },
+    {
+      "epoch": 0.272,
+      "grad_norm": 15.60034465789795,
+      "learning_rate": 3.679435483870968e-05,
+      "loss": 0.8022,
+      "step": 680
+    },
+    {
+      "epoch": 0.276,
+      "grad_norm": 23.985820770263672,
+      "learning_rate": 3.659274193548387e-05,
+      "loss": 0.8189,
+      "step": 690
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 26.464324951171875,
+      "learning_rate": 3.639112903225806e-05,
+      "loss": 0.8447,
+      "step": 700
+    },
+    {
+      "epoch": 0.284,
+      "grad_norm": 24.74170684814453,
+      "learning_rate": 3.6189516129032256e-05,
+      "loss": 0.8458,
+      "step": 710
+    },
+    {
+      "epoch": 0.288,
+      "grad_norm": 15.681292533874512,
+      "learning_rate": 3.598790322580645e-05,
+      "loss": 0.9417,
+      "step": 720
+    },
+    {
+      "epoch": 0.292,
+      "grad_norm": 18.264453887939453,
+      "learning_rate": 3.5786290322580645e-05,
+      "loss": 0.8536,
+      "step": 730
+    },
+    {
+      "epoch": 0.296,
+      "grad_norm": 15.522205352783203,
+      "learning_rate": 3.558467741935484e-05,
+      "loss": 0.6493,
+      "step": 740
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 36.796165466308594,
+      "learning_rate": 3.5383064516129035e-05,
+      "loss": 0.8446,
+      "step": 750
     }
   ],
   "logging_steps": 10,
@@ -377,7 +552,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 9020891125518336.0,
+  "total_flos": 1.3512970727276544e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null