Training in progress, step 1500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b7da8882c4eba065851f3d33946d222f14c2f723a8e4b466de1f227567d55531
+oid sha256:badfbe39f8402d520d6a259ad2deb9dd7e1f6dfb6b9e1a7169877f5ecc01c510
 size 579748776

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3dc6db80c72368f3c3b7f1bca017a3f8af377e6e79bfb95dfa6de9e3819b27d4
+oid sha256:4613374d2023ed2b9eeed79a32ef746ff946c02062fd7d42e828096eaa259890
 size 1159627083

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a4d8242b37901ec7cc0992b7a6173ea32c89632c26198ca917c21035a4c247c4
+oid sha256:71ed970edcf023c3a09dae82375e820aadbfb7a0861253f35a94fb8633387ad3
 size 14917

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6bbac1cf1ce1610978037481a5035e6b523662562dd00a236dbb2507431643e9
+oid sha256:ef3ace7f288164d473a0c04358ab1c2df011edbd9de5a6bde6ef84f6a044d402
 size 14917

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d78ed09f8ef41008377f42bff0e363b7ba82ecd1c922f2e831caad0254e1ac5
+oid sha256:dbe99df1134c19a237dcc24ad13c86b0959bc0c02f203c836365c9b3181e5558
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.6,
+  "epoch": 0.75,
   "eval_steps": 100,
-  "global_step": 1200,
+  "global_step": 1500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -452,6 +452,117 @@
       "eval_samples_per_second": 64.855,
       "eval_steps_per_second": 2.14,
       "step": 1200
+    },
+    {
+      "epoch": 0.6125,
+      "grad_norm": 843.0389404296875,
+      "learning_rate": 3.748328323876868e-05,
+      "loss": 97.997,
+      "step": 1225
+    },
+    {
+      "epoch": 0.625,
+      "grad_norm": 657.6774291992188,
+      "learning_rate": 3.544006862640916e-05,
+      "loss": 97.6659,
+      "step": 1250
+    },
+    {
+      "epoch": 0.6375,
+      "grad_norm": 736.9610595703125,
+      "learning_rate": 3.342309199449991e-05,
+      "loss": 97.2111,
+      "step": 1275
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 629.177490234375,
+      "learning_rate": 3.143598807126035e-05,
+      "loss": 97.152,
+      "step": 1300
+    },
+    {
+      "epoch": 0.65,
+      "eval_accuracy": 0.15122059588304496,
+      "eval_loss": 6.054599761962891,
+      "eval_runtime": 7.3568,
+      "eval_samples_per_second": 65.926,
+      "eval_steps_per_second": 2.175,
+      "step": 1300
+    },
+    {
+      "epoch": 0.6625,
+      "grad_norm": 690.4661254882812,
+      "learning_rate": 2.9482337752269752e-05,
+      "loss": 97.7027,
+      "step": 1325
+    },
+    {
+      "epoch": 0.675,
+      "grad_norm": 853.2005615234375,
+      "learning_rate": 2.7565661647451425e-05,
+      "loss": 98.0302,
+      "step": 1350
+    },
+    {
+      "epoch": 0.6875,
+      "grad_norm": 652.2321166992188,
+      "learning_rate": 2.568941373669562e-05,
+      "loss": 97.5237,
+      "step": 1375
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 17031.59375,
+      "learning_rate": 2.3856975145554318e-05,
+      "loss": 97.8734,
+      "step": 1400
+    },
+    {
+      "epoch": 0.7,
+      "eval_accuracy": 0.14743788467072944,
+      "eval_loss": 6.094700336456299,
+      "eval_runtime": 7.6558,
+      "eval_samples_per_second": 63.351,
+      "eval_steps_per_second": 2.09,
+      "step": 1400
+    },
+    {
+      "epoch": 0.7125,
+      "grad_norm": 795.8380126953125,
+      "learning_rate": 2.2071648052224408e-05,
+      "loss": 98.055,
+      "step": 1425
+    },
+    {
+      "epoch": 0.725,
+      "grad_norm": 1413.1805419921875,
+      "learning_rate": 2.0336649736799495e-05,
+      "loss": 98.1603,
+      "step": 1450
+    },
+    {
+      "epoch": 0.7375,
+      "grad_norm": 746.7064208984375,
+      "learning_rate": 1.865510678351361e-05,
+      "loss": 97.9418,
+      "step": 1475
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 505.42279052734375,
+      "learning_rate": 1.7030049446425132e-05,
+      "loss": 97.4964,
+      "step": 1500
+    },
+    {
+      "epoch": 0.75,
+      "eval_accuracy": 0.15097016545574804,
+      "eval_loss": 6.041877746582031,
+      "eval_runtime": 7.513,
+      "eval_samples_per_second": 64.555,
+      "eval_steps_per_second": 2.13,
+      "step": 1500
     }
   ],
   "logging_steps": 25,
@@ -471,7 +582,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8.026688285835264e+17,
+  "total_flos": 1.003336035729408e+18,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null