Training in progress, step 8500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d70198e690533c8705cb606a2f8554e9c88db3919bc157b0b85cfd40b9163cdf
+oid sha256:df9038fe034db9a047f54c690d06b9114daf20184002362a66632a6acc917267
 size 441688704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f09de07399f3f34149aed6397af707e189d23d41a5d5df6968ab6e71d7d2629a
+oid sha256:748571902301cc129d3d670961c825093e36e3bbfcd02dfeb4d96e478d5d2c39
 size 883473803

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff6f17e3eb221fe462edccd50497bde0f3a71571ed479a52a41576181171c931
+oid sha256:ac39a3789a0a36db49e48938b741df4d9d564ce4af74645a95842f2e1155650b
 size 14645

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a95554cb3d06aec9d05e31c8207a60744e94359015aa846162464c9cdf88bcec
+oid sha256:ad6b24ce4baba0ebc24398b918705f0f0197e697b3b339da567a13464dc9788a
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fef1bbe15ebf93cd14ffe46ac40b68f1ba1e52a58545c7076dbc53cd30fcde1a
+oid sha256:15fd23d03fbf681c8030c1c6b801c1e0af68ea29f95c34bd8f1ed5a61659be76
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.9411764705882353,
+  "epoch": 1.0,
   "eval_steps": 500,
-  "global_step": 8000,
+  "global_step": 8500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1256,6 +1256,84 @@
       "eval_samples_per_second": 49.194,
       "eval_steps_per_second": 1.539,
       "step": 8000
+    },
+    {
+      "epoch": 0.9470588235294117,
+      "grad_norm": 0.37743404507637024,
+      "learning_rate": 2.6529411764705882e-05,
+      "loss": 3.477872314453125,
+      "step": 8050
+    },
+    {
+      "epoch": 0.9529411764705882,
+      "grad_norm": 0.37343254685401917,
+      "learning_rate": 2.3588235294117647e-05,
+      "loss": 3.266590576171875,
+      "step": 8100
+    },
+    {
+      "epoch": 0.9588235294117647,
+      "grad_norm": 0.3546009957790375,
+      "learning_rate": 2.0647058823529412e-05,
+      "loss": 3.2414059448242187,
+      "step": 8150
+    },
+    {
+      "epoch": 0.9647058823529412,
+      "grad_norm": 0.34603244066238403,
+      "learning_rate": 1.7705882352941177e-05,
+      "loss": 3.3995672607421876,
+      "step": 8200
+    },
+    {
+      "epoch": 0.9705882352941176,
+      "grad_norm": 0.34663328528404236,
+      "learning_rate": 1.4764705882352942e-05,
+      "loss": 3.4866387939453123,
+      "step": 8250
+    },
+    {
+      "epoch": 0.9764705882352941,
+      "grad_norm": 0.3719863295555115,
+      "learning_rate": 1.1823529411764707e-05,
+      "loss": 3.5252374267578124,
+      "step": 8300
+    },
+    {
+      "epoch": 0.9823529411764705,
+      "grad_norm": 0.3406435549259186,
+      "learning_rate": 8.882352941176472e-06,
+      "loss": 3.4751815795898438,
+      "step": 8350
+    },
+    {
+      "epoch": 0.9882352941176471,
+      "grad_norm": 0.34062960743904114,
+      "learning_rate": 5.941176470588235e-06,
+      "loss": 3.493436279296875,
+      "step": 8400
+    },
+    {
+      "epoch": 0.9941176470588236,
+      "grad_norm": 0.34683459997177124,
+      "learning_rate": 3e-06,
+      "loss": 3.49129638671875,
+      "step": 8450
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.36988383531570435,
+      "learning_rate": 5.882352941176471e-08,
+      "loss": 3.492980651855469,
+      "step": 8500
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 3.3368608951568604,
+      "eval_runtime": 177.9297,
+      "eval_samples_per_second": 48.856,
+      "eval_steps_per_second": 1.529,
+      "step": 8500
     }
   ],
   "logging_steps": 50,
@@ -1270,12 +1348,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.33781520384e+17,
+  "total_flos": 1.42142865408e+17,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null