Training in progress, epoch 11, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c30855507821eae60b9a8981ec29a51e2006c4710fe70f6eddd878cdf727bc5
+oid sha256:fae6d18c31da2f3123d26fe82f253230f081a7f04d6096c55edf8a79d57c0bff
 size 2682482800

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd9acbde3767dd0193d5328dd03bad7ab2d4f2ea5faf5f9f997bed12d35d2d5f
+oid sha256:57eff680a79bd13191e5837ccb2bf3e205b17f06697567bf05c733d21f919c9e
 size 5365108834

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e18b7a226bd09a1c0b40f0d1408dd50fa3221531aba57476aa3bd09f3bf91da
+oid sha256:7620d0d74aa4af76afd5408d773ed4748a8acb91b0e964a8cddab8e88f040c64
 size 15006

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:14ff11420ab6e05bda6bd86fde16e8ed4af7e505a292540a3a802d06de28458c
+oid sha256:9b2b83ebf1ec1af378519da07bfb09fb79fd0733745840a41e1fc2e6668cb73a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 10.997999636297509,
+  "epoch": 11.997999636297509,
   "eval_steps": 50,
-  "global_step": 3773,
+  "global_step": 4116,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1132,6 +1132,111 @@
       "eval_samples_per_second": 41.449,
       "eval_steps_per_second": 20.725,
       "step": 3750
+    },
+    {
+      "epoch": 11.078559738134206,
+      "grad_norm": 61.34590530395508,
+      "learning_rate": 4.46064139941691e-05,
+      "loss": 0.7639,
+      "step": 3800
+    },
+    {
+      "epoch": 11.078559738134206,
+      "eval_loss": 0.731596052646637,
+      "eval_runtime": 116.4502,
+      "eval_samples_per_second": 41.443,
+      "eval_steps_per_second": 20.721,
+      "step": 3800
+    },
+    {
+      "epoch": 11.224040734679033,
+      "grad_norm": 74.86040496826172,
+      "learning_rate": 4.387755102040816e-05,
+      "loss": 0.7515,
+      "step": 3850
+    },
+    {
+      "epoch": 11.224040734679033,
+      "eval_loss": 0.7297601699829102,
+      "eval_runtime": 116.5358,
+      "eval_samples_per_second": 41.412,
+      "eval_steps_per_second": 20.706,
+      "step": 3850
+    },
+    {
+      "epoch": 11.369521731223859,
+      "grad_norm": 53.91130828857422,
+      "learning_rate": 4.314868804664723e-05,
+      "loss": 0.7567,
+      "step": 3900
+    },
+    {
+      "epoch": 11.369521731223859,
+      "eval_loss": 0.7294139266014099,
+      "eval_runtime": 116.7175,
+      "eval_samples_per_second": 41.348,
+      "eval_steps_per_second": 20.674,
+      "step": 3900
+    },
+    {
+      "epoch": 11.515002727768685,
+      "grad_norm": 63.51275634765625,
+      "learning_rate": 4.2419825072886296e-05,
+      "loss": 0.7519,
+      "step": 3950
+    },
+    {
+      "epoch": 11.515002727768685,
+      "eval_loss": 0.7229241728782654,
+      "eval_runtime": 116.7452,
+      "eval_samples_per_second": 41.338,
+      "eval_steps_per_second": 20.669,
+      "step": 3950
+    },
+    {
+      "epoch": 11.660483724313512,
+      "grad_norm": 44.026119232177734,
+      "learning_rate": 4.1690962099125366e-05,
+      "loss": 0.7494,
+      "step": 4000
+    },
+    {
+      "epoch": 11.660483724313512,
+      "eval_loss": 0.7239974141120911,
+      "eval_runtime": 116.4117,
+      "eval_samples_per_second": 41.456,
+      "eval_steps_per_second": 20.728,
+      "step": 4000
+    },
+    {
+      "epoch": 11.805964720858338,
+      "grad_norm": 54.68580627441406,
+      "learning_rate": 4.0962099125364436e-05,
+      "loss": 0.7452,
+      "step": 4050
+    },
+    {
+      "epoch": 11.805964720858338,
+      "eval_loss": 0.7212454080581665,
+      "eval_runtime": 116.4854,
+      "eval_samples_per_second": 41.43,
+      "eval_steps_per_second": 20.715,
+      "step": 4050
+    },
+    {
+      "epoch": 11.951445717403164,
+      "grad_norm": 68.30030822753906,
+      "learning_rate": 4.02332361516035e-05,
+      "loss": 0.7498,
+      "step": 4100
+    },
+    {
+      "epoch": 11.951445717403164,
+      "eval_loss": 0.7175871133804321,
+      "eval_runtime": 116.3899,
+      "eval_samples_per_second": 41.464,
+      "eval_steps_per_second": 20.732,
+      "step": 4100
     }
   ],
   "logging_steps": 50,
@@ -1151,7 +1256,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 9.827787294554194e+17,
+  "total_flos": 1.072157800433451e+18,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null