Training in progress, step 290000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a559b0eb78c919f7317440c34ff9418c01d3807356031c4529bd37c83a4e55b0
+oid sha256:7f9d4a02e518c6040f400dc71e199bb375bfe7d386fc2532b4f6b29080e6ba85
 size 202194449

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ee323f397e17b15c555d3f760433b7c390cda1ae17a7f66787ce543a9c888720
+oid sha256:ce2bfde6677c6364de7dd881d110ad8c08a2d67e11a6db2ce02cc6aaf9d80410
 size 102501541

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:231bfff5d6e31c2ba099341e84048971dcc6fd877303b4d5b509a5fb9426fe40
+oid sha256:ab923fbe4c25572b44a728c580cd0d9f3b121bade2ff37e411ad54b9de809e39
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:231bfff5d6e31c2ba099341e84048971dcc6fd877303b4d5b509a5fb9426fe40
+oid sha256:ab923fbe4c25572b44a728c580cd0d9f3b121bade2ff37e411ad54b9de809e39
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:231bfff5d6e31c2ba099341e84048971dcc6fd877303b4d5b509a5fb9426fe40
+oid sha256:ab923fbe4c25572b44a728c580cd0d9f3b121bade2ff37e411ad54b9de809e39
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:231bfff5d6e31c2ba099341e84048971dcc6fd877303b4d5b509a5fb9426fe40
+oid sha256:ab923fbe4c25572b44a728c580cd0d9f3b121bade2ff37e411ad54b9de809e39
 size 14503

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:231bfff5d6e31c2ba099341e84048971dcc6fd877303b4d5b509a5fb9426fe40
+oid sha256:ab923fbe4c25572b44a728c580cd0d9f3b121bade2ff37e411ad54b9de809e39
 size 14503

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:231bfff5d6e31c2ba099341e84048971dcc6fd877303b4d5b509a5fb9426fe40
+oid sha256:ab923fbe4c25572b44a728c580cd0d9f3b121bade2ff37e411ad54b9de809e39
 size 14503

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:231bfff5d6e31c2ba099341e84048971dcc6fd877303b4d5b509a5fb9426fe40
+oid sha256:ab923fbe4c25572b44a728c580cd0d9f3b121bade2ff37e411ad54b9de809e39
 size 14503

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:231bfff5d6e31c2ba099341e84048971dcc6fd877303b4d5b509a5fb9426fe40
+oid sha256:ab923fbe4c25572b44a728c580cd0d9f3b121bade2ff37e411ad54b9de809e39
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:80db35d9a6af0da10cd7cebe3bf01f3932293e48fc6a8607555efe3b5591e844
+oid sha256:39bc196d8aea9810b9698ff8cd04e2aeef8774f706fbd61ae0f0055bbacd0eaf
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 6.523917146252242,
-  "global_step": 280000,
+  "epoch": 6.756914187189823,
+  "global_step": 290000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -5606,11 +5606,211 @@
       "eval_samples_per_second": 1557.23,
       "eval_steps_per_second": 24.797,
       "step": 280000
+    },
+    {
+      "epoch": 6.54,
+      "learning_rate": 0.00013777852207079235,
+      "loss": 0.2691,
+      "step": 280500
+    },
+    {
+      "epoch": 6.55,
+      "learning_rate": 0.00013730250483349825,
+      "loss": 0.2686,
+      "step": 281000
+    },
+    {
+      "epoch": 6.55,
+      "eval_loss": 0.2525520324707031,
+      "eval_runtime": 1.4509,
+      "eval_samples_per_second": 1514.902,
+      "eval_steps_per_second": 24.123,
+      "step": 281000
+    },
+    {
+      "epoch": 6.56,
+      "learning_rate": 0.00013682668113317584,
+      "loss": 0.2688,
+      "step": 281500
+    },
+    {
+      "epoch": 6.57,
+      "learning_rate": 0.00013635105617335703,
+      "loss": 0.2686,
+      "step": 282000
+    },
+    {
+      "epoch": 6.57,
+      "eval_loss": 0.2530405819416046,
+      "eval_runtime": 1.446,
+      "eval_samples_per_second": 1520.041,
+      "eval_steps_per_second": 24.204,
+      "step": 282000
+    },
+    {
+      "epoch": 6.58,
+      "learning_rate": 0.00013587563515539996,
+      "loss": 0.2686,
+      "step": 282500
+    },
+    {
+      "epoch": 6.59,
+      "learning_rate": 0.00013540042327843296,
+      "loss": 0.2681,
+      "step": 283000
+    },
+    {
+      "epoch": 6.59,
+      "eval_loss": 0.252304345369339,
+      "eval_runtime": 1.4523,
+      "eval_samples_per_second": 1513.433,
+      "eval_steps_per_second": 24.099,
+      "step": 283000
+    },
+    {
+      "epoch": 6.61,
+      "learning_rate": 0.00013492542573929678,
+      "loss": 0.2686,
+      "step": 283500
+    },
+    {
+      "epoch": 6.62,
+      "learning_rate": 0.00013445064773248846,
+      "loss": 0.2683,
+      "step": 284000
+    },
+    {
+      "epoch": 6.62,
+      "eval_loss": 0.2517680823802948,
+      "eval_runtime": 1.4564,
+      "eval_samples_per_second": 1509.219,
+      "eval_steps_per_second": 24.032,
+      "step": 284000
+    },
+    {
+      "epoch": 6.63,
+      "learning_rate": 0.00013397609445010432,
+      "loss": 0.2684,
+      "step": 284500
+    },
+    {
+      "epoch": 6.64,
+      "learning_rate": 0.00013350177108178288,
+      "loss": 0.268,
+      "step": 285000
+    },
+    {
+      "epoch": 6.64,
+      "eval_loss": 0.25080546736717224,
+      "eval_runtime": 1.4547,
+      "eval_samples_per_second": 1510.937,
+      "eval_steps_per_second": 24.06,
+      "step": 285000
+    },
+    {
+      "epoch": 6.65,
+      "learning_rate": 0.00013302768281464863,
+      "loss": 0.2682,
+      "step": 285500
+    },
+    {
+      "epoch": 6.66,
+      "learning_rate": 0.0001325538348332548,
+      "loss": 0.2683,
+      "step": 286000
+    },
+    {
+      "epoch": 6.66,
+      "eval_loss": 0.25022614002227783,
+      "eval_runtime": 1.4198,
+      "eval_samples_per_second": 1548.074,
+      "eval_steps_per_second": 24.651,
+      "step": 286000
+    },
+    {
+      "epoch": 6.68,
+      "learning_rate": 0.00013208023231952706,
+      "loss": 0.2684,
+      "step": 286500
+    },
+    {
+      "epoch": 6.69,
+      "learning_rate": 0.0001316068804527066,
+      "loss": 0.2681,
+      "step": 287000
+    },
+    {
+      "epoch": 6.69,
+      "eval_loss": 0.2507327198982239,
+      "eval_runtime": 1.423,
+      "eval_samples_per_second": 1544.594,
+      "eval_steps_per_second": 24.595,
+      "step": 287000
+    },
+    {
+      "epoch": 6.7,
+      "learning_rate": 0.00013113378440929353,
+      "loss": 0.2682,
+      "step": 287500
+    },
+    {
+      "epoch": 6.71,
+      "learning_rate": 0.00013066094936299056,
+      "loss": 0.2681,
+      "step": 288000
+    },
+    {
+      "epoch": 6.71,
+      "eval_loss": 0.25175246596336365,
+      "eval_runtime": 1.4465,
+      "eval_samples_per_second": 1519.496,
+      "eval_steps_per_second": 24.196,
+      "step": 288000
+    },
+    {
+      "epoch": 6.72,
+      "learning_rate": 0.00013018838048464582,
+      "loss": 0.2677,
+      "step": 288500
+    },
+    {
+      "epoch": 6.73,
+      "learning_rate": 0.00012971608294219702,
+      "loss": 0.2679,
+      "step": 289000
+    },
+    {
+      "epoch": 6.73,
+      "eval_loss": 0.2503984272480011,
+      "eval_runtime": 1.4389,
+      "eval_samples_per_second": 1527.568,
+      "eval_steps_per_second": 24.324,
+      "step": 289000
+    },
+    {
+      "epoch": 6.75,
+      "learning_rate": 0.00012924406190061423,
+      "loss": 0.2677,
+      "step": 289500
+    },
+    {
+      "epoch": 6.76,
+      "learning_rate": 0.0001287723225218441,
+      "loss": 0.2675,
+      "step": 290000
+    },
+    {
+      "epoch": 6.76,
+      "eval_loss": 0.250543475151062,
+      "eval_runtime": 1.4231,
+      "eval_samples_per_second": 1544.544,
+      "eval_steps_per_second": 24.595,
+      "step": 290000
     }
   ],
   "max_steps": 500000,
   "num_train_epochs": 12,
-  "total_flos": 8.945624903740559e+21,
+  "total_flos": 9.265112042515059e+21,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ee323f397e17b15c555d3f760433b7c390cda1ae17a7f66787ce543a9c888720
+oid sha256:ce2bfde6677c6364de7dd881d110ad8c08a2d67e11a6db2ce02cc6aaf9d80410
 size 102501541