Training in progress, step 150000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a7f5c98114bb03a0107e9edbb2aa57590411cc0a9aced01e13efc323f9c7511d
+oid sha256:92c71503ee1be825f92e3abeedc33b7a6047ab3271078c12e7596499868d30e2
 size 202194449

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1151081009ac294a44ef99911473d89538dee75ada188d7d9e2d8f1a9b3231fc
+oid sha256:024301d8ba60de43a5f5ed99419c50422c1c826da65f5623681ea6f121160a82
 size 102501541

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c91cc3747c6b314cba53effe7863cb06ebbb2887876cfc49af2ce3563922b45f
+oid sha256:19060d643fcaa3a7b8933dd35852a490bf0b6b6b34dc4dd07e146c20f2bf45ce
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c91cc3747c6b314cba53effe7863cb06ebbb2887876cfc49af2ce3563922b45f
+oid sha256:19060d643fcaa3a7b8933dd35852a490bf0b6b6b34dc4dd07e146c20f2bf45ce
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c91cc3747c6b314cba53effe7863cb06ebbb2887876cfc49af2ce3563922b45f
+oid sha256:19060d643fcaa3a7b8933dd35852a490bf0b6b6b34dc4dd07e146c20f2bf45ce
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c91cc3747c6b314cba53effe7863cb06ebbb2887876cfc49af2ce3563922b45f
+oid sha256:19060d643fcaa3a7b8933dd35852a490bf0b6b6b34dc4dd07e146c20f2bf45ce
 size 14503

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c91cc3747c6b314cba53effe7863cb06ebbb2887876cfc49af2ce3563922b45f
+oid sha256:19060d643fcaa3a7b8933dd35852a490bf0b6b6b34dc4dd07e146c20f2bf45ce
 size 14503

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c91cc3747c6b314cba53effe7863cb06ebbb2887876cfc49af2ce3563922b45f
+oid sha256:19060d643fcaa3a7b8933dd35852a490bf0b6b6b34dc4dd07e146c20f2bf45ce
 size 14503

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c91cc3747c6b314cba53effe7863cb06ebbb2887876cfc49af2ce3563922b45f
+oid sha256:19060d643fcaa3a7b8933dd35852a490bf0b6b6b34dc4dd07e146c20f2bf45ce
 size 14503

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c91cc3747c6b314cba53effe7863cb06ebbb2887876cfc49af2ce3563922b45f
+oid sha256:19060d643fcaa3a7b8933dd35852a490bf0b6b6b34dc4dd07e146c20f2bf45ce
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f9522f343e5b1c37fe7e600f7b39d619e850350d8948dc240940a440582a0eb9
+oid sha256:c09454c2cc8aac6faf99c7970cf8bec57b59b683887c6bb291c3a0936d0e7d0d
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 3.5679698251694787,
-  "global_step": 140000,
+  "epoch": 3.822824812681584,
+  "global_step": 150000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2806,11 +2806,211 @@
       "eval_samples_per_second": 782.532,
       "eval_steps_per_second": 12.521,
       "step": 140000
+    },
+    {
+      "epoch": 3.58,
+      "learning_rate": 0.0002597105316716766,
+      "loss": 0.3038,
+      "step": 140500
+    },
+    {
+      "epoch": 3.59,
+      "learning_rate": 0.000259378263551047,
+      "loss": 0.303,
+      "step": 141000
+    },
+    {
+      "epoch": 3.59,
+      "eval_loss": 0.8184419870376587,
+      "eval_runtime": 1.2761,
+      "eval_samples_per_second": 783.611,
+      "eval_steps_per_second": 12.538,
+      "step": 141000
+    },
+    {
+      "epoch": 3.61,
+      "learning_rate": 0.0002590448539664501,
+      "loss": 0.3026,
+      "step": 141500
+    },
+    {
+      "epoch": 3.62,
+      "learning_rate": 0.00025871030656399966,
+      "loss": 0.3027,
+      "step": 142000
+    },
+    {
+      "epoch": 3.62,
+      "eval_loss": 0.8444017171859741,
+      "eval_runtime": 1.2977,
+      "eval_samples_per_second": 770.565,
+      "eval_steps_per_second": 12.329,
+      "step": 142000
+    },
+    {
+      "epoch": 3.63,
+      "learning_rate": 0.00025837462500225255,
+      "loss": 0.3026,
+      "step": 142500
+    },
+    {
+      "epoch": 3.64,
+      "learning_rate": 0.0002580378129521685,
+      "loss": 0.3024,
+      "step": 143000
+    },
+    {
+      "epoch": 3.64,
+      "eval_loss": 0.8401538133621216,
+      "eval_runtime": 1.3317,
+      "eval_samples_per_second": 750.939,
+      "eval_steps_per_second": 12.015,
+      "step": 143000
+    },
+    {
+      "epoch": 3.66,
+      "learning_rate": 0.0002576998740970701,
+      "loss": 0.3031,
+      "step": 143500
+    },
+    {
+      "epoch": 3.67,
+      "learning_rate": 0.00025736081213260253,
+      "loss": 0.3027,
+      "step": 144000
+    },
+    {
+      "epoch": 3.67,
+      "eval_loss": 0.8279548287391663,
+      "eval_runtime": 1.3186,
+      "eval_samples_per_second": 758.406,
+      "eval_steps_per_second": 12.134,
+      "step": 144000
+    },
+    {
+      "epoch": 3.68,
+      "learning_rate": 0.0002570206307666931,
+      "loss": 0.3038,
+      "step": 144500
+    },
+    {
+      "epoch": 3.7,
+      "learning_rate": 0.0002566793337195108,
+      "loss": 0.3029,
+      "step": 145000
+    },
+    {
+      "epoch": 3.7,
+      "eval_loss": 0.8254837393760681,
+      "eval_runtime": 1.2997,
+      "eval_samples_per_second": 769.407,
+      "eval_steps_per_second": 12.311,
+      "step": 145000
+    },
+    {
+      "epoch": 3.71,
+      "learning_rate": 0.0002563369247234254,
+      "loss": 0.3038,
+      "step": 145500
+    },
+    {
+      "epoch": 3.72,
+      "learning_rate": 0.0002559934075229669,
+      "loss": 0.3023,
+      "step": 146000
+    },
+    {
+      "epoch": 3.72,
+      "eval_loss": 0.8286687135696411,
+      "eval_runtime": 1.2798,
+      "eval_samples_per_second": 781.358,
+      "eval_steps_per_second": 12.502,
+      "step": 146000
+    },
+    {
+      "epoch": 3.73,
+      "learning_rate": 0.0002556487858747843,
+      "loss": 0.3023,
+      "step": 146500
+    },
+    {
+      "epoch": 3.75,
+      "learning_rate": 0.00025530306354760464,
+      "loss": 0.3024,
+      "step": 147000
+    },
+    {
+      "epoch": 3.75,
+      "eval_loss": 0.8175866007804871,
+      "eval_runtime": 1.2628,
+      "eval_samples_per_second": 791.915,
+      "eval_steps_per_second": 12.671,
+      "step": 147000
+    },
+    {
+      "epoch": 3.76,
+      "learning_rate": 0.000254956244322192,
+      "loss": 0.3022,
+      "step": 147500
+    },
+    {
+      "epoch": 3.77,
+      "learning_rate": 0.00025460833199130595,
+      "loss": 0.302,
+      "step": 148000
+    },
+    {
+      "epoch": 3.77,
+      "eval_loss": 0.8372282385826111,
+      "eval_runtime": 1.3637,
+      "eval_samples_per_second": 733.286,
+      "eval_steps_per_second": 11.733,
+      "step": 148000
+    },
+    {
+      "epoch": 3.78,
+      "learning_rate": 0.00025425933035965983,
+      "loss": 0.3031,
+      "step": 148500
+    },
+    {
+      "epoch": 3.8,
+      "learning_rate": 0.00025390924324387965,
+      "loss": 0.3019,
+      "step": 149000
+    },
+    {
+      "epoch": 3.8,
+      "eval_loss": 0.8220604658126831,
+      "eval_runtime": 1.363,
+      "eval_samples_per_second": 733.669,
+      "eval_steps_per_second": 11.739,
+      "step": 149000
+    },
+    {
+      "epoch": 3.81,
+      "learning_rate": 0.0002535580744724621,
+      "loss": 0.3021,
+      "step": 149500
+    },
+    {
+      "epoch": 3.82,
+      "learning_rate": 0.00025320582788573246,
+      "loss": 0.3016,
+      "step": 150000
+    },
+    {
+      "epoch": 3.82,
+      "eval_loss": 0.8250831365585327,
+      "eval_runtime": 1.3782,
+      "eval_samples_per_second": 725.588,
+      "eval_steps_per_second": 11.609,
+      "step": 150000
     }
   ],
   "max_steps": 500000,
   "num_train_epochs": 13,
-  "total_flos": 4.472779506103865e+21,
+  "total_flos": 4.792266644878365e+21,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1151081009ac294a44ef99911473d89538dee75ada188d7d9e2d8f1a9b3231fc
+oid sha256:024301d8ba60de43a5f5ed99419c50422c1c826da65f5623681ea6f121160a82
 size 102501541