Training in progress, step 6000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f8804038bfc8c4fff09781205b46f28d914f21115e30a8813fb451cdb64ad17
+oid sha256:546cd4e7ec947305a665edaa2e582e225d7b8301eaa78f72956ea9b0b6882be6
 size 2000137067

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6ccb2c6910f34be7a138f85235698d8f0ec58283fab1416ef6a153c170b333ed
+oid sha256:938f724c0f91c737457d75986a81bb14510b0f67d394e6715914ee6427257f11
 size 1002469625

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:047a205ba65d4143fae2458ea498dbf8e5a685cd3e2e670c6951c8a299de8ae5
+oid sha256:db097afe89ed3c3eb23a6fe209105077506d8139157678f90acd89f98273927d
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5789a0b7645be9b850d95a6b32fdc2dd662d33e25aea9a3e9fcb4a7309e592af
+oid sha256:ace18575c64fb9061a4bdb4187294f04e31e9a65a2e4da680ca78aeef9f963e2
 size 627

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.795248078266946,
-  "global_step": 4000,
+  "epoch": 4.1928721174004195,
+  "global_step": 6000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -268,11 +268,142 @@
       "eval_samples_per_second": 2.402,
       "eval_steps_per_second": 0.301,
       "step": 4000
+    },
+    {
+      "epoch": 2.87,
+      "learning_rate": 4.105945462673223e-05,
+      "loss": 2.9079,
+      "step": 4100
+    },
+    {
+      "epoch": 2.94,
+      "learning_rate": 4.0500670540903e-05,
+      "loss": 2.8688,
+      "step": 4200
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 3.994188645507376e-05,
+      "loss": 2.7398,
+      "step": 4300
+    },
+    {
+      "epoch": 3.07,
+      "learning_rate": 3.938310236924452e-05,
+      "loss": 2.5503,
+      "step": 4400
+    },
+    {
+      "epoch": 3.14,
+      "learning_rate": 3.882431828341529e-05,
+      "loss": 2.5121,
+      "step": 4500
+    },
+    {
+      "epoch": 3.21,
+      "learning_rate": 3.8265534197586055e-05,
+      "loss": 2.4625,
+      "step": 4600
+    },
+    {
+      "epoch": 3.28,
+      "learning_rate": 3.7706750111756815e-05,
+      "loss": 2.3833,
+      "step": 4700
+    },
+    {
+      "epoch": 3.35,
+      "learning_rate": 3.714796602592758e-05,
+      "loss": 2.3133,
+      "step": 4800
+    },
+    {
+      "epoch": 3.42,
+      "learning_rate": 3.658918194009835e-05,
+      "loss": 2.2152,
+      "step": 4900
+    },
+    {
+      "epoch": 3.49,
+      "learning_rate": 3.603039785426911e-05,
+      "loss": 2.2304,
+      "step": 5000
+    },
+    {
+      "epoch": 3.56,
+      "learning_rate": 3.5471613768439874e-05,
+      "loss": 2.1563,
+      "step": 5100
+    },
+    {
+      "epoch": 3.63,
+      "learning_rate": 3.491282968261064e-05,
+      "loss": 2.0991,
+      "step": 5200
+    },
+    {
+      "epoch": 3.7,
+      "learning_rate": 3.4354045596781406e-05,
+      "loss": 2.0702,
+      "step": 5300
+    },
+    {
+      "epoch": 3.77,
+      "learning_rate": 3.379526151095217e-05,
+      "loss": 1.9914,
+      "step": 5400
+    },
+    {
+      "epoch": 3.84,
+      "learning_rate": 3.323647742512294e-05,
+      "loss": 1.9235,
+      "step": 5500
+    },
+    {
+      "epoch": 3.91,
+      "learning_rate": 3.26776933392937e-05,
+      "loss": 1.8922,
+      "step": 5600
+    },
+    {
+      "epoch": 3.98,
+      "learning_rate": 3.2118909253464465e-05,
+      "loss": 1.8512,
+      "step": 5700
+    },
+    {
+      "epoch": 4.05,
+      "learning_rate": 3.156012516763523e-05,
+      "loss": 1.6966,
+      "step": 5800
+    },
+    {
+      "epoch": 4.12,
+      "learning_rate": 3.100134108180599e-05,
+      "loss": 1.6399,
+      "step": 5900
+    },
+    {
+      "epoch": 4.19,
+      "learning_rate": 3.0442556995976757e-05,
+      "loss": 1.5982,
+      "step": 6000
+    },
+    {
+      "epoch": 4.19,
+      "eval_bleu": 56.0747,
+      "eval_em": 0.0017,
+      "eval_gen_len": 43.9021,
+      "eval_loss": 1.7495189905166626,
+      "eval_runtime": 423.2589,
+      "eval_samples_per_second": 2.847,
+      "eval_steps_per_second": 0.357,
+      "step": 6000
     }
   ],
   "max_steps": 11448,
   "num_train_epochs": 8,
-  "total_flos": 2632028349156096.0,
+  "total_flos": 3958404255138432.0,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6ccb2c6910f34be7a138f85235698d8f0ec58283fab1416ef6a153c170b333ed
+oid sha256:938f724c0f91c737457d75986a81bb14510b0f67d394e6715914ee6427257f11
 size 1002469625

runs/Jun05_10-45-59_0a95bf9de5ac/events.out.tfevents.1685962630.0a95bf9de5ac.3272.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bbc2bf10f2e8697285e6c7d205571262251279a84d779b5e1565cd93e4f856da
-size 15654
+oid sha256:7a959ff46eca4f3545c8c05e80af7a2fe5e478b7b3102f1f41ccc3cfcf54b040
+size 19210