Training in progress, step 90000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:991fa5d4e5f5edee4c8ef0d2412d108fe8823401ec1d29bf753ff58c6250ef3e
+oid sha256:6b0288be0c1235e777c27dd9047a36eedfe264bb488a4c0e0bed0c34a7672a27
 size 893439185

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:11bb76b4f4b7c201591694a6bcc8c84f8d309b1f1cea21af022f918961a63b4e
+oid sha256:d7eecde17cb6e9aa8cd7b4552f91801dbea59bd9f43564420f17d5094be8ecd0
 size 449471589

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:194884037966e731fcb91766eca35472e355bcdf78ecca2ffbee8cb9b09126dd
+oid sha256:a05d03c073f727785714559ddd963d68941172e2660ea09c2fa916687be15d30
 size 15587

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ec9980e0e4d49a11c107c88863e01c8ed67819546b646e61e0a1dcaaf5d9232
+oid sha256:2a253357a0f0cc613ebf9506b97610f90339ebe2be5f931702becbaf171e782d
 size 559

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5312022d6e3da19908b0afff153bcac2a5b0f2f58c4dfc36e2fe367687099b95
+oid sha256:8c584c5bb4a0182ed3950a23caf01b869cbb053591dee4ffba4c62961e6b03ec
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 7.400313425039178,
-  "global_step": 85000,
+  "epoch": 7.835625979453248,
+  "global_step": 90000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1162,11 +1162,79 @@
       "eval_samples_per_second": 281.388,
       "eval_steps_per_second": 4.446,
       "step": 85000
+    },
+    {
+      "epoch": 7.44,
+      "learning_rate": 1.4648687806501003e-05,
+      "loss": 0.4022,
+      "step": 85500
+    },
+    {
+      "epoch": 7.49,
+      "learning_rate": 1.433940932686429e-05,
+      "loss": 0.4029,
+      "step": 86000
+    },
+    {
+      "epoch": 7.53,
+      "learning_rate": 1.4040847761852026e-05,
+      "loss": 0.403,
+      "step": 86500
+    },
+    {
+      "epoch": 7.57,
+      "learning_rate": 1.3752447867532768e-05,
+      "loss": 0.403,
+      "step": 87000
+    },
+    {
+      "epoch": 7.62,
+      "learning_rate": 1.3473733388145289e-05,
+      "loss": 0.4027,
+      "step": 87500
+    },
+    {
+      "epoch": 7.66,
+      "learning_rate": 1.3205361274547104e-05,
+      "loss": 0.4016,
+      "step": 88000
+    },
+    {
+      "epoch": 7.71,
+      "learning_rate": 1.2947397743541538e-05,
+      "loss": 0.4024,
+      "step": 88500
+    },
+    {
+      "epoch": 7.75,
+      "learning_rate": 1.2699906443769858e-05,
+      "loss": 0.4025,
+      "step": 89000
+    },
+    {
+      "epoch": 7.79,
+      "learning_rate": 1.2462948440006997e-05,
+      "loss": 0.4016,
+      "step": 89500
+    },
+    {
+      "epoch": 7.84,
+      "learning_rate": 1.2236582198094697e-05,
+      "loss": 0.403,
+      "step": 90000
+    },
+    {
+      "epoch": 7.84,
+      "eval_loss": 0.38297703862190247,
+      "eval_runtime": 16.5367,
+      "eval_samples_per_second": 302.358,
+      "eval_steps_per_second": 4.777,
+      "step": 90000
     }
   ],
   "max_steps": 100000,
   "num_train_epochs": 9,
-  "total_flos": 4.0032518025264523e+21,
+  "total_flos": 4.238744869891214e+21,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:11bb76b4f4b7c201591694a6bcc8c84f8d309b1f1cea21af022f918961a63b4e
+oid sha256:d7eecde17cb6e9aa8cd7b4552f91801dbea59bd9f43564420f17d5094be8ecd0
 size 449471589