Training in progress, step 60000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6640249a1c6041c32dfd1464a658338887363ff5085678afe917eb168bf7a616
+oid sha256:41fea028c5bfc9404f2b619405e732a8bae394cb83febbe5f12b63d0e52dfeb6
 size 202193937

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b9279029389011e28791bcbea261efc23528afcc9ebee41b4e9cca6964cc5f3
+oid sha256:e47c3180802a5713b7e9f66986161446bd671e1f39c69b59568ccc20114bb8c6
 size 102501541

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4bfa0b7d5c3d248e8db4db63af9bfcb5ccbe3aa3f4c28b0b4e1a7ce6f0017bb0
+oid sha256:3ee15e556f62a5c90d23203bf0811cbf2698d3f926956572339a2d795b780843
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4bfa0b7d5c3d248e8db4db63af9bfcb5ccbe3aa3f4c28b0b4e1a7ce6f0017bb0
+oid sha256:3ee15e556f62a5c90d23203bf0811cbf2698d3f926956572339a2d795b780843
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4bfa0b7d5c3d248e8db4db63af9bfcb5ccbe3aa3f4c28b0b4e1a7ce6f0017bb0
+oid sha256:3ee15e556f62a5c90d23203bf0811cbf2698d3f926956572339a2d795b780843
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4bfa0b7d5c3d248e8db4db63af9bfcb5ccbe3aa3f4c28b0b4e1a7ce6f0017bb0
+oid sha256:3ee15e556f62a5c90d23203bf0811cbf2698d3f926956572339a2d795b780843
 size 14503

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4bfa0b7d5c3d248e8db4db63af9bfcb5ccbe3aa3f4c28b0b4e1a7ce6f0017bb0
+oid sha256:3ee15e556f62a5c90d23203bf0811cbf2698d3f926956572339a2d795b780843
 size 14503

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4bfa0b7d5c3d248e8db4db63af9bfcb5ccbe3aa3f4c28b0b4e1a7ce6f0017bb0
+oid sha256:3ee15e556f62a5c90d23203bf0811cbf2698d3f926956572339a2d795b780843
 size 14503

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4bfa0b7d5c3d248e8db4db63af9bfcb5ccbe3aa3f4c28b0b4e1a7ce6f0017bb0
+oid sha256:3ee15e556f62a5c90d23203bf0811cbf2698d3f926956572339a2d795b780843
 size 14503

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4bfa0b7d5c3d248e8db4db63af9bfcb5ccbe3aa3f4c28b0b4e1a7ce6f0017bb0
+oid sha256:3ee15e556f62a5c90d23203bf0811cbf2698d3f926956572339a2d795b780843
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ec5c60f6b831a1ad5ababd554115ca1132f641d196d63d42183ef95c8827963
+oid sha256:1afd4be721b18cec2bad25f6a60e1c3abb5c311277f62eb3e2f010bc31239df1
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.274274937560528,
-  "global_step": 50000,
+  "epoch": 1.5291299250726338,
+  "global_step": 60000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1006,11 +1006,211 @@
       "eval_samples_per_second": 762.871,
       "eval_steps_per_second": 12.206,
       "step": 50000
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 0.0002979426829679962,
+      "loss": 0.3403,
+      "step": 50500
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 0.0002978614137443183,
+      "loss": 0.3398,
+      "step": 51000
+    },
+    {
+      "epoch": 1.3,
+      "eval_loss": 0.8630042672157288,
+      "eval_runtime": 1.1917,
+      "eval_samples_per_second": 839.116,
+      "eval_steps_per_second": 13.426,
+      "step": 51000
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 0.000297778582211108,
+      "loss": 0.3391,
+      "step": 51500
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 0.00029769418927419786,
+      "loss": 0.3387,
+      "step": 52000
+    },
+    {
+      "epoch": 1.33,
+      "eval_loss": 0.8540878891944885,
+      "eval_runtime": 1.2825,
+      "eval_samples_per_second": 779.707,
+      "eval_steps_per_second": 12.475,
+      "step": 52000
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 0.0002976082358564954,
+      "loss": 0.338,
+      "step": 52500
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 0.00029752072289797353,
+      "loss": 0.3373,
+      "step": 53000
+    },
+    {
+      "epoch": 1.35,
+      "eval_loss": 0.8587937355041504,
+      "eval_runtime": 1.3038,
+      "eval_samples_per_second": 766.964,
+      "eval_steps_per_second": 12.271,
+      "step": 53000
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 0.00029743165135565986,
+      "loss": 0.3373,
+      "step": 53500
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 0.00029734102220362654,
+      "loss": 0.3368,
+      "step": 54000
+    },
+    {
+      "epoch": 1.38,
+      "eval_loss": 0.8638780117034912,
+      "eval_runtime": 1.2508,
+      "eval_samples_per_second": 799.458,
+      "eval_steps_per_second": 12.791,
+      "step": 54000
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 0.00029724883643297937,
+      "loss": 0.3362,
+      "step": 54500
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 0.0002971550950518473,
+      "loss": 0.3357,
+      "step": 55000
+    },
+    {
+      "epoch": 1.4,
+      "eval_loss": 0.8546432256698608,
+      "eval_runtime": 1.2572,
+      "eval_samples_per_second": 795.415,
+      "eval_steps_per_second": 12.727,
+      "step": 55000
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 0.000297059799085371,
+      "loss": 0.3351,
+      "step": 55500
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 0.00029696294957569196,
+      "loss": 0.335,
+      "step": 56000
+    },
+    {
+      "epoch": 1.43,
+      "eval_loss": 0.8535034656524658,
+      "eval_runtime": 1.2455,
+      "eval_samples_per_second": 802.916,
+      "eval_steps_per_second": 12.847,
+      "step": 56000
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 0.00029686454758194076,
+      "loss": 0.3343,
+      "step": 56500
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 0.00029676459418022594,
+      "loss": 0.334,
+      "step": 57000
+    },
+    {
+      "epoch": 1.45,
+      "eval_loss": 0.8510599136352539,
+      "eval_runtime": 1.2497,
+      "eval_samples_per_second": 800.205,
+      "eval_steps_per_second": 12.803,
+      "step": 57000
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 0.0002966630904636219,
+      "loss": 0.3335,
+      "step": 57500
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 0.0002965600375421569,
+      "loss": 0.333,
+      "step": 58000
+    },
+    {
+      "epoch": 1.48,
+      "eval_loss": 0.8525308966636658,
+      "eval_runtime": 1.285,
+      "eval_samples_per_second": 778.223,
+      "eval_steps_per_second": 12.452,
+      "step": 58000
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 0.0002964554365428013,
+      "loss": 0.3328,
+      "step": 58500
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 0.00029634928860945486,
+      "loss": 0.3322,
+      "step": 59000
+    },
+    {
+      "epoch": 1.5,
+      "eval_loss": 0.8536081910133362,
+      "eval_runtime": 1.2803,
+      "eval_samples_per_second": 781.08,
+      "eval_steps_per_second": 12.497,
+      "step": 59000
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 0.0002962415949029343,
+      "loss": 0.3319,
+      "step": 59500
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 0.00029613235660096084,
+      "loss": 0.3314,
+      "step": 60000
+    },
+    {
+      "epoch": 1.53,
+      "eval_loss": 0.8421887159347534,
+      "eval_runtime": 1.3286,
+      "eval_samples_per_second": 752.666,
+      "eval_steps_per_second": 12.043,
+      "step": 60000
     }
   ],
   "max_steps": 500000,
   "num_train_epochs": 13,
-  "total_flos": 1.597422214959455e+21,
+  "total_flos": 1.916909353733955e+21,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b9279029389011e28791bcbea261efc23528afcc9ebee41b4e9cca6964cc5f3
+oid sha256:e47c3180802a5713b7e9f66986161446bd671e1f39c69b59568ccc20114bb8c6
 size 102501541