Training in progress, step 30000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ff30f34c03f4aee5e5fd09a1aacd3d7bdd3d177d4232672590b18570ebd00ab
+oid sha256:975602068258161ce5fc091ff74eec76aab489dd430d067c924b2aa7c926da4c
 size 50044241

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ee26862b665697be023c901e312db258d269e332dc1eb7fb87e516e00bf064a6
+oid sha256:ae108dd354088d366218061ee189c243227cfbb67d13fe15c56f1156f5bc73b8
 size 25761253

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:81b2c87ce00f88a26045daeef95098b32592be610ef6295c77558bd47e7dfa25
+oid sha256:c18320fd9d8608fdc95bdf80f9815c530f3042b21d4c3da3a6f04b03d2c98ab7
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:81b2c87ce00f88a26045daeef95098b32592be610ef6295c77558bd47e7dfa25
+oid sha256:c18320fd9d8608fdc95bdf80f9815c530f3042b21d4c3da3a6f04b03d2c98ab7
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:81b2c87ce00f88a26045daeef95098b32592be610ef6295c77558bd47e7dfa25
+oid sha256:c18320fd9d8608fdc95bdf80f9815c530f3042b21d4c3da3a6f04b03d2c98ab7
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:81b2c87ce00f88a26045daeef95098b32592be610ef6295c77558bd47e7dfa25
+oid sha256:c18320fd9d8608fdc95bdf80f9815c530f3042b21d4c3da3a6f04b03d2c98ab7
 size 14503

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:81b2c87ce00f88a26045daeef95098b32592be610ef6295c77558bd47e7dfa25
+oid sha256:c18320fd9d8608fdc95bdf80f9815c530f3042b21d4c3da3a6f04b03d2c98ab7
 size 14503

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:81b2c87ce00f88a26045daeef95098b32592be610ef6295c77558bd47e7dfa25
+oid sha256:c18320fd9d8608fdc95bdf80f9815c530f3042b21d4c3da3a6f04b03d2c98ab7
 size 14503

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:81b2c87ce00f88a26045daeef95098b32592be610ef6295c77558bd47e7dfa25
+oid sha256:c18320fd9d8608fdc95bdf80f9815c530f3042b21d4c3da3a6f04b03d2c98ab7
 size 14503

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:81b2c87ce00f88a26045daeef95098b32592be610ef6295c77558bd47e7dfa25
+oid sha256:c18320fd9d8608fdc95bdf80f9815c530f3042b21d4c3da3a6f04b03d2c98ab7
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2fa6f3c4ec253d8129a7481e01148ec46428b7a6eb1631c7fb589fd92c25c12f
+oid sha256:285c70cc0b99f831fd558ed5749dae6f2d660f449e704cb70ab7d67faaef2748
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.2254901960784315,
-  "global_step": 20000,
+  "epoch": 1.8382352941176472,
+  "global_step": 30000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -406,11 +406,211 @@
       "eval_samples_per_second": 780.312,
       "eval_steps_per_second": 12.485,
       "step": 20000
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 0.000598349790079647,
+      "loss": 0.737,
+      "step": 20500
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 0.000598137291838376,
+      "loss": 0.7365,
+      "step": 21000
+    },
+    {
+      "epoch": 1.29,
+      "eval_loss": 0.8698467016220093,
+      "eval_runtime": 1.2584,
+      "eval_samples_per_second": 794.654,
+      "eval_steps_per_second": 12.714,
+      "step": 21000
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 0.000597911970822327,
+      "loss": 0.7364,
+      "step": 21500
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 0.000597673836887771,
+      "loss": 0.7363,
+      "step": 22000
+    },
+    {
+      "epoch": 1.35,
+      "eval_loss": 0.870046079158783,
+      "eval_runtime": 1.2567,
+      "eval_samples_per_second": 795.734,
+      "eval_steps_per_second": 12.732,
+      "step": 22000
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 0.0005974229004514577,
+      "loss": 0.7363,
+      "step": 22500
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 0.0005971591724901598,
+      "loss": 0.7366,
+      "step": 23000
+    },
+    {
+      "epoch": 1.41,
+      "eval_loss": 0.9021453857421875,
+      "eval_runtime": 1.277,
+      "eval_samples_per_second": 783.107,
+      "eval_steps_per_second": 12.53,
+      "step": 23000
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 0.0005968826645401927,
+      "loss": 0.7368,
+      "step": 23500
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 0.00059659338869691,
+      "loss": 0.7362,
+      "step": 24000
+    },
+    {
+      "epoch": 1.47,
+      "eval_loss": 0.8762597441673279,
+      "eval_runtime": 1.2918,
+      "eval_samples_per_second": 774.091,
+      "eval_steps_per_second": 12.385,
+      "step": 24000
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 0.0005962913576141742,
+      "loss": 0.7354,
+      "step": 24500
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 0.000595976584503803,
+      "loss": 0.7082,
+      "step": 25000
+    },
+    {
+      "epoch": 1.53,
+      "eval_loss": 0.8719052672386169,
+      "eval_runtime": 1.2648,
+      "eval_samples_per_second": 790.61,
+      "eval_steps_per_second": 12.65,
+      "step": 25000
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 0.0005956490831349923,
+      "loss": 0.6914,
+      "step": 25500
+    },
+    {
+      "epoch": 1.59,
+      "learning_rate": 0.0005953088678337129,
+      "loss": 0.6774,
+      "step": 26000
+    },
+    {
+      "epoch": 1.59,
+      "eval_loss": 0.8876385688781738,
+      "eval_runtime": 1.3046,
+      "eval_samples_per_second": 766.511,
+      "eval_steps_per_second": 12.264,
+      "step": 26000
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 0.0005949559534820841,
+      "loss": 0.6675,
+      "step": 26500
+    },
+    {
+      "epoch": 1.65,
+      "learning_rate": 0.0005945903555177229,
+      "loss": 0.6525,
+      "step": 27000
+    },
+    {
+      "epoch": 1.65,
+      "eval_loss": 0.8904880285263062,
+      "eval_runtime": 1.319,
+      "eval_samples_per_second": 758.176,
+      "eval_steps_per_second": 12.131,
+      "step": 27000
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 0.0005942120899330687,
+      "loss": 0.6186,
+      "step": 27500
+    },
+    {
+      "epoch": 1.72,
+      "learning_rate": 0.0005938211732746836,
+      "loss": 0.6022,
+      "step": 28000
+    },
+    {
+      "epoch": 1.72,
+      "eval_loss": 0.8856265544891357,
+      "eval_runtime": 1.2877,
+      "eval_samples_per_second": 776.587,
+      "eval_steps_per_second": 12.425,
+      "step": 28000
+    },
+    {
+      "epoch": 1.75,
+      "learning_rate": 0.0005934176226425286,
+      "loss": 0.593,
+      "step": 28500
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 0.0005930014556892158,
+      "loss": 0.5874,
+      "step": 29000
+    },
+    {
+      "epoch": 1.78,
+      "eval_loss": 0.8793675303459167,
+      "eval_runtime": 1.2489,
+      "eval_samples_per_second": 800.707,
+      "eval_steps_per_second": 12.811,
+      "step": 29000
+    },
+    {
+      "epoch": 1.81,
+      "learning_rate": 0.0005925726906192357,
+      "loss": 0.5837,
+      "step": 29500
+    },
+    {
+      "epoch": 1.84,
+      "learning_rate": 0.0005921313461881617,
+      "loss": 0.5765,
+      "step": 30000
+    },
+    {
+      "epoch": 1.84,
+      "eval_loss": 0.8805580735206604,
+      "eval_runtime": 1.2758,
+      "eval_samples_per_second": 783.816,
+      "eval_steps_per_second": 12.541,
+      "step": 30000
     }
   ],
   "max_steps": 250000,
   "num_train_epochs": 16,
-  "total_flos": 3.203259952279931e+20,
+  "total_flos": 4.8049399809379716e+20,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ee26862b665697be023c901e312db258d269e332dc1eb7fb87e516e00bf064a6
+oid sha256:ae108dd354088d366218061ee189c243227cfbb67d13fe15c56f1156f5bc73b8
 size 25761253