Training in progress, step 630000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f902a0072d31f63b96927b6a6d51b56be111838845c62df2a4b9cbba3e56aec6
+oid sha256:96938a71bc030f81c34720e31da4589b283a118d187bec3979579fe96136d8f0
 size 893439185

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd5261e1974ad45164fe18686543155fd69b03009a425c734e5f5a744490a226
+oid sha256:3e304d0486914d81cfca45cc6ef280fc081501fbe41c19f0e4ff6141ab643b78
 size 449471589

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e37040ab33982f6d1312ce35ee66415b5fb51e1c104e02428f2187d6ddef02e5
+oid sha256:d33ce3108e385660090a22247b2e131088c6273bea93f4243061660df0632b29
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e37040ab33982f6d1312ce35ee66415b5fb51e1c104e02428f2187d6ddef02e5
+oid sha256:d33ce3108e385660090a22247b2e131088c6273bea93f4243061660df0632b29
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e37040ab33982f6d1312ce35ee66415b5fb51e1c104e02428f2187d6ddef02e5
+oid sha256:d33ce3108e385660090a22247b2e131088c6273bea93f4243061660df0632b29
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e37040ab33982f6d1312ce35ee66415b5fb51e1c104e02428f2187d6ddef02e5
+oid sha256:d33ce3108e385660090a22247b2e131088c6273bea93f4243061660df0632b29
 size 14503

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e37040ab33982f6d1312ce35ee66415b5fb51e1c104e02428f2187d6ddef02e5
+oid sha256:d33ce3108e385660090a22247b2e131088c6273bea93f4243061660df0632b29
 size 14503

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e37040ab33982f6d1312ce35ee66415b5fb51e1c104e02428f2187d6ddef02e5
+oid sha256:d33ce3108e385660090a22247b2e131088c6273bea93f4243061660df0632b29
 size 14503

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e37040ab33982f6d1312ce35ee66415b5fb51e1c104e02428f2187d6ddef02e5
+oid sha256:d33ce3108e385660090a22247b2e131088c6273bea93f4243061660df0632b29
 size 14503

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e37040ab33982f6d1312ce35ee66415b5fb51e1c104e02428f2187d6ddef02e5
+oid sha256:d33ce3108e385660090a22247b2e131088c6273bea93f4243061660df0632b29
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87df12c543e6333a1257623848db6de543e5639171e7cc03225528d064da559b
+oid sha256:445023bf71af0013aa9e5796238ea2c1da2dcfc1e0064784bf2e5fc75bdc80c6
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 6.557643621114618,
-  "global_step": 620000,
+  "epoch": 6.669172345337541,
+  "global_step": 630000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -12406,11 +12406,211 @@
       "eval_samples_per_second": 914.603,
       "eval_steps_per_second": 14.334,
       "step": 620000
+    },
+    {
+      "epoch": 6.56,
+      "learning_rate": 5.8258761986213015e-05,
+      "loss": 0.2004,
+      "step": 620500
+    },
+    {
+      "epoch": 6.57,
+      "learning_rate": 5.814877301838688e-05,
+      "loss": 0.2002,
+      "step": 621000
+    },
+    {
+      "epoch": 6.57,
+      "eval_loss": 0.19093768298625946,
+      "eval_runtime": 2.5116,
+      "eval_samples_per_second": 914.543,
+      "eval_steps_per_second": 14.333,
+      "step": 621000
+    },
+    {
+      "epoch": 6.57,
+      "learning_rate": 5.803884379098094e-05,
+      "loss": 0.2005,
+      "step": 621500
+    },
+    {
+      "epoch": 6.58,
+      "learning_rate": 5.7928974604537494e-05,
+      "loss": 0.2003,
+      "step": 622000
+    },
+    {
+      "epoch": 6.58,
+      "eval_loss": 0.19122566282749176,
+      "eval_runtime": 2.5785,
+      "eval_samples_per_second": 890.823,
+      "eval_steps_per_second": 13.962,
+      "step": 622000
+    },
+    {
+      "epoch": 6.59,
+      "learning_rate": 5.781916575943469e-05,
+      "loss": 0.2,
+      "step": 622500
+    },
+    {
+      "epoch": 6.59,
+      "learning_rate": 5.770941755588573e-05,
+      "loss": 0.2005,
+      "step": 623000
+    },
+    {
+      "epoch": 6.59,
+      "eval_loss": 0.19022968411445618,
+      "eval_runtime": 2.5145,
+      "eval_samples_per_second": 913.487,
+      "eval_steps_per_second": 14.317,
+      "step": 623000
+    },
+    {
+      "epoch": 6.6,
+      "learning_rate": 5.7599730293938e-05,
+      "loss": 0.2005,
+      "step": 623500
+    },
+    {
+      "epoch": 6.6,
+      "learning_rate": 5.749010427347233e-05,
+      "loss": 0.1998,
+      "step": 624000
+    },
+    {
+      "epoch": 6.6,
+      "eval_loss": 0.18952861428260803,
+      "eval_runtime": 2.6789,
+      "eval_samples_per_second": 857.447,
+      "eval_steps_per_second": 13.438,
+      "step": 624000
+    },
+    {
+      "epoch": 6.61,
+      "learning_rate": 5.738053979420199e-05,
+      "loss": 0.2004,
+      "step": 624500
+    },
+    {
+      "epoch": 6.61,
+      "learning_rate": 5.7271037155672156e-05,
+      "loss": 0.2,
+      "step": 625000
+    },
+    {
+      "epoch": 6.61,
+      "eval_loss": 0.18912938237190247,
+      "eval_runtime": 2.5074,
+      "eval_samples_per_second": 916.101,
+      "eval_steps_per_second": 14.358,
+      "step": 625000
+    },
+    {
+      "epoch": 6.62,
+      "learning_rate": 5.716159665725883e-05,
+      "loss": 0.1998,
+      "step": 625500
+    },
+    {
+      "epoch": 6.62,
+      "learning_rate": 5.7052218598168154e-05,
+      "loss": 0.1996,
+      "step": 626000
+    },
+    {
+      "epoch": 6.62,
+      "eval_loss": 0.19050002098083496,
+      "eval_runtime": 2.5363,
+      "eval_samples_per_second": 905.665,
+      "eval_steps_per_second": 14.194,
+      "step": 626000
+    },
+    {
+      "epoch": 6.63,
+      "learning_rate": 5.69429032774356e-05,
+      "loss": 0.1999,
+      "step": 626500
+    },
+    {
+      "epoch": 6.64,
+      "learning_rate": 5.6833650993925016e-05,
+      "loss": 0.1998,
+      "step": 627000
+    },
+    {
+      "epoch": 6.64,
+      "eval_loss": 0.19091765582561493,
+      "eval_runtime": 2.6002,
+      "eval_samples_per_second": 883.405,
+      "eval_steps_per_second": 13.845,
+      "step": 627000
+    },
+    {
+      "epoch": 6.64,
+      "learning_rate": 5.6724462046328025e-05,
+      "loss": 0.2,
+      "step": 627500
+    },
+    {
+      "epoch": 6.65,
+      "learning_rate": 5.661533673316303e-05,
+      "loss": 0.2,
+      "step": 628000
+    },
+    {
+      "epoch": 6.65,
+      "eval_loss": 0.19069619476795197,
+      "eval_runtime": 2.549,
+      "eval_samples_per_second": 901.121,
+      "eval_steps_per_second": 14.123,
+      "step": 628000
+    },
+    {
+      "epoch": 6.65,
+      "learning_rate": 5.6506275352774447e-05,
+      "loss": 0.1998,
+      "step": 628500
+    },
+    {
+      "epoch": 6.66,
+      "learning_rate": 5.639727820333198e-05,
+      "loss": 0.2001,
+      "step": 629000
+    },
+    {
+      "epoch": 6.66,
+      "eval_loss": 0.19251221418380737,
+      "eval_runtime": 2.5685,
+      "eval_samples_per_second": 894.303,
+      "eval_steps_per_second": 14.016,
+      "step": 629000
+    },
+    {
+      "epoch": 6.66,
+      "learning_rate": 5.62883455828296e-05,
+      "loss": 0.1996,
+      "step": 629500
+    },
+    {
+      "epoch": 6.67,
+      "learning_rate": 5.617947778908498e-05,
+      "loss": 0.2,
+      "step": 630000
+    },
+    {
+      "epoch": 6.67,
+      "eval_loss": 0.19011762738227844,
+      "eval_runtime": 2.6047,
+      "eval_samples_per_second": 881.86,
+      "eval_steps_per_second": 13.821,
+      "step": 630000
     }
   ],
   "max_steps": 1000000,
   "num_train_epochs": 12,
-  "total_flos": 4.346183325196429e+22,
+  "total_flos": 4.416283586226776e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd5261e1974ad45164fe18686543155fd69b03009a425c734e5f5a744490a226
+oid sha256:3e304d0486914d81cfca45cc6ef280fc081501fbe41c19f0e4ff6141ab643b78
 size 449471589