Training in progress, step 300000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f66cb466fc715e72c4ec81e60ba44dcf7a28e75138eb49dc636ee2010b29cf2d
+oid sha256:ff044e80c574241efa7089a5ec2f633f003713c3c6f5dd2b7df44302f14645b7
 size 202194449

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c5cd5f151c22a36aa02e644aa26cc06f8e87218fd6115b2ca7b3a1e141911eae
+oid sha256:9c5e4cc7c8890a029475b21a89ba73ee51bdbf0169ee989a07985e899b417451
 size 102501541

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:47154c3a981c14b1d0cedd6ba126beed80c62fc2e1c96712050a23feb40f3503
+oid sha256:58bee1da196beb31121585eda29e2f73fb8583fc7e72eb4a3d5453bf8facf2f9
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:47154c3a981c14b1d0cedd6ba126beed80c62fc2e1c96712050a23feb40f3503
+oid sha256:58bee1da196beb31121585eda29e2f73fb8583fc7e72eb4a3d5453bf8facf2f9
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:47154c3a981c14b1d0cedd6ba126beed80c62fc2e1c96712050a23feb40f3503
+oid sha256:58bee1da196beb31121585eda29e2f73fb8583fc7e72eb4a3d5453bf8facf2f9
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:47154c3a981c14b1d0cedd6ba126beed80c62fc2e1c96712050a23feb40f3503
+oid sha256:58bee1da196beb31121585eda29e2f73fb8583fc7e72eb4a3d5453bf8facf2f9
 size 14503

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:47154c3a981c14b1d0cedd6ba126beed80c62fc2e1c96712050a23feb40f3503
+oid sha256:58bee1da196beb31121585eda29e2f73fb8583fc7e72eb4a3d5453bf8facf2f9
 size 14503

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:47154c3a981c14b1d0cedd6ba126beed80c62fc2e1c96712050a23feb40f3503
+oid sha256:58bee1da196beb31121585eda29e2f73fb8583fc7e72eb4a3d5453bf8facf2f9
 size 14503

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:47154c3a981c14b1d0cedd6ba126beed80c62fc2e1c96712050a23feb40f3503
+oid sha256:58bee1da196beb31121585eda29e2f73fb8583fc7e72eb4a3d5453bf8facf2f9
 size 14503

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:47154c3a981c14b1d0cedd6ba126beed80c62fc2e1c96712050a23feb40f3503
+oid sha256:58bee1da196beb31121585eda29e2f73fb8583fc7e72eb4a3d5453bf8facf2f9
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:39bc196d8aea9810b9698ff8cd04e2aeef8774f706fbd61ae0f0055bbacd0eaf
+oid sha256:7914b9f1e3709b1198ec189eb9bb9105cd6b88dedbcbbdd4128934a703cf33e3
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 7.390794637851062,
-  "global_step": 290000,
+  "epoch": 7.645649625363168,
+  "global_step": 300000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -5806,11 +5806,211 @@
       "eval_samples_per_second": 769.098,
       "eval_steps_per_second": 12.306,
       "step": 290000
+    },
+    {
+      "epoch": 7.4,
+      "learning_rate": 0.00012830086996475274,
+      "loss": 0.2829,
+      "step": 290500
+    },
+    {
+      "epoch": 7.42,
+      "learning_rate": 0.00012782970938506988,
+      "loss": 0.2829,
+      "step": 291000
+    },
+    {
+      "epoch": 7.42,
+      "eval_loss": 0.8085091710090637,
+      "eval_runtime": 1.2838,
+      "eval_samples_per_second": 778.958,
+      "eval_steps_per_second": 12.463,
+      "step": 291000
+    },
+    {
+      "epoch": 7.43,
+      "learning_rate": 0.00012735884593533222,
+      "loss": 0.2828,
+      "step": 291500
+    },
+    {
+      "epoch": 7.44,
+      "learning_rate": 0.0001268882847648268,
+      "loss": 0.2827,
+      "step": 292000
+    },
+    {
+      "epoch": 7.44,
+      "eval_loss": 0.8085604310035706,
+      "eval_runtime": 1.2676,
+      "eval_samples_per_second": 788.867,
+      "eval_steps_per_second": 12.622,
+      "step": 292000
+    },
+    {
+      "epoch": 7.45,
+      "learning_rate": 0.00012641803101953535,
+      "loss": 0.2829,
+      "step": 292500
+    },
+    {
+      "epoch": 7.47,
+      "learning_rate": 0.00012594808984207743,
+      "loss": 0.2829,
+      "step": 293000
+    },
+    {
+      "epoch": 7.47,
+      "eval_loss": 0.8101683855056763,
+      "eval_runtime": 1.2565,
+      "eval_samples_per_second": 795.849,
+      "eval_steps_per_second": 12.734,
+      "step": 293000
+    },
+    {
+      "epoch": 7.48,
+      "learning_rate": 0.00012547846637165445,
+      "loss": 0.2826,
+      "step": 293500
+    },
+    {
+      "epoch": 7.49,
+      "learning_rate": 0.00012500916574399346,
+      "loss": 0.2829,
+      "step": 294000
+    },
+    {
+      "epoch": 7.49,
+      "eval_loss": 0.808244526386261,
+      "eval_runtime": 1.3275,
+      "eval_samples_per_second": 753.27,
+      "eval_steps_per_second": 12.052,
+      "step": 294000
+    },
+    {
+      "epoch": 7.51,
+      "learning_rate": 0.00012454019309129095,
+      "loss": 0.2826,
+      "step": 294500
+    },
+    {
+      "epoch": 7.52,
+      "learning_rate": 0.0001240715535421567,
+      "loss": 0.2828,
+      "step": 295000
+    },
+    {
+      "epoch": 7.52,
+      "eval_loss": 0.809823751449585,
+      "eval_runtime": 1.297,
+      "eval_samples_per_second": 770.984,
+      "eval_steps_per_second": 12.336,
+      "step": 295000
+    },
+    {
+      "epoch": 7.53,
+      "learning_rate": 0.00012360325222155773,
+      "loss": 0.2825,
+      "step": 295500
+    },
+    {
+      "epoch": 7.54,
+      "learning_rate": 0.00012313529425076228,
+      "loss": 0.2828,
+      "step": 296000
+    },
+    {
+      "epoch": 7.54,
+      "eval_loss": 0.8033545017242432,
+      "eval_runtime": 1.3012,
+      "eval_samples_per_second": 768.545,
+      "eval_steps_per_second": 12.297,
+      "step": 296000
+    },
+    {
+      "epoch": 7.56,
+      "learning_rate": 0.00012266768474728372,
+      "loss": 0.283,
+      "step": 296500
+    },
+    {
+      "epoch": 7.57,
+      "learning_rate": 0.00012220042882482468,
+      "loss": 0.2831,
+      "step": 297000
+    },
+    {
+      "epoch": 7.57,
+      "eval_loss": 0.8072009086608887,
+      "eval_runtime": 1.2643,
+      "eval_samples_per_second": 790.967,
+      "eval_steps_per_second": 12.655,
+      "step": 297000
+    },
+    {
+      "epoch": 7.58,
+      "learning_rate": 0.00012173353159322102,
+      "loss": 0.2826,
+      "step": 297500
+    },
+    {
+      "epoch": 7.59,
+      "learning_rate": 0.00012126699815838609,
+      "loss": 0.2825,
+      "step": 298000
+    },
+    {
+      "epoch": 7.59,
+      "eval_loss": 0.8063223958015442,
+      "eval_runtime": 1.3228,
+      "eval_samples_per_second": 755.96,
+      "eval_steps_per_second": 12.095,
+      "step": 298000
+    },
+    {
+      "epoch": 7.61,
+      "learning_rate": 0.00012080083362225484,
+      "loss": 0.2819,
+      "step": 298500
+    },
+    {
+      "epoch": 7.62,
+      "learning_rate": 0.00012033504308272786,
+      "loss": 0.282,
+      "step": 299000
+    },
+    {
+      "epoch": 7.62,
+      "eval_loss": 0.812494158744812,
+      "eval_runtime": 1.3695,
+      "eval_samples_per_second": 730.168,
+      "eval_steps_per_second": 11.683,
+      "step": 299000
+    },
+    {
+      "epoch": 7.63,
+      "learning_rate": 0.00011986963163361598,
+      "loss": 0.2826,
+      "step": 299500
+    },
+    {
+      "epoch": 7.65,
+      "learning_rate": 0.0001194046043645841,
+      "loss": 0.2823,
+      "step": 300000
+    },
+    {
+      "epoch": 7.65,
+      "eval_loss": 0.815354585647583,
+      "eval_runtime": 1.3233,
+      "eval_samples_per_second": 755.698,
+      "eval_steps_per_second": 12.091,
+      "step": 300000
     }
   ],
   "max_steps": 500000,
   "num_train_epochs": 13,
-  "total_flos": 9.265032672069185e+21,
+  "total_flos": 9.584519810843685e+21,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c5cd5f151c22a36aa02e644aa26cc06f8e87218fd6115b2ca7b3a1e141911eae
+oid sha256:9c5e4cc7c8890a029475b21a89ba73ee51bdbf0169ee989a07985e899b417451
 size 102501541