Training in progress, step 220000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:20fdb368922f36248fd6b214b7b78335fe829358b5b671adc377a7586ad5707d
+oid sha256:0a4927510127367e9500a6855c39ccf67e69ae9696103dd6206ca76c8228c9e7
 size 202194449

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb8ed6173253524a7574f7166f4857b303d1b69af9c36814e1d9440f006d9566
+oid sha256:fb407692499c91ceb95468636179875a29017b0607fee237df69b7c6f035183b
 size 102501541

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4bf717114abf74d765a1dd76652ea701e4d472d694acc3289369476dcf9946f2
+oid sha256:6a2409314cc97cd170cf372a0918ec1a71b59dc692c1f5814e6639647692d18c
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4bf717114abf74d765a1dd76652ea701e4d472d694acc3289369476dcf9946f2
+oid sha256:6a2409314cc97cd170cf372a0918ec1a71b59dc692c1f5814e6639647692d18c
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4bf717114abf74d765a1dd76652ea701e4d472d694acc3289369476dcf9946f2
+oid sha256:6a2409314cc97cd170cf372a0918ec1a71b59dc692c1f5814e6639647692d18c
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4bf717114abf74d765a1dd76652ea701e4d472d694acc3289369476dcf9946f2
+oid sha256:6a2409314cc97cd170cf372a0918ec1a71b59dc692c1f5814e6639647692d18c
 size 14503

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4bf717114abf74d765a1dd76652ea701e4d472d694acc3289369476dcf9946f2
+oid sha256:6a2409314cc97cd170cf372a0918ec1a71b59dc692c1f5814e6639647692d18c
 size 14503

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4bf717114abf74d765a1dd76652ea701e4d472d694acc3289369476dcf9946f2
+oid sha256:6a2409314cc97cd170cf372a0918ec1a71b59dc692c1f5814e6639647692d18c
 size 14503

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4bf717114abf74d765a1dd76652ea701e4d472d694acc3289369476dcf9946f2
+oid sha256:6a2409314cc97cd170cf372a0918ec1a71b59dc692c1f5814e6639647692d18c
 size 14503

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4bf717114abf74d765a1dd76652ea701e4d472d694acc3289369476dcf9946f2
+oid sha256:6a2409314cc97cd170cf372a0918ec1a71b59dc692c1f5814e6639647692d18c
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de6aa60c12b8dbcda06c27a65ac30e45d66753f2960bee09a7c0ea364ae7e103
+oid sha256:a05d01a7b2f868e6f0e645a01ef2a1ba3ad5ea16b1bff8e9cf0cf653b106d64f
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 4.892937859689182,
-  "global_step": 210000,
+  "epoch": 5.125934900626762,
+  "global_step": 220000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -4206,11 +4206,211 @@
       "eval_samples_per_second": 1564.263,
       "eval_steps_per_second": 24.909,
       "step": 210000
+    },
+    {
+      "epoch": 4.9,
+      "learning_rate": 0.00020389135229309803,
+      "loss": 0.2781,
+      "step": 210500
+    },
+    {
+      "epoch": 4.92,
+      "learning_rate": 0.00020343965962416229,
+      "loss": 0.2783,
+      "step": 211000
+    },
+    {
+      "epoch": 4.92,
+      "eval_loss": 0.26213955879211426,
+      "eval_runtime": 1.4602,
+      "eval_samples_per_second": 1505.253,
+      "eval_steps_per_second": 23.969,
+      "step": 211000
+    },
+    {
+      "epoch": 4.93,
+      "learning_rate": 0.00020298743722686958,
+      "loss": 0.2778,
+      "step": 211500
+    },
+    {
+      "epoch": 4.94,
+      "learning_rate": 0.0002025346900466516,
+      "loss": 0.2781,
+      "step": 212000
+    },
+    {
+      "epoch": 4.94,
+      "eval_loss": 0.2614113390445709,
+      "eval_runtime": 1.4246,
+      "eval_samples_per_second": 1542.853,
+      "eval_steps_per_second": 24.568,
+      "step": 212000
+    },
+    {
+      "epoch": 4.95,
+      "learning_rate": 0.0002020814230346791,
+      "loss": 0.2778,
+      "step": 212500
+    },
+    {
+      "epoch": 4.96,
+      "learning_rate": 0.00020162764114780733,
+      "loss": 0.2779,
+      "step": 213000
+    },
+    {
+      "epoch": 4.96,
+      "eval_loss": 0.2597576975822449,
+      "eval_runtime": 1.4338,
+      "eval_samples_per_second": 1532.976,
+      "eval_steps_per_second": 24.41,
+      "step": 213000
+    },
+    {
+      "epoch": 4.97,
+      "learning_rate": 0.0002011733493485224,
+      "loss": 0.2778,
+      "step": 213500
+    },
+    {
+      "epoch": 4.99,
+      "learning_rate": 0.00020071855260488664,
+      "loss": 0.2776,
+      "step": 214000
+    },
+    {
+      "epoch": 4.99,
+      "eval_loss": 0.2594500780105591,
+      "eval_runtime": 1.4614,
+      "eval_samples_per_second": 1504.034,
+      "eval_steps_per_second": 23.95,
+      "step": 214000
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 0.0002002632558904843,
+      "loss": 0.2777,
+      "step": 214500
+    },
+    {
+      "epoch": 5.01,
+      "learning_rate": 0.00019980746418436736,
+      "loss": 0.2774,
+      "step": 215000
+    },
+    {
+      "epoch": 5.01,
+      "eval_loss": 0.2608456611633301,
+      "eval_runtime": 1.4098,
+      "eval_samples_per_second": 1559.139,
+      "eval_steps_per_second": 24.827,
+      "step": 215000
+    },
+    {
+      "epoch": 5.02,
+      "learning_rate": 0.00019935118247100088,
+      "loss": 0.2777,
+      "step": 215500
+    },
+    {
+      "epoch": 5.03,
+      "learning_rate": 0.00019889441574020864,
+      "loss": 0.2782,
+      "step": 216000
+    },
+    {
+      "epoch": 5.03,
+      "eval_loss": 0.26146388053894043,
+      "eval_runtime": 1.4335,
+      "eval_samples_per_second": 1533.337,
+      "eval_steps_per_second": 24.416,
+      "step": 216000
+    },
+    {
+      "epoch": 5.04,
+      "learning_rate": 0.0001984371689871183,
+      "loss": 0.2775,
+      "step": 216500
+    },
+    {
+      "epoch": 5.06,
+      "learning_rate": 0.00019797944721210725,
+      "loss": 0.2779,
+      "step": 217000
+    },
+    {
+      "epoch": 5.06,
+      "eval_loss": 0.26257631182670593,
+      "eval_runtime": 1.4244,
+      "eval_samples_per_second": 1543.156,
+      "eval_steps_per_second": 24.573,
+      "step": 217000
+    },
+    {
+      "epoch": 5.07,
+      "learning_rate": 0.00019752125542074736,
+      "loss": 0.2785,
+      "step": 217500
+    },
+    {
+      "epoch": 5.08,
+      "learning_rate": 0.00019706259862375074,
+      "loss": 0.2768,
+      "step": 218000
+    },
+    {
+      "epoch": 5.08,
+      "eval_loss": 0.25935330986976624,
+      "eval_runtime": 1.4288,
+      "eval_samples_per_second": 1538.396,
+      "eval_steps_per_second": 24.497,
+      "step": 218000
+    },
+    {
+      "epoch": 5.09,
+      "learning_rate": 0.00019660348183691453,
+      "loss": 0.277,
+      "step": 218500
+    },
+    {
+      "epoch": 5.1,
+      "learning_rate": 0.0001961439100810664,
+      "loss": 0.2774,
+      "step": 219000
+    },
+    {
+      "epoch": 5.1,
+      "eval_loss": 0.2606256604194641,
+      "eval_runtime": 1.4284,
+      "eval_samples_per_second": 1538.738,
+      "eval_steps_per_second": 24.502,
+      "step": 219000
+    },
+    {
+      "epoch": 5.11,
+      "learning_rate": 0.00019568388838200952,
+      "loss": 0.277,
+      "step": 219500
+    },
+    {
+      "epoch": 5.13,
+      "learning_rate": 0.00019522342177046744,
+      "loss": 0.2767,
+      "step": 220000
+    },
+    {
+      "epoch": 5.13,
+      "eval_loss": 0.2605719566345215,
+      "eval_runtime": 1.4163,
+      "eval_samples_per_second": 1551.973,
+      "eval_steps_per_second": 24.713,
+      "step": 220000
     }
   ],
   "max_steps": 500000,
   "num_train_epochs": 12,
-  "total_flos": 6.709219926300873e+21,
+  "total_flos": 7.028704568084466e+21,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb8ed6173253524a7574f7166f4857b303d1b69af9c36814e1d9440f006d9566
+oid sha256:fb407692499c91ceb95468636179875a29017b0607fee237df69b7c6f035183b
 size 102501541