Training in progress, step 110000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4c86fed892e5d853a0aa10f530918fd27c33343c4e8c930c0a02ed36b9c3f12
+oid sha256:49758088a73ffa86cfa7391b8520727f0e91c812a8d23680b3ffbf53509abe86
 size 202194449

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c1656fe19fa26589bb005c2ca1f054c8e8bb207866300c7f3b095bee470e6b55
+oid sha256:2d6b8966d1cc83e4388837c4e32ca9b57abfb21fb0d307bbaed74f29719988a7
 size 102501541

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed45958fcf12318fa043e135a1ac933625a86df5477ef36cf136e443a8e9059f
+oid sha256:3a623d5977f2ffdfbfa35a1493256efb0eabb662e5c36d8f15402dd8b77d8717
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed45958fcf12318fa043e135a1ac933625a86df5477ef36cf136e443a8e9059f
+oid sha256:3a623d5977f2ffdfbfa35a1493256efb0eabb662e5c36d8f15402dd8b77d8717
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed45958fcf12318fa043e135a1ac933625a86df5477ef36cf136e443a8e9059f
+oid sha256:3a623d5977f2ffdfbfa35a1493256efb0eabb662e5c36d8f15402dd8b77d8717
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed45958fcf12318fa043e135a1ac933625a86df5477ef36cf136e443a8e9059f
+oid sha256:3a623d5977f2ffdfbfa35a1493256efb0eabb662e5c36d8f15402dd8b77d8717
 size 14503

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed45958fcf12318fa043e135a1ac933625a86df5477ef36cf136e443a8e9059f
+oid sha256:3a623d5977f2ffdfbfa35a1493256efb0eabb662e5c36d8f15402dd8b77d8717
 size 14503

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed45958fcf12318fa043e135a1ac933625a86df5477ef36cf136e443a8e9059f
+oid sha256:3a623d5977f2ffdfbfa35a1493256efb0eabb662e5c36d8f15402dd8b77d8717
 size 14503

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed45958fcf12318fa043e135a1ac933625a86df5477ef36cf136e443a8e9059f
+oid sha256:3a623d5977f2ffdfbfa35a1493256efb0eabb662e5c36d8f15402dd8b77d8717
 size 14503

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed45958fcf12318fa043e135a1ac933625a86df5477ef36cf136e443a8e9059f
+oid sha256:3a623d5977f2ffdfbfa35a1493256efb0eabb662e5c36d8f15402dd8b77d8717
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7786e0d240c1817a80f936fe537093f6b0f81238abcccea2c0e618f1ac9e9438
+oid sha256:a36392859753540b5ff28a6690e0fb35c1157de322529d1ae210898db91ddda7
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.548549875121056,
-  "global_step": 100000,
+  "epoch": 2.803404862633162,
+  "global_step": 110000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2006,11 +2006,211 @@
       "eval_samples_per_second": 800.914,
       "eval_steps_per_second": 12.815,
       "step": 100000
+    },
+    {
+      "epoch": 2.56,
+      "learning_rate": 0.0002822947773032956,
+      "loss": 0.3117,
+      "step": 100500
+    },
+    {
+      "epoch": 2.57,
+      "learning_rate": 0.0002820644686063602,
+      "loss": 0.3112,
+      "step": 101000
+    },
+    {
+      "epoch": 2.57,
+      "eval_loss": 0.8347204327583313,
+      "eval_runtime": 1.2512,
+      "eval_samples_per_second": 799.226,
+      "eval_steps_per_second": 12.788,
+      "step": 101000
+    },
+    {
+      "epoch": 2.59,
+      "learning_rate": 0.00028183277035275363,
+      "loss": 0.3117,
+      "step": 101500
+    },
+    {
+      "epoch": 2.6,
+      "learning_rate": 0.0002815996850762909,
+      "loss": 0.3112,
+      "step": 102000
+    },
+    {
+      "epoch": 2.6,
+      "eval_loss": 0.8288648724555969,
+      "eval_runtime": 1.2077,
+      "eval_samples_per_second": 828.045,
+      "eval_steps_per_second": 13.249,
+      "step": 102000
+    },
+    {
+      "epoch": 2.61,
+      "learning_rate": 0.00028136521532595515,
+      "loss": 0.311,
+      "step": 102500
+    },
+    {
+      "epoch": 2.63,
+      "learning_rate": 0.00028112936366587023,
+      "loss": 0.3112,
+      "step": 103000
+    },
+    {
+      "epoch": 2.63,
+      "eval_loss": 0.8455829620361328,
+      "eval_runtime": 1.2774,
+      "eval_samples_per_second": 782.835,
+      "eval_steps_per_second": 12.525,
+      "step": 103000
+    },
+    {
+      "epoch": 2.64,
+      "learning_rate": 0.00028089213267527184,
+      "loss": 0.311,
+      "step": 103500
+    },
+    {
+      "epoch": 2.65,
+      "learning_rate": 0.0002806535249484803,
+      "loss": 0.3107,
+      "step": 104000
+    },
+    {
+      "epoch": 2.65,
+      "eval_loss": 0.8414435982704163,
+      "eval_runtime": 1.2285,
+      "eval_samples_per_second": 813.99,
+      "eval_steps_per_second": 13.024,
+      "step": 104000
+    },
+    {
+      "epoch": 2.66,
+      "learning_rate": 0.00028041354309487135,
+      "loss": 0.3108,
+      "step": 104500
+    },
+    {
+      "epoch": 2.68,
+      "learning_rate": 0.0002801721897388482,
+      "loss": 0.3101,
+      "step": 105000
+    },
+    {
+      "epoch": 2.68,
+      "eval_loss": 0.8326617479324341,
+      "eval_runtime": 1.214,
+      "eval_samples_per_second": 823.726,
+      "eval_steps_per_second": 13.18,
+      "step": 105000
+    },
+    {
+      "epoch": 2.69,
+      "learning_rate": 0.0002799294675198124,
+      "loss": 0.3102,
+      "step": 105500
+    },
+    {
+      "epoch": 2.7,
+      "learning_rate": 0.00027968537909213524,
+      "loss": 0.3107,
+      "step": 106000
+    },
+    {
+      "epoch": 2.7,
+      "eval_loss": 0.837422251701355,
+      "eval_runtime": 1.2383,
+      "eval_samples_per_second": 807.572,
+      "eval_steps_per_second": 12.921,
+      "step": 106000
+    },
+    {
+      "epoch": 2.71,
+      "learning_rate": 0.0002794399271251287,
+      "loss": 0.3102,
+      "step": 106500
+    },
+    {
+      "epoch": 2.73,
+      "learning_rate": 0.0002791931143030162,
+      "loss": 0.3103,
+      "step": 107000
+    },
+    {
+      "epoch": 2.73,
+      "eval_loss": 0.8471120595932007,
+      "eval_runtime": 1.2736,
+      "eval_samples_per_second": 785.146,
+      "eval_steps_per_second": 12.562,
+      "step": 107000
+    },
+    {
+      "epoch": 2.74,
+      "learning_rate": 0.00027894494332490315,
+      "loss": 0.3104,
+      "step": 107500
+    },
+    {
+      "epoch": 2.75,
+      "learning_rate": 0.0002786954169047476,
+      "loss": 0.3095,
+      "step": 108000
+    },
+    {
+      "epoch": 2.75,
+      "eval_loss": 0.845231831073761,
+      "eval_runtime": 1.222,
+      "eval_samples_per_second": 818.338,
+      "eval_steps_per_second": 13.093,
+      "step": 108000
+    },
+    {
+      "epoch": 2.77,
+      "learning_rate": 0.0002784445377713306,
+      "loss": 0.3093,
+      "step": 108500
+    },
+    {
+      "epoch": 2.78,
+      "learning_rate": 0.0002781923086682261,
+      "loss": 0.3094,
+      "step": 109000
+    },
+    {
+      "epoch": 2.78,
+      "eval_loss": 0.8512564301490784,
+      "eval_runtime": 1.2211,
+      "eval_samples_per_second": 818.908,
+      "eval_steps_per_second": 13.103,
+      "step": 109000
+    },
+    {
+      "epoch": 2.79,
+      "learning_rate": 0.0002779387323537711,
+      "loss": 0.3091,
+      "step": 109500
+    },
+    {
+      "epoch": 2.8,
+      "learning_rate": 0.0002776838116010356,
+      "loss": 0.3094,
+      "step": 110000
+    },
+    {
+      "epoch": 2.8,
+      "eval_loss": 0.8348438739776611,
+      "eval_runtime": 1.2126,
+      "eval_samples_per_second": 824.682,
+      "eval_steps_per_second": 13.195,
+      "step": 110000
     }
   ],
   "max_steps": 500000,
   "num_train_epochs": 13,
-  "total_flos": 3.19484442991891e+21,
+  "total_flos": 3.51433156869341e+21,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c1656fe19fa26589bb005c2ca1f054c8e8bb207866300c7f3b095bee470e6b55
+oid sha256:2d6b8966d1cc83e4388837c4e32ca9b57abfb21fb0d307bbaed74f29719988a7
 size 102501541