Training in progress, step 440000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c4a14a4b300dc1a5da67108d934f51ece4d032d74a5b22ddb6baf522fdb8c1c
+oid sha256:f92e6cd0767ca59f1527b5967666a322afaf575c9af8775949662404da371092
 size 893439185

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:29a338d7e31f1ebb55d71826f0de824d2a1d8633cac67c074239e146a6c6bf2d
+oid sha256:605e171de557600b4f9eab4567771d6f7b62053eb613a7b7ed22d56f357a201b
 size 449471589

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10c521743622eed6f2a8ce22651670cd6f7fb24994288ac8323ec1f5d533e8a1
-size 14439
+oid sha256:c4e4d0603158355ab30ed464162b9809f49d4b9fe387e337de95c9b6476ba9b3
+size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6dc65d4d1b61d6b6ec0b07de631a3fc7ef2baef1eecd8b2dd63afdc6d03ed25d
-size 14503
+oid sha256:926ff1f312d9731049e2cfd0827e2934c1dc272e72548666a5980946912e0647
+size 14439

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2003a4ffe1876cade3b569b7c4b3d4c928a46e1a7a6a797e8245fc18980679e5
-size 14503
+oid sha256:a69b501354d86430b18ce3c64120582562e9c52da9971d6a0efada8760b427f4
+size 14439

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d19681008a4b6b5d37d79f13ad91bb5cfd25c6887d3949264aeea07e7705212
-size 14567
+oid sha256:89dedfbbaf4906adbb87599ce42dab2b3412c2f3eed1c918df1f52570f878203
+size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c41e7c1f83dca8045fba481a590c3c5a6ca39c080efa3c795ba2e0db9ab191b
+oid sha256:0aa5fdd1e270251efa6239627ae6af3a9eb85be35af9f4cca7399ee33001083c
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 6.566188709209461,
-  "global_step": 430000,
+  "epoch": 6.7188907722143325,
+  "global_step": 440000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3188,11 +3188,85 @@
       "eval_samples_per_second": 910.508,
       "eval_steps_per_second": 14.568,
       "step": 430000
+    },
+    {
+      "epoch": 6.58,
+      "learning_rate": 0.00010141091567565561,
+      "loss": 0.2727,
+      "step": 431000
+    },
+    {
+      "epoch": 6.6,
+      "learning_rate": 0.00010119040759872142,
+      "loss": 0.2725,
+      "step": 432000
+    },
+    {
+      "epoch": 6.61,
+      "learning_rate": 0.00010096966778688472,
+      "loss": 0.2721,
+      "step": 433000
+    },
+    {
+      "epoch": 6.63,
+      "learning_rate": 0.00010074869865412074,
+      "loss": 0.272,
+      "step": 434000
+    },
+    {
+      "epoch": 6.64,
+      "learning_rate": 0.00010052750261691254,
+      "loss": 0.2721,
+      "step": 435000
+    },
+    {
+      "epoch": 6.64,
+      "eval_runtime": 0.9895,
+      "eval_samples_per_second": 1010.612,
+      "eval_steps_per_second": 16.17,
+      "step": 435000
+    },
+    {
+      "epoch": 6.66,
+      "learning_rate": 0.0001003060820942245,
+      "loss": 0.2716,
+      "step": 436000
+    },
+    {
+      "epoch": 6.67,
+      "learning_rate": 0.00010008443950747599,
+      "loss": 0.2716,
+      "step": 437000
+    },
+    {
+      "epoch": 6.69,
+      "learning_rate": 9.986257728051483e-05,
+      "loss": 0.2717,
+      "step": 438000
+    },
+    {
+      "epoch": 6.7,
+      "learning_rate": 9.964049783959082e-05,
+      "loss": 0.2716,
+      "step": 439000
+    },
+    {
+      "epoch": 6.72,
+      "learning_rate": 9.94182036133291e-05,
+      "loss": 0.2715,
+      "step": 440000
+    },
+    {
+      "epoch": 6.72,
+      "eval_runtime": 1.0245,
+      "eval_samples_per_second": 976.131,
+      "eval_steps_per_second": 15.618,
+      "step": 440000
     }
   ],
   "max_steps": 1000000,
   "num_train_epochs": 16,
-  "total_flos": 3.0143072818960347e+22,
+  "total_flos": 3.084407542926382e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:29a338d7e31f1ebb55d71826f0de824d2a1d8633cac67c074239e146a6c6bf2d
+oid sha256:605e171de557600b4f9eab4567771d6f7b62053eb613a7b7ed22d56f357a201b
 size 449471589