Training in progress, step 190000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72fccb2bc18a6b159ce0129ed7e56c6ec84f09bd6759b50adbd1ce42f25059da
+oid sha256:dd33a1577954e215c8437e7980add2f5f9574d602de488a6b0720d3ad4458fca
 size 202194449

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d0c936b0035a44830654c5c990550fb3b911629a82f5429aa175fe0903f7544
+oid sha256:a460f3fbdd157653313f970d730a974ff0dafa62f6d47ebc7be418c29489b80d
 size 102501541

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6620b407ca253e6b33b3a54e07067b9eda93cb36acf8dae1a1425f5a72f25010
+oid sha256:e960d152fa8a2009412029824cd0038b06b011605abe65cb9b329a00e7e113e2
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6620b407ca253e6b33b3a54e07067b9eda93cb36acf8dae1a1425f5a72f25010
+oid sha256:e960d152fa8a2009412029824cd0038b06b011605abe65cb9b329a00e7e113e2
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6620b407ca253e6b33b3a54e07067b9eda93cb36acf8dae1a1425f5a72f25010
+oid sha256:e960d152fa8a2009412029824cd0038b06b011605abe65cb9b329a00e7e113e2
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6620b407ca253e6b33b3a54e07067b9eda93cb36acf8dae1a1425f5a72f25010
+oid sha256:e960d152fa8a2009412029824cd0038b06b011605abe65cb9b329a00e7e113e2
 size 14503

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6620b407ca253e6b33b3a54e07067b9eda93cb36acf8dae1a1425f5a72f25010
+oid sha256:e960d152fa8a2009412029824cd0038b06b011605abe65cb9b329a00e7e113e2
 size 14503

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6620b407ca253e6b33b3a54e07067b9eda93cb36acf8dae1a1425f5a72f25010
+oid sha256:e960d152fa8a2009412029824cd0038b06b011605abe65cb9b329a00e7e113e2
 size 14503

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6620b407ca253e6b33b3a54e07067b9eda93cb36acf8dae1a1425f5a72f25010
+oid sha256:e960d152fa8a2009412029824cd0038b06b011605abe65cb9b329a00e7e113e2
 size 14503

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6620b407ca253e6b33b3a54e07067b9eda93cb36acf8dae1a1425f5a72f25010
+oid sha256:e960d152fa8a2009412029824cd0038b06b011605abe65cb9b329a00e7e113e2
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a265c146087c7b525f93e19ac9e51ad44bfb6af09ebd3ea4e38ee99de52c725
+oid sha256:a0439027dd6f55adc764cb1317d963df8ccf36442066dafecce10b3f538efa8e
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 4.193946736876442,
-  "global_step": 180000,
+  "epoch": 4.426943777814022,
+  "global_step": 190000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3606,11 +3606,211 @@
       "eval_samples_per_second": 1555.751,
       "eval_steps_per_second": 24.773,
       "step": 180000
+    },
+    {
+      "epoch": 4.21,
+      "learning_rate": 0.00022984029903546578,
+      "loss": 0.2835,
+      "step": 180500
+    },
+    {
+      "epoch": 4.22,
+      "learning_rate": 0.00022942919143113572,
+      "loss": 0.2832,
+      "step": 181000
+    },
+    {
+      "epoch": 4.22,
+      "eval_loss": 0.26567918062210083,
+      "eval_runtime": 1.4421,
+      "eval_samples_per_second": 1524.212,
+      "eval_steps_per_second": 24.271,
+      "step": 181000
+    },
+    {
+      "epoch": 4.23,
+      "learning_rate": 0.0002290172698810927,
+      "loss": 0.2832,
+      "step": 181500
+    },
+    {
+      "epoch": 4.24,
+      "learning_rate": 0.00022860453889004493,
+      "loss": 0.2828,
+      "step": 182000
+    },
+    {
+      "epoch": 4.24,
+      "eval_loss": 0.2642976641654968,
+      "eval_runtime": 1.4457,
+      "eval_samples_per_second": 1520.406,
+      "eval_steps_per_second": 24.21,
+      "step": 182000
+    },
+    {
+      "epoch": 4.25,
+      "learning_rate": 0.00022819100297155235,
+      "loss": 0.2825,
+      "step": 182500
+    },
+    {
+      "epoch": 4.26,
+      "learning_rate": 0.0002277766666479774,
+      "loss": 0.2825,
+      "step": 183000
+    },
+    {
+      "epoch": 4.26,
+      "eval_loss": 0.26654452085494995,
+      "eval_runtime": 1.5184,
+      "eval_samples_per_second": 1447.589,
+      "eval_steps_per_second": 23.051,
+      "step": 183000
+    },
+    {
+      "epoch": 4.28,
+      "learning_rate": 0.00022736153445043595,
+      "loss": 0.2833,
+      "step": 183500
+    },
+    {
+      "epoch": 4.29,
+      "learning_rate": 0.00022694561091874706,
+      "loss": 0.2854,
+      "step": 184000
+    },
+    {
+      "epoch": 4.29,
+      "eval_loss": 0.2664638161659241,
+      "eval_runtime": 1.3999,
+      "eval_samples_per_second": 1570.099,
+      "eval_steps_per_second": 25.002,
+      "step": 184000
+    },
+    {
+      "epoch": 4.3,
+      "learning_rate": 0.00022652890060138387,
+      "loss": 0.2833,
+      "step": 184500
+    },
+    {
+      "epoch": 4.31,
+      "learning_rate": 0.00022611140805542366,
+      "loss": 0.2824,
+      "step": 185000
+    },
+    {
+      "epoch": 4.31,
+      "eval_loss": 0.26191577315330505,
+      "eval_runtime": 1.367,
+      "eval_samples_per_second": 1607.943,
+      "eval_steps_per_second": 25.604,
+      "step": 185000
+    },
+    {
+      "epoch": 4.32,
+      "learning_rate": 0.00022569313784649798,
+      "loss": 0.2819,
+      "step": 185500
+    },
+    {
+      "epoch": 4.33,
+      "learning_rate": 0.0002252740945487429,
+      "loss": 0.2819,
+      "step": 186000
+    },
+    {
+      "epoch": 4.33,
+      "eval_loss": 0.26568353176116943,
+      "eval_runtime": 1.413,
+      "eval_samples_per_second": 1555.568,
+      "eval_steps_per_second": 24.77,
+      "step": 186000
+    },
+    {
+      "epoch": 4.35,
+      "learning_rate": 0.00022485428274474867,
+      "loss": 0.2817,
+      "step": 186500
+    },
+    {
+      "epoch": 4.36,
+      "learning_rate": 0.00022443370702551,
+      "loss": 0.2824,
+      "step": 187000
+    },
+    {
+      "epoch": 4.36,
+      "eval_loss": 0.26549944281578064,
+      "eval_runtime": 1.4329,
+      "eval_samples_per_second": 1533.942,
+      "eval_steps_per_second": 24.426,
+      "step": 187000
+    },
+    {
+      "epoch": 4.37,
+      "learning_rate": 0.00022401237199037565,
+      "loss": 0.2822,
+      "step": 187500
+    },
+    {
+      "epoch": 4.38,
+      "learning_rate": 0.0002235902822469979,
+      "loss": 0.2815,
+      "step": 188000
+    },
+    {
+      "epoch": 4.38,
+      "eval_loss": 0.2621370553970337,
+      "eval_runtime": 1.4638,
+      "eval_samples_per_second": 1501.617,
+      "eval_steps_per_second": 23.911,
+      "step": 188000
+    },
+    {
+      "epoch": 4.39,
+      "learning_rate": 0.00022316744241128268,
+      "loss": 0.2815,
+      "step": 188500
+    },
+    {
+      "epoch": 4.4,
+      "learning_rate": 0.00022274385710733855,
+      "loss": 0.2814,
+      "step": 189000
+    },
+    {
+      "epoch": 4.4,
+      "eval_loss": 0.2638288140296936,
+      "eval_runtime": 1.4301,
+      "eval_samples_per_second": 1536.915,
+      "eval_steps_per_second": 24.473,
+      "step": 189000
+    },
+    {
+      "epoch": 4.42,
+      "learning_rate": 0.00022231953096742672,
+      "loss": 0.2826,
+      "step": 189500
+    },
+    {
+      "epoch": 4.43,
+      "learning_rate": 0.00022189446863190974,
+      "loss": 0.2821,
+      "step": 190000
+    },
+    {
+      "epoch": 4.43,
+      "eval_loss": 0.26497727632522583,
+      "eval_runtime": 1.4514,
+      "eval_samples_per_second": 1514.384,
+      "eval_steps_per_second": 24.114,
+      "step": 190000
     }
   ],
   "max_steps": 500000,
   "num_train_epochs": 12,
-  "total_flos": 5.750758509977373e+21,
+  "total_flos": 6.070245648751873e+21,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d0c936b0035a44830654c5c990550fb3b911629a82f5429aa175fe0903f7544
+oid sha256:a460f3fbdd157653313f970d730a974ff0dafa62f6d47ebc7be418c29489b80d
 size 102501541