Training in progress, step 900, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:70bb5bb361cb2c44a3c95065d77a422ed9649be5bd191a41e78d34e35834847b
+oid sha256:12451cbc3f681c4d652adfbac061b94a617fe5288eadb9338e0c0116f1ab09a0
 size 3237829088

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:098af36ab395a778e4ad67ddfa0191cced4901cc9518f1a83364c1e0ed5e1dbe
+oid sha256:e2ac56c591f7d766084f7d7411df625b2b9385404ec3f7c675d4dea7dc7e6caf
 size 2062272049

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e4743b658fa9de4e54f29c9ad2e962e40b252677e30a13b5a792846f596864f
+oid sha256:5dbfcd19dd04e87ea5a0a02be9024658d9d950751b047080030098d848f7be93
 size 14645

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e35963fbe17703d43e57c264c8bf401c049828d6ea5abe6c269f936eebec007
+oid sha256:504b7bc543b9e5f039f6559d07b099507a66c15c86836ff5981e4eee51792c02
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0bb282d448dcf74bd6fbccf99dc933faaae6d52cfc91f1d2df7df3c6a133ab1a
+oid sha256:cb4a875674808f59301dfb232d0f66520f4ad75d8962141e97389a5c2ef15def
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.17219113215669393,
+  "epoch": 0.2582866982350409,
   "eval_steps": 300,
-  "global_step": 600,
+  "global_step": 900,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -428,6 +428,216 @@
       "learning_rate": 0.00018848305761935797,
       "loss": 0.9528,
       "step": 600
+    },
+    {
+      "epoch": 0.1750609843593055,
+      "grad_norm": 9.415815353393555,
+      "learning_rate": 0.00018805083564044802,
+      "loss": 0.8619,
+      "step": 610
+    },
+    {
+      "epoch": 0.17793083656191705,
+      "grad_norm": 9.250490188598633,
+      "learning_rate": 0.0001876111664371025,
+      "loss": 0.9168,
+      "step": 620
+    },
+    {
+      "epoch": 0.18080068876452862,
+      "grad_norm": 15.730814933776855,
+      "learning_rate": 0.0001871640871959672,
+      "loss": 0.94,
+      "step": 630
+    },
+    {
+      "epoch": 0.1836705409671402,
+      "grad_norm": 9.073026657104492,
+      "learning_rate": 0.0001867096357304191,
+      "loss": 0.9471,
+      "step": 640
+    },
+    {
+      "epoch": 0.18654039316975177,
+      "grad_norm": 8.982126235961914,
+      "learning_rate": 0.00018624785047736842,
+      "loss": 0.9177,
+      "step": 650
+    },
+    {
+      "epoch": 0.1894102453723633,
+      "grad_norm": 10.682122230529785,
+      "learning_rate": 0.00018577877049400746,
+      "loss": 0.9402,
+      "step": 660
+    },
+    {
+      "epoch": 0.19228009757497488,
+      "grad_norm": 8.706944465637207,
+      "learning_rate": 0.0001853024354545073,
+      "loss": 0.8867,
+      "step": 670
+    },
+    {
+      "epoch": 0.19514994977758646,
+      "grad_norm": 5.8472371101379395,
+      "learning_rate": 0.00018481888564666208,
+      "loss": 0.9135,
+      "step": 680
+    },
+    {
+      "epoch": 0.19801980198019803,
+      "grad_norm": 5.432713508605957,
+      "learning_rate": 0.00018432816196848172,
+      "loss": 0.8525,
+      "step": 690
+    },
+    {
+      "epoch": 0.20088965418280957,
+      "grad_norm": 28.993038177490234,
+      "learning_rate": 0.00018383030592473266,
+      "loss": 0.8779,
+      "step": 700
+    },
+    {
+      "epoch": 0.20375950638542115,
+      "grad_norm": 5.313049793243408,
+      "learning_rate": 0.0001833253596234274,
+      "loss": 0.9551,
+      "step": 710
+    },
+    {
+      "epoch": 0.20662935858803272,
+      "grad_norm": 18.639175415039062,
+      "learning_rate": 0.00018281336577226327,
+      "loss": 0.8694,
+      "step": 720
+    },
+    {
+      "epoch": 0.2094992107906443,
+      "grad_norm": 15.578129768371582,
+      "learning_rate": 0.00018229436767501012,
+      "loss": 0.9017,
+      "step": 730
+    },
+    {
+      "epoch": 0.21236906299325584,
+      "grad_norm": 18.0419864654541,
+      "learning_rate": 0.0001817684092278477,
+      "loss": 0.8616,
+      "step": 740
+    },
+    {
+      "epoch": 0.2152389151958674,
+      "grad_norm": 8.34323787689209,
+      "learning_rate": 0.00018123553491565308,
+      "loss": 0.8902,
+      "step": 750
+    },
+    {
+      "epoch": 0.21810876739847898,
+      "grad_norm": 8.49802017211914,
+      "learning_rate": 0.00018069578980823816,
+      "loss": 0.8781,
+      "step": 760
+    },
+    {
+      "epoch": 0.22097861960109055,
+      "grad_norm": 6.250750541687012,
+      "learning_rate": 0.00018014921955653772,
+      "loss": 0.8405,
+      "step": 770
+    },
+    {
+      "epoch": 0.2238484718037021,
+      "grad_norm": 25.283082962036133,
+      "learning_rate": 0.00017959587038874822,
+      "loss": 0.93,
+      "step": 780
+    },
+    {
+      "epoch": 0.22671832400631367,
+      "grad_norm": 18.443071365356445,
+      "learning_rate": 0.00017903578910641814,
+      "loss": 0.9202,
+      "step": 790
+    },
+    {
+      "epoch": 0.22958817620892524,
+      "grad_norm": 18.457555770874023,
+      "learning_rate": 0.0001784690230804892,
+      "loss": 0.9446,
+      "step": 800
+    },
+    {
+      "epoch": 0.23245802841153682,
+      "grad_norm": 7.786270618438721,
+      "learning_rate": 0.00017789562024729012,
+      "loss": 0.899,
+      "step": 810
+    },
+    {
+      "epoch": 0.23532788061414836,
+      "grad_norm": 6.527904033660889,
+      "learning_rate": 0.00017731562910448202,
+      "loss": 0.8866,
+      "step": 820
+    },
+    {
+      "epoch": 0.23819773281675993,
+      "grad_norm": 8.394437789916992,
+      "learning_rate": 0.00017672909870695665,
+      "loss": 0.8749,
+      "step": 830
+    },
+    {
+      "epoch": 0.2410675850193715,
+      "grad_norm": 6.815917491912842,
+      "learning_rate": 0.00017613607866268742,
+      "loss": 0.8542,
+      "step": 840
+    },
+    {
+      "epoch": 0.24393743722198308,
+      "grad_norm": 16.42218780517578,
+      "learning_rate": 0.00017553661912853347,
+      "loss": 0.8658,
+      "step": 850
+    },
+    {
+      "epoch": 0.24680728942459462,
+      "grad_norm": 14.373140335083008,
+      "learning_rate": 0.00017493077080599768,
+      "loss": 0.8756,
+      "step": 860
+    },
+    {
+      "epoch": 0.2496771416272062,
+      "grad_norm": 17.368059158325195,
+      "learning_rate": 0.0001743185849369381,
+      "loss": 0.9572,
+      "step": 870
+    },
+    {
+      "epoch": 0.25254699382981777,
+      "grad_norm": 8.744333267211914,
+      "learning_rate": 0.0001737001132992344,
+      "loss": 0.8743,
+      "step": 880
+    },
+    {
+      "epoch": 0.2554168460324293,
+      "grad_norm": 9.240042686462402,
+      "learning_rate": 0.0001730754082024082,
+      "loss": 0.8666,
+      "step": 890
+    },
+    {
+      "epoch": 0.2582866982350409,
+      "grad_norm": 8.81686782836914,
+      "learning_rate": 0.00017244452248319896,
+      "loss": 0.8771,
+      "step": 900
     }
   ],
   "logging_steps": 10,
@@ -447,7 +657,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.4551296598016e+19,
+  "total_flos": 3.6826944897024e+19,
   "train_batch_size": 6,
   "trial_name": null,
   "trial_params": null