Training in progress, step 400, checkpoint

last-checkpoint/model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:52f25f406564918ef37003e4a6d5a99f1faef4c9da3b1bf2fcc9f823e9a999da
+oid sha256:ef38e23f75049612d4593984a7a3ca4d8bb15ca4c375864be026d287d2b3887c
 size 4949934200

last-checkpoint/model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:15f325d357680aa0bea0344df5ec0857bae22ce1c5e0998812aa568c7d86270e
+oid sha256:60e07fbe280b472c7130a237eb85fec83e68ee6443f3e43bba1ecad5a003ea84
 size 1110862568

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:24583f86460237bb133e0ca7ae08cd8e6bf0ec8dc4de79aaf8ae7a9535903918
-size 6159835104
+oid sha256:c3bd6b82fe6f7cb79e53c940f5432d5d84b10deb3c0f16e37914c245e9f465d4
+size 6159835552

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7071f37b1070578e9621f099e4eebb40b9b7a2516b98dda621244e972aa42269
+oid sha256:01bb9290ce3d59c6ff6ad761e9fc828c58d7a70fee34981771ade9f75e7a558c
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:19fbee4f72c5b86d1056ef05f4ba4d9447fc98fa25d61f8928902400859ae945
+oid sha256:9e8b452ae4994b1cf755a70d101c2857ab3a01f90d161421b4c6b76a66a30614
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c10d832b2499164ed4d6dc9f5123bc48630d710354187a8bd9b02570e0ffd51
+oid sha256:f818275221580f93945cc9ffeac693f8727beebedb70d39d160511e90bb32454
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b38612e515e5b3a97a1ebbe98027df6191293cd001adc85c0e1f1872aabcb09
+oid sha256:7fb27e90b9efb2bc1ba3aca816751650d05e50ae0229533972456bd829f8572c
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9cd11d413bc67bf01de9a1a006e9e7655be307353028b25f5b3c299e5b6b7a44
+oid sha256:0e4c78e85c4ba926d25150d4aaddeaf5728dcb066f4afc01202e3e56f29a5487
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 4.545454545454545,
+  "epoch": 9.090909090909092,
   "eval_steps": 200,
-  "global_step": 200,
+  "global_step": 400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -163,6 +163,154 @@
       "eval_samples_per_second": 114.579,
       "eval_steps_per_second": 5.801,
       "step": 200
+    },
+    {
+      "epoch": 4.7727272727272725,
+      "grad_norm": 1.21875,
+      "learning_rate": 0.00015469481581224272,
+      "loss": 0.3798,
+      "step": 210
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 1.40625,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 0.3946,
+      "step": 220
+    },
+    {
+      "epoch": 5.2272727272727275,
+      "grad_norm": 0.92578125,
+      "learning_rate": 0.00014515333583108896,
+      "loss": 0.185,
+      "step": 230
+    },
+    {
+      "epoch": 5.454545454545454,
+      "grad_norm": 0.953125,
+      "learning_rate": 0.00014016954246529696,
+      "loss": 0.2086,
+      "step": 240
+    },
+    {
+      "epoch": 5.681818181818182,
+      "grad_norm": 0.9609375,
+      "learning_rate": 0.00013506375551927547,
+      "loss": 0.2037,
+      "step": 250
+    },
+    {
+      "epoch": 5.909090909090909,
+      "grad_norm": 0.94921875,
+      "learning_rate": 0.00012985148110016947,
+      "loss": 0.2147,
+      "step": 260
+    },
+    {
+      "epoch": 6.136363636363637,
+      "grad_norm": 0.67578125,
+      "learning_rate": 0.00012454854871407994,
+      "loss": 0.1516,
+      "step": 270
+    },
+    {
+      "epoch": 6.363636363636363,
+      "grad_norm": 0.64453125,
+      "learning_rate": 0.00011917106319237386,
+      "loss": 0.1077,
+      "step": 280
+    },
+    {
+      "epoch": 6.590909090909091,
+      "grad_norm": 0.640625,
+      "learning_rate": 0.00011373535578184082,
+      "loss": 0.1024,
+      "step": 290
+    },
+    {
+      "epoch": 6.818181818181818,
+      "grad_norm": 0.62109375,
+      "learning_rate": 0.00010825793454723325,
+      "loss": 0.0919,
+      "step": 300
+    },
+    {
+      "epoch": 7.045454545454546,
+      "grad_norm": 0.392578125,
+      "learning_rate": 0.00010275543423681621,
+      "loss": 0.075,
+      "step": 310
+    },
+    {
+      "epoch": 7.2727272727272725,
+      "grad_norm": 0.3515625,
+      "learning_rate": 9.724456576318381e-05,
+      "loss": 0.0312,
+      "step": 320
+    },
+    {
+      "epoch": 7.5,
+      "grad_norm": 0.3203125,
+      "learning_rate": 9.174206545276677e-05,
+      "loss": 0.0276,
+      "step": 330
+    },
+    {
+      "epoch": 7.7272727272727275,
+      "grad_norm": 0.333984375,
+      "learning_rate": 8.626464421815919e-05,
+      "loss": 0.0259,
+      "step": 340
+    },
+    {
+      "epoch": 7.954545454545455,
+      "grad_norm": 0.30859375,
+      "learning_rate": 8.082893680762619e-05,
+      "loss": 0.0246,
+      "step": 350
+    },
+    {
+      "epoch": 8.181818181818182,
+      "grad_norm": 0.22265625,
+      "learning_rate": 7.54514512859201e-05,
+      "loss": 0.0135,
+      "step": 360
+    },
+    {
+      "epoch": 8.409090909090908,
+      "grad_norm": 0.2294921875,
+      "learning_rate": 7.014851889983057e-05,
+      "loss": 0.0107,
+      "step": 370
+    },
+    {
+      "epoch": 8.636363636363637,
+      "grad_norm": 0.1884765625,
+      "learning_rate": 6.493624448072457e-05,
+      "loss": 0.0105,
+      "step": 380
+    },
+    {
+      "epoch": 8.863636363636363,
+      "grad_norm": 0.267578125,
+      "learning_rate": 5.983045753470308e-05,
+      "loss": 0.0098,
+      "step": 390
+    },
+    {
+      "epoch": 9.090909090909092,
+      "grad_norm": 0.14453125,
+      "learning_rate": 5.484666416891109e-05,
+      "loss": 0.009,
+      "step": 400
+    },
+    {
+      "epoch": 9.090909090909092,
+      "eval_loss": 4.0009965896606445,
+      "eval_runtime": 13.0419,
+      "eval_samples_per_second": 115.091,
+      "eval_steps_per_second": 5.827,
+      "step": 400
     }
   ],
   "logging_steps": 10,
@@ -182,7 +330,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.413855812035543e+17,
+  "total_flos": 2.827003985259397e+17,
   "train_batch_size": 5,
   "trial_name": null,
   "trial_params": null