Training in progress, step 600, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef38e23f75049612d4593984a7a3ca4d8bb15ca4c375864be026d287d2b3887c
+oid sha256:fb956b595ae08ed63fbf1610a2cfe05de08b959291a75296518a168d063764b6
 size 4949934200

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60e07fbe280b472c7130a237eb85fec83e68ee6443f3e43bba1ecad5a003ea84
+oid sha256:463a2b5019a7f5d99135a4b074e05819fb63e66fc2befd429b6109b0a03d6ebb
 size 1110862568

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c3bd6b82fe6f7cb79e53c940f5432d5d84b10deb3c0f16e37914c245e9f465d4
+oid sha256:81a9ce88dbdaec68aeaab7e347846a6d2fe4b90053ffda8da98a7be27e9df5dc
 size 6159835552

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01bb9290ce3d59c6ff6ad761e9fc828c58d7a70fee34981771ade9f75e7a558c
+oid sha256:893344d0f191044a7c114fbf834353023abd8a24ba38e1e169829989ca44cb8f
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e8b452ae4994b1cf755a70d101c2857ab3a01f90d161421b4c6b76a66a30614
+oid sha256:6013d90416725816cb54a25c41a3a14fbb2cd743723bd5c562900e4ffe4f22e3
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f818275221580f93945cc9ffeac693f8727beebedb70d39d160511e90bb32454
+oid sha256:f50a6fddae7f536fdcd52ed2c2881024b7c2eff412e5c9fe5ed024666af442a5
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7fb27e90b9efb2bc1ba3aca816751650d05e50ae0229533972456bd829f8572c
+oid sha256:1daeb68d959a75fd6e1b227ebb24225f2543835019b429ede13432db5890912b
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e4c78e85c4ba926d25150d4aaddeaf5728dcb066f4afc01202e3e56f29a5487
+oid sha256:5ad54995b081fae25638228c5d9c8f38ca277e5c5ad00bc3e49897b543f84405
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 9.090909090909092,
+  "epoch": 13.636363636363637,
   "eval_steps": 200,
-  "global_step": 400,
+  "global_step": 600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -311,6 +311,154 @@
       "eval_samples_per_second": 115.091,
       "eval_steps_per_second": 5.827,
       "step": 400
+    },
+    {
+      "epoch": 9.318181818181818,
+      "grad_norm": 0.171875,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 0.0071,
+      "step": 410
+    },
+    {
+      "epoch": 9.545454545454545,
+      "grad_norm": 0.16796875,
+      "learning_rate": 4.530518418775733e-05,
+      "loss": 0.0072,
+      "step": 420
+    },
+    {
+      "epoch": 9.772727272727273,
+      "grad_norm": 0.2392578125,
+      "learning_rate": 4.077647473350201e-05,
+      "loss": 0.0071,
+      "step": 430
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 0.1572265625,
+      "learning_rate": 3.642762517900322e-05,
+      "loss": 0.0069,
+      "step": 440
+    },
+    {
+      "epoch": 10.227272727272727,
+      "grad_norm": 0.1904296875,
+      "learning_rate": 3.227184283742591e-05,
+      "loss": 0.0066,
+      "step": 450
+    },
+    {
+      "epoch": 10.454545454545455,
+      "grad_norm": 0.1416015625,
+      "learning_rate": 2.8321748683154893e-05,
+      "loss": 0.0066,
+      "step": 460
+    },
+    {
+      "epoch": 10.681818181818182,
+      "grad_norm": 0.15625,
+      "learning_rate": 2.4589339022310386e-05,
+      "loss": 0.0067,
+      "step": 470
+    },
+    {
+      "epoch": 10.909090909090908,
+      "grad_norm": 0.1376953125,
+      "learning_rate": 2.1085949060360654e-05,
+      "loss": 0.0062,
+      "step": 480
+    },
+    {
+      "epoch": 11.136363636363637,
+      "grad_norm": 0.15625,
+      "learning_rate": 1.7822218477475494e-05,
+      "loss": 0.0065,
+      "step": 490
+    },
+    {
+      "epoch": 11.363636363636363,
+      "grad_norm": 0.130859375,
+      "learning_rate": 1.4808059116167305e-05,
+      "loss": 0.0062,
+      "step": 500
+    },
+    {
+      "epoch": 11.590909090909092,
+      "grad_norm": 0.134765625,
+      "learning_rate": 1.2052624879351104e-05,
+      "loss": 0.0061,
+      "step": 510
+    },
+    {
+      "epoch": 11.818181818181818,
+      "grad_norm": 0.1455078125,
+      "learning_rate": 9.564283930242257e-06,
+      "loss": 0.0064,
+      "step": 520
+    },
+    {
+      "epoch": 12.045454545454545,
+      "grad_norm": 0.12255859375,
+      "learning_rate": 7.350593278519824e-06,
+      "loss": 0.0059,
+      "step": 530
+    },
+    {
+      "epoch": 12.272727272727273,
+      "grad_norm": 0.162109375,
+      "learning_rate": 5.418275829936537e-06,
+      "loss": 0.006,
+      "step": 540
+    },
+    {
+      "epoch": 12.5,
+      "grad_norm": 0.1318359375,
+      "learning_rate": 3.7731999690749585e-06,
+      "loss": 0.0061,
+      "step": 550
+    },
+    {
+      "epoch": 12.727272727272727,
+      "grad_norm": 0.11962890625,
+      "learning_rate": 2.420361737256438e-06,
+      "loss": 0.0064,
+      "step": 560
+    },
+    {
+      "epoch": 12.954545454545455,
+      "grad_norm": 0.1376953125,
+      "learning_rate": 1.3638696597277679e-06,
+      "loss": 0.0061,
+      "step": 570
+    },
+    {
+      "epoch": 13.181818181818182,
+      "grad_norm": 0.158203125,
+      "learning_rate": 6.069322682050516e-07,
+      "loss": 0.0063,
+      "step": 580
+    },
+    {
+      "epoch": 13.409090909090908,
+      "grad_norm": 0.11767578125,
+      "learning_rate": 1.518483566683826e-07,
+      "loss": 0.006,
+      "step": 590
+    },
+    {
+      "epoch": 13.636363636363637,
+      "grad_norm": 0.15625,
+      "learning_rate": 0.0,
+      "loss": 0.0063,
+      "step": 600
+    },
+    {
+      "epoch": 13.636363636363637,
+      "eval_loss": 4.043154239654541,
+      "eval_runtime": 13.032,
+      "eval_samples_per_second": 115.178,
+      "eval_steps_per_second": 5.832,
+      "step": 600
     }
   ],
   "logging_steps": 10,
@@ -325,12 +473,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2.827003985259397e+17,
+  "total_flos": 4.240152158483251e+17,
   "train_batch_size": 5,
   "trial_name": null,
   "trial_params": null