Training in progress, step 19000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:714af7538b26941d0b6c17002355149620e21924a5a9fe7c385b2ccb6626063f
+oid sha256:f9581ac4d1703cdbe22ad996a570367abe7aed22a3b302a4e48c035c95928516
 size 4523108832

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b1ac067e345f81cabef3eb89bc66c3a5091a9bf0420b422934f2d70beb62e94f
+oid sha256:d261237b67b656ca363c7ece76d2fc676f64f7d6ebcc6170f7cb85ea5646de45
 size 2912179275

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87b07b911601d04abcbcc91c12340e18730f0dbec6517e92e9000c51517972c9
+oid sha256:0c0b314d655e9be31e93455deb9fbabd83362b86e9c047746bf9788399d89574
 size 14645

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:00b7a5d99d77c7deb7d1fd1da36a8f1a552b9340e346793754509d7c962ffe38
+oid sha256:1855dda48f486fd94b9c88ff064473bb49694350310a824a305372b2d8f1caa6
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bae61de7eccc1d6ebf06b52a6d36b904579ed066577d4884e6d61bab2772f130
+oid sha256:f59aca1bbf4fa132f51f0bd177e99ee325a0dca8330a713e113a51e02ab5322c
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 6.000233333333333,
+  "epoch": 7.000566666666666,
   "eval_steps": 500,
-  "global_step": 18500,
+  "global_step": 19000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2598,6 +2598,76 @@
       "learning_rate": 9.920434206881963e-06,
       "loss": 1.1839189910888672,
       "step": 18500
+    },
+    {
+      "epoch": 2.002066666666667,
+      "grad_norm": 1.7923060655593872,
+      "learning_rate": 9.845354603350045e-06,
+      "loss": 0.5976836395263672,
+      "step": 18550
+    },
+    {
+      "epoch": 2.0037333333333334,
+      "grad_norm": 1.5783723592758179,
+      "learning_rate": 9.770421148024648e-06,
+      "loss": 0.6248928451538086,
+      "step": 18600
+    },
+    {
+      "epoch": 2.0054,
+      "grad_norm": 1.575974464416504,
+      "learning_rate": 9.695635965472885e-06,
+      "loss": 0.629935417175293,
+      "step": 18650
+    },
+    {
+      "epoch": 2.0070666666666668,
+      "grad_norm": 1.6231439113616943,
+      "learning_rate": 9.621001176057947e-06,
+      "loss": 0.6451435852050781,
+      "step": 18700
+    },
+    {
+      "epoch": 2.0087333333333333,
+      "grad_norm": 1.5992910861968994,
+      "learning_rate": 9.546518895878952e-06,
+      "loss": 0.6247399520874023,
+      "step": 18750
+    },
+    {
+      "epoch": 2.0104,
+      "grad_norm": 1.6657859086990356,
+      "learning_rate": 9.473676260970532e-06,
+      "loss": 0.6678472137451172,
+      "step": 18800
+    },
+    {
+      "epoch": 2.0120666666666667,
+      "grad_norm": 1.9037035703659058,
+      "learning_rate": 9.399502175012888e-06,
+      "loss": 0.6817168426513672,
+      "step": 18850
+    },
+    {
+      "epoch": 2.013733333333333,
+      "grad_norm": 1.8003382682800293,
+      "learning_rate": 9.32548687838987e-06,
+      "loss": 0.753537826538086,
+      "step": 18900
+    },
+    {
+      "epoch": 2.0154,
+      "grad_norm": 1.7780545949935913,
+      "learning_rate": 9.251632469636292e-06,
+      "loss": 0.8301016235351563,
+      "step": 18950
+    },
+    {
+      "epoch": 3.0007333333333333,
+      "grad_norm": 1.8590174913406372,
+      "learning_rate": 9.177941042725378e-06,
+      "loss": 0.8636976623535156,
+      "step": 19000
     }
   ],
   "logging_steps": 50,
@@ -2617,7 +2687,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.6201828336082289e+18,
+  "total_flos": 1.6679524867952394e+18,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null