Training in progress, step 16500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:77319477cdefbe2bc1688933a5f277f29c92bb4b3d47d3a96c3c7946d2bf6741
+oid sha256:00b1488540c98e882784cc0d9ae400dc759f4ebe572a80cfe35bb44e0b94170a
 size 4523108832

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:efd7207a9ae82e8a381821d53f23e54a556967f97a1ce8486d0f9efce432dce5
+oid sha256:f6534b5ac43de08af0543a38e27de08a0975938962d3b65029fb4ab32092a9d3
 size 2912179275

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe38f04c4cc7cc11e13d5494c0ea9211eb24b6df6d48f3a89782633a4b0394da
+oid sha256:8bd75f3b287b15c92e6927ee3d2a9e3e9a7c2ea768e141eb8d1ab87cfbf9392a
 size 14645

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7293b66ce992d4c13988430a5f894ce4c198eedbbb9f37b168a7fdf5daf3e2f7
+oid sha256:df99eaf0ea37c5aa6b34d1918c74e46f5e0805e8edf2b115f85552bce117d9ba
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:85b2675f2c6a6fa419cc2f1a43f272f9b788129d668d2ef3263907c517b720c8
+oid sha256:e0625a71bc50b7a12d96e4a43df11fae35d7aa3fe14917f3dd334fdfddb6a190
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 4.4665,
+  "epoch": 6.000233333333333,
   "eval_steps": 500,
-  "global_step": 16000,
+  "global_step": 16500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2248,6 +2248,76 @@
       "learning_rate": 1.3811170223137613e-05,
       "loss": 1.4478152465820313,
       "step": 16000
+    },
+    {
+      "epoch": 1.0016666666666667,
+      "grad_norm": 1.6693629026412964,
+      "learning_rate": 1.3731567699222302e-05,
+      "loss": 1.8988229370117187,
+      "step": 16050
+    },
+    {
+      "epoch": 1.0033333333333334,
+      "grad_norm": 1.6327314376831055,
+      "learning_rate": 1.365200113881011e-05,
+      "loss": 1.7711756896972657,
+      "step": 16100
+    },
+    {
+      "epoch": 1.005,
+      "grad_norm": 1.6666102409362793,
+      "learning_rate": 1.3572472797829294e-05,
+      "loss": 1.6638182067871095,
+      "step": 16150
+    },
+    {
+      "epoch": 1.0066666666666666,
+      "grad_norm": 1.7380634546279907,
+      "learning_rate": 1.3492984931124453e-05,
+      "loss": 1.6675144958496093,
+      "step": 16200
+    },
+    {
+      "epoch": 1.0083333333333333,
+      "grad_norm": 1.6629725694656372,
+      "learning_rate": 1.341353979239265e-05,
+      "loss": 1.617051239013672,
+      "step": 16250
+    },
+    {
+      "epoch": 1.01,
+      "grad_norm": 1.7792505025863647,
+      "learning_rate": 1.3334139634119483e-05,
+      "loss": 1.550360107421875,
+      "step": 16300
+    },
+    {
+      "epoch": 1.0116666666666667,
+      "grad_norm": 1.6665221452713013,
+      "learning_rate": 1.3254786707515244e-05,
+      "loss": 1.5528482055664063,
+      "step": 16350
+    },
+    {
+      "epoch": 1.0133333333333334,
+      "grad_norm": 1.690185785293579,
+      "learning_rate": 1.3175483262451064e-05,
+      "loss": 1.6005775451660156,
+      "step": 16400
+    },
+    {
+      "epoch": 1.015,
+      "grad_norm": 1.4981169700622559,
+      "learning_rate": 1.309623154739515e-05,
+      "loss": 1.6941712951660157,
+      "step": 16450
+    },
+    {
+      "epoch": 2.0004,
+      "grad_norm": 1.5367906093597412,
+      "learning_rate": 1.3017033809349013e-05,
+      "loss": 1.6436634826660157,
+      "step": 16500
     }
   ],
   "logging_steps": 50,
@@ -2267,7 +2337,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.3814272835067494e+18,
+  "total_flos": 1.4293719398339297e+18,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null