Training in progress, step 9000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a592fce447bb7dcfa95e6c2f459b48dd8f3bbbb2b6792342f3f5dd4f7b1e9b7
+oid sha256:38ee0e126a580132596c3d97c2964515718ace488ec6db7b46380f4154ded27d
 size 4523108832

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a4e590112940d8f25a462fc21bc9495771d6dbcda763130af30c384c8af250a
+oid sha256:6437c5952734a3b6ca52d0d68b3bdc35fb243299ba8f58292c61ae631acec1ca
 size 2912179275

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:12d8b6c71ec5842a7f720763e6312f0db9384dc999ad47a74f64d26d1c1cb7ce
+oid sha256:77ca98ed10a20c7ebf9c36ba9d30a165fa497f9abd0ea9c9b3aaf71be5943d05
 size 14645

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:793190053d1293f4ec72cd72bea61df6e622ffbc2a94ef18fbadb35cfca4423b
+oid sha256:00b4eb0c27b559cfd649f7c80a6d3394a55880d92b3ee2ca98f71b67e7b2333a
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b64b4ee8ed3e0046a79e8a5ad65233e0a650bf33583438587eb37eed6953f429
+oid sha256:138616ec4232ecd5388ab77682730507e1759b2be764604e0a3f4489ea9ed002
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 13.020066666666667,
+  "epoch": 8.011033333333334,
   "eval_steps": 500,
-  "global_step": 8500,
+  "global_step": 9000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1198,6 +1198,76 @@
       "learning_rate": 2.4878872801555596e-05,
       "loss": 0.5521516799926758,
       "step": 8500
+    },
+    {
+      "epoch": 1.0016666666666667,
+      "grad_norm": 1.7751977443695068,
+      "learning_rate": 2.4818630060944365e-05,
+      "loss": 0.40423309326171875,
+      "step": 8550
+    },
+    {
+      "epoch": 1.0033333333333334,
+      "grad_norm": 1.3075405359268188,
+      "learning_rate": 2.4758108935485397e-05,
+      "loss": 0.41454471588134767,
+      "step": 8600
+    },
+    {
+      "epoch": 1.005,
+      "grad_norm": 1.5956394672393799,
+      "learning_rate": 2.4697311141117076e-05,
+      "loss": 0.4045108413696289,
+      "step": 8650
+    },
+    {
+      "epoch": 1.0066666666666666,
+      "grad_norm": 2.0534520149230957,
+      "learning_rate": 2.4636238401622122e-05,
+      "loss": 0.3971108627319336,
+      "step": 8700
+    },
+    {
+      "epoch": 1.0083333333333333,
+      "grad_norm": 1.553052544593811,
+      "learning_rate": 2.457489244857867e-05,
+      "loss": 0.3435604476928711,
+      "step": 8750
+    },
+    {
+      "epoch": 1.01,
+      "grad_norm": 1.145978569984436,
+      "learning_rate": 2.451327502131123e-05,
+      "loss": 0.36573856353759765,
+      "step": 8800
+    },
+    {
+      "epoch": 1.0116666666666667,
+      "grad_norm": 1.2501201629638672,
+      "learning_rate": 2.4451387866841323e-05,
+      "loss": 0.4070841598510742,
+      "step": 8850
+    },
+    {
+      "epoch": 1.0133333333333334,
+      "grad_norm": 1.8662524223327637,
+      "learning_rate": 2.438923273983799e-05,
+      "loss": 0.4094845962524414,
+      "step": 8900
+    },
+    {
+      "epoch": 2.000166666666667,
+      "grad_norm": 1.2666409015655518,
+      "learning_rate": 2.4326811402568e-05,
+      "loss": 0.3822321319580078,
+      "step": 8950
+    },
+    {
+      "epoch": 2.0018333333333334,
+      "grad_norm": 1.274243712425232,
+      "learning_rate": 2.4264125624845918e-05,
+      "loss": 0.17029172897338868,
+      "step": 9000
     }
   ],
   "logging_steps": 50,
@@ -1217,7 +1287,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7.58431423521448e+17,
+  "total_flos": 8.0306976809907e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null