Training in progress, step 10000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a481e433fa6eac80981a2ff00a0f8f7cf3e3e08ee088dd15e950410638af8d4
+oid sha256:903447f03d58f6091e77f6c8e86618532694f7851f4bae993e86c4ce18c6f156
 size 496262784

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:80c48bc7e746e70fff3e665a65cbf1675701d35dc75d28205041543695987838
+oid sha256:43d16ca2f5f37c1c8859b2af1e7c37a0df1c1e053e9beab3ae0485a01ee4349e
 size 992621963

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:38818bd9f30dd9f6202fc8de57f60ee4722cb7b211723c490ff280c9aeccae51
+oid sha256:78c70ce0d856bbf974b0d8a026254698e4f48063d82d2b6e496aefa99327d481
 size 14645

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d444c1a49dd1792c344220625a92a47a0fd68dd629b20f674d9dfda9433cfe5
+oid sha256:4bd014c1a4ed62bfbd75417f39dbd6d002ac8b7b9a0b143e7b7bcaa971ce4138
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.16,
+  "epoch": 0.2,
   "eval_steps": 1000,
-  "global_step": 8000,
+  "global_step": 10000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -640,6 +640,164 @@
       "eval_samples_per_second": 327.521,
       "eval_steps_per_second": 20.586,
       "step": 8000
+    },
+    {
+      "epoch": 0.162,
+      "grad_norm": 0.23801666498184204,
+      "learning_rate": 0.0005631375438337147,
+      "loss": 3.632862548828125,
+      "step": 8100
+    },
+    {
+      "epoch": 0.164,
+      "grad_norm": 0.23611237108707428,
+      "learning_rate": 0.0005622243281143698,
+      "loss": 3.6399630737304687,
+      "step": 8200
+    },
+    {
+      "epoch": 0.166,
+      "grad_norm": 0.23898784816265106,
+      "learning_rate": 0.0005613006978341218,
+      "loss": 3.6880291748046874,
+      "step": 8300
+    },
+    {
+      "epoch": 0.168,
+      "grad_norm": 0.29460519552230835,
+      "learning_rate": 0.0005603666896760804,
+      "loss": 3.7291055297851563,
+      "step": 8400
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 0.2292584925889969,
+      "learning_rate": 0.0005594223407355256,
+      "loss": 3.7337985229492188,
+      "step": 8500
+    },
+    {
+      "epoch": 0.172,
+      "grad_norm": 0.2524070739746094,
+      "learning_rate": 0.0005584676885184341,
+      "loss": 3.7386798095703124,
+      "step": 8600
+    },
+    {
+      "epoch": 0.174,
+      "grad_norm": 0.25900545716285706,
+      "learning_rate": 0.0005575027709399899,
+      "loss": 3.7031732177734376,
+      "step": 8700
+    },
+    {
+      "epoch": 0.176,
+      "grad_norm": 0.22311732172966003,
+      "learning_rate": 0.0005565276263230785,
+      "loss": 3.71237060546875,
+      "step": 8800
+    },
+    {
+      "epoch": 0.178,
+      "grad_norm": 0.23083606362342834,
+      "learning_rate": 0.0005555422933967647,
+      "loss": 3.6988143920898438,
+      "step": 8900
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 0.23646661639213562,
+      "learning_rate": 0.0005545468112947544,
+      "loss": 3.692724609375,
+      "step": 9000
+    },
+    {
+      "epoch": 0.18,
+      "eval_accuracy": 0.3474917099443364,
+      "eval_loss": 3.6365442276000977,
+      "eval_runtime": 5.728,
+      "eval_samples_per_second": 338.859,
+      "eval_steps_per_second": 21.299,
+      "step": 9000
+    },
+    {
+      "epoch": 0.182,
+      "grad_norm": 0.2665349841117859,
+      "learning_rate": 0.0005535412195538409,
+      "loss": 3.683785400390625,
+      "step": 9100
+    },
+    {
+      "epoch": 0.184,
+      "grad_norm": 0.22817476093769073,
+      "learning_rate": 0.0005525255581123336,
+      "loss": 3.6991543579101562,
+      "step": 9200
+    },
+    {
+      "epoch": 0.186,
+      "grad_norm": 0.2592155635356903,
+      "learning_rate": 0.000551499867308473,
+      "loss": 3.6590890502929687,
+      "step": 9300
+    },
+    {
+      "epoch": 0.188,
+      "grad_norm": 0.24686357378959656,
+      "learning_rate": 0.0005504641878788275,
+      "loss": 3.6509600830078126,
+      "step": 9400
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 0.22637774050235748,
+      "learning_rate": 0.0005494185609566764,
+      "loss": 3.666563720703125,
+      "step": 9500
+    },
+    {
+      "epoch": 0.192,
+      "grad_norm": 0.21554476022720337,
+      "learning_rate": 0.0005483630280703757,
+      "loss": 3.6956219482421875,
+      "step": 9600
+    },
+    {
+      "epoch": 0.194,
+      "grad_norm": 0.2128387987613678,
+      "learning_rate": 0.0005472976311417091,
+      "loss": 3.661249084472656,
+      "step": 9700
+    },
+    {
+      "epoch": 0.196,
+      "grad_norm": 0.21794714033603668,
+      "learning_rate": 0.0005462224124842225,
+      "loss": 3.6454119873046875,
+      "step": 9800
+    },
+    {
+      "epoch": 0.198,
+      "grad_norm": 0.23011332750320435,
+      "learning_rate": 0.0005451374148015441,
+      "loss": 3.6472012329101564,
+      "step": 9900
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.21280302107334137,
+      "learning_rate": 0.0005440426811856883,
+      "loss": 3.6411611938476565,
+      "step": 10000
+    },
+    {
+      "epoch": 0.2,
+      "eval_accuracy": 0.3510436547424966,
+      "eval_loss": 3.6030726432800293,
+      "eval_runtime": 5.6604,
+      "eval_samples_per_second": 342.906,
+      "eval_steps_per_second": 21.553,
+      "step": 10000
     }
   ],
   "logging_steps": 100,
@@ -659,7 +817,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.5084035072e+17,
+  "total_flos": 3.135504384e+17,
   "train_batch_size": 120,
   "trial_name": null,
   "trial_params": null