Training in progress, step 48000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aba48a88f14f88d2c676b3120dd7519cd2ee052cab006b018c9a25681e031cfa
+oid sha256:f3fc4d626ad6c3cb4de1fc483d63ece29335b1ac5d3a3a09441069e06f25f0f4
 size 579824888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad957f747373b217d0825dc13fc9b44c586655ceaf668fd0b235b21ea08e71e9
+oid sha256:bf775a5e217ca74f861e212773e3c63eebc3516f8b6ebbb367ca371744b5691c
 size 1159794763

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae7080db6ca7826aa7327063ffbab1e6619bd0540a568acd2fb404342bae3b24
+oid sha256:873d111460b6ba6e0cbf9822bc67f72ae2c2daf614f4ccf90863d9afb393298c
 size 14645

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d4c064c012204759619753d64e389586d8e5d36728d74e01c63e63ba6b44abd
+oid sha256:b7889eb31311ac1db79a50295b4c3d90a6a18859f1afe377de3ed83ac3442007
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.28,
+  "epoch": 0.32,
   "eval_steps": 1000,
-  "global_step": 46000,
+  "global_step": 48000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3642,6 +3642,164 @@
       "eval_samples_per_second": 226.054,
       "eval_steps_per_second": 14.208,
       "step": 46000
+    },
+    {
+      "epoch": 0.282,
+      "grad_norm": 0.15725959837436676,
+      "learning_rate": 1.5033941149951102e-05,
+      "loss": 2.9681582641601563,
+      "step": 46100
+    },
+    {
+      "epoch": 0.284,
+      "grad_norm": 0.14279291033744812,
+      "learning_rate": 1.4276689048930535e-05,
+      "loss": 2.9894549560546877,
+      "step": 46200
+    },
+    {
+      "epoch": 0.286,
+      "grad_norm": 0.14746861159801483,
+      "learning_rate": 1.353872804511791e-05,
+      "loss": 2.9572384643554686,
+      "step": 46300
+    },
+    {
+      "epoch": 0.288,
+      "grad_norm": 0.1410951167345047,
+      "learning_rate": 1.2820087447539874e-05,
+      "loss": 2.956263427734375,
+      "step": 46400
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 0.1605064570903778,
+      "learning_rate": 1.212079579788955e-05,
+      "loss": 2.9751992797851563,
+      "step": 46500
+    },
+    {
+      "epoch": 0.292,
+      "grad_norm": 0.24090786278247833,
+      "learning_rate": 1.1440880869392545e-05,
+      "loss": 2.9600045776367185,
+      "step": 46600
+    },
+    {
+      "epoch": 0.294,
+      "grad_norm": 0.14448581635951996,
+      "learning_rate": 1.0780369665704504e-05,
+      "loss": 2.9817608642578124,
+      "step": 46700
+    },
+    {
+      "epoch": 0.296,
+      "grad_norm": 0.1405927687883377,
+      "learning_rate": 1.01392884198383e-05,
+      "loss": 2.9607421875,
+      "step": 46800
+    },
+    {
+      "epoch": 0.298,
+      "grad_norm": 0.1901511251926422,
+      "learning_rate": 9.517662593122034e-06,
+      "loss": 2.9657598876953126,
+      "step": 46900
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 0.14527775347232819,
+      "learning_rate": 8.915516874188124e-06,
+      "loss": 2.9576675415039064,
+      "step": 47000
+    },
+    {
+      "epoch": 0.3,
+      "eval_accuracy": 0.38471705931636907,
+      "eval_loss": 3.275611639022827,
+      "eval_runtime": 8.6293,
+      "eval_samples_per_second": 224.931,
+      "eval_steps_per_second": 14.138,
+      "step": 47000
+    },
+    {
+      "epoch": 0.302,
+      "grad_norm": 0.14045824110507965,
+      "learning_rate": 8.332875177992472e-06,
+      "loss": 2.9552996826171873,
+      "step": 47100
+    },
+    {
+      "epoch": 0.304,
+      "grad_norm": 0.14749419689178467,
+      "learning_rate": 7.769760644864899e-06,
+      "loss": 2.9305706787109376,
+      "step": 47200
+    },
+    {
+      "epoch": 0.306,
+      "grad_norm": 0.144828200340271,
+      "learning_rate": 7.2261956395899274e-06,
+      "loss": 2.9670144653320314,
+      "step": 47300
+    },
+    {
+      "epoch": 0.308,
+      "grad_norm": 0.15692554414272308,
+      "learning_rate": 6.702201750518666e-06,
+      "loss": 2.979140319824219,
+      "step": 47400
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 0.16095846891403198,
+      "learning_rate": 6.197799788711267e-06,
+      "loss": 2.9376812744140626,
+      "step": 47500
+    },
+    {
+      "epoch": 0.312,
+      "grad_norm": 0.1510581076145172,
+      "learning_rate": 5.713009787110424e-06,
+      "loss": 2.9954681396484375,
+      "step": 47600
+    },
+    {
+      "epoch": 0.314,
+      "grad_norm": 0.15443721413612366,
+      "learning_rate": 5.247850999745951e-06,
+      "loss": 2.9577410888671873,
+      "step": 47700
+    },
+    {
+      "epoch": 0.316,
+      "grad_norm": 0.14504078030586243,
+      "learning_rate": 4.80234190096962e-06,
+      "loss": 2.9848419189453126,
+      "step": 47800
+    },
+    {
+      "epoch": 0.318,
+      "grad_norm": 0.14038383960723877,
+      "learning_rate": 4.37650018472191e-06,
+      "loss": 2.9577120971679687,
+      "step": 47900
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.17559103667736053,
+      "learning_rate": 3.970342763829071e-06,
+      "loss": 2.95732421875,
+      "step": 48000
+    },
+    {
+      "epoch": 0.32,
+      "eval_accuracy": 0.3846958867813815,
+      "eval_loss": 3.275059223175049,
+      "eval_runtime": 11.741,
+      "eval_samples_per_second": 165.318,
+      "eval_steps_per_second": 10.391,
+      "step": 48000
     }
   ],
   "logging_steps": 100,
@@ -3661,7 +3819,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.80318199873536e+18,
+  "total_flos": 1.88158121607168e+18,
   "train_batch_size": 120,
   "trial_name": null,
   "trial_params": null