Training in progress, step 8000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a3b1570476040558106ef329ac5c35eaf7b927d872082a820226ad0028b5dd9
+oid sha256:3a481e433fa6eac80981a2ff00a0f8f7cf3e3e08ee088dd15e950410638af8d4
 size 496262784

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac1c439f2b333c6ba22b924fd6eb4e28a8524e3ac41694760d6b949858f9f4ad
+oid sha256:80c48bc7e746e70fff3e665a65cbf1675701d35dc75d28205041543695987838
 size 992621963

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:595e0adb3f51b4014c388d14cb8a20e5767cd34a947ffb570078cd186928d2c7
+oid sha256:38818bd9f30dd9f6202fc8de57f60ee4722cb7b211723c490ff280c9aeccae51
 size 14645

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f43de46bf0618be59b12a78ea440d0013f604015e857ea4a03ea845dabb299ad
+oid sha256:1d444c1a49dd1792c344220625a92a47a0fd68dd629b20f674d9dfda9433cfe5
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.12,
+  "epoch": 0.16,
   "eval_steps": 1000,
-  "global_step": 6000,
+  "global_step": 8000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -482,6 +482,164 @@
       "eval_samples_per_second": 340.705,
       "eval_steps_per_second": 21.415,
       "step": 6000
+    },
+    {
+      "epoch": 0.122,
+      "grad_norm": 0.25070950388908386,
+      "learning_rate": 0.0005791620179029091,
+      "loss": 3.7485830688476565,
+      "step": 6100
+    },
+    {
+      "epoch": 0.124,
+      "grad_norm": 0.23322179913520813,
+      "learning_rate": 0.0005784641497700528,
+      "loss": 3.7345367431640626,
+      "step": 6200
+    },
+    {
+      "epoch": 0.126,
+      "grad_norm": 0.27075648307800293,
+      "learning_rate": 0.0005777552220918525,
+      "loss": 3.747908935546875,
+      "step": 6300
+    },
+    {
+      "epoch": 0.128,
+      "grad_norm": 0.22065384685993195,
+      "learning_rate": 0.0005770352630242405,
+      "loss": 3.7215350341796873,
+      "step": 6400
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 0.2387268990278244,
+      "learning_rate": 0.0005763043011612747,
+      "loss": 3.7065789794921873,
+      "step": 6500
+    },
+    {
+      "epoch": 0.132,
+      "grad_norm": 0.2440839409828186,
+      "learning_rate": 0.0005755623655340019,
+      "loss": 3.7222140502929686,
+      "step": 6600
+    },
+    {
+      "epoch": 0.134,
+      "grad_norm": 0.7614469528198242,
+      "learning_rate": 0.000574809485609306,
+      "loss": 3.7069766235351564,
+      "step": 6700
+    },
+    {
+      "epoch": 0.136,
+      "grad_norm": 0.25670167803764343,
+      "learning_rate": 0.0005740456912887371,
+      "loss": 3.7104458618164062,
+      "step": 6800
+    },
+    {
+      "epoch": 0.138,
+      "grad_norm": 0.25214189291000366,
+      "learning_rate": 0.0005732710129073234,
+      "loss": 3.7040945434570314,
+      "step": 6900
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 0.2262343317270279,
+      "learning_rate": 0.0005724854812323674,
+      "loss": 3.686309814453125,
+      "step": 7000
+    },
+    {
+      "epoch": 0.14,
+      "eval_accuracy": 0.3409998074307532,
+      "eval_loss": 3.705655097961426,
+      "eval_runtime": 6.3038,
+      "eval_samples_per_second": 307.912,
+      "eval_steps_per_second": 19.354,
+      "step": 7000
+    },
+    {
+      "epoch": 0.142,
+      "grad_norm": 0.2256837785243988,
+      "learning_rate": 0.0005716891274622232,
+      "loss": 3.6851046752929686,
+      "step": 7100
+    },
+    {
+      "epoch": 0.144,
+      "grad_norm": 0.22516745328903198,
+      "learning_rate": 0.0005708819832250578,
+      "loss": 3.6776641845703124,
+      "step": 7200
+    },
+    {
+      "epoch": 0.146,
+      "grad_norm": 0.28322234749794006,
+      "learning_rate": 0.000570064080577595,
+      "loss": 3.6858819580078124,
+      "step": 7300
+    },
+    {
+      "epoch": 0.148,
+      "grad_norm": 0.2589821219444275,
+      "learning_rate": 0.0005692354520038415,
+      "loss": 3.683369140625,
+      "step": 7400
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 0.25471949577331543,
+      "learning_rate": 0.0005683961304137982,
+      "loss": 3.6476519775390623,
+      "step": 7500
+    },
+    {
+      "epoch": 0.152,
+      "grad_norm": 0.24686427414417267,
+      "learning_rate": 0.0005675461491421516,
+      "loss": 3.66244873046875,
+      "step": 7600
+    },
+    {
+      "epoch": 0.154,
+      "grad_norm": 0.23603662848472595,
+      "learning_rate": 0.0005666855419469506,
+      "loss": 3.6586270141601562,
+      "step": 7700
+    },
+    {
+      "epoch": 0.156,
+      "grad_norm": 0.23954837024211884,
+      "learning_rate": 0.0005658143430082659,
+      "loss": 3.6526480102539063,
+      "step": 7800
+    },
+    {
+      "epoch": 0.158,
+      "grad_norm": 0.24939873814582825,
+      "learning_rate": 0.0005649325869268321,
+      "loss": 3.6602520751953125,
+      "step": 7900
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.22606751322746277,
+      "learning_rate": 0.0005640403087226739,
+      "loss": 3.6500091552734375,
+      "step": 8000
+    },
+    {
+      "epoch": 0.16,
+      "eval_accuracy": 0.34401134847875336,
+      "eval_loss": 3.6704835891723633,
+      "eval_runtime": 5.9263,
+      "eval_samples_per_second": 327.521,
+      "eval_steps_per_second": 20.586,
+      "step": 8000
     }
   ],
   "logging_steps": 100,
@@ -501,7 +659,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.8813026304e+17,
+  "total_flos": 2.5084035072e+17,
   "train_batch_size": 120,
   "trial_name": null,
   "trial_params": null