Training in progress, step 50000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f3fc4d626ad6c3cb4de1fc483d63ece29335b1ac5d3a3a09441069e06f25f0f4
+oid sha256:820ce0664e8dd374150850bdca06f989fd53e07c16e17ed8101206c3e35d8c6e
 size 579824888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bf775a5e217ca74f861e212773e3c63eebc3516f8b6ebbb367ca371744b5691c
+oid sha256:694364ccca4886052dab7895693a8db8e794f89b0bfe3ae9cc7f08a398332a41
 size 1159794763

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:873d111460b6ba6e0cbf9822bc67f72ae2c2daf614f4ccf90863d9afb393298c
+oid sha256:8cd699a1fbed40cff8a788e14ebb8537b2ce07b97175607d47704825c1ea236f
 size 14645

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b7889eb31311ac1db79a50295b4c3d90a6a18859f1afe377de3ed83ac3442007
+oid sha256:385828656c78fd7663309404035cb45057a1c19eb9bebaaba7e6fb4defcf570d
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.32,
+  "epoch": 0.36,
   "eval_steps": 1000,
-  "global_step": 48000,
+  "global_step": 50000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3800,6 +3800,164 @@
       "eval_samples_per_second": 165.318,
       "eval_steps_per_second": 10.391,
       "step": 48000
+    },
+    {
+      "epoch": 0.322,
+      "grad_norm": 0.1336028277873993,
+      "learning_rate": 3.583885769331385e-06,
+      "loss": 2.9611053466796875,
+      "step": 48100
+    },
+    {
+      "epoch": 0.324,
+      "grad_norm": 0.14741460978984833,
+      "learning_rate": 3.2171445498424545e-06,
+      "loss": 2.9574826049804686,
+      "step": 48200
+    },
+    {
+      "epoch": 0.326,
+      "grad_norm": 0.1761571615934372,
+      "learning_rate": 2.870133670939745e-06,
+      "loss": 2.937596435546875,
+      "step": 48300
+    },
+    {
+      "epoch": 0.328,
+      "grad_norm": 0.1392708420753479,
+      "learning_rate": 2.542866914586106e-06,
+      "loss": 2.9430572509765627,
+      "step": 48400
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 0.1438605785369873,
+      "learning_rate": 2.2353572785822065e-06,
+      "loss": 2.9703692626953124,
+      "step": 48500
+    },
+    {
+      "epoch": 0.332,
+      "grad_norm": 0.14872929453849792,
+      "learning_rate": 1.9476169760506144e-06,
+      "loss": 2.967200927734375,
+      "step": 48600
+    },
+    {
+      "epoch": 0.334,
+      "grad_norm": 0.15221774578094482,
+      "learning_rate": 1.6796574349503546e-06,
+      "loss": 2.975442199707031,
+      "step": 48700
+    },
+    {
+      "epoch": 0.336,
+      "grad_norm": 0.1402570754289627,
+      "learning_rate": 1.4314892976233784e-06,
+      "loss": 2.952536926269531,
+      "step": 48800
+    },
+    {
+      "epoch": 0.338,
+      "grad_norm": 0.13577665388584137,
+      "learning_rate": 1.2031224203717384e-06,
+      "loss": 2.977938537597656,
+      "step": 48900
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 0.143800750374794,
+      "learning_rate": 9.945658730661778e-07,
+      "loss": 2.9537298583984377,
+      "step": 49000
+    },
+    {
+      "epoch": 0.34,
+      "eval_accuracy": 0.3848007412403678,
+      "eval_loss": 3.274916172027588,
+      "eval_runtime": 8.7987,
+      "eval_samples_per_second": 220.6,
+      "eval_steps_per_second": 13.866,
+      "step": 49000
+    },
+    {
+      "epoch": 0.342,
+      "grad_norm": 0.1486690193414688,
+      "learning_rate": 8.05827938785808e-07,
+      "loss": 2.9592388916015624,
+      "step": 49100
+    },
+    {
+      "epoch": 0.344,
+      "grad_norm": 0.14764626324176788,
+      "learning_rate": 6.369161134892055e-07,
+      "loss": 2.9477633666992187,
+      "step": 49200
+    },
+    {
+      "epoch": 0.346,
+      "grad_norm": 0.15068262815475464,
+      "learning_rate": 4.878371057168151e-07,
+      "loss": 2.933819580078125,
+      "step": 49300
+    },
+    {
+      "epoch": 0.348,
+      "grad_norm": 0.13414137065410614,
+      "learning_rate": 3.585968363242209e-07,
+      "loss": 2.9506927490234376,
+      "step": 49400
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 0.16431079804897308,
+      "learning_rate": 2.492004382474433e-07,
+      "loss": 2.9817596435546876,
+      "step": 49500
+    },
+    {
+      "epoch": 0.352,
+      "grad_norm": 0.1382792890071869,
+      "learning_rate": 1.5965225629849257e-07,
+      "loss": 2.9758001708984376,
+      "step": 49600
+    },
+    {
+      "epoch": 0.354,
+      "grad_norm": 0.13877373933792114,
+      "learning_rate": 8.995584699333925e-08,
+      "loss": 2.950361633300781,
+      "step": 49700
+    },
+    {
+      "epoch": 0.356,
+      "grad_norm": 0.1560918092727661,
+      "learning_rate": 4.011397841041653e-08,
+      "loss": 2.9428829956054687,
+      "step": 49800
+    },
+    {
+      "epoch": 0.358,
+      "grad_norm": 0.1353323608636856,
+      "learning_rate": 1.0128630080652456e-08,
+      "loss": 2.9610910034179687,
+      "step": 49900
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 0.18417476117610931,
+      "learning_rate": 9.929089772597876e-13,
+      "loss": 2.9677053833007814,
+      "step": 50000
+    },
+    {
+      "epoch": 0.36,
+      "eval_accuracy": 0.38479065908084986,
+      "eval_loss": 3.274902820587158,
+      "eval_runtime": 8.7288,
+      "eval_samples_per_second": 222.367,
+      "eval_steps_per_second": 13.977,
+      "step": 50000
     }
   ],
   "logging_steps": 100,
@@ -3814,12 +3972,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.88158121607168e+18,
+  "total_flos": 1.959980433408e+18,
   "train_batch_size": 120,
   "trial_name": null,
   "trial_params": null