Training in progress, step 14000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:38983cc6baa199b78ad222dae4c477c4bd0c63e2458372366630348ee28383b5
+oid sha256:54139b974ddfae98ee7fb4da2695b05278ea502ebc86824b3e1c4f49c129b297
 size 579824888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7fd8341a68b63315868b34bd0e54e5f6c54b4a66537f640753aed597e0d3b48d
+oid sha256:ff8e73939ebcb2d4e5ba75a94606f6611749ef65cbf2555cdefc0014ed49429b
 size 1159794763

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d31404d4c654929d8c8604a09997c74ec2ccd4b35e0d5562c9b8d160dc81e06
+oid sha256:4379e0a27d0683dd964c1d70a99193598c03adb1d5cf2808558afd18cfc5f420
 size 14645

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:51b5657716e2096af61b1cdab76b9fd3dc4ab393f10b4ad41400692973ae8e3f
+oid sha256:9fe9a6301d1d1aeac29e6021bcb10e2a37481f63ed32dd3e17e4ef1f6ab45e17
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.24,
+  "epoch": 0.28,
   "eval_steps": 1000,
-  "global_step": 12000,
+  "global_step": 14000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -956,6 +956,164 @@
       "eval_samples_per_second": 290.897,
       "eval_steps_per_second": 18.284,
       "step": 12000
+    },
+    {
+      "epoch": 0.242,
+      "grad_norm": 0.1405150443315506,
+      "learning_rate": 0.0008648077066991736,
+      "loss": 3.527177734375,
+      "step": 12100
+    },
+    {
+      "epoch": 0.244,
+      "grad_norm": 0.16479545831680298,
+      "learning_rate": 0.0008626456096552858,
+      "loss": 3.5393338012695312,
+      "step": 12200
+    },
+    {
+      "epoch": 0.246,
+      "grad_norm": 0.1583888679742813,
+      "learning_rate": 0.0008604691096960961,
+      "loss": 3.5796047973632814,
+      "step": 12300
+    },
+    {
+      "epoch": 0.248,
+      "grad_norm": 0.17304493486881256,
+      "learning_rate": 0.0008582782932639702,
+      "loss": 3.591195068359375,
+      "step": 12400
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 0.15857121348381042,
+      "learning_rate": 0.0008560732473698707,
+      "loss": 3.584400634765625,
+      "step": 12500
+    },
+    {
+      "epoch": 0.252,
+      "grad_norm": 0.14658208191394806,
+      "learning_rate": 0.0008538540595899008,
+      "loss": 3.589564208984375,
+      "step": 12600
+    },
+    {
+      "epoch": 0.254,
+      "grad_norm": 0.143401101231575,
+      "learning_rate": 0.0008516208180618252,
+      "loss": 3.5824600219726563,
+      "step": 12700
+    },
+    {
+      "epoch": 0.256,
+      "grad_norm": 0.16244202852249146,
+      "learning_rate": 0.0008493736114815718,
+      "loss": 3.574875793457031,
+      "step": 12800
+    },
+    {
+      "epoch": 0.258,
+      "grad_norm": 0.1520756632089615,
+      "learning_rate": 0.0008471125290997063,
+      "loss": 3.568282165527344,
+      "step": 12900
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 0.1582706868648529,
+      "learning_rate": 0.00084483766071789,
+      "loss": 3.5930340576171873,
+      "step": 13000
+    },
+    {
+      "epoch": 0.26,
+      "eval_accuracy": 0.35929186944409996,
+      "eval_loss": 3.5190227031707764,
+      "eval_runtime": 6.3791,
+      "eval_samples_per_second": 304.275,
+      "eval_steps_per_second": 19.125,
+      "step": 13000
+    },
+    {
+      "epoch": 0.262,
+      "grad_norm": 0.17478469014167786,
+      "learning_rate": 0.0008425490966853113,
+      "loss": 3.5665899658203126,
+      "step": 13100
+    },
+    {
+      "epoch": 0.264,
+      "grad_norm": 0.15228988230228424,
+      "learning_rate": 0.0008402469278950989,
+      "loss": 3.5444100952148436,
+      "step": 13200
+    },
+    {
+      "epoch": 0.266,
+      "grad_norm": 0.15244163572788239,
+      "learning_rate": 0.0008379312457807102,
+      "loss": 3.5695867919921875,
+      "step": 13300
+    },
+    {
+      "epoch": 0.268,
+      "grad_norm": 0.15935847163200378,
+      "learning_rate": 0.0008356021423123017,
+      "loss": 3.5604925537109375,
+      "step": 13400
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 0.15347428619861603,
+      "learning_rate": 0.000833259709993075,
+      "loss": 3.5551889038085935,
+      "step": 13500
+    },
+    {
+      "epoch": 0.272,
+      "grad_norm": 0.21459928154945374,
+      "learning_rate": 0.0008309040418556038,
+      "loss": 3.550736389160156,
+      "step": 13600
+    },
+    {
+      "epoch": 0.274,
+      "grad_norm": 0.17246893048286438,
+      "learning_rate": 0.0008285352314581378,
+      "loss": 3.5650180053710936,
+      "step": 13700
+    },
+    {
+      "epoch": 0.276,
+      "grad_norm": 0.16454122960567474,
+      "learning_rate": 0.0008261533728808883,
+      "loss": 3.549154968261719,
+      "step": 13800
+    },
+    {
+      "epoch": 0.278,
+      "grad_norm": 0.14885519444942474,
+      "learning_rate": 0.000823758560722291,
+      "loss": 3.5430950927734375,
+      "step": 13900
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 0.1521039605140686,
+      "learning_rate": 0.0008213508900952489,
+      "loss": 3.547527160644531,
+      "step": 14000
+    },
+    {
+      "epoch": 0.28,
+      "eval_accuracy": 0.36159261824608735,
+      "eval_loss": 3.4961202144622803,
+      "eval_runtime": 6.3742,
+      "eval_samples_per_second": 304.507,
+      "eval_steps_per_second": 19.14,
+      "step": 14000
     }
   ],
   "logging_steps": 100,
@@ -975,7 +1133,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.7039530401792e+17,
+  "total_flos": 5.4879452135424e+17,
   "train_batch_size": 120,
   "trial_name": null,
   "trial_params": null