Training in progress, step 50, checkpoint

last-checkpoint/model-00001-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3927460c5be93662d361e0652583a47649298ad5ffbd120a40a71773cd207aca
+oid sha256:2cba411d16e4182625bec2426d023cac727ecf315cd3e9cb0890596aef3184f2
 size 4943178720

last-checkpoint/model-00002-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff66447d15a6da7419c9fdaae48f2df66754bb12387f3096358548645c8277d0
+oid sha256:89987a8836c2e2fb6735a4b1a7b77865034434b5df1fadbb31f324f581dc5d52
 size 4999819336

last-checkpoint/model-00003-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:76dac0c69be005ed49e49458992a7fd3212ea772b71ced9d506db8a08caf089e
+oid sha256:4dff5838d21e7ac63b425d64836ca0fa68b49528511a23a55761f6370b8537eb
 size 4540532728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3cd36532398aa526267b94731fe2352a0a0518b2a340bece982f3f2bd3518fba
+oid sha256:7ec7abc023d7fe3c58d923d6ad40c09929be577418d3d8532673ec5d0941dbca
 size 14710155092

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b1b9f0479324b9b6f1edd389fcd7b47638e6980c8cd3fbd0487a8e891e0040f
+oid sha256:7c5c1df0637047eea0b1eabe544fcb11ca3e5a4720f18459462a89f9826e9168
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f2227e6ae47e426954edaad47574e1686726548477230bedd0b4f0bf3940388
+oid sha256:3353489b38799fd56e115bb7a4e2a7a61242a09d303dca9e218c08878b9b8728
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.35545023696682465,
-  "eval_steps": 50,
-  "global_step": 150,
+  "epoch": 0.11848341232227488,
+  "eval_steps": 100,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -11,139 +11,45 @@
     {
       "epoch": 0.002369668246445498,
       "eval_loss": 1.879074215888977,
-      "eval_runtime": 110.6251,
-      "eval_samples_per_second": 13.568,
-      "eval_steps_per_second": 6.789,
+      "eval_runtime": 109.3265,
+      "eval_samples_per_second": 13.73,
+      "eval_steps_per_second": 6.869,
       "step": 1
     },
     {
       "epoch": 0.023696682464454975,
-      "grad_norm": 23.875,
+      "grad_norm": 23.75,
       "learning_rate": 1.6000000000000003e-05,
       "loss": 1.6552,
       "step": 10
     },
     {
       "epoch": 0.04739336492890995,
-      "grad_norm": 20.5,
+      "grad_norm": 20.375,
       "learning_rate": 3.2000000000000005e-05,
-      "loss": 1.7504,
+      "loss": 1.7472,
       "step": 20
     },
     {
       "epoch": 0.07109004739336493,
-      "grad_norm": 23.5,
+      "grad_norm": 24.25,
       "learning_rate": 4.8e-05,
-      "loss": 1.9291,
+      "loss": 1.9292,
       "step": 30
     },
     {
       "epoch": 0.0947867298578199,
-      "grad_norm": 25.875,
+      "grad_norm": 107.5,
       "learning_rate": 6.400000000000001e-05,
-      "loss": 2.1915,
+      "loss": 2.3565,
       "step": 40
     },
     {
       "epoch": 0.11848341232227488,
-      "grad_norm": 1208.0,
+      "grad_norm": 41.0,
       "learning_rate": 8e-05,
-      "loss": 2.6683,
+      "loss": 2.6061,
       "step": 50
-    },
-    {
-      "epoch": 0.11848341232227488,
-      "eval_loss": 3.161129951477051,
-      "eval_runtime": 110.3687,
-      "eval_samples_per_second": 13.6,
-      "eval_steps_per_second": 6.804,
-      "step": 50
-    },
-    {
-      "epoch": 0.14218009478672985,
-      "grad_norm": 43.25,
-      "learning_rate": 9.6e-05,
-      "loss": 3.2101,
-      "step": 60
-    },
-    {
-      "epoch": 0.16587677725118483,
-      "grad_norm": 55.5,
-      "learning_rate": 0.00011200000000000001,
-      "loss": 3.2406,
-      "step": 70
-    },
-    {
-      "epoch": 0.1895734597156398,
-      "grad_norm": 49.25,
-      "learning_rate": 0.00012800000000000002,
-      "loss": 3.4937,
-      "step": 80
-    },
-    {
-      "epoch": 0.2132701421800948,
-      "grad_norm": 808.0,
-      "learning_rate": 0.000144,
-      "loss": 3.9683,
-      "step": 90
-    },
-    {
-      "epoch": 0.23696682464454977,
-      "grad_norm": 201.0,
-      "learning_rate": 0.00016,
-      "loss": 4.5857,
-      "step": 100
-    },
-    {
-      "epoch": 0.23696682464454977,
-      "eval_loss": 4.856403827667236,
-      "eval_runtime": 110.2664,
-      "eval_samples_per_second": 13.612,
-      "eval_steps_per_second": 6.811,
-      "step": 100
-    },
-    {
-      "epoch": 0.26066350710900477,
-      "grad_norm": 87.5,
-      "learning_rate": 0.00017600000000000002,
-      "loss": 4.4561,
-      "step": 110
-    },
-    {
-      "epoch": 0.2843601895734597,
-      "grad_norm": 137.0,
-      "learning_rate": 0.000192,
-      "loss": 4.4283,
-      "step": 120
-    },
-    {
-      "epoch": 0.3080568720379147,
-      "grad_norm": 344.0,
-      "learning_rate": 0.0001999978128380225,
-      "loss": 5.9584,
-      "step": 130
-    },
-    {
-      "epoch": 0.33175355450236965,
-      "grad_norm": 65.0,
-      "learning_rate": 0.0001999803161162393,
-      "loss": 6.4638,
-      "step": 140
-    },
-    {
-      "epoch": 0.35545023696682465,
-      "grad_norm": 114.5,
-      "learning_rate": 0.00019994532573409262,
-      "loss": 7.2027,
-      "step": 150
-    },
-    {
-      "epoch": 0.35545023696682465,
-      "eval_loss": 8.472414016723633,
-      "eval_runtime": 110.8104,
-      "eval_samples_per_second": 13.546,
-      "eval_steps_per_second": 6.777,
-      "step": 150
     }
   ],
   "logging_steps": 10,
@@ -163,7 +69,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.62127675768832e+16,
+  "total_flos": 8737589192294400.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c6d395a8e654802d6385ed1ba25fef8e0604b0103cee44f7dd323903de4959d9
+oid sha256:eb00fcbb1b223563dc860df53b82c11283bd077e6f853a13396f3fff5da17666
 size 6776