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 sha256:7857b1437a88ff9e1fdaa0b6c2e3c4daf6b6387ea38830b6e73c5c06033c3150
+oid sha256:0d5991d4ae0fc94498a8143cbe4998a750029e51f58a03fa7d87196dd90323f4
 size 4943178720

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd52fbfc22254e7e1622049afc0254da299acce2aa1340ae8381b441117fb64f
+oid sha256:ab0adf5e4a12d0566d1af6170cc37600bf554158b9960ce331bbf55161988fd1
 size 4999819336

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d885d8c8c5995e84f01d8df318ab80138e6b735dd47ba729a289f2cd292dafe
+oid sha256:8c1d5eeee2a3d4aff325f9aa208ce5126187018a83ea8147fea0efdee4117a54
 size 4540532728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dcdf990af1fbeae7a7ccd40f7824862f8691ea0ac3ffde923eb0be58dca9f806
+oid sha256:541203c5d442071eaec535dae26efc2cf78294860f7e1ac99066f4215885bd58
 size 14710155092

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b1b9f0479324b9b6f1edd389fcd7b47638e6980c8cd3fbd0487a8e891e0040f
+oid sha256:455445cc351d1d9c0932fce6221afb99c553d40bbefe6e459ef4b63ef6e54132
 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,
+  "epoch": 0.11848341232227488,
   "eval_steps": 50,
-  "global_step": 150,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -11,139 +11,53 @@
     {
       "epoch": 0.002369668246445498,
       "eval_loss": 1.879074215888977,
-      "eval_runtime": 110.3924,
-      "eval_samples_per_second": 13.597,
-      "eval_steps_per_second": 6.803,
+      "eval_runtime": 110.6251,
+      "eval_samples_per_second": 13.568,
+      "eval_steps_per_second": 6.789,
       "step": 1
     },
     {
       "epoch": 0.023696682464454975,
-      "grad_norm": 48.75,
+      "grad_norm": 23.875,
       "learning_rate": 1.6000000000000003e-05,
-      "loss": 1.6549,
+      "loss": 1.6552,
       "step": 10
     },
     {
       "epoch": 0.04739336492890995,
-      "grad_norm": 22.125,
+      "grad_norm": 20.5,
       "learning_rate": 3.2000000000000005e-05,
-      "loss": 1.7478,
+      "loss": 1.7504,
       "step": 20
     },
     {
       "epoch": 0.07109004739336493,
-      "grad_norm": 22.875,
+      "grad_norm": 23.5,
       "learning_rate": 4.8e-05,
-      "loss": 1.9228,
+      "loss": 1.9291,
       "step": 30
     },
     {
       "epoch": 0.0947867298578199,
-      "grad_norm": 30.0,
+      "grad_norm": 25.875,
       "learning_rate": 6.400000000000001e-05,
-      "loss": 2.186,
+      "loss": 2.1915,
       "step": 40
     },
     {
       "epoch": 0.11848341232227488,
-      "grad_norm": 30.25,
+      "grad_norm": 1208.0,
       "learning_rate": 8e-05,
-      "loss": 2.7775,
+      "loss": 2.6683,
       "step": 50
     },
     {
       "epoch": 0.11848341232227488,
-      "eval_loss": 2.7163915634155273,
-      "eval_runtime": 110.023,
-      "eval_samples_per_second": 13.643,
-      "eval_steps_per_second": 6.826,
+      "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": 88.0,
-      "learning_rate": 9.6e-05,
-      "loss": 3.0907,
-      "step": 60
-    },
-    {
-      "epoch": 0.16587677725118483,
-      "grad_norm": 54.25,
-      "learning_rate": 0.00011200000000000001,
-      "loss": 3.2869,
-      "step": 70
-    },
-    {
-      "epoch": 0.1895734597156398,
-      "grad_norm": 75.5,
-      "learning_rate": 0.00012800000000000002,
-      "loss": 3.5309,
-      "step": 80
-    },
-    {
-      "epoch": 0.2132701421800948,
-      "grad_norm": 72.5,
-      "learning_rate": 0.000144,
-      "loss": 3.6509,
-      "step": 90
-    },
-    {
-      "epoch": 0.23696682464454977,
-      "grad_norm": 70.0,
-      "learning_rate": 0.00016,
-      "loss": 3.7776,
-      "step": 100
-    },
-    {
-      "epoch": 0.23696682464454977,
-      "eval_loss": 3.771571636199951,
-      "eval_runtime": 110.614,
-      "eval_samples_per_second": 13.57,
-      "eval_steps_per_second": 6.789,
-      "step": 100
-    },
-    {
-      "epoch": 0.26066350710900477,
-      "grad_norm": 47.0,
-      "learning_rate": 0.00017600000000000002,
-      "loss": 4.0304,
-      "step": 110
-    },
-    {
-      "epoch": 0.2843601895734597,
-      "grad_norm": 94.5,
-      "learning_rate": 0.000192,
-      "loss": 5.1359,
-      "step": 120
-    },
-    {
-      "epoch": 0.3080568720379147,
-      "grad_norm": 244.0,
-      "learning_rate": 0.0001999978128380225,
-      "loss": 5.2136,
-      "step": 130
-    },
-    {
-      "epoch": 0.33175355450236965,
-      "grad_norm": 74.0,
-      "learning_rate": 0.0001999803161162393,
-      "loss": 5.6738,
-      "step": 140
-    },
-    {
-      "epoch": 0.35545023696682465,
-      "grad_norm": 22.375,
-      "learning_rate": 0.00019994532573409262,
-      "loss": 5.4572,
-      "step": 150
-    },
-    {
-      "epoch": 0.35545023696682465,
-      "eval_loss": 5.4177703857421875,
-      "eval_runtime": 110.5332,
-      "eval_samples_per_second": 13.58,
-      "eval_steps_per_second": 6.794,
-      "step": 150
     }
   ],
   "logging_steps": 10,
@@ -163,7 +77,7 @@
       "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 sha256:275470b754135bb198fe3e1b0d3b0332d2114e36c8e4ac84c30e44373e277d5a
+oid sha256:c6d395a8e654802d6385ed1ba25fef8e0604b0103cee44f7dd323903de4959d9
 size 6776