Training in progress, step 200, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5cb968af799165acf1cfa9ded37b1ef66cc0c047f680efd9d3f9e0669cb5f0c1
+oid sha256:80719f65a4c76f5f9549a9ff6b40c12ab753baa9b2dede5200e8eaf0ee485610
 size 4939116424

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:52fe44bbdbc149f43a4a3f05f9cfada2db0985da8fa1554981ed6616e0a9c909
+oid sha256:93baeb991618ed9cb503e7afa440c283da11219662d8b7e72afa7c5cdb049e3e
 size 4947390880

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5abe838d9f785fd0a874716143de87fdbdc4b78e71af4464450a4d88e1861857
+oid sha256:d8870def62712246e10267b52717c3817d3f0bf0bebf0ca06ac04e24b91d2483
 size 3590619888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2684d4a6449589eb2588954ce7795dbbb7a2529fddfe312248de6713f57bd5a6
-size 13688025904
+oid sha256:098efa6a35bbc23a589b905879b46e073faae5dd61dbde4fc20125cfc535b2c8
+size 13688025584

last-checkpoint/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f20d155a14d34cd1bb6d04e5de90f3224906e1758821edd752a8f1a9085a2db
+size 15024

last-checkpoint/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad18e870a176ca75a54f6620f83de92bdfd5a91302744d90bff8e5feae2fe0c5
+size 15024

last-checkpoint/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9009a52be47b75834407dc5e146ed5360e6f23a35bff27bab34ef6fb47df1661
+size 15024

last-checkpoint/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7fb494a08fd57e7c6f63f06826c872164986e81b271996be0496671f713bdcc3
+size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a673aaf85c0fe6b6c29cb8f3e7dbd829eef637110e4ad9a775f3fcf001c92591
+oid sha256:9cd11d413bc67bf01de9a1a006e9e7655be307353028b25f5b3c299e5b6b7a44
 size 1064

last-checkpoint/trainer_state.json

@@ -1,323 +1,175 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.05919786887672044,
+  "epoch": 1.8518518518518519,
   "eval_steps": 200,
-  "global_step": 400,
+  "global_step": 200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.0001479946721918011,
-      "eval_loss": 2.158451557159424,
-      "eval_runtime": 109.9644,
-      "eval_samples_per_second": 13.659,
-      "eval_steps_per_second": 6.829,
+      "epoch": 0.009259259259259259,
+      "eval_loss": 2.1662161350250244,
+      "eval_runtime": 31.5566,
+      "eval_samples_per_second": 47.565,
+      "eval_steps_per_second": 5.958,
       "step": 1
     },
     {
-      "epoch": 0.001479946721918011,
-      "grad_norm": 19.0,
-      "learning_rate": 1.6000000000000003e-05,
-      "loss": 1.8755,
+      "epoch": 0.09259259259259259,
+      "grad_norm": 1.75,
+      "learning_rate": 6.666666666666667e-05,
+      "loss": 1.857,
       "step": 10
     },
     {
-      "epoch": 0.002959893443836022,
-      "grad_norm": 15.75,
-      "learning_rate": 3.2000000000000005e-05,
-      "loss": 1.8991,
+      "epoch": 0.18518518518518517,
+      "grad_norm": 2.390625,
+      "learning_rate": 0.00013333333333333334,
+      "loss": 1.8324,
       "step": 20
     },
     {
-      "epoch": 0.0044398401657540325,
-      "grad_norm": 20.5,
-      "learning_rate": 4.8e-05,
-      "loss": 1.6921,
+      "epoch": 0.2777777777777778,
+      "grad_norm": 1.515625,
+      "learning_rate": 0.0002,
+      "loss": 1.866,
       "step": 30
     },
     {
-      "epoch": 0.005919786887672044,
-      "grad_norm": 21.25,
-      "learning_rate": 6.400000000000001e-05,
-      "loss": 1.7869,
+      "epoch": 0.37037037037037035,
+      "grad_norm": 1.421875,
+      "learning_rate": 0.00019984815164333163,
+      "loss": 1.974,
       "step": 40
     },
     {
-      "epoch": 0.007399733609590055,
-      "grad_norm": 29.0,
-      "learning_rate": 8e-05,
-      "loss": 1.2968,
+      "epoch": 0.46296296296296297,
+      "grad_norm": 1.28125,
+      "learning_rate": 0.00019939306773179497,
+      "loss": 2.0103,
       "step": 50
     },
     {
-      "epoch": 0.008879680331508065,
-      "grad_norm": 7.1875,
-      "learning_rate": 9.6e-05,
-      "loss": 1.9665,
+      "epoch": 0.5555555555555556,
+      "grad_norm": 1.296875,
+      "learning_rate": 0.00019863613034027224,
+      "loss": 2.0427,
       "step": 60
     },
     {
-      "epoch": 0.010359627053426078,
-      "grad_norm": 14.5625,
-      "learning_rate": 0.00011200000000000001,
-      "loss": 2.0639,
+      "epoch": 0.6481481481481481,
+      "grad_norm": 1.3125,
+      "learning_rate": 0.00019757963826274357,
+      "loss": 2.0967,
       "step": 70
     },
     {
-      "epoch": 0.011839573775344088,
-      "grad_norm": 21.25,
-      "learning_rate": 0.00012800000000000002,
-      "loss": 1.5221,
+      "epoch": 0.7407407407407407,
+      "grad_norm": 1.3515625,
+      "learning_rate": 0.00019622680003092503,
+      "loss": 2.1174,
       "step": 80
     },
     {
-      "epoch": 0.0133195204972621,
-      "grad_norm": 20.75,
-      "learning_rate": 0.000144,
-      "loss": 2.3197,
+      "epoch": 0.8333333333333334,
+      "grad_norm": 1.3515625,
+      "learning_rate": 0.00019458172417006347,
+      "loss": 2.109,
       "step": 90
     },
     {
-      "epoch": 0.01479946721918011,
-      "grad_norm": 132.0,
-      "learning_rate": 0.00016,
-      "loss": 2.2097,
+      "epoch": 0.9259259259259259,
+      "grad_norm": 1.25,
+      "learning_rate": 0.00019264940672148018,
+      "loss": 2.1218,
       "step": 100
     },
     {
-      "epoch": 0.01627941394109812,
-      "grad_norm": 21.0,
-      "learning_rate": 0.00017600000000000002,
-      "loss": 2.2899,
+      "epoch": 1.0185185185185186,
+      "grad_norm": 1.40625,
+      "learning_rate": 0.00019043571606975777,
+      "loss": 1.8774,
       "step": 110
     },
     {
-      "epoch": 0.01775936066301613,
-      "grad_norm": 15.625,
-      "learning_rate": 0.000192,
-      "loss": 2.4378,
+      "epoch": 1.1111111111111112,
+      "grad_norm": 1.21875,
+      "learning_rate": 0.0001879473751206489,
+      "loss": 0.9755,
       "step": 120
     },
     {
-      "epoch": 0.01923930738493414,
-      "grad_norm": 25.625,
-      "learning_rate": 0.0001999978128380225,
-      "loss": 2.581,
+      "epoch": 1.2037037037037037,
+      "grad_norm": 1.1484375,
+      "learning_rate": 0.00018519194088383273,
+      "loss": 0.9357,
       "step": 130
     },
     {
-      "epoch": 0.020719254106852155,
-      "grad_norm": 27.75,
-      "learning_rate": 0.0001999803161162393,
-      "loss": 2.7093,
+      "epoch": 1.2962962962962963,
+      "grad_norm": 1.234375,
+      "learning_rate": 0.0001821777815225245,
+      "loss": 0.9453,
       "step": 140
     },
     {
-      "epoch": 0.022199200828770166,
-      "grad_norm": 80.0,
-      "learning_rate": 0.00019994532573409262,
-      "loss": 3.7613,
+      "epoch": 1.3888888888888888,
+      "grad_norm": 1.1796875,
+      "learning_rate": 0.00017891405093963938,
+      "loss": 0.9413,
       "step": 150
     },
     {
-      "epoch": 0.023679147550688177,
-      "grad_norm": 26.0,
-      "learning_rate": 0.00019989284781388617,
-      "loss": 3.2043,
+      "epoch": 1.4814814814814814,
+      "grad_norm": 1.203125,
+      "learning_rate": 0.00017541066097768963,
+      "loss": 0.9678,
       "step": 160
     },
     {
-      "epoch": 0.025159094272606188,
-      "grad_norm": 16.125,
-      "learning_rate": 0.00019982289153773646,
-      "loss": 2.9456,
+      "epoch": 1.574074074074074,
+      "grad_norm": 1.0703125,
+      "learning_rate": 0.00017167825131684513,
+      "loss": 0.9576,
       "step": 170
     },
     {
-      "epoch": 0.0266390409945242,
-      "grad_norm": 18.25,
-      "learning_rate": 0.00019973546914596623,
-      "loss": 3.1087,
+      "epoch": 1.6666666666666665,
+      "grad_norm": 1.1484375,
+      "learning_rate": 0.00016772815716257412,
+      "loss": 0.9958,
       "step": 180
     },
     {
-      "epoch": 0.02811898771644221,
-      "grad_norm": 16.125,
-      "learning_rate": 0.00019963059593496268,
-      "loss": 2.9073,
+      "epoch": 1.7592592592592593,
+      "grad_norm": 1.1953125,
+      "learning_rate": 0.00016357237482099684,
+      "loss": 0.9805,
       "step": 190
     },
     {
-      "epoch": 0.02959893443836022,
-      "grad_norm": 55.5,
-      "learning_rate": 0.00019950829025450114,
-      "loss": 4.5937,
+      "epoch": 1.8518518518518519,
+      "grad_norm": 1.1875,
+      "learning_rate": 0.00015922352526649803,
+      "loss": 1.0055,
       "step": 200
     },
     {
-      "epoch": 0.02959893443836022,
-      "eval_loss": 3.860623359680176,
-      "eval_runtime": 106.7132,
-      "eval_samples_per_second": 14.075,
-      "eval_steps_per_second": 7.038,
+      "epoch": 1.8518518518518519,
+      "eval_loss": 2.0688600540161133,
+      "eval_runtime": 26.9652,
+      "eval_samples_per_second": 55.664,
+      "eval_steps_per_second": 6.972,
       "step": 200
-    },
-    {
-      "epoch": 0.03107888116027823,
-      "grad_norm": 13.625,
-      "learning_rate": 0.0001993685735045343,
-      "loss": 3.8042,
-      "step": 210
-    },
-    {
-      "epoch": 0.03255882788219624,
-      "grad_norm": 23.375,
-      "learning_rate": 0.0001992114701314478,
-      "loss": 3.0563,
-      "step": 220
-    },
-    {
-      "epoch": 0.03403877460411425,
-      "grad_norm": 20.125,
-      "learning_rate": 0.000199037007623783,
-      "loss": 3.5398,
-      "step": 230
-    },
-    {
-      "epoch": 0.03551872132603226,
-      "grad_norm": 44.75,
-      "learning_rate": 0.00019884521650742715,
-      "loss": 3.8845,
-      "step": 240
-    },
-    {
-      "epoch": 0.036998668047950274,
-      "grad_norm": 17.625,
-      "learning_rate": 0.00019863613034027224,
-      "loss": 3.6043,
-      "step": 250
-    },
-    {
-      "epoch": 0.03847861476986828,
-      "grad_norm": 13.375,
-      "learning_rate": 0.0001984097857063434,
-      "loss": 3.5133,
-      "step": 260
-    },
-    {
-      "epoch": 0.039958561491786296,
-      "grad_norm": 43.25,
-      "learning_rate": 0.0001981662222093976,
-      "loss": 3.1527,
-      "step": 270
-    },
-    {
-      "epoch": 0.04143850821370431,
-      "grad_norm": 26.625,
-      "learning_rate": 0.00019790548246599447,
-      "loss": 3.2272,
-      "step": 280
-    },
-    {
-      "epoch": 0.04291845493562232,
-      "grad_norm": 31.625,
-      "learning_rate": 0.00019762761209803927,
-      "loss": 3.7942,
-      "step": 290
-    },
-    {
-      "epoch": 0.04439840165754033,
-      "grad_norm": 70.0,
-      "learning_rate": 0.0001973326597248006,
-      "loss": 4.5742,
-      "step": 300
-    },
-    {
-      "epoch": 0.04587834837945834,
-      "grad_norm": 20.125,
-      "learning_rate": 0.00019702067695440332,
-      "loss": 3.939,
-      "step": 310
-    },
-    {
-      "epoch": 0.04735829510137635,
-      "grad_norm": 22.25,
-      "learning_rate": 0.00019669171837479873,
-      "loss": 3.4604,
-      "step": 320
-    },
-    {
-      "epoch": 0.04883824182329436,
-      "grad_norm": 14.8125,
-      "learning_rate": 0.00019634584154421317,
-      "loss": 3.731,
-      "step": 330
-    },
-    {
-      "epoch": 0.050318188545212375,
-      "grad_norm": 23.75,
-      "learning_rate": 0.00019598310698107702,
-      "loss": 3.3564,
-      "step": 340
-    },
-    {
-      "epoch": 0.05179813526713038,
-      "grad_norm": 31.875,
-      "learning_rate": 0.00019560357815343577,
-      "loss": 3.7669,
-      "step": 350
-    },
-    {
-      "epoch": 0.0532780819890484,
-      "grad_norm": 7.40625,
-      "learning_rate": 0.00019520732146784491,
-      "loss": 3.9271,
-      "step": 360
-    },
-    {
-      "epoch": 0.054758028710966404,
-      "grad_norm": 12.8125,
-      "learning_rate": 0.0001947944062577507,
-      "loss": 3.8324,
-      "step": 370
-    },
-    {
-      "epoch": 0.05623797543288442,
-      "grad_norm": 20.5,
-      "learning_rate": 0.00019436490477135878,
-      "loss": 3.7409,
-      "step": 380
-    },
-    {
-      "epoch": 0.057717922154802426,
-      "grad_norm": 82.5,
-      "learning_rate": 0.00019391889215899299,
-      "loss": 3.8351,
-      "step": 390
-    },
-    {
-      "epoch": 0.05919786887672044,
-      "grad_norm": 40.0,
-      "learning_rate": 0.0001934564464599461,
-      "loss": 4.4515,
-      "step": 400
-    },
-    {
-      "epoch": 0.05919786887672044,
-      "eval_loss": 4.6751227378845215,
-      "eval_runtime": 106.1002,
-      "eval_samples_per_second": 14.156,
-      "eval_steps_per_second": 7.078,
-      "step": 400
     }
   ],
   "logging_steps": 10,
-  "max_steps": 2500,
+  "max_steps": 600,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 1,
-  "save_steps": 400,
+  "num_train_epochs": 6,
+  "save_steps": 200,
   "stateful_callbacks": {
     "TrainerControl": {
       "args": {
@@ -330,7 +182,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.511585861514035e+16,
+  "total_flos": 1.2990695522435072e+17,
   "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 sha256:2bf6f06544da4fe32a2b63dd4d1f2f74f2cd1ba39da1c617fe85338c0397a8ef
+oid sha256:ba673725c24b475995eb203939e8d5642b3dae413ae05b5e3595152a67bc2b87
 size 6840