Training in progress, step 97800

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b2b71a1693c4833d0a4fa56ef72c0a86bde99cc4cd84faa870ab826523bd961
+oid sha256:aec0c1d18defd241431f12919f56311e5a5a2b33ee98aff0675e2d1054db73a3
 size 1715561468

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:51c0349e11e2f94819ee46dbe2e04d04cc011a97f9f2124c8be293defb0a206a
+oid sha256:d1ec0449a02acf3e70b6f1fd6fbb2ea2224f1607e2a52b78112be63d1a623ec3
 size 3431474364

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:be13e37a24a07e10fc68f5c2cd4ef1d31eaee86b299d03fbc1b4e1c4f98603ae
+oid sha256:3f22dde64bed4a150bba9fae975b5ff2db4d79f2cc7c992c6da344d97f930b61
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d8a59bea0974691465530372450279c1418d6621c1543f23f4ad569da87f652
+oid sha256:72114cb302bd561c7ea851b1b8082add5139795f45804ba466465e1f30e93de9
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 4.3849402462036124,
+  "epoch": 4.178272980501393,
   "eval_steps": 1000,
-  "global_step": 97600,
+  "global_step": 93000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -4006,199 +4006,6 @@
       "eval_samples_per_second": 9.146,
       "eval_steps_per_second": 0.143,
       "step": 93000
-    },
-    {
-      "epoch": 4.187258513792794,
-      "grad_norm": 18.494911193847656,
-      "learning_rate": 4.913983787235996e-05,
-      "loss": 0.5905,
-      "step": 93200
-    },
-    {
-      "epoch": 4.196244047084194,
-      "grad_norm": 4.566243648529053,
-      "learning_rate": 4.913616346215057e-05,
-      "loss": 0.5712,
-      "step": 93400
-    },
-    {
-      "epoch": 4.205229580375596,
-      "grad_norm": 5.748531818389893,
-      "learning_rate": 4.9132481358518735e-05,
-      "loss": 0.558,
-      "step": 93600
-    },
-    {
-      "epoch": 4.214215113666996,
-      "grad_norm": 3.77885365486145,
-      "learning_rate": 4.9128791562638096e-05,
-      "loss": 0.5927,
-      "step": 93800
-    },
-    {
-      "epoch": 4.223200646958397,
-      "grad_norm": 2.6284022331237793,
-      "learning_rate": 4.9125094075684805e-05,
-      "loss": 0.5953,
-      "step": 94000
-    },
-    {
-      "epoch": 4.223200646958397,
-      "eval_loss": 2.712245225906372,
-      "eval_runtime": 1088.8302,
-      "eval_samples_per_second": 9.096,
-      "eval_steps_per_second": 0.142,
-      "step": 94000
-    },
-    {
-      "epoch": 4.232186180249798,
-      "grad_norm": 5.8867645263671875,
-      "learning_rate": 4.9121388898837415e-05,
-      "loss": 0.5895,
-      "step": 94200
-    },
-    {
-      "epoch": 4.241171713541199,
-      "grad_norm": 6.118598937988281,
-      "learning_rate": 4.911767603327698e-05,
-      "loss": 0.6138,
-      "step": 94400
-    },
-    {
-      "epoch": 4.250157246832599,
-      "grad_norm": 7.058086395263672,
-      "learning_rate": 4.911395548018696e-05,
-      "loss": 0.5921,
-      "step": 94600
-    },
-    {
-      "epoch": 4.259142780124001,
-      "grad_norm": 6.587648391723633,
-      "learning_rate": 4.911022724075329e-05,
-      "loss": 0.5778,
-      "step": 94800
-    },
-    {
-      "epoch": 4.268128313415401,
-      "grad_norm": 1.6069397926330566,
-      "learning_rate": 4.910649131616435e-05,
-      "loss": 0.6262,
-      "step": 95000
-    },
-    {
-      "epoch": 4.268128313415401,
-      "eval_loss": 2.6547911167144775,
-      "eval_runtime": 1085.8261,
-      "eval_samples_per_second": 9.121,
-      "eval_steps_per_second": 0.143,
-      "step": 95000
-    },
-    {
-      "epoch": 4.277113846706802,
-      "grad_norm": 6.686661243438721,
-      "learning_rate": 4.910274770761096e-05,
-      "loss": 0.5864,
-      "step": 95200
-    },
-    {
-      "epoch": 4.286099379998203,
-      "grad_norm": 7.897719860076904,
-      "learning_rate": 4.909899641628641e-05,
-      "loss": 0.5884,
-      "step": 95400
-    },
-    {
-      "epoch": 4.295084913289604,
-      "grad_norm": 7.400073528289795,
-      "learning_rate": 4.9095237443386435e-05,
-      "loss": 0.6021,
-      "step": 95600
-    },
-    {
-      "epoch": 4.3040704465810045,
-      "grad_norm": 4.220474720001221,
-      "learning_rate": 4.9091470790109196e-05,
-      "loss": 0.5518,
-      "step": 95800
-    },
-    {
-      "epoch": 4.313055979872406,
-      "grad_norm": 1.6574774980545044,
-      "learning_rate": 4.908769645765532e-05,
-      "loss": 0.5867,
-      "step": 96000
-    },
-    {
-      "epoch": 4.313055979872406,
-      "eval_loss": 2.691925525665283,
-      "eval_runtime": 1089.0317,
-      "eval_samples_per_second": 9.094,
-      "eval_steps_per_second": 0.142,
-      "step": 96000
-    },
-    {
-      "epoch": 4.322041513163806,
-      "grad_norm": 3.5609164237976074,
-      "learning_rate": 4.908391444722787e-05,
-      "loss": 0.5803,
-      "step": 96200
-    },
-    {
-      "epoch": 4.331027046455207,
-      "grad_norm": 3.427290201187134,
-      "learning_rate": 4.908012476003239e-05,
-      "loss": 0.554,
-      "step": 96400
-    },
-    {
-      "epoch": 4.340012579746608,
-      "grad_norm": 52.728878021240234,
-      "learning_rate": 4.907632739727682e-05,
-      "loss": 0.5962,
-      "step": 96600
-    },
-    {
-      "epoch": 4.348998113038009,
-      "grad_norm": 12.754006385803223,
-      "learning_rate": 4.907252236017159e-05,
-      "loss": 0.5742,
-      "step": 96800
-    },
-    {
-      "epoch": 4.3579836463294095,
-      "grad_norm": 8.12136173248291,
-      "learning_rate": 4.9068709649929544e-05,
-      "loss": 0.6085,
-      "step": 97000
-    },
-    {
-      "epoch": 4.3579836463294095,
-      "eval_loss": 2.6768929958343506,
-      "eval_runtime": 1090.8411,
-      "eval_samples_per_second": 9.079,
-      "eval_steps_per_second": 0.142,
-      "step": 97000
-    },
-    {
-      "epoch": 4.366969179620811,
-      "grad_norm": 5.45872688293457,
-      "learning_rate": 4.9064889267766e-05,
-      "loss": 0.5137,
-      "step": 97200
-    },
-    {
-      "epoch": 4.375954712912211,
-      "grad_norm": 3.9804370403289795,
-      "learning_rate": 4.9061061214898707e-05,
-      "loss": 0.5567,
-      "step": 97400
-    },
-    {
-      "epoch": 4.3849402462036124,
-      "grad_norm": 29.226791381835938,
-      "learning_rate": 4.9057225492547846e-05,
-      "loss": 0.5694,
-      "step": 97600
     }
   ],
   "logging_steps": 200,
@@ -4218,7 +4025,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.3991980042616832e+18,
+  "total_flos": 1.333252196683776e+18,
   "train_batch_size": 6,
   "trial_name": null,
   "trial_params": null

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b2b71a1693c4833d0a4fa56ef72c0a86bde99cc4cd84faa870ab826523bd961
+oid sha256:7ff2dae35f81010c72af01f07977963be57010375af5f3bff3c7967ef1499de0
 size 1715561468