Training in progress, step 12000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c8c712d5d70c820407b6c94c687368c68becb6d6d84dc3a2bcdc4617b373e019
+oid sha256:eff0b817ad62fcc65fc9dee0438d878ab8e71018c1b539677298cd06c0087a52
 size 470900144

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cc21ebc10c308798dd2c8f0f7afbcff41dd6ebca458838faddce47a52cf87151
+oid sha256:1c3994c87e1c68f3619f1f97be5d888a519060a20b7771be79e62ace5774a670
 size 942082751

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:67ccb55173fadea7c0282f3777765b577d8947fd4a9edb2a09d0d2467a98377e
+oid sha256:d244da687768ca9b4a58837838181e8b205496715e3f8cb878b13a489eff3806
 size 14645

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:022915fa8ac65fae0f13853519b8aa7ee79efd632a399c1f64c6b87bab0b057a
+oid sha256:ae029a8e6af9f014c9ef8b713fcd28cef1f184648ddde977ce75efc89ca9a242
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd0ab4f2ddae6f03ec40afd304de8313743a9194ba7cdd247fd992e5b4fb480a
+oid sha256:9d19e7633d39b5670a0b0a7c3ebfe8f61674a68c2c0192b1e58c8ed35834a040
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.0862215282256695,
+  "epoch": 1.6293492650802812,
   "eval_steps": 500,
-  "global_step": 8000,
+  "global_step": 12000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -288,6 +288,146 @@
       "learning_rate": 2.8380885453267747e-05,
       "loss": 2.185189056396484,
       "step": 8000
+    },
+    {
+      "epoch": 1.1133779150684002,
+      "grad_norm": 0.8224326968193054,
+      "learning_rate": 2.7537596626844694e-05,
+      "loss": 2.187441101074219,
+      "step": 8200
+    },
+    {
+      "epoch": 1.1405343019111307,
+      "grad_norm": 0.8320621848106384,
+      "learning_rate": 2.6694307800421644e-05,
+      "loss": 2.1721092224121095,
+      "step": 8400
+    },
+    {
+      "epoch": 1.1676906887538614,
+      "grad_norm": 0.8610696196556091,
+      "learning_rate": 2.5851018973998595e-05,
+      "loss": 2.178549957275391,
+      "step": 8600
+    },
+    {
+      "epoch": 1.1948470755965919,
+      "grad_norm": 0.8490989208221436,
+      "learning_rate": 2.5007730147575545e-05,
+      "loss": 2.1787890625,
+      "step": 8800
+    },
+    {
+      "epoch": 1.2220034624393223,
+      "grad_norm": 0.843935489654541,
+      "learning_rate": 2.4164441321152495e-05,
+      "loss": 2.1710661315917967,
+      "step": 9000
+    },
+    {
+      "epoch": 1.249159849282053,
+      "grad_norm": 0.831099808216095,
+      "learning_rate": 2.3321152494729446e-05,
+      "loss": 2.1735246276855467,
+      "step": 9200
+    },
+    {
+      "epoch": 1.2763162361247837,
+      "grad_norm": 0.8413128852844238,
+      "learning_rate": 2.2477863668306396e-05,
+      "loss": 2.1660111999511718,
+      "step": 9400
+    },
+    {
+      "epoch": 1.3034726229675142,
+      "grad_norm": 0.8495444655418396,
+      "learning_rate": 2.1634574841883346e-05,
+      "loss": 2.169669647216797,
+      "step": 9600
+    },
+    {
+      "epoch": 1.3306290098102447,
+      "grad_norm": 0.8403661847114563,
+      "learning_rate": 2.0791286015460293e-05,
+      "loss": 2.1661985778808592,
+      "step": 9800
+    },
+    {
+      "epoch": 1.3577853966529754,
+      "grad_norm": 0.8322446346282959,
+      "learning_rate": 1.9947997189037247e-05,
+      "loss": 2.1720236206054686,
+      "step": 10000
+    },
+    {
+      "epoch": 1.3849417834957058,
+      "grad_norm": 0.8749573826789856,
+      "learning_rate": 1.9104708362614197e-05,
+      "loss": 2.1759602355957033,
+      "step": 10200
+    },
+    {
+      "epoch": 1.4120981703384365,
+      "grad_norm": 0.8350988030433655,
+      "learning_rate": 1.8261419536191144e-05,
+      "loss": 2.1585594177246095,
+      "step": 10400
+    },
+    {
+      "epoch": 1.439254557181167,
+      "grad_norm": 0.8635809421539307,
+      "learning_rate": 1.7418130709768098e-05,
+      "loss": 2.160636138916016,
+      "step": 10600
+    },
+    {
+      "epoch": 1.4664109440238975,
+      "grad_norm": 0.8428000211715698,
+      "learning_rate": 1.6574841883345048e-05,
+      "loss": 2.155465545654297,
+      "step": 10800
+    },
+    {
+      "epoch": 1.4935673308666282,
+      "grad_norm": 0.8638054728507996,
+      "learning_rate": 1.5731553056921995e-05,
+      "loss": 2.168834991455078,
+      "step": 11000
+    },
+    {
+      "epoch": 1.5207237177093589,
+      "grad_norm": 0.8284506797790527,
+      "learning_rate": 1.4888264230498947e-05,
+      "loss": 2.1634239196777343,
+      "step": 11200
+    },
+    {
+      "epoch": 1.5478801045520894,
+      "grad_norm": 0.8089849352836609,
+      "learning_rate": 1.4044975404075897e-05,
+      "loss": 2.153994903564453,
+      "step": 11400
+    },
+    {
+      "epoch": 1.5750364913948198,
+      "grad_norm": 0.849999725818634,
+      "learning_rate": 1.3201686577652846e-05,
+      "loss": 2.160932159423828,
+      "step": 11600
+    },
+    {
+      "epoch": 1.6021928782375505,
+      "grad_norm": 0.8596501350402832,
+      "learning_rate": 1.2358397751229796e-05,
+      "loss": 2.1521231079101564,
+      "step": 11800
+    },
+    {
+      "epoch": 1.6293492650802812,
+      "grad_norm": 0.8179290890693665,
+      "learning_rate": 1.1515108924806746e-05,
+      "loss": 2.1560073852539063,
+      "step": 12000
     }
   ],
   "logging_steps": 200,
@@ -307,7 +447,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.462240400198861e+16,
+  "total_flos": 6.693482621357261e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null