Training in progress, step 1200, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:613c90b1b4ae60a4b8ad63967dbfa78734fe3378c04edf9596e0ee759ad29869
+oid sha256:fc1ae1c044492419628f6d88c645e0dda5140604c950945a6b2f85e79af26bbb
 size 393799132

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8627faeeee44b88dfb68093e29393176942377271d54882f3552104fd3a8ae5e
+oid sha256:66db0c308e6c6cf0284bcd03534d71001f4850fb1c2d80c80a82a96f2dd6862f
 size 112281209

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:66dec4af3c2d8dc6ca18e985bf95361c8988f2f9d378886c25eb80a73759e237
+oid sha256:29829f35f4613951eb90019903210b7b8e528d2aa0f184c4457533eedb32481b
 size 14645

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5357f8c89955bc990803217fa4d48fb7a40d34aeaa2d0b1a89e6aaa5b7aa2f41
+oid sha256:cc7830117a5044b6dd50deaa1b84ae2b8ab22744e6fc75b07306406c5cd662ce
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d760b148563b7de810eb2c6379deb9f08244981acc1c77967840bee4635b56b5
+oid sha256:9c8d4b2f3082381b3f41b17562e35c0568313120fce2152795ee7a9e136c271d
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0058430669089591745,
+  "epoch": 0.007011680290751009,
   "eval_steps": 500,
-  "global_step": 1000,
+  "global_step": 1200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -708,6 +708,146 @@
       "learning_rate": 0.00019999975874043395,
       "loss": 55.35384521484375,
       "step": 1000
+    },
+    {
+      "epoch": 0.005901497578048766,
+      "grad_norm": 297.33001708984375,
+      "learning_rate": 0.0001999997517880673,
+      "loss": 55.16865234375,
+      "step": 1010
+    },
+    {
+      "epoch": 0.005959928247138358,
+      "grad_norm": 245.5879364013672,
+      "learning_rate": 0.00019999974473694564,
+      "loss": 55.22572631835938,
+      "step": 1020
+    },
+    {
+      "epoch": 0.00601835891622795,
+      "grad_norm": 2691.163818359375,
+      "learning_rate": 0.00019999973758706894,
+      "loss": 57.4362548828125,
+      "step": 1030
+    },
+    {
+      "epoch": 0.006076789585317542,
+      "grad_norm": 234.8723907470703,
+      "learning_rate": 0.0001999997303384372,
+      "loss": 55.82191162109375,
+      "step": 1040
+    },
+    {
+      "epoch": 0.006135220254407134,
+      "grad_norm": 311.34661865234375,
+      "learning_rate": 0.00019999972299105046,
+      "loss": 55.76887817382813,
+      "step": 1050
+    },
+    {
+      "epoch": 0.006193650923496725,
+      "grad_norm": 322.7856750488281,
+      "learning_rate": 0.0001999997155449087,
+      "loss": 57.26973266601563,
+      "step": 1060
+    },
+    {
+      "epoch": 0.006252081592586316,
+      "grad_norm": 478.2718200683594,
+      "learning_rate": 0.0001999997080000119,
+      "loss": 58.59776000976562,
+      "step": 1070
+    },
+    {
+      "epoch": 0.006310512261675908,
+      "grad_norm": 301.3092041015625,
+      "learning_rate": 0.00019999970035636014,
+      "loss": 58.48822021484375,
+      "step": 1080
+    },
+    {
+      "epoch": 0.0063689429307655,
+      "grad_norm": 512.6185913085938,
+      "learning_rate": 0.00019999969261395335,
+      "loss": 57.57078247070312,
+      "step": 1090
+    },
+    {
+      "epoch": 0.006427373599855092,
+      "grad_norm": 24003.73828125,
+      "learning_rate": 0.0001999996847727916,
+      "loss": 59.79292602539063,
+      "step": 1100
+    },
+    {
+      "epoch": 0.006485804268944684,
+      "grad_norm": 453.1183776855469,
+      "learning_rate": 0.00019999967683287487,
+      "loss": 60.21820068359375,
+      "step": 1110
+    },
+    {
+      "epoch": 0.006544234938034276,
+      "grad_norm": 457.7259521484375,
+      "learning_rate": 0.00019999966879420317,
+      "loss": 62.034857177734374,
+      "step": 1120
+    },
+    {
+      "epoch": 0.006602665607123867,
+      "grad_norm": 556.26904296875,
+      "learning_rate": 0.0001999996606567765,
+      "loss": 62.449578857421876,
+      "step": 1130
+    },
+    {
+      "epoch": 0.006661096276213459,
+      "grad_norm": 452.7843933105469,
+      "learning_rate": 0.0001999996524205949,
+      "loss": 61.5654296875,
+      "step": 1140
+    },
+    {
+      "epoch": 0.006719526945303051,
+      "grad_norm": 453.83734130859375,
+      "learning_rate": 0.00019999964408565834,
+      "loss": 62.3664794921875,
+      "step": 1150
+    },
+    {
+      "epoch": 0.006777957614392642,
+      "grad_norm": 475.32330322265625,
+      "learning_rate": 0.00019999963565196685,
+      "loss": 62.6634033203125,
+      "step": 1160
+    },
+    {
+      "epoch": 0.006836388283482234,
+      "grad_norm": 294.16552734375,
+      "learning_rate": 0.0001999996271195204,
+      "loss": 62.187567138671874,
+      "step": 1170
+    },
+    {
+      "epoch": 0.006894818952571826,
+      "grad_norm": 306.7320556640625,
+      "learning_rate": 0.00019999961848831907,
+      "loss": 64.75111694335938,
+      "step": 1180
+    },
+    {
+      "epoch": 0.0069532496216614175,
+      "grad_norm": 445.7840576171875,
+      "learning_rate": 0.00019999960975836283,
+      "loss": 65.01791381835938,
+      "step": 1190
+    },
+    {
+      "epoch": 0.007011680290751009,
+      "grad_norm": 591.8782348632812,
+      "learning_rate": 0.00019999960092965166,
+      "loss": 64.0755126953125,
+      "step": 1200
     }
   ],
   "logging_steps": 10,
@@ -727,7 +867,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8024504823238656.0,
+  "total_flos": 9648201721294848.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null