Training in progress, step 60000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:469e1f89eccfb155338fd5db39f32fd0c4eb9dd326d3a7d29a4d2672a07d4b21
+oid sha256:05a30dcc4066c74987493dbc2a267fc6d98cb8159f7cd132cf51d35e7905c50a
 size 357393656

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:131fac4f70e3c78c776224a1d93835a3169eb37f76ab0c797fa8b50cabbb2ff2
+oid sha256:d3a41286438e9fd35f9bdf47cbadeb04807c4c2d4f0a9fb94e912dce25f586e5
 size 714964666

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9080fe56036d364eeed3a3e17bc011e2720636fbd1cd74b0b67060e1c6f9fd0b
+oid sha256:5c1934cdc6a6281fbbbb65f91e6a59588aa3aa21c101b0948ed814af372256f2
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b5a1f66ccb3d7e0c17977550a1bc585bff50e438a8704fb2fe2f661fb58928b
+oid sha256:b426d42a4e9592ccb13e91eff14490693255fb2d0c2b3d028db69ce729eb760f
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:17767a352adb7f4edfdb7e9a788ffce018ee7072087581f483d4c5cf01d238db
+oid sha256:20ca3cb91477d18e43f14bf0f696487d6551646ca2aee7b0317f7c8df3b4406b
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 4.157658406785298,
+  "epoch": 4.989190088142358,
   "eval_steps": 10000,
-  "global_step": 50000,
+  "global_step": 60000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -748,6 +748,154 @@
       "eval_samples_per_second": 133.107,
       "eval_steps_per_second": 4.16,
       "step": 50000
+    },
+    {
+      "epoch": 4.199234990853151,
+      "grad_norm": 0.21643032133579254,
+      "learning_rate": 8.159986470488753e-05,
+      "loss": 7.9383,
+      "step": 50500
+    },
+    {
+      "epoch": 4.240811574921005,
+      "grad_norm": 0.670906662940979,
+      "learning_rate": 7.737189244038559e-05,
+      "loss": 7.9348,
+      "step": 51000
+    },
+    {
+      "epoch": 4.282388158988858,
+      "grad_norm": 0.21291261911392212,
+      "learning_rate": 7.315237612041264e-05,
+      "loss": 7.9352,
+      "step": 51500
+    },
+    {
+      "epoch": 4.3239647430567105,
+      "grad_norm": 0.330913782119751,
+      "learning_rate": 6.89244038559107e-05,
+      "loss": 7.9266,
+      "step": 52000
+    },
+    {
+      "epoch": 4.365541327124563,
+      "grad_norm": 0.37971287965774536,
+      "learning_rate": 6.469643159140875e-05,
+      "loss": 7.9368,
+      "step": 52500
+    },
+    {
+      "epoch": 4.407117911192416,
+      "grad_norm": 0.46552345156669617,
+      "learning_rate": 6.0468459326906816e-05,
+      "loss": 7.9407,
+      "step": 53000
+    },
+    {
+      "epoch": 4.44869449526027,
+      "grad_norm": 0.32077756524086,
+      "learning_rate": 5.624048706240487e-05,
+      "loss": 7.9331,
+      "step": 53500
+    },
+    {
+      "epoch": 4.490271079328123,
+      "grad_norm": 0.5039647221565247,
+      "learning_rate": 5.201251479790293e-05,
+      "loss": 7.9327,
+      "step": 54000
+    },
+    {
+      "epoch": 4.5318476633959754,
+      "grad_norm": 0.7789810299873352,
+      "learning_rate": 4.779299847792998e-05,
+      "loss": 7.9297,
+      "step": 54500
+    },
+    {
+      "epoch": 4.573424247463828,
+      "grad_norm": 0.33232608437538147,
+      "learning_rate": 4.356502621342804e-05,
+      "loss": 7.9354,
+      "step": 55000
+    },
+    {
+      "epoch": 4.615000831531681,
+      "grad_norm": 0.9029014706611633,
+      "learning_rate": 3.9337053948926096e-05,
+      "loss": 7.941,
+      "step": 55500
+    },
+    {
+      "epoch": 4.656577415599534,
+      "grad_norm": 0.39622828364372253,
+      "learning_rate": 3.510908168442415e-05,
+      "loss": 7.9325,
+      "step": 56000
+    },
+    {
+      "epoch": 4.698153999667388,
+      "grad_norm": 0.19301092624664307,
+      "learning_rate": 3.0881109419922204e-05,
+      "loss": 7.9323,
+      "step": 56500
+    },
+    {
+      "epoch": 4.73973058373524,
+      "grad_norm": 0.8889003992080688,
+      "learning_rate": 2.6661593099949264e-05,
+      "loss": 7.9267,
+      "step": 57000
+    },
+    {
+      "epoch": 4.781307167803093,
+      "grad_norm": 0.31362804770469666,
+      "learning_rate": 2.243362083544732e-05,
+      "loss": 7.9302,
+      "step": 57500
+    },
+    {
+      "epoch": 4.822883751870946,
+      "grad_norm": 0.329970121383667,
+      "learning_rate": 1.8205648570945376e-05,
+      "loss": 7.933,
+      "step": 58000
+    },
+    {
+      "epoch": 4.8644603359388,
+      "grad_norm": 0.5594154596328735,
+      "learning_rate": 1.397767630644343e-05,
+      "loss": 7.9314,
+      "step": 58500
+    },
+    {
+      "epoch": 4.9060369200066525,
+      "grad_norm": 0.4558698236942291,
+      "learning_rate": 9.749704041941485e-06,
+      "loss": 7.927,
+      "step": 59000
+    },
+    {
+      "epoch": 4.947613504074505,
+      "grad_norm": 0.39327356219291687,
+      "learning_rate": 5.530187721968544e-06,
+      "loss": 7.9275,
+      "step": 59500
+    },
+    {
+      "epoch": 4.989190088142358,
+      "grad_norm": 0.227029949426651,
+      "learning_rate": 1.3022154574665992e-06,
+      "loss": 7.9352,
+      "step": 60000
+    },
+    {
+      "epoch": 4.989190088142358,
+      "eval_loss": 9.034906387329102,
+      "eval_runtime": 2885.2471,
+      "eval_samples_per_second": 133.376,
+      "eval_steps_per_second": 4.168,
+      "step": 60000
     }
   ],
   "logging_steps": 500,
@@ -767,7 +915,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.6054932837341696e+17,
+  "total_flos": 6.726749069113344e+17,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null