Training in progress, step 2500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3daa573e6c713aaba8eac212b616972e27300562149c5a86cf161a20a2986ab7
+oid sha256:748811954799fb8207c027f9b41646692c79d79091f80ac4e270ed4cc9d5b86d
 size 3826461296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ecb57a7b1bc6df393a4d72695c3003da6933e5235a702cfb45b794fb4c7477bb
+oid sha256:b67e674b05b252f5f41be162214aad1c332bd589e7f1ad1cc4ce742dbb1b2122
 size 2479955235

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db5e98494f4088139d10e50b166d461cb7e004fb4e01c00728b39a7d5b780d91
+oid sha256:9cb7c2d8a4305600ccebb18dd04e9a0785ea448686f24e449566e93d850fb957
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a2e9f05b210aeadfc93d7bb7ed80d64988a89f8306f57d2f4dda99778443c8e5
+oid sha256:b6c7d122b19d10b5d68d81c5fb7ac1f07cbefaf32391619951f39bd376dd10e0
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.96,
+  "epoch": 1.0,
   "eval_steps": 500,
-  "global_step": 2400,
+  "global_step": 2500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1688,6 +1688,76 @@
       "learning_rate": 2.1101286173633444e-06,
       "loss": 0.2135,
       "step": 2400
+    },
+    {
+      "epoch": 0.964,
+      "grad_norm": 4.838590621948242,
+      "learning_rate": 1.909163987138264e-06,
+      "loss": 0.3181,
+      "step": 2410
+    },
+    {
+      "epoch": 0.968,
+      "grad_norm": 6.775151252746582,
+      "learning_rate": 1.7081993569131833e-06,
+      "loss": 0.2516,
+      "step": 2420
+    },
+    {
+      "epoch": 0.972,
+      "grad_norm": 13.491608619689941,
+      "learning_rate": 1.507234726688103e-06,
+      "loss": 0.2294,
+      "step": 2430
+    },
+    {
+      "epoch": 0.976,
+      "grad_norm": 7.067889213562012,
+      "learning_rate": 1.3062700964630226e-06,
+      "loss": 0.2206,
+      "step": 2440
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 6.7473530769348145,
+      "learning_rate": 1.1053054662379423e-06,
+      "loss": 0.2003,
+      "step": 2450
+    },
+    {
+      "epoch": 0.984,
+      "grad_norm": 9.074109077453613,
+      "learning_rate": 9.043408360128617e-07,
+      "loss": 0.2343,
+      "step": 2460
+    },
+    {
+      "epoch": 0.988,
+      "grad_norm": 10.73699951171875,
+      "learning_rate": 7.033762057877814e-07,
+      "loss": 0.6721,
+      "step": 2470
+    },
+    {
+      "epoch": 0.992,
+      "grad_norm": 5.29847526550293,
+      "learning_rate": 5.02411575562701e-07,
+      "loss": 0.236,
+      "step": 2480
+    },
+    {
+      "epoch": 0.996,
+      "grad_norm": 10.172593116760254,
+      "learning_rate": 3.014469453376206e-07,
+      "loss": 0.216,
+      "step": 2490
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 16.507993698120117,
+      "learning_rate": 1.0048231511254019e-07,
+      "loss": 0.2836,
+      "step": 2500
     }
   ],
   "logging_steps": 10,
@@ -1702,12 +1772,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 4.334241751385702e+16,
+  "total_flos": 4.513321594098893e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null