Training in progress, step 20500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d9c1cefb9a4eba5c37ddb3f1fd9c87aa220ebdd37d6dca8bf44e86197ef0b3f
+oid sha256:5756810596360925f62477252be4ef4d8963636196c68f3a6630e80c0e6084e2
 size 4523108832

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:378c103450b9f57a2150a1883a6da51ed2aa62d726a672f3ad438f5a1186f5fa
+oid sha256:21c41628f6e46e2f03850fbb1433d7dbc5a898fe92fe5885639875ca1fc396dd
 size 2912179275

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:50dd579ef1d2d932c3d7726ef0f6ec72d0e25b023ae2fd8b67112ac75e1041b9
+oid sha256:ae2914830368f46e9c6d2b2e5cbe7fbed0fa5772149d7c8cbec7c8589a46483c
 size 14645

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:489c5c7b3eb8c654fb99b2307b26bef5ab573d173ac5583a0472f5ab307ed300
+oid sha256:cb2e34d098aadc800b0425e7e182bffad68ed2b8e7619903a86bd70be3e76095
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dd10e570fb10a3dddd222e4af27841df0902397065c880157d50ad88813e460c
+oid sha256:fe3c98f2329aa0f175c12b4015dcbc8bc5f06490e916ca5f121c605678026b21
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 9.001333333333333,
+  "epoch": 10.001366666666666,
   "eval_steps": 500,
-  "global_step": 20000,
+  "global_step": 20500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2808,6 +2808,76 @@
       "learning_rate": 7.741520511928819e-06,
       "loss": 0.6710720825195312,
       "step": 20000
+    },
+    {
+      "epoch": 5.003166666666667,
+      "grad_norm": 1.949172854423523,
+      "learning_rate": 7.671726707847171e-06,
+      "loss": 1.0902951049804688,
+      "step": 20050
+    },
+    {
+      "epoch": 5.004833333333333,
+      "grad_norm": 1.7889505624771118,
+      "learning_rate": 7.602140680230471e-06,
+      "loss": 1.0368961334228515,
+      "step": 20100
+    },
+    {
+      "epoch": 5.0065,
+      "grad_norm": 1.857659935951233,
+      "learning_rate": 7.5327644020317124e-06,
+      "loss": 1.07505859375,
+      "step": 20150
+    },
+    {
+      "epoch": 5.008166666666667,
+      "grad_norm": 1.8462475538253784,
+      "learning_rate": 7.4635998402569545e-06,
+      "loss": 1.0229257202148438,
+      "step": 20200
+    },
+    {
+      "epoch": 5.009833333333333,
+      "grad_norm": 1.9917975664138794,
+      "learning_rate": 7.394648955909486e-06,
+      "loss": 1.0416568756103515,
+      "step": 20250
+    },
+    {
+      "epoch": 5.0115,
+      "grad_norm": 1.6674444675445557,
+      "learning_rate": 7.327286283161366e-06,
+      "loss": 1.0210507202148438,
+      "step": 20300
+    },
+    {
+      "epoch": 5.013166666666667,
+      "grad_norm": 1.5405360460281372,
+      "learning_rate": 7.2587642417068355e-06,
+      "loss": 1.0572975921630858,
+      "step": 20350
+    },
+    {
+      "epoch": 5.014833333333334,
+      "grad_norm": 1.8200913667678833,
+      "learning_rate": 7.190461685325534e-06,
+      "loss": 1.0956484985351562,
+      "step": 20400
+    },
+    {
+      "epoch": 5.0165,
+      "grad_norm": 2.1134114265441895,
+      "learning_rate": 7.122380550580563e-06,
+      "loss": 1.2368092346191406,
+      "step": 20450
+    },
+    {
+      "epoch": 6.001533333333334,
+      "grad_norm": 1.9816176891326904,
+      "learning_rate": 7.054522767757137e-06,
+      "loss": 1.5210466003417968,
+      "step": 20500
     }
   ],
   "logging_steps": 50,
@@ -2827,7 +2897,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.7630490710553477e+18,
+  "total_flos": 1.811200416963625e+18,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null