Training in progress, step 21000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5756810596360925f62477252be4ef4d8963636196c68f3a6630e80c0e6084e2
+oid sha256:5808c4d4a871b3a3feef39008a78693f4b002bad6b751d4a55ecf03b18ce28d2
 size 4523108832

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:21c41628f6e46e2f03850fbb1433d7dbc5a898fe92fe5885639875ca1fc396dd
+oid sha256:cb3917c9a0b5a1a4684d0f418f0f18616f6c636c241010cfdfa0cab6ff0ea1ed
 size 2912179275

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae2914830368f46e9c6d2b2e5cbe7fbed0fa5772149d7c8cbec7c8589a46483c
+oid sha256:495527095ce64d42859bf28983716fbe3891476c1dd8d77f6b07b794fa6428e3
 size 14645

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb2e34d098aadc800b0425e7e182bffad68ed2b8e7619903a86bd70be3e76095
+oid sha256:1ba426160bf784af2f74f1fee215f1c1e222f9b82fe4e028acd5d90af568a23c
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe3c98f2329aa0f175c12b4015dcbc8bc5f06490e916ca5f121c605678026b21
+oid sha256:f191eb532c66480b881d02a99bfe981f86631ebea22d7fa2c791adb20fea8a3f
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 10.001366666666666,
+  "epoch": 11.0017,
   "eval_steps": 500,
-  "global_step": 20500,
+  "global_step": 21000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2878,6 +2878,76 @@
       "learning_rate": 7.054522767757137e-06,
       "loss": 1.5210466003417968,
       "step": 20500
+    },
+    {
+      "epoch": 6.0032,
+      "grad_norm": 1.9438225030899048,
+      "learning_rate": 6.986890260807822e-06,
+      "loss": 1.4293966674804688,
+      "step": 20550
+    },
+    {
+      "epoch": 6.004866666666667,
+      "grad_norm": 1.842617392539978,
+      "learning_rate": 6.919484947298004e-06,
+      "loss": 1.4090545654296875,
+      "step": 20600
+    },
+    {
+      "epoch": 6.0065333333333335,
+      "grad_norm": 2.061250686645508,
+      "learning_rate": 6.852308738351514e-06,
+      "loss": 1.41453125,
+      "step": 20650
+    },
+    {
+      "epoch": 6.0082,
+      "grad_norm": 1.9555222988128662,
+      "learning_rate": 6.7853635385964585e-06,
+      "loss": 1.3674409484863281,
+      "step": 20700
+    },
+    {
+      "epoch": 6.0098666666666665,
+      "grad_norm": 2.1003122329711914,
+      "learning_rate": 6.718651246111195e-06,
+      "loss": 1.3919035339355468,
+      "step": 20750
+    },
+    {
+      "epoch": 6.011533333333333,
+      "grad_norm": 1.9350862503051758,
+      "learning_rate": 6.652173752370525e-06,
+      "loss": 1.3142074584960937,
+      "step": 20800
+    },
+    {
+      "epoch": 6.0132,
+      "grad_norm": 1.7350631952285767,
+      "learning_rate": 6.585932942192071e-06,
+      "loss": 1.3737037658691407,
+      "step": 20850
+    },
+    {
+      "epoch": 6.014866666666666,
+      "grad_norm": 1.7135426998138428,
+      "learning_rate": 6.519930693682841e-06,
+      "loss": 1.4159625244140626,
+      "step": 20900
+    },
+    {
+      "epoch": 7.0002,
+      "grad_norm": 1.8795244693756104,
+      "learning_rate": 6.454168878185959e-06,
+      "loss": 1.4865910339355468,
+      "step": 20950
+    },
+    {
+      "epoch": 7.0018666666666665,
+      "grad_norm": 1.576035499572754,
+      "learning_rate": 6.388649360227622e-06,
+      "loss": 1.3686183166503907,
+      "step": 21000
     }
   ],
   "logging_steps": 50,
@@ -2897,7 +2967,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.811200416963625e+18,
+  "total_flos": 1.8586919781536072e+18,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null