Training in progress, step 7000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b3fa5f3cc96b9529f1d5e8131a37292779653704815b4b746c1b0250f3602851
+oid sha256:b597ae305154571a9cf0fc318fd2f02878b6fc2337475a4dbbe0703d844213e4
 size 471641972

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d3069535c22641a38713fff287cf58793629ef335a6f4aaae5f29618ceb3cf78
+oid sha256:85bb5c5574de9da9d3ba8e7a266718161ca8465cc2f476d079631453bb47755d
 size 943408715

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ccb6179f49cce810022d0c802f8e81da4fd7eb3709d6bbcc537ba23b3534b12
+oid sha256:4e245b446c6f11ba7b61a7b70b2e26db93445e984c29a565ba9fa0a4c06c6c7e
 size 14645

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:55d8b55e9978d7e769745e58c7c6bfb5428be48a72c7ac40133ec5d5a5a6ecf3
+oid sha256:6af8329711dde815df15cc29a7be4297f7e74c40a36d0acc98aace42529f4f55
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:29aaacffc58307b53773121c6ce847a4fc500d48fc100ea58c51bf12996f60ab
+oid sha256:aded58ff1e996ada0739166f06f8ea3e063c8206207381ac3ffc60d844872983
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.6091215958985813,
+  "epoch": 0.7106418618816781,
   "eval_steps": 500,
-  "global_step": 6000,
+  "global_step": 7000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -435,6 +435,76 @@
       "learning_rate": 4.116264159008335e-05,
       "loss": 2.0788,
       "step": 6000
+    },
+    {
+      "epoch": 0.619273622496891,
+      "grad_norm": 6.831523895263672,
+      "learning_rate": 4.009403718743321e-05,
+      "loss": 2.0606,
+      "step": 6100
+    },
+    {
+      "epoch": 0.6294256490952006,
+      "grad_norm": 6.920884132385254,
+      "learning_rate": 3.9025432784783075e-05,
+      "loss": 2.0504,
+      "step": 6200
+    },
+    {
+      "epoch": 0.6395776756935103,
+      "grad_norm": 5.9327802658081055,
+      "learning_rate": 3.7956828382132936e-05,
+      "loss": 2.061,
+      "step": 6300
+    },
+    {
+      "epoch": 0.64972970229182,
+      "grad_norm": 7.0381550788879395,
+      "learning_rate": 3.68882239794828e-05,
+      "loss": 2.021,
+      "step": 6400
+    },
+    {
+      "epoch": 0.6598817288901296,
+      "grad_norm": 5.229250431060791,
+      "learning_rate": 3.581961957683266e-05,
+      "loss": 2.0095,
+      "step": 6500
+    },
+    {
+      "epoch": 0.6700337554884394,
+      "grad_norm": 5.998141288757324,
+      "learning_rate": 3.475101517418252e-05,
+      "loss": 2.0756,
+      "step": 6600
+    },
+    {
+      "epoch": 0.6801857820867491,
+      "grad_norm": 7.094350814819336,
+      "learning_rate": 3.368241077153238e-05,
+      "loss": 2.019,
+      "step": 6700
+    },
+    {
+      "epoch": 0.6903378086850588,
+      "grad_norm": 6.863796710968018,
+      "learning_rate": 3.2613806368882245e-05,
+      "loss": 2.0057,
+      "step": 6800
+    },
+    {
+      "epoch": 0.7004898352833684,
+      "grad_norm": 7.739531993865967,
+      "learning_rate": 3.15452019662321e-05,
+      "loss": 2.0452,
+      "step": 6900
+    },
+    {
+      "epoch": 0.7106418618816781,
+      "grad_norm": 6.940340995788574,
+      "learning_rate": 3.0476597563581964e-05,
+      "loss": 2.0123,
+      "step": 7000
     }
   ],
   "logging_steps": 100,
@@ -454,7 +524,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3261969040829952.0,
+  "total_flos": 3807757501036032.0,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null