Training in progress, step 7500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:09917938851a93d2d6274c38c477208678c3de4028f8754cb6af6099dda183e7
+oid sha256:3f6372dd1fcac73a6d002b862e253a8f529a21bfb6505d426eb6490685b99079
 size 4523108832

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:213cb24e7d7a2f9e099ae98089d6eea055e619489262fe48fac366bb2dfdcafc
+oid sha256:3f4efb829900eca9ce90bdd07233b37b80c9ba4ef109e90b06c024612e54b339
 size 2912179275

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9445552595536daf5bd8731be4eabb308bd26e76a3f4f0c20c4aa55fcf9ea202
+oid sha256:9e51a42ec5ffac256f3cd0ee0ccd7a6d3befe58914ad400c0cc707bc4a5ee283
 size 14645

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:be40a03f70bb2a35bb567114fb5ceb05ce1222c8df24b1e1100746c617c5be10
+oid sha256:642827d515e7c3d88d20c04224822701abbbc9250deb1d366045f974d08b8258
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd05c974819b00eb2c62a2d0cfe8adf7395c3b8cd189d35df1a15045e0bcd525
+oid sha256:05b7199eafacf3aebfb36d08706c780a64bb0c6ec2f9e812edb49fb3334dca22
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 10.014533333333333,
+  "epoch": 11.016366666666666,
   "eval_steps": 500,
-  "global_step": 7000,
+  "global_step": 7500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -988,6 +988,76 @@
       "learning_rate": 2.654852922998545e-05,
       "loss": 0.22788461685180664,
       "step": 7000
+    },
+    {
+      "epoch": 4.007,
+      "grad_norm": 1.1483008861541748,
+      "learning_rate": 2.649739510214025e-05,
+      "loss": 0.22346155166625978,
+      "step": 7050
+    },
+    {
+      "epoch": 4.008666666666667,
+      "grad_norm": 1.2172214984893799,
+      "learning_rate": 2.6445934991895764e-05,
+      "loss": 0.23918920516967773,
+      "step": 7100
+    },
+    {
+      "epoch": 4.0103333333333335,
+      "grad_norm": 1.1359659433364868,
+      "learning_rate": 2.639415035828598e-05,
+      "loss": 0.24985692977905274,
+      "step": 7150
+    },
+    {
+      "epoch": 4.012,
+      "grad_norm": 1.475920557975769,
+      "learning_rate": 2.6342042669546e-05,
+      "loss": 0.2808365821838379,
+      "step": 7200
+    },
+    {
+      "epoch": 4.0136666666666665,
+      "grad_norm": 1.2670186758041382,
+      "learning_rate": 2.628961340307043e-05,
+      "loss": 0.2782126426696777,
+      "step": 7250
+    },
+    {
+      "epoch": 5.0005,
+      "grad_norm": 1.717673659324646,
+      "learning_rate": 2.6236864045371453e-05,
+      "loss": 0.36194786071777346,
+      "step": 7300
+    },
+    {
+      "epoch": 5.002166666666667,
+      "grad_norm": 1.797800898551941,
+      "learning_rate": 2.618379609203674e-05,
+      "loss": 0.6739380645751953,
+      "step": 7350
+    },
+    {
+      "epoch": 5.003833333333334,
+      "grad_norm": 2.0240073204040527,
+      "learning_rate": 2.613041104768699e-05,
+      "loss": 0.6977305603027344,
+      "step": 7400
+    },
+    {
+      "epoch": 5.0055,
+      "grad_norm": 1.6391247510910034,
+      "learning_rate": 2.6076710425933307e-05,
+      "loss": 0.6162394332885742,
+      "step": 7450
+    },
+    {
+      "epoch": 5.0071666666666665,
+      "grad_norm": 2.932299852371216,
+      "learning_rate": 2.6022695749334263e-05,
+      "loss": 0.6486746215820313,
+      "step": 7500
     }
   ],
   "logging_steps": 50,
@@ -1007,7 +1077,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.245582025697198e+17,
+  "total_flos": 6.69187376704045e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null