Training in progress, step 3500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc90e72e9df06c7a8b2859568abbda018ecb77710946f3069e0c35fa974f19ee
+oid sha256:ca1d58e2cd18a1fc09601b5143bb78b5307a273e6e2f1750228c18041d7fe77e
 size 3809184360

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:655084455e5e897aa7ef7acbe8b134c275ee59dd5ff109b69ff76cd085fd6e07
+oid sha256:3d9b3bc32af7a9c7224769cd6c49a9680aa7f8795c0d4e082d32018b4c599ff6
 size 2458291491

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea341a3d505626ad57a03d7f2e993437556ed56796356e3afaa8f1db62445455
+oid sha256:d8841fa7aad843ffcf2b76d868211d81553f8ce267313764fca81be4f5b42b4d
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2cc273b404670a1098fedda6e7c02f1509edb236f0c25d50ae9fbf6dd87e347b
+oid sha256:1c493c177a6a7b8f4b53d9f320f001568436248d37644f960edb69a4818ec2df
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.8666666666666667,
+  "epoch": 0.9333333333333333,
   "eval_steps": 500,
-  "global_step": 3250,
+  "global_step": 3500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2283,6 +2283,181 @@
       "learning_rate": 6.805929919137468e-06,
       "loss": 0.2464,
       "step": 3250
+    },
+    {
+      "epoch": 0.8693333333333333,
+      "grad_norm": 5.073930740356445,
+      "learning_rate": 6.671159029649596e-06,
+      "loss": 0.2491,
+      "step": 3260
+    },
+    {
+      "epoch": 0.872,
+      "grad_norm": 6.984921932220459,
+      "learning_rate": 6.536388140161725e-06,
+      "loss": 0.2212,
+      "step": 3270
+    },
+    {
+      "epoch": 0.8746666666666667,
+      "grad_norm": 5.525951862335205,
+      "learning_rate": 6.401617250673856e-06,
+      "loss": 0.2446,
+      "step": 3280
+    },
+    {
+      "epoch": 0.8773333333333333,
+      "grad_norm": 5.485599040985107,
+      "learning_rate": 6.266846361185984e-06,
+      "loss": 0.2735,
+      "step": 3290
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 6.451603889465332,
+      "learning_rate": 6.132075471698113e-06,
+      "loss": 0.2499,
+      "step": 3300
+    },
+    {
+      "epoch": 0.8826666666666667,
+      "grad_norm": 8.449997901916504,
+      "learning_rate": 5.997304582210243e-06,
+      "loss": 0.262,
+      "step": 3310
+    },
+    {
+      "epoch": 0.8853333333333333,
+      "grad_norm": 2.8802688121795654,
+      "learning_rate": 5.862533692722373e-06,
+      "loss": 0.248,
+      "step": 3320
+    },
+    {
+      "epoch": 0.888,
+      "grad_norm": 6.58447790145874,
+      "learning_rate": 5.727762803234501e-06,
+      "loss": 0.1707,
+      "step": 3330
+    },
+    {
+      "epoch": 0.8906666666666667,
+      "grad_norm": 10.708820343017578,
+      "learning_rate": 5.592991913746631e-06,
+      "loss": 0.2294,
+      "step": 3340
+    },
+    {
+      "epoch": 0.8933333333333333,
+      "grad_norm": 8.319356918334961,
+      "learning_rate": 5.458221024258761e-06,
+      "loss": 0.2165,
+      "step": 3350
+    },
+    {
+      "epoch": 0.896,
+      "grad_norm": 6.977818012237549,
+      "learning_rate": 5.3234501347708894e-06,
+      "loss": 0.2321,
+      "step": 3360
+    },
+    {
+      "epoch": 0.8986666666666666,
+      "grad_norm": 6.978248119354248,
+      "learning_rate": 5.188679245283019e-06,
+      "loss": 0.2039,
+      "step": 3370
+    },
+    {
+      "epoch": 0.9013333333333333,
+      "grad_norm": 7.0379438400268555,
+      "learning_rate": 5.053908355795149e-06,
+      "loss": 0.2364,
+      "step": 3380
+    },
+    {
+      "epoch": 0.904,
+      "grad_norm": 5.10407018661499,
+      "learning_rate": 4.9191374663072775e-06,
+      "loss": 0.3408,
+      "step": 3390
+    },
+    {
+      "epoch": 0.9066666666666666,
+      "grad_norm": 4.217552185058594,
+      "learning_rate": 4.784366576819407e-06,
+      "loss": 0.1653,
+      "step": 3400
+    },
+    {
+      "epoch": 0.9093333333333333,
+      "grad_norm": 8.982743263244629,
+      "learning_rate": 4.649595687331537e-06,
+      "loss": 0.208,
+      "step": 3410
+    },
+    {
+      "epoch": 0.912,
+      "grad_norm": 7.103553295135498,
+      "learning_rate": 4.5148247978436664e-06,
+      "loss": 0.1838,
+      "step": 3420
+    },
+    {
+      "epoch": 0.9146666666666666,
+      "grad_norm": 6.565107822418213,
+      "learning_rate": 4.380053908355795e-06,
+      "loss": 0.2254,
+      "step": 3430
+    },
+    {
+      "epoch": 0.9173333333333333,
+      "grad_norm": 8.163582801818848,
+      "learning_rate": 4.245283018867925e-06,
+      "loss": 0.1598,
+      "step": 3440
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 4.565555095672607,
+      "learning_rate": 4.1105121293800545e-06,
+      "loss": 0.1888,
+      "step": 3450
+    },
+    {
+      "epoch": 0.9226666666666666,
+      "grad_norm": 7.8352508544921875,
+      "learning_rate": 3.975741239892183e-06,
+      "loss": 0.2683,
+      "step": 3460
+    },
+    {
+      "epoch": 0.9253333333333333,
+      "grad_norm": 8.402386665344238,
+      "learning_rate": 3.840970350404313e-06,
+      "loss": 0.1869,
+      "step": 3470
+    },
+    {
+      "epoch": 0.928,
+      "grad_norm": 8.078757286071777,
+      "learning_rate": 3.706199460916442e-06,
+      "loss": 0.2293,
+      "step": 3480
+    },
+    {
+      "epoch": 0.9306666666666666,
+      "grad_norm": 7.771483898162842,
+      "learning_rate": 3.5714285714285714e-06,
+      "loss": 0.3479,
+      "step": 3490
+    },
+    {
+      "epoch": 0.9333333333333333,
+      "grad_norm": 3.739326000213623,
+      "learning_rate": 3.436657681940701e-06,
+      "loss": 0.1441,
+      "step": 3500
     }
   ],
   "logging_steps": 10,
@@ -2302,7 +2477,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.87649798448128e+16,
+  "total_flos": 6.32834922129408e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null