Training in progress, step 2000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d0af6d4f7601d404d24813692db718e4a2d20f4a48d8d3a2a68e00699d0b26e2
+oid sha256:21a8e3a7c437f2596088fad50489a7bb2ed9def0a75481fa3ea23cf009f8e2d7
 size 2682482800

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d167acd227ba225cf9bce9364be165f3171f2eff7a8fde60e11549d6d9cd16bb
+oid sha256:315ef2407c690abd058c31d25ca395651dae325fc56d06a59faa635e22d871e6
 size 5365108834

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:887cd30e708bc2625838e7001c0fa0e942c4fa64e444f4e787d569c422ad050b
+oid sha256:0ea26f59a420497cca21bbb6c5a76b307a2356fa2099a000f1378e8c6c7dd674
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d259281a955df924ac4ebaa856cdb89459a9b9a13b350ef866b2af10d6d0eea
+oid sha256:ed285da3bd9884d1b491678c6c4c4443831eaa068a1151035b5d832ffe3502b2
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f7a835a139362a57ef1920d9ff07a816b3a580439245876e608a4108c26e7ddf
+oid sha256:bdf537be4628de0ed5f960b43d5cc07c3b03484d41ff68f24d8ec2c14b057a9a
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d1dfb8149dc214370833c8d5100239e81ec9e9ffa5511208d50605d9d0e710f5
+oid sha256:5e611ba9650a64094177d437392c96ee2158ab3d2635b77d9b1072b9aa35c974
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e5da8ca094d5fd2cfde37c2e69ed055e71f3022c86dd39598472f504a4eab8b3
+oid sha256:e949960d3d4b878da9fe1bb0cd20ae8736c4aa4b7e2ccd57b11e5b880260dcdd
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.1150814201047241,
+  "epoch": 0.15344189347296547,
   "eval_steps": 500,
-  "global_step": 1500,
+  "global_step": 2000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -217,6 +217,76 @@
       "learning_rate": 8.849163725640633e-05,
       "loss": 65.2446,
       "step": 1500
+    },
+    {
+      "epoch": 0.11891746744154823,
+      "grad_norm": 14.789810180664062,
+      "learning_rate": 8.81080251649532e-05,
+      "loss": 64.8275,
+      "step": 1550
+    },
+    {
+      "epoch": 0.12275351477837236,
+      "grad_norm": 44.35984802246094,
+      "learning_rate": 8.772441307350008e-05,
+      "loss": 64.7482,
+      "step": 1600
+    },
+    {
+      "epoch": 0.1265895621151965,
+      "grad_norm": 16.479351043701172,
+      "learning_rate": 8.734080098204695e-05,
+      "loss": 64.3666,
+      "step": 1650
+    },
+    {
+      "epoch": 0.13042560945202064,
+      "grad_norm": 27.057039260864258,
+      "learning_rate": 8.695718889059383e-05,
+      "loss": 64.3815,
+      "step": 1700
+    },
+    {
+      "epoch": 0.13426165678884477,
+      "grad_norm": 47.9273681640625,
+      "learning_rate": 8.65735767991407e-05,
+      "loss": 64.2401,
+      "step": 1750
+    },
+    {
+      "epoch": 0.1380977041256689,
+      "grad_norm": 29.331714630126953,
+      "learning_rate": 8.618996470768759e-05,
+      "loss": 63.8462,
+      "step": 1800
+    },
+    {
+      "epoch": 0.14193375146249304,
+      "grad_norm": 57.99611282348633,
+      "learning_rate": 8.580635261623447e-05,
+      "loss": 63.6392,
+      "step": 1850
+    },
+    {
+      "epoch": 0.14576979879931717,
+      "grad_norm": 54.53227233886719,
+      "learning_rate": 8.542274052478134e-05,
+      "loss": 63.5283,
+      "step": 1900
+    },
+    {
+      "epoch": 0.1496058461361413,
+      "grad_norm": 30.265884399414062,
+      "learning_rate": 8.503912843332822e-05,
+      "loss": 63.378,
+      "step": 1950
+    },
+    {
+      "epoch": 0.15344189347296547,
+      "grad_norm": 19.72339630126953,
+      "learning_rate": 8.46555163418751e-05,
+      "loss": 63.123,
+      "step": 2000
     }
   ],
   "logging_steps": 50,
@@ -236,7 +306,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.57076562005223e+18,
+  "total_flos": 3.4284373374266245e+18,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null