Training in progress, step 40500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b86dc095c2649030c80dbb3b306b6dc458cfc29054732a394c23118a3921570
+oid sha256:a9879d5d88e7644494f4c879b1c5e524603249d32b69969a0534f73a0d99cdd8
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cbe16dcb2945b2b310dff07ecbc105e5d8932c93cc840533642e145b021fcd46
+oid sha256:b43d2d95bf538247d49799d209038264216cbb911042f24a24e56175bd002ec5
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:996bcc2fc9a86c5f72875fc2c94242013d036dcc7c497de3b8bae67dc7683e4b
+oid sha256:78de93de67391223b4c448919361f3b2f57691bd51a633014c5f582b70c0d977
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3bc8f3c97f58f2fb9ce92ef34272eb4a5ca6976677613743a4e1abd3e5adada4
+oid sha256:6aeb9cc77150e881276f00e59441fb5620f10d8b951379e0f05e5c2a60199333
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.6666666666666665,
+  "epoch": 2.7,
   "eval_steps": 500,
-  "global_step": 40000,
+  "global_step": 40500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2823,6 +2823,41 @@
       "learning_rate": 2.228888888888889e-06,
       "loss": 0.0502,
       "step": 40000
+    },
+    {
+      "epoch": 2.6733333333333333,
+      "grad_norm": 0.3002031147480011,
+      "learning_rate": 2.1844444444444446e-06,
+      "loss": 0.0525,
+      "step": 40100
+    },
+    {
+      "epoch": 2.68,
+      "grad_norm": 0.20131170749664307,
+      "learning_rate": 2.1400000000000003e-06,
+      "loss": 0.0489,
+      "step": 40200
+    },
+    {
+      "epoch": 2.6866666666666665,
+      "grad_norm": 0.134327694773674,
+      "learning_rate": 2.0955555555555555e-06,
+      "loss": 0.0526,
+      "step": 40300
+    },
+    {
+      "epoch": 2.6933333333333334,
+      "grad_norm": 0.208841010928154,
+      "learning_rate": 2.051111111111111e-06,
+      "loss": 0.0554,
+      "step": 40400
+    },
+    {
+      "epoch": 2.7,
+      "grad_norm": 0.1784680038690567,
+      "learning_rate": 2.006666666666667e-06,
+      "loss": 0.0529,
+      "step": 40500
     }
   ],
   "logging_steps": 100,
@@ -2842,7 +2877,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 9.74332624896e+16,
+  "total_flos": 9.865117827072e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null