Training in progress, step 37000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:66629fbba7f2d42de83407ccc7c4a7cb20d143079ca2ed45dbc07d04a90a40bf
+oid sha256:0fd691e92552d902e006c1dbd51666fbe879b2be04760327e9ca887670be688f
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d02b75121788cccbde8e0ee668a0edad332b5ebb58494b81e48d2fa78f15f7d
+oid sha256:f14ad18c691195cd15268660ba702ce3fc7337f8480e501b361bd9677af8b07e
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e9822f3fcdc1597872af5dd87f19db7e35ac92105cd8babdb7bf1d6ea8c5abd
+oid sha256:810ed5e7c2ae1b96c2bbc38902777e6779874b7cdcf097af17b2123a3bf9831a
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e696025a153a4c23b525b445028cbabae1500984cfdb159ce8be1d5922b1b1ea
+oid sha256:f866da3a9c3c847bb3514492ca12f1bdef65b499f47966b6692e65b75559e3e5
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.4333333333333336,
+  "epoch": 2.466666666666667,
   "eval_steps": 500,
-  "global_step": 36500,
+  "global_step": 37000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2578,6 +2578,41 @@
       "learning_rate": 3.7840000000000005e-06,
       "loss": 0.0445,
       "step": 36500
+    },
+    {
+      "epoch": 2.44,
+      "grad_norm": 0.07145357877016068,
+      "learning_rate": 3.7395555555555558e-06,
+      "loss": 0.0478,
+      "step": 36600
+    },
+    {
+      "epoch": 2.4466666666666668,
+      "grad_norm": 0.12996427714824677,
+      "learning_rate": 3.6951111111111114e-06,
+      "loss": 0.0501,
+      "step": 36700
+    },
+    {
+      "epoch": 2.453333333333333,
+      "grad_norm": 0.13270486891269684,
+      "learning_rate": 3.6506666666666666e-06,
+      "loss": 0.0542,
+      "step": 36800
+    },
+    {
+      "epoch": 2.46,
+      "grad_norm": 0.18757346272468567,
+      "learning_rate": 3.6062222222222227e-06,
+      "loss": 0.0522,
+      "step": 36900
+    },
+    {
+      "epoch": 2.466666666666667,
+      "grad_norm": 0.2180936336517334,
+      "learning_rate": 3.561777777777778e-06,
+      "loss": 0.0522,
+      "step": 37000
     }
   ],
   "logging_steps": 100,
@@ -2597,7 +2632,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8.890785202176e+16,
+  "total_flos": 9.012576780288e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null