Training in progress, step 65, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:63c7a01dc61b313d8583d8a08228880fa8842d92d780e7237646f2136eacf2ef
+oid sha256:e57994952775701010727b731745c577de0e9fe9d26c2a339a810c688b398388
 size 97307544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e14e1fa4ab8015d37e3149ec9b51c68e183b579f63215d86201930ce8313446
+oid sha256:c522a92351ac6bdc8c664ee803b651528514d928a5a42d1556a4e377d4283a97
 size 49846260

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:21365e7b00897a249521d8104e82416fb0f16cf5d8cfa1dac2b6d8f47f6a4b63
+oid sha256:2514d83dfe35d755cc78f91af8bb937820a9474979a674fc7a75720c6f7898b3
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:98afba9f38131883de969650d3feefb56184380f9dbf857187fdffd2e1ec0fc8
+oid sha256:ccd2b573b1eec8d0fb3b8a132ed34c8ce03266e455024ff257bb21f3e84c3669
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.07764477515367195,
+  "epoch": 0.08411517308314462,
   "eval_steps": 386,
-  "global_step": 60,
+  "global_step": 65,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -435,6 +435,41 @@
       "learning_rate": 9.999830024102874e-05,
       "loss": 0.9312,
       "step": 60
+    },
+    {
+      "epoch": 0.07893885473956648,
+      "grad_norm": 1.1909526586532593,
+      "learning_rate": 9.999794329409194e-05,
+      "loss": 0.9959,
+      "step": 61
+    },
+    {
+      "epoch": 0.08023293432546101,
+      "grad_norm": 0.9989166259765625,
+      "learning_rate": 9.999755235318337e-05,
+      "loss": 0.934,
+      "step": 62
+    },
+    {
+      "epoch": 0.08152701391135554,
+      "grad_norm": 1.0302046537399292,
+      "learning_rate": 9.999712741856889e-05,
+      "loss": 1.1017,
+      "step": 63
+    },
+    {
+      "epoch": 0.08282109349725009,
+      "grad_norm": 0.9583478569984436,
+      "learning_rate": 9.999666849053738e-05,
+      "loss": 1.1384,
+      "step": 64
+    },
+    {
+      "epoch": 0.08411517308314462,
+      "grad_norm": 1.001126766204834,
+      "learning_rate": 9.999617556940085e-05,
+      "loss": 0.9279,
+      "step": 65
     }
   ],
   "logging_steps": 1,
@@ -454,7 +489,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.707623030161408e+16,
+  "total_flos": 7.266591616008192e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null