Training in progress, step 81, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b640a13586a8ddaf8af206ceb427b23824056b8e5ac8f6466ee4942daea4a9d
+oid sha256:23ae89bac01b1983f47ebbd71598a57e302514078d431e7eb6afc8d73076643d
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f3e7d193b2ea8d745bf561d24fdf24f1260fdc96256c3c498b8b27226fe06be1
+oid sha256:09f2d66f12c15f1c195b4c65479573770a4b3f7f0e92412b2b62ed2e101441c9
 size 85723284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:455977057132821379da92f1a77f9b1f540991d9dd7c684ba956aca72c970f71
+oid sha256:eaef23ad6b9358048cfa2eb81866d8f39693a1c7df686b619cd9d9ea3051d3a5
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d899e046e5eb8fee9b81979db8db7b88d6dc92f30a13d049b906f3a3be1dfc0f
+oid sha256:bec84b33191b76a1f66109f05ca2863b65ba9c0ae66be6a4921ad95ad9f1a38e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.006514952721350043,
+  "epoch": 0.007329321811518798,
   "eval_steps": 9,
-  "global_step": 72,
+  "global_step": 81,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -247,6 +247,35 @@
       "eval_samples_per_second": 12.934,
       "eval_steps_per_second": 1.617,
       "step": 72
+    },
+    {
+      "epoch": 0.006786409084739628,
+      "grad_norm": 2.103365421295166,
+      "learning_rate": 8.930309757836517e-06,
+      "loss": 0.5615,
+      "step": 75
+    },
+    {
+      "epoch": 0.007057865448129213,
+      "grad_norm": 1.8247758150100708,
+      "learning_rate": 7.016504991533726e-06,
+      "loss": 0.4278,
+      "step": 78
+    },
+    {
+      "epoch": 0.007329321811518798,
+      "grad_norm": 2.0524744987487793,
+      "learning_rate": 5.299731159831953e-06,
+      "loss": 0.5058,
+      "step": 81
+    },
+    {
+      "epoch": 0.007329321811518798,
+      "eval_loss": 0.48786625266075134,
+      "eval_runtime": 1439.1036,
+      "eval_samples_per_second": 12.934,
+      "eval_steps_per_second": 1.617,
+      "step": 81
     }
   ],
   "logging_steps": 3,
@@ -266,7 +295,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.0398154478321664e+17,
+  "total_flos": 1.1697923788111872e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null