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:e613f930d547332863452957fb45aa99653ab5ed08a4ec2af7186169d6916eef
+oid sha256:b8bdf7d6baf6a1ec958a49ad5f5c6436f502f5e6bded4b8110866df93e09c630
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a92016c661f957cfa6230a067c03e51d428c5fc5cc949b26801ad3821f179411
+oid sha256:fbbcb5fa3e4e4da5ba19d0a97b59fce7a66adc4571b4893b8b581a4268f74d48
 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": 0.006127398834092166,
+  "epoch": 0.006893323688353687,
   "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": 13.842,
       "eval_steps_per_second": 1.73,
       "step": 72
+    },
+    {
+      "epoch": 0.0063827071188460064,
+      "grad_norm": 2.891840696334839,
+      "learning_rate": 8.930309757836517e-06,
+      "loss": 4.4975,
+      "step": 75
+    },
+    {
+      "epoch": 0.006638015403599847,
+      "grad_norm": 2.6543121337890625,
+      "learning_rate": 7.016504991533726e-06,
+      "loss": 4.3666,
+      "step": 78
+    },
+    {
+      "epoch": 0.006893323688353687,
+      "grad_norm": 2.696539878845215,
+      "learning_rate": 5.299731159831953e-06,
+      "loss": 4.3767,
+      "step": 81
+    },
+    {
+      "epoch": 0.006893323688353687,
+      "eval_loss": 1.1115138530731201,
+      "eval_runtime": 1428.6614,
+      "eval_samples_per_second": 13.853,
+      "eval_steps_per_second": 1.732,
+      "step": 81
     }
   ],
   "logging_steps": 3,
@@ -266,7 +295,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.0125076377423053e+17,
+  "total_flos": 1.1390710924600934e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null