Training in progress, step 54, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d13ab3ed212e21ed52f8f0a92452aa3d61afcea656510bd0bee79af1faf89852
+oid sha256:133eafb2c8e1df54efee04bef3768bd5313ac7c86b6624bced11cdd26471e4a8
 size 161533192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:003db3a9356c96106853c72a407f60220caf5ca6154babca4e94b404598b7683
+oid sha256:7b397d7d1a8907c16b9eff1fc545ec24762a907fe322532943c17793fe3cd228
 size 82460660

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d610764392ac240f248e060bc3ee4289569690c159fa277ffe5813b3bbe106d8
+oid sha256:b024515ce20a004b08c0bf3dc69a92c9aad8dfd484c2ab33afd709779025b6bc
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9776c8df8be516beee92201f32f4a3f5d90539bf47f8ef27e1636cdc132a851e
+oid sha256:ec430a8fba90f7f39f74e916eb32712c363a0fd20bb4904251fce0eb82f2b9cf
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.021948542860626752,
+  "epoch": 0.026338251432752105,
   "eval_steps": 9,
-  "global_step": 45,
+  "global_step": 54,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -160,6 +160,35 @@
       "eval_samples_per_second": 12.133,
       "eval_steps_per_second": 1.518,
       "step": 45
+    },
+    {
+      "epoch": 0.023411779051335204,
+      "grad_norm": 0.530996561050415,
+      "learning_rate": 3.104804738999169e-05,
+      "loss": 0.8087,
+      "step": 48
+    },
+    {
+      "epoch": 0.024875015242043653,
+      "grad_norm": 0.4066341519355774,
+      "learning_rate": 2.8479327524001636e-05,
+      "loss": 0.757,
+      "step": 51
+    },
+    {
+      "epoch": 0.026338251432752105,
+      "grad_norm": 0.49550753831863403,
+      "learning_rate": 2.587248741756253e-05,
+      "loss": 0.8163,
+      "step": 54
+    },
+    {
+      "epoch": 0.026338251432752105,
+      "eval_loss": 0.7791209816932678,
+      "eval_runtime": 284.3762,
+      "eval_samples_per_second": 12.142,
+      "eval_steps_per_second": 1.519,
+      "step": 54
     }
   ],
   "logging_steps": 3,
@@ -179,7 +208,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7.339906279931904e+16,
+  "total_flos": 8.842839470584627e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null