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:f7daaf51f3cc455e2138ff58283519d242cd7e85f565d08f363ae131f5abbc20
+oid sha256:f68589cc9e840a9d2cf1e9bbd7a73b257ada3360a9e37027ae511224563a5b21
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0288ad511b4a2a84815dde298475ee9c70959c7b339b8ab9a53c544506c21672
+oid sha256:d62bd2094db4b5c03761e8383c99fead7d40d01106f96385073ec8f6a302edc4
 size 85723284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d478d6bfdc4a22cc9744896e3b50e5ddeee0db93a0a74564602341cc9b34247e
+oid sha256:c2b7e3f7f3d4cdab0671ff5feab74498bf3ca02bf473edcf2d1ddaa38062dddc
 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": 0.3237410071942446,
+  "epoch": 0.38848920863309355,
   "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": 12.099,
       "eval_steps_per_second": 1.551,
       "step": 45
+    },
+    {
+      "epoch": 0.34532374100719426,
+      "grad_norm": 2.3433644771575928,
+      "learning_rate": 3.104804738999169e-05,
+      "loss": 4.616,
+      "step": 48
+    },
+    {
+      "epoch": 0.3669064748201439,
+      "grad_norm": 1.8417110443115234,
+      "learning_rate": 2.8479327524001636e-05,
+      "loss": 3.9965,
+      "step": 51
+    },
+    {
+      "epoch": 0.38848920863309355,
+      "grad_norm": 2.258572578430176,
+      "learning_rate": 2.587248741756253e-05,
+      "loss": 4.2638,
+      "step": 54
+    },
+    {
+      "epoch": 0.38848920863309355,
+      "eval_loss": 1.0222728252410889,
+      "eval_runtime": 19.3615,
+      "eval_samples_per_second": 12.086,
+      "eval_steps_per_second": 1.549,
+      "step": 54
     }
   ],
   "logging_steps": 3,
@@ -179,7 +208,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7.66411153562665e+16,
+  "total_flos": 9.246152907659674e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null