Training in progress, step 63, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1eecd25559c9189c8612de06e403e95edc7b91bb1570d780cb66259b876a5902
+oid sha256:fb97d9d163a73ea7f9751d1416577a26bb4b0dd126962fec44a06677503ff529
 size 34793120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d512dd2ac705c75c747ff69579fc5045a258495d0bc226e232574fce800ccdb2
+oid sha256:0227abca3d752bb4f21e6bead416e0d844ff970d3c99e49714c2d6eb85f9f259
 size 18132116

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d9412651d3546e8955cfba636a91b429e14260cf96ea084a0944945e5f2ed03
+oid sha256:3a505b6f4b73db6520699af0051d1b07d67320ce5266a6dfbde7ef46ef8dab4d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec430a8fba90f7f39f74e916eb32712c363a0fd20bb4904251fce0eb82f2b9cf
+oid sha256:922634a168fad3088c2a461ec82359f2941891b1472f492b835996e27c3cba9d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.7632508833922261,
+  "epoch": 0.8904593639575972,
   "eval_steps": 9,
-  "global_step": 54,
+  "global_step": 63,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -189,6 +189,35 @@
       "eval_samples_per_second": 40.017,
       "eval_steps_per_second": 5.002,
       "step": 54
+    },
+    {
+      "epoch": 0.8056537102473498,
+      "grad_norm": 0.05651354417204857,
+      "learning_rate": 2.3256088156396868e-05,
+      "loss": 2.4944,
+      "step": 57
+    },
+    {
+      "epoch": 0.8480565371024735,
+      "grad_norm": 0.06623954325914383,
+      "learning_rate": 2.0658795558326743e-05,
+      "loss": 2.4146,
+      "step": 60
+    },
+    {
+      "epoch": 0.8904593639575972,
+      "grad_norm": 0.059099238365888596,
+      "learning_rate": 1.8109066104575023e-05,
+      "loss": 2.5197,
+      "step": 63
+    },
+    {
+      "epoch": 0.8904593639575972,
+      "eval_loss": 2.3530490398406982,
+      "eval_runtime": 3.0239,
+      "eval_samples_per_second": 39.684,
+      "eval_steps_per_second": 4.96,
+      "step": 63
     }
   ],
   "logging_steps": 3,
@@ -208,7 +237,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6865241065390080.0,
+  "total_flos": 8009447909621760.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null