Training in progress, step 40, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:04ee1664bd29ace74cd834abf6756c1c6ad85e31fbf6b86e8e410e92077635c6
+oid sha256:17d8f9775ef2fc3a60893fdca6a2f8fbd01a155a36670674014b038c051fc527
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b31db628080555eedcc22be53e02e0d4a14ffe0bf6a0862b41c6b5703441cc5a
+oid sha256:82c445a33110cf590c00717fb81366f88f5a2e00b4e27ea9ef86d91ed7c3b78a
 size 168149074

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:866fac83e501a78c2e403a48d4ac843b9f01dc29bc6df7eeed2838bc1ca90679
+oid sha256:9ce5912b5c181cd4af1762a4a94b7debbebce7064999c1ea87bd89f515b28a5f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fbf1d1277664600b4e977089813b848af48515edea03c4bdcf1a506540fabd37
+oid sha256:7c792918044964431737f4cb39f3769dbfd230048b1125ac69a6439eb6c8534b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.1533406352683461,
+  "epoch": 0.17524644030668127,
   "eval_steps": 5,
-  "global_step": 35,
+  "global_step": 40,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -316,6 +316,49 @@
       "eval_samples_per_second": 9.406,
       "eval_steps_per_second": 4.751,
       "step": 35
+    },
+    {
+      "epoch": 0.15772179627601315,
+      "grad_norm": 0.09998418390750885,
+      "learning_rate": 5.4600950026045326e-05,
+      "loss": 0.0126,
+      "step": 36
+    },
+    {
+      "epoch": 0.16210295728368018,
+      "grad_norm": 0.060268584638834,
+      "learning_rate": 4.7750143528405126e-05,
+      "loss": 0.0054,
+      "step": 37
+    },
+    {
+      "epoch": 0.1664841182913472,
+      "grad_norm": 0.05094964802265167,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 0.0067,
+      "step": 38
+    },
+    {
+      "epoch": 0.17086527929901424,
+      "grad_norm": 0.07953735440969467,
+      "learning_rate": 3.5055195166981645e-05,
+      "loss": 0.0135,
+      "step": 39
+    },
+    {
+      "epoch": 0.17524644030668127,
+      "grad_norm": 0.07781189680099487,
+      "learning_rate": 2.9289321881345254e-05,
+      "loss": 0.0124,
+      "step": 40
+    },
+    {
+      "epoch": 0.17524644030668127,
+      "eval_loss": 0.01449812576174736,
+      "eval_runtime": 10.3095,
+      "eval_samples_per_second": 9.409,
+      "eval_steps_per_second": 4.753,
+      "step": 40
     }
   ],
   "logging_steps": 1,
@@ -335,7 +378,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.589389947404288e+16,
+  "total_flos": 2.959302797033472e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null