Training in progress, step 40, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:15e78fa49fb00271ad118e01dad1e6674dfce4334a69cbe9e3cf1f3e76ece4a4
+oid sha256:f23294f8b89cf6925e8d59776d5a66dd2d4c6da2ed4d25863a2dd3fe47b031c5
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e12cf4a8339ad6e6ccc2e4a2b586e7d84e101d5a489f8144ee3b6d4413b9990
+oid sha256:5904f1110d6059c1226c28dec7c4e85eeb3cc24651b9e84f3a948758f7ec1fe9
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5daf23a304609686c8d20bb6fce1b79761fd95eb6abbd30d197b1a5200625adb
+oid sha256:ce9f59fd5c03d0708261ef0e7af3053978f1a8a6c1d8fb67d92ba701dee6b3ec
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0aa0f75a1f3e346be25756b578158b09a68943f0b9f1cfe29f97939687f864ef
+oid sha256:7c792918044964431737f4cb39f3769dbfd230048b1125ac69a6439eb6c8534b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.09690444145356662,
+  "epoch": 0.10767160161507403,
   "eval_steps": 4,
-  "global_step": 36,
+  "global_step": 40,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -339,6 +339,42 @@
       "eval_samples_per_second": 7.749,
       "eval_steps_per_second": 7.749,
       "step": 36
+    },
+    {
+      "epoch": 0.09959623149394348,
+      "grad_norm": 1.368626356124878,
+      "learning_rate": 4.7750143528405126e-05,
+      "loss": 0.4373,
+      "step": 37
+    },
+    {
+      "epoch": 0.10228802153432032,
+      "grad_norm": 0.7500585913658142,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 0.2919,
+      "step": 38
+    },
+    {
+      "epoch": 0.10497981157469717,
+      "grad_norm": 0.903423011302948,
+      "learning_rate": 3.5055195166981645e-05,
+      "loss": 0.3673,
+      "step": 39
+    },
+    {
+      "epoch": 0.10767160161507403,
+      "grad_norm": 0.7334548830986023,
+      "learning_rate": 2.9289321881345254e-05,
+      "loss": 0.2465,
+      "step": 40
+    },
+    {
+      "epoch": 0.10767160161507403,
+      "eval_loss": 0.27042919397354126,
+      "eval_runtime": 10.1181,
+      "eval_samples_per_second": 7.808,
+      "eval_steps_per_second": 7.808,
+      "step": 40
     }
   ],
   "logging_steps": 1,
@@ -358,7 +394,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.4745009760763904e+16,
+  "total_flos": 1.62287843278848e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null