Training in progress, step 15, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e9ea66dd4489f55c292edd6ab8d9352d70360f9ad5a4ceab786a717ee5fd7974
+oid sha256:18380544eb6c248ace57d5b2611a8b5db4a345bf8dce5d46443b474710775615
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0aeca6749dd845c34cfa3cdf59a1bc387ddede928591cc424678f55715fb2f2f
+oid sha256:e8fb2e38ab6132834105e5cc2fe40cdcd9adc080a63012f4fec2d809cf6ccb9c
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d1bf24cd4bf25e308928bff2034c8266e5fe111aaec9b6d5c14e665ac843e0bc
+oid sha256:839ed907b4898f905e1782706e665b0346b345247c5e18f5c1f147e21076e284
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:67680b8b35ea230d53acee387012f8809825a2c511bd41340f42320f849e349d
+oid sha256:55cc6a3635d19619caf820a77458fa3cfe7756f7bb9d10678c62733cb46f36c0
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.004890274466654441,
+  "epoch": 0.007335411699981661,
   "eval_steps": 34,
-  "global_step": 10,
+  "global_step": 15,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -85,6 +85,41 @@
       "learning_rate": 6.666666666666667e-05,
       "loss": 1.2595,
       "step": 10
+    },
+    {
+      "epoch": 0.005379301913319885,
+      "grad_norm": 0.6462928652763367,
+      "learning_rate": 7.333333333333333e-05,
+      "loss": 1.3136,
+      "step": 11
+    },
+    {
+      "epoch": 0.005868329359985329,
+      "grad_norm": 0.514143168926239,
+      "learning_rate": 8e-05,
+      "loss": 1.1999,
+      "step": 12
+    },
+    {
+      "epoch": 0.006357356806650773,
+      "grad_norm": 0.43792784214019775,
+      "learning_rate": 8.666666666666667e-05,
+      "loss": 1.0675,
+      "step": 13
+    },
+    {
+      "epoch": 0.0068463842533162175,
+      "grad_norm": 0.6212848424911499,
+      "learning_rate": 9.333333333333334e-05,
+      "loss": 1.3066,
+      "step": 14
+    },
+    {
+      "epoch": 0.007335411699981661,
+      "grad_norm": 0.6186118125915527,
+      "learning_rate": 0.0001,
+      "loss": 1.2355,
+      "step": 15
     }
   ],
   "logging_steps": 1,
@@ -104,7 +139,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.438954195550208e+16,
+  "total_flos": 6.658431293325312e+16,
   "train_batch_size": 3,
   "trial_name": null,
   "trial_params": null