Training in progress, step 190, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:776cec9cf12dba4edbc666da11f20f14eff4789b304a641b85c8b02060d2f9fc
+oid sha256:8318c9dddfde2626e16874ceab9b5d73d41a57875ba111796e77fac52c497fe2
 size 48679352

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:84601093108a66d9bc78ce4988113205ced8e3faec71d2128b66c8bf76bb4bff
+oid sha256:9dd6070eee2e88beac2318243b02e70f68a06b1d2ce5278e1d7a89b7b0a14e01
 size 25152500

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d7ba1183a4e6a2706678b09a9085a1829e9abfdfbc778423e9dab06b73f84622
+oid sha256:6c22a61a5b47d1b3a3a2eb5d25761bba9dd7d0f656b8993398fcde00940b097b
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:31cc4c125027b06153274d1c1fcc2291ff49e04af7d8c2cae65dd480bfd90a0c
+oid sha256:b289b438571df9d34409287e67864402aaad98d9ecdf87ccd44b9abb7f5b6982
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.09047007763310716,
+  "epoch": 0.09291521486643438,
   "eval_steps": 34,
-  "global_step": 185,
+  "global_step": 190,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1350,6 +1350,41 @@
       "learning_rate": 3.817435682718096e-06,
       "loss": 1.0669,
       "step": 185
+    },
+    {
+      "epoch": 0.0909591050797726,
+      "grad_norm": 0.2308908998966217,
+      "learning_rate": 3.3281595730812575e-06,
+      "loss": 1.0341,
+      "step": 186
+    },
+    {
+      "epoch": 0.09144813252643805,
+      "grad_norm": 0.28636959195137024,
+      "learning_rate": 2.8718968083886075e-06,
+      "loss": 1.2459,
+      "step": 187
+    },
+    {
+      "epoch": 0.09193715997310349,
+      "grad_norm": 0.2441776990890503,
+      "learning_rate": 2.4488032019563402e-06,
+      "loss": 1.0977,
+      "step": 188
+    },
+    {
+      "epoch": 0.09242618741976893,
+      "grad_norm": 0.4734705686569214,
+      "learning_rate": 2.0590232398634114e-06,
+      "loss": 1.0091,
+      "step": 189
+    },
+    {
+      "epoch": 0.09291521486643438,
+      "grad_norm": 0.32178983092308044,
+      "learning_rate": 1.7026900316098215e-06,
+      "loss": 1.1748,
+      "step": 190
     }
   ],
   "logging_steps": 1,
@@ -1369,7 +1404,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.089010322833408e+17,
+  "total_flos": 3.172497088315392e+17,
   "train_batch_size": 3,
   "trial_name": null,
   "trial_params": null