Training in progress, step 195, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8318c9dddfde2626e16874ceab9b5d73d41a57875ba111796e77fac52c497fe2
+oid sha256:f2677dd4a92b174119d84e1626685f2540ff3efdaac5ef15f2eefc7965415be8
 size 48679352

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9dd6070eee2e88beac2318243b02e70f68a06b1d2ce5278e1d7a89b7b0a14e01
+oid sha256:aa9ee12d2d1983b469d62c943ef7e32af98d0056c03fb247b708a5b815a83e52
 size 25152500

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6c22a61a5b47d1b3a3a2eb5d25761bba9dd7d0f656b8993398fcde00940b097b
+oid sha256:d725b764a9f7a07542bff2bd49e82f50571269a38edb42c4d371ddaac7f6a8e3
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b289b438571df9d34409287e67864402aaad98d9ecdf87ccd44b9abb7f5b6982
+oid sha256:a35430a05f2b9748f37dd11667a782564c85a35d840d60cbaddfa2c905ab7c0a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.09291521486643438,
+  "epoch": 0.0953603520997616,
   "eval_steps": 34,
-  "global_step": 190,
+  "global_step": 195,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1385,6 +1385,41 @@
       "learning_rate": 1.7026900316098215e-06,
       "loss": 1.1748,
       "step": 190
+    },
+    {
+      "epoch": 0.09340424231309982,
+      "grad_norm": 0.2973954677581787,
+      "learning_rate": 1.3799252646597426e-06,
+      "loss": 1.2553,
+      "step": 191
+    },
+    {
+      "epoch": 0.09389326975976527,
+      "grad_norm": 0.30735060572624207,
+      "learning_rate": 1.0908391628854041e-06,
+      "loss": 1.0603,
+      "step": 192
+    },
+    {
+      "epoch": 0.09438229720643071,
+      "grad_norm": 0.39257532358169556,
+      "learning_rate": 8.355304489257254e-07,
+      "loss": 1.0304,
+      "step": 193
+    },
+    {
+      "epoch": 0.09487132465309615,
+      "grad_norm": 0.31010863184928894,
+      "learning_rate": 6.140863104726391e-07,
+      "loss": 1.0806,
+      "step": 194
+    },
+    {
+      "epoch": 0.0953603520997616,
+      "grad_norm": 0.2375696897506714,
+      "learning_rate": 4.2658237049655323e-07,
+      "loss": 1.1009,
+      "step": 195
     }
   ],
   "logging_steps": 1,
@@ -1404,7 +1439,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.172497088315392e+17,
+  "total_flos": 3.255983853797376e+17,
   "train_batch_size": 3,
   "trial_name": null,
   "trial_params": null