Training in progress, step 190, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:216911c39630b8029330e697b538168e8e4a1fd44cef032ce0432f2a681df877
+oid sha256:a4a5c97dbf76ff33b307a5750999b650fdca855b6fccfb24cfb317d17b551db2
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5edfb201cf07670aa206c2100799f9f2d9aa5a4a7afd966ce133d52f87f58e8f
+oid sha256:e14756a84c0c36abc832c0c104bd27a99e8fd2062b9726fdee254c458fe1f7b4
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:44f07ee7727b2a57ec87aa201844eb2406bc5b699b1d99c8190698d036889705
+oid sha256:bf11cdd535ea662ff270636f900a467408683d2b7101cb9dbc848f0681f26dea
 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": 0.9719,
       "step": 185
+    },
+    {
+      "epoch": 0.0909591050797726,
+      "grad_norm": 0.26452943682670593,
+      "learning_rate": 3.3281595730812575e-06,
+      "loss": 0.9504,
+      "step": 186
+    },
+    {
+      "epoch": 0.09144813252643805,
+      "grad_norm": 0.36320924758911133,
+      "learning_rate": 2.8718968083886075e-06,
+      "loss": 1.1415,
+      "step": 187
+    },
+    {
+      "epoch": 0.09193715997310349,
+      "grad_norm": 0.24845726788043976,
+      "learning_rate": 2.4488032019563402e-06,
+      "loss": 1.0171,
+      "step": 188
+    },
+    {
+      "epoch": 0.09242618741976893,
+      "grad_norm": 0.5962578058242798,
+      "learning_rate": 2.0590232398634114e-06,
+      "loss": 0.9151,
+      "step": 189
+    },
+    {
+      "epoch": 0.09291521486643438,
+      "grad_norm": 0.3705110549926758,
+      "learning_rate": 1.7026900316098215e-06,
+      "loss": 1.1048,
+      "step": 190
     }
   ],
   "logging_steps": 1,
@@ -1369,7 +1404,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8.212065261767885e+17,
+  "total_flos": 8.434012971545395e+17,
   "train_batch_size": 3,
   "trial_name": null,
   "trial_params": null