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:ad1aa5a6aae02bb7fc612c226782b2532fa37329e1010f72e27df037ab25cee6
+oid sha256:9b0dee2372e0f18f2926fc6260eec903f5561fa89a64d712e0b7d8365d17c593
 size 59827904

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8fe029025b390129dfda46b9ae7d3c4ae995b75c4e24acf8877cddb5262499fa
+oid sha256:3b975acebc204f6e79db6fa817f78ef570e8350fee5fb167ce316257a8482e30
 size 30875540

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:977ff09e0c2768597b76a3b64add1b9f5188e8ddfb34d4e801a7ae1dfcc89c53
+oid sha256:e0dfa4c978e9e36a07b5616ff9458f53247c12dc4ecf4c596cc8b6cb0fe8c5e1
 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": 9.3022,
       "step": 190
+    },
+    {
+      "epoch": 0.09340424231309982,
+      "grad_norm": Infinity,
+      "learning_rate": 1.3799252646597426e-06,
+      "loss": 9.6389,
+      "step": 191
+    },
+    {
+      "epoch": 0.09389326975976527,
+      "grad_norm": Infinity,
+      "learning_rate": 1.0908391628854041e-06,
+      "loss": 9.3169,
+      "step": 192
+    },
+    {
+      "epoch": 0.09438229720643071,
+      "grad_norm": 4.0833470417810227e+18,
+      "learning_rate": 8.355304489257254e-07,
+      "loss": 8.7958,
+      "step": 193
+    },
+    {
+      "epoch": 0.09487132465309615,
+      "grad_norm": Infinity,
+      "learning_rate": 6.140863104726391e-07,
+      "loss": 8.5085,
+      "step": 194
+    },
+    {
+      "epoch": 0.0953603520997616,
+      "grad_norm": Infinity,
+      "learning_rate": 4.2658237049655323e-07,
+      "loss": 9.1892,
+      "step": 195
     }
   ],
   "logging_steps": 1,
@@ -1404,7 +1439,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.188511384318771e+17,
+  "total_flos": 4.2987353681166336e+17,
   "train_batch_size": 3,
   "trial_name": null,
   "trial_params": null