Training in progress, step 165, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:53bad8d26f88728dcad49d9d67620340a524e6147bc3971fc55bb8b1402df5b4
+oid sha256:f9354ab4a7ce8547671b14d84f50c16c066ccb67d905ae21bb089417cb3367e5
 size 59827904

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ecd579c529539ff37f6b6ff96f02721f0d3685a0b8a5cfa862e349f56ed45cd0
+oid sha256:fb39ebd7a334944e5a271162b8f2bd07cc32d5062d51c937404ee4aad36c5bb8
 size 30875540

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a492bc11190965aaac7d5575038263ec57f90649266f6d672b0255bafe0953f
+oid sha256:7ae36b88f579a5ac24bd63c58055344d0b6ee1ce3c4b9a88d6e3a11fff784ffe
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fda70a7e2255bb2a6bed4064da315669732f8ee1496404c42573741f484eb69b
+oid sha256:b9d255475980828d00dffcac4a69741da74c7e5ef4f645ab21d69e57306e3317
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.07824439146647105,
+  "epoch": 0.08068952869979827,
   "eval_steps": 34,
-  "global_step": 160,
+  "global_step": 165,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1167,6 +1167,41 @@
       "learning_rate": 2.6099108277934103e-05,
       "loss": 10.5182,
       "step": 160
+    },
+    {
+      "epoch": 0.0787334189131365,
+      "grad_norm": 1.8735052790064742e+18,
+      "learning_rate": 2.4866811044312665e-05,
+      "loss": 9.7353,
+      "step": 161
+    },
+    {
+      "epoch": 0.07922244635980194,
+      "grad_norm": 1.1486916833747927e+19,
+      "learning_rate": 2.36601717258897e-05,
+      "loss": 8.3726,
+      "step": 162
+    },
+    {
+      "epoch": 0.07971147380646738,
+      "grad_norm": Infinity,
+      "learning_rate": 2.2479602388887012e-05,
+      "loss": 9.6089,
+      "step": 163
+    },
+    {
+      "epoch": 0.08020050125313283,
+      "grad_norm": Infinity,
+      "learning_rate": 2.132550619665168e-05,
+      "loss": 8.7235,
+      "step": 164
+    },
+    {
+      "epoch": 0.08068952869979827,
+      "grad_norm": Infinity,
+      "learning_rate": 2.0198277271976052e-05,
+      "loss": 8.9486,
+      "step": 165
     }
   ],
   "logging_steps": 1,
@@ -1186,7 +1221,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.527167481531597e+17,
+  "total_flos": 3.637391465329459e+17,
   "train_batch_size": 3,
   "trial_name": null,
   "trial_params": null