Training in progress, step 90, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8a32db2828cd0be16ca1dc3270a14ecfcccac3e23ecb40538485602e53ee626
+oid sha256:46a287a3794fcb8dbbceecf2b88cc096624efe5b27177b5a1abef1ee12514a57
 size 59827904

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:67ffd950c52cfbd9f40af5c0a5c4c61abf9542c299135c6338adc11abc2b1dfe
+oid sha256:f91efb653a8a76c016afa4c81f46c30f802355e458aa26c84d7be92cc93de2f2
 size 30875540

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7168b0d6c665cd748268e687051b0b7d92835f5a5784945e8c1488a08a50658e
+oid sha256:1d7e9b37fba6634a583fc8b1bf58a4648f316317630483e214e684618a5aa0cb
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d9707e13ab424365dde92daf30c033711d2caa0fada77309f65d41532581807
+oid sha256:dfdc0543e9ce40f0d0b0ee9752d10d130598c759cc5a2bd973736f6096894d17
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.041567332966562745,
+  "epoch": 0.04401247019988997,
   "eval_steps": 34,
-  "global_step": 85,
+  "global_step": 90,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -626,6 +626,41 @@
       "learning_rate": 0.0001526432162877356,
       "loss": 8.1738,
       "step": 85
+    },
+    {
+      "epoch": 0.042056360413228196,
+      "grad_norm": Infinity,
+      "learning_rate": 0.0001510631193180907,
+      "loss": 9.8915,
+      "step": 86
+    },
+    {
+      "epoch": 0.04254538785989364,
+      "grad_norm": 2.3853981730414264e+18,
+      "learning_rate": 0.0001494655843399779,
+      "loss": 8.3371,
+      "step": 87
+    },
+    {
+      "epoch": 0.04303441530655908,
+      "grad_norm": Infinity,
+      "learning_rate": 0.00014785115691012864,
+      "loss": 8.893,
+      "step": 88
+    },
+    {
+      "epoch": 0.04352344275322453,
+      "grad_norm": Infinity,
+      "learning_rate": 0.00014622038835403133,
+      "loss": 8.3023,
+      "step": 89
+    },
+    {
+      "epoch": 0.04401247019988997,
+      "grad_norm": Infinity,
+      "learning_rate": 0.00014457383557765386,
+      "loss": 8.9136,
+      "step": 90
     }
   ],
   "logging_steps": 1,
@@ -645,7 +680,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.8738077245636608e+17,
+  "total_flos": 1.9840317083615232e+17,
   "train_batch_size": 3,
   "trial_name": null,
   "trial_params": null