Training in progress, step 95, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f637121ce35d5914bb4d4da56f0273cb33d6a87e092ad743032eb48d171a679e
+oid sha256:310684c461415e0f62ae581c5b75592546654a93bc7bb5bd0acd595778734a4b
 size 191968

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dba34b5c73d351a314fcc2d8ad1b544b2c4b4e98182c2cc8497d9a0f851e9866
+oid sha256:05279a72b8a85f85a81b4dca093186f30ace4416bff59d98d82e3d80607cc8a1
 size 253144

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:912547e3439c087a494b30d9f86b186e0f5dd1b1bc4e41596aeb4a26e2e169e9
+oid sha256:a09ac20c395c9ed5d9434cf9abe75b4c8e2dafd97fa0cdf706b7b28e5d097bad
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f6423aaf07b0a3e5bef1b21c59ae6d997dd59505ca758247471609a32b152cd
+oid sha256:60ca561a785d3802440b426c58aafe0f1cf10dc4bab5c0b5dbec38821026a8aa
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.16927634363097757,
+  "epoch": 0.20101565806178587,
   "eval_steps": 55,
-  "global_step": 80,
+  "global_step": 95,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -205,6 +205,41 @@
       "learning_rate": 3.12696703292044e-05,
       "loss": 10.2394,
       "step": 78
+    },
+    {
+      "epoch": 0.1713922979263648,
+      "grad_norm": 0.2242937535047531,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 10.2176,
+      "step": 81
+    },
+    {
+      "epoch": 0.17774016081252644,
+      "grad_norm": 0.3547563850879669,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 10.1373,
+      "step": 84
+    },
+    {
+      "epoch": 0.1840880236986881,
+      "grad_norm": 0.16841305792331696,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 10.2393,
+      "step": 87
+    },
+    {
+      "epoch": 0.19043588658484978,
+      "grad_norm": 0.223463773727417,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 10.2272,
+      "step": 90
+    },
+    {
+      "epoch": 0.19678374947101143,
+      "grad_norm": 0.21468529105186462,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 10.2198,
+      "step": 93
     }
   ],
   "logging_steps": 3,
@@ -219,12 +254,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2788766515200.0,
+  "total_flos": 3311660236800.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null