Training in progress, step 95, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:984a7527231fdcf924c550cc4a8e0ad6fc5902a246abec109bf86ee6e40f3e96
+oid sha256:f9b8ed5bd2b484501ed9a9750ab3c46606b53a398ada09af49075cb9868a1dbd
 size 97307544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:69da363107c07a785017addea26230ce3041c8a5b658259b6c960c80f4cd4391
+oid sha256:873e123d716b4e3681b7bdcf8b6d4024d99e642a789148deeef040a213b7988f
 size 49846260

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8226228c393b137baf64ed3f82c6ed8807e456d3f8e179f09160bf26e5dcc037
+oid sha256:55974460331ed68231a1ad9dc00a5262b80738898a81bf122859c075aa9b16c2
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d72920266addd1520c8e9d88dcca5854048e355bd6edd8cc80e32e4e48b95586
+oid sha256:574ab12ec5e33abca7f4c7bc83b682560fcb2b9d98fc4110c6edb18204a6e3fe
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.11646716273050793,
+  "epoch": 0.12293756065998059,
   "eval_steps": 386,
-  "global_step": 90,
+  "global_step": 95,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -645,6 +645,41 @@
       "learning_rate": 9.997280616774147e-05,
       "loss": 1.1672,
       "step": 90
+    },
+    {
+      "epoch": 0.11776124231640246,
+      "grad_norm": 1.0035395622253418,
+      "learning_rate": 9.997142961110634e-05,
+      "loss": 0.9294,
+      "step": 91
+    },
+    {
+      "epoch": 0.11905532190229699,
+      "grad_norm": 1.1194915771484375,
+      "learning_rate": 9.997001907852635e-05,
+      "loss": 1.0857,
+      "step": 92
+    },
+    {
+      "epoch": 0.12034940148819152,
+      "grad_norm": 1.5234825611114502,
+      "learning_rate": 9.996857457096047e-05,
+      "loss": 1.027,
+      "step": 93
+    },
+    {
+      "epoch": 0.12164348107408605,
+      "grad_norm": 0.949878454208374,
+      "learning_rate": 9.996709608939088e-05,
+      "loss": 0.8173,
+      "step": 94
+    },
+    {
+      "epoch": 0.12293756065998059,
+      "grad_norm": 0.8736472129821777,
+      "learning_rate": 9.996558363482277e-05,
+      "loss": 0.855,
+      "step": 95
     }
   ],
   "logging_steps": 1,
@@ -664,7 +699,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.0061434545242112e+17,
+  "total_flos": 1.0620403131088896e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null