Training in progress, step 570, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cdb8ebe1fdeaef6e74e23d6dfb833ade6a25cee79d23f802b9013874b57d4eee
+oid sha256:4584dc7b0cb76f460c8d711cb91e7a00115c4b8b6e4c5f64c026bab2b1ffec56
 size 97307544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9411786f9b96464651735395a94e7711e9840e8e226611003010c107f2f57342
+oid sha256:e34737a84c54468cc2ddb658609e3abb120334092064eaaf03c2dd0f9ccf8bfa
 size 49846644

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:95e1a0472a4b7efd6160b24567cef071ac85a9b8b7bcca2274aa35f9ad966be1
+oid sha256:e31720c6202686d6b213f1d4f529251465f67b801085538ab4bd286d72ff5e4d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a81c2473e91beba8f8b9fa27ab4fd41402b289ee84be898e2c7de1d41842ce6e
+oid sha256:cac34b28e1ee591b304cbd862bb43f437e9105f534e9b2ad7a541d74d74af47f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.7311549660304109,
+  "epoch": 0.7376253639598835,
   "eval_steps": 386,
-  "global_step": 565,
+  "global_step": 570,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3978,6 +3978,41 @@
       "learning_rate": 9.555912937606895e-05,
       "loss": 0.8989,
       "step": 565
+    },
+    {
+      "epoch": 0.7324490456163054,
+      "grad_norm": 0.8132615089416504,
+      "learning_rate": 9.554212773629164e-05,
+      "loss": 0.809,
+      "step": 566
+    },
+    {
+      "epoch": 0.7337431252022,
+      "grad_norm": 0.9693892002105713,
+      "learning_rate": 9.552509513208456e-05,
+      "loss": 0.959,
+      "step": 567
+    },
+    {
+      "epoch": 0.7350372047880944,
+      "grad_norm": 0.8740898966789246,
+      "learning_rate": 9.550803157502831e-05,
+      "loss": 0.9758,
+      "step": 568
+    },
+    {
+      "epoch": 0.736331284373989,
+      "grad_norm": 0.8451546430587769,
+      "learning_rate": 9.549093707672453e-05,
+      "loss": 0.9776,
+      "step": 569
+    },
+    {
+      "epoch": 0.7376253639598835,
+      "grad_norm": 0.8144363760948181,
+      "learning_rate": 9.54738116487959e-05,
+      "loss": 0.8114,
+      "step": 570
     }
   ],
   "logging_steps": 1,
@@ -3997,7 +4032,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.316345020068659e+17,
+  "total_flos": 6.372241878653338e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null