Training in progress, step 285, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:766bc29da4dd8f6ea69d080821e925bf3230dbf524883a26bacdbe8e6bdd7a55
+oid sha256:bff5ea59540fe9486298d16b1c5e07e830cb7454df8e49fb5701941042f38970
 size 97307544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7074266859ed51b765dcb9e59295560b54f7517b3b32919d5126064139e6615c
+oid sha256:cf8e705be49471bb0c8b7ab4e2654c27c1bbbac7d427de970d6341d4d6a51632
 size 49846644

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7be84e9390ed163408a0abac028539ac68753c7bc3079d2a87d83274ace9ae69
+oid sha256:2bd08400b897a4c94f407fc6f069e4949e235fcc43163cb517cd39dcd6f04847
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f975d6c1fc2270e579841b403d67bdb756eda7f69f91461b9a04eabdad070c25
+oid sha256:00305a50c12f8c5ecbafd69a728a0a7449bc703aaaf50988de0f32f2f4bdb6e8
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.3623422840504691,
+  "epoch": 0.36881268197994177,
   "eval_steps": 386,
-  "global_step": 280,
+  "global_step": 285,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1975,6 +1975,41 @@
       "learning_rate": 9.910351424831546e-05,
       "loss": 0.9349,
       "step": 280
+    },
+    {
+      "epoch": 0.36363636363636365,
+      "grad_norm": 0.8846459984779358,
+      "learning_rate": 9.909572540723202e-05,
+      "loss": 0.7986,
+      "step": 281
+    },
+    {
+      "epoch": 0.36493044322225815,
+      "grad_norm": 0.8271780610084534,
+      "learning_rate": 9.908790318560146e-05,
+      "loss": 0.8179,
+      "step": 282
+    },
+    {
+      "epoch": 0.3662245228081527,
+      "grad_norm": 0.8694506883621216,
+      "learning_rate": 9.908004758874216e-05,
+      "loss": 0.8453,
+      "step": 283
+    },
+    {
+      "epoch": 0.3675186023940472,
+      "grad_norm": 0.8625207543373108,
+      "learning_rate": 9.90721586219952e-05,
+      "loss": 0.7825,
+      "step": 284
+    },
+    {
+      "epoch": 0.36881268197994177,
+      "grad_norm": 0.8270084261894226,
+      "learning_rate": 9.906423629072434e-05,
+      "loss": 1.0889,
+      "step": 285
     }
   ],
   "logging_steps": 1,
@@ -1994,7 +2029,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.1302240807419904e+17,
+  "total_flos": 3.186120939326669e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null