Training in progress, step 25, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:791c778d50e613af2b99c77aca642cb9aee7567880abcf258132c18df775d086
+oid sha256:dbeb203f46fb1c1ec8f6e277a8fabff750773722580b461a96e1cbac96a2291f
 size 45118424

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2cb76dc8f7221ff9781f9474a0e568f828e3700c7b08284ec4b9c505e19679e9
+oid sha256:23e132835a2fd7e3ed3d5cfe045d84119b7967d8c3a6685bd84957e36e914460
 size 23159290

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:558b680d20c8a456dc87962293f6d283ceca35e3120c8340321f6e2afcd6b25f
+oid sha256:c7ec2f1de877992cebf6fbce0e472b6b0ae06bf82cd1caccb4ee85e3a5063b21
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c297c5cf11a27c75d9f99f1df69752f78c3ad41b0275adf50cdd1b67f9d0bb3
+oid sha256:3295bdd7cfd599ec7f00b8b43fe7ebc7026edcd2d9d9a208dde1fb88ec2e55ef
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.42105263157894735,
+  "epoch": 0.5263157894736842,
   "eval_steps": 8,
-  "global_step": 20,
+  "global_step": 25,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -171,6 +171,49 @@
       "learning_rate": 0.00019749279121818235,
       "loss": 1.3514,
       "step": 20
+    },
+    {
+      "epoch": 0.4421052631578947,
+      "grad_norm": 0.398816853761673,
+      "learning_rate": 0.0001969689520376687,
+      "loss": 1.0967,
+      "step": 21
+    },
+    {
+      "epoch": 0.4631578947368421,
+      "grad_norm": 0.30981966853141785,
+      "learning_rate": 0.00019639628606958533,
+      "loss": 1.1732,
+      "step": 22
+    },
+    {
+      "epoch": 0.4842105263157895,
+      "grad_norm": 0.33735471963882446,
+      "learning_rate": 0.00019577508166849304,
+      "loss": 1.2267,
+      "step": 23
+    },
+    {
+      "epoch": 0.5052631578947369,
+      "grad_norm": 0.4743439555168152,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 1.2174,
+      "step": 24
+    },
+    {
+      "epoch": 0.5052631578947369,
+      "eval_loss": 1.1610326766967773,
+      "eval_runtime": 2.0948,
+      "eval_samples_per_second": 47.737,
+      "eval_steps_per_second": 4.774,
+      "step": 24
+    },
+    {
+      "epoch": 0.5263157894736842,
+      "grad_norm": 0.3302611708641052,
+      "learning_rate": 0.00019438833303083678,
+      "loss": 1.199,
+      "step": 25
     }
   ],
   "logging_steps": 1,
@@ -190,7 +233,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2033729462599680.0,
+  "total_flos": 2528931246243840.0,
   "train_batch_size": 10,
   "trial_name": null,
   "trial_params": null