Training in progress, step 24, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f7253ba1237acfee8c78a3575cba5cfadccea4524aadeaacebe294db62c9f85d
+oid sha256:11067a4e0db7180e978b4680751a828e92fddd604955a774a9541dda8c89fec6
 size 2964338224

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:088943970770a526c2bcbbff1af74447c48df2eb3818f77c5660bb058e25196e
+oid sha256:5c14bc07640d4fa6ba0101c179b86e554410d022d886f62d6db2e15e49478a47
 size 1485440604

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6cd5cd4d318d8a5b26b81d3764647251e70de609f8492e3bb5f24f102d716e01
+oid sha256:42b568ba95f7567b0629ca524a99586d93f3235f65e98122124dda6ec920acd2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.1490125673249552,
+  "epoch": 1.3788150807899462,
   "eval_steps": 500,
-  "global_step": 20,
+  "global_step": 24,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -147,6 +147,34 @@
       "learning_rate": 4.301303984001967e-05,
       "loss": 2.0976,
       "step": 20
+    },
+    {
+      "epoch": 1.2064631956912029,
+      "grad_norm": 1.2366828918457031,
+      "learning_rate": 4.163314250413913e-05,
+      "loss": 2.0682,
+      "step": 21
+    },
+    {
+      "epoch": 1.2639138240574506,
+      "grad_norm": 1.3221453428268433,
+      "learning_rate": 4.015563527416595e-05,
+      "loss": 2.0266,
+      "step": 22
+    },
+    {
+      "epoch": 1.3213644524236985,
+      "grad_norm": 1.269490122795105,
+      "learning_rate": 3.858918875003053e-05,
+      "loss": 2.011,
+      "step": 23
+    },
+    {
+      "epoch": 1.3788150807899462,
+      "grad_norm": 1.2723491191864014,
+      "learning_rate": 3.694299546280657e-05,
+      "loss": 2.0503,
+      "step": 24
     }
   ],
   "logging_steps": 1,
@@ -166,7 +194,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.3667697985769472e+16,
+  "total_flos": 1.6461756269580288e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null