Training in progress, step 2500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f80c9aca402cfbbf591e593318b9f70f957f0ab87eb54dd3bec7feb17dc184ef
+oid sha256:72117a71368ced5e54ae93d21ad8c58e91215e17e67c439bf35beb716448c540
 size 8137792

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:89cbc2c12d484f3a1336f266ba11e1ddd4cb9081c7fdc2b8f86d0ecfd16378fc
+oid sha256:90ec71681264a4e6df68bd6631ea2eedd8d07d066b65f39d1984f0723e362d2a
 size 16386426

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f7db8c8799503ac725f3e85e9e34a31747e78dbced1baebabe9003ce86bf931c
+oid sha256:edb8f7923ee0e8daac5e34b79e2823d1578191c5c180db7ca2ba4be0e2deec91
 size 15006

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b2319160d5dd25c12876dc189aa82af20f2eed3bcd566ffee789098a96fe3e2
+oid sha256:908e1b653c7ae160cec9eddd33f8d8b292344f12ebe951b0f4e9be7145ee92a3
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 4.799250117169192,
+  "epoch": 4.999218872051242,
   "eval_steps": 500,
-  "global_step": 2400,
+  "global_step": 2500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -207,6 +207,21 @@
       "learning_rate": 8.4e-05,
       "loss": 1.2801,
       "step": 2400
+    },
+    {
+      "epoch": 4.999218872051242,
+      "grad_norm": 0.14972414076328278,
+      "learning_rate": 8.333333333333334e-05,
+      "loss": 1.2854,
+      "step": 2500
+    },
+    {
+      "epoch": 4.999218872051242,
+      "eval_loss": 1.1568653583526611,
+      "eval_runtime": 780.3841,
+      "eval_samples_per_second": 19.89,
+      "eval_steps_per_second": 2.487,
+      "step": 2500
     }
   ],
   "logging_steps": 100,
@@ -226,7 +241,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.7457626810348995e+18,
+  "total_flos": 3.901837652223066e+18,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null