Training in progress, step 90, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:23f58b4a9202258b21beb132c01d655ad34106f9a0fb2e19af758715eb13b525
+oid sha256:cca4cfde1f99feabb8f5d5ccb09c595af064f92b12fdacb233b236b2bccf95b7
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac9d7f35a5b532bb3d04a2e6f3b80d1ed31906ac083164340272cd72ec9904c3
+oid sha256:61a7d2573a5a32007bd6c2ceadc59348a150768d242b854e6816b57621248000
 size 81730196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:979794a4a3185028b4f75463d82e4ab26027400d1e653ca29bde685c7d8d3488
+oid sha256:f65d33f8dbb303a0d5f68445f3c91506d6bca32bb2475114b5510685edbdcace
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90f7a57653bcfdeb8d3e27706e79cc5f6e1f14bbd0ff72a8e33edaaa89ef8274
+oid sha256:7f7d03f1dba06dbe949e0b7294b5a80e81e1c97413b12e930c7d1d62b4e569ba
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.05266579973992198,
+  "epoch": 0.05851755526657997,
   "eval_steps": 9,
-  "global_step": 81,
+  "global_step": 90,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -276,6 +276,35 @@
       "eval_samples_per_second": 11.044,
       "eval_steps_per_second": 1.381,
       "step": 81
+    },
+    {
+      "epoch": 0.054616384915474644,
+      "grad_norm": 1.0339871644973755,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 4.4122,
+      "step": 84
+    },
+    {
+      "epoch": 0.056566970091027305,
+      "grad_norm": 1.2999656200408936,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 4.9167,
+      "step": 87
+    },
+    {
+      "epoch": 0.05851755526657997,
+      "grad_norm": 0.8609194159507751,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 4.6119,
+      "step": 90
+    },
+    {
+      "epoch": 0.05851755526657997,
+      "eval_loss": 1.1394809484481812,
+      "eval_runtime": 234.4733,
+      "eval_samples_per_second": 11.05,
+      "eval_steps_per_second": 1.382,
+      "step": 90
     }
   ],
   "logging_steps": 3,
@@ -295,7 +324,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.0586127238535578e+17,
+  "total_flos": 1.1762363598372864e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null