Training in progress, step 18, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6bbd7e1be8bbb3868d8b1b53c8c91ce02f2da6d291d3d6acae587b3af532c560
+oid sha256:aa4260381083b222aecc224cd6f68a5aedff0d2947a843a1a4c66591bc35d925
 size 402688040

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e06bf7b979e50f9e07d88d17707f35bc5d01b78d738b02d54ab408ccae471f6a
+oid sha256:840c1ee366495267b1933eca7bb487fc23c79c9a1b10c6aa0e2a3081a0e3c33b
 size 204773716

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:70ccbad1612d7daf5dc583d6ae1187ddbe5614f2b80f2e1a9171293dbd04a9f5
+oid sha256:be8423cc9920092dc49fdcbf5a44ed945910b1f86985bc15e34fe153a16334ac
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1eca0ddb3ec890c90e8e6e7325bec40cdb8b59e4bebf5c0da8473b02809de875
+oid sha256:5ed723721bc2dad2381ab5522e40123ba4aa738fa3e449c48809fa9c2697eb95
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.09183673469387756,
+  "epoch": 0.1836734693877551,
   "eval_steps": 9,
-  "global_step": 9,
+  "global_step": 18,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -44,6 +44,35 @@
       "eval_samples_per_second": 14.817,
       "eval_steps_per_second": 1.886,
       "step": 9
+    },
+    {
+      "epoch": 0.12244897959183673,
+      "grad_norm": 5.729458332061768,
+      "learning_rate": 9.987820251299122e-05,
+      "loss": 7.2274,
+      "step": 12
+    },
+    {
+      "epoch": 0.15306122448979592,
+      "grad_norm": 5.534293174743652,
+      "learning_rate": 9.924038765061042e-05,
+      "loss": 7.2317,
+      "step": 15
+    },
+    {
+      "epoch": 0.1836734693877551,
+      "grad_norm": 6.290515899658203,
+      "learning_rate": 9.806308479691595e-05,
+      "loss": 7.4009,
+      "step": 18
+    },
+    {
+      "epoch": 0.1836734693877551,
+      "eval_loss": 1.7399932146072388,
+      "eval_runtime": 11.152,
+      "eval_samples_per_second": 14.796,
+      "eval_steps_per_second": 1.883,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6765120092897280.0,
+  "total_flos": 1.353024018579456e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null