Training in progress, step 18, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:06f8a8192c1c37aba820bf4da1c076b1441b4739eea1e6e728b5380c317e1731
+oid sha256:2830447767b7ed55beb40e131ec75361eaed5ad5254d093ed476e5b240d0c332
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:971526348a763b03750ab2ed05d50adbac972c474c22533364cfbad7c66c2e07
+oid sha256:8104df234be5d0a51cbe58cc1f91b229c5d3e07019eb8984ee7244ad2b61c376
 size 81730196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b021586ad95e1c2e97ec869a3b299cced93b91cacfdf2ed76c29bd8df15a09cb
+oid sha256:8b95368ad08097d0eab036ad0754a086d773cbf9ea3b711a05bf89fb2b621ff0
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d4d20cdfdd80bd4f7336e0d1d85ea3a727e6acd58210dc60f9f2cd451325f653
+oid sha256:e7f75dad5b4fa698adb63b89c53682112a536ec6b4f570bd7793123dfd2a0133
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.09836065573770492,
+  "epoch": 0.19672131147540983,
   "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": 15.484,
       "eval_steps_per_second": 2.011,
       "step": 9
+    },
+    {
+      "epoch": 0.13114754098360656,
+      "grad_norm": 1.64967942237854,
+      "learning_rate": 4.993910125649561e-05,
+      "loss": 8.735,
+      "step": 12
+    },
+    {
+      "epoch": 0.16393442622950818,
+      "grad_norm": 1.896277666091919,
+      "learning_rate": 4.962019382530521e-05,
+      "loss": 8.176,
+      "step": 15
+    },
+    {
+      "epoch": 0.19672131147540983,
+      "grad_norm": 1.1657590866088867,
+      "learning_rate": 4.9031542398457974e-05,
+      "loss": 7.7598,
+      "step": 18
+    },
+    {
+      "epoch": 0.19672131147540983,
+      "eval_loss": 1.973254680633545,
+      "eval_runtime": 9.9953,
+      "eval_samples_per_second": 15.407,
+      "eval_steps_per_second": 2.001,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.2088976735207424e+16,
+  "total_flos": 2.417795347041485e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null