Training in progress, step 18, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:68385e2f57305aab8ffcadf610e875902d5899dfefe8caae7d4aa09aef07f0d8
+oid sha256:e5fd693e6ff375d02b620f26b32b599b5d1e4169fd83778fa25461beaa297299
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:598d6823601ef3d8b4e880600ab6b61a061acef8c5db652e43d40e49a94b6458
+oid sha256:787b784a4a6dd4e5c7e961f2510701b0001417d07c97fa1315af87db5dc03e92
 size 85723284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:332759cf7b5cf921f7c9ebfe29466512b01ff3dba8f0377398688b0a48981a95
+oid sha256:6cf30c4e1dfd3b199f004d48c615f0058d9d8168fc7715316fa0d2b53a3286f2
 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": 0.0008143690901687554,
+  "epoch": 0.0016287381803375108,
   "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": 12.933,
       "eval_steps_per_second": 1.617,
       "step": 9
+    },
+    {
+      "epoch": 0.0010858254535583405,
+      "grad_norm": 2.4520862102508545,
+      "learning_rate": 4.993910125649561e-05,
+      "loss": 0.9936,
+      "step": 12
+    },
+    {
+      "epoch": 0.0013572818169479257,
+      "grad_norm": 2.1917343139648438,
+      "learning_rate": 4.962019382530521e-05,
+      "loss": 0.7332,
+      "step": 15
+    },
+    {
+      "epoch": 0.0016287381803375108,
+      "grad_norm": 2.0286247730255127,
+      "learning_rate": 4.9031542398457974e-05,
+      "loss": 0.6707,
+      "step": 18
+    },
+    {
+      "epoch": 0.0016287381803375108,
+      "eval_loss": 0.708565354347229,
+      "eval_runtime": 1438.9184,
+      "eval_samples_per_second": 12.935,
+      "eval_steps_per_second": 1.617,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.299769309790208e+16,
+  "total_flos": 2.599538619580416e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null