Training in progress, step 27, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3cb421132bc89a9c76e0db8bd08ac3b7183d01154ca6a751c2ae74ef88bdfe83
+oid sha256:9d78737a8c5017e576aa33e636aff5f03d2c8589e058c1f920084324d1f463ff
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:75bf40a6433f9b526167356c5bb1a12f0e5773676cdd39f94010c260da77fc2a
+oid sha256:4e0cc9f8a7409e541fb182a96e0e76bad78892039ee8aa3c2c1b1f8945a23b8d
 size 85723284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a8cb3fa95b19277c546f2944ac11cb384ba5fe8f2ef886c6f07e6edb2d31ba0
+oid sha256:0dd1a7ec32b6511f98f8fdc2427d030159b8d93f82e54abc269c1f81f1b4b37d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ed723721bc2dad2381ab5522e40123ba4aa738fa3e449c48809fa9c2697eb95
+oid sha256:bd4a07944f7914b974e23583756a2e0907223f4627a9b1ba247bd8f732140689
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.013937282229965157,
+  "epoch": 0.020905923344947737,
   "eval_steps": 9,
-  "global_step": 18,
+  "global_step": 27,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -73,6 +73,35 @@
       "eval_samples_per_second": 11.565,
       "eval_steps_per_second": 1.446,
       "step": 18
+    },
+    {
+      "epoch": 0.016260162601626018,
+      "grad_norm": 5.278903961181641,
+      "learning_rate": 9.635919272833938e-05,
+      "loss": 0.0318,
+      "step": 21
+    },
+    {
+      "epoch": 0.018583042973286876,
+      "grad_norm": 1.8316158056259155,
+      "learning_rate": 9.414737964294636e-05,
+      "loss": 0.0377,
+      "step": 24
+    },
+    {
+      "epoch": 0.020905923344947737,
+      "grad_norm": 0.3559686243534088,
+      "learning_rate": 9.145187862775209e-05,
+      "loss": 0.0169,
+      "step": 27
+    },
+    {
+      "epoch": 0.020905923344947737,
+      "eval_loss": 0.006285559851676226,
+      "eval_runtime": 188.0824,
+      "eval_samples_per_second": 11.569,
+      "eval_steps_per_second": 1.446,
+      "step": 27
     }
   ],
   "logging_steps": 3,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.376505934367949e+16,
+  "total_flos": 5.064758901551923e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null