Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d3d2aa559fa8d428c8e117e49acee69d2655e96a80e4616bf452e525b18de15f
+oid sha256:4e9ca11790735fcabf53acc64f6cee7d3a7e587302f3066d8ab7b794c3897ec3
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:66e12876464725b529354bc0df69f396e197848af89576d45ae1be086a402452
+oid sha256:8092270fb4a8f6a51e23cc8cafadea465a895f9a53b093a6ed029d1e40c75548
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f478f0c85c1033258c058dbb270fd910f4cfcd4116020451b8423efc28027c55
+oid sha256:8cde9ca23dfe033d10028cbe0dd91dfa734d0be4761346f37da51e83a1e32cda
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
+oid sha256:9c8e6b04902f17ae368c3e6cfd97a31ad4de2f025d673daea8c033ce0e260946
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 7.812347415089549e-05,
+  "epoch": 0.00011718521122634323,
   "eval_steps": 3,
-  "global_step": 6,
+  "global_step": 9,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -73,6 +73,35 @@
       "eval_samples_per_second": 14.82,
       "eval_steps_per_second": 7.41,
       "step": 6
+    },
+    {
+      "epoch": 9.114405317604474e-05,
+      "grad_norm": 1.0010603666305542,
+      "learning_rate": 0.00014,
+      "loss": 0.9171,
+      "step": 7
+    },
+    {
+      "epoch": 0.00010416463220119398,
+      "grad_norm": 1.1102145910263062,
+      "learning_rate": 0.00016,
+      "loss": 1.0455,
+      "step": 8
+    },
+    {
+      "epoch": 0.00011718521122634323,
+      "grad_norm": 2.4663655757904053,
+      "learning_rate": 0.00018,
+      "loss": 1.1359,
+      "step": 9
+    },
+    {
+      "epoch": 0.00011718521122634323,
+      "eval_loss": 0.8952555060386658,
+      "eval_runtime": 2178.9639,
+      "eval_samples_per_second": 14.841,
+      "eval_steps_per_second": 7.42,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1202216761294848.0,
+  "total_flos": 1757086035738624.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null