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:d3f3075c6ca5892b290c9ec2e545ac7d548616a9ac143b0bc178fdf05cbadd08
+oid sha256:ae0ef2768cbe8e74d6243ef58cc268fd401a78786630c176a9206a7f81982279
 size 41581360

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9db6a4cd3e7ccd98ddd5254b3b696128958172c9d71379ce00423a7f73b4e34a
+oid sha256:f6574f33386df2df75dfa587dc081e363023f42404246171b55d4bfb686086e8
 size 21505540

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:97a6caa870b6dc9a8c88458e23cc836a23db70a62629a6b0b992d3304258bab8
+oid sha256:e16ec8e925e5b9ae843bb76e4269fce7ee1835270ac93429d9b626791da9117e
 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": 0.03785488958990536,
+  "epoch": 0.056782334384858045,
   "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": 30.97,
       "eval_steps_per_second": 15.716,
       "step": 6
+    },
+    {
+      "epoch": 0.04416403785488959,
+      "grad_norm": 29.903905868530273,
+      "learning_rate": 0.00014,
+      "loss": 6.9666,
+      "step": 7
+    },
+    {
+      "epoch": 0.050473186119873815,
+      "grad_norm": 23.711275100708008,
+      "learning_rate": 0.00016,
+      "loss": 4.5659,
+      "step": 8
+    },
+    {
+      "epoch": 0.056782334384858045,
+      "grad_norm": 16.82898712158203,
+      "learning_rate": 0.00018,
+      "loss": 2.8434,
+      "step": 9
+    },
+    {
+      "epoch": 0.056782334384858045,
+      "eval_loss": 1.9197030067443848,
+      "eval_runtime": 2.1341,
+      "eval_samples_per_second": 31.395,
+      "eval_steps_per_second": 15.932,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 350068131495936.0,
+  "total_flos": 512599763976192.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null