Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10a6a1ffd64f7e05989c88da7f083032e30095579a92a376504f200c0e4fe511
+oid sha256:962d4f515eda7abf090901bb2bc8a31d37b413effdae7d8fbf317a2061bebbf0
 size 5327744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb818be4e19bb55e58e93748844a948c4857805febaf9a0d775da2c57164b3ea
+oid sha256:db8eceda1b551fabf756cfa8cfaa79be6acf136ad75c9de85e4c102c33a257a2
 size 2857722

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6463ff3f0292c2f4dc253548d03eb324fc2ec5143a5cd37816a281f3c32c0ff4
+oid sha256:0cda0ba450d27bbf2281f6a3a6a9d6b8e9a27248312721aa88724608eaf3ee7a
 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": 0.0004409414099101582,
+  "epoch": 0.0006614121148652373,
   "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": 132.692,
       "eval_steps_per_second": 66.346,
       "step": 6
+    },
+    {
+      "epoch": 0.0005144316448951845,
+      "grad_norm": 7.660728931427002,
+      "learning_rate": 0.00014,
+      "loss": 14.763,
+      "step": 7
+    },
+    {
+      "epoch": 0.0005879218798802109,
+      "grad_norm": 6.398442268371582,
+      "learning_rate": 0.00016,
+      "loss": 13.3612,
+      "step": 8
+    },
+    {
+      "epoch": 0.0006614121148652373,
+      "grad_norm": 7.0156145095825195,
+      "learning_rate": 0.00018,
+      "loss": 12.6919,
+      "step": 9
+    },
+    {
+      "epoch": 0.0006614121148652373,
+      "eval_loss": 3.3300187587738037,
+      "eval_runtime": 43.082,
+      "eval_samples_per_second": 133.002,
+      "eval_steps_per_second": 66.501,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 12737706983424.0,
+  "total_flos": 19106560475136.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null