Training in progress, step 12, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:579c3ed68b3a3c96ad4fd0337d8c80697fed4efc4f8708830f12bede93a2e0ce
+oid sha256:a50310b6274b149eaf9b41e9d3a3a8bbadd0b1580f8c2c90f56923512e4aa0e6
 size 27024

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b68786650c623898a22093355a033da32c1f176f86fdbcf609deced0b9c5660
+oid sha256:93ab902db33f33d25537e4b5b40ad01e63f453104f563bea9fd7b2c98b64931e
 size 70922

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:56e4c605570ee3c73fe8ff5167e52a53ea3100415d1bfd842431b5b9a62a411e
+oid sha256:327540e290467d72686492f12b097459a06d803af478d6fa7b843fa1eab466b6
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c8e6b04902f17ae368c3e6cfd97a31ad4de2f025d673daea8c033ce0e260946
+oid sha256:a125c681316bfce03f3558f5956b9c0ad33dcb35c93b2ae66a440f25335c8901
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0006379585326953748,
+  "epoch": 0.0008506113769271664,
   "eval_steps": 3,
-  "global_step": 9,
+  "global_step": 12,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -102,6 +102,35 @@
       "eval_samples_per_second": 136.152,
       "eval_steps_per_second": 136.152,
       "step": 9
+    },
+    {
+      "epoch": 0.000708842814105972,
+      "grad_norm": 0.08561215549707413,
+      "learning_rate": 0.0002,
+      "loss": 10.382,
+      "step": 10
+    },
+    {
+      "epoch": 0.0007797270955165692,
+      "grad_norm": 0.09970103204250336,
+      "learning_rate": 0.00019781476007338058,
+      "loss": 10.389,
+      "step": 11
+    },
+    {
+      "epoch": 0.0008506113769271664,
+      "grad_norm": 0.09796269983053207,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 10.385,
+      "step": 12
+    },
+    {
+      "epoch": 0.0008506113769271664,
+      "eval_loss": 10.384222984313965,
+      "eval_runtime": 21.8059,
+      "eval_samples_per_second": 136.202,
+      "eval_steps_per_second": 136.202,
+      "step": 12
     }
   ],
   "logging_steps": 1,
@@ -121,7 +150,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 232756346880.0,
+  "total_flos": 310341795840.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null