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:e1e4de72ee40562136cd4623647eda4b3e2d8100931a564d40222bfa708c37ab
+oid sha256:5c9ea197136412c298320477da31493c1e303dea2aa199643ebe4628c1975b1c
 size 14696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:caef1a8d2bc9533eea80c1156e3f3b7771926c0501e169ab561d155fa6e325ae
+oid sha256:13921336a7c3cf37284fa9824893b7e730bd24afd72e919fa4ee37e374778d3c
 size 39398

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c8f9bfbb25b5742af971410f7969204872224492d0748212c97b7e3aec33a144
+oid sha256:8b6a6a011f28f85007de1213aaf2d9d99df9d84c0278f3612751bd8de1562285
 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": 0.016689847009735744,
+  "epoch": 0.025034770514603615,
   "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": 181.685,
       "eval_steps_per_second": 90.843,
       "step": 6
+    },
+    {
+      "epoch": 0.019471488178025034,
+      "grad_norm": 0.006066080182790756,
+      "learning_rate": 0.00014,
+      "loss": 11.9294,
+      "step": 7
+    },
+    {
+      "epoch": 0.022253129346314324,
+      "grad_norm": 0.008948218077421188,
+      "learning_rate": 0.00016,
+      "loss": 11.9354,
+      "step": 8
+    },
+    {
+      "epoch": 0.025034770514603615,
+      "grad_norm": 0.007288319058716297,
+      "learning_rate": 0.00018,
+      "loss": 11.935,
+      "step": 9
+    },
+    {
+      "epoch": 0.025034770514603615,
+      "eval_loss": 11.932028770446777,
+      "eval_runtime": 0.8261,
+      "eval_samples_per_second": 183.991,
+      "eval_steps_per_second": 91.995,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1388396544.0,
+  "total_flos": 1979203584.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null