Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d9f9f866c23a668c02a0ba1ebdcd38b0ba9337ccff85651adc36e20c6f0ce00
+oid sha256:2d65631f63710eef60db1df6ea21802b0102a05a0a33208fc3c04cf498ab7f6e
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43300016a86339335341a47c02e7b9f54ecd8ef8bb4c4bd04440ccc6b4a421df
+oid sha256:b739b7988211135826a1933575db03c251b4611b0de38bbee2e19ebe7f43c95b
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:98034a841a8af8a89a4f252e5ef6fd9b07235038469ab65e4215a2b643097c02
+oid sha256:40f97bfccd229445f360530dbc1fbaff299ee1ca72d89b2724959b4b2d971e0d
 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": 0.002340778308787672,
+  "epoch": 0.003511167463181508,
   "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": 18.66,
       "eval_steps_per_second": 9.33,
       "step": 6
+    },
+    {
+      "epoch": 0.0027309080269189503,
+      "grad_norm": 3.4334750175476074,
+      "learning_rate": 0.00014,
+      "loss": 3.3178,
+      "step": 7
+    },
+    {
+      "epoch": 0.003121037745050229,
+      "grad_norm": 3.7431459426879883,
+      "learning_rate": 0.00016,
+      "loss": 3.3982,
+      "step": 8
+    },
+    {
+      "epoch": 0.003511167463181508,
+      "grad_norm": 3.4571352005004883,
+      "learning_rate": 0.00018,
+      "loss": 3.3138,
+      "step": 9
+    },
+    {
+      "epoch": 0.003511167463181508,
+      "eval_loss": 0.7286794185638428,
+      "eval_runtime": 57.5525,
+      "eval_samples_per_second": 18.765,
+      "eval_steps_per_second": 9.383,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2059386998489088.0,
+  "total_flos": 3110988870057984.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null