Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:86e63f3d1bd3b0ed3da9fa4d0b9af4e535ea1f8aac5d732da421aed475bd1400
+oid sha256:4b3a6581ae97b021c5280e77b51d4bef4fd7d12057b347470336799cd93dfb36
 size 6804608

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d1d55489a11504df79570d1149a11d2496702532d1fd2f50147a70ee3590e5b1
+oid sha256:580627a591ab2e9562738dbf84f494f731c8564e463c36e050b81bed833bf321
 size 3633530

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:616dacf53bb8fbe792993ba3437fa1700d6e4e98de7f15a000b196b6dd6aa515
+oid sha256:d648a1322336ba65450c8c6b38551a9c8a4b8d3ca0a43997d4dca4e78ff923ae
 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": 8.42948211369264e-05,
+  "epoch": 0.0001264422317053896,
   "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": 72.354,
       "eval_steps_per_second": 36.177,
       "step": 6
+    },
+    {
+      "epoch": 9.83439579930808e-05,
+      "grad_norm": 13.912890434265137,
+      "learning_rate": 0.00014,
+      "loss": 12.4402,
+      "step": 7
+    },
+    {
+      "epoch": 0.0001123930948492352,
+      "grad_norm": 3.7871077060699463,
+      "learning_rate": 0.00016,
+      "loss": 10.6176,
+      "step": 8
+    },
+    {
+      "epoch": 0.0001264422317053896,
+      "grad_norm": 7.042935848236084,
+      "learning_rate": 0.00018,
+      "loss": 10.2955,
+      "step": 9
+    },
+    {
+      "epoch": 0.0001264422317053896,
+      "eval_loss": 11.75953197479248,
+      "eval_runtime": 408.0518,
+      "eval_samples_per_second": 73.447,
+      "eval_steps_per_second": 36.723,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 20575590285312.0,
+  "total_flos": 30863385427968.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null