Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e2950de54c9d82f6bdedc849e61dd8d93cfd24e0290abe953823d0399254b32
+oid sha256:25046799da9cd14dbf2b191d19c4ea876482fef720612eae380d0e73c1f14370
 size 9864

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7976adf1c3f8235f36bf0ae01be2de677227f5623fcd8dd7a9fbdc076e440f60
+oid sha256:acd017759bc63b153d41d240c9a48e649af9c8e9de2a56de116602eee8854954
 size 27002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eea3c70b2d57c0a465ad1106d89bd6bdc5eaad90c7ca6addabcab15e4421426d
+oid sha256:da212283b2b7a0bbff4ab7ea6ad9a364cde6eea0958471709889adfdc18c077b
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b28ee0addfe1fdb5c9554035d0aace280dc61b8aded9640b8ddc91a063558e8
+oid sha256:22e67cb47ff12ababb2db5752a0059510ef75c13ebd9ed242d32d1eb2ba8aa08
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.006352567496029645,
+  "epoch": 0.01270513499205929,
   "eval_steps": 8,
-  "global_step": 10,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -44,6 +44,35 @@
       "learning_rate": 0.00027,
       "loss": 138.0,
       "step": 9
+    },
+    {
+      "epoch": 0.0076230809952355745,
+      "grad_norm": 2.7144717023475096e-05,
+      "learning_rate": 0.00029265847744427303,
+      "loss": 138.0,
+      "step": 12
+    },
+    {
+      "epoch": 0.009528851244044468,
+      "grad_norm": 2.6359681214671582e-05,
+      "learning_rate": 0.00025606601717798207,
+      "loss": 138.0,
+      "step": 15
+    },
+    {
+      "epoch": 0.010164107993647432,
+      "eval_loss": 11.5,
+      "eval_runtime": 23.7115,
+      "eval_samples_per_second": 125.804,
+      "eval_steps_per_second": 41.963,
+      "step": 16
+    },
+    {
+      "epoch": 0.011434621492853361,
+      "grad_norm": 3.279528027633205e-05,
+      "learning_rate": 0.0001963525491562421,
+      "loss": 138.0,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3351271440384.0,
+  "total_flos": 6567893581824.0,
   "train_batch_size": 3,
   "trial_name": null,
   "trial_params": null