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:a30687bcd005fcec158c28f62ace716be9c57679a57a2c352e2daea61d3a64ac
+oid sha256:fa8646cfe55f64b3a6c57958c653f73d38f54ddda9366931b6578a3d714d4eb1
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f834ae35b50d9b9fba36f0f4f6690c775ad958ecacde69108fd591e9ccff256b
+oid sha256:1d18fac1bc9609412e625f51458b57e0cb252eb09cd447176227cc0736a21ec0
 size 85723284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f9d63457fb0762bec521007b4b65dfde2dbfedf3cf13f579982482514a7d902
+oid sha256:094837089fa2ed1c4f9dc6c25bac04422ed41c22630725ca5cdf86ffa65f03cf
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a2972d8cacb091bd0e98bfff54b2e4933301753087ce149a9bf9a205a5e2d795
+oid sha256:cda2d7da3ce8a95be6df505b84eace6ccd5aa18ffc6d1bcc9a79572045c8d78f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.002122954444935869,
+  "epoch": 0.003184431667403804,
   "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": 5.104,
       "eval_steps_per_second": 5.104,
       "step": 6
+    },
+    {
+      "epoch": 0.002476780185758514,
+      "grad_norm": 87.67485046386719,
+      "learning_rate": 6e-05,
+      "loss": 12.3813,
+      "step": 7
+    },
+    {
+      "epoch": 0.002830605926581159,
+      "grad_norm": 123.6387939453125,
+      "learning_rate": 8e-05,
+      "loss": 17.1364,
+      "step": 8
+    },
+    {
+      "epoch": 0.003184431667403804,
+      "grad_norm": 77.38605499267578,
+      "learning_rate": 0.0001,
+      "loss": 11.6124,
+      "step": 9
+    },
+    {
+      "epoch": 0.003184431667403804,
+      "eval_loss": 2.0625381469726562,
+      "eval_runtime": 116.5884,
+      "eval_samples_per_second": 5.103,
+      "eval_steps_per_second": 5.103,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4220632417959936.0,
+  "total_flos": 6330948626939904.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null