Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8bd946391f5a81b5c64ee949613eac64881429fc1ac1869b53df434bb7652a67
+oid sha256:e2665116653644186ff9e8438580419e056be8f4f53af06d3589adeccf385503
 size 26008

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:12ae458744f71d0ddf91c37f5814d2e35276a3bdeb97009a2769523faa1fcfde
+oid sha256:ee94bb166345d91eb99fe7cc897407a45042956050271205fc42ba0ee06cb93b
 size 68874

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e97ead28242dd097af80112cb3bd8d751944021cbf255fca1535e0f2a22344d9
+oid sha256:c5288ed9323916daf49e9e619b5ce81ab40c19e01021e3ee0c12210ac8bab7de
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
+oid sha256:a62e6ea25099651400ff4a3142a50e40bef5b52ba883be53b2fcb9d1a5b0a98c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0364963503649635,
+  "epoch": 0.072992700729927,
   "eval_steps": 5,
-  "global_step": 10,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -52,6 +52,43 @@
       "eval_samples_per_second": 108.773,
       "eval_steps_per_second": 54.386,
       "step": 10
+    },
+    {
+      "epoch": 0.043795620437956206,
+      "grad_norm": 0.02010119892656803,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 11.9369,
+      "step": 12
+    },
+    {
+      "epoch": 0.05474452554744526,
+      "grad_norm": 0.017448164522647858,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 11.9364,
+      "step": 15
+    },
+    {
+      "epoch": 0.05474452554744526,
+      "eval_loss": 11.936670303344727,
+      "eval_runtime": 1.0228,
+      "eval_samples_per_second": 113.41,
+      "eval_steps_per_second": 56.705,
+      "step": 15
+    },
+    {
+      "epoch": 0.06569343065693431,
+      "grad_norm": 0.02098945714533329,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 11.9356,
+      "step": 18
+    },
+    {
+      "epoch": 0.072992700729927,
+      "eval_loss": 11.936407089233398,
+      "eval_runtime": 1.0226,
+      "eval_samples_per_second": 113.436,
+      "eval_steps_per_second": 56.718,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -71,7 +108,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3747348480.0,
+  "total_flos": 7494696960.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null