Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d90dd46819334ff29892ebe023c1086351e6c5d00209fb43f49c7a36b3ad8b80
+oid sha256:98397bf9fd7e81b116845bc0247e61c7238b315699f870a1ca2238dd7362021c
 size 161533192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:894051ba84b18c1e318d21026d7a8df02c1e7f6c9eba43a30a638efb4ab59e92
+oid sha256:6e22864e6c0f7e3883e26f53e90cfcf7d3180ccb51335e4f231270e564a8a35a
 size 82460660

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c7d6d2fea5cb2d6a3cad845e5270490a5c7edd9942bc0bd86e4689daeebe1e7
+oid sha256:ddcf7038476bef84b65789b15b15467397d2298671b204bfba007022f85ef2d5
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cda2d7da3ce8a95be6df505b84eace6ccd5aa18ffc6d1bcc9a79572045c8d78f
+oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.002823662289990117,
+  "epoch": 0.005647324579980234,
   "eval_steps": 3,
-  "global_step": 5,
+  "global_step": 10,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -58,6 +58,57 @@
       "learning_rate": 0.0001,
       "loss": 4.1929,
       "step": 5
+    },
+    {
+      "epoch": 0.0033883947479881405,
+      "grad_norm": 0.9634608626365662,
+      "learning_rate": 0.00012,
+      "loss": 3.5782,
+      "step": 6
+    },
+    {
+      "epoch": 0.0033883947479881405,
+      "eval_loss": 3.3583006858825684,
+      "eval_runtime": 483.2032,
+      "eval_samples_per_second": 1.544,
+      "eval_steps_per_second": 0.772,
+      "step": 6
+    },
+    {
+      "epoch": 0.003953127205986164,
+      "grad_norm": 0.9008206129074097,
+      "learning_rate": 0.00014,
+      "loss": 3.1416,
+      "step": 7
+    },
+    {
+      "epoch": 0.004517859663984188,
+      "grad_norm": 1.6466256380081177,
+      "learning_rate": 0.00016,
+      "loss": 3.4634,
+      "step": 8
+    },
+    {
+      "epoch": 0.005082592121982211,
+      "grad_norm": 1.5605720281600952,
+      "learning_rate": 0.00018,
+      "loss": 3.26,
+      "step": 9
+    },
+    {
+      "epoch": 0.005082592121982211,
+      "eval_loss": 3.190641164779663,
+      "eval_runtime": 482.9053,
+      "eval_samples_per_second": 1.545,
+      "eval_steps_per_second": 0.772,
+      "step": 9
+    },
+    {
+      "epoch": 0.005647324579980234,
+      "grad_norm": 1.0107780694961548,
+      "learning_rate": 0.0002,
+      "loss": 2.3809,
+      "step": 10
     }
   ],
   "logging_steps": 1,
@@ -72,12 +123,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 6990386933268480.0,
+  "total_flos": 1.398077386653696e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null