Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e9ec579bd55556459515c7962500bfc24c9847d4c618c1964d8129c163ec858
+oid sha256:de22bde3c301ce01af8e89f3dbd3e0f8a50ecc00843e927fb39d0845fde5ea89
 size 45118424

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b37acda8782d478a2cda5dbc10e440a1040e2651c6ae5bc2b2212665952f3ff
+oid sha256:ccaf895e102502b007b8629c20e30aa460728bdc5c8656fb0be5bc75ba9e315d
 size 23159290

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:24df05627e2e86925ca37683e21f902381144a8ad40105a0738461c44ce5f2e2
+oid sha256:32fae2f082bc2b8a4f93f074fb88d1c6113a4081d21b0babdad2ac6534f83080
 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": 0.0008150291372916582,
+  "epoch": 0.0016300582745833164,
   "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": 1.2632,
       "step": 5
+    },
+    {
+      "epoch": 0.0009780349647499898,
+      "grad_norm": 1.1788365840911865,
+      "learning_rate": 0.00012,
+      "loss": 1.782,
+      "step": 6
+    },
+    {
+      "epoch": 0.0009780349647499898,
+      "eval_loss": 1.522881031036377,
+      "eval_runtime": 394.7109,
+      "eval_samples_per_second": 6.544,
+      "eval_steps_per_second": 3.273,
+      "step": 6
+    },
+    {
+      "epoch": 0.0011410407922083214,
+      "grad_norm": 1.252583384513855,
+      "learning_rate": 0.00014,
+      "loss": 1.5854,
+      "step": 7
+    },
+    {
+      "epoch": 0.0013040466196666532,
+      "grad_norm": 3.332509994506836,
+      "learning_rate": 0.00016,
+      "loss": 2.092,
+      "step": 8
+    },
+    {
+      "epoch": 0.0014670524471249848,
+      "grad_norm": 0.9126483201980591,
+      "learning_rate": 0.00018,
+      "loss": 1.5811,
+      "step": 9
+    },
+    {
+      "epoch": 0.0014670524471249848,
+      "eval_loss": 1.4459682703018188,
+      "eval_runtime": 393.4548,
+      "eval_samples_per_second": 6.565,
+      "eval_steps_per_second": 3.284,
+      "step": 9
+    },
+    {
+      "epoch": 0.0016300582745833164,
+      "grad_norm": 0.939946174621582,
+      "learning_rate": 0.0002,
+      "loss": 1.2683,
+      "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": 967722569564160.0,
+  "total_flos": 1935445139128320.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null