Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2118886d6bf5000c959e4169d1eeddb60efd33265883c2d05717616e54b92b20
+oid sha256:a6da54fde1b7ffda641ac9b2621b31d2d27ede33018baa00200a5d2ef7d517b7
 size 45118424

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c2d47150b764c434d5cc8d8f5478c93c589ec66689311099f7bc8a5e2ebaea9f
+oid sha256:7ec8d57cccb7e916765bd0ca2531abe28646537b852e782109867c4b3377cbbe
 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": 0.012894906511927788,
+  "epoch": 0.025789813023855575,
   "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": 0.8563,
       "step": 5
+    },
+    {
+      "epoch": 0.015473887814313346,
+      "grad_norm": 0.9101985692977905,
+      "learning_rate": 0.00012,
+      "loss": 0.8854,
+      "step": 6
+    },
+    {
+      "epoch": 0.015473887814313346,
+      "eval_loss": 0.9519971609115601,
+      "eval_runtime": 25.2384,
+      "eval_samples_per_second": 6.498,
+      "eval_steps_per_second": 3.249,
+      "step": 6
+    },
+    {
+      "epoch": 0.018052869116698903,
+      "grad_norm": 0.8173288702964783,
+      "learning_rate": 0.00014,
+      "loss": 0.9227,
+      "step": 7
+    },
+    {
+      "epoch": 0.020631850419084462,
+      "grad_norm": 0.7781127095222473,
+      "learning_rate": 0.00016,
+      "loss": 0.8288,
+      "step": 8
+    },
+    {
+      "epoch": 0.02321083172147002,
+      "grad_norm": 0.607376217842102,
+      "learning_rate": 0.00018,
+      "loss": 0.9619,
+      "step": 9
+    },
+    {
+      "epoch": 0.02321083172147002,
+      "eval_loss": 0.9006651639938354,
+      "eval_runtime": 25.2807,
+      "eval_samples_per_second": 6.487,
+      "eval_steps_per_second": 3.244,
+      "step": 9
+    },
+    {
+      "epoch": 0.025789813023855575,
+      "grad_norm": 0.6585434675216675,
+      "learning_rate": 0.0002,
+      "loss": 0.8898,
+      "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