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:c0335c6813b301c3b864907d00587eb6d699944df71348f257cb71caecf4df88
+oid sha256:431028f685a4d4db7044143e90d4c21084637610df285ed9f5e6d5cf413bdcf6
 size 63592

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f368c87329c93e3ff140f6c93b504044e95345f5052c76c8554cdb85d8b79a04
+oid sha256:96aabacb9e55661a7d45dc964d1bcfb3ee639b2a93be7e794ab4adfed4f81e72
 size 132798

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8cbc589a06e2970f3d1e1f484146819e64848b461fbefd953e917f429a552096
+oid sha256:bd53346fd5a654d3e32df025210c49ec943f00f49e54c4d7d1fb40b5ae52d930
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:55cc6a3635d19619caf820a77458fa3cfe7756f7bb9d10678c62733cb46f36c0
+oid sha256:1e2ed9259304616a8ecebc61c5d000777b2978635f7a705b8d7081c480ce0bde
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.004259246113437922,
+  "epoch": 0.0056789948179172284,
   "eval_steps": 5,
-  "global_step": 15,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -144,6 +144,49 @@
       "eval_samples_per_second": 149.79,
       "eval_steps_per_second": 74.946,
       "step": 15
+    },
+    {
+      "epoch": 0.004543195854333783,
+      "grad_norm": 1.0141512155532837,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 44.271,
+      "step": 16
+    },
+    {
+      "epoch": 0.004827145595229644,
+      "grad_norm": 1.2082080841064453,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 44.2314,
+      "step": 17
+    },
+    {
+      "epoch": 0.005111095336125505,
+      "grad_norm": 1.2328360080718994,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 44.2302,
+      "step": 18
+    },
+    {
+      "epoch": 0.005395045077021367,
+      "grad_norm": 0.9566083550453186,
+      "learning_rate": 4.8943483704846475e-06,
+      "loss": 44.2651,
+      "step": 19
+    },
+    {
+      "epoch": 0.0056789948179172284,
+      "grad_norm": 2.174668788909912,
+      "learning_rate": 0.0,
+      "loss": 44.195,
+      "step": 20
+    },
+    {
+      "epoch": 0.0056789948179172284,
+      "eval_loss": 11.055340766906738,
+      "eval_runtime": 9.8681,
+      "eval_samples_per_second": 150.283,
+      "eval_steps_per_second": 75.192,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -158,12 +201,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 63638077440.0,
+  "total_flos": 85162721280.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null