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:b6667046d8b5a4ff3af285f3f345e00437ea76cbf6f9a4f1a446508bf4704ed2
+oid sha256:fcfacd5fb2948bcde69b20e18c78ce613b7402af888fddc72600e2cc4cf3c86c
 size 45118424

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:624c5b80e6b18fa413feb446c29718ec41f83ed03fb34a2468e5b5449cf2da27
+oid sha256:ae8b0868930c7eef1cd7253ff4cd6ce9a75832e886b8af46e4254b08fe472081
 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": 0.0008501594048884166,
+  "epoch": 0.0017003188097768332,
   "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": 1.2143,
       "step": 5
+    },
+    {
+      "epoch": 0.0010201912858660998,
+      "grad_norm": 1.040611743927002,
+      "learning_rate": 0.00012,
+      "loss": 0.9643,
+      "step": 6
+    },
+    {
+      "epoch": 0.0010201912858660998,
+      "eval_loss": 1.0490574836730957,
+      "eval_runtime": 376.4499,
+      "eval_samples_per_second": 6.58,
+      "eval_steps_per_second": 3.291,
+      "step": 6
+    },
+    {
+      "epoch": 0.0011902231668437832,
+      "grad_norm": 1.5477181673049927,
+      "learning_rate": 0.00014,
+      "loss": 1.2377,
+      "step": 7
+    },
+    {
+      "epoch": 0.0013602550478214665,
+      "grad_norm": 1.29509699344635,
+      "learning_rate": 0.00016,
+      "loss": 0.8408,
+      "step": 8
+    },
+    {
+      "epoch": 0.0015302869287991498,
+      "grad_norm": 1.7048213481903076,
+      "learning_rate": 0.00018,
+      "loss": 1.0168,
+      "step": 9
+    },
+    {
+      "epoch": 0.0015302869287991498,
+      "eval_loss": 0.952135443687439,
+      "eval_runtime": 376.1474,
+      "eval_samples_per_second": 6.585,
+      "eval_steps_per_second": 3.294,
+      "step": 9
+    },
+    {
+      "epoch": 0.0017003188097768332,
+      "grad_norm": 1.1248693466186523,
+      "learning_rate": 0.0002,
+      "loss": 0.9549,
+      "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