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:ff6ff14986e8cb1c83960aa27bf4b5c1ab108d445933f9b2cff82b2055d9b0c3
+oid sha256:3c4ddb1ded69d70d1bb62d6c35b64b25ba8b88d8c206c1adef40825bd090132a
 size 45118424

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d6f44aa004a6745acf17f83369d1b969fa01a7bc554eb26883b2d0a5f676520
+oid sha256:26b7f00ba54fd4ef45ef715dd8bba6462bb31351ec20341fb3da9f1877c645d7
 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": 0.021052631578947368,
+  "epoch": 0.042105263157894736,
   "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": 1.2381,
       "step": 5
+    },
+    {
+      "epoch": 0.02526315789473684,
+      "grad_norm": 1.6964524984359741,
+      "learning_rate": 0.00012,
+      "loss": 1.4776,
+      "step": 6
+    },
+    {
+      "epoch": 0.02526315789473684,
+      "eval_loss": 1.2117630243301392,
+      "eval_runtime": 15.3111,
+      "eval_samples_per_second": 6.531,
+      "eval_steps_per_second": 3.266,
+      "step": 6
+    },
+    {
+      "epoch": 0.029473684210526315,
+      "grad_norm": 1.1385055780410767,
+      "learning_rate": 0.00014,
+      "loss": 1.3072,
+      "step": 7
+    },
+    {
+      "epoch": 0.03368421052631579,
+      "grad_norm": 1.230075716972351,
+      "learning_rate": 0.00016,
+      "loss": 1.6303,
+      "step": 8
+    },
+    {
+      "epoch": 0.037894736842105266,
+      "grad_norm": 1.3661742210388184,
+      "learning_rate": 0.00018,
+      "loss": 1.283,
+      "step": 9
+    },
+    {
+      "epoch": 0.037894736842105266,
+      "eval_loss": 1.2184972763061523,
+      "eval_runtime": 15.3612,
+      "eval_samples_per_second": 6.51,
+      "eval_steps_per_second": 3.255,
+      "step": 9
+    },
+    {
+      "epoch": 0.042105263157894736,
+      "grad_norm": 1.0414800643920898,
+      "learning_rate": 0.0002,
+      "loss": 1.4822,
+      "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