Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72306066c5c8abd8ae60be2d2862f0c41a31c70383bf5cb0318d1c2939445146
+oid sha256:ce80cec3357ff0a725f6b0c6f43c151f5d7d21b36d9441dbd9c86d6def4f2c57
 size 45118424

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd17945e61b5c49d548f2e122eeba67a5ada86d925593e1e630714b2712cf94f
+oid sha256:ccf11d1e42efe1d3b8743e3a388d9b8c41123f9cc52f1bf178bffff2ab3bd312
 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": 8.0012,
       "step": 5
+    },
+    {
+      "epoch": 0.015473887814313346,
+      "grad_norm": 16.180191040039062,
+      "learning_rate": 0.00012,
+      "loss": 7.3197,
+      "step": 6
+    },
+    {
+      "epoch": 0.015473887814313346,
+      "eval_loss": 6.428730487823486,
+      "eval_runtime": 23.797,
+      "eval_samples_per_second": 6.892,
+      "eval_steps_per_second": 3.446,
+      "step": 6
+    },
+    {
+      "epoch": 0.018052869116698903,
+      "grad_norm": 12.541686058044434,
+      "learning_rate": 0.00014,
+      "loss": 5.5577,
+      "step": 7
+    },
+    {
+      "epoch": 0.020631850419084462,
+      "grad_norm": 11.04792308807373,
+      "learning_rate": 0.00016,
+      "loss": 5.01,
+      "step": 8
+    },
+    {
+      "epoch": 0.02321083172147002,
+      "grad_norm": 12.31761646270752,
+      "learning_rate": 0.00018,
+      "loss": 5.0647,
+      "step": 9
+    },
+    {
+      "epoch": 0.02321083172147002,
+      "eval_loss": 3.7855212688446045,
+      "eval_runtime": 23.7876,
+      "eval_samples_per_second": 6.894,
+      "eval_steps_per_second": 3.447,
+      "step": 9
+    },
+    {
+      "epoch": 0.025789813023855575,
+      "grad_norm": 16.142803192138672,
+      "learning_rate": 0.0002,
+      "loss": 4.0176,
+      "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