Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8fab06ea34f43af4705986620cfb869fd701ccc2708fd23dce4bcb1382de6cd3
+oid sha256:32d8a527b3a964032a82ee829afd0eeb6a0f464846d4874694016f9d030e33b4
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:52338f2f8a0528eb49cec35ce5e8af6f7d967c7adce88b3981d173b6218bff47
+oid sha256:f44cf1fb28af47ae24a2bc654af2df93445cf3327faf220ddecba08e100befaf
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bee1b249b23d3c7045b61d986525da9475988e143778f6c2587b190ecfa13a70
+oid sha256:f34bba95447e0ec764b895aa1b44bf630fd1c25c2065aec5f8a5c165a3d1b571
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c50dbaa792cda4a28fbbc2acb2a3e03c59530712bbc5107212d33064d193da4
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0032907921105368634,
+  "epoch": 0.00421896424427803,
   "eval_steps": 10,
-  "global_step": 39,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -88,6 +88,43 @@
       "learning_rate": 3.086582838174551e-05,
       "loss": 0.1035,
       "step": 35
+    },
+    {
+      "epoch": 0.0033751713954224237,
+      "grad_norm": 3.8980655670166016,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.0706,
+      "step": 40
+    },
+    {
+      "epoch": 0.0033751713954224237,
+      "eval_loss": 0.03316744044423103,
+      "eval_runtime": 416.306,
+      "eval_samples_per_second": 11.986,
+      "eval_steps_per_second": 5.993,
+      "step": 40
+    },
+    {
+      "epoch": 0.0037970678198502267,
+      "grad_norm": 1.4486910104751587,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.0732,
+      "step": 45
+    },
+    {
+      "epoch": 0.00421896424427803,
+      "grad_norm": 14.409627914428711,
+      "learning_rate": 0.0,
+      "loss": 0.1699,
+      "step": 50
+    },
+    {
+      "epoch": 0.00421896424427803,
+      "eval_loss": 0.03202228248119354,
+      "eval_runtime": 413.9912,
+      "eval_samples_per_second": 12.053,
+      "eval_steps_per_second": 6.027,
+      "step": 50
     }
   ],
   "logging_steps": 5,
@@ -102,12 +139,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 8631898695794688.0,
+  "total_flos": 1.0910369417527296e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null