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:d0b3ddb24075672017937ed3bc3c47497af8691215538fe35cbcec9f3c590f24
+oid sha256:ee602a7deda3e01c9a69e15760e2a797b6ed6d78a587fd6f32c2260a5ff9cced
 size 25192496

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e183901845d2c7224b7e38ffba813ab5debef0ea6910db9a55e90175149f9479
+oid sha256:f6abaa768fea7930b48e2520249435132d80c44ea6aff3331b1b066af8794b94
 size 13005178

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1094888e690d760f5dc6beb93863816b44facd96c60f74f3826e1336734dec25
+oid sha256:130f83d7572933f80bdda13f98b642dbe09d56e48883a8ec5725d2ff52b6e465
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ccc7e73cc5879da996ace4c3a10d9efe08a100111973e801d61997747e95e982
+oid sha256:e69e2b49ea642509f0c688c16fb190b7cf27dac0a18903a5e2d1467d0343d8b8
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.009437386569872959,
+  "epoch": 0.012099213551119177,
   "eval_steps": 13,
-  "global_step": 39,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -312,6 +312,83 @@
       "eval_samples_per_second": 50.148,
       "eval_steps_per_second": 25.074,
       "step": 39
+    },
+    {
+      "epoch": 0.009679370840895343,
+      "grad_norm": 4.230708599090576,
+      "learning_rate": 2.9289321881345254e-05,
+      "loss": 6.783,
+      "step": 40
+    },
+    {
+      "epoch": 0.009921355111917725,
+      "grad_norm": 2.771728754043579,
+      "learning_rate": 2.3959403439996907e-05,
+      "loss": 5.4397,
+      "step": 41
+    },
+    {
+      "epoch": 0.010163339382940109,
+      "grad_norm": 2.9131264686584473,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 5.1459,
+      "step": 42
+    },
+    {
+      "epoch": 0.010405323653962493,
+      "grad_norm": 3.516796350479126,
+      "learning_rate": 1.4735983564590783e-05,
+      "loss": 4.8108,
+      "step": 43
+    },
+    {
+      "epoch": 0.010647307924984877,
+      "grad_norm": 2.349928379058838,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 5.0233,
+      "step": 44
+    },
+    {
+      "epoch": 0.010889292196007259,
+      "grad_norm": 3.442686080932617,
+      "learning_rate": 7.612046748871327e-06,
+      "loss": 5.8234,
+      "step": 45
+    },
+    {
+      "epoch": 0.011131276467029643,
+      "grad_norm": 4.57712459564209,
+      "learning_rate": 4.8943483704846475e-06,
+      "loss": 5.9854,
+      "step": 46
+    },
+    {
+      "epoch": 0.011373260738052027,
+      "grad_norm": 2.746769666671753,
+      "learning_rate": 2.7630079602323442e-06,
+      "loss": 6.1983,
+      "step": 47
+    },
+    {
+      "epoch": 0.01161524500907441,
+      "grad_norm": 3.05855655670166,
+      "learning_rate": 1.231165940486234e-06,
+      "loss": 4.7803,
+      "step": 48
+    },
+    {
+      "epoch": 0.011857229280096793,
+      "grad_norm": 2.8926703929901123,
+      "learning_rate": 3.0826662668720364e-07,
+      "loss": 5.5748,
+      "step": 49
+    },
+    {
+      "epoch": 0.012099213551119177,
+      "grad_norm": 3.569244861602783,
+      "learning_rate": 0.0,
+      "loss": 5.9647,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -326,12 +403,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1492861845504000.0,
+  "total_flos": 1910863162245120.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null