Training in progress, epoch 1, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e8a25da8297e93942e4f4f3123fe0abe8ed413a42f9ed244bdb442015acf5868
+oid sha256:690a76f619e21b48558756b8bbec56e79b8371b898fa88f7167d9f424eefcef5
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:754a392aa2efc3b179115b83d68c1db605a09b567413d573f37feb4f2f61bc97
+oid sha256:9db567843af32e4c52bfb860b334bbfb9a5ec1354cba8ac858584c7d5840cbc4
 size 671473298

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:50230aece8ef23936030fb9dcc64f50e28a42b78d5375eed902f9a55c400ebbf
+oid sha256:2b35c00f4803911ea6635aaeb44357adb5dba1b1bd1abf48a8ec2c30fbc3caee
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e4f49bf404f521f8f5c3a8ed01e62c6d21f591d6fed46c8b9eaac6da87530db8
+oid sha256:891cad020bf7bee78efa739dc10e1e4315e34b096ed70226b38590ec81d7d418
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.9998204345483929,
+  "epoch": 1.0773927096426648,
   "eval_steps": 500,
-  "global_step": 1392,
+  "global_step": 1500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1393,6 +1393,118 @@
       "learning_rate": 1.6271353668471655e-06,
       "loss": 11.2749,
       "step": 1386
+    },
+    {
+      "epoch": 1.0005386963548213,
+      "grad_norm": 18.41912078857422,
+      "learning_rate": 1.4343784586718311e-06,
+      "loss": 10.5337,
+      "step": 1393
+    },
+    {
+      "epoch": 1.0055665289998204,
+      "grad_norm": 21.589204788208008,
+      "learning_rate": 1.2536043909088191e-06,
+      "loss": 8.6184,
+      "step": 1400
+    },
+    {
+      "epoch": 1.0105943616448196,
+      "grad_norm": 24.172691345214844,
+      "learning_rate": 1.0848577668543802e-06,
+      "loss": 7.873,
+      "step": 1407
+    },
+    {
+      "epoch": 1.0156221942898187,
+      "grad_norm": 24.2752685546875,
+      "learning_rate": 9.281802222129765e-07,
+      "loss": 7.5302,
+      "step": 1414
+    },
+    {
+      "epoch": 1.0206500269348178,
+      "grad_norm": 31.572771072387695,
+      "learning_rate": 7.836104148243484e-07,
+      "loss": 7.3235,
+      "step": 1421
+    },
+    {
+      "epoch": 1.0256778595798168,
+      "grad_norm": 21.84587860107422,
+      "learning_rate": 6.511840151252169e-07,
+      "loss": 8.3397,
+      "step": 1428
+    },
+    {
+      "epoch": 1.030705692224816,
+      "grad_norm": 18.46891212463379,
+      "learning_rate": 5.309336973481683e-07,
+      "loss": 7.7921,
+      "step": 1435
+    },
+    {
+      "epoch": 1.035733524869815,
+      "grad_norm": 20.261125564575195,
+      "learning_rate": 4.228891314597694e-07,
+      "loss": 8.1837,
+      "step": 1442
+    },
+    {
+      "epoch": 1.0407613575148142,
+      "grad_norm": 16.873432159423828,
+      "learning_rate": 3.2707697583995167e-07,
+      "loss": 8.444,
+      "step": 1449
+    },
+    {
+      "epoch": 1.0457891901598133,
+      "grad_norm": 36.37105178833008,
+      "learning_rate": 2.4352087070443895e-07,
+      "loss": 8.4496,
+      "step": 1456
+    },
+    {
+      "epoch": 1.0508170228048124,
+      "grad_norm": 18.1140193939209,
+      "learning_rate": 1.7224143227190236e-07,
+      "loss": 7.6435,
+      "step": 1463
+    },
+    {
+      "epoch": 1.0558448554498114,
+      "grad_norm": 31.300342559814453,
+      "learning_rate": 1.132562476771959e-07,
+      "loss": 7.3236,
+      "step": 1470
+    },
+    {
+      "epoch": 1.0608726880948105,
+      "grad_norm": 18.59470558166504,
+      "learning_rate": 6.657987063200533e-08,
+      "loss": 7.7571,
+      "step": 1477
+    },
+    {
+      "epoch": 1.0659005207398096,
+      "grad_norm": 22.76087760925293,
+      "learning_rate": 3.2223817833931805e-08,
+      "loss": 7.9631,
+      "step": 1484
+    },
+    {
+      "epoch": 1.0709283533848089,
+      "grad_norm": 21.996257781982422,
+      "learning_rate": 1.019656612492592e-08,
+      "loss": 7.6284,
+      "step": 1491
+    },
+    {
+      "epoch": 1.075956186029808,
+      "grad_norm": 26.012069702148438,
+      "learning_rate": 5.035503997385949e-10,
+      "loss": 8.3136,
+      "step": 1498
     }
   ],
   "logging_steps": 7,
@@ -1407,12 +1519,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.055089571080962e+18,
+  "total_flos": 1.1371309739016192e+18,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null