Training in progress, step 4650, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b3514c73345f69d0c9842f4ae7671f25a434e86505a1a2eb1ce04573fead9d03
+oid sha256:e892cb1a4cbe178b5793fc4bc7b06df7ba09245ba7288ee2bc0ba93be87167f8
 size 1482788592

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d6ee7f3a10460f3ffb6333f04ca0412b319601b5d8bf66fb361bd45ab5758c2
+oid sha256:06fb50533439b160e16eaa506c92e9c15f37289f74228471e7951b6d1e0ee78c
 size 2897966842

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2483a85e0c4bab047f3ed01375369019a5f42e1b495801c626999c441bf2b7d8
+oid sha256:30d893290e5e1fdb574b3915ebc94cb574860f01edf82e3dbe4acb2cc67e7660
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f72d12e08f2981b12196a00ff48fe5cac0ba4d9d1aa54f91464a195ecde87c8
+oid sha256:931d38342b692c160fcb90f4d9acb8e6f6634f499984cdd5b99b0563194d400a
 size 1256

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 2.08717679977417,
   "best_model_checkpoint": "./output/checkpoint-4500",
-  "epoch": 0.2786205188533218,
+  "epoch": 0.28790786948176583,
   "eval_steps": 150,
-  "global_step": 4500,
+  "global_step": 4650,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3397,6 +3397,119 @@
       "eval_samples_per_second": 9.727,
       "eval_steps_per_second": 9.727,
       "step": 4500
+    },
+    {
+      "epoch": 0.2792396755618847,
+      "grad_norm": 30.00826644897461,
+      "learning_rate": 5.472047830984499e-07,
+      "loss": 1.8833,
+      "step": 4510
+    },
+    {
+      "epoch": 0.27985883227044767,
+      "grad_norm": 25.873231887817383,
+      "learning_rate": 5.252725889984403e-07,
+      "loss": 1.6589,
+      "step": 4520
+    },
+    {
+      "epoch": 0.2804779889790106,
+      "grad_norm": 35.64846420288086,
+      "learning_rate": 5.037783829820298e-07,
+      "loss": 1.7872,
+      "step": 4530
+    },
+    {
+      "epoch": 0.28109714568757355,
+      "grad_norm": 18.542455673217773,
+      "learning_rate": 4.827230485918372e-07,
+      "loss": 1.7618,
+      "step": 4540
+    },
+    {
+      "epoch": 0.2817163023961365,
+      "grad_norm": 16.17365837097168,
+      "learning_rate": 4.6210745133019236e-07,
+      "loss": 1.4652,
+      "step": 4550
+    },
+    {
+      "epoch": 0.2823354591046994,
+      "grad_norm": 33.95541763305664,
+      "learning_rate": 4.419324386235529e-07,
+      "loss": 1.7503,
+      "step": 4560
+    },
+    {
+      "epoch": 0.2829546158132623,
+      "grad_norm": 18.06041145324707,
+      "learning_rate": 4.2219883978767386e-07,
+      "loss": 1.9819,
+      "step": 4570
+    },
+    {
+      "epoch": 0.28357377252182525,
+      "grad_norm": 27.695892333984375,
+      "learning_rate": 4.029074659935082e-07,
+      "loss": 1.7574,
+      "step": 4580
+    },
+    {
+      "epoch": 0.2841929292303882,
+      "grad_norm": 37.04735565185547,
+      "learning_rate": 3.8405911023387444e-07,
+      "loss": 1.7715,
+      "step": 4590
+    },
+    {
+      "epoch": 0.28481208593895113,
+      "grad_norm": 27.74335289001465,
+      "learning_rate": 3.6565454729085526e-07,
+      "loss": 1.9633,
+      "step": 4600
+    },
+    {
+      "epoch": 0.28543124264751407,
+      "grad_norm": 23.256072998046875,
+      "learning_rate": 3.4769453370394753e-07,
+      "loss": 1.8392,
+      "step": 4610
+    },
+    {
+      "epoch": 0.286050399356077,
+      "grad_norm": 24.18708038330078,
+      "learning_rate": 3.301798077389637e-07,
+      "loss": 1.8558,
+      "step": 4620
+    },
+    {
+      "epoch": 0.28666955606463995,
+      "grad_norm": 33.63625717163086,
+      "learning_rate": 3.1311108935768926e-07,
+      "loss": 1.9262,
+      "step": 4630
+    },
+    {
+      "epoch": 0.2872887127732029,
+      "grad_norm": 23.810638427734375,
+      "learning_rate": 2.964890801882817e-07,
+      "loss": 1.7218,
+      "step": 4640
+    },
+    {
+      "epoch": 0.28790786948176583,
+      "grad_norm": 33.80169677734375,
+      "learning_rate": 2.8031446349643393e-07,
+      "loss": 1.9988,
+      "step": 4650
+    },
+    {
+      "epoch": 0.28790786948176583,
+      "eval_loss": 2.0872082710266113,
+      "eval_runtime": 49.569,
+      "eval_samples_per_second": 10.087,
+      "eval_steps_per_second": 10.087,
+      "step": 4650
     }
   ],
   "logging_steps": 10,
@@ -3416,7 +3529,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.118865314362163e+17,
+  "total_flos": 3.228632494763213e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null