Training in progress, step 600, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7069f216076f8433d0ee19ab17d20e3b7e17c2ae5a826a713f8b7bac95ccde8c
+oid sha256:4cc463b5882899b82375819d9216cecfb1139e96dc7b949fdc0b4cc4957bf3db
 size 35237104

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3778aacae24b15c07db841005074de08e7a15b98faa1191c0052439ba9be62a0
+oid sha256:e8045a865742cc6a3c4da7b82b19ae835573901d2e723f3e689b96a3089e14c1
 size 70667778

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:98d123b91162e1acbfd2068d1a0f8d03cd5ac9977dd5c429c7e4796c8caf6f46
+oid sha256:0327e18585591f05056cc5ee51c325edecdc04ed79d28c6089ab5783f0f9d65d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d48e757787bf7fc889c741def8f67efb8c383ce859146812f7dbd958398696a3
+oid sha256:0faaff1eaeb01ac673cde04e45352a5ca536ee1dfd9544b36554717d21724b65
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.037466526031494,
-  "best_model_checkpoint": "miner_id_24/checkpoint-450",
-  "epoch": 0.04408739100617223,
+  "best_metric": 2.0348799228668213,
+  "best_model_checkpoint": "miner_id_24/checkpoint-600",
+  "epoch": 0.058783188008229646,
   "eval_steps": 150,
-  "global_step": 450,
+  "global_step": 600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -354,6 +354,119 @@
       "eval_samples_per_second": 70.574,
       "eval_steps_per_second": 17.668,
       "step": 450
+    },
+    {
+      "epoch": 0.045067110806309395,
+      "grad_norm": 3.0501604080200195,
+      "learning_rate": 6.902683966887863e-06,
+      "loss": 1.9057,
+      "step": 460
+    },
+    {
+      "epoch": 0.04604683060644656,
+      "grad_norm": 2.0422005653381348,
+      "learning_rate": 5.997779885392928e-06,
+      "loss": 1.8502,
+      "step": 470
+    },
+    {
+      "epoch": 0.04702655040658372,
+      "grad_norm": 2.0223166942596436,
+      "learning_rate": 5.147022251382486e-06,
+      "loss": 2.1528,
+      "step": 480
+    },
+    {
+      "epoch": 0.04800627020672088,
+      "grad_norm": 2.5460333824157715,
+      "learning_rate": 4.3532897593890356e-06,
+      "loss": 2.062,
+      "step": 490
+    },
+    {
+      "epoch": 0.04898599000685804,
+      "grad_norm": 2.885043144226074,
+      "learning_rate": 3.619268148915402e-06,
+      "loss": 2.0503,
+      "step": 500
+    },
+    {
+      "epoch": 0.0499657098069952,
+      "grad_norm": 2.628741979598999,
+      "learning_rate": 2.947441116742348e-06,
+      "loss": 1.9733,
+      "step": 510
+    },
+    {
+      "epoch": 0.05094542960713236,
+      "grad_norm": 3.8591113090515137,
+      "learning_rate": 2.3400819128849325e-06,
+      "loss": 2.128,
+      "step": 520
+    },
+    {
+      "epoch": 0.05192514940726952,
+      "grad_norm": 3.2337727546691895,
+      "learning_rate": 1.7992456486339744e-06,
+      "loss": 2.0159,
+      "step": 530
+    },
+    {
+      "epoch": 0.05290486920740668,
+      "grad_norm": 3.3239448070526123,
+      "learning_rate": 1.326762342710017e-06,
+      "loss": 2.2092,
+      "step": 540
+    },
+    {
+      "epoch": 0.053884589007543844,
+      "grad_norm": 1.9489779472351074,
+      "learning_rate": 9.242307290592442e-07,
+      "loss": 1.8123,
+      "step": 550
+    },
+    {
+      "epoch": 0.054864308807681006,
+      "grad_norm": 3.490032434463501,
+      "learning_rate": 5.930128472438762e-07,
+      "loss": 2.0926,
+      "step": 560
+    },
+    {
+      "epoch": 0.05584402860781816,
+      "grad_norm": 3.1768524646759033,
+      "learning_rate": 3.3422943373142354e-07,
+      "loss": 2.1623,
+      "step": 570
+    },
+    {
+      "epoch": 0.05682374840795532,
+      "grad_norm": 2.5022518634796143,
+      "learning_rate": 1.4875612967725348e-07,
+      "loss": 2.075,
+      "step": 580
+    },
+    {
+      "epoch": 0.057803468208092484,
+      "grad_norm": 3.5616374015808105,
+      "learning_rate": 3.722051803210014e-08,
+      "loss": 1.8666,
+      "step": 590
+    },
+    {
+      "epoch": 0.058783188008229646,
+      "grad_norm": 3.008579969406128,
+      "learning_rate": 0.0,
+      "loss": 2.0734,
+      "step": 600
+    },
+    {
+      "epoch": 0.058783188008229646,
+      "eval_loss": 2.0348799228668213,
+      "eval_runtime": 30.5609,
+      "eval_samples_per_second": 70.319,
+      "eval_steps_per_second": 17.604,
+      "step": 600
     }
   ],
   "logging_steps": 10,
@@ -377,12 +490,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2338595513303040.0,
+  "total_flos": 3118127351070720.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null