Training in progress, step 600, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87cde6486c35628a78131ccfa610958d63909981057cea19f61f997831ec8bd0
+oid sha256:e31bd9c05958a502ad58f98e4caaf363d8b90b434e941fea3a27f89ddf2ad7fe
 size 2658231320

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1daae0ca44d228a8465d6aa7c2d88252e137152940f76b9e87e7702f3352cf75
+oid sha256:75f3670147b721cf51216916c358822dbc60e4bea6dac113678e78133df05f03
 size 2141361944

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd0165412adf3eda5f3cdc0f31ef8d9f5126906af89e7bffeaf0ed1a8018bbd4
+oid sha256:c66f4d84f4b7894f4bfca7a072a85f9f2536def175c2fe32bdb84e05433c5d3e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de723127fb29334c1d5f5d4d0ba1d4e78fc916dfc4e8f6b4bb5846a069a13ba9
+oid sha256:9d89303aa828aaa9e241260e2ca606db088309d8b5a7ba3d79cb10ce1887994d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 5.836884021759033,
-  "best_model_checkpoint": "miner_id_24/checkpoint-450",
-  "epoch": 0.6521739130434783,
+  "best_metric": 5.665431499481201,
+  "best_model_checkpoint": "miner_id_24/checkpoint-600",
+  "epoch": 0.8695652173913043,
   "eval_steps": 50,
-  "global_step": 450,
+  "global_step": 600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -402,6 +402,135 @@
       "eval_samples_per_second": 7.412,
       "eval_steps_per_second": 1.856,
       "step": 450
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 3.266097068786621,
+      "learning_rate": 2.6522584913693294e-05,
+      "loss": 6.0702,
+      "step": 460
+    },
+    {
+      "epoch": 0.6811594202898551,
+      "grad_norm": 4.725111961364746,
+      "learning_rate": 2.301660165700936e-05,
+      "loss": 5.8329,
+      "step": 470
+    },
+    {
+      "epoch": 0.6956521739130435,
+      "grad_norm": 2.761223554611206,
+      "learning_rate": 1.9728836206903656e-05,
+      "loss": 5.7463,
+      "step": 480
+    },
+    {
+      "epoch": 0.7101449275362319,
+      "grad_norm": 4.28662109375,
+      "learning_rate": 1.6668608091748495e-05,
+      "loss": 5.7134,
+      "step": 490
+    },
+    {
+      "epoch": 0.7246376811594203,
+      "grad_norm": 10.329545021057129,
+      "learning_rate": 1.3844591860619383e-05,
+      "loss": 5.4993,
+      "step": 500
+    },
+    {
+      "epoch": 0.7246376811594203,
+      "eval_loss": 5.768553733825684,
+      "eval_runtime": 156.7554,
+      "eval_samples_per_second": 7.413,
+      "eval_steps_per_second": 1.856,
+      "step": 500
+    },
+    {
+      "epoch": 0.7391304347826086,
+      "grad_norm": 4.405299186706543,
+      "learning_rate": 1.1264792494342857e-05,
+      "loss": 6.0287,
+      "step": 510
+    },
+    {
+      "epoch": 0.7536231884057971,
+      "grad_norm": 7.695607662200928,
+      "learning_rate": 8.936522714508678e-06,
+      "loss": 5.7608,
+      "step": 520
+    },
+    {
+      "epoch": 0.7681159420289855,
+      "grad_norm": 2.8553273677825928,
+      "learning_rate": 6.866382254766157e-06,
+      "loss": 5.7145,
+      "step": 530
+    },
+    {
+      "epoch": 0.782608695652174,
+      "grad_norm": 3.349501132965088,
+      "learning_rate": 5.060239153161872e-06,
+      "loss": 5.664,
+      "step": 540
+    },
+    {
+      "epoch": 0.7971014492753623,
+      "grad_norm": 9.870193481445312,
+      "learning_rate": 3.5232131185484076e-06,
+      "loss": 5.5165,
+      "step": 550
+    },
+    {
+      "epoch": 0.7971014492753623,
+      "eval_loss": 5.6852006912231445,
+      "eval_runtime": 156.7306,
+      "eval_samples_per_second": 7.414,
+      "eval_steps_per_second": 1.857,
+      "step": 550
+    },
+    {
+      "epoch": 0.8115942028985508,
+      "grad_norm": 2.617950677871704,
+      "learning_rate": 2.259661018213333e-06,
+      "loss": 5.893,
+      "step": 560
+    },
+    {
+      "epoch": 0.8260869565217391,
+      "grad_norm": 2.5789644718170166,
+      "learning_rate": 1.2731645278655445e-06,
+      "loss": 5.713,
+      "step": 570
+    },
+    {
+      "epoch": 0.8405797101449275,
+      "grad_norm": 2.826625108718872,
+      "learning_rate": 5.665199789862907e-07,
+      "loss": 5.7296,
+      "step": 580
+    },
+    {
+      "epoch": 0.855072463768116,
+      "grad_norm": 3.6776087284088135,
+      "learning_rate": 1.4173043232380557e-07,
+      "loss": 5.5956,
+      "step": 590
+    },
+    {
+      "epoch": 0.8695652173913043,
+      "grad_norm": 11.325143814086914,
+      "learning_rate": 0.0,
+      "loss": 5.657,
+      "step": 600
+    },
+    {
+      "epoch": 0.8695652173913043,
+      "eval_loss": 5.665431499481201,
+      "eval_runtime": 156.7272,
+      "eval_samples_per_second": 7.414,
+      "eval_steps_per_second": 1.857,
+      "step": 600
     }
   ],
   "logging_steps": 10,
@@ -425,12 +554,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.3362870558350377e+18,
+  "total_flos": 1.7814695724995052e+18,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null