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:b588f8a016404d801f6d123b7e0ceb79b40ddf90f516afa3ab6a427f19ed81b6
+oid sha256:7542dd14658061991a45f51ae2c2059f63ed37ddca4e5d248949fedfbe523011
 size 419475904

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c8306092a9a5b7d4cb37a3202446d898bb8754afb28488ddb0a3b6f6b22caea
+oid sha256:79da4d6f666aa22fbcbfedb7681f9d27c2ca9f68c7ad876a48ef307b3be3a415
 size 213368916

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:96036273dc69d8772050eb416abe30f5c8813a76d1e8f8be692bf5694d44166f
+oid sha256:353318efa98279f57d56884999ae829966fe7b708086896056f46790f1fb1923
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:70f0f789b56065211b8c0b1a5e2a97dd0b5b08a816bbbe288fb6f9c677282af9
+oid sha256:5ad54995b081fae25638228c5d9c8f38ca277e5c5ad00bc3e49897b543f84405
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.0015856274403631687,
-  "best_model_checkpoint": "miner_id_24/checkpoint-450",
-  "epoch": 0.07246960302761897,
+  "best_metric": 0.0013703653821721673,
+  "best_model_checkpoint": "miner_id_24/checkpoint-600",
+  "epoch": 0.09662613737015863,
   "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": 9.522,
       "eval_steps_per_second": 2.381,
       "step": 450
+    },
+    {
+      "epoch": 0.07408003865045495,
+      "grad_norm": 0.13987891376018524,
+      "learning_rate": 2.6522584913693294e-05,
+      "loss": 0.0211,
+      "step": 460
+    },
+    {
+      "epoch": 0.07569047427329093,
+      "grad_norm": 0.008718649856746197,
+      "learning_rate": 2.301660165700936e-05,
+      "loss": 0.003,
+      "step": 470
+    },
+    {
+      "epoch": 0.0773009098961269,
+      "grad_norm": 0.05980238318443298,
+      "learning_rate": 1.9728836206903656e-05,
+      "loss": 0.0042,
+      "step": 480
+    },
+    {
+      "epoch": 0.07891134551896288,
+      "grad_norm": 0.14900194108486176,
+      "learning_rate": 1.6668608091748495e-05,
+      "loss": 0.0059,
+      "step": 490
+    },
+    {
+      "epoch": 0.08052178114179885,
+      "grad_norm": 0.24069011211395264,
+      "learning_rate": 1.3844591860619383e-05,
+      "loss": 0.0066,
+      "step": 500
+    },
+    {
+      "epoch": 0.08052178114179885,
+      "eval_loss": 0.0014473887858912349,
+      "eval_runtime": 1098.9912,
+      "eval_samples_per_second": 9.517,
+      "eval_steps_per_second": 2.379,
+      "step": 500
+    },
+    {
+      "epoch": 0.08213221676463484,
+      "grad_norm": 0.010411093942821026,
+      "learning_rate": 1.1264792494342857e-05,
+      "loss": 0.0041,
+      "step": 510
+    },
+    {
+      "epoch": 0.0837426523874708,
+      "grad_norm": 0.15242089331150055,
+      "learning_rate": 8.936522714508678e-06,
+      "loss": 0.0062,
+      "step": 520
+    },
+    {
+      "epoch": 0.08535308801030679,
+      "grad_norm": 0.26096779108047485,
+      "learning_rate": 6.866382254766157e-06,
+      "loss": 0.0046,
+      "step": 530
+    },
+    {
+      "epoch": 0.08696352363314276,
+      "grad_norm": 0.014391699805855751,
+      "learning_rate": 5.060239153161872e-06,
+      "loss": 0.0016,
+      "step": 540
+    },
+    {
+      "epoch": 0.08857395925597875,
+      "grad_norm": 0.13847970962524414,
+      "learning_rate": 3.5232131185484076e-06,
+      "loss": 0.0039,
+      "step": 550
+    },
+    {
+      "epoch": 0.08857395925597875,
+      "eval_loss": 0.0013709530467167497,
+      "eval_runtime": 1099.0,
+      "eval_samples_per_second": 9.517,
+      "eval_steps_per_second": 2.379,
+      "step": 550
+    },
+    {
+      "epoch": 0.09018439487881472,
+      "grad_norm": 0.01671081967651844,
+      "learning_rate": 2.259661018213333e-06,
+      "loss": 0.0047,
+      "step": 560
+    },
+    {
+      "epoch": 0.0917948305016507,
+      "grad_norm": 0.03844922035932541,
+      "learning_rate": 1.2731645278655445e-06,
+      "loss": 0.0021,
+      "step": 570
+    },
+    {
+      "epoch": 0.09340526612448667,
+      "grad_norm": 0.028714220970869064,
+      "learning_rate": 5.665199789862907e-07,
+      "loss": 0.0031,
+      "step": 580
+    },
+    {
+      "epoch": 0.09501570174732266,
+      "grad_norm": 0.037552349269390106,
+      "learning_rate": 1.4173043232380557e-07,
+      "loss": 0.0042,
+      "step": 590
+    },
+    {
+      "epoch": 0.09662613737015863,
+      "grad_norm": 0.05559389293193817,
+      "learning_rate": 0.0,
+      "loss": 0.0057,
+      "step": 600
+    },
+    {
+      "epoch": 0.09662613737015863,
+      "eval_loss": 0.0013703653821721673,
+      "eval_runtime": 1098.9665,
+      "eval_samples_per_second": 9.517,
+      "eval_steps_per_second": 2.38,
+      "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": 1.1370262248082637e+18,
+  "total_flos": 1.5164558534089114e+18,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null