Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ea9bbaa9f836e88548307399cd646ed9a9e416b5de868e1aa57e4c6da5e3452
+oid sha256:fe87b7f23a8620b30ebfbc17310fdf64b065c3b1a22de0cbe4e08604e02bc988
 size 70430032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9247931af67bd9a86e518ee6d4ef73669be7902d5224f399ccb69ba606d7bc86
+oid sha256:b39c5b7295e0b751ad1c0bbef4163c678467b44bb4c378ae5d258a7679b01a9b
 size 141053442

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:599ddcee07d5a861ece0f4de1903724e4aca1c3286a9c2cbd77dcae86ba5fdf1
+oid sha256:6089676789037860dbb4a886aeb4957073983ed4d05ee9f00b3701d6c3be381b
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:56e481d3f13ff36459d8279663c80a3f95d42710e9f0e63fccf59b1bd807e90b
+oid sha256:84bbf0db14e2efd4b4c26bd887f7ba654e43e5343f4efe1d325190e985117acc
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a6844d3eabdd14fe6c38335fcbc9f23cfe6cfecd9d4e6657f75d84170558131
+oid sha256:e85ee4c1bb54c798ef97374b8f37491b4dcee21def5302c1e153f1caa94c9a9d
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b7454acfb1745ea0de3b382e69cb8a8d7b6de3387a7648d0332213c440912038
+oid sha256:5cde5ec8c22d04aa0c3169d2dcd02cb11605370753522b7c73a4f7c104fb9337
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:344fc18df9c84f214bc47e69d1bbde70d66cf3ec6caeac9cd529dfb5814c4b9a
+oid sha256:051dee7dfbeecb34b46e8409ffafec324501f465585234624669bc8c9e863ae4
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.4749317169189453,
-  "best_model_checkpoint": "miner_id_24/checkpoint-75",
-  "epoch": 1.0530934620447565,
+  "best_metric": 2.4680612087249756,
+  "best_model_checkpoint": "miner_id_24/checkpoint-100",
+  "epoch": 1.4041246160596752,
   "eval_steps": 25,
-  "global_step": 75,
+  "global_step": 100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -564,6 +564,189 @@
       "eval_samples_per_second": 99.064,
       "eval_steps_per_second": 25.757,
       "step": 75
+    },
+    {
+      "epoch": 1.0671347082053533,
+      "grad_norm": 0.7719098925590515,
+      "learning_rate": 2.3444344707738015e-05,
+      "loss": 2.3545,
+      "step": 76
+    },
+    {
+      "epoch": 1.08117595436595,
+      "grad_norm": 0.8498649001121521,
+      "learning_rate": 2.2400865784401e-05,
+      "loss": 2.5526,
+      "step": 77
+    },
+    {
+      "epoch": 1.0952172005265468,
+      "grad_norm": 1.025146484375,
+      "learning_rate": 2.1393033535713093e-05,
+      "loss": 2.88,
+      "step": 78
+    },
+    {
+      "epoch": 1.1092584466871436,
+      "grad_norm": 1.3467072248458862,
+      "learning_rate": 2.0421950011441354e-05,
+      "loss": 2.7158,
+      "step": 79
+    },
+    {
+      "epoch": 1.1232996928477403,
+      "grad_norm": 1.4670014381408691,
+      "learning_rate": 1.9488677077162295e-05,
+      "loss": 2.8973,
+      "step": 80
+    },
+    {
+      "epoch": 1.1373409390083369,
+      "grad_norm": 1.7755794525146484,
+      "learning_rate": 1.8594235253127375e-05,
+      "loss": 2.9892,
+      "step": 81
+    },
+    {
+      "epoch": 1.1513821851689336,
+      "grad_norm": 2.5536394119262695,
+      "learning_rate": 1.77396025983391e-05,
+      "loss": 3.3171,
+      "step": 82
+    },
+    {
+      "epoch": 1.1654234313295304,
+      "grad_norm": 3.319047451019287,
+      "learning_rate": 1.6925713641057904e-05,
+      "loss": 3.4315,
+      "step": 83
+    },
+    {
+      "epoch": 1.1794646774901272,
+      "grad_norm": 1.3052607774734497,
+      "learning_rate": 1.6153458356909176e-05,
+      "loss": 2.2188,
+      "step": 84
+    },
+    {
+      "epoch": 1.193505923650724,
+      "grad_norm": 0.33176228404045105,
+      "learning_rate": 1.5423681195707997e-05,
+      "loss": 2.1613,
+      "step": 85
+    },
+    {
+      "epoch": 1.2075471698113207,
+      "grad_norm": 0.4036065340042114,
+      "learning_rate": 1.4737180158065644e-05,
+      "loss": 1.8675,
+      "step": 86
+    },
+    {
+      "epoch": 1.2215884159719175,
+      "grad_norm": 0.5903648734092712,
+      "learning_rate": 1.4094705922787687e-05,
+      "loss": 1.971,
+      "step": 87
+    },
+    {
+      "epoch": 1.2356296621325142,
+      "grad_norm": 0.816626250743866,
+      "learning_rate": 1.3496961026017687e-05,
+      "loss": 2.235,
+      "step": 88
+    },
+    {
+      "epoch": 1.249670908293111,
+      "grad_norm": 0.8417714834213257,
+      "learning_rate": 1.2944599093024267e-05,
+      "loss": 2.3109,
+      "step": 89
+    },
+    {
+      "epoch": 1.2637121544537078,
+      "grad_norm": 0.9843570590019226,
+      "learning_rate": 1.2438224123471442e-05,
+      "loss": 2.4662,
+      "step": 90
+    },
+    {
+      "epoch": 1.2777534006143045,
+      "grad_norm": 1.1565916538238525,
+      "learning_rate": 1.1978389830953907e-05,
+      "loss": 2.7704,
+      "step": 91
+    },
+    {
+      "epoch": 1.2917946467749013,
+      "grad_norm": 1.2723060846328735,
+      "learning_rate": 1.1565599037519316e-05,
+      "loss": 2.7589,
+      "step": 92
+    },
+    {
+      "epoch": 1.305835892935498,
+      "grad_norm": 1.5614339113235474,
+      "learning_rate": 1.1200303123839742e-05,
+      "loss": 2.9048,
+      "step": 93
+    },
+    {
+      "epoch": 1.3198771390960948,
+      "grad_norm": 1.889614462852478,
+      "learning_rate": 1.088290153563358e-05,
+      "loss": 3.2427,
+      "step": 94
+    },
+    {
+      "epoch": 1.3339183852566916,
+      "grad_norm": 2.9528310298919678,
+      "learning_rate": 1.0613741346877497e-05,
+      "loss": 3.3262,
+      "step": 95
+    },
+    {
+      "epoch": 1.3479596314172884,
+      "grad_norm": 6.621575832366943,
+      "learning_rate": 1.0393116880286118e-05,
+      "loss": 4.0112,
+      "step": 96
+    },
+    {
+      "epoch": 1.3620008775778851,
+      "grad_norm": 2.7021443843841553,
+      "learning_rate": 1.0221269385474488e-05,
+      "loss": 2.6302,
+      "step": 97
+    },
+    {
+      "epoch": 1.3760421237384817,
+      "grad_norm": 0.3131318986415863,
+      "learning_rate": 1.0098386775155147e-05,
+      "loss": 1.4645,
+      "step": 98
+    },
+    {
+      "epoch": 1.3900833698990787,
+      "grad_norm": 0.44030845165252686,
+      "learning_rate": 1.0024603419658329e-05,
+      "loss": 1.8176,
+      "step": 99
+    },
+    {
+      "epoch": 1.4041246160596752,
+      "grad_norm": 0.6400426626205444,
+      "learning_rate": 1e-05,
+      "loss": 2.0536,
+      "step": 100
+    },
+    {
+      "epoch": 1.4041246160596752,
+      "eval_loss": 2.4680612087249756,
+      "eval_runtime": 0.5034,
+      "eval_samples_per_second": 99.333,
+      "eval_steps_per_second": 25.827,
+      "step": 100
     }
   ],
   "logging_steps": 1,
@@ -587,12 +770,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 4.42951368966144e+16,
+  "total_flos": 5.90601825288192e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null