Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:84ee2fc77cefd6cdb1eeb06fbe962369c49faa0bcdb4c245cd867d6da19ccb18
+oid sha256:fc981a8541b4212ef2489d101c6c386a03e65518e165360d9f5c945313a53f1f
 size 97307544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b51c1ae4168480680e62a3050e206071981b135b93bf81fc1caea27401ea59bc
+oid sha256:8603c066558a89ff372b4608a81268de82ea70ea2fd09a7b77ccbfc0197251d0
 size 194840426

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:877a643c19bf2e8680b443d83c1aa738cb8c7e9ea7cc043d29088c7be33e662a
+oid sha256:ae3bcd226fc59044e85381b588e33dead337537b0f505f9dab9526109ab1a3d9
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d4ae3842d5f151f968dca77e1398d806e7ccbbb71022d80233230f6c7d83bcb
+oid sha256:9567f2f3182e832808fd621212e0dd5e8f1a88bd24ddda3ea0d289496073738c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 3.7259087562561035,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.027114967462039046,
+  "epoch": 0.05422993492407809,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,189 @@
       "eval_samples_per_second": 6.248,
       "eval_steps_per_second": 3.132,
       "step": 25
+    },
+    {
+      "epoch": 0.028199566160520606,
+      "grad_norm": 1.8431979417800903,
+      "learning_rate": 0.00017684011108568592,
+      "loss": 3.2201,
+      "step": 26
+    },
+    {
+      "epoch": 0.02928416485900217,
+      "grad_norm": 2.0144472122192383,
+      "learning_rate": 0.0001746821476984154,
+      "loss": 3.8161,
+      "step": 27
+    },
+    {
+      "epoch": 0.03036876355748373,
+      "grad_norm": 2.105778694152832,
+      "learning_rate": 0.00017244252047910892,
+      "loss": 3.7448,
+      "step": 28
+    },
+    {
+      "epoch": 0.031453362255965296,
+      "grad_norm": 2.065922737121582,
+      "learning_rate": 0.00017012367842724887,
+      "loss": 3.5692,
+      "step": 29
+    },
+    {
+      "epoch": 0.03253796095444685,
+      "grad_norm": 2.4118812084198,
+      "learning_rate": 0.00016772815716257412,
+      "loss": 3.5881,
+      "step": 30
+    },
+    {
+      "epoch": 0.033622559652928416,
+      "grad_norm": 2.6568493843078613,
+      "learning_rate": 0.00016525857615241687,
+      "loss": 3.729,
+      "step": 31
+    },
+    {
+      "epoch": 0.03470715835140998,
+      "grad_norm": 2.1998934745788574,
+      "learning_rate": 0.0001627176358473537,
+      "loss": 3.6211,
+      "step": 32
+    },
+    {
+      "epoch": 0.03579175704989154,
+      "grad_norm": 2.378908395767212,
+      "learning_rate": 0.00016010811472830252,
+      "loss": 3.9732,
+      "step": 33
+    },
+    {
+      "epoch": 0.0368763557483731,
+      "grad_norm": 2.6396965980529785,
+      "learning_rate": 0.00015743286626829437,
+      "loss": 3.6206,
+      "step": 34
+    },
+    {
+      "epoch": 0.03796095444685466,
+      "grad_norm": 2.891078472137451,
+      "learning_rate": 0.00015469481581224272,
+      "loss": 3.6655,
+      "step": 35
+    },
+    {
+      "epoch": 0.039045553145336226,
+      "grad_norm": 2.687089204788208,
+      "learning_rate": 0.00015189695737812152,
+      "loss": 3.7126,
+      "step": 36
+    },
+    {
+      "epoch": 0.04013015184381779,
+      "grad_norm": 3.26758074760437,
+      "learning_rate": 0.00014904235038305083,
+      "loss": 3.4765,
+      "step": 37
+    },
+    {
+      "epoch": 0.04121475054229935,
+      "grad_norm": 2.8796169757843018,
+      "learning_rate": 0.0001461341162978688,
+      "loss": 3.3265,
+      "step": 38
+    },
+    {
+      "epoch": 0.04229934924078091,
+      "grad_norm": 2.7735259532928467,
+      "learning_rate": 0.00014317543523384928,
+      "loss": 3.3651,
+      "step": 39
+    },
+    {
+      "epoch": 0.04338394793926247,
+      "grad_norm": 2.856086254119873,
+      "learning_rate": 0.00014016954246529696,
+      "loss": 3.4886,
+      "step": 40
+    },
+    {
+      "epoch": 0.044468546637744036,
+      "grad_norm": 3.116877794265747,
+      "learning_rate": 0.00013711972489182208,
+      "loss": 3.2934,
+      "step": 41
+    },
+    {
+      "epoch": 0.0455531453362256,
+      "grad_norm": 3.317661762237549,
+      "learning_rate": 0.00013402931744416433,
+      "loss": 3.9233,
+      "step": 42
+    },
+    {
+      "epoch": 0.046637744034707156,
+      "grad_norm": 3.2693092823028564,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 3.6349,
+      "step": 43
+    },
+    {
+      "epoch": 0.04772234273318872,
+      "grad_norm": 3.303534984588623,
+      "learning_rate": 0.00012774029087618446,
+      "loss": 3.4023,
+      "step": 44
+    },
+    {
+      "epoch": 0.04880694143167028,
+      "grad_norm": 3.6019227504730225,
+      "learning_rate": 0.00012454854871407994,
+      "loss": 3.3989,
+      "step": 45
+    },
+    {
+      "epoch": 0.049891540130151846,
+      "grad_norm": 4.163827419281006,
+      "learning_rate": 0.0001213299630743747,
+      "loss": 3.7876,
+      "step": 46
+    },
+    {
+      "epoch": 0.0509761388286334,
+      "grad_norm": 3.6856470108032227,
+      "learning_rate": 0.000118088053433211,
+      "loss": 3.3211,
+      "step": 47
+    },
+    {
+      "epoch": 0.052060737527114966,
+      "grad_norm": 4.466559886932373,
+      "learning_rate": 0.0001148263647711842,
+      "loss": 3.3403,
+      "step": 48
+    },
+    {
+      "epoch": 0.05314533622559653,
+      "grad_norm": 5.289233684539795,
+      "learning_rate": 0.00011154846369695863,
+      "loss": 3.9621,
+      "step": 49
+    },
+    {
+      "epoch": 0.05422993492407809,
+      "grad_norm": 8.265725135803223,
+      "learning_rate": 0.00010825793454723325,
+      "loss": 4.6722,
+      "step": 50
+    },
+    {
+      "epoch": 0.05422993492407809,
+      "eval_loss": 3.752061605453491,
+      "eval_runtime": 62.2465,
+      "eval_samples_per_second": 6.249,
+      "eval_steps_per_second": 3.133,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -212,7 +395,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 0
+        "early_stopping_patience_counter": 1
       }
     },
     "TrainerControl": {
@@ -221,12 +404,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.39742146461696e+16,
+  "total_flos": 2.79484292923392e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null