Training in progress, step 99, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ffb0b2511916105682cf80bf9696833163afb4bee41004ff0b8200c9f08b191
+oid sha256:fc138d6658e8e095c787a05ea8c7acb9723acdbbf5b49bfb28685fe7044e575d
 size 237402

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:791ddabfb59f09149d5becaccac457c6ba26c528908751e157b0ccc437888f6c
+oid sha256:7b32541ba1a16f052d7a3db977d9ece8dc9ce41f7f9b6ec83f2008a1b8e73123
 size 222294

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1318a700856bcdf76961c92e318a3b39bde15057dc94458041a6ee7452060e66
+oid sha256:7db5f040100ef639879df4e7ff2bd3ab5f6e11208b015560d33f3f4bb39c680d
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:020fbe0f82efc7984cb137980f674aa1a26f24fc1774e038e8433aa642c4aa86
+oid sha256:a03cc7a398e34f4833c81504da7e98a819dc8ef2649b1ba38633a959d049481f
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:346ae7ad1ffbb1ba7d9f71113f7ade9f0a382da141487c6347a82436c307f147
+oid sha256:a263fdde13fc7b695eb316b07ca5835d2c7b10e46642c1a58a0ca11d5a739f0b
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:68333bc873842e58e67b8ea867c281a4c5484cc61d73e761bb48e26bc6301317
+oid sha256:b31521eec184753dbe4c30573b992c5bd063a8acd795f7c130b28632b36a9f18
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:355b85b545659c2cc1d9c5605cde8c2d283fa57cb41a54787534d12dd02cbb89
+oid sha256:2377833f26b6f1902c6fcca29fee5c63db83bdd037d63afc31b5aa4a26de7f6d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 6.883584976196289,
   "best_model_checkpoint": "miner_id_24/checkpoint-75",
-  "epoch": 2.3000949667616335,
+  "epoch": 3.03988603988604,
   "eval_steps": 25,
-  "global_step": 75,
+  "global_step": 99,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -564,6 +564,174 @@
       "eval_samples_per_second": 724.277,
       "eval_steps_per_second": 188.312,
       "step": 75
+    },
+    {
+      "epoch": 2.3304843304843303,
+      "grad_norm": 0.09302153438329697,
+      "learning_rate": 2.2400865784401e-05,
+      "loss": 6.88,
+      "step": 76
+    },
+    {
+      "epoch": 2.3608736942070276,
+      "grad_norm": 0.09038078039884567,
+      "learning_rate": 2.1393033535713093e-05,
+      "loss": 6.9026,
+      "step": 77
+    },
+    {
+      "epoch": 2.3912630579297245,
+      "grad_norm": 0.09370548278093338,
+      "learning_rate": 2.0421950011441354e-05,
+      "loss": 6.9711,
+      "step": 78
+    },
+    {
+      "epoch": 2.421652421652422,
+      "grad_norm": 0.09348244965076447,
+      "learning_rate": 1.9488677077162295e-05,
+      "loss": 6.8911,
+      "step": 79
+    },
+    {
+      "epoch": 2.4520417853751186,
+      "grad_norm": 0.09923094511032104,
+      "learning_rate": 1.8594235253127375e-05,
+      "loss": 6.91,
+      "step": 80
+    },
+    {
+      "epoch": 2.482431149097816,
+      "grad_norm": 0.12247008085250854,
+      "learning_rate": 1.77396025983391e-05,
+      "loss": 7.1999,
+      "step": 81
+    },
+    {
+      "epoch": 2.5128205128205128,
+      "grad_norm": 0.08389267325401306,
+      "learning_rate": 1.6925713641057904e-05,
+      "loss": 6.4161,
+      "step": 82
+    },
+    {
+      "epoch": 2.5432098765432096,
+      "grad_norm": 0.08750791847705841,
+      "learning_rate": 1.6153458356909176e-05,
+      "loss": 6.8745,
+      "step": 83
+    },
+    {
+      "epoch": 2.573599240265907,
+      "grad_norm": 0.08594594895839691,
+      "learning_rate": 1.5423681195707997e-05,
+      "loss": 6.9089,
+      "step": 84
+    },
+    {
+      "epoch": 2.603988603988604,
+      "grad_norm": 0.09055335074663162,
+      "learning_rate": 1.4737180158065644e-05,
+      "loss": 6.8928,
+      "step": 85
+    },
+    {
+      "epoch": 2.634377967711301,
+      "grad_norm": 0.09193196147680283,
+      "learning_rate": 1.4094705922787687e-05,
+      "loss": 6.8778,
+      "step": 86
+    },
+    {
+      "epoch": 2.664767331433998,
+      "grad_norm": 0.09884382039308548,
+      "learning_rate": 1.3496961026017687e-05,
+      "loss": 7.1493,
+      "step": 87
+    },
+    {
+      "epoch": 2.695156695156695,
+      "grad_norm": 0.09690383821725845,
+      "learning_rate": 1.2944599093024267e-05,
+      "loss": 6.6664,
+      "step": 88
+    },
+    {
+      "epoch": 2.725546058879392,
+      "grad_norm": 0.12492170184850693,
+      "learning_rate": 1.2438224123471442e-05,
+      "loss": 7.3624,
+      "step": 89
+    },
+    {
+      "epoch": 2.7559354226020893,
+      "grad_norm": 0.08144571632146835,
+      "learning_rate": 1.1978389830953907e-05,
+      "loss": 6.2938,
+      "step": 90
+    },
+    {
+      "epoch": 2.786324786324786,
+      "grad_norm": 0.08170946687459946,
+      "learning_rate": 1.1565599037519316e-05,
+      "loss": 6.8895,
+      "step": 91
+    },
+    {
+      "epoch": 2.8167141500474835,
+      "grad_norm": 0.08227747678756714,
+      "learning_rate": 1.1200303123839742e-05,
+      "loss": 6.9282,
+      "step": 92
+    },
+    {
+      "epoch": 2.8471035137701803,
+      "grad_norm": 0.08924560993909836,
+      "learning_rate": 1.088290153563358e-05,
+      "loss": 6.8725,
+      "step": 93
+    },
+    {
+      "epoch": 2.8774928774928776,
+      "grad_norm": 0.09153356403112411,
+      "learning_rate": 1.0613741346877497e-05,
+      "loss": 6.9255,
+      "step": 94
+    },
+    {
+      "epoch": 2.9078822412155745,
+      "grad_norm": 0.09689171612262726,
+      "learning_rate": 1.0393116880286118e-05,
+      "loss": 7.0523,
+      "step": 95
+    },
+    {
+      "epoch": 2.9382716049382713,
+      "grad_norm": 0.09343353658914566,
+      "learning_rate": 1.0221269385474488e-05,
+      "loss": 6.7672,
+      "step": 96
+    },
+    {
+      "epoch": 2.9686609686609686,
+      "grad_norm": 0.1134086549282074,
+      "learning_rate": 1.0098386775155147e-05,
+      "loss": 7.2979,
+      "step": 97
+    },
+    {
+      "epoch": 3.009496676163343,
+      "grad_norm": 0.11922775208950043,
+      "learning_rate": 1.0024603419658329e-05,
+      "loss": 9.4261,
+      "step": 98
+    },
+    {
+      "epoch": 3.03988603988604,
+      "grad_norm": 0.08165828138589859,
+      "learning_rate": 1e-05,
+      "loss": 6.7951,
+      "step": 99
     }
   ],
   "logging_steps": 1,
@@ -587,12 +755,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 8558936064000.0,
+  "total_flos": 11297795604480.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null