Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:22955aa7616ef2135bed9cb48ed4112f912c57fbf226210ad12bb34234980816
+oid sha256:38a169d8026492b4a4b2d08d29c618ce5bef4292d424a96a55e96bfa8aa0ce75
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f73a9ee50a5d11d6f46e6b904ca45a420d7d5a90df2597807d1b39319941148f
+oid sha256:bd1287ffc4b8f85622198a0ba7f8ab3912323f91e511c56e9853bbe5d0b2f084
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:15f8068815a8f9410e8650b3634811a915e6af878885194160328c30f559375b
+oid sha256:4c4cb33e74c510d0693f32b437395d95719cd52b0e71ddb050d24ed3cf8e7477
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ea7ff16b0c30a914eb0d145e3fb06ff9027c6cd2408e766ce8a09accab89a4d
+oid sha256:e69e2b49ea642509f0c688c16fb190b7cf27dac0a18903a5e2d1467d0343d8b8
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.5998122692108154,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.0017201341704652963,
+  "best_metric": 0.5190518498420715,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.0034402683409305926,
   "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": 2.857,
       "eval_steps_per_second": 1.429,
       "step": 25
+    },
+    {
+      "epoch": 0.0017889395372839081,
+      "grad_norm": 1.5337985754013062,
+      "learning_rate": 0.0001,
+      "loss": 0.3045,
+      "step": 26
+    },
+    {
+      "epoch": 0.00185774490410252,
+      "grad_norm": 1.4691545963287354,
+      "learning_rate": 9.345968707698569e-05,
+      "loss": 0.3119,
+      "step": 27
+    },
+    {
+      "epoch": 0.0019265502709211318,
+      "grad_norm": 1.3081196546554565,
+      "learning_rate": 8.694738077799488e-05,
+      "loss": 0.2755,
+      "step": 28
+    },
+    {
+      "epoch": 0.0019953556377397437,
+      "grad_norm": 1.1037979125976562,
+      "learning_rate": 8.049096779838719e-05,
+      "loss": 0.2116,
+      "step": 29
+    },
+    {
+      "epoch": 0.0020641610045583555,
+      "grad_norm": 0.4469464421272278,
+      "learning_rate": 7.411809548974792e-05,
+      "loss": 0.1618,
+      "step": 30
+    },
+    {
+      "epoch": 0.0021329663713769674,
+      "grad_norm": 4.526829242706299,
+      "learning_rate": 6.785605346968386e-05,
+      "loss": 0.2283,
+      "step": 31
+    },
+    {
+      "epoch": 0.0022017717381955793,
+      "grad_norm": 3.505985736846924,
+      "learning_rate": 6.173165676349103e-05,
+      "loss": 0.2295,
+      "step": 32
+    },
+    {
+      "epoch": 0.002270577105014191,
+      "grad_norm": 1.414526343345642,
+      "learning_rate": 5.577113097809989e-05,
+      "loss": 0.1727,
+      "step": 33
+    },
+    {
+      "epoch": 0.002339382471832803,
+      "grad_norm": 0.5344605445861816,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 0.1778,
+      "step": 34
+    },
+    {
+      "epoch": 0.002408187838651415,
+      "grad_norm": 0.6289926767349243,
+      "learning_rate": 4.444297669803981e-05,
+      "loss": 0.1095,
+      "step": 35
+    },
+    {
+      "epoch": 0.0024769932054700267,
+      "grad_norm": 0.9150691628456116,
+      "learning_rate": 3.9123857099127936e-05,
+      "loss": 0.0482,
+      "step": 36
+    },
+    {
+      "epoch": 0.0025457985722886385,
+      "grad_norm": 0.17626339197158813,
+      "learning_rate": 3.406541848999312e-05,
+      "loss": 0.0967,
+      "step": 37
+    },
+    {
+      "epoch": 0.0026146039391072504,
+      "grad_norm": 0.4345886707305908,
+      "learning_rate": 2.9289321881345254e-05,
+      "loss": 0.0217,
+      "step": 38
+    },
+    {
+      "epoch": 0.002683409305925862,
+      "grad_norm": 1.1442958116531372,
+      "learning_rate": 2.4816019252102273e-05,
+      "loss": 0.1938,
+      "step": 39
+    },
+    {
+      "epoch": 0.002752214672744474,
+      "grad_norm": 1.16999351978302,
+      "learning_rate": 2.0664665970876496e-05,
+      "loss": 0.2015,
+      "step": 40
+    },
+    {
+      "epoch": 0.002821020039563086,
+      "grad_norm": 0.31168338656425476,
+      "learning_rate": 1.6853038769745467e-05,
+      "loss": 0.0151,
+      "step": 41
+    },
+    {
+      "epoch": 0.0028898254063816978,
+      "grad_norm": 0.39355605840682983,
+      "learning_rate": 1.339745962155613e-05,
+      "loss": 0.1057,
+      "step": 42
+    },
+    {
+      "epoch": 0.0029586307732003096,
+      "grad_norm": 0.34757792949676514,
+      "learning_rate": 1.0312725846731175e-05,
+      "loss": 0.0168,
+      "step": 43
+    },
+    {
+      "epoch": 0.0030274361400189215,
+      "grad_norm": 1.0999107360839844,
+      "learning_rate": 7.612046748871327e-06,
+      "loss": 0.1886,
+      "step": 44
+    },
+    {
+      "epoch": 0.0030962415068375333,
+      "grad_norm": 0.3693877160549164,
+      "learning_rate": 5.306987050489442e-06,
+      "loss": 0.0992,
+      "step": 45
+    },
+    {
+      "epoch": 0.003165046873656145,
+      "grad_norm": 0.39368072152137756,
+      "learning_rate": 3.40741737109318e-06,
+      "loss": 0.0189,
+      "step": 46
+    },
+    {
+      "epoch": 0.003233852240474757,
+      "grad_norm": 1.0401899814605713,
+      "learning_rate": 1.921471959676957e-06,
+      "loss": 0.1791,
+      "step": 47
+    },
+    {
+      "epoch": 0.003302657607293369,
+      "grad_norm": 0.31976115703582764,
+      "learning_rate": 8.555138626189618e-07,
+      "loss": 0.0979,
+      "step": 48
+    },
+    {
+      "epoch": 0.0033714629741119807,
+      "grad_norm": 1.008750081062317,
+      "learning_rate": 2.141076761396521e-07,
+      "loss": 0.1768,
+      "step": 49
+    },
+    {
+      "epoch": 0.0034402683409305926,
+      "grad_norm": 1.0031132698059082,
+      "learning_rate": 0.0,
+      "loss": 0.1768,
+      "step": 50
+    },
+    {
+      "epoch": 0.0034402683409305926,
+      "eval_loss": 0.5190518498420715,
+      "eval_runtime": 2142.0667,
+      "eval_samples_per_second": 2.857,
+      "eval_steps_per_second": 1.429,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -221,12 +404,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 3.70943641780224e+16,
+  "total_flos": 7.41887283560448e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null