Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:50a828d9e289d6e47c52d7a46ec04f7b7401b68d2dda17c2474386ed52a877cb
+oid sha256:e11d5d2ac0f1e24fcbd852bd394f3b45d5ff4bb469bab09608406fb4130e58d0
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:62d09d272001e1cd2f2a4b9f2083541f7e101d63ca66430a5fa939afdc7f7055
+oid sha256:be651d772fa174baabf41ed5ceeff20138cbd755523edb6e0e0a421a79e4345f
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3dfbe8dc8c5d3c8ea8dbaf49dfe0bce5ff97fc0dfc257ccafac6d2ac84969f49
+oid sha256:cacf92f92fe6acd0ccda1db3ab395ea9c5949fed579128b1b4bb79dd31a1e077
 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": 0.5954957604408264,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.0002807766281534725,
+  "best_metric": 0.5892420411109924,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.000561553256306945,
   "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": 2.837,
       "eval_steps_per_second": 1.419,
       "step": 25
+    },
+    {
+      "epoch": 0.0002920076932796114,
+      "grad_norm": 0.7325270771980286,
+      "learning_rate": 0.0001,
+      "loss": 0.7688,
+      "step": 26
+    },
+    {
+      "epoch": 0.0003032387584057503,
+      "grad_norm": 0.7012045979499817,
+      "learning_rate": 9.345968707698569e-05,
+      "loss": 0.6944,
+      "step": 27
+    },
+    {
+      "epoch": 0.0003144698235318892,
+      "grad_norm": 0.6815605163574219,
+      "learning_rate": 8.694738077799488e-05,
+      "loss": 0.6855,
+      "step": 28
+    },
+    {
+      "epoch": 0.0003257008886580281,
+      "grad_norm": 0.7034103274345398,
+      "learning_rate": 8.049096779838719e-05,
+      "loss": 0.6411,
+      "step": 29
+    },
+    {
+      "epoch": 0.000336931953784167,
+      "grad_norm": 0.7424677014350891,
+      "learning_rate": 7.411809548974792e-05,
+      "loss": 0.6832,
+      "step": 30
+    },
+    {
+      "epoch": 0.0003481630189103059,
+      "grad_norm": 0.7293113470077515,
+      "learning_rate": 6.785605346968386e-05,
+      "loss": 0.568,
+      "step": 31
+    },
+    {
+      "epoch": 0.0003593940840364448,
+      "grad_norm": 0.8168377876281738,
+      "learning_rate": 6.173165676349103e-05,
+      "loss": 0.6995,
+      "step": 32
+    },
+    {
+      "epoch": 0.00037062514916258373,
+      "grad_norm": 0.7216925024986267,
+      "learning_rate": 5.577113097809989e-05,
+      "loss": 0.705,
+      "step": 33
+    },
+    {
+      "epoch": 0.0003818562142887226,
+      "grad_norm": 1.9464884996414185,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 0.6531,
+      "step": 34
+    },
+    {
+      "epoch": 0.0003930872794148615,
+      "grad_norm": 0.8291040062904358,
+      "learning_rate": 4.444297669803981e-05,
+      "loss": 0.6667,
+      "step": 35
+    },
+    {
+      "epoch": 0.0004043183445410004,
+      "grad_norm": 0.8872710466384888,
+      "learning_rate": 3.9123857099127936e-05,
+      "loss": 0.5128,
+      "step": 36
+    },
+    {
+      "epoch": 0.0004155494096671393,
+      "grad_norm": 0.967703640460968,
+      "learning_rate": 3.406541848999312e-05,
+      "loss": 0.7342,
+      "step": 37
+    },
+    {
+      "epoch": 0.0004267804747932782,
+      "grad_norm": 0.8660141825675964,
+      "learning_rate": 2.9289321881345254e-05,
+      "loss": 0.5803,
+      "step": 38
+    },
+    {
+      "epoch": 0.0004380115399194171,
+      "grad_norm": 1.001227855682373,
+      "learning_rate": 2.4816019252102273e-05,
+      "loss": 0.617,
+      "step": 39
+    },
+    {
+      "epoch": 0.000449242605045556,
+      "grad_norm": 0.9558192491531372,
+      "learning_rate": 2.0664665970876496e-05,
+      "loss": 0.8064,
+      "step": 40
+    },
+    {
+      "epoch": 0.0004604736701716949,
+      "grad_norm": 1.4016711711883545,
+      "learning_rate": 1.6853038769745467e-05,
+      "loss": 1.0338,
+      "step": 41
+    },
+    {
+      "epoch": 0.00047170473529783383,
+      "grad_norm": 0.9859164953231812,
+      "learning_rate": 1.339745962155613e-05,
+      "loss": 0.7711,
+      "step": 42
+    },
+    {
+      "epoch": 0.0004829358004239727,
+      "grad_norm": 0.8740882873535156,
+      "learning_rate": 1.0312725846731175e-05,
+      "loss": 0.6106,
+      "step": 43
+    },
+    {
+      "epoch": 0.0004941668655501116,
+      "grad_norm": 1.0575542449951172,
+      "learning_rate": 7.612046748871327e-06,
+      "loss": 0.6771,
+      "step": 44
+    },
+    {
+      "epoch": 0.0005053979306762505,
+      "grad_norm": 1.3176660537719727,
+      "learning_rate": 5.306987050489442e-06,
+      "loss": 0.9257,
+      "step": 45
+    },
+    {
+      "epoch": 0.0005166289958023894,
+      "grad_norm": 0.936985433101654,
+      "learning_rate": 3.40741737109318e-06,
+      "loss": 0.6682,
+      "step": 46
+    },
+    {
+      "epoch": 0.0005278600609285283,
+      "grad_norm": 1.1479442119598389,
+      "learning_rate": 1.921471959676957e-06,
+      "loss": 0.7345,
+      "step": 47
+    },
+    {
+      "epoch": 0.0005390911260546673,
+      "grad_norm": 1.1492356061935425,
+      "learning_rate": 8.555138626189618e-07,
+      "loss": 0.5426,
+      "step": 48
+    },
+    {
+      "epoch": 0.0005503221911808061,
+      "grad_norm": 1.387621283531189,
+      "learning_rate": 2.141076761396521e-07,
+      "loss": 0.574,
+      "step": 49
+    },
+    {
+      "epoch": 0.000561553256306945,
+      "grad_norm": 1.3614716529846191,
+      "learning_rate": 0.0,
+      "loss": 0.5347,
+      "step": 50
+    },
+    {
+      "epoch": 0.000561553256306945,
+      "eval_loss": 0.5892420411109924,
+      "eval_runtime": 13214.8134,
+      "eval_samples_per_second": 2.837,
+      "eval_steps_per_second": 1.418,
+      "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