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:b4e7ea31198894cffeed1f94ca0b6498960b49ae3277ac664dfbb1a48c8a145c
+oid sha256:06028e699931144f7ddd7c18b06581bd451ea404d793a817cb83718a029c33f4
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:88af9e610fc9103369df7f88fc3e99ca1de2b3b5657a071dff3f2a727b5a10ca
+oid sha256:3fdd600d0b4b7543c90546ea2dcce8ff1636bb46847b4aea06446d63036b1419
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ab4d3282a7fca4473107087858815527ab7fea7b581560bf0babebdc8adaec1
+oid sha256:62df9e30b5c751227baa39d829b010cbb6b39d0330a759bd6dbf1764b556c087
 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": 0.32778090238571167,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.04737091425864519,
+  "best_metric": 0.24849273264408112,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.09474182851729038,
   "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": 3.576,
       "eval_steps_per_second": 1.796,
       "step": 25
+    },
+    {
+      "epoch": 0.049265750828991,
+      "grad_norm": 1.4925986528396606,
+      "learning_rate": 0.0001,
+      "loss": 0.3496,
+      "step": 26
+    },
+    {
+      "epoch": 0.05116058739933681,
+      "grad_norm": 1.0122554302215576,
+      "learning_rate": 9.345968707698569e-05,
+      "loss": 0.3341,
+      "step": 27
+    },
+    {
+      "epoch": 0.053055423969682616,
+      "grad_norm": 2.3204073905944824,
+      "learning_rate": 8.694738077799488e-05,
+      "loss": 0.3444,
+      "step": 28
+    },
+    {
+      "epoch": 0.054950260540028426,
+      "grad_norm": 0.687174916267395,
+      "learning_rate": 8.049096779838719e-05,
+      "loss": 0.3201,
+      "step": 29
+    },
+    {
+      "epoch": 0.05684509711037423,
+      "grad_norm": 2.4244771003723145,
+      "learning_rate": 7.411809548974792e-05,
+      "loss": 0.2972,
+      "step": 30
+    },
+    {
+      "epoch": 0.05873993368072004,
+      "grad_norm": 3.1649410724639893,
+      "learning_rate": 6.785605346968386e-05,
+      "loss": 0.3351,
+      "step": 31
+    },
+    {
+      "epoch": 0.060634770251065846,
+      "grad_norm": 4.414581775665283,
+      "learning_rate": 6.173165676349103e-05,
+      "loss": 0.4242,
+      "step": 32
+    },
+    {
+      "epoch": 0.06252960682141165,
+      "grad_norm": 4.019096851348877,
+      "learning_rate": 5.577113097809989e-05,
+      "loss": 0.4118,
+      "step": 33
+    },
+    {
+      "epoch": 0.06442444339175746,
+      "grad_norm": 2.4438300132751465,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 0.3164,
+      "step": 34
+    },
+    {
+      "epoch": 0.06631927996210327,
+      "grad_norm": 2.3303329944610596,
+      "learning_rate": 4.444297669803981e-05,
+      "loss": 0.3527,
+      "step": 35
+    },
+    {
+      "epoch": 0.06821411653244908,
+      "grad_norm": 1.2413207292556763,
+      "learning_rate": 3.9123857099127936e-05,
+      "loss": 0.2543,
+      "step": 36
+    },
+    {
+      "epoch": 0.07010895310279489,
+      "grad_norm": 0.9027528166770935,
+      "learning_rate": 3.406541848999312e-05,
+      "loss": 0.26,
+      "step": 37
+    },
+    {
+      "epoch": 0.0720037896731407,
+      "grad_norm": 1.1008473634719849,
+      "learning_rate": 2.9289321881345254e-05,
+      "loss": 0.2368,
+      "step": 38
+    },
+    {
+      "epoch": 0.0738986262434865,
+      "grad_norm": 1.1780225038528442,
+      "learning_rate": 2.4816019252102273e-05,
+      "loss": 0.2697,
+      "step": 39
+    },
+    {
+      "epoch": 0.07579346281383231,
+      "grad_norm": 2.025906562805176,
+      "learning_rate": 2.0664665970876496e-05,
+      "loss": 0.3411,
+      "step": 40
+    },
+    {
+      "epoch": 0.07768829938417811,
+      "grad_norm": 2.19376277923584,
+      "learning_rate": 1.6853038769745467e-05,
+      "loss": 0.2697,
+      "step": 41
+    },
+    {
+      "epoch": 0.07958313595452392,
+      "grad_norm": 2.385338306427002,
+      "learning_rate": 1.339745962155613e-05,
+      "loss": 0.3528,
+      "step": 42
+    },
+    {
+      "epoch": 0.08147797252486973,
+      "grad_norm": 1.4501081705093384,
+      "learning_rate": 1.0312725846731175e-05,
+      "loss": 0.1934,
+      "step": 43
+    },
+    {
+      "epoch": 0.08337280909521554,
+      "grad_norm": 1.3427797555923462,
+      "learning_rate": 7.612046748871327e-06,
+      "loss": 0.2357,
+      "step": 44
+    },
+    {
+      "epoch": 0.08526764566556135,
+      "grad_norm": 1.3562896251678467,
+      "learning_rate": 5.306987050489442e-06,
+      "loss": 0.3346,
+      "step": 45
+    },
+    {
+      "epoch": 0.08716248223590715,
+      "grad_norm": 2.4184749126434326,
+      "learning_rate": 3.40741737109318e-06,
+      "loss": 0.1874,
+      "step": 46
+    },
+    {
+      "epoch": 0.08905731880625296,
+      "grad_norm": 2.308922290802002,
+      "learning_rate": 1.921471959676957e-06,
+      "loss": 0.2183,
+      "step": 47
+    },
+    {
+      "epoch": 0.09095215537659877,
+      "grad_norm": 2.909156084060669,
+      "learning_rate": 8.555138626189618e-07,
+      "loss": 0.2822,
+      "step": 48
+    },
+    {
+      "epoch": 0.09284699194694458,
+      "grad_norm": 2.4265296459198,
+      "learning_rate": 2.141076761396521e-07,
+      "loss": 0.2447,
+      "step": 49
+    },
+    {
+      "epoch": 0.09474182851729038,
+      "grad_norm": 1.9471189975738525,
+      "learning_rate": 0.0,
+      "loss": 0.2413,
+      "step": 50
+    },
+    {
+      "epoch": 0.09474182851729038,
+      "eval_loss": 0.24849273264408112,
+      "eval_runtime": 62.377,
+      "eval_samples_per_second": 3.575,
+      "eval_steps_per_second": 1.796,
+      "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