Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6740824cbc6569b879192958aba8d7c19a37b1e0fb8af92c41f019465a1f23e9
+oid sha256:2206f18da13cac26d2ec2bed36b4f821c658adeb423f55dbe543fa605dc63437
 size 50624

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43cdfff71f3671e67b631c510d30860951cd1872dab1cc7488a49c23c28c990b
+oid sha256:6ed9fceb0c35d65f5d58672fde2d67c762de0beaca47c748dfbc4eba7292e086
 size 118090

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb15352bd7e2341ded30f538e02252ffedee1e06f9a15f2330c824cec2916b72
+oid sha256:f2222dabb2df8ccac51e050564dd2094b99cc4c0e68f8182da0376974a8cdc25
 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": 10.378252029418945,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.00026476599980936846,
+  "best_metric": 10.368429183959961,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.0005295319996187369,
   "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": 155.156,
       "eval_steps_per_second": 77.578,
       "step": 25
+    },
+    {
+      "epoch": 0.0002753566398017432,
+      "grad_norm": 0.24394074082374573,
+      "learning_rate": 0.0001,
+      "loss": 10.3524,
+      "step": 26
+    },
+    {
+      "epoch": 0.00028594727979411793,
+      "grad_norm": 0.21432097256183624,
+      "learning_rate": 9.345968707698569e-05,
+      "loss": 10.3553,
+      "step": 27
+    },
+    {
+      "epoch": 0.0002965379197864927,
+      "grad_norm": 0.22124646604061127,
+      "learning_rate": 8.694738077799488e-05,
+      "loss": 10.3506,
+      "step": 28
+    },
+    {
+      "epoch": 0.00030712855977886746,
+      "grad_norm": 0.21801720559597015,
+      "learning_rate": 8.049096779838719e-05,
+      "loss": 10.3924,
+      "step": 29
+    },
+    {
+      "epoch": 0.0003177191997712422,
+      "grad_norm": 0.22025315463542938,
+      "learning_rate": 7.411809548974792e-05,
+      "loss": 10.3803,
+      "step": 30
+    },
+    {
+      "epoch": 0.0003283098397636169,
+      "grad_norm": 0.2573018968105316,
+      "learning_rate": 6.785605346968386e-05,
+      "loss": 10.3521,
+      "step": 31
+    },
+    {
+      "epoch": 0.00033890047975599166,
+      "grad_norm": 0.23922796547412872,
+      "learning_rate": 6.173165676349103e-05,
+      "loss": 10.3644,
+      "step": 32
+    },
+    {
+      "epoch": 0.0003494911197483664,
+      "grad_norm": 0.23983879387378693,
+      "learning_rate": 5.577113097809989e-05,
+      "loss": 10.3523,
+      "step": 33
+    },
+    {
+      "epoch": 0.00036008175974074113,
+      "grad_norm": 0.2627752125263214,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 10.3997,
+      "step": 34
+    },
+    {
+      "epoch": 0.00037067239973311586,
+      "grad_norm": 0.26665353775024414,
+      "learning_rate": 4.444297669803981e-05,
+      "loss": 10.3918,
+      "step": 35
+    },
+    {
+      "epoch": 0.0003812630397254906,
+      "grad_norm": 0.2439327985048294,
+      "learning_rate": 3.9123857099127936e-05,
+      "loss": 10.3513,
+      "step": 36
+    },
+    {
+      "epoch": 0.00039185367971786533,
+      "grad_norm": 0.2464238703250885,
+      "learning_rate": 3.406541848999312e-05,
+      "loss": 10.366,
+      "step": 37
+    },
+    {
+      "epoch": 0.00040244431971024006,
+      "grad_norm": 0.2734537422657013,
+      "learning_rate": 2.9289321881345254e-05,
+      "loss": 10.3739,
+      "step": 38
+    },
+    {
+      "epoch": 0.00041303495970261485,
+      "grad_norm": 0.27960556745529175,
+      "learning_rate": 2.4816019252102273e-05,
+      "loss": 10.398,
+      "step": 39
+    },
+    {
+      "epoch": 0.0004236255996949896,
+      "grad_norm": 0.25336456298828125,
+      "learning_rate": 2.0664665970876496e-05,
+      "loss": 10.3466,
+      "step": 40
+    },
+    {
+      "epoch": 0.0004342162396873643,
+      "grad_norm": 0.2658770978450775,
+      "learning_rate": 1.6853038769745467e-05,
+      "loss": 10.3344,
+      "step": 41
+    },
+    {
+      "epoch": 0.00044480687967973906,
+      "grad_norm": 0.28324833512306213,
+      "learning_rate": 1.339745962155613e-05,
+      "loss": 10.3558,
+      "step": 42
+    },
+    {
+      "epoch": 0.0004553975196721138,
+      "grad_norm": 0.2617306411266327,
+      "learning_rate": 1.0312725846731175e-05,
+      "loss": 10.3627,
+      "step": 43
+    },
+    {
+      "epoch": 0.0004659881596644885,
+      "grad_norm": 0.28455761075019836,
+      "learning_rate": 7.612046748871327e-06,
+      "loss": 10.3325,
+      "step": 44
+    },
+    {
+      "epoch": 0.00047657879965686326,
+      "grad_norm": 0.2544795572757721,
+      "learning_rate": 5.306987050489442e-06,
+      "loss": 10.3822,
+      "step": 45
+    },
+    {
+      "epoch": 0.000487169439649238,
+      "grad_norm": 0.2631848454475403,
+      "learning_rate": 3.40741737109318e-06,
+      "loss": 10.375,
+      "step": 46
+    },
+    {
+      "epoch": 0.0004977600796416127,
+      "grad_norm": 0.2916587293148041,
+      "learning_rate": 1.921471959676957e-06,
+      "loss": 10.3545,
+      "step": 47
+    },
+    {
+      "epoch": 0.0005083507196339875,
+      "grad_norm": 0.3416881263256073,
+      "learning_rate": 8.555138626189618e-07,
+      "loss": 10.3671,
+      "step": 48
+    },
+    {
+      "epoch": 0.0005189413596263622,
+      "grad_norm": 0.2896738052368164,
+      "learning_rate": 2.141076761396521e-07,
+      "loss": 10.3615,
+      "step": 49
+    },
+    {
+      "epoch": 0.0005295319996187369,
+      "grad_norm": 0.3720775246620178,
+      "learning_rate": 0.0,
+      "loss": 10.3921,
+      "step": 50
+    },
+    {
+      "epoch": 0.0005295319996187369,
+      "eval_loss": 10.368429183959961,
+      "eval_runtime": 256.1367,
+      "eval_samples_per_second": 155.222,
+      "eval_steps_per_second": 77.611,
+      "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": 2615122329600.0,
+  "total_flos": 5230244659200.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null