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:c9be2f883ee1b2090c0c73c05f10a4fba61a762998132123ca81c1a60c8f1123
+oid sha256:8d73f1922b3b94b9ebb6566d7fce6c21d46e85a91e0df4d2ea1a32815fb36822
 size 767856

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5267e38832ec92bc0933dda305a440ef2be4072e0306d650f9ec348d818ea5b7
+oid sha256:c80599a0c69c2651d389b1423bbe1f8fe1e75e1ffd46e80d07d384db51e2612a
 size 1601338

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b9c217816778ee86c5a2341ec591bf4058760d8f1c8409e59ea5be2a6dbb933
+oid sha256:43bac18ef42cf35157a53c1f2f95158a166daa7d6ec1b9b872d8664603343ecc
 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": 7.113040924072266,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.005514807257486351,
+  "best_metric": 7.017041206359863,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.011029614514972702,
   "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": 95.241,
       "eval_steps_per_second": 47.645,
       "step": 25
+    },
+    {
+      "epoch": 0.005735399547785805,
+      "grad_norm": 2.8481411933898926,
+      "learning_rate": 0.0001,
+      "loss": 7.006,
+      "step": 26
+    },
+    {
+      "epoch": 0.005955991838085259,
+      "grad_norm": 3.5465781688690186,
+      "learning_rate": 9.345968707698569e-05,
+      "loss": 7.1405,
+      "step": 27
+    },
+    {
+      "epoch": 0.006176584128384713,
+      "grad_norm": 3.2511773109436035,
+      "learning_rate": 8.694738077799488e-05,
+      "loss": 7.0427,
+      "step": 28
+    },
+    {
+      "epoch": 0.006397176418684167,
+      "grad_norm": 3.1548283100128174,
+      "learning_rate": 8.049096779838719e-05,
+      "loss": 7.1469,
+      "step": 29
+    },
+    {
+      "epoch": 0.006617768708983621,
+      "grad_norm": 3.4234230518341064,
+      "learning_rate": 7.411809548974792e-05,
+      "loss": 7.2329,
+      "step": 30
+    },
+    {
+      "epoch": 0.0068383609992830755,
+      "grad_norm": 3.0600433349609375,
+      "learning_rate": 6.785605346968386e-05,
+      "loss": 6.6121,
+      "step": 31
+    },
+    {
+      "epoch": 0.007058953289582529,
+      "grad_norm": 3.1275887489318848,
+      "learning_rate": 6.173165676349103e-05,
+      "loss": 7.1327,
+      "step": 32
+    },
+    {
+      "epoch": 0.007279545579881983,
+      "grad_norm": 4.214815139770508,
+      "learning_rate": 5.577113097809989e-05,
+      "loss": 7.3558,
+      "step": 33
+    },
+    {
+      "epoch": 0.007500137870181437,
+      "grad_norm": 3.6205644607543945,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 7.1521,
+      "step": 34
+    },
+    {
+      "epoch": 0.007720730160480891,
+      "grad_norm": 4.0161452293396,
+      "learning_rate": 4.444297669803981e-05,
+      "loss": 6.7042,
+      "step": 35
+    },
+    {
+      "epoch": 0.007941322450780346,
+      "grad_norm": 5.151815414428711,
+      "learning_rate": 3.9123857099127936e-05,
+      "loss": 6.7373,
+      "step": 36
+    },
+    {
+      "epoch": 0.0081619147410798,
+      "grad_norm": 4.190551280975342,
+      "learning_rate": 3.406541848999312e-05,
+      "loss": 8.0788,
+      "step": 37
+    },
+    {
+      "epoch": 0.008382507031379252,
+      "grad_norm": 4.7776570320129395,
+      "learning_rate": 2.9289321881345254e-05,
+      "loss": 7.3549,
+      "step": 38
+    },
+    {
+      "epoch": 0.008603099321678707,
+      "grad_norm": 5.777076721191406,
+      "learning_rate": 2.4816019252102273e-05,
+      "loss": 6.666,
+      "step": 39
+    },
+    {
+      "epoch": 0.00882369161197816,
+      "grad_norm": 4.582779407501221,
+      "learning_rate": 2.0664665970876496e-05,
+      "loss": 6.011,
+      "step": 40
+    },
+    {
+      "epoch": 0.009044283902277616,
+      "grad_norm": 5.211250305175781,
+      "learning_rate": 1.6853038769745467e-05,
+      "loss": 6.9135,
+      "step": 41
+    },
+    {
+      "epoch": 0.009264876192577069,
+      "grad_norm": 5.360510349273682,
+      "learning_rate": 1.339745962155613e-05,
+      "loss": 7.4839,
+      "step": 42
+    },
+    {
+      "epoch": 0.009485468482876524,
+      "grad_norm": 6.11507511138916,
+      "learning_rate": 1.0312725846731175e-05,
+      "loss": 6.7759,
+      "step": 43
+    },
+    {
+      "epoch": 0.009706060773175977,
+      "grad_norm": 6.635857582092285,
+      "learning_rate": 7.612046748871327e-06,
+      "loss": 7.8113,
+      "step": 44
+    },
+    {
+      "epoch": 0.009926653063475432,
+      "grad_norm": 7.438478469848633,
+      "learning_rate": 5.306987050489442e-06,
+      "loss": 7.3099,
+      "step": 45
+    },
+    {
+      "epoch": 0.010147245353774885,
+      "grad_norm": 6.5027923583984375,
+      "learning_rate": 3.40741737109318e-06,
+      "loss": 7.0473,
+      "step": 46
+    },
+    {
+      "epoch": 0.01036783764407434,
+      "grad_norm": 5.755157947540283,
+      "learning_rate": 1.921471959676957e-06,
+      "loss": 7.2164,
+      "step": 47
+    },
+    {
+      "epoch": 0.010588429934373794,
+      "grad_norm": 10.475558280944824,
+      "learning_rate": 8.555138626189618e-07,
+      "loss": 6.7425,
+      "step": 48
+    },
+    {
+      "epoch": 0.010809022224673248,
+      "grad_norm": 8.64743423461914,
+      "learning_rate": 2.141076761396521e-07,
+      "loss": 7.6537,
+      "step": 49
+    },
+    {
+      "epoch": 0.011029614514972702,
+      "grad_norm": 9.511824607849121,
+      "learning_rate": 0.0,
+      "loss": 7.135,
+      "step": 50
+    },
+    {
+      "epoch": 0.011029614514972702,
+      "eval_loss": 7.017041206359863,
+      "eval_runtime": 19.9636,
+      "eval_samples_per_second": 95.624,
+      "eval_steps_per_second": 47.837,
+      "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": 13574760038400.0,
+  "total_flos": 27149520076800.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null