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:b8b2ef065b3c0dfc476292baf3a4ecb946e3e702d8cd4d923a67a54ad7a156db
+oid sha256:1d4e18070f1fbb323ff7ff66736dbb195610e6b5ce5e81b24898f35e97a06abc
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e9ddd5b71df8d6e526fc9747b388672bd6f89d40f3eefa87e679e2f259ddd899
+oid sha256:39f29dcc78510dc497cd6eee55d10960c256b53fccec8fb8f066642446661b29
 size 170920084

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5537e910b76a6f610d3778b948cabe4cd17467c9f407942be9530729a5c41a5a
+oid sha256:b628271795a824ff26c9ba2c9328f6e4104a7f47aab89bc3ae57b145971748ed
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6676fe28230ae15b45fb334c871c6fdf1a7984a935952b9f8650896c37a8c106
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.0832998752593994,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.07732456988208003,
+  "best_metric": 1.06325101852417,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.15464913976416006,
   "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": 3.628,
       "eval_steps_per_second": 1.817,
       "step": 25
+    },
+    {
+      "epoch": 0.08041755267736324,
+      "grad_norm": 24.669111251831055,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 17.5459,
+      "step": 26
+    },
+    {
+      "epoch": 0.08351053547264643,
+      "grad_norm": 23.340457916259766,
+      "learning_rate": 6.167226819279528e-05,
+      "loss": 16.5561,
+      "step": 27
+    },
+    {
+      "epoch": 0.08660351826792964,
+      "grad_norm": 25.84408950805664,
+      "learning_rate": 5.782172325201155e-05,
+      "loss": 17.3012,
+      "step": 28
+    },
+    {
+      "epoch": 0.08969650106321284,
+      "grad_norm": 25.935504913330078,
+      "learning_rate": 5.392295478639225e-05,
+      "loss": 18.7042,
+      "step": 29
+    },
+    {
+      "epoch": 0.09278948385849603,
+      "grad_norm": 23.08302879333496,
+      "learning_rate": 5e-05,
+      "loss": 16.2506,
+      "step": 30
+    },
+    {
+      "epoch": 0.09588246665377924,
+      "grad_norm": 24.507280349731445,
+      "learning_rate": 4.607704521360776e-05,
+      "loss": 18.5361,
+      "step": 31
+    },
+    {
+      "epoch": 0.09897544944906243,
+      "grad_norm": 22.492021560668945,
+      "learning_rate": 4.2178276747988446e-05,
+      "loss": 16.9076,
+      "step": 32
+    },
+    {
+      "epoch": 0.10206843224434564,
+      "grad_norm": 24.12836456298828,
+      "learning_rate": 3.832773180720475e-05,
+      "loss": 18.5358,
+      "step": 33
+    },
+    {
+      "epoch": 0.10516141503962884,
+      "grad_norm": 22.608657836914062,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 16.6398,
+      "step": 34
+    },
+    {
+      "epoch": 0.10825439783491204,
+      "grad_norm": 21.76448631286621,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 16.4674,
+      "step": 35
+    },
+    {
+      "epoch": 0.11134738063019524,
+      "grad_norm": 24.399173736572266,
+      "learning_rate": 2.7300475013022663e-05,
+      "loss": 16.219,
+      "step": 36
+    },
+    {
+      "epoch": 0.11444036342547845,
+      "grad_norm": 21.240434646606445,
+      "learning_rate": 2.3875071764202563e-05,
+      "loss": 14.7258,
+      "step": 37
+    },
+    {
+      "epoch": 0.11753334622076164,
+      "grad_norm": 23.667985916137695,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 17.4903,
+      "step": 38
+    },
+    {
+      "epoch": 0.12062632901604485,
+      "grad_norm": 24.75313377380371,
+      "learning_rate": 1.7527597583490822e-05,
+      "loss": 18.4833,
+      "step": 39
+    },
+    {
+      "epoch": 0.12371931181132804,
+      "grad_norm": 28.104583740234375,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 16.1857,
+      "step": 40
+    },
+    {
+      "epoch": 0.12681229460661125,
+      "grad_norm": 24.995805740356445,
+      "learning_rate": 1.1979701719998453e-05,
+      "loss": 16.9785,
+      "step": 41
+    },
+    {
+      "epoch": 0.12990527740189445,
+      "grad_norm": 26.10293197631836,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 17.8392,
+      "step": 42
+    },
+    {
+      "epoch": 0.13299826019717764,
+      "grad_norm": 22.538623809814453,
+      "learning_rate": 7.367991782295391e-06,
+      "loss": 16.8663,
+      "step": 43
+    },
+    {
+      "epoch": 0.13609124299246086,
+      "grad_norm": 23.371549606323242,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 17.0096,
+      "step": 44
+    },
+    {
+      "epoch": 0.13918422578774406,
+      "grad_norm": 22.70631980895996,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 16.9947,
+      "step": 45
+    },
+    {
+      "epoch": 0.14227720858302725,
+      "grad_norm": 26.935110092163086,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 17.6166,
+      "step": 46
+    },
+    {
+      "epoch": 0.14537019137831045,
+      "grad_norm": 24.898109436035156,
+      "learning_rate": 1.3815039801161721e-06,
+      "loss": 17.4678,
+      "step": 47
+    },
+    {
+      "epoch": 0.14846317417359367,
+      "grad_norm": 23.253236770629883,
+      "learning_rate": 6.15582970243117e-07,
+      "loss": 17.145,
+      "step": 48
+    },
+    {
+      "epoch": 0.15155615696887687,
+      "grad_norm": 23.85171890258789,
+      "learning_rate": 1.5413331334360182e-07,
+      "loss": 17.1861,
+      "step": 49
+    },
+    {
+      "epoch": 0.15464913976416006,
+      "grad_norm": 22.377422332763672,
+      "learning_rate": 0.0,
+      "loss": 19.1859,
+      "step": 50
+    },
+    {
+      "epoch": 0.15464913976416006,
+      "eval_loss": 1.06325101852417,
+      "eval_runtime": 150.4088,
+      "eval_samples_per_second": 3.623,
+      "eval_steps_per_second": 1.815,
+      "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": 7.709054073411994e+16,
+  "total_flos": 1.5435789463506125e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null