Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2db613785a45f6801b485affa8c8bd1b8011ef518080fa324d21ccf5764c31e1
+oid sha256:9f69bb59fbc33759115bc690abb9c0c601b3b189c9e3110add01c17710e54ee2
 size 60599872

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f214007a3e56453fd51af0d910d0b6daf3eec20618bc94c749bab57fde93eefa
+oid sha256:8a178a14594ef1d01994df326fc444517c4b2f75983055700c808f50e1476b25
 size 121392706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ffcc015966458fb6ed1151f970535149e78428154726cdbf9e00cb9c9f138fb1
+oid sha256:53f67fc01bfe2d0fe5280e361d920639e6a00c364af5ad002a1ff7c1d9c8ab47
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48f1d4688b3913b3a952f1cf3ee84c928790f2447f697c3b2a1e8f51615c0ef6
+oid sha256:7b41ae8c84fb1447fe6a8a970ea16bda2569b7175a6a3403e64b94e7bf7bad93
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:35e60cfdccdbf805ae74a3b760f044ec0a95cacb492066077d6ad9032463a8d3
+oid sha256:b274bece9d6337d868ce3b2a28f2cb128a7502172e6b463bf58ce380da6f79b8
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a086cc7c47ab3670d44db1b56a8c23c0aa4e98586eaf00dc3dc66836a24bc04
+oid sha256:ac783c39f7f4d700c336e5bb46cd88671ad47706aa24bf80b19faa012a0dc426
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d271cdb95f63cd655315f063ca2e25c78dc5ae4275523c5d4f80f367586b3351
+oid sha256:5607f6de446164d9d9adb8b91c44cec55b14aa391e24ba5637c08b834eedda2a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.1271306425333023,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 1.352159468438538,
+  "epoch": 2.704318936877076,
   "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": 69.606,
       "eval_steps_per_second": 18.098,
       "step": 25
+    },
+    {
+      "epoch": 1.4053156146179402,
+      "grad_norm": 0.520526647567749,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.0646,
+      "step": 26
+    },
+    {
+      "epoch": 1.4584717607973423,
+      "grad_norm": 1.3327345848083496,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 0.0993,
+      "step": 27
+    },
+    {
+      "epoch": 1.5116279069767442,
+      "grad_norm": 1.7566813230514526,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 0.0945,
+      "step": 28
+    },
+    {
+      "epoch": 1.564784053156146,
+      "grad_norm": 4.805406093597412,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 0.0618,
+      "step": 29
+    },
+    {
+      "epoch": 1.6179401993355482,
+      "grad_norm": 0.9493386149406433,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 0.135,
+      "step": 30
+    },
+    {
+      "epoch": 1.6710963455149501,
+      "grad_norm": 0.8112987279891968,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 0.0761,
+      "step": 31
+    },
+    {
+      "epoch": 1.7242524916943522,
+      "grad_norm": 1.9758391380310059,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 0.1024,
+      "step": 32
+    },
+    {
+      "epoch": 1.7774086378737541,
+      "grad_norm": 0.5663211941719055,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 0.0501,
+      "step": 33
+    },
+    {
+      "epoch": 1.830564784053156,
+      "grad_norm": 0.7831739783287048,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 0.092,
+      "step": 34
+    },
+    {
+      "epoch": 1.8837209302325582,
+      "grad_norm": 1.0481925010681152,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 0.1153,
+      "step": 35
+    },
+    {
+      "epoch": 1.9368770764119603,
+      "grad_norm": 0.7795256972312927,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 0.1191,
+      "step": 36
+    },
+    {
+      "epoch": 2.0132890365448506,
+      "grad_norm": 0.9911825060844421,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 0.1322,
+      "step": 37
+    },
+    {
+      "epoch": 2.0664451827242525,
+      "grad_norm": 0.6058715581893921,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.0589,
+      "step": 38
+    },
+    {
+      "epoch": 2.1196013289036544,
+      "grad_norm": 0.5736090540885925,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 0.0648,
+      "step": 39
+    },
+    {
+      "epoch": 2.1727574750830563,
+      "grad_norm": 0.7126216888427734,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 0.0467,
+      "step": 40
+    },
+    {
+      "epoch": 2.2259136212624586,
+      "grad_norm": 0.5185224413871765,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 0.0806,
+      "step": 41
+    },
+    {
+      "epoch": 2.2790697674418605,
+      "grad_norm": 0.7146442532539368,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 0.1057,
+      "step": 42
+    },
+    {
+      "epoch": 2.3322259136212624,
+      "grad_norm": 0.48135268688201904,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 0.0501,
+      "step": 43
+    },
+    {
+      "epoch": 2.3853820598006643,
+      "grad_norm": 0.6691005825996399,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 0.0646,
+      "step": 44
+    },
+    {
+      "epoch": 2.438538205980066,
+      "grad_norm": 0.4291771948337555,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 0.0691,
+      "step": 45
+    },
+    {
+      "epoch": 2.4916943521594686,
+      "grad_norm": 0.6109609007835388,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 0.0705,
+      "step": 46
+    },
+    {
+      "epoch": 2.5448504983388704,
+      "grad_norm": 0.7353491187095642,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 0.0619,
+      "step": 47
+    },
+    {
+      "epoch": 2.5980066445182723,
+      "grad_norm": 0.4926731586456299,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 0.0537,
+      "step": 48
+    },
+    {
+      "epoch": 2.6511627906976747,
+      "grad_norm": 0.6144967079162598,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 0.0533,
+      "step": 49
+    },
+    {
+      "epoch": 2.704318936877076,
+      "grad_norm": 0.7941309213638306,
+      "learning_rate": 1e-05,
+      "loss": 0.1014,
+      "step": 50
+    },
+    {
+      "epoch": 2.704318936877076,
+      "eval_loss": 0.14437605440616608,
+      "eval_runtime": 0.739,
+      "eval_samples_per_second": 67.658,
+      "eval_steps_per_second": 17.591,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -212,7 +395,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 0
+        "early_stopping_patience_counter": 1
       }
     },
     "TrainerControl": {
@@ -221,12 +404,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.27222702669824e+16,
+  "total_flos": 2.54445405339648e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null