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:ea4ff4ebaf513b94d0e365762cb6eb2c4c811da4baaef1c1337cc02ff46f6269
+oid sha256:63a5896afe845576a3badf7c846aae19272b36c71d1c3f985c84b6976f8f751b
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4fbb3767d82557ccdec19c1eb5416fcd500ffa84a7d648992339a6146c708048
+oid sha256:b4be3cb46ee5b41c4cd0a8a9a7055066ab19dc71a525ebb5eb43bbd8c24bd8d5
 size 341314196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:487a416c08616739437554bc1e64b7a42925248a47025dea53ebda2624d7f54a
+oid sha256:71f4fde50ed59bec556eb63d90f21bbf0a124f5e79bd04ed2e48fbbc2af7e7d6
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb15fdd4c0ab874f4afa0ea95fae119cbc74554df5fbe92ab825fe27063eaa04
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.9541823863983154,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.005465376837732962,
+  "epoch": 0.010930753675465924,
   "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": 13.481,
       "eval_steps_per_second": 1.685,
       "step": 25
+    },
+    {
+      "epoch": 0.00568399191124228,
+      "grad_norm": 5.85664176940918,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 4.9116,
+      "step": 26
+    },
+    {
+      "epoch": 0.005902606984751598,
+      "grad_norm": 5.565213203430176,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 4.7688,
+      "step": 27
+    },
+    {
+      "epoch": 0.006121222058260917,
+      "grad_norm": 5.267945289611816,
+      "learning_rate": 4.825502516487497e-05,
+      "loss": 4.3886,
+      "step": 28
+    },
+    {
+      "epoch": 0.006339837131770235,
+      "grad_norm": 5.487580299377441,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 4.937,
+      "step": 29
+    },
+    {
+      "epoch": 0.006558452205279554,
+      "grad_norm": 5.872722625732422,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 4.5749,
+      "step": 30
+    },
+    {
+      "epoch": 0.0067770672787888725,
+      "grad_norm": 5.429628849029541,
+      "learning_rate": 3.790390522001662e-05,
+      "loss": 4.0589,
+      "step": 31
+    },
+    {
+      "epoch": 0.006995682352298191,
+      "grad_norm": 6.078123092651367,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 4.3092,
+      "step": 32
+    },
+    {
+      "epoch": 0.00721429742580751,
+      "grad_norm": 6.005480766296387,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 4.3421,
+      "step": 33
+    },
+    {
+      "epoch": 0.007432912499316828,
+      "grad_norm": 6.326774597167969,
+      "learning_rate": 2.8081442660546125e-05,
+      "loss": 4.169,
+      "step": 34
+    },
+    {
+      "epoch": 0.007651527572826147,
+      "grad_norm": 8.954018592834473,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 2.4574,
+      "step": 35
+    },
+    {
+      "epoch": 0.007870142646335464,
+      "grad_norm": 12.161307334899902,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 1.1153,
+      "step": 36
+    },
+    {
+      "epoch": 0.008088757719844783,
+      "grad_norm": 10.752105712890625,
+      "learning_rate": 1.9216926233717085e-05,
+      "loss": 1.0455,
+      "step": 37
+    },
+    {
+      "epoch": 0.008307372793354102,
+      "grad_norm": 9.942269325256348,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 0.9616,
+      "step": 38
+    },
+    {
+      "epoch": 0.00852598786686342,
+      "grad_norm": 9.08958625793457,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 1.0565,
+      "step": 39
+    },
+    {
+      "epoch": 0.008744602940372739,
+      "grad_norm": 9.308728218078613,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 1.0039,
+      "step": 40
+    },
+    {
+      "epoch": 0.008963218013882057,
+      "grad_norm": 8.348808288574219,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.9989,
+      "step": 41
+    },
+    {
+      "epoch": 0.009181833087391376,
+      "grad_norm": 6.326083660125732,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 0.9553,
+      "step": 42
+    },
+    {
+      "epoch": 0.009400448160900694,
+      "grad_norm": 7.869330406188965,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 1.0569,
+      "step": 43
+    },
+    {
+      "epoch": 0.009619063234410013,
+      "grad_norm": 10.216377258300781,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 1.0558,
+      "step": 44
+    },
+    {
+      "epoch": 0.009837678307919331,
+      "grad_norm": 11.092399597167969,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 0.9817,
+      "step": 45
+    },
+    {
+      "epoch": 0.01005629338142865,
+      "grad_norm": 8.00503921508789,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 1.0639,
+      "step": 46
+    },
+    {
+      "epoch": 0.010274908454937969,
+      "grad_norm": 6.840457916259766,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 0.8486,
+      "step": 47
+    },
+    {
+      "epoch": 0.010493523528447287,
+      "grad_norm": 6.971992492675781,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 0.884,
+      "step": 48
+    },
+    {
+      "epoch": 0.010712138601956606,
+      "grad_norm": 10.650803565979004,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 0.8533,
+      "step": 49
+    },
+    {
+      "epoch": 0.010930753675465924,
+      "grad_norm": 8.342534065246582,
+      "learning_rate": 0.0,
+      "loss": 0.8778,
+      "step": 50
+    },
+    {
+      "epoch": 0.010930753675465924,
+      "eval_loss": 0.9805046319961548,
+      "eval_runtime": 571.055,
+      "eval_samples_per_second": 13.491,
+      "eval_steps_per_second": 1.686,
+      "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": 3.57749904900096e+16,
+  "total_flos": 7.11922310751191e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null