Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:812be499888096298ca7d75388e0969e7aa670cdbb7467874ad6d365a094ba49
+oid sha256:500843db00f9baeb48eab99a773c32150fdaf52c44c97e5304434c21d8817796
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a6bab1cbd34e05d9c730b80d125f9e60b27b89a11b220122b01737944b957da
+oid sha256:b37844f66afda71c1247a1cd6b52d647c7e48cb92112d1c982f8e61ed56058bd
 size 341314196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:379c58a408ef94f3d7ecd9bc961201dc701eb60205183c48dffc6c016e01854e
+oid sha256:46964a8a602ff121db6e87f2c6587f038d4a86adbb740827629596721c749474
 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": 1.8889018297195435,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.002304784733105928,
+  "epoch": 0.004609569466211856,
   "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": 26.098,
       "eval_steps_per_second": 3.263,
       "step": 25
+    },
+    {
+      "epoch": 0.002396976122430165,
+      "grad_norm": 1.6782158613204956,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 1.8472,
+      "step": 26
+    },
+    {
+      "epoch": 0.0024891675117544023,
+      "grad_norm": 2.059053897857666,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 1.8412,
+      "step": 27
+    },
+    {
+      "epoch": 0.0025813589010786394,
+      "grad_norm": 1.918933391571045,
+      "learning_rate": 4.825502516487497e-05,
+      "loss": 2.0778,
+      "step": 28
+    },
+    {
+      "epoch": 0.0026735502904028765,
+      "grad_norm": 1.7663246393203735,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 1.7202,
+      "step": 29
+    },
+    {
+      "epoch": 0.0027657416797271135,
+      "grad_norm": 2.2439804077148438,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 1.7479,
+      "step": 30
+    },
+    {
+      "epoch": 0.0028579330690513506,
+      "grad_norm": 1.8399550914764404,
+      "learning_rate": 3.790390522001662e-05,
+      "loss": 1.8053,
+      "step": 31
+    },
+    {
+      "epoch": 0.0029501244583755876,
+      "grad_norm": 1.9142265319824219,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 1.6902,
+      "step": 32
+    },
+    {
+      "epoch": 0.0030423158476998247,
+      "grad_norm": 2.07477068901062,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 2.0066,
+      "step": 33
+    },
+    {
+      "epoch": 0.0031345072370240618,
+      "grad_norm": 2.425363302230835,
+      "learning_rate": 2.8081442660546125e-05,
+      "loss": 1.7472,
+      "step": 34
+    },
+    {
+      "epoch": 0.0032266986263482992,
+      "grad_norm": 2.3599395751953125,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 1.8948,
+      "step": 35
+    },
+    {
+      "epoch": 0.0033188900156725363,
+      "grad_norm": 2.2230958938598633,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 1.7077,
+      "step": 36
+    },
+    {
+      "epoch": 0.0034110814049967734,
+      "grad_norm": 2.254925489425659,
+      "learning_rate": 1.9216926233717085e-05,
+      "loss": 1.8379,
+      "step": 37
+    },
+    {
+      "epoch": 0.0035032727943210104,
+      "grad_norm": 2.3377599716186523,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 1.8644,
+      "step": 38
+    },
+    {
+      "epoch": 0.0035954641836452475,
+      "grad_norm": 2.5051825046539307,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 2.2087,
+      "step": 39
+    },
+    {
+      "epoch": 0.0036876555729694845,
+      "grad_norm": 2.2585108280181885,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 2.0316,
+      "step": 40
+    },
+    {
+      "epoch": 0.0037798469622937216,
+      "grad_norm": 2.4597954750061035,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 2.1561,
+      "step": 41
+    },
+    {
+      "epoch": 0.003872038351617959,
+      "grad_norm": 2.5078132152557373,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 2.0898,
+      "step": 42
+    },
+    {
+      "epoch": 0.003964229740942196,
+      "grad_norm": 2.5703673362731934,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 2.0668,
+      "step": 43
+    },
+    {
+      "epoch": 0.004056421130266433,
+      "grad_norm": 2.4447693824768066,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 1.77,
+      "step": 44
+    },
+    {
+      "epoch": 0.00414861251959067,
+      "grad_norm": 2.7371108531951904,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 2.4302,
+      "step": 45
+    },
+    {
+      "epoch": 0.004240803908914907,
+      "grad_norm": 2.6438939571380615,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 2.1652,
+      "step": 46
+    },
+    {
+      "epoch": 0.004332995298239144,
+      "grad_norm": 2.910571813583374,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 2.3887,
+      "step": 47
+    },
+    {
+      "epoch": 0.0044251866875633815,
+      "grad_norm": 3.2206871509552,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 2.2811,
+      "step": 48
+    },
+    {
+      "epoch": 0.0045173780768876185,
+      "grad_norm": 3.3698575496673584,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 2.4843,
+      "step": 49
+    },
+    {
+      "epoch": 0.004609569466211856,
+      "grad_norm": 4.109394073486328,
+      "learning_rate": 0.0,
+      "loss": 2.6098,
+      "step": 50
+    },
+    {
+      "epoch": 0.004609569466211856,
+      "eval_loss": 1.9887616634368896,
+      "eval_runtime": 700.7022,
+      "eval_samples_per_second": 26.072,
+      "eval_steps_per_second": 3.26,
+      "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": 1.904498393166643e+16,
+  "total_flos": 3.790140366598963e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null