Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:06993c290d732445090ed939b0db373cf6b003e0ca4c346e17e9d6c9e3de72e7
+oid sha256:e299759c52821b41d42b61d5b8f556cc3371b5eaf4c5def42e1e3ba6da1bedc0
 size 134235712

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a6459b0e2fe829dfe2d3e1655e1e93d3d9370a5a0f61658bc1bdc1f0747ef559
+oid sha256:6a12dbc67d235443d019c899aa639d7308e0f4a3eed8939c67981e267ef789f5
 size 68309690

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f75ae57b1328d1177a6e69e82cc9d700759ed59eb9502bf3f468ece6e8121ec
+oid sha256:32f583723654dbc46df018f367ee946fb8622d6e66539d5bacf8311cddbe3a3a
 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": 1.1216108798980713,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.0021329693065716784,
+  "best_metric": 1.0769927501678467,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.004265938613143357,
   "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": 83.311,
       "eval_steps_per_second": 10.416,
       "step": 25
+    },
+    {
+      "epoch": 0.0022182880788345458,
+      "grad_norm": 2.925053834915161,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 5.5309,
+      "step": 26
+    },
+    {
+      "epoch": 0.0023036068510974127,
+      "grad_norm": 3.0282070636749268,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 6.1285,
+      "step": 27
+    },
+    {
+      "epoch": 0.0023889256233602797,
+      "grad_norm": 2.7216405868530273,
+      "learning_rate": 4.825502516487497e-05,
+      "loss": 5.2937,
+      "step": 28
+    },
+    {
+      "epoch": 0.002474244395623147,
+      "grad_norm": 2.9761924743652344,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 5.4515,
+      "step": 29
+    },
+    {
+      "epoch": 0.002559563167886014,
+      "grad_norm": 3.0058114528656006,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 5.3687,
+      "step": 30
+    },
+    {
+      "epoch": 0.0026448819401488815,
+      "grad_norm": 2.876269817352295,
+      "learning_rate": 3.790390522001662e-05,
+      "loss": 4.9538,
+      "step": 31
+    },
+    {
+      "epoch": 0.0027302007124117484,
+      "grad_norm": 2.80983304977417,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 4.7287,
+      "step": 32
+    },
+    {
+      "epoch": 0.0028155194846746154,
+      "grad_norm": 3.582716703414917,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 5.5357,
+      "step": 33
+    },
+    {
+      "epoch": 0.0029008382569374828,
+      "grad_norm": 3.126375675201416,
+      "learning_rate": 2.8081442660546125e-05,
+      "loss": 5.0843,
+      "step": 34
+    },
+    {
+      "epoch": 0.0029861570292003497,
+      "grad_norm": 2.9568567276000977,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 4.7067,
+      "step": 35
+    },
+    {
+      "epoch": 0.003071475801463217,
+      "grad_norm": 2.714190721511841,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 3.7083,
+      "step": 36
+    },
+    {
+      "epoch": 0.003156794573726084,
+      "grad_norm": 3.0618250370025635,
+      "learning_rate": 1.9216926233717085e-05,
+      "loss": 3.3322,
+      "step": 37
+    },
+    {
+      "epoch": 0.003242113345988951,
+      "grad_norm": 2.9036190509796143,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 3.4382,
+      "step": 38
+    },
+    {
+      "epoch": 0.0033274321182518185,
+      "grad_norm": 2.511988401412964,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 3.1006,
+      "step": 39
+    },
+    {
+      "epoch": 0.0034127508905146854,
+      "grad_norm": 2.61822772026062,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 2.9746,
+      "step": 40
+    },
+    {
+      "epoch": 0.003498069662777553,
+      "grad_norm": 2.7285141944885254,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 3.3553,
+      "step": 41
+    },
+    {
+      "epoch": 0.0035833884350404198,
+      "grad_norm": 2.4301650524139404,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 3.1297,
+      "step": 42
+    },
+    {
+      "epoch": 0.0036687072073032867,
+      "grad_norm": 2.53094220161438,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 3.2159,
+      "step": 43
+    },
+    {
+      "epoch": 0.003754025979566154,
+      "grad_norm": 2.4559786319732666,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 2.9607,
+      "step": 44
+    },
+    {
+      "epoch": 0.003839344751829021,
+      "grad_norm": 2.5060479640960693,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 3.117,
+      "step": 45
+    },
+    {
+      "epoch": 0.003924663524091888,
+      "grad_norm": 2.513113260269165,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 3.2779,
+      "step": 46
+    },
+    {
+      "epoch": 0.0040099822963547554,
+      "grad_norm": 2.574754476547241,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 3.263,
+      "step": 47
+    },
+    {
+      "epoch": 0.004095301068617623,
+      "grad_norm": 2.6792495250701904,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 3.1335,
+      "step": 48
+    },
+    {
+      "epoch": 0.004180619840880489,
+      "grad_norm": 2.810391902923584,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 3.3076,
+      "step": 49
+    },
+    {
+      "epoch": 0.004265938613143357,
+      "grad_norm": 3.56740403175354,
+      "learning_rate": 0.0,
+      "loss": 3.6467,
+      "step": 50
+    },
+    {
+      "epoch": 0.004265938613143357,
+      "eval_loss": 1.0769927501678467,
+      "eval_runtime": 237.1606,
+      "eval_samples_per_second": 83.235,
+      "eval_steps_per_second": 10.406,
+      "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": 4631659177574400.0,
+  "total_flos": 8128561856643072.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null