Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:006334d3c92d37c629677a8da64cd8e4d9d1d2c92277ee8846073e69172ff7cc
+oid sha256:f6237a275d04b15a7414d47bc9da47ed92982db62dd7146bc564ce0261beddb6
 size 838906392

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a0f4722f02464ec605fbb1f44f0614bf9f1d009301e25e392953d97427b81a2
+oid sha256:267da94718242b8962b4ecd083425fd7eda1dbef0e22de50f4ea3ce5b730485a
 size 426360596

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea836466501fe2d2b2db8be640386133d29e395c2a25463a2dd0896ddb2ee455
+oid sha256:06ea856b7201a395513949c3227a4161bebd3a2aa55c5376c9e3c16853f910ae
 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": NaN,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.005195344970906068,
+  "epoch": 0.010390689941812137,
   "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": 12.844,
       "eval_steps_per_second": 1.607,
       "step": 25
+    },
+    {
+      "epoch": 0.005403158769742311,
+      "grad_norm": 1.3431106805801392,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 6.5966,
+      "step": 26
+    },
+    {
+      "epoch": 0.005610972568578554,
+      "grad_norm": 0.0,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 0.005818786367414797,
+      "grad_norm": 0.0,
+      "learning_rate": 4.825502516487497e-05,
+      "loss": 0.0,
+      "step": 28
+    },
+    {
+      "epoch": 0.006026600166251039,
+      "grad_norm": 0.0,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 0.0,
+      "step": 29
+    },
+    {
+      "epoch": 0.006234413965087282,
+      "grad_norm": 0.0,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.006442227763923524,
+      "grad_norm": 0.0,
+      "learning_rate": 3.790390522001662e-05,
+      "loss": 0.0,
+      "step": 31
+    },
+    {
+      "epoch": 0.006650041562759767,
+      "grad_norm": 0.0,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 0.0,
+      "step": 32
+    },
+    {
+      "epoch": 0.00685785536159601,
+      "grad_norm": 0.0,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 0.0,
+      "step": 33
+    },
+    {
+      "epoch": 0.007065669160432253,
+      "grad_norm": 0.0,
+      "learning_rate": 2.8081442660546125e-05,
+      "loss": 0.0,
+      "step": 34
+    },
+    {
+      "epoch": 0.007273482959268496,
+      "grad_norm": 0.0,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.0,
+      "step": 35
+    },
+    {
+      "epoch": 0.007481296758104738,
+      "grad_norm": 0.0,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 0.0,
+      "step": 36
+    },
+    {
+      "epoch": 0.007689110556940981,
+      "grad_norm": 0.0,
+      "learning_rate": 1.9216926233717085e-05,
+      "loss": 0.0,
+      "step": 37
+    },
+    {
+      "epoch": 0.007896924355777223,
+      "grad_norm": 0.0,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 0.0,
+      "step": 38
+    },
+    {
+      "epoch": 0.008104738154613466,
+      "grad_norm": 0.0,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 0.0,
+      "step": 39
+    },
+    {
+      "epoch": 0.00831255195344971,
+      "grad_norm": 0.0,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 0.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.008520365752285953,
+      "grad_norm": 0.0,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.0,
+      "step": 41
+    },
+    {
+      "epoch": 0.008728179551122194,
+      "grad_norm": 0.0,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 0.0,
+      "step": 42
+    },
+    {
+      "epoch": 0.008935993349958437,
+      "grad_norm": 0.0,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 0.0,
+      "step": 43
+    },
+    {
+      "epoch": 0.00914380714879468,
+      "grad_norm": 0.0,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 0.0,
+      "step": 44
+    },
+    {
+      "epoch": 0.009351620947630923,
+      "grad_norm": 0.0,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 0.0,
+      "step": 45
+    },
+    {
+      "epoch": 0.009559434746467166,
+      "grad_norm": 0.0,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 0.0,
+      "step": 46
+    },
+    {
+      "epoch": 0.009767248545303408,
+      "grad_norm": 0.0,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 0.0,
+      "step": 47
+    },
+    {
+      "epoch": 0.00997506234413965,
+      "grad_norm": 0.0,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 0.0,
+      "step": 48
+    },
+    {
+      "epoch": 0.010182876142975894,
+      "grad_norm": 0.0,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 0.0,
+      "step": 49
+    },
+    {
+      "epoch": 0.010390689941812137,
+      "grad_norm": 0.0,
+      "learning_rate": 0.0,
+      "loss": 0.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.010390689941812137,
+      "eval_loss": NaN,
+      "eval_runtime": 632.0878,
+      "eval_samples_per_second": 12.823,
+      "eval_steps_per_second": 1.604,
+      "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": 6.3648445759488e+16,
+  "total_flos": 9.642739532562432e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null