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:c5fde3e096bfd321ca7ef43da544748c266972916b7d43c1f5a1f2d9cfeac9d5
+oid sha256:b78aec5a767c490307e0f52bc1f175926a533359c33aa29e38a5ada101f62439
 size 295488936

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3265631ef6098f69e503135cc74c10f43a6aff31c552d5c951a8a45f55af517b
+oid sha256:0e0c6a6705dda315d87e53dc4f45c49ef3eda7c10203368a0a410b6f70a8740c
 size 150486964

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:00232e97a2ee007008a7027c0bc814ccd78a98292311c559a14218c779acf1c8
+oid sha256:07dd1512a79888eacbcce2601f625cc6db154ee830f37557fc0d8f4ba3fb4525
 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": 0.6226545572280884,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.004349906477010744,
+  "best_metric": 0.600761353969574,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.008699812954021488,
   "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": 51.201,
       "eval_steps_per_second": 6.4,
       "step": 25
+    },
+    {
+      "epoch": 0.004523902736091174,
+      "grad_norm": 0.3160538673400879,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 0.6095,
+      "step": 26
+    },
+    {
+      "epoch": 0.004697898995171604,
+      "grad_norm": 0.3224450349807739,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 0.6285,
+      "step": 27
+    },
+    {
+      "epoch": 0.004871895254252034,
+      "grad_norm": 0.3256780505180359,
+      "learning_rate": 4.825502516487497e-05,
+      "loss": 0.594,
+      "step": 28
+    },
+    {
+      "epoch": 0.005045891513332464,
+      "grad_norm": 0.3396569788455963,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 0.5926,
+      "step": 29
+    },
+    {
+      "epoch": 0.0052198877724128935,
+      "grad_norm": 0.31964659690856934,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 0.6237,
+      "step": 30
+    },
+    {
+      "epoch": 0.0053938840314933225,
+      "grad_norm": 0.34242039918899536,
+      "learning_rate": 3.790390522001662e-05,
+      "loss": 0.6296,
+      "step": 31
+    },
+    {
+      "epoch": 0.0055678802905737524,
+      "grad_norm": 0.33837223052978516,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 0.6333,
+      "step": 32
+    },
+    {
+      "epoch": 0.005741876549654182,
+      "grad_norm": 0.3152254819869995,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 0.538,
+      "step": 33
+    },
+    {
+      "epoch": 0.005915872808734612,
+      "grad_norm": 0.35449615120887756,
+      "learning_rate": 2.8081442660546125e-05,
+      "loss": 0.6579,
+      "step": 34
+    },
+    {
+      "epoch": 0.006089869067815042,
+      "grad_norm": 0.36308395862579346,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.6059,
+      "step": 35
+    },
+    {
+      "epoch": 0.006263865326895472,
+      "grad_norm": 0.35584306716918945,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 0.6145,
+      "step": 36
+    },
+    {
+      "epoch": 0.006437861585975902,
+      "grad_norm": 0.4302743077278137,
+      "learning_rate": 1.9216926233717085e-05,
+      "loss": 0.7358,
+      "step": 37
+    },
+    {
+      "epoch": 0.006611857845056331,
+      "grad_norm": 0.39490967988967896,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 0.6569,
+      "step": 38
+    },
+    {
+      "epoch": 0.006785854104136761,
+      "grad_norm": 0.3838157057762146,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 0.571,
+      "step": 39
+    },
+    {
+      "epoch": 0.006959850363217191,
+      "grad_norm": 0.43212297558784485,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 0.6841,
+      "step": 40
+    },
+    {
+      "epoch": 0.007133846622297621,
+      "grad_norm": 0.4221954643726349,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.6014,
+      "step": 41
+    },
+    {
+      "epoch": 0.0073078428813780506,
+      "grad_norm": 0.460354745388031,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 0.6769,
+      "step": 42
+    },
+    {
+      "epoch": 0.0074818391404584805,
+      "grad_norm": 0.456825852394104,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 0.6126,
+      "step": 43
+    },
+    {
+      "epoch": 0.0076558353995389095,
+      "grad_norm": 0.49616795778274536,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 0.5843,
+      "step": 44
+    },
+    {
+      "epoch": 0.00782983165861934,
+      "grad_norm": 0.531218409538269,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 0.611,
+      "step": 45
+    },
+    {
+      "epoch": 0.00800382791769977,
+      "grad_norm": 0.5422489047050476,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 0.5836,
+      "step": 46
+    },
+    {
+      "epoch": 0.0081778241767802,
+      "grad_norm": 0.5895936489105225,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 0.6907,
+      "step": 47
+    },
+    {
+      "epoch": 0.008351820435860628,
+      "grad_norm": 0.6002499461174011,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 0.635,
+      "step": 48
+    },
+    {
+      "epoch": 0.008525816694941058,
+      "grad_norm": 0.6959513425827026,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 0.6863,
+      "step": 49
+    },
+    {
+      "epoch": 0.008699812954021488,
+      "grad_norm": 1.0589532852172852,
+      "learning_rate": 0.0,
+      "loss": 0.759,
+      "step": 50
+    },
+    {
+      "epoch": 0.008699812954021488,
+      "eval_loss": 0.600761353969574,
+      "eval_runtime": 188.8374,
+      "eval_samples_per_second": 51.261,
+      "eval_steps_per_second": 6.408,
+      "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": 5817093618401280.0,
+  "total_flos": 9218902751969280.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null