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:ded9a2f83d8fc977a3743ecf1c97335e2bfbd849b963e7e9213e5229fa675185
+oid sha256:056ccaf4dc47fb56e6e598281c446d848e0792c2d888fe2e44c45618a384a3ab
 size 2772512088

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:185f9489ab3180f458667bce833bf00132aae15e0709f701e5815d796028aab1
+oid sha256:b73234246750646c7fafd6e063c9705d9f66ab122d7c4d7eac76887a33cedb0d
 size 341314196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f4f7b15790355217dfef1ad19b922cc7f620a24d713e97dc901c54f88bfbf556
+oid sha256:51409030a1d78bd7327d7bc96720da5b15dd925a23090b38b9a3026111b65e1a
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c931ece4da598a541d357f6c98f67481603252e193960022d37ddd49c584b1f
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.5085862278938293,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.008450942280064227,
+  "best_metric": 0.3495233654975891,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.016901884560128453,
   "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": 10.875,
       "eval_steps_per_second": 1.36,
       "step": 25
+    },
+    {
+      "epoch": 0.008788979971266797,
+      "grad_norm": 3.4989237785339355,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 0.3807,
+      "step": 26
+    },
+    {
+      "epoch": 0.009127017662469365,
+      "grad_norm": 6.824868679046631,
+      "learning_rate": 8.715724127386972e-05,
+      "loss": 0.5406,
+      "step": 27
+    },
+    {
+      "epoch": 0.009465055353671934,
+      "grad_norm": 5.974666118621826,
+      "learning_rate": 8.345653031794292e-05,
+      "loss": 0.5547,
+      "step": 28
+    },
+    {
+      "epoch": 0.009803093044874504,
+      "grad_norm": 3.5786073207855225,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 0.5986,
+      "step": 29
+    },
+    {
+      "epoch": 0.010141130736077072,
+      "grad_norm": 3.5324819087982178,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 0.4509,
+      "step": 30
+    },
+    {
+      "epoch": 0.010479168427279641,
+      "grad_norm": 4.868967533111572,
+      "learning_rate": 7.033683215379002e-05,
+      "loss": 0.5524,
+      "step": 31
+    },
+    {
+      "epoch": 0.010817206118482211,
+      "grad_norm": 4.9027838706970215,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 0.555,
+      "step": 32
+    },
+    {
+      "epoch": 0.01115524380968478,
+      "grad_norm": 3.5219500064849854,
+      "learning_rate": 6.0395584540887963e-05,
+      "loss": 0.5586,
+      "step": 33
+    },
+    {
+      "epoch": 0.011493281500887348,
+      "grad_norm": 2.3164947032928467,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 0.3178,
+      "step": 34
+    },
+    {
+      "epoch": 0.011831319192089918,
+      "grad_norm": 3.6856961250305176,
+      "learning_rate": 5e-05,
+      "loss": 0.6171,
+      "step": 35
+    },
+    {
+      "epoch": 0.012169356883292487,
+      "grad_norm": 4.217321395874023,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 0.5073,
+      "step": 36
+    },
+    {
+      "epoch": 0.012507394574495055,
+      "grad_norm": 3.870985269546509,
+      "learning_rate": 3.960441545911204e-05,
+      "loss": 0.3877,
+      "step": 37
+    },
+    {
+      "epoch": 0.012845432265697626,
+      "grad_norm": 3.3955981731414795,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 0.4761,
+      "step": 38
+    },
+    {
+      "epoch": 0.013183469956900194,
+      "grad_norm": 2.7234582901000977,
+      "learning_rate": 2.9663167846209998e-05,
+      "loss": 0.2456,
+      "step": 39
+    },
+    {
+      "epoch": 0.013521507648102763,
+      "grad_norm": 2.449373483657837,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.3517,
+      "step": 40
+    },
+    {
+      "epoch": 0.013859545339305333,
+      "grad_norm": 3.2577102184295654,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 0.5938,
+      "step": 41
+    },
+    {
+      "epoch": 0.014197583030507901,
+      "grad_norm": 4.181509494781494,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 0.3242,
+      "step": 42
+    },
+    {
+      "epoch": 0.01453562072171047,
+      "grad_norm": 2.031233549118042,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 0.4193,
+      "step": 43
+    },
+    {
+      "epoch": 0.01487365841291304,
+      "grad_norm": 2.2585036754608154,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.3848,
+      "step": 44
+    },
+    {
+      "epoch": 0.015211696104115609,
+      "grad_norm": 2.401160955429077,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.2766,
+      "step": 45
+    },
+    {
+      "epoch": 0.015549733795318177,
+      "grad_norm": 2.7615787982940674,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 0.4673,
+      "step": 46
+    },
+    {
+      "epoch": 0.015887771486520746,
+      "grad_norm": 2.5677614212036133,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 0.3196,
+      "step": 47
+    },
+    {
+      "epoch": 0.016225809177723316,
+      "grad_norm": 3.2868287563323975,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 0.3484,
+      "step": 48
+    },
+    {
+      "epoch": 0.016563846868925886,
+      "grad_norm": 2.633810043334961,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 0.3876,
+      "step": 49
+    },
+    {
+      "epoch": 0.016901884560128453,
+      "grad_norm": 2.183506727218628,
+      "learning_rate": 0.0,
+      "loss": 0.3819,
+      "step": 50
+    },
+    {
+      "epoch": 0.016901884560128453,
+      "eval_loss": 0.3495233654975891,
+      "eval_runtime": 458.0308,
+      "eval_samples_per_second": 10.879,
+      "eval_steps_per_second": 1.36,
+      "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": 3.77128596013056e+16,
+  "total_flos": 7.580284779862426e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null