Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:448eb26c9e4ed101b18e5c86fed35ec190f8e69b1accae34ed4211d3f70808b9
+oid sha256:eaba62e4a3f9562e9c5fc99cd21e0f351e2c4cf3ca3b4e7207f1c5e20029274b
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:61280eac728a01c4505cb871e75be964f4582d3a0f9293db9ae72a6203d49e6e
+oid sha256:037f56eba9900ffc56db17cb27624bc25bf2267bdced350c90ebb6088c767409
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bedec9bcbcae3122894aa07b0859bdc87cc7dd02d8936c2c38526e849b378cd5
+oid sha256:0cbc783f8080853606206c65e1a840cc2d0612f002a4bd68757a3f9ab97e0bc3
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:51fbeffaca99f2560c943cb1caddf4d5941e63f2a5b49cfd36631d4820d71c34
+oid sha256:a814139de9fd5366195752301a4e0496355ddb223ad492421fa12acd0d75bb39
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:174dd8b9c6ddec05182c1eb5d0b2dfa8d805482b54c340da313efaf206c28792
+oid sha256:c3184f1d929e3ddf29eabe509db274df2c7cd02db1940b803edc742ee7a8aa67
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b7a21f3e9238bc262b286b36468a53225ec4af545e317363271b00601cc87a9
+oid sha256:99e57fb4f903d863c1020da13b91b19ea7ba5806908940a07f4f2d43113d4ed7
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d271cdb95f63cd655315f063ca2e25c78dc5ae4275523c5d4f80f367586b3351
+oid sha256:5607f6de446164d9d9adb8b91c44cec55b14aa391e24ba5637c08b834eedda2a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.22433076798915863,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.6589785831960461,
+  "best_metric": 0.06989976763725281,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 1.3410214168039538,
   "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": 24.444,
       "eval_steps_per_second": 6.355,
       "step": 25
+    },
+    {
+      "epoch": 0.685337726523888,
+      "grad_norm": 1.986502766609192,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.2799,
+      "step": 26
+    },
+    {
+      "epoch": 0.7116968698517299,
+      "grad_norm": 1.9361213445663452,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 0.3052,
+      "step": 27
+    },
+    {
+      "epoch": 0.7380560131795717,
+      "grad_norm": 3.370849370956421,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 0.4228,
+      "step": 28
+    },
+    {
+      "epoch": 0.7644151565074135,
+      "grad_norm": 3.750485420227051,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 0.2901,
+      "step": 29
+    },
+    {
+      "epoch": 0.7907742998352554,
+      "grad_norm": 2.9256770610809326,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 0.1042,
+      "step": 30
+    },
+    {
+      "epoch": 0.8171334431630972,
+      "grad_norm": 2.44817852973938,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 0.1124,
+      "step": 31
+    },
+    {
+      "epoch": 0.8434925864909391,
+      "grad_norm": 1.4348925352096558,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 0.1066,
+      "step": 32
+    },
+    {
+      "epoch": 0.8698517298187809,
+      "grad_norm": 1.0853517055511475,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 0.0853,
+      "step": 33
+    },
+    {
+      "epoch": 0.8962108731466227,
+      "grad_norm": 2.7698771953582764,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 0.127,
+      "step": 34
+    },
+    {
+      "epoch": 0.9225700164744646,
+      "grad_norm": 2.3615007400512695,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 0.2138,
+      "step": 35
+    },
+    {
+      "epoch": 0.9489291598023064,
+      "grad_norm": 2.252959966659546,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 0.2065,
+      "step": 36
+    },
+    {
+      "epoch": 0.9752883031301482,
+      "grad_norm": 4.12150239944458,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 0.2188,
+      "step": 37
+    },
+    {
+      "epoch": 1.0247116968698518,
+      "grad_norm": 5.144357681274414,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.3064,
+      "step": 38
+    },
+    {
+      "epoch": 1.0510708401976936,
+      "grad_norm": 0.48973578214645386,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 0.0159,
+      "step": 39
+    },
+    {
+      "epoch": 1.0774299835255354,
+      "grad_norm": 0.3477337658405304,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 0.0171,
+      "step": 40
+    },
+    {
+      "epoch": 1.1037891268533773,
+      "grad_norm": 0.7385883927345276,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 0.0308,
+      "step": 41
+    },
+    {
+      "epoch": 1.130148270181219,
+      "grad_norm": 0.7831564545631409,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 0.0379,
+      "step": 42
+    },
+    {
+      "epoch": 1.156507413509061,
+      "grad_norm": 0.731144368648529,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 0.0718,
+      "step": 43
+    },
+    {
+      "epoch": 1.1828665568369028,
+      "grad_norm": 1.3186781406402588,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 0.0928,
+      "step": 44
+    },
+    {
+      "epoch": 1.2092257001647446,
+      "grad_norm": 1.7480039596557617,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 0.1888,
+      "step": 45
+    },
+    {
+      "epoch": 1.2355848434925865,
+      "grad_norm": 1.843854546546936,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 0.1448,
+      "step": 46
+    },
+    {
+      "epoch": 1.2619439868204283,
+      "grad_norm": 0.9175070524215698,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 0.0842,
+      "step": 47
+    },
+    {
+      "epoch": 1.2883031301482701,
+      "grad_norm": 0.22026900947093964,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 0.0107,
+      "step": 48
+    },
+    {
+      "epoch": 1.314662273476112,
+      "grad_norm": 0.20567184686660767,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 0.0084,
+      "step": 49
+    },
+    {
+      "epoch": 1.3410214168039538,
+      "grad_norm": 0.2838402986526489,
+      "learning_rate": 1e-05,
+      "loss": 0.0205,
+      "step": 50
+    },
+    {
+      "epoch": 1.3410214168039538,
+      "eval_loss": 0.06989976763725281,
+      "eval_runtime": 2.0408,
+      "eval_samples_per_second": 24.501,
+      "eval_steps_per_second": 6.37,
+      "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": 2.984041808658432e+17,
+  "total_flos": 5.968083617316864e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null