Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:24c807282e1be3d0d7d030f3190eb2c0e4f7996b17fd90c1d72c4a0a3bed77cb
+oid sha256:f403f7664a19ac81cfbd228a242f3468ef684d9d7350178abce73ad86fa8f2e3
 size 323014168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ad6a14682da037a17c16757c7583dc78294e0e6c368e109cb2fd9d64d44ce32
+oid sha256:139e1e33a750ae1ecb25dd349a9ce3e6901c20ded70cc019545f4ba191d0cbff
 size 646253418

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a0c8853472ebe275041d5955fa9c04870d0446b1d9c6fc165a169c3bcb9a5db0
+oid sha256:8631e2b4766031c702b83e8571b9beec164fdf46425b20539ad2bf36bfe5d32b
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dd362a498f8aa5d7c14d354e1202a39307367aaeda05211be916e0b9756d5c08
+oid sha256:4f7fafad7062f9bfe007bf24f64d8446742cf021f4ec8c740c4f0c06133c8e5f
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b07b54203cab453defb2d86bdbb4797132163855a6aa9c050258a2df0aaea4e
+oid sha256:84c7b5ac2227d7511c3d08db80ac12be0229115094b01df5485842f5d014a9a3
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ee901a5f8347c3d5a3a32a5745004823feb348d044d126a81bffa1a40ecf47c3
+oid sha256:fc5281431afef74f1271a9beaf14e2967a67917e88bceb417a6fe58ed6ad0871
 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": NaN,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.8676789587852495,
+  "epoch": 1.7527114967462039,
   "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": 15.376,
       "eval_steps_per_second": 3.998,
       "step": 25
+    },
+    {
+      "epoch": 0.9023861171366594,
+      "grad_norm": 1.270917534828186,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 4.3487,
+      "step": 26
+    },
+    {
+      "epoch": 0.9370932754880694,
+      "grad_norm": 1.400947093963623,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 4.1771,
+      "step": 27
+    },
+    {
+      "epoch": 0.9718004338394793,
+      "grad_norm": 1.8828790187835693,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 4.5593,
+      "step": 28
+    },
+    {
+      "epoch": 1.0238611713665944,
+      "grad_norm": 1.7455302476882935,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 7.0855,
+      "step": 29
+    },
+    {
+      "epoch": 1.0585683297180044,
+      "grad_norm": 1.0067161321640015,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 4.1927,
+      "step": 30
+    },
+    {
+      "epoch": 1.0932754880694142,
+      "grad_norm": 0.9785596132278442,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 3.8184,
+      "step": 31
+    },
+    {
+      "epoch": 1.1279826464208242,
+      "grad_norm": 1.14651358127594,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 4.2095,
+      "step": 32
+    },
+    {
+      "epoch": 1.1626898047722343,
+      "grad_norm": 1.0360416173934937,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 4.0984,
+      "step": 33
+    },
+    {
+      "epoch": 1.1973969631236443,
+      "grad_norm": 1.2359875440597534,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 4.1898,
+      "step": 34
+    },
+    {
+      "epoch": 1.2321041214750543,
+      "grad_norm": 1.3868677616119385,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 3.7502,
+      "step": 35
+    },
+    {
+      "epoch": 1.2668112798264641,
+      "grad_norm": 1.1134669780731201,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 3.8309,
+      "step": 36
+    },
+    {
+      "epoch": 1.3015184381778742,
+      "grad_norm": 0.9911520481109619,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 3.8265,
+      "step": 37
+    },
+    {
+      "epoch": 1.3362255965292842,
+      "grad_norm": 0.9708497524261475,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 3.5501,
+      "step": 38
+    },
+    {
+      "epoch": 1.3709327548806942,
+      "grad_norm": 1.183776617050171,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 4.2784,
+      "step": 39
+    },
+    {
+      "epoch": 1.405639913232104,
+      "grad_norm": 1.1506365537643433,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 3.6222,
+      "step": 40
+    },
+    {
+      "epoch": 1.440347071583514,
+      "grad_norm": 1.267316222190857,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 3.9714,
+      "step": 41
+    },
+    {
+      "epoch": 1.475054229934924,
+      "grad_norm": 1.6185253858566284,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 4.3338,
+      "step": 42
+    },
+    {
+      "epoch": 1.509761388286334,
+      "grad_norm": 1.0542787313461304,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 3.8664,
+      "step": 43
+    },
+    {
+      "epoch": 1.5444685466377441,
+      "grad_norm": 0.9902780055999756,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 3.4753,
+      "step": 44
+    },
+    {
+      "epoch": 1.579175704989154,
+      "grad_norm": 1.081815481185913,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 4.0674,
+      "step": 45
+    },
+    {
+      "epoch": 1.613882863340564,
+      "grad_norm": 1.1183944940567017,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 3.8616,
+      "step": 46
+    },
+    {
+      "epoch": 1.648590021691974,
+      "grad_norm": 1.1336209774017334,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 3.8991,
+      "step": 47
+    },
+    {
+      "epoch": 1.6832971800433838,
+      "grad_norm": 1.3395631313323975,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 4.0566,
+      "step": 48
+    },
+    {
+      "epoch": 1.718004338394794,
+      "grad_norm": 1.4792617559432983,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 3.8368,
+      "step": 49
+    },
+    {
+      "epoch": 1.7527114967462039,
+      "grad_norm": 1.0658278465270996,
+      "learning_rate": 1e-05,
+      "loss": 3.6137,
+      "step": 50
+    },
+    {
+      "epoch": 1.7527114967462039,
+      "eval_loss": NaN,
+      "eval_runtime": 3.2427,
+      "eval_samples_per_second": 15.419,
+      "eval_steps_per_second": 4.009,
+      "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": 2.812028905324544e+17,
+  "total_flos": 5.624057810649088e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null