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:fa4d058faa469a127f10a3ce15d460d3be184f42cfd0313b4e932029249c2c9c
+oid sha256:74e9599ac9880d1971789b8f048142aec81cdf0d59aecbfdb9bb6a1dd7b6a42e
 size 432223744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c27419118fccbc8d65469219bd2146ce065fe0f3c76589d78fd079558356188
+oid sha256:3618980d6e3ca5bab7759877668f978438e30381152e7f8e7205cabee8e523de
 size 864785974

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c71fe8e67ae37ff864c0f1c02b12c384a3e5b21a9eeb843cbcefb5863ec29b4c
+oid sha256:28da33fdb203c18ae6c8e0d8fa42f5904e566f0537c8b6b3b3b62bd9a2192c67
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:59628f6648bc1484f9bf31df62847fc0b378295eac59c97ce5b89dfb485e2a66
+oid sha256:8315990ceadedccb27443134cb2aba19200077b6018555febd37ed4d94aad57f
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46c19a76a4db3c0f8651fbbac2d1619f4657db6e7246d6e54d2b858bb8f1098d
+oid sha256:a485b18184cb34f54cd064950a2140e0d791cb844a3191f8449df4ffb52a28e8
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd21a2a20c600dfb7a4d74c933768edc3fa4c44658c31842f6d766438374f343
+oid sha256:6aa6d01519334de4b9a8219b1319eb0ba019375cee7654b44a5f612164d4abfc
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f37b2aa490ccb1598b01e14cda36e9081f7ce646deab4d3c2d03de0d2169a755
+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": 0.30120481927710846,
+  "epoch": 0.6024096385542169,
   "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": 19.322,
       "eval_steps_per_second": 2.42,
       "step": 25
+    },
+    {
+      "epoch": 0.3132530120481928,
+      "grad_norm": 3.159722089767456,
+      "learning_rate": 5e-05,
+      "loss": 0.7818,
+      "step": 26
+    },
+    {
+      "epoch": 0.3253012048192771,
+      "grad_norm": 2.7830989360809326,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.7339,
+      "step": 27
+    },
+    {
+      "epoch": 0.3373493975903614,
+      "grad_norm": 2.162112236022949,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.6881,
+      "step": 28
+    },
+    {
+      "epoch": 0.3493975903614458,
+      "grad_norm": 1.7972179651260376,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.6253,
+      "step": 29
+    },
+    {
+      "epoch": 0.3614457831325301,
+      "grad_norm": 1.317353367805481,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.5675,
+      "step": 30
+    },
+    {
+      "epoch": 0.37349397590361444,
+      "grad_norm": 1.1669085025787354,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.5628,
+      "step": 31
+    },
+    {
+      "epoch": 0.3855421686746988,
+      "grad_norm": 1.1037367582321167,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.5072,
+      "step": 32
+    },
+    {
+      "epoch": 0.39759036144578314,
+      "grad_norm": 1.0369112491607666,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.5365,
+      "step": 33
+    },
+    {
+      "epoch": 0.40963855421686746,
+      "grad_norm": 1.1754462718963623,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.4381,
+      "step": 34
+    },
+    {
+      "epoch": 0.42168674698795183,
+      "grad_norm": 1.9122074842453003,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.6633,
+      "step": 35
+    },
+    {
+      "epoch": 0.43373493975903615,
+      "grad_norm": 4.505143165588379,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.9713,
+      "step": 36
+    },
+    {
+      "epoch": 0.4457831325301205,
+      "grad_norm": 6.352746486663818,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.9435,
+      "step": 37
+    },
+    {
+      "epoch": 0.4578313253012048,
+      "grad_norm": 1.7827593088150024,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.6166,
+      "step": 38
+    },
+    {
+      "epoch": 0.46987951807228917,
+      "grad_norm": 1.7395880222320557,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.6181,
+      "step": 39
+    },
+    {
+      "epoch": 0.4819277108433735,
+      "grad_norm": 1.064204216003418,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.5321,
+      "step": 40
+    },
+    {
+      "epoch": 0.4939759036144578,
+      "grad_norm": 0.9078404903411865,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.4611,
+      "step": 41
+    },
+    {
+      "epoch": 0.5060240963855421,
+      "grad_norm": 0.9963672757148743,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.5253,
+      "step": 42
+    },
+    {
+      "epoch": 0.5180722891566265,
+      "grad_norm": 0.907263994216919,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.4595,
+      "step": 43
+    },
+    {
+      "epoch": 0.5301204819277109,
+      "grad_norm": 0.938334584236145,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.5145,
+      "step": 44
+    },
+    {
+      "epoch": 0.5421686746987951,
+      "grad_norm": 0.8603211641311646,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.4521,
+      "step": 45
+    },
+    {
+      "epoch": 0.5542168674698795,
+      "grad_norm": 0.9404347538948059,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.4437,
+      "step": 46
+    },
+    {
+      "epoch": 0.5662650602409639,
+      "grad_norm": 1.001924753189087,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.447,
+      "step": 47
+    },
+    {
+      "epoch": 0.5783132530120482,
+      "grad_norm": 2.0918359756469727,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.7458,
+      "step": 48
+    },
+    {
+      "epoch": 0.5903614457831325,
+      "grad_norm": 3.8851842880249023,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.7572,
+      "step": 49
+    },
+    {
+      "epoch": 0.6024096385542169,
+      "grad_norm": 5.830325603485107,
+      "learning_rate": 0.0,
+      "loss": 0.7994,
+      "step": 50
+    },
+    {
+      "epoch": 0.6024096385542169,
+      "eval_loss": NaN,
+      "eval_runtime": 28.9215,
+      "eval_samples_per_second": 19.328,
+      "eval_steps_per_second": 2.42,
+      "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": 3.315690861756416e+17,
+  "total_flos": 6.631381723512832e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null