Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:58c44bdbaa8e89e7e69b058511ebd1caad969ca9b2ce95ded5c5721618ecd0b1
+oid sha256:7b473d65afae556b9bc1aa105b7daa3c845d8d2d466c4837cbfd31e1526e4021
 size 275341720

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a33553b8c71cfead5fd00b54f6303cf305a33747df73f4db7b00d831e70dfa58
+oid sha256:b8dc7c1887295e2718cfd82e73bb0c342e8cce362272846792635884970db20f
 size 551070514

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9abdacfb17a22e16561c83aca0316ad32805895926bffe171dd835ebebbae885
+oid sha256:14570c7e6717a0a8eba1e8dcbd4c5c73634bfcea555d3e3c613d12095cd094d5
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d4ae3842d5f151f968dca77e1398d806e7ccbbb71022d80233230f6c7d83bcb
+oid sha256:9567f2f3182e832808fd621212e0dd5e8f1a88bd24ddda3ea0d289496073738c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.20686934888362885,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.013448090371167294,
+  "epoch": 0.02689618074233459,
   "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": 1.623,
       "eval_steps_per_second": 0.813,
       "step": 25
+    },
+    {
+      "epoch": 0.013986013986013986,
+      "grad_norm": 1.5185937881469727,
+      "learning_rate": 0.00017684011108568592,
+      "loss": 0.2361,
+      "step": 26
+    },
+    {
+      "epoch": 0.014523937600860678,
+      "grad_norm": 0.9820839762687683,
+      "learning_rate": 0.0001746821476984154,
+      "loss": 0.1982,
+      "step": 27
+    },
+    {
+      "epoch": 0.01506186121570737,
+      "grad_norm": 5.153009414672852,
+      "learning_rate": 0.00017244252047910892,
+      "loss": 0.2591,
+      "step": 28
+    },
+    {
+      "epoch": 0.015599784830554062,
+      "grad_norm": 1.0352336168289185,
+      "learning_rate": 0.00017012367842724887,
+      "loss": 0.14,
+      "step": 29
+    },
+    {
+      "epoch": 0.01613770844540075,
+      "grad_norm": 2.7931392192840576,
+      "learning_rate": 0.00016772815716257412,
+      "loss": 0.3103,
+      "step": 30
+    },
+    {
+      "epoch": 0.016675632060247445,
+      "grad_norm": 3.7326819896698,
+      "learning_rate": 0.00016525857615241687,
+      "loss": 0.2908,
+      "step": 31
+    },
+    {
+      "epoch": 0.017213555675094135,
+      "grad_norm": 1.1818197965621948,
+      "learning_rate": 0.0001627176358473537,
+      "loss": 0.1197,
+      "step": 32
+    },
+    {
+      "epoch": 0.01775147928994083,
+      "grad_norm": 3.522305727005005,
+      "learning_rate": 0.00016010811472830252,
+      "loss": 0.2051,
+      "step": 33
+    },
+    {
+      "epoch": 0.01828940290478752,
+      "grad_norm": 1.0128105878829956,
+      "learning_rate": 0.00015743286626829437,
+      "loss": 0.1311,
+      "step": 34
+    },
+    {
+      "epoch": 0.018827326519634213,
+      "grad_norm": 4.8102593421936035,
+      "learning_rate": 0.00015469481581224272,
+      "loss": 0.3403,
+      "step": 35
+    },
+    {
+      "epoch": 0.019365250134480903,
+      "grad_norm": 13.774560928344727,
+      "learning_rate": 0.00015189695737812152,
+      "loss": 0.9765,
+      "step": 36
+    },
+    {
+      "epoch": 0.019903173749327596,
+      "grad_norm": 5.964848518371582,
+      "learning_rate": 0.00014904235038305083,
+      "loss": 0.4839,
+      "step": 37
+    },
+    {
+      "epoch": 0.020441097364174286,
+      "grad_norm": 10.879966735839844,
+      "learning_rate": 0.0001461341162978688,
+      "loss": 0.685,
+      "step": 38
+    },
+    {
+      "epoch": 0.02097902097902098,
+      "grad_norm": 6.293717384338379,
+      "learning_rate": 0.00014317543523384928,
+      "loss": 0.3725,
+      "step": 39
+    },
+    {
+      "epoch": 0.02151694459386767,
+      "grad_norm": 0.753055214881897,
+      "learning_rate": 0.00014016954246529696,
+      "loss": 0.1652,
+      "step": 40
+    },
+    {
+      "epoch": 0.022054868208714364,
+      "grad_norm": 1.0214154720306396,
+      "learning_rate": 0.00013711972489182208,
+      "loss": 0.1115,
+      "step": 41
+    },
+    {
+      "epoch": 0.022592791823561054,
+      "grad_norm": 3.1957497596740723,
+      "learning_rate": 0.00013402931744416433,
+      "loss": 0.173,
+      "step": 42
+    },
+    {
+      "epoch": 0.023130715438407747,
+      "grad_norm": 0.9727430939674377,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 0.211,
+      "step": 43
+    },
+    {
+      "epoch": 0.023668639053254437,
+      "grad_norm": 4.678534030914307,
+      "learning_rate": 0.00012774029087618446,
+      "loss": 0.3037,
+      "step": 44
+    },
+    {
+      "epoch": 0.02420656266810113,
+      "grad_norm": 3.1848816871643066,
+      "learning_rate": 0.00012454854871407994,
+      "loss": 0.2527,
+      "step": 45
+    },
+    {
+      "epoch": 0.02474448628294782,
+      "grad_norm": 2.432804584503174,
+      "learning_rate": 0.0001213299630743747,
+      "loss": 0.1629,
+      "step": 46
+    },
+    {
+      "epoch": 0.025282409897794515,
+      "grad_norm": 1.7503596544265747,
+      "learning_rate": 0.000118088053433211,
+      "loss": 0.1667,
+      "step": 47
+    },
+    {
+      "epoch": 0.025820333512641205,
+      "grad_norm": 3.7610039710998535,
+      "learning_rate": 0.0001148263647711842,
+      "loss": 0.2712,
+      "step": 48
+    },
+    {
+      "epoch": 0.026358257127487898,
+      "grad_norm": 1.4483740329742432,
+      "learning_rate": 0.00011154846369695863,
+      "loss": 0.1399,
+      "step": 49
+    },
+    {
+      "epoch": 0.02689618074233459,
+      "grad_norm": 2.2921817302703857,
+      "learning_rate": 0.00010825793454723325,
+      "loss": 0.091,
+      "step": 50
+    },
+    {
+      "epoch": 0.02689618074233459,
+      "eval_loss": 0.21423955261707306,
+      "eval_runtime": 482.3607,
+      "eval_samples_per_second": 1.623,
+      "eval_steps_per_second": 0.813,
+      "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": 6.91090822791168e+16,
+  "total_flos": 1.382181645582336e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null