Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:915ea4099387160f6f5eae7abdeae2de6c69835fb4c8d762d3402a291d541f54
+oid sha256:6a51181047fd76cbf0f51d4400e88e594f9c9cd64012ac84deafa750d35ac389
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c583c6cb9c3000bd163c4ca8a208fb3031c69461a18797c9767a1e480ea36e5b
+oid sha256:75d5f26fdb3be09c99cf852f14965efcadc498ae20718de26123d3bbf32234f0
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e66f97d325f9b549c16ae26a357ab8843d29a1e87d7878348c297e763833855b
+oid sha256:4d720c6e1f219b2c53b5c9e1942d9915e419957ee6cadf32f076d697c3531c27
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ea7ff16b0c30a914eb0d145e3fb06ff9027c6cd2408e766ce8a09accab89a4d
+oid sha256:e69e2b49ea642509f0c688c16fb190b7cf27dac0a18903a5e2d1467d0343d8b8
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.16282150149345398,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.01855976243504083,
+  "epoch": 0.03711952487008166,
   "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": 2.857,
       "eval_steps_per_second": 1.428,
       "step": 25
+    },
+    {
+      "epoch": 0.019302152932442463,
+      "grad_norm": 0.3026466369628906,
+      "learning_rate": 0.0001,
+      "loss": 0.007,
+      "step": 26
+    },
+    {
+      "epoch": 0.0200445434298441,
+      "grad_norm": 0.882306694984436,
+      "learning_rate": 9.345968707698569e-05,
+      "loss": 0.136,
+      "step": 27
+    },
+    {
+      "epoch": 0.020786933927245732,
+      "grad_norm": 0.8444817066192627,
+      "learning_rate": 8.694738077799488e-05,
+      "loss": 0.0609,
+      "step": 28
+    },
+    {
+      "epoch": 0.021529324424647365,
+      "grad_norm": 1.1410984992980957,
+      "learning_rate": 8.049096779838719e-05,
+      "loss": 0.0993,
+      "step": 29
+    },
+    {
+      "epoch": 0.022271714922048998,
+      "grad_norm": 0.5272141098976135,
+      "learning_rate": 7.411809548974792e-05,
+      "loss": 0.0364,
+      "step": 30
+    },
+    {
+      "epoch": 0.02301410541945063,
+      "grad_norm": 0.3858809769153595,
+      "learning_rate": 6.785605346968386e-05,
+      "loss": 0.0412,
+      "step": 31
+    },
+    {
+      "epoch": 0.023756495916852263,
+      "grad_norm": 0.44752252101898193,
+      "learning_rate": 6.173165676349103e-05,
+      "loss": 0.0214,
+      "step": 32
+    },
+    {
+      "epoch": 0.024498886414253896,
+      "grad_norm": 0.5306777954101562,
+      "learning_rate": 5.577113097809989e-05,
+      "loss": 0.011,
+      "step": 33
+    },
+    {
+      "epoch": 0.025241276911655532,
+      "grad_norm": 0.9459553360939026,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 0.0844,
+      "step": 34
+    },
+    {
+      "epoch": 0.025983667409057165,
+      "grad_norm": 0.47654223442077637,
+      "learning_rate": 4.444297669803981e-05,
+      "loss": 0.0523,
+      "step": 35
+    },
+    {
+      "epoch": 0.026726057906458798,
+      "grad_norm": 0.9003578424453735,
+      "learning_rate": 3.9123857099127936e-05,
+      "loss": 0.0696,
+      "step": 36
+    },
+    {
+      "epoch": 0.02746844840386043,
+      "grad_norm": 2.070967674255371,
+      "learning_rate": 3.406541848999312e-05,
+      "loss": 0.1786,
+      "step": 37
+    },
+    {
+      "epoch": 0.028210838901262063,
+      "grad_norm": 0.4337747097015381,
+      "learning_rate": 2.9289321881345254e-05,
+      "loss": 0.0155,
+      "step": 38
+    },
+    {
+      "epoch": 0.028953229398663696,
+      "grad_norm": 0.3766095042228699,
+      "learning_rate": 2.4816019252102273e-05,
+      "loss": 0.0135,
+      "step": 39
+    },
+    {
+      "epoch": 0.02969561989606533,
+      "grad_norm": 1.6106809377670288,
+      "learning_rate": 2.0664665970876496e-05,
+      "loss": 0.0379,
+      "step": 40
+    },
+    {
+      "epoch": 0.030438010393466965,
+      "grad_norm": 2.527824878692627,
+      "learning_rate": 1.6853038769745467e-05,
+      "loss": 0.042,
+      "step": 41
+    },
+    {
+      "epoch": 0.031180400890868598,
+      "grad_norm": 2.065561056137085,
+      "learning_rate": 1.339745962155613e-05,
+      "loss": 0.0284,
+      "step": 42
+    },
+    {
+      "epoch": 0.03192279138827023,
+      "grad_norm": 0.4519674777984619,
+      "learning_rate": 1.0312725846731175e-05,
+      "loss": 0.0148,
+      "step": 43
+    },
+    {
+      "epoch": 0.032665181885671864,
+      "grad_norm": 0.6088566184043884,
+      "learning_rate": 7.612046748871327e-06,
+      "loss": 0.0132,
+      "step": 44
+    },
+    {
+      "epoch": 0.0334075723830735,
+      "grad_norm": 0.1786351203918457,
+      "learning_rate": 5.306987050489442e-06,
+      "loss": 0.0076,
+      "step": 45
+    },
+    {
+      "epoch": 0.03414996288047513,
+      "grad_norm": 0.5400381684303284,
+      "learning_rate": 3.40741737109318e-06,
+      "loss": 0.0073,
+      "step": 46
+    },
+    {
+      "epoch": 0.034892353377876766,
+      "grad_norm": 62.15085983276367,
+      "learning_rate": 1.921471959676957e-06,
+      "loss": 1.0234,
+      "step": 47
+    },
+    {
+      "epoch": 0.035634743875278395,
+      "grad_norm": 23.811513900756836,
+      "learning_rate": 8.555138626189618e-07,
+      "loss": 0.7888,
+      "step": 48
+    },
+    {
+      "epoch": 0.03637713437268003,
+      "grad_norm": 27.518611907958984,
+      "learning_rate": 2.141076761396521e-07,
+      "loss": 0.8569,
+      "step": 49
+    },
+    {
+      "epoch": 0.03711952487008166,
+      "grad_norm": 50.407073974609375,
+      "learning_rate": 0.0,
+      "loss": 1.3908,
+      "step": 50
+    },
+    {
+      "epoch": 0.03711952487008166,
+      "eval_loss": 0.1675003468990326,
+      "eval_runtime": 198.8265,
+      "eval_samples_per_second": 2.857,
+      "eval_steps_per_second": 1.428,
+      "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": 3.746530781980262e+16,
+  "total_flos": 7.455967199782502e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null