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:d18b568d0fd735c4464aeaab995a2c9e45072baa60040524a09bf08f8dabb1a7
+oid sha256:d44508ed5b40e328eb07c4e3a08dd1708959a4b0dae9b570f6c73bfdb30dffd2
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d99e2ac3620494d9c1635ec648bdd02aa7bdd7b461c9490d44e0455ad3a8da3
+oid sha256:0416e945be1acded9f273b96927a759a966a9fd9c98b098d53f9d0c591dbaa36
 size 320194002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc786613781c3c2fd9abc02a404d23790edaf66e4dc0e926170c7883fb3d2c0a
+oid sha256:c901e7aec9feb7fb3c537c4a436133209089c9e44693e395cb1f9fa08b81dbef
 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": 0.6165056824684143,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.02685284640171858,
+  "best_metric": 0.5707394480705261,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.05370569280343716,
   "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": 1.538,
       "eval_steps_per_second": 0.769,
       "step": 25
+    },
+    {
+      "epoch": 0.027926960257787327,
+      "grad_norm": 3.5959391593933105,
+      "learning_rate": 0.0001,
+      "loss": 2.7773,
+      "step": 26
+    },
+    {
+      "epoch": 0.02900107411385607,
+      "grad_norm": 3.213015079498291,
+      "learning_rate": 9.345968707698569e-05,
+      "loss": 2.4237,
+      "step": 27
+    },
+    {
+      "epoch": 0.03007518796992481,
+      "grad_norm": 3.6218926906585693,
+      "learning_rate": 8.694738077799488e-05,
+      "loss": 2.8496,
+      "step": 28
+    },
+    {
+      "epoch": 0.031149301825993556,
+      "grad_norm": 3.0756144523620605,
+      "learning_rate": 8.049096779838719e-05,
+      "loss": 1.9848,
+      "step": 29
+    },
+    {
+      "epoch": 0.0322234156820623,
+      "grad_norm": 3.864434003829956,
+      "learning_rate": 7.411809548974792e-05,
+      "loss": 3.1022,
+      "step": 30
+    },
+    {
+      "epoch": 0.03329752953813104,
+      "grad_norm": 3.296337842941284,
+      "learning_rate": 6.785605346968386e-05,
+      "loss": 2.2655,
+      "step": 31
+    },
+    {
+      "epoch": 0.034371643394199784,
+      "grad_norm": 3.269047498703003,
+      "learning_rate": 6.173165676349103e-05,
+      "loss": 2.284,
+      "step": 32
+    },
+    {
+      "epoch": 0.03544575725026853,
+      "grad_norm": 3.5344269275665283,
+      "learning_rate": 5.577113097809989e-05,
+      "loss": 1.8864,
+      "step": 33
+    },
+    {
+      "epoch": 0.036519871106337275,
+      "grad_norm": 4.668367385864258,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 2.3255,
+      "step": 34
+    },
+    {
+      "epoch": 0.03759398496240601,
+      "grad_norm": 4.970749855041504,
+      "learning_rate": 4.444297669803981e-05,
+      "loss": 2.8352,
+      "step": 35
+    },
+    {
+      "epoch": 0.03866809881847476,
+      "grad_norm": 3.3336353302001953,
+      "learning_rate": 3.9123857099127936e-05,
+      "loss": 2.0678,
+      "step": 36
+    },
+    {
+      "epoch": 0.0397422126745435,
+      "grad_norm": 3.146103620529175,
+      "learning_rate": 3.406541848999312e-05,
+      "loss": 1.6564,
+      "step": 37
+    },
+    {
+      "epoch": 0.04081632653061224,
+      "grad_norm": 4.855753421783447,
+      "learning_rate": 2.9289321881345254e-05,
+      "loss": 2.3859,
+      "step": 38
+    },
+    {
+      "epoch": 0.04189044038668099,
+      "grad_norm": 4.550353050231934,
+      "learning_rate": 2.4816019252102273e-05,
+      "loss": 2.1639,
+      "step": 39
+    },
+    {
+      "epoch": 0.04296455424274973,
+      "grad_norm": 7.876417636871338,
+      "learning_rate": 2.0664665970876496e-05,
+      "loss": 2.2466,
+      "step": 40
+    },
+    {
+      "epoch": 0.04403866809881848,
+      "grad_norm": 4.67519474029541,
+      "learning_rate": 1.6853038769745467e-05,
+      "loss": 1.9059,
+      "step": 41
+    },
+    {
+      "epoch": 0.045112781954887216,
+      "grad_norm": 5.316860675811768,
+      "learning_rate": 1.339745962155613e-05,
+      "loss": 2.3931,
+      "step": 42
+    },
+    {
+      "epoch": 0.04618689581095596,
+      "grad_norm": 4.196220874786377,
+      "learning_rate": 1.0312725846731175e-05,
+      "loss": 2.2159,
+      "step": 43
+    },
+    {
+      "epoch": 0.047261009667024706,
+      "grad_norm": 4.706377029418945,
+      "learning_rate": 7.612046748871327e-06,
+      "loss": 2.0003,
+      "step": 44
+    },
+    {
+      "epoch": 0.04833512352309345,
+      "grad_norm": 5.4141154289245605,
+      "learning_rate": 5.306987050489442e-06,
+      "loss": 2.9123,
+      "step": 45
+    },
+    {
+      "epoch": 0.04940923737916219,
+      "grad_norm": 6.08075475692749,
+      "learning_rate": 3.40741737109318e-06,
+      "loss": 2.6994,
+      "step": 46
+    },
+    {
+      "epoch": 0.050483351235230935,
+      "grad_norm": 4.99581241607666,
+      "learning_rate": 1.921471959676957e-06,
+      "loss": 3.621,
+      "step": 47
+    },
+    {
+      "epoch": 0.05155746509129968,
+      "grad_norm": 7.598954677581787,
+      "learning_rate": 8.555138626189618e-07,
+      "loss": 2.4808,
+      "step": 48
+    },
+    {
+      "epoch": 0.05263157894736842,
+      "grad_norm": 6.14135217666626,
+      "learning_rate": 2.141076761396521e-07,
+      "loss": 2.6089,
+      "step": 49
+    },
+    {
+      "epoch": 0.05370569280343716,
+      "grad_norm": 9.300232887268066,
+      "learning_rate": 0.0,
+      "loss": 1.8088,
+      "step": 50
+    },
+    {
+      "epoch": 0.05370569280343716,
+      "eval_loss": 0.5707394480705261,
+      "eval_runtime": 255.0357,
+      "eval_samples_per_second": 1.537,
+      "eval_steps_per_second": 0.769,
+      "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": 3.26732322177024e+16,
+  "total_flos": 6.53464644354048e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null