Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a519973be0e4ef025ea6c74a00f4024cf27af3f03633463d32837c7941e76c3
+oid sha256:79c87e5f669f45cfffbdab0257b92e9818605958e193cc9fef6e363b04e41d0c
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:94158a65a02c1713501e897938b99324595a7d96e0814545512acb93f3376213
+oid sha256:d0c5b504fe25309820115a67269aae9133894d36acc498fb0af3e020f243a694
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b24be202e504f3f248309237bd16ea4c722802edc74c9bf06c03ad7d447a7a0
+oid sha256:bae2500b6e8661fe83dc9d9b64c10d5a60c6edf433542fc37b82a56ff5d88de6
 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": 1.3677418231964111,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.016761649346295676,
+  "best_metric": 1.3384933471679688,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.03352329869259135,
   "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": 1.429,
       "step": 25
+    },
+    {
+      "epoch": 0.017432115320147504,
+      "grad_norm": 1.7336963415145874,
+      "learning_rate": 0.0001,
+      "loss": 1.3554,
+      "step": 26
+    },
+    {
+      "epoch": 0.018102581293999328,
+      "grad_norm": 1.6814982891082764,
+      "learning_rate": 9.345968707698569e-05,
+      "loss": 1.2641,
+      "step": 27
+    },
+    {
+      "epoch": 0.018773047267851155,
+      "grad_norm": 1.820735216140747,
+      "learning_rate": 8.694738077799488e-05,
+      "loss": 1.3903,
+      "step": 28
+    },
+    {
+      "epoch": 0.019443513241702983,
+      "grad_norm": 1.9364521503448486,
+      "learning_rate": 8.049096779838719e-05,
+      "loss": 1.4451,
+      "step": 29
+    },
+    {
+      "epoch": 0.02011397921555481,
+      "grad_norm": 2.0241713523864746,
+      "learning_rate": 7.411809548974792e-05,
+      "loss": 1.3482,
+      "step": 30
+    },
+    {
+      "epoch": 0.02078444518940664,
+      "grad_norm": 1.512275218963623,
+      "learning_rate": 6.785605346968386e-05,
+      "loss": 1.2534,
+      "step": 31
+    },
+    {
+      "epoch": 0.021454911163258466,
+      "grad_norm": 1.9568251371383667,
+      "learning_rate": 6.173165676349103e-05,
+      "loss": 1.5905,
+      "step": 32
+    },
+    {
+      "epoch": 0.02212537713711029,
+      "grad_norm": 2.224773645401001,
+      "learning_rate": 5.577113097809989e-05,
+      "loss": 1.1378,
+      "step": 33
+    },
+    {
+      "epoch": 0.022795843110962118,
+      "grad_norm": 1.7800034284591675,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 1.0066,
+      "step": 34
+    },
+    {
+      "epoch": 0.023466309084813945,
+      "grad_norm": 2.645667314529419,
+      "learning_rate": 4.444297669803981e-05,
+      "loss": 0.9694,
+      "step": 35
+    },
+    {
+      "epoch": 0.024136775058665773,
+      "grad_norm": 2.402721405029297,
+      "learning_rate": 3.9123857099127936e-05,
+      "loss": 1.3358,
+      "step": 36
+    },
+    {
+      "epoch": 0.0248072410325176,
+      "grad_norm": 2.066645860671997,
+      "learning_rate": 3.406541848999312e-05,
+      "loss": 1.2806,
+      "step": 37
+    },
+    {
+      "epoch": 0.025477707006369428,
+      "grad_norm": 1.59635329246521,
+      "learning_rate": 2.9289321881345254e-05,
+      "loss": 0.834,
+      "step": 38
+    },
+    {
+      "epoch": 0.026148172980221252,
+      "grad_norm": 1.2451773881912231,
+      "learning_rate": 2.4816019252102273e-05,
+      "loss": 0.767,
+      "step": 39
+    },
+    {
+      "epoch": 0.02681863895407308,
+      "grad_norm": 2.293517589569092,
+      "learning_rate": 2.0664665970876496e-05,
+      "loss": 1.1113,
+      "step": 40
+    },
+    {
+      "epoch": 0.027489104927924907,
+      "grad_norm": 1.319640040397644,
+      "learning_rate": 1.6853038769745467e-05,
+      "loss": 0.6773,
+      "step": 41
+    },
+    {
+      "epoch": 0.028159570901776735,
+      "grad_norm": 1.7485390901565552,
+      "learning_rate": 1.339745962155613e-05,
+      "loss": 1.0643,
+      "step": 42
+    },
+    {
+      "epoch": 0.028830036875628563,
+      "grad_norm": 1.466673493385315,
+      "learning_rate": 1.0312725846731175e-05,
+      "loss": 0.7863,
+      "step": 43
+    },
+    {
+      "epoch": 0.02950050284948039,
+      "grad_norm": 1.6620216369628906,
+      "learning_rate": 7.612046748871327e-06,
+      "loss": 0.7743,
+      "step": 44
+    },
+    {
+      "epoch": 0.030170968823332214,
+      "grad_norm": 2.3844711780548096,
+      "learning_rate": 5.306987050489442e-06,
+      "loss": 0.5747,
+      "step": 45
+    },
+    {
+      "epoch": 0.030841434797184042,
+      "grad_norm": 1.4075263738632202,
+      "learning_rate": 3.40741737109318e-06,
+      "loss": 0.6564,
+      "step": 46
+    },
+    {
+      "epoch": 0.03151190077103587,
+      "grad_norm": 1.3964762687683105,
+      "learning_rate": 1.921471959676957e-06,
+      "loss": 0.6778,
+      "step": 47
+    },
+    {
+      "epoch": 0.0321823667448877,
+      "grad_norm": 1.50095796585083,
+      "learning_rate": 8.555138626189618e-07,
+      "loss": 0.6561,
+      "step": 48
+    },
+    {
+      "epoch": 0.032852832718739525,
+      "grad_norm": 1.9353364706039429,
+      "learning_rate": 2.141076761396521e-07,
+      "loss": 0.5138,
+      "step": 49
+    },
+    {
+      "epoch": 0.03352329869259135,
+      "grad_norm": 2.526801824569702,
+      "learning_rate": 0.0,
+      "loss": 0.5273,
+      "step": 50
+    },
+    {
+      "epoch": 0.03352329869259135,
+      "eval_loss": 1.3384933471679688,
+      "eval_runtime": 219.8146,
+      "eval_samples_per_second": 2.857,
+      "eval_steps_per_second": 1.428,
+      "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": 3.70943641780224e+16,
+  "total_flos": 7.41887283560448e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null