Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:71dfa7ebede8b2ec604aec3944b32417e052cf69880fd2fd6fce943672c3e772
+oid sha256:b83ca0ab5681fc17c74f783eb6347a9fe1247abc014d1b5b0ee68b2d4136db73
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0bf5093e4c3b58df31690561aa50ca19f1af3dd6e95f205d38cc1e11f83ac92b
+oid sha256:573001383ff9e8d9439e8b53ae625010a7ea2a0a9967b4763b7712d825cbee8c
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:84aba502cc412e757660390722fa607499392cce6ed13514f4bfec61647e859d
+oid sha256:128475de4c8a561f44fb7b2af72e0538448437d4e6c8e4218308cbdfdbd9c969
 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": 0.49429598450660706,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.013220518244315178,
+  "best_metric": 0.44097796082496643,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.026441036488630356,
   "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": 2.844,
       "eval_steps_per_second": 1.424,
       "step": 25
+    },
+    {
+      "epoch": 0.013749338974087784,
+      "grad_norm": 2.0070135593414307,
+      "learning_rate": 0.0001,
+      "loss": 0.3063,
+      "step": 26
+    },
+    {
+      "epoch": 0.014278159703860392,
+      "grad_norm": 2.7425220012664795,
+      "learning_rate": 9.345968707698569e-05,
+      "loss": 0.5191,
+      "step": 27
+    },
+    {
+      "epoch": 0.014806980433632998,
+      "grad_norm": 1.8991012573242188,
+      "learning_rate": 8.694738077799488e-05,
+      "loss": 0.4107,
+      "step": 28
+    },
+    {
+      "epoch": 0.015335801163405606,
+      "grad_norm": 2.079669237136841,
+      "learning_rate": 8.049096779838719e-05,
+      "loss": 0.575,
+      "step": 29
+    },
+    {
+      "epoch": 0.015864621893178214,
+      "grad_norm": 1.5450035333633423,
+      "learning_rate": 7.411809548974792e-05,
+      "loss": 0.285,
+      "step": 30
+    },
+    {
+      "epoch": 0.01639344262295082,
+      "grad_norm": 1.7861802577972412,
+      "learning_rate": 6.785605346968386e-05,
+      "loss": 0.3807,
+      "step": 31
+    },
+    {
+      "epoch": 0.016922263352723427,
+      "grad_norm": 1.9254704713821411,
+      "learning_rate": 6.173165676349103e-05,
+      "loss": 0.4574,
+      "step": 32
+    },
+    {
+      "epoch": 0.017451084082496033,
+      "grad_norm": 2.295936107635498,
+      "learning_rate": 5.577113097809989e-05,
+      "loss": 0.4582,
+      "step": 33
+    },
+    {
+      "epoch": 0.017979904812268643,
+      "grad_norm": 2.942246437072754,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 0.5926,
+      "step": 34
+    },
+    {
+      "epoch": 0.01850872554204125,
+      "grad_norm": 1.30338454246521,
+      "learning_rate": 4.444297669803981e-05,
+      "loss": 0.2572,
+      "step": 35
+    },
+    {
+      "epoch": 0.019037546271813855,
+      "grad_norm": 2.0632126331329346,
+      "learning_rate": 3.9123857099127936e-05,
+      "loss": 0.4064,
+      "step": 36
+    },
+    {
+      "epoch": 0.01956636700158646,
+      "grad_norm": 1.9891884326934814,
+      "learning_rate": 3.406541848999312e-05,
+      "loss": 0.397,
+      "step": 37
+    },
+    {
+      "epoch": 0.02009518773135907,
+      "grad_norm": 1.516108751296997,
+      "learning_rate": 2.9289321881345254e-05,
+      "loss": 0.2141,
+      "step": 38
+    },
+    {
+      "epoch": 0.020624008461131677,
+      "grad_norm": 2.0183143615722656,
+      "learning_rate": 2.4816019252102273e-05,
+      "loss": 0.2988,
+      "step": 39
+    },
+    {
+      "epoch": 0.021152829190904283,
+      "grad_norm": 1.2690092325210571,
+      "learning_rate": 2.0664665970876496e-05,
+      "loss": 0.3371,
+      "step": 40
+    },
+    {
+      "epoch": 0.02168164992067689,
+      "grad_norm": 1.9884178638458252,
+      "learning_rate": 1.6853038769745467e-05,
+      "loss": 0.3387,
+      "step": 41
+    },
+    {
+      "epoch": 0.0222104706504495,
+      "grad_norm": 1.528070092201233,
+      "learning_rate": 1.339745962155613e-05,
+      "loss": 0.275,
+      "step": 42
+    },
+    {
+      "epoch": 0.022739291380222106,
+      "grad_norm": 1.3429299592971802,
+      "learning_rate": 1.0312725846731175e-05,
+      "loss": 0.2422,
+      "step": 43
+    },
+    {
+      "epoch": 0.023268112109994712,
+      "grad_norm": 2.5254251956939697,
+      "learning_rate": 7.612046748871327e-06,
+      "loss": 0.4689,
+      "step": 44
+    },
+    {
+      "epoch": 0.023796932839767318,
+      "grad_norm": 1.6032429933547974,
+      "learning_rate": 5.306987050489442e-06,
+      "loss": 0.371,
+      "step": 45
+    },
+    {
+      "epoch": 0.024325753569539928,
+      "grad_norm": 1.51561439037323,
+      "learning_rate": 3.40741737109318e-06,
+      "loss": 0.1822,
+      "step": 46
+    },
+    {
+      "epoch": 0.024854574299312534,
+      "grad_norm": 2.3901467323303223,
+      "learning_rate": 1.921471959676957e-06,
+      "loss": 0.3474,
+      "step": 47
+    },
+    {
+      "epoch": 0.02538339502908514,
+      "grad_norm": 1.7008579969406128,
+      "learning_rate": 8.555138626189618e-07,
+      "loss": 0.2807,
+      "step": 48
+    },
+    {
+      "epoch": 0.025912215758857746,
+      "grad_norm": 5.191266059875488,
+      "learning_rate": 2.141076761396521e-07,
+      "loss": 0.5048,
+      "step": 49
+    },
+    {
+      "epoch": 0.026441036488630356,
+      "grad_norm": 2.155629873275757,
+      "learning_rate": 0.0,
+      "loss": 0.4876,
+      "step": 50
+    },
+    {
+      "epoch": 0.026441036488630356,
+      "eval_loss": 0.44097796082496643,
+      "eval_runtime": 280.5295,
+      "eval_samples_per_second": 2.841,
+      "eval_steps_per_second": 1.422,
+      "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