Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b808c2037ad307b7ff925c0b14b45ca160e62d355b061009a742c5672383fdc
+oid sha256:18ced76aa43901c129a17f352512c606416703aa22b91d8dab7dd0634d76985c
 size 295488936

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:33e20c3e44bcf205a7570290c0deea82b0ce4c763e413027e60dfa2dd016d950
+oid sha256:82bc7f8e848ac5be37f06986b8f210e7980b0291b953262afccb9db63abdf64c
 size 150486964

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:20f2bf0e770bb608ef603ceabe91189e217e09579ea32dc32ae924b0325848d6
+oid sha256:b3f0d9b0cc656904417ffcd11052d4e16ab35d154d0010c2f939eb30274c133f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb15fdd4c0ab874f4afa0ea95fae119cbc74554df5fbe92ab825fe27063eaa04
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.30090656876564026,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.08163265306122448,
+  "best_metric": 0.25239303708076477,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.16326530612244897,
   "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": 67.322,
       "eval_steps_per_second": 8.48,
       "step": 25
+    },
+    {
+      "epoch": 0.08489795918367347,
+      "grad_norm": 0.9594360589981079,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 0.2411,
+      "step": 26
+    },
+    {
+      "epoch": 0.08816326530612245,
+      "grad_norm": 1.0107917785644531,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 0.2269,
+      "step": 27
+    },
+    {
+      "epoch": 0.09142857142857143,
+      "grad_norm": 0.818159818649292,
+      "learning_rate": 4.825502516487497e-05,
+      "loss": 0.1497,
+      "step": 28
+    },
+    {
+      "epoch": 0.0946938775510204,
+      "grad_norm": 0.8434842228889465,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 0.1922,
+      "step": 29
+    },
+    {
+      "epoch": 0.09795918367346938,
+      "grad_norm": 0.9174337387084961,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 0.1636,
+      "step": 30
+    },
+    {
+      "epoch": 0.10122448979591837,
+      "grad_norm": 1.1038657426834106,
+      "learning_rate": 3.790390522001662e-05,
+      "loss": 0.2656,
+      "step": 31
+    },
+    {
+      "epoch": 0.10448979591836735,
+      "grad_norm": 1.095961570739746,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 0.1834,
+      "step": 32
+    },
+    {
+      "epoch": 0.10775510204081633,
+      "grad_norm": 1.1964353322982788,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 0.2125,
+      "step": 33
+    },
+    {
+      "epoch": 0.1110204081632653,
+      "grad_norm": 0.8366175293922424,
+      "learning_rate": 2.8081442660546125e-05,
+      "loss": 0.1703,
+      "step": 34
+    },
+    {
+      "epoch": 0.11428571428571428,
+      "grad_norm": 1.1785513162612915,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.2255,
+      "step": 35
+    },
+    {
+      "epoch": 0.11755102040816326,
+      "grad_norm": 2.2549848556518555,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 0.3386,
+      "step": 36
+    },
+    {
+      "epoch": 0.12081632653061225,
+      "grad_norm": 1.7458455562591553,
+      "learning_rate": 1.9216926233717085e-05,
+      "loss": 0.3218,
+      "step": 37
+    },
+    {
+      "epoch": 0.12408163265306123,
+      "grad_norm": 1.4194711446762085,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 0.2834,
+      "step": 38
+    },
+    {
+      "epoch": 0.1273469387755102,
+      "grad_norm": 2.6166067123413086,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 0.2846,
+      "step": 39
+    },
+    {
+      "epoch": 0.1306122448979592,
+      "grad_norm": 1.725498914718628,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 0.2775,
+      "step": 40
+    },
+    {
+      "epoch": 0.13387755102040816,
+      "grad_norm": 2.382291316986084,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.3032,
+      "step": 41
+    },
+    {
+      "epoch": 0.13714285714285715,
+      "grad_norm": 1.5899585485458374,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 0.2299,
+      "step": 42
+    },
+    {
+      "epoch": 0.1404081632653061,
+      "grad_norm": 1.4460498094558716,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 0.2016,
+      "step": 43
+    },
+    {
+      "epoch": 0.1436734693877551,
+      "grad_norm": 1.338460922241211,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 0.1473,
+      "step": 44
+    },
+    {
+      "epoch": 0.1469387755102041,
+      "grad_norm": 1.4085112810134888,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 0.1917,
+      "step": 45
+    },
+    {
+      "epoch": 0.15020408163265306,
+      "grad_norm": 1.4453519582748413,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 0.1925,
+      "step": 46
+    },
+    {
+      "epoch": 0.15346938775510205,
+      "grad_norm": 1.7839909791946411,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 0.2506,
+      "step": 47
+    },
+    {
+      "epoch": 0.156734693877551,
+      "grad_norm": 2.2615933418273926,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 0.3894,
+      "step": 48
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 2.7066493034362793,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 0.4126,
+      "step": 49
+    },
+    {
+      "epoch": 0.16326530612244897,
+      "grad_norm": 2.8546383380889893,
+      "learning_rate": 0.0,
+      "loss": 0.2516,
+      "step": 50
+    },
+    {
+      "epoch": 0.16326530612244897,
+      "eval_loss": 0.25239303708076477,
+      "eval_runtime": 7.6536,
+      "eval_samples_per_second": 67.419,
+      "eval_steps_per_second": 8.493,
+      "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": 3401809133568000.0,
+  "total_flos": 6803618267136000.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null