Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8849dc5962d50981de96e8cf8b244e02a8f3f2cad190948ec38ed89d1c3290a
+oid sha256:1fd039ccda2590e10924b6760c58d8d1a796922cf00f12110dac84afd4e330df
 size 26008

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa948f9c7d7fb031c7d1ca7849f1572cbe00489db7edd671feed203792aa214a
+oid sha256:10afcaff9681b4e825ed1fd77a99621ebf37f7697375e3349db6e0b302e200e5
 size 61862

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e97ead28242dd097af80112cb3bd8d751944021cbf255fca1535e0f2a22344d9
+oid sha256:c5288ed9323916daf49e9e619b5ce81ab40c19e01021e3ee0c12210ac8bab7de
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4849a6ac0a1d895740f1ab4eba9d346b8d898008d0cfe93dd108cd928d7c63e
+oid sha256:46d68217ddf3e899bf1495ee33b9ec14e2c91ed912ffcb460a7bb01192b04b7d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 11.931888580322266,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.004253056884635832,
+  "best_metric": 11.931757926940918,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.008506113769271665,
   "eval_steps": 5,
-  "global_step": 10,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -52,6 +52,43 @@
       "eval_samples_per_second": 69.474,
       "eval_steps_per_second": 34.737,
       "step": 10
+    },
+    {
+      "epoch": 0.005103668261562998,
+      "grad_norm": 0.009385287761688232,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 11.9327,
+      "step": 12
+    },
+    {
+      "epoch": 0.006379585326953748,
+      "grad_norm": 0.01152839045971632,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 11.9341,
+      "step": 15
+    },
+    {
+      "epoch": 0.006379585326953748,
+      "eval_loss": 11.931816101074219,
+      "eval_runtime": 13.5936,
+      "eval_samples_per_second": 72.829,
+      "eval_steps_per_second": 36.414,
+      "step": 15
+    },
+    {
+      "epoch": 0.007655502392344498,
+      "grad_norm": 0.013427882455289364,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 11.9304,
+      "step": 18
+    },
+    {
+      "epoch": 0.008506113769271665,
+      "eval_loss": 11.931757926940918,
+      "eval_runtime": 14.2756,
+      "eval_samples_per_second": 69.349,
+      "eval_steps_per_second": 34.675,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -80,7 +117,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3747348480.0,
+  "total_flos": 7588380672.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null