Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0fbd63e47c4e9a910d9a087ec24c1ba96537376084a9311f7a2d569e11a84e4b
+oid sha256:7e865908f709316176feee7b94d6472fab01ab159a18575443026979cab1e424
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f8fe2250fa57c54640e5bff783a27bfcea23bb0c072b812e8ff146814433a49f
+oid sha256:7cc1c2eebf235dc06b3eff514c22b49c3d7c0f31c874fee34a4e1f8de12140f4
 size 320194002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d82f897481655c7b3148db8a1ede2ab43fb18736cfe2c2b191e8497e85756de3
+oid sha256:beb07234a3b2450909dbdd8c935ebb33cae5d683491846c7af37296213d8d53e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c188a6a4749e6ca627bb6d536eb7443f499d5b1b88d98a78f9c713443e010d9c
+oid sha256:015707cb16790250630febca682498cb5d3456d5a13443b953687f19dc7d59ed
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.2053143978118896,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.0034302375439499186,
+  "best_metric": 2.099807024002075,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.006860475087899837,
   "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": 4.156,
       "eval_steps_per_second": 2.078,
       "step": 10
+    },
+    {
+      "epoch": 0.004116285052739903,
+      "grad_norm": 0.28495797514915466,
+      "learning_rate": 0.000163742398974869,
+      "loss": 2.2277,
+      "step": 12
+    },
+    {
+      "epoch": 0.005145356315924878,
+      "grad_norm": 0.2962561547756195,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 2.1012,
+      "step": 15
+    },
+    {
+      "epoch": 0.005145356315924878,
+      "eval_loss": 2.138622999191284,
+      "eval_runtime": 296.2609,
+      "eval_samples_per_second": 4.145,
+      "eval_steps_per_second": 2.072,
+      "step": 15
+    },
+    {
+      "epoch": 0.0061744275791098535,
+      "grad_norm": 0.3018041253089905,
+      "learning_rate": 9.372094804706867e-05,
+      "loss": 2.0662,
+      "step": 18
+    },
+    {
+      "epoch": 0.006860475087899837,
+      "eval_loss": 2.099807024002075,
+      "eval_runtime": 295.8571,
+      "eval_samples_per_second": 4.151,
+      "eval_steps_per_second": 2.075,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -80,7 +117,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4410842862845952.0,
+  "total_flos": 8658321175216128.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null