Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:924f7d076b1fc2e1a8a0598b795da9a71ef32887f3cbacc642adb418936e83e3
+oid sha256:649e97773a75a0e0f7435ac49c00810398fe968d0acb7ade2848555e32cbec9d
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:123a21e8caef8e70fafce3476389dd71fa60cd457b338b138e21160932c9407a
+oid sha256:c726a2e0173e25ef6291dec23cfdfcb1e3c7e35e9a880ab2b36eb16a65430dcb
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e336ffb4f2385fe7817a79ed4d3cfcc71e6b65eaf2fdf9bb2447eedac0e09f6
+oid sha256:52a137807b35a9891cffdb2f9791f8581d1b36563a2d02b3103be81857f35d0b
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:015707cb16790250630febca682498cb5d3456d5a13443b953687f19dc7d59ed
+oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.7658795714378357,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.0061562139284340135,
+  "best_metric": 0.7537251710891724,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.00923432089265102,
   "eval_steps": 5,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -89,6 +89,50 @@
       "eval_samples_per_second": 7.587,
       "eval_steps_per_second": 3.793,
       "step": 20
+    },
+    {
+      "epoch": 0.006464024624855714,
+      "grad_norm": 0.8081445097923279,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 0.7547,
+      "step": 21
+    },
+    {
+      "epoch": 0.007387456714120816,
+      "grad_norm": 0.6903554797172546,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 0.6985,
+      "step": 24
+    },
+    {
+      "epoch": 0.007695267410542516,
+      "eval_loss": 0.7558912038803101,
+      "eval_runtime": 180.6183,
+      "eval_samples_per_second": 7.574,
+      "eval_steps_per_second": 3.787,
+      "step": 25
+    },
+    {
+      "epoch": 0.008310888803385917,
+      "grad_norm": 0.6000914573669434,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 0.8753,
+      "step": 27
+    },
+    {
+      "epoch": 0.00923432089265102,
+      "grad_norm": 0.6622340679168701,
+      "learning_rate": 0.0,
+      "loss": 0.8675,
+      "step": 30
+    },
+    {
+      "epoch": 0.00923432089265102,
+      "eval_loss": 0.7537251710891724,
+      "eval_runtime": 180.2351,
+      "eval_samples_per_second": 7.59,
+      "eval_steps_per_second": 3.795,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -112,12 +156,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 7511608746049536.0,
+  "total_flos": 1.1313781074296832e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null