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:a4f826ff38790ebface697d1e3c3090dcaedb3dd6d61853bcd13cfba97253862
+oid sha256:07da38c4b5194617a10c2de536b85491e286b4e18aef3c662e5b168840497eb2
 size 100697728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b508a8d02bcb82c4a3282efc993d9cf46001eb9e2657d288f46a92ce80f1085
+oid sha256:97654ef08d152fae9d41ee5f779406eadc5cacd38b5571a89093bc1ff027cba5
 size 201541754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eff7fd73f973e46014ca0cba260ef1bf771431578dfc80d8fcdb5d9fe1ecc859
+oid sha256:d0384a91293efd3ba6280cd22395b5c719e02504ad3e64b7952c1b9f54bd096a
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e2eb657255baf6b1420bbcfab19529abd45c6011f0c415bddb3c278a51f7f142
+oid sha256:f0e9cc72c20ddd925ef39b6005e82a4d8730b1dde32cfcd070d74c83a8a3564a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.5124326944351196,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.09111617312072894,
+  "best_metric": 0.4956277906894684,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.1366742596810934,
   "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": 3.825,
       "eval_steps_per_second": 1.933,
       "step": 20
+    },
+    {
+      "epoch": 0.09567198177676538,
+      "grad_norm": 1.0827614068984985,
+      "learning_rate": 2.8711035421746367e-05,
+      "loss": 2.0686,
+      "step": 21
+    },
+    {
+      "epoch": 0.10933940774487472,
+      "grad_norm": 0.9726663827896118,
+      "learning_rate": 1.3551568628929434e-05,
+      "loss": 2.0358,
+      "step": 24
+    },
+    {
+      "epoch": 0.11389521640091116,
+      "eval_loss": 0.49780604243278503,
+      "eval_runtime": 24.3262,
+      "eval_samples_per_second": 3.823,
+      "eval_steps_per_second": 1.932,
+      "step": 25
+    },
+    {
+      "epoch": 0.12300683371298406,
+      "grad_norm": 0.9599548578262329,
+      "learning_rate": 3.511175705587433e-06,
+      "loss": 1.8731,
+      "step": 27
+    },
+    {
+      "epoch": 0.1366742596810934,
+      "grad_norm": 0.8642181754112244,
+      "learning_rate": 0.0,
+      "loss": 1.7943,
+      "step": 30
+    },
+    {
+      "epoch": 0.1366742596810934,
+      "eval_loss": 0.4956277906894684,
+      "eval_runtime": 24.2854,
+      "eval_samples_per_second": 3.829,
+      "eval_steps_per_second": 1.935,
+      "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": 7368366033469440.0,
+  "total_flos": 1.105254905020416e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null