Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d5ac93ed6a938c1b32a5c42a3260267d3221a59f23d460ddf0afa0fabb87145
+oid sha256:2ea859e88c19bed2f6bbfc202e3cbde185a8519f35b2b12b41694708359d987b
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ccef7dee44bfd169bf32ddcb88bff9d0748b03d26aab4f0ca761249d2cb8b6f
+oid sha256:4562d0225026750e98dc450480a87a99b4582a990486ba3aa1af7d1726c6e0fd
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b362a0f9206f50744ad3d91894f7ac7b2751f29b8976ecdd39441ca9506c460
+oid sha256:02850a98cdfcc5449495cdbb71d659ae3f37d8844c32a80eb728b983fd53c16f
 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": 1.7933586835861206,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.011697616610615587,
+  "best_metric": 1.772423267364502,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.01754642491592338,
   "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": 4.444,
       "eval_steps_per_second": 2.222,
       "step": 20
+    },
+    {
+      "epoch": 0.012282497441146366,
+      "grad_norm": 1.2276713848114014,
+      "learning_rate": 2.8711035421746367e-05,
+      "loss": 1.5985,
+      "step": 21
+    },
+    {
+      "epoch": 0.014037139932738705,
+      "grad_norm": 0.8209657669067383,
+      "learning_rate": 1.3551568628929434e-05,
+      "loss": 1.7915,
+      "step": 24
+    },
+    {
+      "epoch": 0.014622020763269484,
+      "eval_loss": 1.7752649784088135,
+      "eval_runtime": 163.0051,
+      "eval_samples_per_second": 4.417,
+      "eval_steps_per_second": 2.209,
+      "step": 25
+    },
+    {
+      "epoch": 0.015791782424331043,
+      "grad_norm": 1.2699406147003174,
+      "learning_rate": 3.511175705587433e-06,
+      "loss": 1.833,
+      "step": 27
+    },
+    {
+      "epoch": 0.01754642491592338,
+      "grad_norm": 0.857429563999176,
+      "learning_rate": 0.0,
+      "loss": 1.8152,
+      "step": 30
+    },
+    {
+      "epoch": 0.01754642491592338,
+      "eval_loss": 1.772423267364502,
+      "eval_runtime": 161.964,
+      "eval_samples_per_second": 4.445,
+      "eval_steps_per_second": 2.223,
+      "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": 7882552387829760.0,
+  "total_flos": 1.1684724716077056e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null