Training in progress, step 500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a1f933e5a7751a110a868391b13655f8f8f70565e499fe9ca187ff22e4ff4a0
+oid sha256:40eca4d85d98b5d33fd4932d9284ce9edc0503355914c66828e7466285a4cf44
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b1ab10ed23531f3edd901ff685b0c94f0c5cf25efba599cf9fa968de6c9d70be
+oid sha256:23f4b6f839724533ee11a0fd7cc67882017985f109a2bf890b2bd84e9e2d4716
 size 85723732

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d167e425f74e69f670f2a849bec8ce4b0bf755ee6f86e8caa56931889c9dd655
+oid sha256:147af0e62629fe4137b0053feec36817ba1e67430b3251ae7e46621c0720598c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5fa0f7e2faaa98aa485e5dc42922e1b1819381507fa6961c3be50a0b49af04c0
+oid sha256:b617d9f149fb11f5d9825dc6193f0b55aa7bf4899d1811982c0c93a389d7300b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.1549522876739502,
-  "best_model_checkpoint": "miner_id_24/checkpoint-450",
-  "epoch": 0.038026026702720976,
+  "best_metric": 1.1538832187652588,
+  "best_model_checkpoint": "miner_id_24/checkpoint-500",
+  "epoch": 0.04225114078080108,
   "eval_steps": 50,
-  "global_step": 450,
+  "global_step": 500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -402,6 +402,49 @@
       "eval_samples_per_second": 9.354,
       "eval_steps_per_second": 2.339,
       "step": 450
+    },
+    {
+      "epoch": 0.038871049518336996,
+      "grad_norm": 2.293142795562744,
+      "learning_rate": 4.106260230538197e-06,
+      "loss": 2.4559,
+      "step": 460
+    },
+    {
+      "epoch": 0.039716072333953016,
+      "grad_norm": 2.3784384727478027,
+      "learning_rate": 2.316354322216597e-06,
+      "loss": 2.5043,
+      "step": 470
+    },
+    {
+      "epoch": 0.040561095149569036,
+      "grad_norm": 2.946791172027588,
+      "learning_rate": 1.0315847133935416e-06,
+      "loss": 2.4185,
+      "step": 480
+    },
+    {
+      "epoch": 0.04140611796518506,
+      "grad_norm": 3.2220916748046875,
+      "learning_rate": 2.582106724586351e-07,
+      "loss": 2.1889,
+      "step": 490
+    },
+    {
+      "epoch": 0.04225114078080108,
+      "grad_norm": 3.6168417930603027,
+      "learning_rate": 0.0,
+      "loss": 1.9537,
+      "step": 500
+    },
+    {
+      "epoch": 0.04225114078080108,
+      "eval_loss": 1.1538832187652588,
+      "eval_runtime": 532.5509,
+      "eval_samples_per_second": 9.357,
+      "eval_steps_per_second": 2.34,
+      "step": 500
     }
   ],
   "logging_steps": 10,
@@ -425,12 +468,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.582041372033024e+17,
+  "total_flos": 1.75782374670336e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null