Training in progress, step 500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a3da280c702e3fe509a111a7fc862c4db0fe83962d4d60d855ae455daeb43a0
+oid sha256:23730b8c9c4f371fb02943be782d840ccbbe8525c187292b209428a06ecfe4e7
 size 997533656

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:83b42ccc78fc9f6a5f23b89793ebcc68b3e09aded426c3afdb92755a1d0609d3
+oid sha256:b7fa582cfd18ebcfcb7fa3bff37ce6468f5765e688b41659117e2aca0f699321
 size 507180756

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f611f73c481744a010adf9dea97a7693cf4a6264df18bb312fb66e7779f46c1
+oid sha256:89a5aaec5c15433aa13f7612875ffa14a1732c247dc5f571a4f11a15e3868d83
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe3012fb121cd84e6e41f718fd33de9e34ed33145ada7b055f7e25e49408431d
+oid sha256:71a96715f430c2eb0d6104363f54769b2c1bdb005671dc81f0d67833a84ba743
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.3588438034057617,
-  "best_model_checkpoint": "miner_id_24/checkpoint-450",
-  "epoch": 0.16553246275519587,
+  "best_metric": 1.3565335273742676,
+  "best_model_checkpoint": "miner_id_24/checkpoint-500",
+  "epoch": 0.18392495861688432,
   "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": 10.679,
       "eval_steps_per_second": 2.677,
       "step": 450
+    },
+    {
+      "epoch": 0.16921096192753357,
+      "grad_norm": 0.6076942682266235,
+      "learning_rate": 4.22247514272324e-06,
+      "loss": 1.4677,
+      "step": 460
+    },
+    {
+      "epoch": 0.17288946109987124,
+      "grad_norm": 0.5937750935554504,
+      "learning_rate": 2.38191152001518e-06,
+      "loss": 1.3644,
+      "step": 470
+    },
+    {
+      "epoch": 0.17656796027220895,
+      "grad_norm": 0.5931702852249146,
+      "learning_rate": 1.0607805071688306e-06,
+      "loss": 1.3443,
+      "step": 480
+    },
+    {
+      "epoch": 0.18024645944454662,
+      "grad_norm": 0.6748533844947815,
+      "learning_rate": 2.655185216791625e-07,
+      "loss": 1.2941,
+      "step": 490
+    },
+    {
+      "epoch": 0.18392495861688432,
+      "grad_norm": 0.8280065059661865,
+      "learning_rate": 0.0,
+      "loss": 1.2717,
+      "step": 500
+    },
+    {
+      "epoch": 0.18392495861688432,
+      "eval_loss": 1.3565335273742676,
+      "eval_runtime": 107.2901,
+      "eval_samples_per_second": 10.672,
+      "eval_steps_per_second": 2.675,
+      "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": 1.50826339270656e+17,
+  "total_flos": 1.6758482141184e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null