Training in progress, step 150, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb92d94cfcb1117e0121afa54fb545d7e269b2a0339f4d13a13c8695475fed90
+oid sha256:91a9805601b3a37da5eec4036f7883ac9e977fd04b2444e642d86d6341973a73
 size 2436967616

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ce16b6e427a5fd59ce67256fa4f939499b469a4ad65773d12d8ee1377acefa7
+oid sha256:80bac36c8d7e69d9c9785885c7a6cb29ee5f919f3648e7a04fb8500db72430f6
 size 170920084

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e257f15754dc942930744d629340bfa9563b830898c02d6e10c06366d6f435a6
+oid sha256:6a40fa307c8c591dcfc24aaa28b94acee940e8d4d3469093ca4b746bc04e8cce
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87bb1aa192c7f9c0516bbbf45e738ece50573944baeb2415a4a135a1ac346045
+oid sha256:5220d0af0ff98b2d6e04334f1c29842da7230747bf3383cf1f883a4d2eb6d4f2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.15586192905902863,
-  "best_model_checkpoint": "miner_id_24/checkpoint-100",
-  "epoch": 0.15847860538827258,
+  "best_metric": 0.15055163204669952,
+  "best_model_checkpoint": "miner_id_24/checkpoint-150",
+  "epoch": 0.23771790808240886,
   "eval_steps": 50,
-  "global_step": 100,
+  "global_step": 150,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -101,6 +101,49 @@
       "eval_samples_per_second": 10.933,
       "eval_steps_per_second": 2.747,
       "step": 100
+    },
+    {
+      "epoch": 0.17432646592709986,
+      "grad_norm": 1.1320366859436035,
+      "learning_rate": 5.095e-06,
+      "loss": 0.1502,
+      "step": 110
+    },
+    {
+      "epoch": 0.1901743264659271,
+      "grad_norm": 1.3633605241775513,
+      "learning_rate": 4.5288888888888885e-06,
+      "loss": 0.153,
+      "step": 120
+    },
+    {
+      "epoch": 0.20602218700475436,
+      "grad_norm": 21.038341522216797,
+      "learning_rate": 3.9627777777777784e-06,
+      "loss": 0.1643,
+      "step": 130
+    },
+    {
+      "epoch": 0.2218700475435816,
+      "grad_norm": 3.7287445068359375,
+      "learning_rate": 3.3966666666666666e-06,
+      "loss": 0.1585,
+      "step": 140
+    },
+    {
+      "epoch": 0.23771790808240886,
+      "grad_norm": 1.4687708616256714,
+      "learning_rate": 2.830555555555556e-06,
+      "loss": 0.1692,
+      "step": 150
+    },
+    {
+      "epoch": 0.23771790808240886,
+      "eval_loss": 0.15055163204669952,
+      "eval_runtime": 18.1953,
+      "eval_samples_per_second": 10.937,
+      "eval_steps_per_second": 2.748,
+      "step": 150
     }
   ],
   "logging_steps": 10,
@@ -129,7 +172,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.79754070556672e+16,
+  "total_flos": 4.19631105835008e+16,
   "train_batch_size": 6,
   "trial_name": null,
   "trial_params": null