Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8778efc2982fc9024cdb38a2cce28a2c542357b2410f0ef5cac1fde1d88dbe06
+oid sha256:1f16a15c5b434eb34ed23890595fc14705674a7a01f74bcc32c2abc141bdf64a
 size 186962

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ab45eed3a654ee6f244d89f4f356b04ab4163610210603b517479f414f9f790
+oid sha256:2caee354bdcc1a915206780f8dee66b77ab445594b8912afeb8c98a2e765a732
 size 121430

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b73b43b2e6e7654f681327fbc9d8864ac66d7432ad9f407444f6bf6170764eb9
+oid sha256:57f103553ccd91c62a5573bcd9df27b1afa1a11876221074b56904954f3a1852
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a62e6ea25099651400ff4a3142a50e40bef5b52ba883be53b2fcb9d1a5b0a98c
+oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 6.926670074462891,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.0018859473349206724,
+  "best_metric": 6.925025463104248,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.0028289210023810085,
   "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": 441.9,
       "eval_steps_per_second": 220.95,
       "step": 20
+    },
+    {
+      "epoch": 0.001980244701666706,
+      "grad_norm": 0.11661473661661148,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 6.9263,
+      "step": 21
+    },
+    {
+      "epoch": 0.0022631368019048067,
+      "grad_norm": 0.09650826454162598,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 6.9279,
+      "step": 24
+    },
+    {
+      "epoch": 0.0023574341686508405,
+      "eval_loss": 6.925273418426514,
+      "eval_runtime": 10.2622,
+      "eval_samples_per_second": 435.19,
+      "eval_steps_per_second": 217.595,
+      "step": 25
+    },
+    {
+      "epoch": 0.0025460289021429078,
+      "grad_norm": 0.13508102297782898,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 6.9218,
+      "step": 27
+    },
+    {
+      "epoch": 0.0028289210023810085,
+      "grad_norm": 0.12174210697412491,
+      "learning_rate": 0.0,
+      "loss": 6.928,
+      "step": 30
+    },
+    {
+      "epoch": 0.0028289210023810085,
+      "eval_loss": 6.925025463104248,
+      "eval_runtime": 10.1991,
+      "eval_samples_per_second": 437.882,
+      "eval_steps_per_second": 218.941,
+      "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": 63350071296.0,
+  "total_flos": 97234993152.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null