Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ce22bdb1d49c68e0efc5424bfdbd884977280e695b7b367313af903c1ce1d72
+oid sha256:73cc2aa4513b0a9e1dd57531c8aa9e9f42c111939f564cfbf7a9f6a5f9f91d8b
 size 319876032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1da092be2eff288e8febebf1204d0f3a28ff77146b05861f79ef77c3b6ba8603
+oid sha256:c29e1e2855fced08ae8442d1df06e8fa19dd9e702d19aeecfbbe34f73c40bc16
 size 162933396

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d1f086bd1035ab8cc673b7d310e7ef2d72721fe09f2bf3f4f1d40725d551247
+oid sha256:81e41c2618bb2a68223808a3ba94e34beefb26f0517e8c2e8814c61693c45279
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5220d0af0ff98b2d6e04334f1c29842da7230747bf3383cf1f883a4d2eb6d4f2
+oid sha256:90c455b2a7603e9003556345290fd0185bd6c6017de2b595e3f9c6216f721e5e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.3112847805023193,
-  "best_model_checkpoint": "miner_id_24/checkpoint-150",
-  "epoch": 0.023433838462740195,
+  "best_metric": 2.3089747428894043,
+  "best_model_checkpoint": "miner_id_24/checkpoint-200",
+  "epoch": 0.031245117950320263,
   "eval_steps": 50,
-  "global_step": 150,
+  "global_step": 200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -144,6 +144,49 @@
       "eval_samples_per_second": 13.807,
       "eval_steps_per_second": 3.455,
       "step": 150
+    },
+    {
+      "epoch": 0.02499609436025621,
+      "grad_norm": 0.40746375918388367,
+      "learning_rate": 2.2644444444444443e-06,
+      "loss": 2.2168,
+      "step": 160
+    },
+    {
+      "epoch": 0.02655835025777222,
+      "grad_norm": 0.49461621046066284,
+      "learning_rate": 1.6983333333333333e-06,
+      "loss": 2.328,
+      "step": 170
+    },
+    {
+      "epoch": 0.028120606155288237,
+      "grad_norm": 0.42978784441947937,
+      "learning_rate": 1.1322222222222221e-06,
+      "loss": 2.3236,
+      "step": 180
+    },
+    {
+      "epoch": 0.029682862052804248,
+      "grad_norm": 0.5799306631088257,
+      "learning_rate": 5.661111111111111e-07,
+      "loss": 2.2985,
+      "step": 190
+    },
+    {
+      "epoch": 0.031245117950320263,
+      "grad_norm": 0.6257038712501526,
+      "learning_rate": 0.0,
+      "loss": 2.4146,
+      "step": 200
+    },
+    {
+      "epoch": 0.031245117950320263,
+      "eval_loss": 2.3089747428894043,
+      "eval_runtime": 146.4061,
+      "eval_samples_per_second": 13.811,
+      "eval_steps_per_second": 3.456,
+      "step": 200
     }
   ],
   "logging_steps": 10,
@@ -167,12 +210,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 3.722496579521741e+16,
+  "total_flos": 4.955111340952781e+16,
   "train_batch_size": 6,
   "trial_name": null,
   "trial_params": null