Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d0853ccbc49c74ed52d86573779397092af38d6770ea7340c36f0d76555e3c4
+oid sha256:31ad9834a1e11bc10c38d7be894b6bfa04d3ca9ef372e35d48d994a28d7b6cf2
 size 56662456

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a4561c456d651b8a435f898c6b533102771df8f28fda2e9c0d6ba23759fcf1ed
+oid sha256:1d8bfd9bbc8d1e5a910dbb5198330780b3df142e1845d6cadfdd4936bbc765a0
 size 113488058

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2984c51083c54f2a93eb7c7b2418dea66d8f3c5351ed7e42b1e0477edc7c96a3
+oid sha256:87ac1a33f136aa1f47e5b25f5555000c65160f91613dd9094dd725f4ba48f816
 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": 0.9311612844467163,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.21052631578947367,
+  "best_metric": 0.9053700566291809,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.3157894736842105,
   "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": 23.853,
       "eval_steps_per_second": 11.926,
       "step": 20
+    },
+    {
+      "epoch": 0.22105263157894736,
+      "grad_norm": 1.3441416025161743,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 3.6624,
+      "step": 21
+    },
+    {
+      "epoch": 0.25263157894736843,
+      "grad_norm": 1.47910737991333,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 3.7006,
+      "step": 24
+    },
+    {
+      "epoch": 0.2631578947368421,
+      "eval_loss": 0.9099543690681458,
+      "eval_runtime": 1.6772,
+      "eval_samples_per_second": 23.849,
+      "eval_steps_per_second": 11.924,
+      "step": 25
+    },
+    {
+      "epoch": 0.28421052631578947,
+      "grad_norm": 1.3131358623504639,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 3.6337,
+      "step": 27
+    },
+    {
+      "epoch": 0.3157894736842105,
+      "grad_norm": 1.1569862365722656,
+      "learning_rate": 0.0,
+      "loss": 3.5561,
+      "step": 30
+    },
+    {
+      "epoch": 0.3157894736842105,
+      "eval_loss": 0.9053700566291809,
+      "eval_runtime": 1.6825,
+      "eval_samples_per_second": 23.774,
+      "eval_steps_per_second": 11.887,
+      "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": 1201875462389760.0,
+  "total_flos": 1802813193584640.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null