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:b87c5255c08dfb785b38f94676b64ae5f69c37f1b1eaf1e74ff80d9fc7a6bd2d
+oid sha256:6e9c1ecd711599a29317d807fa7e8849c735d3acaeab1dbca13a85f15e1aafe7
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a4cbbf6bce86b8b18f8947810c3b186cce6a01b91520055147ba17b94e041ed7
+oid sha256:082d662021f54ec8f77e88fc1f1ff9806cf2a33f99cecb63dc779651682287d3
 size 320194002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f88431b600c091712847abac58452223fc04768337c0a249239a522c8ce713ff
+oid sha256:073830112659a5a5c37d243596f542f234f12ba9e25a35bf382da4048f3a10c5
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:015707cb16790250630febca682498cb5d3456d5a13443b953687f19dc7d59ed
+oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.5715872049331665,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.005999250093738283,
+  "best_metric": 0.5411311984062195,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.008998875140607425,
   "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": 4.213,
       "eval_steps_per_second": 2.107,
       "step": 20
+    },
+    {
+      "epoch": 0.006299212598425197,
+      "grad_norm": 0.20800277590751648,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 0.5715,
+      "step": 21
+    },
+    {
+      "epoch": 0.007199100112485939,
+      "grad_norm": 0.20942150056362152,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 0.5524,
+      "step": 24
+    },
+    {
+      "epoch": 0.0074990626171728535,
+      "eval_loss": 0.5460241436958313,
+      "eval_runtime": 333.1931,
+      "eval_samples_per_second": 4.214,
+      "eval_steps_per_second": 2.107,
+      "step": 25
+    },
+    {
+      "epoch": 0.008098987626546681,
+      "grad_norm": 0.18511688709259033,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 0.545,
+      "step": 27
+    },
+    {
+      "epoch": 0.008998875140607425,
+      "grad_norm": 0.19074997305870056,
+      "learning_rate": 0.0,
+      "loss": 0.5388,
+      "step": 30
+    },
+    {
+      "epoch": 0.008998875140607425,
+      "eval_loss": 0.5411311984062195,
+      "eval_runtime": 333.237,
+      "eval_samples_per_second": 4.213,
+      "eval_steps_per_second": 2.107,
+      "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": 1.306916403806208e+16,
+  "total_flos": 1.960374605709312e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null