Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a2e7ae795b48079654062b03185343cc73d85495dc328fc3db72a78c1e5c19a
+oid sha256:b067d92d6cf743d10bf07fdd765f926080867aa7e8f87fb48c7c64d6fc8292b9
 size 222865880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca7f9f78b6b9890f06599e9567e27447734a5dd7b4261958ab14ab066969252a
+oid sha256:b0804c5958837f3d5429177016e1997c0f5d3f6f779ecfbba33221e73e0b57fb
 size 445914554

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b2afbdc2003c7a988105c1c7bed9fe94f498880cef8384cbeca36532f532b80
+oid sha256:7d5441e3c9f163aec4c8838db8aad21ee9d960135a0cb80d47ee92365310135d
 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": 5.251645565032959,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.05115089514066496,
+  "best_metric": 5.112382888793945,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.07672634271099744,
   "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": 4.395,
       "eval_steps_per_second": 1.105,
       "step": 20
+    },
+    {
+      "epoch": 0.05370843989769821,
+      "grad_norm": 8.359580993652344,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 15.5105,
+      "step": 21
+    },
+    {
+      "epoch": 0.061381074168797956,
+      "grad_norm": 8.11271858215332,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 16.5227,
+      "step": 24
+    },
+    {
+      "epoch": 0.0639386189258312,
+      "eval_loss": 5.127615928649902,
+      "eval_runtime": 75.2873,
+      "eval_samples_per_second": 4.383,
+      "eval_steps_per_second": 1.102,
+      "step": 25
+    },
+    {
+      "epoch": 0.06905370843989769,
+      "grad_norm": 9.202075004577637,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 16.8827,
+      "step": 27
+    },
+    {
+      "epoch": 0.07672634271099744,
+      "grad_norm": 12.595846176147461,
+      "learning_rate": 0.0,
+      "loss": 17.2095,
+      "step": 30
+    },
+    {
+      "epoch": 0.07672634271099744,
+      "eval_loss": 5.112382888793945,
+      "eval_runtime": 75.2566,
+      "eval_samples_per_second": 4.385,
+      "eval_steps_per_second": 1.103,
+      "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": 2.723369975808e+16,
+  "total_flos": 4.085054963712e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null