Training in progress, step 150, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8234fba92739f9ba49d65e85141151ea3e3f941b1fc02a890d6f96c892e54c95
+oid sha256:329779a9d75f81c59138e004c74680cb2f6109c19967aebb8a6af114432882d1
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b82b04ea09710aa4213cb03ab0b5cc1dd4aa0201bac4c985f2111eba665c109
+oid sha256:664c4791853bfcdd7ad0bd0ff4f7aa982b6789073a49409259639cbe20c19306
 size 341314196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43d2d8263b8cbac44fb13353f2a54b95985b179bd30ff324f943f58b6fa81a87
+oid sha256:818f16670711f557472473aa4463545c4162b79354ecd58d3965097bd34e18c6
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:697eb5c311706d748c20f07b0521bb9d1f71aee638eb745112aecf80a82e51da
+oid sha256:d4ffe1cc6011db9bcd26d2a5ee9a2f60bf90f43b3c6aed165ee32997fe344b31
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.351407289505005,
-  "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.036081544290095614,
+  "best_metric": 2.2884583473205566,
+  "best_model_checkpoint": "miner_id_24/checkpoint-150",
+  "epoch": 0.054122316435143425,
   "eval_steps": 50,
-  "global_step": 100,
+  "global_step": 150,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -101,6 +101,49 @@
       "eval_samples_per_second": 15.907,
       "eval_steps_per_second": 3.98,
       "step": 100
+    },
+    {
+      "epoch": 0.03968969871910518,
+      "grad_norm": 1.5597459077835083,
+      "learning_rate": 0.0002085764548830435,
+      "loss": 2.2556,
+      "step": 110
+    },
+    {
+      "epoch": 0.04329785314811474,
+      "grad_norm": 1.775914192199707,
+      "learning_rate": 0.00020524128762162305,
+      "loss": 2.3104,
+      "step": 120
+    },
+    {
+      "epoch": 0.0469060075771243,
+      "grad_norm": 1.6727547645568848,
+      "learning_rate": 0.00020143724248105043,
+      "loss": 2.1549,
+      "step": 130
+    },
+    {
+      "epoch": 0.050514162006133866,
+      "grad_norm": 2.4896557331085205,
+      "learning_rate": 0.0001971828523868693,
+      "loss": 2.1205,
+      "step": 140
+    },
+    {
+      "epoch": 0.054122316435143425,
+      "grad_norm": 4.250438213348389,
+      "learning_rate": 0.0001924988442999686,
+      "loss": 2.0478,
+      "step": 150
+    },
+    {
+      "epoch": 0.054122316435143425,
+      "eval_loss": 2.2884583473205566,
+      "eval_runtime": 73.1329,
+      "eval_samples_per_second": 15.957,
+      "eval_steps_per_second": 3.993,
+      "step": 150
     }
   ],
   "logging_steps": 10,
@@ -115,7 +158,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 1
+        "early_stopping_patience_counter": 0
       }
     },
     "TrainerControl": {
@@ -129,7 +172,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.9422112326352896e+16,
+  "total_flos": 2.922745058820096e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null