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:af2ac5f9f5a8afc2e8593a354e1ce27658149294c8a0f40656b51bdb30548427
+oid sha256:2de37fa0ffcc640e1ff40701bfd8a9e450c2fabfb066af254678d42e1973e814
 size 645975704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:580a06c4127fa8d71e3b8052907a41660172d23f22384c9c5b0defa79dbefabb
+oid sha256:9bb249581fe642bb092877c3229ff71a0e08259f2968534f6bb0c0fa1df21209
 size 328468404

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5abd636d1fcde191adce24dac333f45255e5374fcf26e016a2e8b2fc91ca0902
+oid sha256:0a2cfbf75bd4762702bdf3a9445a6bbdc2eed82805837735a49a7dd8811f2f77
 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": 1.7293239831924438,
   "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.0859106529209622,
+  "epoch": 0.12886597938144329,
   "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": 17.74,
       "eval_steps_per_second": 4.453,
       "step": 100
+    },
+    {
+      "epoch": 0.09450171821305842,
+      "grad_norm": 0.9484879970550537,
+      "learning_rate": 0.0002085764548830435,
+      "loss": 1.7982,
+      "step": 110
+    },
+    {
+      "epoch": 0.10309278350515463,
+      "grad_norm": 0.964938759803772,
+      "learning_rate": 0.00020524128762162305,
+      "loss": 1.7195,
+      "step": 120
+    },
+    {
+      "epoch": 0.11168384879725086,
+      "grad_norm": 1.1392478942871094,
+      "learning_rate": 0.00020143724248105043,
+      "loss": 1.5898,
+      "step": 130
+    },
+    {
+      "epoch": 0.12027491408934708,
+      "grad_norm": 1.2410438060760498,
+      "learning_rate": 0.0001971828523868693,
+      "loss": 1.4812,
+      "step": 140
+    },
+    {
+      "epoch": 0.12886597938144329,
+      "grad_norm": 3.722848892211914,
+      "learning_rate": 0.0001924988442999686,
+      "loss": 1.4084,
+      "step": 150
+    },
+    {
+      "epoch": 0.12886597938144329,
+      "eval_loss": 1.7576016187667847,
+      "eval_runtime": 27.7184,
+      "eval_samples_per_second": 17.678,
+      "eval_steps_per_second": 4.437,
+      "step": 150
     }
   ],
   "logging_steps": 10,
@@ -115,7 +158,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 1
+        "early_stopping_patience_counter": 2
       }
     },
     "TrainerControl": {
@@ -129,7 +172,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.7773608566784e+16,
+  "total_flos": 2.6660412850176e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null