Training in progress, step 150, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:34873289a69d95dd03e68fee973c7b642782c3918c3b8ea959f6763c5946dea8
+oid sha256:f7d89f45ed7a74588a1be035d2ea199a8be4704f9015b71bd3026c99251b02fa
 size 1157746040

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e3ed6d9149a7bc56acca7c63d4ebf114fe924e5da3ee3affd4e0307d15ffca2
+oid sha256:f4a8bac2db7d0fa672694df4ee9566e4246e340c39abdb988b54892f0b9d4a6f
 size 588699796

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ccd1c6ca381034486ac9d3bd5b155e1c2fee70137075805fcdf59b77d7b2b55
+oid sha256:62f4d181893c9bc040ba0fad0dbbee9a3f2de880b67f739edfd1460a79f556c2
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e231c2c515a5ff10f1e544b2aa46a8eaae94bd71a11db0123cabe0d1726bb1ba
+oid sha256:80e3c543dd881d7b92b58f753c91bcd488f8269b3e4ffd67623431c55e782209
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 1.2476589679718018,
   "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.01697792869269949,
+  "epoch": 0.025466893039049237,
   "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": 5.269,
       "eval_steps_per_second": 1.317,
       "step": 100
+    },
+    {
+      "epoch": 0.01867572156196944,
+      "grad_norm": 0.6778289675712585,
+      "learning_rate": 0.00019805195486600916,
+      "loss": 1.3131,
+      "step": 110
+    },
+    {
+      "epoch": 0.02037351443123939,
+      "grad_norm": 0.7167655825614929,
+      "learning_rate": 0.00019488507586089894,
+      "loss": 1.1878,
+      "step": 120
+    },
+    {
+      "epoch": 0.022071307300509338,
+      "grad_norm": 0.786454975605011,
+      "learning_rate": 0.00019127297795219008,
+      "loss": 1.2166,
+      "step": 130
+    },
+    {
+      "epoch": 0.023769100169779286,
+      "grad_norm": 0.8451493382453918,
+      "learning_rate": 0.00018723325891780706,
+      "loss": 1.2909,
+      "step": 140
+    },
+    {
+      "epoch": 0.025466893039049237,
+      "grad_norm": 0.7425501942634583,
+      "learning_rate": 0.0001827855998628142,
+      "loss": 1.1985,
+      "step": 150
+    },
+    {
+      "epoch": 0.025466893039049237,
+      "eval_loss": 1.248077630996704,
+      "eval_runtime": 235.4875,
+      "eval_samples_per_second": 5.266,
+      "eval_steps_per_second": 1.316,
+      "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": 3.193703014544179e+16,
+  "total_flos": 4.844195528520499e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null