Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa801ab9ee48224fa4d1d83e72854490d15942438db7177c3948b55506d0d6c9
+oid sha256:dd26ed06157a5fabb527b16c8361dfc667f28bcfc0363c92e5401c7ae4231cfb
 size 59827904

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa8bddd6e29593c5c58adc1a166bc2a71d9e8efd664ccd407467b10575bb5f5c
+oid sha256:3a107011bb30edc87bf6f7685f13334fcccaf1db8a3b1a381d988ef241ad68de
 size 30875540

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1805dd3420e721c0a9085e366ef0669c06e290b95722d5e3748acf7759141c9f
+oid sha256:7eea9693132e6849eda2690ec914c474715bb1d769cbcef7f501a36c450891a1
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ae7559c87b7ffb9e2fc8a14f2140f4d67007939fa4f54b542e73e9ef24c02fc
+oid sha256:3b8bc8abd4c9f82dfc46828b9bd127304694d7b33110834b4b23e29a7f6b47fd
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 9.236889839172363,
   "best_model_checkpoint": "miner_id_besimray/checkpoint-5",
-  "epoch": 0.0010187449062754685,
+  "epoch": 0.002037489812550937,
   "eval_steps": 5,
-  "global_step": 5,
+  "global_step": 10,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -58,6 +58,49 @@
       "eval_samples_per_second": 3.065,
       "eval_steps_per_second": 0.307,
       "step": 5
+    },
+    {
+      "epoch": 0.0012224938875305623,
+      "grad_norm": 7954734698725376.0,
+      "learning_rate": 1.2e-05,
+      "loss": 8.1799,
+      "step": 6
+    },
+    {
+      "epoch": 0.0014262428687856561,
+      "grad_norm": Infinity,
+      "learning_rate": 1.4e-05,
+      "loss": 9.2379,
+      "step": 7
+    },
+    {
+      "epoch": 0.0016299918500407497,
+      "grad_norm": Infinity,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 11.4264,
+      "step": 8
+    },
+    {
+      "epoch": 0.0018337408312958435,
+      "grad_norm": 9.681396420271145e+17,
+      "learning_rate": 1.8e-05,
+      "loss": 8.77,
+      "step": 9
+    },
+    {
+      "epoch": 0.002037489812550937,
+      "grad_norm": 2.2846267641246515e+17,
+      "learning_rate": 2e-05,
+      "loss": 10.016,
+      "step": 10
+    },
+    {
+      "epoch": 0.002037489812550937,
+      "eval_loss": 9.262293815612793,
+      "eval_runtime": 843.2301,
+      "eval_samples_per_second": 3.063,
+      "eval_steps_per_second": 0.307,
+      "step": 10
     }
   ],
   "logging_steps": 1,
@@ -72,7 +115,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 0
+        "early_stopping_patience_counter": 1
       }
     },
     "TrainerControl": {
@@ -86,7 +129,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4592665991577600.0,
+  "total_flos": 9185331983155200.0,
   "train_batch_size": 10,
   "trial_name": null,
   "trial_params": null