Training in progress, step 40, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:061c34a8ed6809cd0904d70b19b43324b3658413d60d98a7f6d48e2c3bffaef4
+oid sha256:f7c64749f73b3f3a5d89b895d9a7cda164f3d9c079c61a743d42dbfdad4b0209
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b94daf7dfa353715d4f279c393bf368a95cc77df273199877d1783020bbc946
+oid sha256:690b1653700e58de40b3ff6b61c00bbbac153cf7c5c51151346d224efe7c87fe
 size 170920084

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c68f05fddafe7d9625cc40fb5e03db579f2837d87b6225adf6c39031a56218a
+oid sha256:d9c10501b47aba97f7694378ee8a126f4d92e6dc5888f3a053ba82ed4ba7880d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60663a94a33586da5717f6f80de424ce9fe5b18a8c8d13d4ca09aa40f102443b
+oid sha256:f924e37bc06756f5535d9fa2079568e2b7869291abee642e58937943662c2f6f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.3060170114040375,
   "best_model_checkpoint": "miner_id_24/checkpoint-30",
-  "epoch": 0.05545286506469501,
+  "epoch": 0.07393715341959335,
   "eval_steps": 5,
-  "global_step": 30,
+  "global_step": 40,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -273,6 +273,92 @@
       "eval_samples_per_second": 1.311,
       "eval_steps_per_second": 0.655,
       "step": 30
+    },
+    {
+      "epoch": 0.05730129390018484,
+      "grad_norm": 6.309504508972168,
+      "learning_rate": 0.00019909497617679348,
+      "loss": 1.9929,
+      "step": 31
+    },
+    {
+      "epoch": 0.059149722735674676,
+      "grad_norm": 3.596278190612793,
+      "learning_rate": 0.0001990068775649202,
+      "loss": 1.3422,
+      "step": 32
+    },
+    {
+      "epoch": 0.06099815157116451,
+      "grad_norm": 3.6826868057250977,
+      "learning_rate": 0.00019891470916809362,
+      "loss": 1.3938,
+      "step": 33
+    },
+    {
+      "epoch": 0.06284658040665435,
+      "grad_norm": 2.7460691928863525,
+      "learning_rate": 0.00019881847477499557,
+      "loss": 0.8931,
+      "step": 34
+    },
+    {
+      "epoch": 0.06469500924214418,
+      "grad_norm": 4.063459873199463,
+      "learning_rate": 0.00019871817834144504,
+      "loss": 1.4139,
+      "step": 35
+    },
+    {
+      "epoch": 0.06469500924214418,
+      "eval_loss": 0.3002864420413971,
+      "eval_runtime": 173.4727,
+      "eval_samples_per_second": 1.314,
+      "eval_steps_per_second": 0.657,
+      "step": 35
+    },
+    {
+      "epoch": 0.066543438077634,
+      "grad_norm": 3.00803804397583,
+      "learning_rate": 0.0001986138239902355,
+      "loss": 0.9237,
+      "step": 36
+    },
+    {
+      "epoch": 0.06839186691312385,
+      "grad_norm": 3.4707858562469482,
+      "learning_rate": 0.0001985054160109657,
+      "loss": 1.6732,
+      "step": 37
+    },
+    {
+      "epoch": 0.07024029574861368,
+      "grad_norm": 4.129047393798828,
+      "learning_rate": 0.00019839295885986296,
+      "loss": 1.4183,
+      "step": 38
+    },
+    {
+      "epoch": 0.07208872458410351,
+      "grad_norm": 3.468799352645874,
+      "learning_rate": 0.0001982764571596004,
+      "loss": 1.1402,
+      "step": 39
+    },
+    {
+      "epoch": 0.07393715341959335,
+      "grad_norm": 2.87471079826355,
+      "learning_rate": 0.00019815591569910654,
+      "loss": 1.4329,
+      "step": 40
+    },
+    {
+      "epoch": 0.07393715341959335,
+      "eval_loss": 0.3075679838657379,
+      "eval_runtime": 173.655,
+      "eval_samples_per_second": 1.313,
+      "eval_steps_per_second": 0.656,
+      "step": 40
     }
   ],
   "logging_steps": 1,
@@ -287,7 +373,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 0
+        "early_stopping_patience_counter": 1
       }
     },
     "TrainerControl": {
@@ -296,12 +382,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 4.243520835551232e+16,
+  "total_flos": 5.658027780734976e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null