Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7dfc7a638c89b7d63d91296e4cf88ac4c52c1689d253d77a12a25227a7ef6af6
+oid sha256:057a98ceeb7249ec2256070c0037b406c100a3d9fa2809beeb424a449a1d546e
 size 1195486552

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae0dcc57207e3b4d6680095350ad3ae51d429a1a7467b18d3b23f62f307e2dbc
+oid sha256:89242bc107acea230cfc1c92abefd30264f1c89e19a695cf9e1c2bd1b00ab1b2
 size 341314196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:03a128b50400c706994048f5ca5298b8dab47fde198714e4523b0c61ab752151
+oid sha256:4a484a9feef9028d02e7d1f772db09becf19fd5f909ba5f57acd35b7e0624fb9
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4bf1a6f89c4ccfeb423775f70e378195af348273ade7a1d504b8ad665994fa62
+oid sha256:7a29a98d7724cf179d3beb2d49a34c568e23cf47a86cb77f3cd39efdcdbcc2de
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.8471082448959351,
   "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.04486316733961418,
+  "epoch": 0.08972633467922836,
   "eval_steps": 50,
-  "global_step": 100,
+  "global_step": 200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -101,6 +101,92 @@
       "eval_samples_per_second": 9.778,
       "eval_steps_per_second": 2.447,
       "step": 100
+    },
+    {
+      "epoch": 0.049349484073575596,
+      "grad_norm": 3.512911558151245,
+      "learning_rate": 0.000203792591238937,
+      "loss": 1.645,
+      "step": 110
+    },
+    {
+      "epoch": 0.05383580080753701,
+      "grad_norm": 3.946240186691284,
+      "learning_rate": 0.0002005339186394757,
+      "loss": 1.6842,
+      "step": 120
+    },
+    {
+      "epoch": 0.05832211754149843,
+      "grad_norm": 4.178013324737549,
+      "learning_rate": 0.00019681712224065936,
+      "loss": 1.6473,
+      "step": 130
+    },
+    {
+      "epoch": 0.06280843427545985,
+      "grad_norm": 4.492946624755859,
+      "learning_rate": 0.0001926603099009319,
+      "loss": 1.8509,
+      "step": 140
+    },
+    {
+      "epoch": 0.06729475100942127,
+      "grad_norm": 9.499361991882324,
+      "learning_rate": 0.00018808373319217114,
+      "loss": 1.9255,
+      "step": 150
+    },
+    {
+      "epoch": 0.06729475100942127,
+      "eval_loss": 0.9034681916236877,
+      "eval_runtime": 95.6255,
+      "eval_samples_per_second": 9.82,
+      "eval_steps_per_second": 2.458,
+      "step": 150
+    },
+    {
+      "epoch": 0.07178106774338268,
+      "grad_norm": 3.9133944511413574,
+      "learning_rate": 0.00018310968873606635,
+      "loss": 1.6616,
+      "step": 160
+    },
+    {
+      "epoch": 0.0762673844773441,
+      "grad_norm": 4.055591583251953,
+      "learning_rate": 0.0001777624095772184,
+      "loss": 1.6122,
+      "step": 170
+    },
+    {
+      "epoch": 0.08075370121130551,
+      "grad_norm": 4.28033447265625,
+      "learning_rate": 0.0001720679471221826,
+      "loss": 1.5771,
+      "step": 180
+    },
+    {
+      "epoch": 0.08524001794526694,
+      "grad_norm": 4.180228233337402,
+      "learning_rate": 0.00016605404421963453,
+      "loss": 1.7657,
+      "step": 190
+    },
+    {
+      "epoch": 0.08972633467922836,
+      "grad_norm": 18.84837532043457,
+      "learning_rate": 0.00015975,
+      "loss": 1.9318,
+      "step": 200
+    },
+    {
+      "epoch": 0.08972633467922836,
+      "eval_loss": 0.8709530830383301,
+      "eval_runtime": 95.776,
+      "eval_samples_per_second": 9.804,
+      "eval_steps_per_second": 2.454,
+      "step": 200
     }
   ],
   "logging_steps": 10,
@@ -115,7 +201,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 1
+        "early_stopping_patience_counter": 3
       }
     },
     "TrainerControl": {
@@ -124,12 +210,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 3.1571446874505216e+16,
+  "total_flos": 6.376895643490714e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null