Training in progress, step 150, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:88fb81e440d85a6605618a0971084cb49fe2a7e39a58f2bd580aea3401d0b6f8
+oid sha256:da9e1d165d8719ec9f780eb8920883a80b63e242e51bdee30659745e50827b33
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a4ac9ea3ee5a462c9ceab4a9e4ae719693693e0cf78a6ec875aed88f35960ce
+oid sha256:26d83b0491c54271b98a7a8ac65d71d04b9a149eed85787a94b4873a11c78998
 size 341314196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e936836b2cdc132491f556998ba2d3f8cb2dd14428b1b18cd5fae4ebbcb5a994
+oid sha256:6ca1d3a29ddde696f94089676e8882cda32984390a8fca557ea6d5cc2578ecc4
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a760ba92960f08f363394eee4df1edc2c66e6b8b22489dbac9e6aa0f5ae478e1
+oid sha256:9a7c1078eb5a1a7c3016e3bc1b27b5075c61ea30d4750bf448abc31716e92a9c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 2.5439529418945312,
   "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.03623844899438304,
+  "epoch": 0.05435767349157456,
   "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": 15.648,
       "eval_steps_per_second": 3.919,
       "step": 100
+    },
+    {
+      "epoch": 0.03986229389382134,
+      "grad_norm": 1.4899482727050781,
+      "learning_rate": 0.00019709518213718787,
+      "loss": 2.4953,
+      "step": 110
+    },
+    {
+      "epoch": 0.043486138793259646,
+      "grad_norm": 1.4345935583114624,
+      "learning_rate": 0.00019394360206446948,
+      "loss": 2.3727,
+      "step": 120
+    },
+    {
+      "epoch": 0.047109983692697956,
+      "grad_norm": 1.8238986730575562,
+      "learning_rate": 0.00019034895390411186,
+      "loss": 2.4042,
+      "step": 130
+    },
+    {
+      "epoch": 0.05073382859213626,
+      "grad_norm": 2.5793519020080566,
+      "learning_rate": 0.0001863287504206196,
+      "loss": 2.3586,
+      "step": 140
+    },
+    {
+      "epoch": 0.05435767349157456,
+      "grad_norm": 5.261249542236328,
+      "learning_rate": 0.00018190257764125471,
+      "loss": 2.2702,
+      "step": 150
+    },
+    {
+      "epoch": 0.05435767349157456,
+      "eval_loss": 2.756633758544922,
+      "eval_runtime": 74.3689,
+      "eval_samples_per_second": 15.625,
+      "eval_steps_per_second": 3.913,
+      "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": 1.932783022768128e+16,
+  "total_flos": 2.903888639085773e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null