Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:563fd7ccb26c297691bf71e4f62a18f0e565c7f0b3f466b6f0c3a264bb5b9250
+oid sha256:1e31f8cfe0024a4da2763f3a55d331e01735d640b24d6e350b69361abaaa4f7b
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b1835af6db358172f284a2aae4890ce5aa55d968db1d192adba6e29e33aa15df
+oid sha256:5e4da8e51e365ad74c85877bbb464e6fcc191dcc9b44346e9140a3ef130d9b0e
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e51b44f99ff87608ce8ff6ee4b2c245fc027a3d6d2fe73381cc7aa0d42859b0
+oid sha256:446d20ed2c5e285231636d66cf45117861a1b763b188166fb21a8343e0d4ab1d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ea7ff16b0c30a914eb0d145e3fb06ff9027c6cd2408e766ce8a09accab89a4d
+oid sha256:e69e2b49ea642509f0c688c16fb190b7cf27dac0a18903a5e2d1467d0343d8b8
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.04647363722324371,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.0029315196998123826,
+  "epoch": 0.005863039399624765,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,189 @@
       "eval_samples_per_second": 2.842,
       "eval_steps_per_second": 1.422,
       "step": 25
+    },
+    {
+      "epoch": 0.003048780487804878,
+      "grad_norm": 1.4755140542984009,
+      "learning_rate": 0.0001,
+      "loss": 0.04,
+      "step": 26
+    },
+    {
+      "epoch": 0.0031660412757973733,
+      "grad_norm": 0.9295901656150818,
+      "learning_rate": 9.345968707698569e-05,
+      "loss": 0.0678,
+      "step": 27
+    },
+    {
+      "epoch": 0.003283302063789869,
+      "grad_norm": 0.893139660358429,
+      "learning_rate": 8.694738077799488e-05,
+      "loss": 0.086,
+      "step": 28
+    },
+    {
+      "epoch": 0.003400562851782364,
+      "grad_norm": 0.3992539346218109,
+      "learning_rate": 8.049096779838719e-05,
+      "loss": 0.0083,
+      "step": 29
+    },
+    {
+      "epoch": 0.003517823639774859,
+      "grad_norm": 0.5577191114425659,
+      "learning_rate": 7.411809548974792e-05,
+      "loss": 0.0452,
+      "step": 30
+    },
+    {
+      "epoch": 0.0036350844277673548,
+      "grad_norm": 0.5358323454856873,
+      "learning_rate": 6.785605346968386e-05,
+      "loss": 0.0179,
+      "step": 31
+    },
+    {
+      "epoch": 0.00375234521575985,
+      "grad_norm": 1.5596437454223633,
+      "learning_rate": 6.173165676349103e-05,
+      "loss": 0.0734,
+      "step": 32
+    },
+    {
+      "epoch": 0.003869606003752345,
+      "grad_norm": 0.3839088976383209,
+      "learning_rate": 5.577113097809989e-05,
+      "loss": 0.0078,
+      "step": 33
+    },
+    {
+      "epoch": 0.00398686679174484,
+      "grad_norm": 0.25893858075141907,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 0.0079,
+      "step": 34
+    },
+    {
+      "epoch": 0.004104127579737336,
+      "grad_norm": 0.04539264738559723,
+      "learning_rate": 4.444297669803981e-05,
+      "loss": 0.0016,
+      "step": 35
+    },
+    {
+      "epoch": 0.004221388367729831,
+      "grad_norm": 0.35133206844329834,
+      "learning_rate": 3.9123857099127936e-05,
+      "loss": 0.0107,
+      "step": 36
+    },
+    {
+      "epoch": 0.0043386491557223265,
+      "grad_norm": 0.2603636085987091,
+      "learning_rate": 3.406541848999312e-05,
+      "loss": 0.0058,
+      "step": 37
+    },
+    {
+      "epoch": 0.004455909943714822,
+      "grad_norm": 0.9423990249633789,
+      "learning_rate": 2.9289321881345254e-05,
+      "loss": 0.0551,
+      "step": 38
+    },
+    {
+      "epoch": 0.004573170731707317,
+      "grad_norm": 0.5868332386016846,
+      "learning_rate": 2.4816019252102273e-05,
+      "loss": 0.0317,
+      "step": 39
+    },
+    {
+      "epoch": 0.004690431519699813,
+      "grad_norm": 0.42275911569595337,
+      "learning_rate": 2.0664665970876496e-05,
+      "loss": 0.0522,
+      "step": 40
+    },
+    {
+      "epoch": 0.004807692307692308,
+      "grad_norm": 2.300081491470337,
+      "learning_rate": 1.6853038769745467e-05,
+      "loss": 0.0088,
+      "step": 41
+    },
+    {
+      "epoch": 0.004924953095684803,
+      "grad_norm": 0.07799982279539108,
+      "learning_rate": 1.339745962155613e-05,
+      "loss": 0.0022,
+      "step": 42
+    },
+    {
+      "epoch": 0.005042213883677298,
+      "grad_norm": 0.6381279230117798,
+      "learning_rate": 1.0312725846731175e-05,
+      "loss": 0.0158,
+      "step": 43
+    },
+    {
+      "epoch": 0.005159474671669793,
+      "grad_norm": 2.301848888397217,
+      "learning_rate": 7.612046748871327e-06,
+      "loss": 0.085,
+      "step": 44
+    },
+    {
+      "epoch": 0.0052767354596622885,
+      "grad_norm": 0.0752975270152092,
+      "learning_rate": 5.306987050489442e-06,
+      "loss": 0.0022,
+      "step": 45
+    },
+    {
+      "epoch": 0.0053939962476547846,
+      "grad_norm": 0.47218722105026245,
+      "learning_rate": 3.40741737109318e-06,
+      "loss": 0.0113,
+      "step": 46
+    },
+    {
+      "epoch": 0.00551125703564728,
+      "grad_norm": 1.4857302904129028,
+      "learning_rate": 1.921471959676957e-06,
+      "loss": 0.0386,
+      "step": 47
+    },
+    {
+      "epoch": 0.005628517823639775,
+      "grad_norm": 2.381000518798828,
+      "learning_rate": 8.555138626189618e-07,
+      "loss": 0.1459,
+      "step": 48
+    },
+    {
+      "epoch": 0.00574577861163227,
+      "grad_norm": 2.9941911697387695,
+      "learning_rate": 2.141076761396521e-07,
+      "loss": 0.2355,
+      "step": 49
+    },
+    {
+      "epoch": 0.005863039399624765,
+      "grad_norm": 6.046911716461182,
+      "learning_rate": 0.0,
+      "loss": 0.2114,
+      "step": 50
+    },
+    {
+      "epoch": 0.005863039399624765,
+      "eval_loss": 0.0718505010008812,
+      "eval_runtime": 1264.6821,
+      "eval_samples_per_second": 2.839,
+      "eval_steps_per_second": 1.42,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -212,7 +395,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 0
+        "early_stopping_patience_counter": 1
       }
     },
     "TrainerControl": {
@@ -221,12 +404,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 3.70943641780224e+16,
+  "total_flos": 7.41887283560448e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null