Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:68134253d2389b24fd95c0ae0c7adbdd4249bbf62bf5c3de64018611f985f5fb
+oid sha256:fc06e839d50fc18120aba4f1cbcaf164c42d0a5593d2d963bba8c1b50bee33cc
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c88bd1e5f2b0b00d43aa8a7422c5113136f878cee8cc3b50ca3865218908e07f
+oid sha256:19ad0bf02d7f11d12366ce2c107e4638f2442428c3b652e479207e4507c7be84
 size 341314196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b4db7d1e27af765f2d084f464bd481c0d8fc79b5eaacc1c1a9b9a14e9589867
+oid sha256:ca22520008fa903f8d99865e7a7f87625cf0ba7bb062d2f1dba8a0b462054390
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb15fdd4c0ab874f4afa0ea95fae119cbc74554df5fbe92ab825fe27063eaa04
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 2.109341621398926,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.14104372355430184,
+  "epoch": 0.2820874471086037,
   "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": 23.308,
       "eval_steps_per_second": 2.962,
       "step": 25
+    },
+    {
+      "epoch": 0.1466854724964739,
+      "grad_norm": 3.798450231552124,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 8.1461,
+      "step": 26
+    },
+    {
+      "epoch": 0.152327221438646,
+      "grad_norm": 3.666520833969116,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 8.5359,
+      "step": 27
+    },
+    {
+      "epoch": 0.15796897038081806,
+      "grad_norm": 3.717135190963745,
+      "learning_rate": 4.825502516487497e-05,
+      "loss": 8.4781,
+      "step": 28
+    },
+    {
+      "epoch": 0.16361071932299012,
+      "grad_norm": 3.7907662391662598,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 8.3698,
+      "step": 29
+    },
+    {
+      "epoch": 0.1692524682651622,
+      "grad_norm": 3.6420655250549316,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 8.2384,
+      "step": 30
+    },
+    {
+      "epoch": 0.17489421720733428,
+      "grad_norm": 3.860008478164673,
+      "learning_rate": 3.790390522001662e-05,
+      "loss": 8.2665,
+      "step": 31
+    },
+    {
+      "epoch": 0.18053596614950634,
+      "grad_norm": 3.6068201065063477,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 8.0287,
+      "step": 32
+    },
+    {
+      "epoch": 0.1861777150916784,
+      "grad_norm": 3.9249439239501953,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 8.5235,
+      "step": 33
+    },
+    {
+      "epoch": 0.1918194640338505,
+      "grad_norm": 3.696990728378296,
+      "learning_rate": 2.8081442660546125e-05,
+      "loss": 8.3245,
+      "step": 34
+    },
+    {
+      "epoch": 0.19746121297602257,
+      "grad_norm": 3.890031576156616,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 8.3047,
+      "step": 35
+    },
+    {
+      "epoch": 0.20310296191819463,
+      "grad_norm": 3.9633665084838867,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 8.4369,
+      "step": 36
+    },
+    {
+      "epoch": 0.20874471086036672,
+      "grad_norm": 3.764096736907959,
+      "learning_rate": 1.9216926233717085e-05,
+      "loss": 8.1852,
+      "step": 37
+    },
+    {
+      "epoch": 0.2143864598025388,
+      "grad_norm": 3.8843536376953125,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 8.1857,
+      "step": 38
+    },
+    {
+      "epoch": 0.22002820874471085,
+      "grad_norm": 3.861175298690796,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 8.0496,
+      "step": 39
+    },
+    {
+      "epoch": 0.22566995768688294,
+      "grad_norm": 3.900156259536743,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 7.8856,
+      "step": 40
+    },
+    {
+      "epoch": 0.231311706629055,
+      "grad_norm": 4.102020263671875,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 8.3495,
+      "step": 41
+    },
+    {
+      "epoch": 0.23695345557122707,
+      "grad_norm": 4.508086204528809,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 8.3085,
+      "step": 42
+    },
+    {
+      "epoch": 0.24259520451339917,
+      "grad_norm": 5.05258321762085,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 8.6964,
+      "step": 43
+    },
+    {
+      "epoch": 0.24823695345557123,
+      "grad_norm": 5.212568283081055,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 8.0306,
+      "step": 44
+    },
+    {
+      "epoch": 0.2538787023977433,
+      "grad_norm": 8.90238094329834,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 8.5885,
+      "step": 45
+    },
+    {
+      "epoch": 0.25952045133991536,
+      "grad_norm": 9.267271995544434,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 8.831,
+      "step": 46
+    },
+    {
+      "epoch": 0.2651622002820874,
+      "grad_norm": 7.736325263977051,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 8.9213,
+      "step": 47
+    },
+    {
+      "epoch": 0.27080394922425954,
+      "grad_norm": 8.406316757202148,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 8.7541,
+      "step": 48
+    },
+    {
+      "epoch": 0.2764456981664316,
+      "grad_norm": 8.496612548828125,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 8.6838,
+      "step": 49
+    },
+    {
+      "epoch": 0.2820874471086037,
+      "grad_norm": 7.6794891357421875,
+      "learning_rate": 0.0,
+      "loss": 8.8579,
+      "step": 50
+    },
+    {
+      "epoch": 0.2820874471086037,
+      "eval_loss": 2.1287615299224854,
+      "eval_runtime": 12.5797,
+      "eval_samples_per_second": 23.769,
+      "eval_steps_per_second": 3.021,
+      "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": 2.146535668187136e+16,
+  "total_flos": 4.293071336374272e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null