Training in progress, step 1500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:36fc532e459997e1f3cea185135d693a4255d757ec455ad56d17d0c92ef2e4aa
+oid sha256:017f0be8f8d99715ca3ec28b54209784eacd83dd0271af9c31bfde94b646e6eb
 size 14293800

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb2c193e15d8557a84bbd133a2916816bd7d637c7d73076b38cc257a16e1a85f
+oid sha256:7913747af857b0bb4337964cb26b9bdbe346330b06cd7241762a40d602d11c01
 size 7580068

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a9ae421db5a78d090f71025d41a6101ea86a922a0b4ca692805947af183c1c09
+oid sha256:d3005759b561fa9f699a68a943ec85483904a8709ac1b807c326652d75f02a21
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df814464c49d6114ced0cb2649f86ff3e3c60dbf90905c8abb1f6369d1225fb1
+oid sha256:e7592e941fa77449d9f7015724b6a3901e596c11e155596880b96def1f284283
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.1607765108346939,
-  "best_model_checkpoint": "miner_id_24/checkpoint-1200",
-  "epoch": 1.9041951800059507,
+  "best_metric": 0.15164193511009216,
+  "best_model_checkpoint": "miner_id_24/checkpoint-1500",
+  "epoch": 2.3802439750074385,
   "eval_steps": 300,
-  "global_step": 1200,
+  "global_step": 1500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -887,6 +887,224 @@
       "eval_samples_per_second": 52.614,
       "eval_steps_per_second": 26.307,
       "step": 1200
+    },
+    {
+      "epoch": 1.920063473172667,
+      "grad_norm": 0.09009451419115067,
+      "learning_rate": 4.7745751406263165e-06,
+      "loss": 2.4052,
+      "step": 1210
+    },
+    {
+      "epoch": 1.9359317663393831,
+      "grad_norm": 0.17990677058696747,
+      "learning_rate": 4.460970818476718e-06,
+      "loss": 1.4775,
+      "step": 1220
+    },
+    {
+      "epoch": 1.9518000595060994,
+      "grad_norm": 0.12437444925308228,
+      "learning_rate": 4.15700759802175e-06,
+      "loss": 0.324,
+      "step": 1230
+    },
+    {
+      "epoch": 1.9676683526728156,
+      "grad_norm": 10.639348983764648,
+      "learning_rate": 3.862828160801707e-06,
+      "loss": 5.8774,
+      "step": 1240
+    },
+    {
+      "epoch": 1.983536645839532,
+      "grad_norm": 2.456026554107666,
+      "learning_rate": 3.578570595810274e-06,
+      "loss": 1.141,
+      "step": 1250
+    },
+    {
+      "epoch": 1.999404939006248,
+      "grad_norm": 0.1565844863653183,
+      "learning_rate": 3.3043683346749647e-06,
+      "loss": 0.5981,
+      "step": 1260
+    },
+    {
+      "epoch": 2.0152732321729645,
+      "grad_norm": 0.07377956062555313,
+      "learning_rate": 3.040350089023844e-06,
+      "loss": 9.0139,
+      "step": 1270
+    },
+    {
+      "epoch": 2.0311415253396805,
+      "grad_norm": 0.08124233037233353,
+      "learning_rate": 2.786639790067719e-06,
+      "loss": 0.0013,
+      "step": 1280
+    },
+    {
+      "epoch": 2.047009818506397,
+      "grad_norm": 2.749391794204712,
+      "learning_rate": 2.543356530426394e-06,
+      "loss": 3.0041,
+      "step": 1290
+    },
+    {
+      "epoch": 2.062878111673113,
+      "grad_norm": 0.2070658802986145,
+      "learning_rate": 2.310614508226078e-06,
+      "loss": 1.6242,
+      "step": 1300
+    },
+    {
+      "epoch": 2.0787464048398294,
+      "grad_norm": 0.257577121257782,
+      "learning_rate": 2.0885229734943502e-06,
+      "loss": 0.7873,
+      "step": 1310
+    },
+    {
+      "epoch": 2.094614698006546,
+      "grad_norm": 0.10661296546459198,
+      "learning_rate": 1.8771861768777792e-06,
+      "loss": 10.207,
+      "step": 1320
+    },
+    {
+      "epoch": 2.110482991173262,
+      "grad_norm": 0.10888644307851791,
+      "learning_rate": 1.67670332070623e-06,
+      "loss": 0.0016,
+      "step": 1330
+    },
+    {
+      "epoch": 2.1263512843399783,
+      "grad_norm": 0.3325011134147644,
+      "learning_rate": 1.4871685124269008e-06,
+      "loss": 1.2929,
+      "step": 1340
+    },
+    {
+      "epoch": 2.1422195775066943,
+      "grad_norm": 0.17756295204162598,
+      "learning_rate": 1.3086707204299414e-06,
+      "loss": 0.5661,
+      "step": 1350
+    },
+    {
+      "epoch": 2.158087870673411,
+      "grad_norm": 0.14974133670330048,
+      "learning_rate": 1.141293732286297e-06,
+      "loss": 0.1841,
+      "step": 1360
+    },
+    {
+      "epoch": 2.173956163840127,
+      "grad_norm": 0.03758949786424637,
+      "learning_rate": 9.851161154175337e-07,
+      "loss": 9.0455,
+      "step": 1370
+    },
+    {
+      "epoch": 2.1898244570068433,
+      "grad_norm": 0.11239814013242722,
+      "learning_rate": 8.402111802159412e-07,
+      "loss": 0.0012,
+      "step": 1380
+    },
+    {
+      "epoch": 2.2056927501735593,
+      "grad_norm": 8.04785442352295,
+      "learning_rate": 7.06646945632361e-07,
+      "loss": 1.5707,
+      "step": 1390
+    },
+    {
+      "epoch": 2.2215610433402757,
+      "grad_norm": 0.21494823694229126,
+      "learning_rate": 5.844861072478336e-07,
+      "loss": 1.3041,
+      "step": 1400
+    },
+    {
+      "epoch": 2.237429336506992,
+      "grad_norm": 0.06655854731798172,
+      "learning_rate": 4.7378600784402093e-07,
+      "loss": 0.0125,
+      "step": 1410
+    },
+    {
+      "epoch": 2.253297629673708,
+      "grad_norm": 0.04861687868833542,
+      "learning_rate": 3.745986104862903e-07,
+      "loss": 7.9542,
+      "step": 1420
+    },
+    {
+      "epoch": 2.2691659228404246,
+      "grad_norm": 0.28239357471466064,
+      "learning_rate": 2.869704741320478e-07,
+      "loss": 0.0149,
+      "step": 1430
+    },
+    {
+      "epoch": 2.2850342160071406,
+      "grad_norm": 3.703979730606079,
+      "learning_rate": 2.1094273177576507e-07,
+      "loss": 2.4253,
+      "step": 1440
+    },
+    {
+      "epoch": 2.300902509173857,
+      "grad_norm": 12.898768424987793,
+      "learning_rate": 1.4655107114101007e-07,
+      "loss": 1.5493,
+      "step": 1450
+    },
+    {
+      "epoch": 2.316770802340573,
+      "grad_norm": 0.1730128526687622,
+      "learning_rate": 9.382571792846961e-08,
+      "loss": 0.0024,
+      "step": 1460
+    },
+    {
+      "epoch": 2.3326390955072895,
+      "grad_norm": 0.5157439708709717,
+      "learning_rate": 5.279142162789019e-08,
+      "loss": 10.4643,
+      "step": 1470
+    },
+    {
+      "epoch": 2.3485073886740055,
+      "grad_norm": 0.039575349539518356,
+      "learning_rate": 2.3467443900582198e-08,
+      "loss": 0.0022,
+      "step": 1480
+    },
+    {
+      "epoch": 2.364375681840722,
+      "grad_norm": 6.6210455894470215,
+      "learning_rate": 5.86754953789681e-09,
+      "loss": 2.0089,
+      "step": 1490
+    },
+    {
+      "epoch": 2.3802439750074385,
+      "grad_norm": 0.16222581267356873,
+      "learning_rate": 0.0,
+      "loss": 0.4287,
+      "step": 1500
+    },
+    {
+      "epoch": 2.3802439750074385,
+      "eval_loss": 0.15164193511009216,
+      "eval_runtime": 20.031,
+      "eval_samples_per_second": 53.018,
+      "eval_steps_per_second": 26.509,
+      "step": 1500
     }
   ],
   "logging_steps": 10,
@@ -910,12 +1128,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 5.30181159691223e+16,
+  "total_flos": 6.594947874973286e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null