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:f260250549c16c3ecb64bd2819036cfab57f8c19a3bfa45cac88ee5cfe46de33
+oid sha256:e2f6e5cd47eedbc53074e92ae36566c891c26c3fe75602f03485a870a2a0ce5d
 size 275341720

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6848bcafac4fff67c8cc70ca10dcc225bbfbb8573518329f8899cf915a48bd8a
+oid sha256:18b5c68d8572a9e68bd871f944a924bf346dae412f3e3759bf059b5d651f0682
 size 551070514

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f0a2d9ca1a9e66ef28b5cf11a8e98f2820581d89e2108427d4b536e634ff3ca
+oid sha256:9e305ab3ea564838740d2f6c959f7078a99215c6e511f8be412e1e9a1c5e1b70
 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": 0.17134732007980347,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.0008518903446748335,
+  "best_metric": 0.06993943452835083,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.001703780689349667,
   "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": 1.575,
       "eval_steps_per_second": 0.788,
       "step": 25
+    },
+    {
+      "epoch": 0.0008859659584618268,
+      "grad_norm": 0.8896116018295288,
+      "learning_rate": 0.0001,
+      "loss": 0.0399,
+      "step": 26
+    },
+    {
+      "epoch": 0.0009200415722488202,
+      "grad_norm": 1.7912120819091797,
+      "learning_rate": 9.345968707698569e-05,
+      "loss": 0.1075,
+      "step": 27
+    },
+    {
+      "epoch": 0.0009541171860358135,
+      "grad_norm": 2.0380702018737793,
+      "learning_rate": 8.694738077799488e-05,
+      "loss": 0.1464,
+      "step": 28
+    },
+    {
+      "epoch": 0.0009881927998228069,
+      "grad_norm": 2.9125843048095703,
+      "learning_rate": 8.049096779838719e-05,
+      "loss": 0.1015,
+      "step": 29
+    },
+    {
+      "epoch": 0.0010222684136098,
+      "grad_norm": 1.1429842710494995,
+      "learning_rate": 7.411809548974792e-05,
+      "loss": 0.0189,
+      "step": 30
+    },
+    {
+      "epoch": 0.0010563440273967935,
+      "grad_norm": 2.3157050609588623,
+      "learning_rate": 6.785605346968386e-05,
+      "loss": 0.0953,
+      "step": 31
+    },
+    {
+      "epoch": 0.0010904196411837869,
+      "grad_norm": 3.368072509765625,
+      "learning_rate": 6.173165676349103e-05,
+      "loss": 0.1659,
+      "step": 32
+    },
+    {
+      "epoch": 0.0011244952549707803,
+      "grad_norm": 1.4271526336669922,
+      "learning_rate": 5.577113097809989e-05,
+      "loss": 0.0579,
+      "step": 33
+    },
+    {
+      "epoch": 0.0011585708687577734,
+      "grad_norm": 0.96360844373703,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 0.0371,
+      "step": 34
+    },
+    {
+      "epoch": 0.0011926464825447668,
+      "grad_norm": 1.0970512628555298,
+      "learning_rate": 4.444297669803981e-05,
+      "loss": 0.0368,
+      "step": 35
+    },
+    {
+      "epoch": 0.0012267220963317602,
+      "grad_norm": 0.5222811698913574,
+      "learning_rate": 3.9123857099127936e-05,
+      "loss": 0.014,
+      "step": 36
+    },
+    {
+      "epoch": 0.0012607977101187534,
+      "grad_norm": 2.5938470363616943,
+      "learning_rate": 3.406541848999312e-05,
+      "loss": 0.0974,
+      "step": 37
+    },
+    {
+      "epoch": 0.0012948733239057468,
+      "grad_norm": 0.8170644044876099,
+      "learning_rate": 2.9289321881345254e-05,
+      "loss": 0.0307,
+      "step": 38
+    },
+    {
+      "epoch": 0.0013289489376927402,
+      "grad_norm": 0.9838296175003052,
+      "learning_rate": 2.4816019252102273e-05,
+      "loss": 0.0276,
+      "step": 39
+    },
+    {
+      "epoch": 0.0013630245514797336,
+      "grad_norm": 2.9819869995117188,
+      "learning_rate": 2.0664665970876496e-05,
+      "loss": 0.1533,
+      "step": 40
+    },
+    {
+      "epoch": 0.0013971001652667268,
+      "grad_norm": 2.393613576889038,
+      "learning_rate": 1.6853038769745467e-05,
+      "loss": 0.1044,
+      "step": 41
+    },
+    {
+      "epoch": 0.0014311757790537202,
+      "grad_norm": 1.6655608415603638,
+      "learning_rate": 1.339745962155613e-05,
+      "loss": 0.048,
+      "step": 42
+    },
+    {
+      "epoch": 0.0014652513928407136,
+      "grad_norm": 16.368389129638672,
+      "learning_rate": 1.0312725846731175e-05,
+      "loss": 0.0653,
+      "step": 43
+    },
+    {
+      "epoch": 0.0014993270066277068,
+      "grad_norm": 2.2346484661102295,
+      "learning_rate": 7.612046748871327e-06,
+      "loss": 0.167,
+      "step": 44
+    },
+    {
+      "epoch": 0.0015334026204147002,
+      "grad_norm": 2.2778067588806152,
+      "learning_rate": 5.306987050489442e-06,
+      "loss": 0.0613,
+      "step": 45
+    },
+    {
+      "epoch": 0.0015674782342016936,
+      "grad_norm": 0.7512469291687012,
+      "learning_rate": 3.40741737109318e-06,
+      "loss": 0.041,
+      "step": 46
+    },
+    {
+      "epoch": 0.001601553847988687,
+      "grad_norm": 4.560179710388184,
+      "learning_rate": 1.921471959676957e-06,
+      "loss": 0.0939,
+      "step": 47
+    },
+    {
+      "epoch": 0.0016356294617756802,
+      "grad_norm": 9.43427848815918,
+      "learning_rate": 8.555138626189618e-07,
+      "loss": 0.3062,
+      "step": 48
+    },
+    {
+      "epoch": 0.0016697050755626736,
+      "grad_norm": 8.753609657287598,
+      "learning_rate": 2.141076761396521e-07,
+      "loss": 0.4055,
+      "step": 49
+    },
+    {
+      "epoch": 0.001703780689349667,
+      "grad_norm": 5.78505277633667,
+      "learning_rate": 0.0,
+      "loss": 0.1969,
+      "step": 50
+    },
+    {
+      "epoch": 0.001703780689349667,
+      "eval_loss": 0.06993943452835083,
+      "eval_runtime": 7845.7082,
+      "eval_samples_per_second": 1.575,
+      "eval_steps_per_second": 0.788,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -221,12 +404,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 6.980017310190797e+16,
+  "total_flos": 1.3890925538102477e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null