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:f386e94f3ed6e428682b4abb7a2110f007379bfff6da47fbd6b332af14e20ce2
+oid sha256:76526ea305e376b5fafc484d3f52d21e4c519f16c47a621a683becbff94e462d
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e8bef72547906782aa8128e5a495baeddc8a708171cd2c30e9e52592455a119b
+oid sha256:6cb9cff90e6d550081512f533ea157d42726442731cb2893c2bbda3bffc101e0
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:762abef99eec69ebb337fcee02a5803b1c48d882076e39db9aaa7253936d8969
+oid sha256:142dab6d5ed4f166afa5dc00c857f7833c43f10b86264cf53626779f551b1886
 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": 0.23284952342510223,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.0021108179419525065,
+  "best_metric": 0.0934281200170517,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.004221635883905013,
   "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": 2.837,
       "eval_steps_per_second": 1.419,
       "step": 25
+    },
+    {
+      "epoch": 0.002195250659630607,
+      "grad_norm": 4.415905952453613,
+      "learning_rate": 0.0001,
+      "loss": 0.2306,
+      "step": 26
+    },
+    {
+      "epoch": 0.002279683377308707,
+      "grad_norm": 2.082292318344116,
+      "learning_rate": 9.345968707698569e-05,
+      "loss": 0.0689,
+      "step": 27
+    },
+    {
+      "epoch": 0.0023641160949868074,
+      "grad_norm": 0.1635982245206833,
+      "learning_rate": 8.694738077799488e-05,
+      "loss": 0.0034,
+      "step": 28
+    },
+    {
+      "epoch": 0.0024485488126649076,
+      "grad_norm": 5.064727306365967,
+      "learning_rate": 8.049096779838719e-05,
+      "loss": 0.1768,
+      "step": 29
+    },
+    {
+      "epoch": 0.002532981530343008,
+      "grad_norm": 1.381342887878418,
+      "learning_rate": 7.411809548974792e-05,
+      "loss": 0.0235,
+      "step": 30
+    },
+    {
+      "epoch": 0.002617414248021108,
+      "grad_norm": 2.433394193649292,
+      "learning_rate": 6.785605346968386e-05,
+      "loss": 0.0458,
+      "step": 31
+    },
+    {
+      "epoch": 0.0027018469656992085,
+      "grad_norm": 0.16443267464637756,
+      "learning_rate": 6.173165676349103e-05,
+      "loss": 0.0031,
+      "step": 32
+    },
+    {
+      "epoch": 0.0027862796833773087,
+      "grad_norm": 5.821410179138184,
+      "learning_rate": 5.577113097809989e-05,
+      "loss": 0.1666,
+      "step": 33
+    },
+    {
+      "epoch": 0.002870712401055409,
+      "grad_norm": 0.13388852775096893,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 0.0039,
+      "step": 34
+    },
+    {
+      "epoch": 0.0029551451187335093,
+      "grad_norm": 3.2496159076690674,
+      "learning_rate": 4.444297669803981e-05,
+      "loss": 0.2075,
+      "step": 35
+    },
+    {
+      "epoch": 0.0030395778364116096,
+      "grad_norm": 0.4470334053039551,
+      "learning_rate": 3.9123857099127936e-05,
+      "loss": 0.0083,
+      "step": 36
+    },
+    {
+      "epoch": 0.00312401055408971,
+      "grad_norm": 2.798367977142334,
+      "learning_rate": 3.406541848999312e-05,
+      "loss": 0.0599,
+      "step": 37
+    },
+    {
+      "epoch": 0.00320844327176781,
+      "grad_norm": 0.4125634431838989,
+      "learning_rate": 2.9289321881345254e-05,
+      "loss": 0.0067,
+      "step": 38
+    },
+    {
+      "epoch": 0.0032928759894459104,
+      "grad_norm": 5.9901323318481445,
+      "learning_rate": 2.4816019252102273e-05,
+      "loss": 0.1536,
+      "step": 39
+    },
+    {
+      "epoch": 0.0033773087071240107,
+      "grad_norm": 1.085100769996643,
+      "learning_rate": 2.0664665970876496e-05,
+      "loss": 0.0135,
+      "step": 40
+    },
+    {
+      "epoch": 0.003461741424802111,
+      "grad_norm": 8.561752319335938,
+      "learning_rate": 1.6853038769745467e-05,
+      "loss": 0.2638,
+      "step": 41
+    },
+    {
+      "epoch": 0.0035461741424802113,
+      "grad_norm": 5.0624847412109375,
+      "learning_rate": 1.339745962155613e-05,
+      "loss": 0.2491,
+      "step": 42
+    },
+    {
+      "epoch": 0.0036306068601583115,
+      "grad_norm": 3.0588884353637695,
+      "learning_rate": 1.0312725846731175e-05,
+      "loss": 0.0416,
+      "step": 43
+    },
+    {
+      "epoch": 0.003715039577836412,
+      "grad_norm": 0.11724475026130676,
+      "learning_rate": 7.612046748871327e-06,
+      "loss": 0.0022,
+      "step": 44
+    },
+    {
+      "epoch": 0.003799472295514512,
+      "grad_norm": 0.7609636783599854,
+      "learning_rate": 5.306987050489442e-06,
+      "loss": 0.0195,
+      "step": 45
+    },
+    {
+      "epoch": 0.003883905013192612,
+      "grad_norm": 0.0424778014421463,
+      "learning_rate": 3.40741737109318e-06,
+      "loss": 0.0007,
+      "step": 46
+    },
+    {
+      "epoch": 0.003968337730870713,
+      "grad_norm": 0.03648586571216583,
+      "learning_rate": 1.921471959676957e-06,
+      "loss": 0.0007,
+      "step": 47
+    },
+    {
+      "epoch": 0.0040527704485488125,
+      "grad_norm": 3.957385301589966,
+      "learning_rate": 8.555138626189618e-07,
+      "loss": 0.1444,
+      "step": 48
+    },
+    {
+      "epoch": 0.004137203166226913,
+      "grad_norm": 1.900801420211792,
+      "learning_rate": 2.141076761396521e-07,
+      "loss": 0.0386,
+      "step": 49
+    },
+    {
+      "epoch": 0.004221635883905013,
+      "grad_norm": 11.870166778564453,
+      "learning_rate": 0.0,
+      "loss": 0.8645,
+      "step": 50
+    },
+    {
+      "epoch": 0.004221635883905013,
+      "eval_loss": 0.0934281200170517,
+      "eval_runtime": 1757.9204,
+      "eval_samples_per_second": 2.837,
+      "eval_steps_per_second": 1.419,
+      "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": 3.70943641780224e+16,
+  "total_flos": 7.41887283560448e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null