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:aeebdaa98302c33d966b7357c67e05bd7e65bfb1a11b4d4d73a84a0cea80f4fd
+oid sha256:a60df2d43eea647390400c4daeeec04a2d4a70113f14753f65beec30dcb09a74
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7976373e2a7cedc8585a1e026e436dd8ed13d6f8c36aae8c3f0b3ded288ea482
+oid sha256:6bff178a5f5b5dcf562a5ad3780a8df0127f808a8e7cdecdd98dbb56262cd0f9
 size 320194002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:22d071bbca013848170aa6bc4c576d735ecf57f53d4bde328bde3b21442f8bec
+oid sha256:c37a2a3d34b699e0c66be82326f1a4866032b8953cc231b4af63104f66ac5481
 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": 0.5663574934005737,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.21505376344086022,
+  "best_metric": 0.45772695541381836,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.43010752688172044,
   "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": 3.878,
       "eval_steps_per_second": 1.979,
       "step": 25
+    },
+    {
+      "epoch": 0.22365591397849463,
+      "grad_norm": 10.534406661987305,
+      "learning_rate": 0.0001,
+      "loss": 3.744,
+      "step": 26
+    },
+    {
+      "epoch": 0.23225806451612904,
+      "grad_norm": 6.486779689788818,
+      "learning_rate": 9.345968707698569e-05,
+      "loss": 1.9199,
+      "step": 27
+    },
+    {
+      "epoch": 0.24086021505376345,
+      "grad_norm": 9.214913368225098,
+      "learning_rate": 8.694738077799488e-05,
+      "loss": 2.5619,
+      "step": 28
+    },
+    {
+      "epoch": 0.24946236559139784,
+      "grad_norm": 10.509803771972656,
+      "learning_rate": 8.049096779838719e-05,
+      "loss": 2.3158,
+      "step": 29
+    },
+    {
+      "epoch": 0.25806451612903225,
+      "grad_norm": 9.7291841506958,
+      "learning_rate": 7.411809548974792e-05,
+      "loss": 3.2134,
+      "step": 30
+    },
+    {
+      "epoch": 0.26666666666666666,
+      "grad_norm": 11.299739837646484,
+      "learning_rate": 6.785605346968386e-05,
+      "loss": 3.0947,
+      "step": 31
+    },
+    {
+      "epoch": 0.2752688172043011,
+      "grad_norm": 8.215875625610352,
+      "learning_rate": 6.173165676349103e-05,
+      "loss": 2.1678,
+      "step": 32
+    },
+    {
+      "epoch": 0.2838709677419355,
+      "grad_norm": 4.7149434089660645,
+      "learning_rate": 5.577113097809989e-05,
+      "loss": 1.4623,
+      "step": 33
+    },
+    {
+      "epoch": 0.2924731182795699,
+      "grad_norm": 5.680448532104492,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 1.5995,
+      "step": 34
+    },
+    {
+      "epoch": 0.3010752688172043,
+      "grad_norm": 8.507613182067871,
+      "learning_rate": 4.444297669803981e-05,
+      "loss": 1.7745,
+      "step": 35
+    },
+    {
+      "epoch": 0.3096774193548387,
+      "grad_norm": 4.99240779876709,
+      "learning_rate": 3.9123857099127936e-05,
+      "loss": 1.0125,
+      "step": 36
+    },
+    {
+      "epoch": 0.31827956989247314,
+      "grad_norm": 5.999588489532471,
+      "learning_rate": 3.406541848999312e-05,
+      "loss": 1.3784,
+      "step": 37
+    },
+    {
+      "epoch": 0.32688172043010755,
+      "grad_norm": 5.480283260345459,
+      "learning_rate": 2.9289321881345254e-05,
+      "loss": 2.107,
+      "step": 38
+    },
+    {
+      "epoch": 0.33548387096774196,
+      "grad_norm": 3.4129068851470947,
+      "learning_rate": 2.4816019252102273e-05,
+      "loss": 0.8842,
+      "step": 39
+    },
+    {
+      "epoch": 0.34408602150537637,
+      "grad_norm": 4.122173309326172,
+      "learning_rate": 2.0664665970876496e-05,
+      "loss": 1.2184,
+      "step": 40
+    },
+    {
+      "epoch": 0.35268817204301073,
+      "grad_norm": 4.307172775268555,
+      "learning_rate": 1.6853038769745467e-05,
+      "loss": 1.2531,
+      "step": 41
+    },
+    {
+      "epoch": 0.36129032258064514,
+      "grad_norm": 3.4182629585266113,
+      "learning_rate": 1.339745962155613e-05,
+      "loss": 1.0525,
+      "step": 42
+    },
+    {
+      "epoch": 0.36989247311827955,
+      "grad_norm": 6.133404731750488,
+      "learning_rate": 1.0312725846731175e-05,
+      "loss": 1.8617,
+      "step": 43
+    },
+    {
+      "epoch": 0.37849462365591396,
+      "grad_norm": 4.430727958679199,
+      "learning_rate": 7.612046748871327e-06,
+      "loss": 1.5402,
+      "step": 44
+    },
+    {
+      "epoch": 0.3870967741935484,
+      "grad_norm": 6.002130031585693,
+      "learning_rate": 5.306987050489442e-06,
+      "loss": 1.6745,
+      "step": 45
+    },
+    {
+      "epoch": 0.3956989247311828,
+      "grad_norm": 5.143777370452881,
+      "learning_rate": 3.40741737109318e-06,
+      "loss": 1.7129,
+      "step": 46
+    },
+    {
+      "epoch": 0.4043010752688172,
+      "grad_norm": 5.8984551429748535,
+      "learning_rate": 1.921471959676957e-06,
+      "loss": 1.8639,
+      "step": 47
+    },
+    {
+      "epoch": 0.4129032258064516,
+      "grad_norm": 6.393105506896973,
+      "learning_rate": 8.555138626189618e-07,
+      "loss": 2.57,
+      "step": 48
+    },
+    {
+      "epoch": 0.421505376344086,
+      "grad_norm": 5.643848896026611,
+      "learning_rate": 2.141076761396521e-07,
+      "loss": 1.3948,
+      "step": 49
+    },
+    {
+      "epoch": 0.43010752688172044,
+      "grad_norm": 4.860955715179443,
+      "learning_rate": 0.0,
+      "loss": 1.7264,
+      "step": 50
+    },
+    {
+      "epoch": 0.43010752688172044,
+      "eval_loss": 0.45772695541381836,
+      "eval_runtime": 12.6513,
+      "eval_samples_per_second": 3.873,
+      "eval_steps_per_second": 1.976,
+      "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": 3.26729100951552e+16,
+  "total_flos": 6.53458201903104e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null