Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1521bda3c0c77e04a80b61484dd7946f1a833bcf6abb9115e267309bbe9d07f1
+oid sha256:6e3d578d018cb5bf24f4874b2571641aa62d4fcc9702e6813cec5ca41d7b799e
 size 186962

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:74c6407f142ea1646df683dcceec62877688e9859494d6bd78283b0cdd898b44
+oid sha256:04bfbfbbb9a02a4fe09a9d8f86a081ccd688659b6f27b94c61d31afa8b6562c0
 size 121430

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c8327981cd4f73a1ca2eb302631cc30a64f00cbff0406ce77006eecdce4bce5
+oid sha256:2107e18af918b0a39b4e8f91d0a6ffe0d7bbe3c1481fc5bea7ec425fc56719be
 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": 6.769979000091553,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.021838829438742085,
+  "best_metric": 6.705550670623779,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.04367765887748417,
   "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": 324.343,
       "eval_steps_per_second": 162.171,
       "step": 25
+    },
+    {
+      "epoch": 0.022712382616291767,
+      "grad_norm": 1.6252830028533936,
+      "learning_rate": 0.0001,
+      "loss": 6.7582,
+      "step": 26
+    },
+    {
+      "epoch": 0.02358593579384145,
+      "grad_norm": 2.0401527881622314,
+      "learning_rate": 9.345968707698569e-05,
+      "loss": 6.793,
+      "step": 27
+    },
+    {
+      "epoch": 0.024459488971391132,
+      "grad_norm": 1.6296247243881226,
+      "learning_rate": 8.694738077799488e-05,
+      "loss": 6.7417,
+      "step": 28
+    },
+    {
+      "epoch": 0.025333042148940818,
+      "grad_norm": 1.617932677268982,
+      "learning_rate": 8.049096779838719e-05,
+      "loss": 6.7578,
+      "step": 29
+    },
+    {
+      "epoch": 0.0262065953264905,
+      "grad_norm": 1.6912728548049927,
+      "learning_rate": 7.411809548974792e-05,
+      "loss": 6.7625,
+      "step": 30
+    },
+    {
+      "epoch": 0.027080148504040183,
+      "grad_norm": 1.5618200302124023,
+      "learning_rate": 6.785605346968386e-05,
+      "loss": 6.7321,
+      "step": 31
+    },
+    {
+      "epoch": 0.027953701681589865,
+      "grad_norm": 1.3636630773544312,
+      "learning_rate": 6.173165676349103e-05,
+      "loss": 6.7536,
+      "step": 32
+    },
+    {
+      "epoch": 0.02882725485913955,
+      "grad_norm": 1.4335569143295288,
+      "learning_rate": 5.577113097809989e-05,
+      "loss": 6.6962,
+      "step": 33
+    },
+    {
+      "epoch": 0.029700808036689234,
+      "grad_norm": 1.4494646787643433,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 6.7455,
+      "step": 34
+    },
+    {
+      "epoch": 0.030574361214238916,
+      "grad_norm": 1.7528541088104248,
+      "learning_rate": 4.444297669803981e-05,
+      "loss": 6.7389,
+      "step": 35
+    },
+    {
+      "epoch": 0.0314479143917886,
+      "grad_norm": 1.5459141731262207,
+      "learning_rate": 3.9123857099127936e-05,
+      "loss": 6.7231,
+      "step": 36
+    },
+    {
+      "epoch": 0.032321467569338284,
+      "grad_norm": 1.9405611753463745,
+      "learning_rate": 3.406541848999312e-05,
+      "loss": 6.7433,
+      "step": 37
+    },
+    {
+      "epoch": 0.03319502074688797,
+      "grad_norm": 1.3924881219863892,
+      "learning_rate": 2.9289321881345254e-05,
+      "loss": 6.7279,
+      "step": 38
+    },
+    {
+      "epoch": 0.03406857392443765,
+      "grad_norm": 1.5491060018539429,
+      "learning_rate": 2.4816019252102273e-05,
+      "loss": 6.7159,
+      "step": 39
+    },
+    {
+      "epoch": 0.03494212710198733,
+      "grad_norm": 1.3519071340560913,
+      "learning_rate": 2.0664665970876496e-05,
+      "loss": 6.719,
+      "step": 40
+    },
+    {
+      "epoch": 0.035815680279537014,
+      "grad_norm": 1.2949579954147339,
+      "learning_rate": 1.6853038769745467e-05,
+      "loss": 6.7065,
+      "step": 41
+    },
+    {
+      "epoch": 0.036689233457086703,
+      "grad_norm": 1.5274921655654907,
+      "learning_rate": 1.339745962155613e-05,
+      "loss": 6.7177,
+      "step": 42
+    },
+    {
+      "epoch": 0.037562786634636386,
+      "grad_norm": 1.569133996963501,
+      "learning_rate": 1.0312725846731175e-05,
+      "loss": 6.7193,
+      "step": 43
+    },
+    {
+      "epoch": 0.03843633981218607,
+      "grad_norm": 1.6965569257736206,
+      "learning_rate": 7.612046748871327e-06,
+      "loss": 6.6912,
+      "step": 44
+    },
+    {
+      "epoch": 0.03930989298973575,
+      "grad_norm": 1.5818424224853516,
+      "learning_rate": 5.306987050489442e-06,
+      "loss": 6.7327,
+      "step": 45
+    },
+    {
+      "epoch": 0.04018344616728543,
+      "grad_norm": 1.557110071182251,
+      "learning_rate": 3.40741737109318e-06,
+      "loss": 6.7336,
+      "step": 46
+    },
+    {
+      "epoch": 0.041056999344835116,
+      "grad_norm": 1.4650180339813232,
+      "learning_rate": 1.921471959676957e-06,
+      "loss": 6.7215,
+      "step": 47
+    },
+    {
+      "epoch": 0.0419305525223848,
+      "grad_norm": 1.3557387590408325,
+      "learning_rate": 8.555138626189618e-07,
+      "loss": 6.7157,
+      "step": 48
+    },
+    {
+      "epoch": 0.04280410569993448,
+      "grad_norm": 1.563228964805603,
+      "learning_rate": 2.141076761396521e-07,
+      "loss": 6.6898,
+      "step": 49
+    },
+    {
+      "epoch": 0.04367765887748417,
+      "grad_norm": 1.5504145622253418,
+      "learning_rate": 0.0,
+      "loss": 6.707,
+      "step": 50
+    },
+    {
+      "epoch": 0.04367765887748417,
+      "eval_loss": 6.705550670623779,
+      "eval_runtime": 1.4939,
+      "eval_samples_per_second": 322.655,
+      "eval_steps_per_second": 161.328,
+      "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": 294651494400.0,
+  "total_flos": 589302988800.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null