Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:381a0efbd16f24c30a442dfe836d5e1167b0c53ed438aeba76b25ca1f9c5ed72
+oid sha256:d9abb324bdb6981dc8d185e28f34baa76fe30b23ff7c3390f8dc3b56c078c675
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db03af34ec718dde71d1ac30556ea46a8e467539870797ccb965f73da78bb667
+oid sha256:d0ba1efc77025619552b866d5b7dc17c39997021b37e2fcdde8e16dc60d10d49
 size 341314196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:764a6873ddb2313b79baf623bc05db7cfce490bcc328142b981cbe6e476af233
+oid sha256:663786479e3e2067e10a8ad17262c1bf863c2409883b4c5957bbc15345bc21c0
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb15fdd4c0ab874f4afa0ea95fae119cbc74554df5fbe92ab825fe27063eaa04
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.387269526720047,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.016181229773462782,
+  "best_metric": 0.3560263514518738,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.032362459546925564,
   "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": 24.253,
       "eval_steps_per_second": 3.037,
       "step": 25
+    },
+    {
+      "epoch": 0.016828478964401296,
+      "grad_norm": 6.530815124511719,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 1.2529,
+      "step": 26
+    },
+    {
+      "epoch": 0.017475728155339806,
+      "grad_norm": 5.5826096534729,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 1.3388,
+      "step": 27
+    },
+    {
+      "epoch": 0.018122977346278317,
+      "grad_norm": 5.376560211181641,
+      "learning_rate": 4.825502516487497e-05,
+      "loss": 1.2726,
+      "step": 28
+    },
+    {
+      "epoch": 0.018770226537216828,
+      "grad_norm": 5.761511325836182,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 1.1466,
+      "step": 29
+    },
+    {
+      "epoch": 0.019417475728155338,
+      "grad_norm": 5.3690266609191895,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 1.1776,
+      "step": 30
+    },
+    {
+      "epoch": 0.020064724919093852,
+      "grad_norm": 5.804825305938721,
+      "learning_rate": 3.790390522001662e-05,
+      "loss": 1.322,
+      "step": 31
+    },
+    {
+      "epoch": 0.020711974110032363,
+      "grad_norm": 7.030401229858398,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 1.3815,
+      "step": 32
+    },
+    {
+      "epoch": 0.021359223300970873,
+      "grad_norm": 6.575643062591553,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 1.2383,
+      "step": 33
+    },
+    {
+      "epoch": 0.022006472491909384,
+      "grad_norm": 7.8663763999938965,
+      "learning_rate": 2.8081442660546125e-05,
+      "loss": 1.4263,
+      "step": 34
+    },
+    {
+      "epoch": 0.022653721682847898,
+      "grad_norm": 6.203314781188965,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 1.283,
+      "step": 35
+    },
+    {
+      "epoch": 0.02330097087378641,
+      "grad_norm": 7.10265588760376,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 1.3987,
+      "step": 36
+    },
+    {
+      "epoch": 0.02394822006472492,
+      "grad_norm": 7.17543363571167,
+      "learning_rate": 1.9216926233717085e-05,
+      "loss": 1.2639,
+      "step": 37
+    },
+    {
+      "epoch": 0.02459546925566343,
+      "grad_norm": 7.629087924957275,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 1.3724,
+      "step": 38
+    },
+    {
+      "epoch": 0.02524271844660194,
+      "grad_norm": 7.922370910644531,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 1.5521,
+      "step": 39
+    },
+    {
+      "epoch": 0.025889967637540454,
+      "grad_norm": 7.377615928649902,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 1.2888,
+      "step": 40
+    },
+    {
+      "epoch": 0.026537216828478965,
+      "grad_norm": 8.394305229187012,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 1.2991,
+      "step": 41
+    },
+    {
+      "epoch": 0.027184466019417475,
+      "grad_norm": 7.840498447418213,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 1.1786,
+      "step": 42
+    },
+    {
+      "epoch": 0.027831715210355986,
+      "grad_norm": 10.578374862670898,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 1.4825,
+      "step": 43
+    },
+    {
+      "epoch": 0.0284789644012945,
+      "grad_norm": 9.716651916503906,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 1.4621,
+      "step": 44
+    },
+    {
+      "epoch": 0.02912621359223301,
+      "grad_norm": 11.308793067932129,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 1.5274,
+      "step": 45
+    },
+    {
+      "epoch": 0.02977346278317152,
+      "grad_norm": 13.435274124145508,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 1.3785,
+      "step": 46
+    },
+    {
+      "epoch": 0.030420711974110032,
+      "grad_norm": 16.50029182434082,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 1.6574,
+      "step": 47
+    },
+    {
+      "epoch": 0.031067961165048542,
+      "grad_norm": 11.9188871383667,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 1.2691,
+      "step": 48
+    },
+    {
+      "epoch": 0.03171521035598705,
+      "grad_norm": 47.62702178955078,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 1.8136,
+      "step": 49
+    },
+    {
+      "epoch": 0.032362459546925564,
+      "grad_norm": 85.18385314941406,
+      "learning_rate": 0.0,
+      "loss": 2.0817,
+      "step": 50
+    },
+    {
+      "epoch": 0.032362459546925564,
+      "eval_loss": 0.3560263514518738,
+      "eval_runtime": 107.2714,
+      "eval_samples_per_second": 24.266,
+      "eval_steps_per_second": 3.039,
+      "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": 2.128611934155571e+16,
+  "total_flos": 3.917361458656051e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null