Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b4a1e2e3c7593743ffeca82cc0d59ba96a06c22c324f667555e0f74612c4bd9
+oid sha256:3b877d9d47c7fc5ac3b7bc6f431c22bbb9d850f22cbc405de25f8dd948a37399
 size 186962

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46e7a842828d3a24de9a348aacf85472c2fab66f7b0bae59ba79681c1a4c2ea4
+oid sha256:80d6d00176615b374b0927da1d02ddd03cb8e9e86d7a2a17ffd0e974f835a401
 size 121430

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6930f018376f4f3ba3c9bb4dd38084c6b60eabe4508e0e63e6a5338c2066f5d1
+oid sha256:a31dbe1041a96af95995c515c9d0cf9cc920b1e6eff3c5e028113dbf2c1af400
 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": 6.926918983459473,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.0028231839869004263,
+  "best_metric": 6.920986652374268,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.005646367973800853,
   "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": 314.671,
       "eval_steps_per_second": 157.378,
       "step": 25
+    },
+    {
+      "epoch": 0.0029361113463764435,
+      "grad_norm": 0.20033280551433563,
+      "learning_rate": 0.0001,
+      "loss": 6.9243,
+      "step": 26
+    },
+    {
+      "epoch": 0.0030490387058524603,
+      "grad_norm": 0.2356751710176468,
+      "learning_rate": 9.345968707698569e-05,
+      "loss": 6.9204,
+      "step": 27
+    },
+    {
+      "epoch": 0.0031619660653284774,
+      "grad_norm": 0.2633371949195862,
+      "learning_rate": 8.694738077799488e-05,
+      "loss": 6.9216,
+      "step": 28
+    },
+    {
+      "epoch": 0.0032748934248044946,
+      "grad_norm": 0.2085108906030655,
+      "learning_rate": 8.049096779838719e-05,
+      "loss": 6.9298,
+      "step": 29
+    },
+    {
+      "epoch": 0.0033878207842805113,
+      "grad_norm": 0.2274623066186905,
+      "learning_rate": 7.411809548974792e-05,
+      "loss": 6.9212,
+      "step": 30
+    },
+    {
+      "epoch": 0.0035007481437565285,
+      "grad_norm": 0.22422252595424652,
+      "learning_rate": 6.785605346968386e-05,
+      "loss": 6.9258,
+      "step": 31
+    },
+    {
+      "epoch": 0.0036136755032325457,
+      "grad_norm": 0.22745665907859802,
+      "learning_rate": 6.173165676349103e-05,
+      "loss": 6.9075,
+      "step": 32
+    },
+    {
+      "epoch": 0.003726602862708563,
+      "grad_norm": 0.24554090201854706,
+      "learning_rate": 5.577113097809989e-05,
+      "loss": 6.9261,
+      "step": 33
+    },
+    {
+      "epoch": 0.0038395302221845796,
+      "grad_norm": 0.21141235530376434,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 6.9256,
+      "step": 34
+    },
+    {
+      "epoch": 0.003952457581660597,
+      "grad_norm": 0.22744667530059814,
+      "learning_rate": 4.444297669803981e-05,
+      "loss": 6.9244,
+      "step": 35
+    },
+    {
+      "epoch": 0.004065384941136614,
+      "grad_norm": 0.22644877433776855,
+      "learning_rate": 3.9123857099127936e-05,
+      "loss": 6.9293,
+      "step": 36
+    },
+    {
+      "epoch": 0.004178312300612631,
+      "grad_norm": 0.2632388472557068,
+      "learning_rate": 3.406541848999312e-05,
+      "loss": 6.9136,
+      "step": 37
+    },
+    {
+      "epoch": 0.004291239660088648,
+      "grad_norm": 0.23912282288074493,
+      "learning_rate": 2.9289321881345254e-05,
+      "loss": 6.92,
+      "step": 38
+    },
+    {
+      "epoch": 0.004404167019564665,
+      "grad_norm": 0.2523389756679535,
+      "learning_rate": 2.4816019252102273e-05,
+      "loss": 6.9173,
+      "step": 39
+    },
+    {
+      "epoch": 0.004517094379040682,
+      "grad_norm": 0.24466051161289215,
+      "learning_rate": 2.0664665970876496e-05,
+      "loss": 6.9196,
+      "step": 40
+    },
+    {
+      "epoch": 0.004630021738516699,
+      "grad_norm": 0.24103286862373352,
+      "learning_rate": 1.6853038769745467e-05,
+      "loss": 6.9223,
+      "step": 41
+    },
+    {
+      "epoch": 0.004742949097992716,
+      "grad_norm": 0.25864821672439575,
+      "learning_rate": 1.339745962155613e-05,
+      "loss": 6.914,
+      "step": 42
+    },
+    {
+      "epoch": 0.004855876457468733,
+      "grad_norm": 0.2653087079524994,
+      "learning_rate": 1.0312725846731175e-05,
+      "loss": 6.922,
+      "step": 43
+    },
+    {
+      "epoch": 0.0049688038169447505,
+      "grad_norm": 0.2347327023744583,
+      "learning_rate": 7.612046748871327e-06,
+      "loss": 6.9263,
+      "step": 44
+    },
+    {
+      "epoch": 0.005081731176420768,
+      "grad_norm": 0.24755509197711945,
+      "learning_rate": 5.306987050489442e-06,
+      "loss": 6.9262,
+      "step": 45
+    },
+    {
+      "epoch": 0.005194658535896784,
+      "grad_norm": 0.23600712418556213,
+      "learning_rate": 3.40741737109318e-06,
+      "loss": 6.9333,
+      "step": 46
+    },
+    {
+      "epoch": 0.005307585895372801,
+      "grad_norm": 0.23946261405944824,
+      "learning_rate": 1.921471959676957e-06,
+      "loss": 6.9247,
+      "step": 47
+    },
+    {
+      "epoch": 0.005420513254848818,
+      "grad_norm": 0.24361290037631989,
+      "learning_rate": 8.555138626189618e-07,
+      "loss": 6.9205,
+      "step": 48
+    },
+    {
+      "epoch": 0.0055334406143248355,
+      "grad_norm": 0.26696720719337463,
+      "learning_rate": 2.141076761396521e-07,
+      "loss": 6.9275,
+      "step": 49
+    },
+    {
+      "epoch": 0.005646367973800853,
+      "grad_norm": 0.27215808629989624,
+      "learning_rate": 0.0,
+      "loss": 6.9104,
+      "step": 50
+    },
+    {
+      "epoch": 0.005646367973800853,
+      "eval_loss": 6.920986652374268,
+      "eval_runtime": 11.8994,
+      "eval_samples_per_second": 313.378,
+      "eval_steps_per_second": 156.731,
+      "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": 297598009344.0,
+  "total_flos": 592249503744.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null