Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3612226dc1e5994c776b8f5aba9ff0b99caa90934a619d1cabd2fa985768eb68
+oid sha256:a5f10112e9cef44a1783ae83183ec226e77e0aa765076b98d4bafab696cb30cd
 size 216151256

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:39b860c69612f4a705533c516097591693fb882c0d7b24ace8dca434ebd3225d
+oid sha256:139b94d97f57bc43c1f37d3f05ef905c461dfd01b640bd9e5603913a53d72f7f
 size 432640054

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3233b2c1d81f526ea891c28e383ed026dc217699cb47deb84cf150984410f49a
+oid sha256:444a1343202e84b85beae9482da900be504c62c1030c70496984ce2847da3967
 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": 3.883234739303589,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.1443001443001443,
+  "best_metric": 3.52176570892334,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.2886002886002886,
   "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": 2.442,
       "eval_steps_per_second": 1.238,
       "step": 25
+    },
+    {
+      "epoch": 0.15007215007215008,
+      "grad_norm": 5.483874320983887,
+      "learning_rate": 0.0001,
+      "loss": 2.8525,
+      "step": 26
+    },
+    {
+      "epoch": 0.15584415584415584,
+      "grad_norm": 4.851412296295166,
+      "learning_rate": 9.345968707698569e-05,
+      "loss": 3.1477,
+      "step": 27
+    },
+    {
+      "epoch": 0.16161616161616163,
+      "grad_norm": 5.818398952484131,
+      "learning_rate": 8.694738077799488e-05,
+      "loss": 3.1177,
+      "step": 28
+    },
+    {
+      "epoch": 0.1673881673881674,
+      "grad_norm": 6.832301139831543,
+      "learning_rate": 8.049096779838719e-05,
+      "loss": 3.5393,
+      "step": 29
+    },
+    {
+      "epoch": 0.17316017316017315,
+      "grad_norm": 5.470390319824219,
+      "learning_rate": 7.411809548974792e-05,
+      "loss": 3.6273,
+      "step": 30
+    },
+    {
+      "epoch": 0.17893217893217894,
+      "grad_norm": 7.099745750427246,
+      "learning_rate": 6.785605346968386e-05,
+      "loss": 2.8683,
+      "step": 31
+    },
+    {
+      "epoch": 0.1847041847041847,
+      "grad_norm": 6.852536678314209,
+      "learning_rate": 6.173165676349103e-05,
+      "loss": 4.697,
+      "step": 32
+    },
+    {
+      "epoch": 0.19047619047619047,
+      "grad_norm": 7.737475395202637,
+      "learning_rate": 5.577113097809989e-05,
+      "loss": 5.2704,
+      "step": 33
+    },
+    {
+      "epoch": 0.19624819624819625,
+      "grad_norm": 8.485671997070312,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 4.3796,
+      "step": 34
+    },
+    {
+      "epoch": 0.20202020202020202,
+      "grad_norm": 5.709878444671631,
+      "learning_rate": 4.444297669803981e-05,
+      "loss": 3.9743,
+      "step": 35
+    },
+    {
+      "epoch": 0.2077922077922078,
+      "grad_norm": 5.483663082122803,
+      "learning_rate": 3.9123857099127936e-05,
+      "loss": 3.9421,
+      "step": 36
+    },
+    {
+      "epoch": 0.21356421356421357,
+      "grad_norm": 4.827873706817627,
+      "learning_rate": 3.406541848999312e-05,
+      "loss": 4.0746,
+      "step": 37
+    },
+    {
+      "epoch": 0.21933621933621933,
+      "grad_norm": 15.908256530761719,
+      "learning_rate": 2.9289321881345254e-05,
+      "loss": 7.8459,
+      "step": 38
+    },
+    {
+      "epoch": 0.22510822510822512,
+      "grad_norm": 17.669963836669922,
+      "learning_rate": 2.4816019252102273e-05,
+      "loss": 7.6677,
+      "step": 39
+    },
+    {
+      "epoch": 0.23088023088023088,
+      "grad_norm": 15.907238006591797,
+      "learning_rate": 2.0664665970876496e-05,
+      "loss": 6.4001,
+      "step": 40
+    },
+    {
+      "epoch": 0.23665223665223664,
+      "grad_norm": 11.9762601852417,
+      "learning_rate": 1.6853038769745467e-05,
+      "loss": 7.4365,
+      "step": 41
+    },
+    {
+      "epoch": 0.24242424242424243,
+      "grad_norm": 8.19090461730957,
+      "learning_rate": 1.339745962155613e-05,
+      "loss": 6.703,
+      "step": 42
+    },
+    {
+      "epoch": 0.2481962481962482,
+      "grad_norm": 8.14680290222168,
+      "learning_rate": 1.0312725846731175e-05,
+      "loss": 7.3564,
+      "step": 43
+    },
+    {
+      "epoch": 0.25396825396825395,
+      "grad_norm": 7.9732561111450195,
+      "learning_rate": 7.612046748871327e-06,
+      "loss": 2.4814,
+      "step": 44
+    },
+    {
+      "epoch": 0.2597402597402597,
+      "grad_norm": 8.285723686218262,
+      "learning_rate": 5.306987050489442e-06,
+      "loss": 3.1881,
+      "step": 45
+    },
+    {
+      "epoch": 0.26551226551226553,
+      "grad_norm": 10.690110206604004,
+      "learning_rate": 3.40741737109318e-06,
+      "loss": 3.5401,
+      "step": 46
+    },
+    {
+      "epoch": 0.2712842712842713,
+      "grad_norm": 9.28165340423584,
+      "learning_rate": 1.921471959676957e-06,
+      "loss": 3.6229,
+      "step": 47
+    },
+    {
+      "epoch": 0.27705627705627706,
+      "grad_norm": 12.119881629943848,
+      "learning_rate": 8.555138626189618e-07,
+      "loss": 3.1769,
+      "step": 48
+    },
+    {
+      "epoch": 0.2828282828282828,
+      "grad_norm": 8.861678123474121,
+      "learning_rate": 2.141076761396521e-07,
+      "loss": 3.5118,
+      "step": 49
+    },
+    {
+      "epoch": 0.2886002886002886,
+      "grad_norm": 9.257101058959961,
+      "learning_rate": 0.0,
+      "loss": 3.6435,
+      "step": 50
+    },
+    {
+      "epoch": 0.2886002886002886,
+      "eval_loss": 3.52176570892334,
+      "eval_runtime": 29.8722,
+      "eval_samples_per_second": 2.444,
+      "eval_steps_per_second": 1.239,
+      "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": 4.11806271012864e+16,
+  "total_flos": 8.23612542025728e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null