Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:74a28a1e4c35dd8c6f49bda4b2bac9dfd5b519d834647591ac89e4eabed5b9e6
+oid sha256:60389732127d2a040d8b3c9a481aa333d0dd810c55e655e8a17d15556b4d2fa6
 size 161533192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b1770a0afcf652c41b978dc0f77694aada50a13724aabc853ba202a4aec09313
+oid sha256:5aeeed5a398d18ece052f51f2900c260f90a5cfda1313f235f40319e3998871a
 size 323290986

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb848f21b8849e8eca566a35adf976e489f5fdb43c156d7ac92cce4d73724d04
+oid sha256:fa0090eff02a237356709f1aa94f97a78088ed43d412f7cf19314d5550534c1a
 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": 2.0701565742492676,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.016909029421711193,
+  "best_metric": 1.9626966714859009,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.033818058843422386,
   "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": 3.2,
       "eval_steps_per_second": 1.602,
       "step": 25
+    },
+    {
+      "epoch": 0.01758539059857964,
+      "grad_norm": 1.495153546333313,
+      "learning_rate": 0.0001,
+      "loss": 1.8544,
+      "step": 26
+    },
+    {
+      "epoch": 0.01826175177544809,
+      "grad_norm": 1.4844993352890015,
+      "learning_rate": 9.345968707698569e-05,
+      "loss": 1.8767,
+      "step": 27
+    },
+    {
+      "epoch": 0.018938112952316538,
+      "grad_norm": 1.3397953510284424,
+      "learning_rate": 8.694738077799488e-05,
+      "loss": 1.6618,
+      "step": 28
+    },
+    {
+      "epoch": 0.019614474129184985,
+      "grad_norm": 1.5711033344268799,
+      "learning_rate": 8.049096779838719e-05,
+      "loss": 2.3755,
+      "step": 29
+    },
+    {
+      "epoch": 0.020290835306053433,
+      "grad_norm": 1.9921696186065674,
+      "learning_rate": 7.411809548974792e-05,
+      "loss": 2.4551,
+      "step": 30
+    },
+    {
+      "epoch": 0.02096719648292188,
+      "grad_norm": 1.5649608373641968,
+      "learning_rate": 6.785605346968386e-05,
+      "loss": 1.9198,
+      "step": 31
+    },
+    {
+      "epoch": 0.021643557659790327,
+      "grad_norm": 1.696977138519287,
+      "learning_rate": 6.173165676349103e-05,
+      "loss": 1.6022,
+      "step": 32
+    },
+    {
+      "epoch": 0.022319918836658775,
+      "grad_norm": 1.4416958093643188,
+      "learning_rate": 5.577113097809989e-05,
+      "loss": 1.3089,
+      "step": 33
+    },
+    {
+      "epoch": 0.022996280013527222,
+      "grad_norm": 1.7796907424926758,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 1.6978,
+      "step": 34
+    },
+    {
+      "epoch": 0.023672641190395673,
+      "grad_norm": 1.6904518604278564,
+      "learning_rate": 4.444297669803981e-05,
+      "loss": 1.2775,
+      "step": 35
+    },
+    {
+      "epoch": 0.02434900236726412,
+      "grad_norm": 1.994644045829773,
+      "learning_rate": 3.9123857099127936e-05,
+      "loss": 2.167,
+      "step": 36
+    },
+    {
+      "epoch": 0.025025363544132567,
+      "grad_norm": 1.8310939073562622,
+      "learning_rate": 3.406541848999312e-05,
+      "loss": 1.9692,
+      "step": 37
+    },
+    {
+      "epoch": 0.025701724721001015,
+      "grad_norm": 1.9705989360809326,
+      "learning_rate": 2.9289321881345254e-05,
+      "loss": 1.7298,
+      "step": 38
+    },
+    {
+      "epoch": 0.026378085897869462,
+      "grad_norm": 1.8787919282913208,
+      "learning_rate": 2.4816019252102273e-05,
+      "loss": 1.8196,
+      "step": 39
+    },
+    {
+      "epoch": 0.02705444707473791,
+      "grad_norm": 2.238896369934082,
+      "learning_rate": 2.0664665970876496e-05,
+      "loss": 1.8322,
+      "step": 40
+    },
+    {
+      "epoch": 0.027730808251606356,
+      "grad_norm": 2.45574951171875,
+      "learning_rate": 1.6853038769745467e-05,
+      "loss": 1.2616,
+      "step": 41
+    },
+    {
+      "epoch": 0.028407169428474807,
+      "grad_norm": 2.3934166431427,
+      "learning_rate": 1.339745962155613e-05,
+      "loss": 1.8453,
+      "step": 42
+    },
+    {
+      "epoch": 0.029083530605343254,
+      "grad_norm": 2.7318978309631348,
+      "learning_rate": 1.0312725846731175e-05,
+      "loss": 1.7748,
+      "step": 43
+    },
+    {
+      "epoch": 0.029759891782211702,
+      "grad_norm": 2.291386127471924,
+      "learning_rate": 7.612046748871327e-06,
+      "loss": 1.4839,
+      "step": 44
+    },
+    {
+      "epoch": 0.03043625295908015,
+      "grad_norm": 4.89447546005249,
+      "learning_rate": 5.306987050489442e-06,
+      "loss": 2.0595,
+      "step": 45
+    },
+    {
+      "epoch": 0.031112614135948596,
+      "grad_norm": 3.6170737743377686,
+      "learning_rate": 3.40741737109318e-06,
+      "loss": 1.7889,
+      "step": 46
+    },
+    {
+      "epoch": 0.03178897531281705,
+      "grad_norm": 4.144750595092773,
+      "learning_rate": 1.921471959676957e-06,
+      "loss": 2.3446,
+      "step": 47
+    },
+    {
+      "epoch": 0.03246533648968549,
+      "grad_norm": 3.9355359077453613,
+      "learning_rate": 8.555138626189618e-07,
+      "loss": 1.7349,
+      "step": 48
+    },
+    {
+      "epoch": 0.03314169766655394,
+      "grad_norm": 5.390147686004639,
+      "learning_rate": 2.141076761396521e-07,
+      "loss": 1.8468,
+      "step": 49
+    },
+    {
+      "epoch": 0.033818058843422386,
+      "grad_norm": 5.725734710693359,
+      "learning_rate": 0.0,
+      "loss": 2.9805,
+      "step": 50
+    },
+    {
+      "epoch": 0.033818058843422386,
+      "eval_loss": 1.9626966714859009,
+      "eval_runtime": 194.7074,
+      "eval_samples_per_second": 3.2,
+      "eval_steps_per_second": 1.602,
+      "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": 3.49519346663424e+16,
+  "total_flos": 6.99038693326848e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null