Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:74d8aa526d5ad3c27f3dccb2241dc3ca3321a4211d19aae0114f90bb03a77a25
+oid sha256:322d41b9946a27751803d5f38434ab789462c34e5c3293b8da1a2ca308dd7bc3
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:50a733b5597d7aba71273690d976e0f2809334ad8accc3a78efb97a3ed08d9e5
+oid sha256:91615525ce7d836547ae903c922d936154385a08bbd9d6b328d9a40d425f3b39
 size 341314196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e1cd91016c05522d65bf761ff7d6665aaf444fe68fe7396c3f093e41e4303b9a
+oid sha256:9f26228cdef39b900b7538fa5e6fd502177411408e4d296d7daf626ba036a98b
 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": 2.3222522735595703,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.5025125628140703,
+  "best_metric": 2.2518882751464844,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 1.0050251256281406,
   "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": 26.303,
       "eval_steps_per_second": 3.444,
       "step": 25
+    },
+    {
+      "epoch": 0.5226130653266332,
+      "grad_norm": 4.116923809051514,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 2.274,
+      "step": 26
+    },
+    {
+      "epoch": 0.542713567839196,
+      "grad_norm": 3.029874563217163,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 2.216,
+      "step": 27
+    },
+    {
+      "epoch": 0.5628140703517588,
+      "grad_norm": 3.178542137145996,
+      "learning_rate": 4.825502516487497e-05,
+      "loss": 2.2473,
+      "step": 28
+    },
+    {
+      "epoch": 0.5829145728643216,
+      "grad_norm": 2.835803508758545,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 2.2682,
+      "step": 29
+    },
+    {
+      "epoch": 0.6030150753768844,
+      "grad_norm": 2.7178564071655273,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 2.1825,
+      "step": 30
+    },
+    {
+      "epoch": 0.6231155778894473,
+      "grad_norm": 2.9375200271606445,
+      "learning_rate": 3.790390522001662e-05,
+      "loss": 2.1947,
+      "step": 31
+    },
+    {
+      "epoch": 0.6432160804020101,
+      "grad_norm": 2.9287827014923096,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 2.1413,
+      "step": 32
+    },
+    {
+      "epoch": 0.6633165829145728,
+      "grad_norm": 3.3967692852020264,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 2.136,
+      "step": 33
+    },
+    {
+      "epoch": 0.6834170854271356,
+      "grad_norm": 3.2882797718048096,
+      "learning_rate": 2.8081442660546125e-05,
+      "loss": 1.9974,
+      "step": 34
+    },
+    {
+      "epoch": 0.7035175879396985,
+      "grad_norm": 3.09812068939209,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 2.0237,
+      "step": 35
+    },
+    {
+      "epoch": 0.7236180904522613,
+      "grad_norm": 3.9332921504974365,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 2.2785,
+      "step": 36
+    },
+    {
+      "epoch": 0.7437185929648241,
+      "grad_norm": 2.945986747741699,
+      "learning_rate": 1.9216926233717085e-05,
+      "loss": 2.165,
+      "step": 37
+    },
+    {
+      "epoch": 0.7638190954773869,
+      "grad_norm": 3.223416805267334,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 2.28,
+      "step": 38
+    },
+    {
+      "epoch": 0.7839195979899497,
+      "grad_norm": 3.715877056121826,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 2.3652,
+      "step": 39
+    },
+    {
+      "epoch": 0.8040201005025126,
+      "grad_norm": 3.0044689178466797,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 2.1738,
+      "step": 40
+    },
+    {
+      "epoch": 0.8241206030150754,
+      "grad_norm": 2.8815624713897705,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 2.1436,
+      "step": 41
+    },
+    {
+      "epoch": 0.8442211055276382,
+      "grad_norm": 3.3641395568847656,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 2.0327,
+      "step": 42
+    },
+    {
+      "epoch": 0.864321608040201,
+      "grad_norm": 2.9802918434143066,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 2.3803,
+      "step": 43
+    },
+    {
+      "epoch": 0.8844221105527639,
+      "grad_norm": 2.903658628463745,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 1.9058,
+      "step": 44
+    },
+    {
+      "epoch": 0.9045226130653267,
+      "grad_norm": 2.8861379623413086,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 1.847,
+      "step": 45
+    },
+    {
+      "epoch": 0.9246231155778895,
+      "grad_norm": 2.8846468925476074,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 1.9794,
+      "step": 46
+    },
+    {
+      "epoch": 0.9447236180904522,
+      "grad_norm": 3.5555076599121094,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 2.0817,
+      "step": 47
+    },
+    {
+      "epoch": 0.964824120603015,
+      "grad_norm": 4.338587284088135,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 2.3208,
+      "step": 48
+    },
+    {
+      "epoch": 0.9849246231155779,
+      "grad_norm": 3.71798038482666,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 2.1975,
+      "step": 49
+    },
+    {
+      "epoch": 1.0050251256281406,
+      "grad_norm": 4.210870742797852,
+      "learning_rate": 0.0,
+      "loss": 3.0183,
+      "step": 50
+    },
+    {
+      "epoch": 1.0050251256281406,
+      "eval_loss": 2.2518882751464844,
+      "eval_runtime": 3.2059,
+      "eval_samples_per_second": 26.202,
+      "eval_steps_per_second": 3.431,
+      "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": 1.88564197343232e+16,
+  "total_flos": 3.759498684530688e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null