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:cfdf64799140b19cfb89b0ee19b2d148a18313c9011e31fdd284926f46a330e4
+oid sha256:fdaf6261273c8ab7ec339ab19b126b2128b4b64594bce3f61621b5fe4e7ed9f4
 size 93608

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cc78cb519cc53355be59712fdf0f47c7374c3ed88e7cf3b596e57cd60dfc169e
+oid sha256:fd4f8a9f585d4e6f68c16a433a8e5db3ff8e79dd4b91387d9e4b83a2a94d876d
 size 197158

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d29b8622e4f53233981ad13c1a54436d9046f80e94b203b91a7190714acd3c94
+oid sha256:7e6ebd5d90a901ab3a4882911629cbc8bf4142ee87fa52fdfdbc3ef30adc53d3
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c931ece4da598a541d357f6c98f67481603252e193960022d37ddd49c584b1f
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 11.931512832641602,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.056085249579360626,
+  "best_metric": 11.929618835449219,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.11217049915872125,
   "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": 185.677,
       "eval_steps_per_second": 23.241,
       "step": 25
+    },
+    {
+      "epoch": 0.05832865956253505,
+      "grad_norm": 0.021957021206617355,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 11.9322,
+      "step": 26
+    },
+    {
+      "epoch": 0.06057206954570948,
+      "grad_norm": 0.025794783607125282,
+      "learning_rate": 8.715724127386972e-05,
+      "loss": 11.9327,
+      "step": 27
+    },
+    {
+      "epoch": 0.0628154795288839,
+      "grad_norm": 0.034966181963682175,
+      "learning_rate": 8.345653031794292e-05,
+      "loss": 11.9313,
+      "step": 28
+    },
+    {
+      "epoch": 0.06505888951205833,
+      "grad_norm": 0.032141417264938354,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 11.9309,
+      "step": 29
+    },
+    {
+      "epoch": 0.06730229949523275,
+      "grad_norm": 0.036759525537490845,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 11.9322,
+      "step": 30
+    },
+    {
+      "epoch": 0.06954570947840717,
+      "grad_norm": 0.028740139678120613,
+      "learning_rate": 7.033683215379002e-05,
+      "loss": 11.9313,
+      "step": 31
+    },
+    {
+      "epoch": 0.0717891194615816,
+      "grad_norm": 0.03210673853754997,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 11.931,
+      "step": 32
+    },
+    {
+      "epoch": 0.07403252944475602,
+      "grad_norm": 0.05024946480989456,
+      "learning_rate": 6.0395584540887963e-05,
+      "loss": 11.9295,
+      "step": 33
+    },
+    {
+      "epoch": 0.07627593942793046,
+      "grad_norm": 0.041959248483181,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 11.932,
+      "step": 34
+    },
+    {
+      "epoch": 0.07851934941110487,
+      "grad_norm": 0.050003744661808014,
+      "learning_rate": 5e-05,
+      "loss": 11.9288,
+      "step": 35
+    },
+    {
+      "epoch": 0.08076275939427931,
+      "grad_norm": 0.04736671969294548,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 11.9286,
+      "step": 36
+    },
+    {
+      "epoch": 0.08300616937745373,
+      "grad_norm": 0.0493813119828701,
+      "learning_rate": 3.960441545911204e-05,
+      "loss": 11.9302,
+      "step": 37
+    },
+    {
+      "epoch": 0.08524957936062816,
+      "grad_norm": 0.04406358674168587,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 11.9318,
+      "step": 38
+    },
+    {
+      "epoch": 0.08749298934380258,
+      "grad_norm": 0.05293726176023483,
+      "learning_rate": 2.9663167846209998e-05,
+      "loss": 11.9301,
+      "step": 39
+    },
+    {
+      "epoch": 0.08973639932697701,
+      "grad_norm": 0.04568186402320862,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 11.9317,
+      "step": 40
+    },
+    {
+      "epoch": 0.09197980931015143,
+      "grad_norm": 0.06105807051062584,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 11.9306,
+      "step": 41
+    },
+    {
+      "epoch": 0.09422321929332586,
+      "grad_norm": 0.05900374799966812,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 11.9279,
+      "step": 42
+    },
+    {
+      "epoch": 0.09646662927650028,
+      "grad_norm": 0.05491477623581886,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 11.9291,
+      "step": 43
+    },
+    {
+      "epoch": 0.09871003925967471,
+      "grad_norm": 0.039628300815820694,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 11.9298,
+      "step": 44
+    },
+    {
+      "epoch": 0.10095344924284913,
+      "grad_norm": 0.05878068134188652,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 11.9303,
+      "step": 45
+    },
+    {
+      "epoch": 0.10319685922602355,
+      "grad_norm": 0.06594429910182953,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 11.9312,
+      "step": 46
+    },
+    {
+      "epoch": 0.10544026920919798,
+      "grad_norm": 0.05928008258342743,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 11.9317,
+      "step": 47
+    },
+    {
+      "epoch": 0.1076836791923724,
+      "grad_norm": 0.07683888077735901,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 11.9279,
+      "step": 48
+    },
+    {
+      "epoch": 0.10992708917554683,
+      "grad_norm": 0.06153682991862297,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 11.9302,
+      "step": 49
+    },
+    {
+      "epoch": 0.11217049915872125,
+      "grad_norm": 0.06444248557090759,
+      "learning_rate": 0.0,
+      "loss": 11.9299,
+      "step": 50
+    },
+    {
+      "epoch": 0.11217049915872125,
+      "eval_loss": 11.929618835449219,
+      "eval_runtime": 4.0408,
+      "eval_samples_per_second": 185.856,
+      "eval_steps_per_second": 23.263,
+      "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": 120520704000.0,
+  "total_flos": 241041408000.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null