Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:95449fd2241b7b076c5415d38296f8d42e607b4bec7bc9cf5d74e2af185b84da
+oid sha256:13d7d076c8aa43764aabd85b17b49c2310e3835e49ba9ec879f2e9d1ca7113de
 size 203456160

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb3ebd35360bc00b4ce9e9ef36df3f311437e705fe8ccd12b0f79b3309f66ead
+oid sha256:ba189e339551f6dddde8cca89d31c2784ba363467fcfb08a4d1d800ffb1a258f
 size 407121750

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b012cd407afde9d46200f914243d907c8912d957f64cdb6707d061679344b631
+oid sha256:2e20cd09f6c30f83c7f4cd01cc8e0cf89743b81a29ed83f1a61fc9874d485084
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a84fa2ff5c75b115d4254e6c84abd691bf821b8c15480266a97c3fd734ed28aa
+oid sha256:f02082005aa59208c03193c32f26ce90a8f5c53cb2596c7163cac29263e9937a
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:323207e88c6ddf7f8f1b5ae3811b269ee426648d5d8831bb830c4a503a9c4721
+oid sha256:c1ddc592cc431fcaae272c0e0d6e6f07bff85a8aa7e40d854412a5dda76fc05d
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b18a8ac1f5a4e44b15dad2ca17cea51972d827ef1a4311ce20825601b32d579a
+oid sha256:48e797a8c40a54a8a843cae4e77f8c8301575a73bd488d3293e276363cb20dfa
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d271cdb95f63cd655315f063ca2e25c78dc5ae4275523c5d4f80f367586b3351
+oid sha256:5607f6de446164d9d9adb8b91c44cec55b14aa391e24ba5637c08b834eedda2a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": NaN,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.006126887847317955,
+  "epoch": 0.01225377569463591,
   "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": 18.92,
       "eval_steps_per_second": 4.919,
       "step": 25
+    },
+    {
+      "epoch": 0.006371963361210673,
+      "grad_norm": 0.0,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.0,
+      "step": 26
+    },
+    {
+      "epoch": 0.006617038875103391,
+      "grad_norm": 0.0,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 0.0068621143889961095,
+      "grad_norm": 0.0,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 0.0,
+      "step": 28
+    },
+    {
+      "epoch": 0.007107189902888828,
+      "grad_norm": 0.0,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 0.0,
+      "step": 29
+    },
+    {
+      "epoch": 0.007352265416781546,
+      "grad_norm": 0.0,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.007597340930674264,
+      "grad_norm": 0.0,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 0.0,
+      "step": 31
+    },
+    {
+      "epoch": 0.007842416444566982,
+      "grad_norm": 0.0,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 0.0,
+      "step": 32
+    },
+    {
+      "epoch": 0.008087491958459701,
+      "grad_norm": 0.0,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 0.0,
+      "step": 33
+    },
+    {
+      "epoch": 0.008332567472352418,
+      "grad_norm": 0.0,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 0.0,
+      "step": 34
+    },
+    {
+      "epoch": 0.008577642986245138,
+      "grad_norm": 0.0,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 0.0,
+      "step": 35
+    },
+    {
+      "epoch": 0.008822718500137855,
+      "grad_norm": 0.0,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 0.0,
+      "step": 36
+    },
+    {
+      "epoch": 0.009067794014030572,
+      "grad_norm": 0.0,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 0.0,
+      "step": 37
+    },
+    {
+      "epoch": 0.009312869527923292,
+      "grad_norm": 0.0,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.0,
+      "step": 38
+    },
+    {
+      "epoch": 0.009557945041816009,
+      "grad_norm": 0.0,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 0.0,
+      "step": 39
+    },
+    {
+      "epoch": 0.009803020555708728,
+      "grad_norm": 0.0,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 0.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.010048096069601446,
+      "grad_norm": 0.0,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 0.0,
+      "step": 41
+    },
+    {
+      "epoch": 0.010293171583494165,
+      "grad_norm": 0.0,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 0.0,
+      "step": 42
+    },
+    {
+      "epoch": 0.010538247097386882,
+      "grad_norm": 0.0,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 0.0,
+      "step": 43
+    },
+    {
+      "epoch": 0.010783322611279601,
+      "grad_norm": 0.0,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 0.0,
+      "step": 44
+    },
+    {
+      "epoch": 0.011028398125172319,
+      "grad_norm": 0.0,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 0.0,
+      "step": 45
+    },
+    {
+      "epoch": 0.011273473639065036,
+      "grad_norm": 0.0,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 0.0,
+      "step": 46
+    },
+    {
+      "epoch": 0.011518549152957755,
+      "grad_norm": 0.0,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 0.0,
+      "step": 47
+    },
+    {
+      "epoch": 0.011763624666850473,
+      "grad_norm": 0.0,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 0.0,
+      "step": 48
+    },
+    {
+      "epoch": 0.012008700180743192,
+      "grad_norm": 0.0,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 0.0,
+      "step": 49
+    },
+    {
+      "epoch": 0.01225377569463591,
+      "grad_norm": 0.0,
+      "learning_rate": 1e-05,
+      "loss": 0.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.01225377569463591,
+      "eval_loss": NaN,
+      "eval_runtime": 2.6288,
+      "eval_samples_per_second": 19.02,
+      "eval_steps_per_second": 4.945,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -212,7 +395,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 0
+        "early_stopping_patience_counter": 1
       }
     },
     "TrainerControl": {
@@ -221,12 +404,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.327074698592256e+17,
+  "total_flos": 2.654149397184512e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null