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:bbd87c1b6e9e536f82534dcde7cde197315831023ba4c5d6b9fb1735a5167244
+oid sha256:34eb96dc0e75c7885f26a8b7b4d7cde919441dbdfd7da528ec11518894f6b2b7
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f2d5484e53fd4ff951625beaa8b6c5a0805a17872299dcf7c2ca4fdf1a174de
+oid sha256:cedf81716edc13c614f17d73e5bfb9408d99263a470804d69b51bda86fd761f2
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43c0ab1e92c1a7bdf35c21bddab22072570f30a008844ce96abd19833291ccc0
+oid sha256:bc0a70dba7682708fd028d3704aa6c0db05a862d2d693dfb9abc36ed4f70518f
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6fc3e2cd813bd2501c936dd3c27c76a3d5fda648c7098c07f48e5e5c5e78492b
+oid sha256:99e6f26e9612ef37121b0cf304e939c9a9832cc66c3605193e783ae9cff01d2b
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:68f2dd7a4fb2b3072857d83665ab2a94e49494910a6e44f71b569fd76b5abb60
+oid sha256:fa9660eb5814b30c17b382ae8b61930eb796528f7b4a16c6187cccf1d45c785a
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0633886f0b3e4d21ae4b56c0b64d3a00f3a418ec45ac5c3a379daf94c51cb8bd
+oid sha256:5dd102a4c6656f6a94892497949d433a9ee5b4c19af3af8dfc11022bb6a9c107
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5eda964d5b06109c7ff637060199d72e397eeb7027b50e10972a323edbe81312
+oid sha256:fb0ce41087f0939d63a9a6eb297660d82f62bda022868309a8c97328e5da41a5
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": NaN,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.031256104707950774,
+  "epoch": 0.06251220941590155,
   "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": 11.229,
       "eval_steps_per_second": 2.92,
       "step": 25
+    },
+    {
+      "epoch": 0.0325063488962688,
+      "grad_norm": 4.290698528289795,
+      "learning_rate": 7.917848237560709e-05,
+      "loss": 2.7465,
+      "step": 26
+    },
+    {
+      "epoch": 0.03375659308458683,
+      "grad_norm": 3.880889415740967,
+      "learning_rate": 7.75e-05,
+      "loss": 2.5353,
+      "step": 27
+    },
+    {
+      "epoch": 0.035006837272904864,
+      "grad_norm": 2.8910319805145264,
+      "learning_rate": 7.577868759557654e-05,
+      "loss": 2.6292,
+      "step": 28
+    },
+    {
+      "epoch": 0.0362570814612229,
+      "grad_norm": 2.103529453277588,
+      "learning_rate": 7.401782177833148e-05,
+      "loss": 2.3267,
+      "step": 29
+    },
+    {
+      "epoch": 0.03750732564954093,
+      "grad_norm": 2.1339449882507324,
+      "learning_rate": 7.222075445642904e-05,
+      "loss": 2.4088,
+      "step": 30
+    },
+    {
+      "epoch": 0.038757569837858954,
+      "grad_norm": 2.083258867263794,
+      "learning_rate": 7.03909064496551e-05,
+      "loss": 2.2545,
+      "step": 31
+    },
+    {
+      "epoch": 0.04000781402617699,
+      "grad_norm": 1.7957262992858887,
+      "learning_rate": 6.853176097769229e-05,
+      "loss": 2.2531,
+      "step": 32
+    },
+    {
+      "epoch": 0.04125805821449502,
+      "grad_norm": 1.5465190410614014,
+      "learning_rate": 6.664685702961344e-05,
+      "loss": 2.2347,
+      "step": 33
+    },
+    {
+      "epoch": 0.04250830240281305,
+      "grad_norm": 1.6104645729064941,
+      "learning_rate": 6.473978262721463e-05,
+      "loss": 2.1565,
+      "step": 34
+    },
+    {
+      "epoch": 0.04375854659113108,
+      "grad_norm": 1.7143096923828125,
+      "learning_rate": 6.281416799501188e-05,
+      "loss": 2.0586,
+      "step": 35
+    },
+    {
+      "epoch": 0.04500879077944911,
+      "grad_norm": 1.9381986856460571,
+      "learning_rate": 6.087367864990233e-05,
+      "loss": 1.9545,
+      "step": 36
+    },
+    {
+      "epoch": 0.04625903496776714,
+      "grad_norm": 1.737153172492981,
+      "learning_rate": 5.8922008423644624e-05,
+      "loss": 1.8466,
+      "step": 37
+    },
+    {
+      "epoch": 0.047509279156085174,
+      "grad_norm": 1.7730242013931274,
+      "learning_rate": 5.696287243144013e-05,
+      "loss": 2.2282,
+      "step": 38
+    },
+    {
+      "epoch": 0.048759523344403206,
+      "grad_norm": 1.610041856765747,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 2.2569,
+      "step": 39
+    },
+    {
+      "epoch": 0.05000976753272123,
+      "grad_norm": 1.6900049448013306,
+      "learning_rate": 5.303712756855988e-05,
+      "loss": 2.3254,
+      "step": 40
+    },
+    {
+      "epoch": 0.051260011721039264,
+      "grad_norm": 1.7346092462539673,
+      "learning_rate": 5.107799157635538e-05,
+      "loss": 2.3187,
+      "step": 41
+    },
+    {
+      "epoch": 0.0525102559093573,
+      "grad_norm": 1.3713421821594238,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 2.2042,
+      "step": 42
+    },
+    {
+      "epoch": 0.05376050009767533,
+      "grad_norm": 1.1843212842941284,
+      "learning_rate": 4.718583200498814e-05,
+      "loss": 2.1743,
+      "step": 43
+    },
+    {
+      "epoch": 0.05501074428599336,
+      "grad_norm": 1.167022705078125,
+      "learning_rate": 4.526021737278538e-05,
+      "loss": 2.2873,
+      "step": 44
+    },
+    {
+      "epoch": 0.05626098847431139,
+      "grad_norm": 1.212775468826294,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 2.2581,
+      "step": 45
+    },
+    {
+      "epoch": 0.05751123266262942,
+      "grad_norm": 1.5787919759750366,
+      "learning_rate": 4.146823902230772e-05,
+      "loss": 2.0386,
+      "step": 46
+    },
+    {
+      "epoch": 0.05876147685094745,
+      "grad_norm": 1.6239919662475586,
+      "learning_rate": 3.960909355034491e-05,
+      "loss": 1.9584,
+      "step": 47
+    },
+    {
+      "epoch": 0.060011721039265484,
+      "grad_norm": 1.540845513343811,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 1.9723,
+      "step": 48
+    },
+    {
+      "epoch": 0.06126196522758351,
+      "grad_norm": 1.7158163785934448,
+      "learning_rate": 3.598217822166854e-05,
+      "loss": 1.8209,
+      "step": 49
+    },
+    {
+      "epoch": 0.06251220941590155,
+      "grad_norm": 2.355154275894165,
+      "learning_rate": 3.422131240442349e-05,
+      "loss": 1.611,
+      "step": 50
+    },
+    {
+      "epoch": 0.06251220941590155,
+      "eval_loss": NaN,
+      "eval_runtime": 4.358,
+      "eval_samples_per_second": 11.473,
+      "eval_steps_per_second": 2.983,
+      "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": 2.984041808658432e+17,
+  "total_flos": 5.968083617316864e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null