Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ecfc7815d512a0d31e9d0aad0a1ef164631caec42c2181d93d88514008a6821
+oid sha256:525160c99c2a10c83e0299fa8de0ea1cbb7dd598574fe02860298aac05e7e573
 size 156926880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:be7d0212d918aa7bfd297b54ff268c8321c62769f03e07e05211e23067d17659
+oid sha256:5ce6667e5570ceaa3da59662bb2b8d62fb492e569206a748db0edb932ef7c245
 size 313998650

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc075eb4da7af0bc855b0d255f2384ba711474c3b3f9b2ec93961f6d61458a0e
+oid sha256:e28d43345437f86c16c88a086b0400312228d513b822c76194a682edcd6e91bd
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:391aa240e9fad0f95b38e2caf27a2cfd5518664eb6d6342e9960820b256e1e79
+oid sha256:3977402e627e07730b5c30c723eabfc20e799d4541c91a8dca54c39f91456da1
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:11ef2b5eb9f4907b538e31f3ef8919cc749ad0cd2db8af4046ddfa9e5e3e330a
+oid sha256:b10cf6426c8342dcb744ed131da4e244d8b7e8d673d57a6f63a2b190c41d5007
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3004123c24c27f30f7bbb540ed760fa238f2724cedbcc1adbedebda43fa54614
+oid sha256:3e2505252120e69df2d823852bb4c3d5f0ed2c3fc8fd7d9249a6dd5cdd08cd30
 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": 0.31286664059444663,
+  "epoch": 0.6257332811888933,
   "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": 24.576,
       "eval_steps_per_second": 6.39,
       "step": 25
+    },
+    {
+      "epoch": 0.3253813062182245,
+      "grad_norm": 2.0011110305786133,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.991,
+      "step": 26
+    },
+    {
+      "epoch": 0.3378959718420024,
+      "grad_norm": 2.0475192070007324,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 1.3608,
+      "step": 27
+    },
+    {
+      "epoch": 0.3504106374657802,
+      "grad_norm": 1.8558727502822876,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 1.5395,
+      "step": 28
+    },
+    {
+      "epoch": 0.36292530308955806,
+      "grad_norm": 1.5381715297698975,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 1.183,
+      "step": 29
+    },
+    {
+      "epoch": 0.37543996871333596,
+      "grad_norm": 1.9737073183059692,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 1.2611,
+      "step": 30
+    },
+    {
+      "epoch": 0.3879546343371138,
+      "grad_norm": 2.4097700119018555,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 1.0897,
+      "step": 31
+    },
+    {
+      "epoch": 0.40046929996089164,
+      "grad_norm": 1.9280041456222534,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 1.2415,
+      "step": 32
+    },
+    {
+      "epoch": 0.41298396558466954,
+      "grad_norm": 1.7732486724853516,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 1.3308,
+      "step": 33
+    },
+    {
+      "epoch": 0.4254986312084474,
+      "grad_norm": 1.8770219087600708,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 1.2773,
+      "step": 34
+    },
+    {
+      "epoch": 0.4380132968322253,
+      "grad_norm": 2.209496021270752,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 1.1981,
+      "step": 35
+    },
+    {
+      "epoch": 0.45052796245600313,
+      "grad_norm": 2.2610745429992676,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 1.0344,
+      "step": 36
+    },
+    {
+      "epoch": 0.46304262807978097,
+      "grad_norm": 2.2316040992736816,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 1.2909,
+      "step": 37
+    },
+    {
+      "epoch": 0.47555729370355887,
+      "grad_norm": 1.6294275522232056,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.9738,
+      "step": 38
+    },
+    {
+      "epoch": 0.4880719593273367,
+      "grad_norm": 1.528761625289917,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 0.8498,
+      "step": 39
+    },
+    {
+      "epoch": 0.5005866249511146,
+      "grad_norm": 1.7920118570327759,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 1.5672,
+      "step": 40
+    },
+    {
+      "epoch": 0.5131012905748924,
+      "grad_norm": 1.6099443435668945,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 1.1178,
+      "step": 41
+    },
+    {
+      "epoch": 0.5256159561986703,
+      "grad_norm": 1.7412190437316895,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 1.1435,
+      "step": 42
+    },
+    {
+      "epoch": 0.5381306218224482,
+      "grad_norm": 1.6830037832260132,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 1.075,
+      "step": 43
+    },
+    {
+      "epoch": 0.5506452874462261,
+      "grad_norm": 1.8176605701446533,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 1.1402,
+      "step": 44
+    },
+    {
+      "epoch": 0.5631599530700039,
+      "grad_norm": 1.6718379259109497,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 1.1893,
+      "step": 45
+    },
+    {
+      "epoch": 0.5756746186937818,
+      "grad_norm": 1.240828037261963,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 0.6582,
+      "step": 46
+    },
+    {
+      "epoch": 0.5881892843175597,
+      "grad_norm": 1.8477025032043457,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 0.9412,
+      "step": 47
+    },
+    {
+      "epoch": 0.6007039499413375,
+      "grad_norm": 2.1296470165252686,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 0.9925,
+      "step": 48
+    },
+    {
+      "epoch": 0.6132186155651154,
+      "grad_norm": 1.826198935508728,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 0.9655,
+      "step": 49
+    },
+    {
+      "epoch": 0.6257332811888933,
+      "grad_norm": 2.643702745437622,
+      "learning_rate": 1e-05,
+      "loss": 1.618,
+      "step": 50
+    },
+    {
+      "epoch": 0.6257332811888933,
+      "eval_loss": NaN,
+      "eval_runtime": 2.0353,
+      "eval_samples_per_second": 24.567,
+      "eval_steps_per_second": 6.387,
+      "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": 7.94731890081792e+16,
+  "total_flos": 1.589463780163584e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null