Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:610e34cdf9b80a2912a37e3d25729a0992c62d3f10988b8951799f30fa9bc01c
+oid sha256:22fcd5c8640e7e767b7e58634f8734c8fc2b9d7ee2078b0f7afef08c800f433e
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e06402033e833be9057fcfdbf2ae7f2c9fad1efab5fda816716d3f35b67941ac
+oid sha256:0d1a7ff04ace5d0b99ffdc1c9973b40dee8579f33badf0161697ce59311c2a40
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2caedf686ab4c95429fd37c90ce225adf3b783aed23da8b160fea466ab8d1d89
+oid sha256:272d67c5c14c168a0fdd609b63d5ba62094c3bb2b0be930a85da8268b5a8d329
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f1ef1b1e19b21527a6965bae79dd781de201df760cb7933c4fd5e4908022189
+oid sha256:f9f4f6f355f01d32d30d95b34a7e42e650a5843ea60d3bf7cee23a1bdbaafb2d
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cfabe9d58037df00141a72b803aeea68b68eee40e7420cef86367193b49411d9
+oid sha256:0d334b3c8b3959a34e572b4791d333884dda0cab1fda382388fbd8c7cbdee8fe
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b1ecc74f0538ebf24f05e39e36ddefb23ac0000df1ab10567a49c22b2662735
+oid sha256:3f13adf62bc262763980f8854eb63010b695d11b7f1b1bb4a5ec58585092fc2a
 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": 0.9184845005740528,
+  "epoch": 1.8369690011481055,
   "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": 31.897,
       "eval_steps_per_second": 8.293,
       "step": 25
+    },
+    {
+      "epoch": 0.9552238805970149,
+      "grad_norm": 1.1894108057022095,
+      "learning_rate": 7.917848237560709e-05,
+      "loss": 1.3724,
+      "step": 26
+    },
+    {
+      "epoch": 0.9919632606199771,
+      "grad_norm": 1.7453018426895142,
+      "learning_rate": 7.75e-05,
+      "loss": 1.2575,
+      "step": 27
+    },
+    {
+      "epoch": 1.0287026406429391,
+      "grad_norm": 2.426978349685669,
+      "learning_rate": 7.577868759557654e-05,
+      "loss": 3.0889,
+      "step": 28
+    },
+    {
+      "epoch": 1.0654420206659012,
+      "grad_norm": 1.067915916442871,
+      "learning_rate": 7.401782177833148e-05,
+      "loss": 1.7397,
+      "step": 29
+    },
+    {
+      "epoch": 1.1021814006888633,
+      "grad_norm": 1.5281691551208496,
+      "learning_rate": 7.222075445642904e-05,
+      "loss": 1.7003,
+      "step": 30
+    },
+    {
+      "epoch": 1.1389207807118256,
+      "grad_norm": 1.1140716075897217,
+      "learning_rate": 7.03909064496551e-05,
+      "loss": 1.7107,
+      "step": 31
+    },
+    {
+      "epoch": 1.1756601607347876,
+      "grad_norm": 0.9925709366798401,
+      "learning_rate": 6.853176097769229e-05,
+      "loss": 1.2638,
+      "step": 32
+    },
+    {
+      "epoch": 1.2123995407577497,
+      "grad_norm": 1.4794470071792603,
+      "learning_rate": 6.664685702961344e-05,
+      "loss": 1.2194,
+      "step": 33
+    },
+    {
+      "epoch": 1.2491389207807118,
+      "grad_norm": 0.6699503660202026,
+      "learning_rate": 6.473978262721463e-05,
+      "loss": 0.531,
+      "step": 34
+    },
+    {
+      "epoch": 1.2858783008036738,
+      "grad_norm": 1.4114007949829102,
+      "learning_rate": 6.281416799501188e-05,
+      "loss": 2.5394,
+      "step": 35
+    },
+    {
+      "epoch": 1.322617680826636,
+      "grad_norm": 1.0232292413711548,
+      "learning_rate": 6.087367864990233e-05,
+      "loss": 1.6208,
+      "step": 36
+    },
+    {
+      "epoch": 1.3593570608495982,
+      "grad_norm": 1.3607043027877808,
+      "learning_rate": 5.8922008423644624e-05,
+      "loss": 1.1508,
+      "step": 37
+    },
+    {
+      "epoch": 1.3960964408725602,
+      "grad_norm": 1.3985986709594727,
+      "learning_rate": 5.696287243144013e-05,
+      "loss": 1.4222,
+      "step": 38
+    },
+    {
+      "epoch": 1.4328358208955223,
+      "grad_norm": 1.3112035989761353,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 1.1613,
+      "step": 39
+    },
+    {
+      "epoch": 1.4695752009184844,
+      "grad_norm": 1.5417652130126953,
+      "learning_rate": 5.303712756855988e-05,
+      "loss": 0.938,
+      "step": 40
+    },
+    {
+      "epoch": 1.5063145809414467,
+      "grad_norm": 1.0807812213897705,
+      "learning_rate": 5.107799157635538e-05,
+      "loss": 1.291,
+      "step": 41
+    },
+    {
+      "epoch": 1.5430539609644087,
+      "grad_norm": 0.9991649985313416,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 1.8465,
+      "step": 42
+    },
+    {
+      "epoch": 1.5797933409873708,
+      "grad_norm": 1.1210612058639526,
+      "learning_rate": 4.718583200498814e-05,
+      "loss": 1.1593,
+      "step": 43
+    },
+    {
+      "epoch": 1.616532721010333,
+      "grad_norm": 1.4225951433181763,
+      "learning_rate": 4.526021737278538e-05,
+      "loss": 1.2247,
+      "step": 44
+    },
+    {
+      "epoch": 1.653272101033295,
+      "grad_norm": 1.6108145713806152,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 1.4636,
+      "step": 45
+    },
+    {
+      "epoch": 1.6900114810562572,
+      "grad_norm": 1.3490177392959595,
+      "learning_rate": 4.146823902230772e-05,
+      "loss": 0.9067,
+      "step": 46
+    },
+    {
+      "epoch": 1.7267508610792193,
+      "grad_norm": 1.700265884399414,
+      "learning_rate": 3.960909355034491e-05,
+      "loss": 0.9955,
+      "step": 47
+    },
+    {
+      "epoch": 1.7634902411021813,
+      "grad_norm": 1.0068745613098145,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 1.0694,
+      "step": 48
+    },
+    {
+      "epoch": 1.8002296211251436,
+      "grad_norm": 1.1462795734405518,
+      "learning_rate": 3.598217822166854e-05,
+      "loss": 1.4829,
+      "step": 49
+    },
+    {
+      "epoch": 1.8369690011481055,
+      "grad_norm": 1.6393139362335205,
+      "learning_rate": 3.422131240442349e-05,
+      "loss": 1.2071,
+      "step": 50
+    },
+    {
+      "epoch": 1.8369690011481055,
+      "eval_loss": NaN,
+      "eval_runtime": 1.5666,
+      "eval_samples_per_second": 31.917,
+      "eval_steps_per_second": 8.298,
+      "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