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:e2cb59863ce07573c0cbafc6a3c447502de819600d3668c6164e9fd3981c2b2c
+oid sha256:3f2581a94647f764a28c2918d8d727e85b9fb2486485a4e5b857afbe2a41e5e8
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d4492fbf2c5108de4cc20fee1330e4e85865d8355253575f5f2b1d7acbf20449
+oid sha256:b33b949b6bc108dd2ac761981bd5e7eeedd0b7b816678d40a9458f1db1104932
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ee894b648bff50a24edb79a5cb9d259d702f40b5fc99f5e98e208fea2773d08e
+oid sha256:67242176b558ffbe77ca81edacc2aface2eac28cfb6ff90028e4d4576caa3c97
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:52bfada1e745d8bdac7842fa0d4412392ed19502351a418f105633b57806b972
+oid sha256:535da3300c116e74d7a05530913ebda301823d414dfaf1f776d6b8c07430f052
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f0c2f937718c4f9a2b4cb93ece9fe4fdc73c2e8040a41389a9a0d262b692d9b
+oid sha256:fbfeac0e5570816b31b71ca9aa7ef9075c641a095f41c83f43b784b72e89627f
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:af52ad1aa0eb7908b3e09220b4742e38d4962e0c4254d99404c64ba7995b1465
+oid sha256:9a80e2248707479650e1610b9dc6f81a9ebd4dd58d5eb787286cee99e9daa6be
 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": 0.09762722998857498,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.1328462304882099,
+  "best_metric": 0.03121613711118698,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.2656924609764198,
   "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": 14.295,
       "eval_steps_per_second": 3.717,
       "step": 25
+    },
+    {
+      "epoch": 0.1381600797077383,
+      "grad_norm": 1.816712498664856,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.1879,
+      "step": 26
+    },
+    {
+      "epoch": 0.14347392892726668,
+      "grad_norm": 2.036473274230957,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 0.1885,
+      "step": 27
+    },
+    {
+      "epoch": 0.14878777814679509,
+      "grad_norm": 2.3719797134399414,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 0.137,
+      "step": 28
+    },
+    {
+      "epoch": 0.1541016273663235,
+      "grad_norm": 1.672696590423584,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 0.1344,
+      "step": 29
+    },
+    {
+      "epoch": 0.15941547658585187,
+      "grad_norm": 2.002915859222412,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 0.1307,
+      "step": 30
+    },
+    {
+      "epoch": 0.16472932580538027,
+      "grad_norm": 1.9717336893081665,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 0.0723,
+      "step": 31
+    },
+    {
+      "epoch": 0.17004317502490868,
+      "grad_norm": 2.640728712081909,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 0.1429,
+      "step": 32
+    },
+    {
+      "epoch": 0.17535702424443705,
+      "grad_norm": 2.67779803276062,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 0.2118,
+      "step": 33
+    },
+    {
+      "epoch": 0.18067087346396546,
+      "grad_norm": 2.2781598567962646,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 0.1246,
+      "step": 34
+    },
+    {
+      "epoch": 0.18598472268349386,
+      "grad_norm": 1.9362671375274658,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 0.1466,
+      "step": 35
+    },
+    {
+      "epoch": 0.19129857190302224,
+      "grad_norm": 1.3575589656829834,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 0.0624,
+      "step": 36
+    },
+    {
+      "epoch": 0.19661242112255065,
+      "grad_norm": 1.8417307138442993,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 0.1473,
+      "step": 37
+    },
+    {
+      "epoch": 0.20192627034207905,
+      "grad_norm": 1.4421743154525757,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.1223,
+      "step": 38
+    },
+    {
+      "epoch": 0.20724011956160743,
+      "grad_norm": 1.2103627920150757,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 0.0951,
+      "step": 39
+    },
+    {
+      "epoch": 0.21255396878113583,
+      "grad_norm": 1.4762458801269531,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 0.1311,
+      "step": 40
+    },
+    {
+      "epoch": 0.21786781800066424,
+      "grad_norm": 1.3953089714050293,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 0.1134,
+      "step": 41
+    },
+    {
+      "epoch": 0.22318166722019261,
+      "grad_norm": 1.0033924579620361,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 0.1072,
+      "step": 42
+    },
+    {
+      "epoch": 0.22849551643972102,
+      "grad_norm": 1.3283861875534058,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 0.0743,
+      "step": 43
+    },
+    {
+      "epoch": 0.23380936565924942,
+      "grad_norm": 1.3830900192260742,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 0.0845,
+      "step": 44
+    },
+    {
+      "epoch": 0.2391232148787778,
+      "grad_norm": 1.0678446292877197,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 0.0436,
+      "step": 45
+    },
+    {
+      "epoch": 0.2444370640983062,
+      "grad_norm": 1.7523692846298218,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 0.0892,
+      "step": 46
+    },
+    {
+      "epoch": 0.2497509133178346,
+      "grad_norm": 1.321276068687439,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 0.0527,
+      "step": 47
+    },
+    {
+      "epoch": 0.255064762537363,
+      "grad_norm": 1.239159345626831,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 0.0494,
+      "step": 48
+    },
+    {
+      "epoch": 0.2603786117568914,
+      "grad_norm": 2.1219425201416016,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 0.0874,
+      "step": 49
+    },
+    {
+      "epoch": 0.2656924609764198,
+      "grad_norm": 1.0668234825134277,
+      "learning_rate": 1e-05,
+      "loss": 0.0246,
+      "step": 50
+    },
+    {
+      "epoch": 0.2656924609764198,
+      "eval_loss": 0.03121613711118698,
+      "eval_runtime": 3.4987,
+      "eval_samples_per_second": 14.291,
+      "eval_steps_per_second": 3.716,
+      "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": 2.984041808658432e+17,
+  "total_flos": 5.968083617316864e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null