Training in progress, step 43, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d31afbd7cea36e1adf289fb4f9de2e6de1a801425c07f5815abf57a51418f20
+oid sha256:c41d03449ab1c3c1bccf599d64eabf550dedb42a2caa53ded6e299f59c2c2156
 size 97728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:02000612a0f31798b8d29f220004893b686ad8145f2f706644d7a460af778f0b
+oid sha256:d5758ba8f0d5d79f526604b4ca60ee19debc708804b8d4f06d085c5217e1f745
 size 212298

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:413e28c341f2b119009ad612fcc23d19c096e95a6fb4accaeb6d5ca17bb015e1
+oid sha256:39a7d56fc4e6b8b2ea7c485352ffc371bebcbee3abae231250af778f25fc42b7
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d8aa13548823fa6f28836c8f83fbd2d1467ddabbc1698fdf8f0fc2f5ff79a30
+oid sha256:2e2adabed50d05ebda056e2c18b8f47f9647c13f563123d8961e65f81c3a00cf
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:af6814247bb7d1ec9c74c82a406e1625b3c233602ca47536cca792b8add2a670
+oid sha256:b7d264ca19fb1897d09f117ddcbf01ebee35113c87dc2ae173165d0c41506eaa
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:019dc0d03930ca855b32c0b14ec69b471492a934b278e602a8813f1e7a0c3cf2
+oid sha256:32c71307301598fe1c25cd5099a2b242fff8f4a14df78460b5fe0cff0923ca64
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f73e6deadf3f08547d8bef9e9b3d87995c0c2ef87d51b8801270b8b2d32ac55
+oid sha256:d9ca16dc5125aa616f8880e7477dabd4029e096d950b1e4b31474d314c00eace
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 10.368718147277832,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 1.7621145374449338,
+  "epoch": 3.0308370044052864,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 43,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,132 @@
       "eval_samples_per_second": 266.863,
       "eval_steps_per_second": 69.384,
       "step": 25
+    },
+    {
+      "epoch": 1.8325991189427313,
+      "grad_norm": 0.23158004879951477,
+      "learning_rate": 4.307583240115024e-05,
+      "loss": 10.6369,
+      "step": 26
+    },
+    {
+      "epoch": 1.9030837004405288,
+      "grad_norm": 0.23809461295604706,
+      "learning_rate": 3.9789240471617385e-05,
+      "loss": 10.3091,
+      "step": 27
+    },
+    {
+      "epoch": 1.973568281938326,
+      "grad_norm": 0.2416485697031021,
+      "learning_rate": 3.659191132728971e-05,
+      "loss": 10.3553,
+      "step": 28
+    },
+    {
+      "epoch": 2.0440528634361232,
+      "grad_norm": 0.4224947988986969,
+      "learning_rate": 3.350260816694816e-05,
+      "loss": 19.7858,
+      "step": 29
+    },
+    {
+      "epoch": 2.1145374449339207,
+      "grad_norm": 0.21910975873470306,
+      "learning_rate": 3.0539460249945056e-05,
+      "loss": 9.4865,
+      "step": 30
+    },
+    {
+      "epoch": 2.185022026431718,
+      "grad_norm": 0.2511979639530182,
+      "learning_rate": 2.7719856506501306e-05,
+      "loss": 10.3491,
+      "step": 31
+    },
+    {
+      "epoch": 2.255506607929515,
+      "grad_norm": 0.21490304172039032,
+      "learning_rate": 2.5060343492549566e-05,
+      "loss": 9.5953,
+      "step": 32
+    },
+    {
+      "epoch": 2.3259911894273126,
+      "grad_norm": 0.25810712575912476,
+      "learning_rate": 2.257652828796459e-05,
+      "loss": 11.2614,
+      "step": 33
+    },
+    {
+      "epoch": 2.39647577092511,
+      "grad_norm": 0.24142640829086304,
+      "learning_rate": 2.0282986908012567e-05,
+      "loss": 10.2079,
+      "step": 34
+    },
+    {
+      "epoch": 2.4669603524229076,
+      "grad_norm": 0.2538101077079773,
+      "learning_rate": 1.819317876549771e-05,
+      "loss": 10.3802,
+      "step": 35
+    },
+    {
+      "epoch": 2.537444933920705,
+      "grad_norm": 0.26082903146743774,
+      "learning_rate": 1.631936768557596e-05,
+      "loss": 11.26,
+      "step": 36
+    },
+    {
+      "epoch": 2.607929515418502,
+      "grad_norm": 0.23028650879859924,
+      "learning_rate": 1.4672549936752506e-05,
+      "loss": 9.44,
+      "step": 37
+    },
+    {
+      "epoch": 2.6784140969162995,
+      "grad_norm": 0.2575504779815674,
+      "learning_rate": 1.3262389700405744e-05,
+      "loss": 10.3462,
+      "step": 38
+    },
+    {
+      "epoch": 2.748898678414097,
+      "grad_norm": 0.234547421336174,
+      "learning_rate": 1.2097162357528127e-05,
+      "loss": 9.6301,
+      "step": 39
+    },
+    {
+      "epoch": 2.8193832599118944,
+      "grad_norm": 0.27662456035614014,
+      "learning_rate": 1.1183705925499948e-05,
+      "loss": 11.245,
+      "step": 40
+    },
+    {
+      "epoch": 2.889867841409692,
+      "grad_norm": 0.2530806362628937,
+      "learning_rate": 1.0527380929884324e-05,
+      "loss": 10.1797,
+      "step": 41
+    },
+    {
+      "epoch": 2.960352422907489,
+      "grad_norm": 0.267768919467926,
+      "learning_rate": 1.013203894673168e-05,
+      "loss": 10.3897,
+      "step": 42
+    },
+    {
+      "epoch": 3.0308370044052864,
+      "grad_norm": 0.47571516036987305,
+      "learning_rate": 1e-05,
+      "loss": 20.5396,
+      "step": 43
     }
   ],
   "logging_steps": 1,
@@ -221,12 +347,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 21457537400832.0,
+  "total_flos": 36920863948800.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null