Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:09fc1fe6cd3408bfc7fd1630e3c13b3f59e94ed09ce037fb97bb1cc10c92f2fa
+oid sha256:f3e50582e4b3077ce1b3c079e05431ee3e0ebf16f769bcfb991541dabf1d2046
 size 319876032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16c8fe5747dbe45db5b713e5822e9591e191fb41d2074242255e4ce6268c0f26
+oid sha256:f9c1d5c67c4745347f4671a04dff61c07adcff9a94614aee59df32beb5c6659b
 size 640009682

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb2584afa297318af54415269ee51c870c87a184e9d7cc995bfbab377f33fd82
+oid sha256:1eed6832f47a600282708793eafe394a78973dcd1edb5c8ced1d2414469f9aab
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8de12a58b5d531be5e48aa27d5990c46de4c7c42c3f4af4a248a24bce087a86c
+oid sha256:ca047d4c82f8b2806a8ad264ad7b8980f23024db04e48d6a06142618a08802e2
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff515d5b395c6c94cd05f93c6861533e427df0ec2d70a37e5d6408596230a6e2
+oid sha256:bdee61b08f2e882a43d7c17ba12f79dc9073a9487bc8b78c7001dc23b58b48ff
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:14478563f982de6d3e11bb28c159104efb1a637985fa65b7945edae61dd99828
+oid sha256:520081ec4b76df206094dcb89cb6c67b961479ce6b7e962bc819aa231dda705d
 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": 9.30055193748558e-06,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.060505218575102104,
+  "best_metric": 7.964809810800944e-06,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.12101043715020421,
   "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": 28.53,
       "eval_steps_per_second": 7.418,
       "step": 25
+    },
+    {
+      "epoch": 0.06292542731810619,
+      "grad_norm": 5.305076599121094,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.7256,
+      "step": 26
+    },
+    {
+      "epoch": 0.06534563606111027,
+      "grad_norm": 0.0032348379027098417,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 0.0001,
+      "step": 27
+    },
+    {
+      "epoch": 0.06776584480411435,
+      "grad_norm": 0.0031625886913388968,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 0.0001,
+      "step": 28
+    },
+    {
+      "epoch": 0.07018605354711843,
+      "grad_norm": 0.0025414996780455112,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 0.0001,
+      "step": 29
+    },
+    {
+      "epoch": 0.07260626229012253,
+      "grad_norm": 0.0029857661575078964,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 0.0001,
+      "step": 30
+    },
+    {
+      "epoch": 0.07502647103312661,
+      "grad_norm": 0.002130489330738783,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 0.0001,
+      "step": 31
+    },
+    {
+      "epoch": 0.07744667977613069,
+      "grad_norm": 0.008826849050819874,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 0.0001,
+      "step": 32
+    },
+    {
+      "epoch": 0.07986688851913477,
+      "grad_norm": 7.8028435707092285,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 0.0752,
+      "step": 33
+    },
+    {
+      "epoch": 0.08228709726213886,
+      "grad_norm": 0.00196323124691844,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 0.0001,
+      "step": 34
+    },
+    {
+      "epoch": 0.08470730600514294,
+      "grad_norm": 0.00294469203799963,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 0.0001,
+      "step": 35
+    },
+    {
+      "epoch": 0.08712751474814703,
+      "grad_norm": 0.002938171150162816,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 0.0001,
+      "step": 36
+    },
+    {
+      "epoch": 0.08954772349115112,
+      "grad_norm": 0.003095130668953061,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 0.0001,
+      "step": 37
+    },
+    {
+      "epoch": 0.0919679322341552,
+      "grad_norm": 7.44374942779541,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 1.1725,
+      "step": 38
+    },
+    {
+      "epoch": 0.09438814097715928,
+      "grad_norm": 0.0023158295080065727,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 0.0001,
+      "step": 39
+    },
+    {
+      "epoch": 0.09680834972016336,
+      "grad_norm": 0.0025635056663304567,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 0.0001,
+      "step": 40
+    },
+    {
+      "epoch": 0.09922855846316744,
+      "grad_norm": 0.0020631614606827497,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 0.0001,
+      "step": 41
+    },
+    {
+      "epoch": 0.10164876720617154,
+      "grad_norm": 0.002352768089622259,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 0.0001,
+      "step": 42
+    },
+    {
+      "epoch": 0.10406897594917562,
+      "grad_norm": 0.002028629882261157,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 0.0001,
+      "step": 43
+    },
+    {
+      "epoch": 0.1064891846921797,
+      "grad_norm": 0.002459727693349123,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 0.0001,
+      "step": 44
+    },
+    {
+      "epoch": 0.10890939343518379,
+      "grad_norm": 0.0026463617105036974,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 0.0001,
+      "step": 45
+    },
+    {
+      "epoch": 0.11132960217818787,
+      "grad_norm": 0.0025314614176750183,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 0.0001,
+      "step": 46
+    },
+    {
+      "epoch": 0.11374981092119195,
+      "grad_norm": 0.0033576921559870243,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 0.0001,
+      "step": 47
+    },
+    {
+      "epoch": 0.11617001966419603,
+      "grad_norm": 0.004283377435058355,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 0.0001,
+      "step": 48
+    },
+    {
+      "epoch": 0.11859022840720013,
+      "grad_norm": 17.353458404541016,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 0.1331,
+      "step": 49
+    },
+    {
+      "epoch": 0.12101043715020421,
+      "grad_norm": 82.0785903930664,
+      "learning_rate": 1e-05,
+      "loss": 0.1721,
+      "step": 50
+    },
+    {
+      "epoch": 0.12101043715020421,
+      "eval_loss": 7.964809810800944e-06,
+      "eval_runtime": 1.7366,
+      "eval_samples_per_second": 28.793,
+      "eval_steps_per_second": 7.486,
+      "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": 2.631221648430203e+17,
+  "total_flos": 5.262443296860406e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null