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:a14e8e71415d5a76726bf0963a2b5ad3eeaf3156eaad46de17217914799aee99
+oid sha256:2110e91a9a8737c0c3c097b52251503ed42a2eb8d150e753e46b3bc1260e485d
 size 400084608

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e26b1e1ba8cd7ec89d563d557ab4e671cc7ea4752387a49410ad4df0c0668865
+oid sha256:8aebcc21c44cffaf58411a81216955213c7979eb651c6614df79be4902cd1487
 size 800394282

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ef018eb42d910f119339e0762739377d16aca0241d2b784af1824bf414b965a
+oid sha256:c446382304e967e647c6f685b41699f34424d9c055a9681448f44a107edecc78
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d7ecef26408fb57fb7f215d9bec01403e98cab62ddac8aa7d17c10108c39285
+oid sha256:93608881366ab9e4a7b28a050450c0aeb7ca061cb07823d43f92b2415cb2430f
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a1466659f56baeeef5801d958de5f1d8087d5e578a0c394e2377112a118386a1
+oid sha256:97d5b07f32209e17e5e67cbad7a43ba03a3e138fc8c33e5c8821ebb259942bd2
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:24a19072b7cde63aa47d3ff1756f1dab8d626e246251e1a2d33c8d50e72042f8
+oid sha256:b86201378ade65308c72fd7a643d21d1d77d73f5fdd369eda75a8dc2465bdc84
 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": 0.0019476765301078558,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.5979073243647235,
+  "best_metric": 0.0012785379076376557,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 1.2062780269058295,
   "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": 9.816,
       "eval_steps_per_second": 2.552,
       "step": 25
+    },
+    {
+      "epoch": 0.6218236173393124,
+      "grad_norm": 0.04498022794723511,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.0014,
+      "step": 26
+    },
+    {
+      "epoch": 0.6457399103139013,
+      "grad_norm": 0.06719963252544403,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 0.0016,
+      "step": 27
+    },
+    {
+      "epoch": 0.6696562032884903,
+      "grad_norm": 0.07147950679063797,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 0.0015,
+      "step": 28
+    },
+    {
+      "epoch": 0.6935724962630793,
+      "grad_norm": 0.11482597142457962,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 0.0013,
+      "step": 29
+    },
+    {
+      "epoch": 0.7174887892376681,
+      "grad_norm": 0.05224405601620674,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 0.0007,
+      "step": 30
+    },
+    {
+      "epoch": 0.7414050822122571,
+      "grad_norm": 0.0664152279496193,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 0.01,
+      "step": 31
+    },
+    {
+      "epoch": 0.7653213751868461,
+      "grad_norm": 0.038789551705121994,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 0.0021,
+      "step": 32
+    },
+    {
+      "epoch": 0.7892376681614349,
+      "grad_norm": 0.03222445398569107,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 0.0019,
+      "step": 33
+    },
+    {
+      "epoch": 0.8131539611360239,
+      "grad_norm": 0.04085226729512215,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 0.0016,
+      "step": 34
+    },
+    {
+      "epoch": 0.8370702541106129,
+      "grad_norm": 0.041735582053661346,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 0.0013,
+      "step": 35
+    },
+    {
+      "epoch": 0.8609865470852018,
+      "grad_norm": 0.060009196400642395,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 0.0018,
+      "step": 36
+    },
+    {
+      "epoch": 0.8849028400597907,
+      "grad_norm": 0.05532706901431084,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 0.0022,
+      "step": 37
+    },
+    {
+      "epoch": 0.9088191330343797,
+      "grad_norm": 0.009391087107360363,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.0001,
+      "step": 38
+    },
+    {
+      "epoch": 0.9327354260089686,
+      "grad_norm": 0.10321075469255447,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 0.0026,
+      "step": 39
+    },
+    {
+      "epoch": 0.9566517189835575,
+      "grad_norm": 0.03513889014720917,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 0.0003,
+      "step": 40
+    },
+    {
+      "epoch": 0.9805680119581465,
+      "grad_norm": 0.047013089060783386,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 0.0008,
+      "step": 41
+    },
+    {
+      "epoch": 1.014947683109118,
+      "grad_norm": 0.051135145127773285,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 0.0137,
+      "step": 42
+    },
+    {
+      "epoch": 1.038863976083707,
+      "grad_norm": 0.025920534506440163,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 0.001,
+      "step": 43
+    },
+    {
+      "epoch": 1.062780269058296,
+      "grad_norm": 0.02824629843235016,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 0.0013,
+      "step": 44
+    },
+    {
+      "epoch": 1.086696562032885,
+      "grad_norm": 0.0347956158220768,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 0.0011,
+      "step": 45
+    },
+    {
+      "epoch": 1.1106128550074739,
+      "grad_norm": 0.021422594785690308,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 0.0007,
+      "step": 46
+    },
+    {
+      "epoch": 1.1345291479820627,
+      "grad_norm": 0.020450716838240623,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 0.0004,
+      "step": 47
+    },
+    {
+      "epoch": 1.1584454409566518,
+      "grad_norm": 0.04902283474802971,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 0.0012,
+      "step": 48
+    },
+    {
+      "epoch": 1.1823617339312407,
+      "grad_norm": 0.03443044051527977,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 0.0003,
+      "step": 49
+    },
+    {
+      "epoch": 1.2062780269058295,
+      "grad_norm": 0.024215981364250183,
+      "learning_rate": 1e-05,
+      "loss": 0.0002,
+      "step": 50
+    },
+    {
+      "epoch": 1.2062780269058295,
+      "eval_loss": 0.0012785379076376557,
+      "eval_runtime": 4.7582,
+      "eval_samples_per_second": 10.508,
+      "eval_steps_per_second": 2.732,
+      "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": 3.1567025970715034e+17,
+  "total_flos": 6.29218041065898e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null