Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:138382ada37278656e20dac6e50229c5d1709cd116fa5776b9edb03eab84a4d8
+oid sha256:e70ecc782780c4f102324599220a9debba24a622a0ff2e485bbb51b22a4a5cbc
 size 70430032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10f54a716a8861aa08a36bd36caf2b6a691a951cd4bc53772e5ec76d3220a31d
+oid sha256:93f6ac868b98b6170f68911505ab7302d7a6b499b2b11f0bd97a611be40f607d
 size 141053442

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:83b0afd217c69ae7915b01678d660351de935938871ec1f2f869362c8fa78728
+oid sha256:a80d62cd98c8417e8d15bec909059478e2063dd1c0f19e8f2dc17b626c36349f
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f6e144e766e3d541075112d87dcca6f0cbf6f2c169c4d48932332777c38be16
+oid sha256:64f28b60fd47e3433106546373871b12fb32ad393589362bdfae6fa1837f5663
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fbb1137992914e412e5bedc32facd544a1f54bfcf242350d70dbde7b391968ab
+oid sha256:e67c4cb4254345dfe5db3a8dc5a8891cb399cde7c563a21b7d9f7ef21f442b4d
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60efc31c13552e9c12aefa81638a6573e2cd6550905b1babdd10b0f9950ba07f
+oid sha256:34ac966045990c670e4349a9a7083d1259ae5a19a2dd961b7dade2503b7c3a5d
 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": 3.9596316128154285e-06,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.0607579554947976,
+  "best_metric": 2.623548425617628e-06,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.1215159109895952,
   "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": 33.793,
       "eval_steps_per_second": 8.786,
       "step": 25
+    },
+    {
+      "epoch": 0.0631882737145895,
+      "grad_norm": 0.00042510413913987577,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.0,
+      "step": 26
+    },
+    {
+      "epoch": 0.06561859193438141,
+      "grad_norm": 0.00035989907337352633,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 0.06804891015417332,
+      "grad_norm": 0.00035917776403948665,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 0.0,
+      "step": 28
+    },
+    {
+      "epoch": 0.07047922837396521,
+      "grad_norm": 0.0003286278515588492,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 0.0,
+      "step": 29
+    },
+    {
+      "epoch": 0.07290954659375712,
+      "grad_norm": 0.00031797558767721057,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.07533986481354903,
+      "grad_norm": 0.00030757233616895974,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 0.0,
+      "step": 31
+    },
+    {
+      "epoch": 0.07777018303334093,
+      "grad_norm": 0.00030923346639610827,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 0.0,
+      "step": 32
+    },
+    {
+      "epoch": 0.08020050125313283,
+      "grad_norm": 0.00029912899481132627,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 0.0,
+      "step": 33
+    },
+    {
+      "epoch": 0.08263081947292474,
+      "grad_norm": 0.0002802808303385973,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 0.0,
+      "step": 34
+    },
+    {
+      "epoch": 0.08506113769271664,
+      "grad_norm": 0.0002648854861035943,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 0.0,
+      "step": 35
+    },
+    {
+      "epoch": 0.08749145591250855,
+      "grad_norm": 0.00025963204097934067,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 0.0,
+      "step": 36
+    },
+    {
+      "epoch": 0.08992177413230044,
+      "grad_norm": 0.00027164211496710777,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 0.0,
+      "step": 37
+    },
+    {
+      "epoch": 0.09235209235209235,
+      "grad_norm": 0.0002490248007234186,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.0,
+      "step": 38
+    },
+    {
+      "epoch": 0.09478241057188426,
+      "grad_norm": 0.00024242346989922225,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 0.0,
+      "step": 39
+    },
+    {
+      "epoch": 0.09721272879167615,
+      "grad_norm": 0.00022952283325139433,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 0.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.09964304701146806,
+      "grad_norm": 0.0002252504782518372,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 0.0,
+      "step": 41
+    },
+    {
+      "epoch": 0.10207336523125997,
+      "grad_norm": 0.00022119212371762842,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 0.0,
+      "step": 42
+    },
+    {
+      "epoch": 0.10450368345105188,
+      "grad_norm": 0.00021124388149473816,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 0.0,
+      "step": 43
+    },
+    {
+      "epoch": 0.10693400167084377,
+      "grad_norm": 0.00021805534197483212,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 0.0,
+      "step": 44
+    },
+    {
+      "epoch": 0.10936431989063568,
+      "grad_norm": 0.00021745653066318482,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 0.0,
+      "step": 45
+    },
+    {
+      "epoch": 0.11179463811042759,
+      "grad_norm": 0.0002112941292580217,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 0.0,
+      "step": 46
+    },
+    {
+      "epoch": 0.1142249563302195,
+      "grad_norm": 0.00020633387612178922,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 0.0,
+      "step": 47
+    },
+    {
+      "epoch": 0.11665527455001139,
+      "grad_norm": 0.00020409161515999585,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 0.0,
+      "step": 48
+    },
+    {
+      "epoch": 0.1190855927698033,
+      "grad_norm": 0.00021153417765162885,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 0.0,
+      "step": 49
+    },
+    {
+      "epoch": 0.1215159109895952,
+      "grad_norm": 0.00021407307940535247,
+      "learning_rate": 1e-05,
+      "loss": 0.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.1215159109895952,
+      "eval_loss": 2.623548425617628e-06,
+      "eval_runtime": 1.4808,
+      "eval_samples_per_second": 33.766,
+      "eval_steps_per_second": 8.779,
+      "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": 1.476965970214912e+16,
+  "total_flos": 2.953470533435392e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null