Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:12f5847c1576df76c6207598fecdf13e01409ee3fcacd1eb9d3a3c159157806d
+oid sha256:da65b1535a271beea5e16105734bce813d8ceac77724e7b9d82e89bcce0aafbf
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43be0dd0d7f3d68d1a8e4a56f5685c282f6c00afbd5cefccfc433b0ad06bb0ce
+oid sha256:1f43deec71377a50311e51768a90f266f29108b88ff046ce65ac255096ceee85
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b3ec34e942a6dfbfca94ecd73ebd04fd479b3380b4d907fe9877188a9b17dbd1
+oid sha256:29f5114ede452eac424f705ad3fca2b3083b1534733eaa43957f852cdbc21aa2
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:23b6592de88d307bf8f1a38382160daee13c2e1018c34f24f2540d5d93b8d39f
+oid sha256:83a27994044477d801c4f3a821bf771f2ec66c90b193711059ed5612727851fa
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:20dd695fc8310862c15158ac54641336569b15aade3c529adf714c29cad5418f
+oid sha256:8ec446d236138a6edbee88eb73292de7bf95abeecb18078e6377fcc0f0816349
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad21b499b2adcc614c1ce65b531533e04cf4df4465d0d308a76728f9a757d771
+oid sha256:bfaa585ab69044633597967c364ec19a8dd3266db2886c43d9c6a6debc0721e6
 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": 0.5146859884262085,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.029708853238265002,
+  "best_metric": 0.34419700503349304,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.059417706476530004,
   "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": 21.305,
       "eval_steps_per_second": 5.539,
       "step": 25
+    },
+    {
+      "epoch": 0.030897207367795602,
+      "grad_norm": 1.3286805152893066,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.7485,
+      "step": 26
+    },
+    {
+      "epoch": 0.03208556149732621,
+      "grad_norm": 1.5405412912368774,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 0.5451,
+      "step": 27
+    },
+    {
+      "epoch": 0.033273915626856804,
+      "grad_norm": 1.233147382736206,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 0.5002,
+      "step": 28
+    },
+    {
+      "epoch": 0.0344622697563874,
+      "grad_norm": 1.0292119979858398,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 0.4288,
+      "step": 29
+    },
+    {
+      "epoch": 0.035650623885918005,
+      "grad_norm": 1.3014405965805054,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 0.4733,
+      "step": 30
+    },
+    {
+      "epoch": 0.0368389780154486,
+      "grad_norm": 1.4494003057479858,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 0.494,
+      "step": 31
+    },
+    {
+      "epoch": 0.038027332144979206,
+      "grad_norm": 1.3643971681594849,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 0.5351,
+      "step": 32
+    },
+    {
+      "epoch": 0.0392156862745098,
+      "grad_norm": 1.1455105543136597,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 0.525,
+      "step": 33
+    },
+    {
+      "epoch": 0.04040404040404041,
+      "grad_norm": 1.1091620922088623,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 0.447,
+      "step": 34
+    },
+    {
+      "epoch": 0.041592394533571005,
+      "grad_norm": 1.2071998119354248,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 0.6096,
+      "step": 35
+    },
+    {
+      "epoch": 0.0427807486631016,
+      "grad_norm": 1.4972431659698486,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 0.5981,
+      "step": 36
+    },
+    {
+      "epoch": 0.043969102792632206,
+      "grad_norm": 1.3450655937194824,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 0.6781,
+      "step": 37
+    },
+    {
+      "epoch": 0.0451574569221628,
+      "grad_norm": 1.5478042364120483,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.8215,
+      "step": 38
+    },
+    {
+      "epoch": 0.04634581105169341,
+      "grad_norm": 1.301225185394287,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 0.4669,
+      "step": 39
+    },
+    {
+      "epoch": 0.047534165181224004,
+      "grad_norm": 1.215628743171692,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 0.4811,
+      "step": 40
+    },
+    {
+      "epoch": 0.0487225193107546,
+      "grad_norm": 1.021491289138794,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 0.37,
+      "step": 41
+    },
+    {
+      "epoch": 0.049910873440285206,
+      "grad_norm": 1.1163012981414795,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 0.3745,
+      "step": 42
+    },
+    {
+      "epoch": 0.0510992275698158,
+      "grad_norm": 1.2882263660430908,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 0.4898,
+      "step": 43
+    },
+    {
+      "epoch": 0.05228758169934641,
+      "grad_norm": 1.1887884140014648,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 0.4594,
+      "step": 44
+    },
+    {
+      "epoch": 0.053475935828877004,
+      "grad_norm": 1.2757731676101685,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 0.3928,
+      "step": 45
+    },
+    {
+      "epoch": 0.05466428995840761,
+      "grad_norm": 1.0226280689239502,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 0.4737,
+      "step": 46
+    },
+    {
+      "epoch": 0.055852644087938205,
+      "grad_norm": 1.1754165887832642,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 0.5274,
+      "step": 47
+    },
+    {
+      "epoch": 0.0570409982174688,
+      "grad_norm": 1.3346490859985352,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 0.5732,
+      "step": 48
+    },
+    {
+      "epoch": 0.058229352346999406,
+      "grad_norm": 1.156563401222229,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 0.5148,
+      "step": 49
+    },
+    {
+      "epoch": 0.059417706476530004,
+      "grad_norm": 1.2868088483810425,
+      "learning_rate": 1e-05,
+      "loss": 0.6007,
+      "step": 50
+    },
+    {
+      "epoch": 0.059417706476530004,
+      "eval_loss": 0.34419700503349304,
+      "eval_runtime": 2.344,
+      "eval_samples_per_second": 21.331,
+      "eval_steps_per_second": 5.546,
+      "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": 3.02134233260884e+17,
+  "total_flos": 6.037089589846344e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null