Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b0c7a0f3c58c6d22e67390695d3bd0dec92c33a6c60893f9f77328251448aaf
+oid sha256:922a105306a94c623a2af239b54a49970e9c7e7d3e734ed733294999e54771fd
 size 201361312

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef18d31fd341beeed320b7279057cd5b2fa251e26f30e9350c55f396f928cc54
+oid sha256:ab260f94b869e5f23b2bcc25a3154874be77747a93a2d3b10fbf7e80ebc99d25
 size 402868986

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9dee56ccbdbd1e8bce3c8fc706d455ffc45d9a37c3a2fa2266f1bb4a5f41c7a4
+oid sha256:bec9522bb3f87669529ca9ef64e20b4eed14af626f6d5b018c061c1df473d70f
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a1389ea04de3164895c225428933963d138158dc42e5bff7b41e38d190eff75b
+oid sha256:ed036ad75662c5988dc0dd9c0cc412e11bcc76149e15bfa0a86bd42153a36f0c
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1095776e2efe365ac0e30c9f640f65724432ffab6c66e379f7333ea3638045b2
+oid sha256:afda1fc1cf80745ffb58cb0f9c3f3ba9f7f53ff856da0db74b766c8f364bc758
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b471660b834a67899a1c97c5b150fc2e886206e35059fc6bfdda5980177b0f96
+oid sha256:a7cc7b3d5c46111bbce6365d02c33f94f3abbf1cf31dd13292dd41dcd6e64d44
 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": 0.03677130490541458,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.20085362791865427,
+  "best_metric": 0.03200618177652359,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.40170725583730854,
   "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": 5.28,
       "eval_steps_per_second": 1.373,
       "step": 25
+    },
+    {
+      "epoch": 0.20888777303540046,
+      "grad_norm": 1.0484713315963745,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 2.2505,
+      "step": 26
+    },
+    {
+      "epoch": 0.21692191815214662,
+      "grad_norm": 0.9066623449325562,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 1.9859,
+      "step": 27
+    },
+    {
+      "epoch": 0.22495606326889278,
+      "grad_norm": 1.164398431777954,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 2.5357,
+      "step": 28
+    },
+    {
+      "epoch": 0.23299020838563897,
+      "grad_norm": 1.3508579730987549,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 1.3002,
+      "step": 29
+    },
+    {
+      "epoch": 0.24102435350238513,
+      "grad_norm": 1.0967586040496826,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 2.3312,
+      "step": 30
+    },
+    {
+      "epoch": 0.24905849861913132,
+      "grad_norm": 1.0712722539901733,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 1.8359,
+      "step": 31
+    },
+    {
+      "epoch": 0.2570926437358775,
+      "grad_norm": 1.9306401014328003,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 3.1769,
+      "step": 32
+    },
+    {
+      "epoch": 0.26512678885262364,
+      "grad_norm": 6.797326564788818,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 3.3287,
+      "step": 33
+    },
+    {
+      "epoch": 0.2731609339693698,
+      "grad_norm": 8.896469116210938,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 9.3152,
+      "step": 34
+    },
+    {
+      "epoch": 0.281195079086116,
+      "grad_norm": 16.196805953979492,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 3.3369,
+      "step": 35
+    },
+    {
+      "epoch": 0.2892292242028622,
+      "grad_norm": 1.467756748199463,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 0.103,
+      "step": 36
+    },
+    {
+      "epoch": 0.29726336931960834,
+      "grad_norm": 0.8828189969062805,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 0.0758,
+      "step": 37
+    },
+    {
+      "epoch": 0.3052975144363545,
+      "grad_norm": 3.7422118186950684,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 1.0237,
+      "step": 38
+    },
+    {
+      "epoch": 0.31333165955310066,
+      "grad_norm": 0.6260557770729065,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 0.9247,
+      "step": 39
+    },
+    {
+      "epoch": 0.3213658046698468,
+      "grad_norm": 0.7009216547012329,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 0.6326,
+      "step": 40
+    },
+    {
+      "epoch": 0.32939994978659304,
+      "grad_norm": 0.8966463804244995,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 1.6609,
+      "step": 41
+    },
+    {
+      "epoch": 0.3374340949033392,
+      "grad_norm": 0.7447260618209839,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 0.3863,
+      "step": 42
+    },
+    {
+      "epoch": 0.34546824002008536,
+      "grad_norm": 1.1738234758377075,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 2.4486,
+      "step": 43
+    },
+    {
+      "epoch": 0.3535023851368315,
+      "grad_norm": 1.7264965772628784,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 3.7159,
+      "step": 44
+    },
+    {
+      "epoch": 0.3615365302535777,
+      "grad_norm": 2.1729681491851807,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 3.7855,
+      "step": 45
+    },
+    {
+      "epoch": 0.3695706753703239,
+      "grad_norm": 8.315459251403809,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 7.1132,
+      "step": 46
+    },
+    {
+      "epoch": 0.37760482048707006,
+      "grad_norm": 7.717396259307861,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 3.3517,
+      "step": 47
+    },
+    {
+      "epoch": 0.3856389656038162,
+      "grad_norm": 0.874803364276886,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 0.0699,
+      "step": 48
+    },
+    {
+      "epoch": 0.3936731107205624,
+      "grad_norm": 0.9983109831809998,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 0.0663,
+      "step": 49
+    },
+    {
+      "epoch": 0.40170725583730854,
+      "grad_norm": 0.7316238880157471,
+      "learning_rate": 1e-05,
+      "loss": 0.0602,
+      "step": 50
+    },
+    {
+      "epoch": 0.40170725583730854,
+      "eval_loss": 0.03200618177652359,
+      "eval_runtime": 9.516,
+      "eval_samples_per_second": 5.254,
+      "eval_steps_per_second": 1.366,
+      "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": 2.539684357996544e+17,
+  "total_flos": 5.083077645738967e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null