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:a6f640e20d30913e77828665331c3178423e0e89a7f788659dc6739937386300
+oid sha256:8cc9ee50f95758b54c8f161ed341c2216b14819f446a22ed7671b1055af5d476
 size 48552

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a60d3291074e4bc0595392ffeed1a4e7ae40bd510c1ad07bdbcdd51442e99f1b
+oid sha256:a3955fe701f0bf7969a252b4742c0a5353674398a1cbfe3ad4168eb947d8beda
 size 113994

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c8e24c7259bfbf6ad33e7084f19222af6d4be8e265552e011266bc8897c2eaa6
+oid sha256:9c7e54329a0bc46bc62efeae8121cdc2722effbbe20e932f6ccb54b9f4eaba5c
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e3403cdbf81fcd262aeca932625e7b207de3c69108c53072982b5c95e8d3c1a
+oid sha256:e8f1cebfe1d357c87d55f1744b9fea8f2fba518431be6c81fe3fd2eb1c0f0b05
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3315a415538293d3793b599e19586a353847b68c589d90d7b61ed912ab53cb76
+oid sha256:47749c1f8af1ffe5d9a771cbfe2b3f43f2d527b39b426b4935e01e4b72cd624f
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5971ad341a7c14655e4760ae7986e800b19da4331ba970566e3790af205c74e6
+oid sha256:06944e370dfbed6790f40873f5e8e8e46f0edea35504642f60168d87ce23f66a
 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": 11.931483268737793,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.014359563469270534,
+  "best_metric": 11.930744171142578,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.02871912693854107,
   "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": 293.322,
       "eval_steps_per_second": 76.264,
       "step": 25
+    },
+    {
+      "epoch": 0.014933946008041356,
+      "grad_norm": 0.026962852105498314,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 11.9314,
+      "step": 26
+    },
+    {
+      "epoch": 0.015508328546812177,
+      "grad_norm": 0.02874499186873436,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 11.9315,
+      "step": 27
+    },
+    {
+      "epoch": 0.016082711085583,
+      "grad_norm": 0.028867153450846672,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 11.9317,
+      "step": 28
+    },
+    {
+      "epoch": 0.01665709362435382,
+      "grad_norm": 0.028029875829815865,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 11.9323,
+      "step": 29
+    },
+    {
+      "epoch": 0.01723147616312464,
+      "grad_norm": 0.03006923571228981,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 11.9313,
+      "step": 30
+    },
+    {
+      "epoch": 0.017805858701895463,
+      "grad_norm": 0.031214896589517593,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 11.9311,
+      "step": 31
+    },
+    {
+      "epoch": 0.018380241240666284,
+      "grad_norm": 0.03501607105135918,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 11.9312,
+      "step": 32
+    },
+    {
+      "epoch": 0.018954623779437105,
+      "grad_norm": 0.03202120214700699,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 11.9315,
+      "step": 33
+    },
+    {
+      "epoch": 0.019529006318207927,
+      "grad_norm": 0.03382125496864319,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 11.9313,
+      "step": 34
+    },
+    {
+      "epoch": 0.020103388856978748,
+      "grad_norm": 0.03120032697916031,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 11.9313,
+      "step": 35
+    },
+    {
+      "epoch": 0.02067777139574957,
+      "grad_norm": 0.03863793984055519,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 11.9302,
+      "step": 36
+    },
+    {
+      "epoch": 0.02125215393452039,
+      "grad_norm": 0.04094834253191948,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 11.9311,
+      "step": 37
+    },
+    {
+      "epoch": 0.021826536473291212,
+      "grad_norm": 0.03583959490060806,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 11.9315,
+      "step": 38
+    },
+    {
+      "epoch": 0.022400919012062034,
+      "grad_norm": 0.031415995210409164,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 11.931,
+      "step": 39
+    },
+    {
+      "epoch": 0.022975301550832855,
+      "grad_norm": 0.03263179212808609,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 11.931,
+      "step": 40
+    },
+    {
+      "epoch": 0.023549684089603676,
+      "grad_norm": 0.034333061426877975,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 11.9312,
+      "step": 41
+    },
+    {
+      "epoch": 0.024124066628374498,
+      "grad_norm": 0.036884188652038574,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 11.9314,
+      "step": 42
+    },
+    {
+      "epoch": 0.02469844916714532,
+      "grad_norm": 0.0348326712846756,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 11.9313,
+      "step": 43
+    },
+    {
+      "epoch": 0.02527283170591614,
+      "grad_norm": 0.04102734848856926,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 11.9316,
+      "step": 44
+    },
+    {
+      "epoch": 0.025847214244686962,
+      "grad_norm": 0.03495470806956291,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 11.931,
+      "step": 45
+    },
+    {
+      "epoch": 0.026421596783457783,
+      "grad_norm": 0.03532187640666962,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 11.9313,
+      "step": 46
+    },
+    {
+      "epoch": 0.026995979322228605,
+      "grad_norm": 0.04098067060112953,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 11.9304,
+      "step": 47
+    },
+    {
+      "epoch": 0.027570361860999426,
+      "grad_norm": 0.038192637264728546,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 11.9313,
+      "step": 48
+    },
+    {
+      "epoch": 0.028144744399770247,
+      "grad_norm": 0.045579973608255386,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 11.9315,
+      "step": 49
+    },
+    {
+      "epoch": 0.02871912693854107,
+      "grad_norm": 0.04336276277899742,
+      "learning_rate": 1e-05,
+      "loss": 11.9313,
+      "step": 50
+    },
+    {
+      "epoch": 0.02871912693854107,
+      "eval_loss": 11.930744171142578,
+      "eval_runtime": 0.1654,
+      "eval_samples_per_second": 302.244,
+      "eval_steps_per_second": 78.583,
+      "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": 521898688512.0,
+  "total_flos": 1043797377024.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null