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:a5986e147b9ede41b44f04c433150a0e1924da465625f5baeb4d721d3e1b9ab8
+oid sha256:975b69a99a9dc453adc91a4d05f19e3836b680ad61ee47d115364b336d4fe18a
 size 100966336

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e6c7d635fc0808865f975d3a125c3c989da842d79cb4c6d71f863df5a3c1aa13
+oid sha256:2aae3168a6de965e61ea9fad85082728391aed26b5660ee3337892fa136d8c2e
 size 202110330

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:252554704c0c717fe7dfba01cd56ce2a8bbe00ceaed880276854ee7108b62631
+oid sha256:800f0414779a2197296e2144d659adfe4d3260f365f63dbd9ce9634c40d55329
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1cd58c794206c8e585858977a31ea5e0b556ee8f9005e832627aa747b4297e40
+oid sha256:bba45c8192260445892bf3369b3cef89b910f2fbafce70bbd0dd8f6ec9129e8a
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9234c6a38173d95ac99cf9849a73747fcc065d42700e1b41d04b1dc832efbffa
+oid sha256:bfc5111e5ca1f9867f5fe9c8ba35c475436e3cea712bb405f01a2abc6ee3a10f
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:33d6bc473aa7e1bb7969f34c1fd5feef2cadc6de657e686d04c3f7fd60dda456
+oid sha256:17250cf10fece67d99d5e3123cda4556eae5f5d9e7ccbe2916c7b607eefe64c7
 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": 1.4106637239456177,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.22805017103762829,
+  "best_metric": 1.3095707893371582,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.45610034207525657,
   "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": 49.001,
       "eval_steps_per_second": 12.74,
       "step": 25
+    },
+    {
+      "epoch": 0.23717217787913342,
+      "grad_norm": 0.9181596040725708,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 1.1175,
+      "step": 26
+    },
+    {
+      "epoch": 0.24629418472063855,
+      "grad_norm": 0.6287382245063782,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 1.3472,
+      "step": 27
+    },
+    {
+      "epoch": 0.2554161915621437,
+      "grad_norm": 0.8954634666442871,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 1.382,
+      "step": 28
+    },
+    {
+      "epoch": 0.2645381984036488,
+      "grad_norm": 0.5583573579788208,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 1.4087,
+      "step": 29
+    },
+    {
+      "epoch": 0.27366020524515394,
+      "grad_norm": 0.7373714447021484,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 1.4713,
+      "step": 30
+    },
+    {
+      "epoch": 0.28278221208665905,
+      "grad_norm": 0.46830883622169495,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 1.4206,
+      "step": 31
+    },
+    {
+      "epoch": 0.2919042189281642,
+      "grad_norm": 0.445218950510025,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 1.4428,
+      "step": 32
+    },
+    {
+      "epoch": 0.3010262257696693,
+      "grad_norm": 0.5559998750686646,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 1.5217,
+      "step": 33
+    },
+    {
+      "epoch": 0.31014823261117447,
+      "grad_norm": 0.6704520583152771,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 1.4832,
+      "step": 34
+    },
+    {
+      "epoch": 0.31927023945267957,
+      "grad_norm": 0.9207093715667725,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 1.5879,
+      "step": 35
+    },
+    {
+      "epoch": 0.32839224629418473,
+      "grad_norm": 0.606840193271637,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 1.5241,
+      "step": 36
+    },
+    {
+      "epoch": 0.33751425313568983,
+      "grad_norm": 1.1559696197509766,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 1.5729,
+      "step": 37
+    },
+    {
+      "epoch": 0.346636259977195,
+      "grad_norm": 0.6878672242164612,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 1.0944,
+      "step": 38
+    },
+    {
+      "epoch": 0.3557582668187001,
+      "grad_norm": 0.4424948990345001,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 1.2331,
+      "step": 39
+    },
+    {
+      "epoch": 0.36488027366020526,
+      "grad_norm": 0.46379706263542175,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 1.4107,
+      "step": 40
+    },
+    {
+      "epoch": 0.37400228050171036,
+      "grad_norm": 0.5940743088722229,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 1.3661,
+      "step": 41
+    },
+    {
+      "epoch": 0.3831242873432155,
+      "grad_norm": 0.5553629994392395,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 1.4202,
+      "step": 42
+    },
+    {
+      "epoch": 0.3922462941847206,
+      "grad_norm": 0.40024417638778687,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 1.3746,
+      "step": 43
+    },
+    {
+      "epoch": 0.4013683010262258,
+      "grad_norm": 0.4371756613254547,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 1.4586,
+      "step": 44
+    },
+    {
+      "epoch": 0.4104903078677309,
+      "grad_norm": 0.49693790078163147,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 1.444,
+      "step": 45
+    },
+    {
+      "epoch": 0.41961231470923605,
+      "grad_norm": 0.463955819606781,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 1.5353,
+      "step": 46
+    },
+    {
+      "epoch": 0.42873432155074115,
+      "grad_norm": 0.496754914522171,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 1.4412,
+      "step": 47
+    },
+    {
+      "epoch": 0.4378563283922463,
+      "grad_norm": 0.680721640586853,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 1.5626,
+      "step": 48
+    },
+    {
+      "epoch": 0.4469783352337514,
+      "grad_norm": 0.5851555466651917,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 1.5285,
+      "step": 49
+    },
+    {
+      "epoch": 0.45610034207525657,
+      "grad_norm": 1.3343528509140015,
+      "learning_rate": 1e-05,
+      "loss": 1.6886,
+      "step": 50
+    },
+    {
+      "epoch": 0.45610034207525657,
+      "eval_loss": 1.3095707893371582,
+      "eval_runtime": 1.0162,
+      "eval_samples_per_second": 49.203,
+      "eval_steps_per_second": 12.793,
+      "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": 4.182708527824896e+16,
+  "total_flos": 8.368021483552768e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null