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:d87794ec2d3efb689d6df7d3660ed28372f6aeba30e333777672a9b650935273
+oid sha256:33d679f36db792107920ad8ac97ba19f2d9fa22c1c7d258793011039278b7ed3
 size 100966336

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4cbc35cd7d3b643e601f04a2bc779273ec90f4001564dbacccebca587962261
+oid sha256:8f0cfa027f2eb8d93d297a7e2b8223b53526c7d028dc6e34e7f5997604968d30
 size 202110330

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05d3528a3a149fe181d1844ac84cc28661e63a51660d18f11ba74ec6a7023482
+oid sha256:bc5bb940bc6cc532d61376a88a1e1a753de17945cc8a439a60343cb93c34c407
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f631d92c0e7703d5d85ff3bb71515e2729a31ea8b730f70b158c96a2f187469a
+oid sha256:875c4d4817628a526be3b6f2c3af1fbd14a74c6c97a1f9e1b9c347f8f37fb27e
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c01f021afbb1ffbe3ee2ce89239be4a18a860de737adfce52ef0d3aed2e6c1d
+oid sha256:b695ef590b1f4aea0d39713ef8518154f9d2d4af99048726d47f5252a5710383
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea74304cd8262763ed5d89794eb2c6c5d3843d2420208c357a0152fc14ef363d
+oid sha256:743df376798b1177bbb1954bdcf7ada54cfc0e6ef953f6e5a8016bb759617a92
 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": 1.028018832206726,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.025547678354729514,
+  "best_metric": 1.023098111152649,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.05109535670945903,
   "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": 87.137,
       "eval_steps_per_second": 22.656,
       "step": 25
+    },
+    {
+      "epoch": 0.026569585488918693,
+      "grad_norm": 0.09364611655473709,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.9923,
+      "step": 26
+    },
+    {
+      "epoch": 0.027591492623107877,
+      "grad_norm": 0.11099690198898315,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 0.9531,
+      "step": 27
+    },
+    {
+      "epoch": 0.028613399757297056,
+      "grad_norm": 0.08575939387083054,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 1.0044,
+      "step": 28
+    },
+    {
+      "epoch": 0.029635306891486236,
+      "grad_norm": 0.08077307045459747,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 0.9996,
+      "step": 29
+    },
+    {
+      "epoch": 0.030657214025675415,
+      "grad_norm": 0.08190269023180008,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 0.9721,
+      "step": 30
+    },
+    {
+      "epoch": 0.0316791211598646,
+      "grad_norm": 0.07466033101081848,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 0.9926,
+      "step": 31
+    },
+    {
+      "epoch": 0.032701028294053774,
+      "grad_norm": 0.08436423540115356,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 0.955,
+      "step": 32
+    },
+    {
+      "epoch": 0.03372293542824296,
+      "grad_norm": 0.11776597052812576,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 1.0573,
+      "step": 33
+    },
+    {
+      "epoch": 0.03474484256243214,
+      "grad_norm": 0.1015639677643776,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 1.0632,
+      "step": 34
+    },
+    {
+      "epoch": 0.03576674969662132,
+      "grad_norm": 0.1283145695924759,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 1.0964,
+      "step": 35
+    },
+    {
+      "epoch": 0.0367886568308105,
+      "grad_norm": 0.15790176391601562,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 1.0945,
+      "step": 36
+    },
+    {
+      "epoch": 0.03781056396499968,
+      "grad_norm": 0.19052524864673615,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 1.1391,
+      "step": 37
+    },
+    {
+      "epoch": 0.03883247109918886,
+      "grad_norm": 0.09945850074291229,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.9936,
+      "step": 38
+    },
+    {
+      "epoch": 0.03985437823337804,
+      "grad_norm": 0.07477223873138428,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 0.9394,
+      "step": 39
+    },
+    {
+      "epoch": 0.040876285367567225,
+      "grad_norm": 0.07209737598896027,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 1.0002,
+      "step": 40
+    },
+    {
+      "epoch": 0.0418981925017564,
+      "grad_norm": 0.07749871164560318,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 1.0618,
+      "step": 41
+    },
+    {
+      "epoch": 0.042920099635945584,
+      "grad_norm": 0.07592491060495377,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 1.0342,
+      "step": 42
+    },
+    {
+      "epoch": 0.04394200677013477,
+      "grad_norm": 0.07187314331531525,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 0.9313,
+      "step": 43
+    },
+    {
+      "epoch": 0.04496391390432394,
+      "grad_norm": 0.0747632384300232,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 1.0292,
+      "step": 44
+    },
+    {
+      "epoch": 0.045985821038513126,
+      "grad_norm": 0.07752417773008347,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 0.9398,
+      "step": 45
+    },
+    {
+      "epoch": 0.0470077281727023,
+      "grad_norm": 0.08928266912698746,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 1.0053,
+      "step": 46
+    },
+    {
+      "epoch": 0.048029635306891486,
+      "grad_norm": 0.10782655328512192,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 1.0748,
+      "step": 47
+    },
+    {
+      "epoch": 0.04905154244108067,
+      "grad_norm": 0.13183674216270447,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 1.0275,
+      "step": 48
+    },
+    {
+      "epoch": 0.050073449575269845,
+      "grad_norm": 0.1651250123977661,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 1.1571,
+      "step": 49
+    },
+    {
+      "epoch": 0.05109535670945903,
+      "grad_norm": 0.23413170874118805,
+      "learning_rate": 1e-05,
+      "loss": 1.2371,
+      "step": 50
+    },
+    {
+      "epoch": 0.05109535670945903,
+      "eval_loss": 1.023098111152649,
+      "eval_runtime": 0.5662,
+      "eval_samples_per_second": 88.309,
+      "eval_steps_per_second": 22.96,
+      "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": 4.16708196040704e+16,
+  "total_flos": 8.33416392081408e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null