Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e29e3ea1c21bd036e1ff3125df6ef5d48833391bf7cfae4a6c29e698fab8e9c
+oid sha256:0bc0fbfc36e9448708959119726d7af6531d4dc340cbd39b9b95872115ef87c0
 size 27153960

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ed7babd207856db0284d73b3afcd52816cd015c76c274cae8fabf8439f1c77d
+oid sha256:bf3a52773b56e7998a6494b39ce70e497cef2d24ab24f4989f94e40d4e61ea60
 size 54405050

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7cae23a9342a4191971a4b9e7eb0f0b55ac11be948c4fe3a1c0d17f1589fc975
+oid sha256:476c82319781250b78f6c65289a8d7a7f9ed5880ece5b0c03d8de41d237904fa
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bbd303d5b0a656b290d5b484516d08c7d74b3663e30bcce30df1ed04b8299409
+oid sha256:8c8d1fea6db016edb20fcc3fbfdebb8807cc24de61faed839e797aae1f24d0fb
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:731b1dc2d4872eaa5a200972e68e65963981126de0c11ed89471a3ab21d11fe2
+oid sha256:245a4f0a0976127d3bac91a62c5ab37cdc797acadc97fe241ea2229fdd3e24c8
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c29923cf34680db993faf5ecda053cac6a74fd2090a6dbfbe0182dc9e60bb26
+oid sha256:257f4b3fc828dad422d39110a9e5c131779eaa14cdb1c7bfff0af3fc01356ad7
 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": 4.552499294281006,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.017114862118392058,
+  "best_metric": 4.4408369064331055,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.034229724236784116,
   "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": 69.705,
       "eval_steps_per_second": 18.123,
       "step": 25
+    },
+    {
+      "epoch": 0.01779945660312774,
+      "grad_norm": 0.62814861536026,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 4.89,
+      "step": 26
+    },
+    {
+      "epoch": 0.018484051087863423,
+      "grad_norm": 0.7369610071182251,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 4.7008,
+      "step": 27
+    },
+    {
+      "epoch": 0.019168645572599105,
+      "grad_norm": 0.4340572655200958,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 4.5668,
+      "step": 28
+    },
+    {
+      "epoch": 0.019853240057334787,
+      "grad_norm": 0.39323368668556213,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 4.4916,
+      "step": 29
+    },
+    {
+      "epoch": 0.02053783454207047,
+      "grad_norm": 0.3761708736419678,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 4.4375,
+      "step": 30
+    },
+    {
+      "epoch": 0.021222429026806152,
+      "grad_norm": 0.3994690477848053,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 4.5058,
+      "step": 31
+    },
+    {
+      "epoch": 0.021907023511541834,
+      "grad_norm": 0.342385858297348,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 4.5325,
+      "step": 32
+    },
+    {
+      "epoch": 0.022591617996277517,
+      "grad_norm": 0.3298172056674957,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 4.5148,
+      "step": 33
+    },
+    {
+      "epoch": 0.0232762124810132,
+      "grad_norm": 0.34544578194618225,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 4.5301,
+      "step": 34
+    },
+    {
+      "epoch": 0.02396080696574888,
+      "grad_norm": 0.36276698112487793,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 4.4603,
+      "step": 35
+    },
+    {
+      "epoch": 0.024645401450484564,
+      "grad_norm": 0.3994443714618683,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 4.4842,
+      "step": 36
+    },
+    {
+      "epoch": 0.025329995935220246,
+      "grad_norm": 0.4487013518810272,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 4.571,
+      "step": 37
+    },
+    {
+      "epoch": 0.02601459041995593,
+      "grad_norm": 0.5831749439239502,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 4.9017,
+      "step": 38
+    },
+    {
+      "epoch": 0.02669918490469161,
+      "grad_norm": 0.49567192792892456,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 4.7503,
+      "step": 39
+    },
+    {
+      "epoch": 0.027383779389427293,
+      "grad_norm": 0.41273921728134155,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 4.5314,
+      "step": 40
+    },
+    {
+      "epoch": 0.028068373874162975,
+      "grad_norm": 0.32999297976493835,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 4.4739,
+      "step": 41
+    },
+    {
+      "epoch": 0.028752968358898658,
+      "grad_norm": 0.3798677325248718,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 4.3849,
+      "step": 42
+    },
+    {
+      "epoch": 0.02943756284363434,
+      "grad_norm": 0.3015289306640625,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 4.4318,
+      "step": 43
+    },
+    {
+      "epoch": 0.030122157328370022,
+      "grad_norm": 0.3044837713241577,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 4.393,
+      "step": 44
+    },
+    {
+      "epoch": 0.030806751813105705,
+      "grad_norm": 0.2872242033481598,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 4.4336,
+      "step": 45
+    },
+    {
+      "epoch": 0.03149134629784139,
+      "grad_norm": 0.3284749388694763,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 4.4342,
+      "step": 46
+    },
+    {
+      "epoch": 0.03217594078257707,
+      "grad_norm": 0.2982497215270996,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 4.4723,
+      "step": 47
+    },
+    {
+      "epoch": 0.03286053526731275,
+      "grad_norm": 0.3299315571784973,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 4.4427,
+      "step": 48
+    },
+    {
+      "epoch": 0.03354512975204844,
+      "grad_norm": 0.3700416386127472,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 4.5147,
+      "step": 49
+    },
+    {
+      "epoch": 0.034229724236784116,
+      "grad_norm": 0.47993677854537964,
+      "learning_rate": 1e-05,
+      "loss": 4.5846,
+      "step": 50
+    },
+    {
+      "epoch": 0.034229724236784116,
+      "eval_loss": 4.4408369064331055,
+      "eval_runtime": 0.7646,
+      "eval_samples_per_second": 65.397,
+      "eval_steps_per_second": 17.003,
+      "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": 5978313860317184.0,
+  "total_flos": 1.1942410556801024e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null