Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:407a17f341eddb58b7c22e984342aefd467b5a7f025a7605690f782ff24f5948
+oid sha256:f7260231b0d2be92847e348ab777ae5fe1c13bae7be21706f48218ad9bbf94ec
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c4e2c25128e9b6589a2f4a127944402ae1170e2e8318b4ae84fccff31ac6e872
+oid sha256:524288c80c74be4f60cb1284406cca4888f8425bd942a9581833dc7b37511b8e
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b444d2be758f7ca51732d9dc9ef153a794d252a8cdcde50363b0d7ff8509ae6
+oid sha256:5e708396abdc2dc3d78efbb81a7cac671746bdb7074d75fc3446093d912372ce
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a3b4d0598f9cbd588a5f569ebcaf8f17f7ca7f84b2ea02880d6787f412d8f01
+oid sha256:7b19308f1dcf1a609635ebf664e0d53a72bfe9468b0963724481fac0a29e72a1
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:834fcd8429becca8d8d1fc891010f71d1f38cf63b3bb4e45640d2115a759e903
+oid sha256:8180db303f1318594a7a963597fd6b33323bf5e5e4f98912bbc3dda8c86e9252
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b32afb39232e2e996dc72b970960c31cf0222f61347e481f0974a6ad3c0a2fd7
+oid sha256:5ccb99a9f46fe7754b46f8ff53da86f9390734cedeb1adec83cc6406ccdfe697
 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": 1.4504622220993042,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.05177323323841574,
+  "best_metric": 1.3929436206817627,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.10354646647683148,
   "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": 17.59,
       "eval_steps_per_second": 4.573,
       "step": 25
+    },
+    {
+      "epoch": 0.05384416256795237,
+      "grad_norm": 31.022377014160156,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 26.6118,
+      "step": 26
+    },
+    {
+      "epoch": 0.055915091897489,
+      "grad_norm": 30.95768928527832,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 25.1946,
+      "step": 27
+    },
+    {
+      "epoch": 0.057986021227025626,
+      "grad_norm": 29.154560089111328,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 25.1868,
+      "step": 28
+    },
+    {
+      "epoch": 0.06005695055656226,
+      "grad_norm": 24.8858585357666,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 23.3337,
+      "step": 29
+    },
+    {
+      "epoch": 0.062127879886098886,
+      "grad_norm": 29.466028213500977,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 23.2492,
+      "step": 30
+    },
+    {
+      "epoch": 0.06419880921563552,
+      "grad_norm": 30.200267791748047,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 24.1636,
+      "step": 31
+    },
+    {
+      "epoch": 0.06626973854517215,
+      "grad_norm": 25.208112716674805,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 23.3895,
+      "step": 32
+    },
+    {
+      "epoch": 0.06834066787470877,
+      "grad_norm": 28.123592376708984,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 22.7258,
+      "step": 33
+    },
+    {
+      "epoch": 0.0704115972042454,
+      "grad_norm": 25.637325286865234,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 20.7519,
+      "step": 34
+    },
+    {
+      "epoch": 0.07248252653378204,
+      "grad_norm": 28.706199645996094,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 22.0374,
+      "step": 35
+    },
+    {
+      "epoch": 0.07455345586331867,
+      "grad_norm": 31.979381561279297,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 25.2104,
+      "step": 36
+    },
+    {
+      "epoch": 0.07662438519285529,
+      "grad_norm": 29.22161102294922,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 21.5501,
+      "step": 37
+    },
+    {
+      "epoch": 0.07869531452239192,
+      "grad_norm": 32.82600402832031,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 26.7117,
+      "step": 38
+    },
+    {
+      "epoch": 0.08076624385192856,
+      "grad_norm": 23.496782302856445,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 23.4681,
+      "step": 39
+    },
+    {
+      "epoch": 0.08283717318146518,
+      "grad_norm": 23.55754852294922,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 23.5918,
+      "step": 40
+    },
+    {
+      "epoch": 0.08490810251100181,
+      "grad_norm": 21.707534790039062,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 23.0793,
+      "step": 41
+    },
+    {
+      "epoch": 0.08697903184053844,
+      "grad_norm": 22.5666446685791,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 23.2998,
+      "step": 42
+    },
+    {
+      "epoch": 0.08904996117007508,
+      "grad_norm": 25.450773239135742,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 24.0463,
+      "step": 43
+    },
+    {
+      "epoch": 0.0911208904996117,
+      "grad_norm": 23.49583625793457,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 22.0392,
+      "step": 44
+    },
+    {
+      "epoch": 0.09319181982914833,
+      "grad_norm": 24.161685943603516,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 23.1251,
+      "step": 45
+    },
+    {
+      "epoch": 0.09526274915868496,
+      "grad_norm": 25.985092163085938,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 22.9135,
+      "step": 46
+    },
+    {
+      "epoch": 0.0973336784882216,
+      "grad_norm": 27.213834762573242,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 21.3944,
+      "step": 47
+    },
+    {
+      "epoch": 0.09940460781775821,
+      "grad_norm": 26.962932586669922,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 22.9309,
+      "step": 48
+    },
+    {
+      "epoch": 0.10147553714729485,
+      "grad_norm": 28.983320236206055,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 22.1032,
+      "step": 49
+    },
+    {
+      "epoch": 0.10354646647683148,
+      "grad_norm": 32.67425537109375,
+      "learning_rate": 1e-05,
+      "loss": 21.5083,
+      "step": 50
+    },
+    {
+      "epoch": 0.10354646647683148,
+      "eval_loss": 1.3929436206817627,
+      "eval_runtime": 2.834,
+      "eval_samples_per_second": 17.643,
+      "eval_steps_per_second": 4.587,
+      "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": 2.829010669142016e+17,
+  "total_flos": 5.658021338284032e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null