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:baed10735a50eaf00b4732e0419a7f8b5a59bb7d29ac0e077006b26cfdf24dbb
+oid sha256:ea51ed58c2de95e84f42cabceb7b2a0f2d6cf8ad772f836235ac77670faf6261
 size 203456160

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:63d8d08de48e514417091736bf6af6ee12721b42e7aebc55026dcafaa534ca54
+oid sha256:6f365fdd6e9173903cb3c1886a7ecc2925dc9f9b35c3e274573f2d6e632c178c
 size 407121750

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d869ceca7e92d3cd5aa11d97f921b22231eaf52b597d26d9500e3a7da5618894
+oid sha256:829950e24e3cf67e99486a5b34ee73f0d39e19d28a1b6535337b45eef569315d
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e09cdb8788771c517a68cc425ac1a9ed8397b1b4e975d36ae5af0401fa84a0d7
+oid sha256:397b3f458c5c2bb97a05c951db370e38f04d740c2e9dc7d2c1c3ec0a0a290bc6
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:199bde9ae9e93e37a354f2651422d316e5d8e4a100331c0f64a805658dd72208
+oid sha256:376c605096f691336ca8023fc2c0bcdb347fb4672ddc3662464a445b87d6b9ad
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:159548945686da1eec2a665a62d710094000348dea9942ce0f5c0e967a9820c5
+oid sha256:4123402b18a04f694bb968a1e0df830c88a7a074d79ba8778dd97c205b505567
 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": 1.165574312210083,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.8547008547008547,
+  "best_metric": 1.1214191913604736,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 1.7094017094017095,
   "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": 11.247,
       "eval_steps_per_second": 2.924,
       "step": 25
+    },
+    {
+      "epoch": 0.8888888888888888,
+      "grad_norm": 0.18219228088855743,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 1.1871,
+      "step": 26
+    },
+    {
+      "epoch": 0.9230769230769231,
+      "grad_norm": 0.23712663352489471,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 1.2762,
+      "step": 27
+    },
+    {
+      "epoch": 0.9572649572649573,
+      "grad_norm": 0.26627615094184875,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 1.23,
+      "step": 28
+    },
+    {
+      "epoch": 0.9914529914529915,
+      "grad_norm": 0.48001009225845337,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 1.2439,
+      "step": 29
+    },
+    {
+      "epoch": 1.0256410256410255,
+      "grad_norm": 0.3259235918521881,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 1.9017,
+      "step": 30
+    },
+    {
+      "epoch": 1.0598290598290598,
+      "grad_norm": 0.1634763777256012,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 1.0099,
+      "step": 31
+    },
+    {
+      "epoch": 1.0940170940170941,
+      "grad_norm": 0.18364383280277252,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 1.074,
+      "step": 32
+    },
+    {
+      "epoch": 1.1282051282051282,
+      "grad_norm": 0.17964854836463928,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 1.1117,
+      "step": 33
+    },
+    {
+      "epoch": 1.1623931623931625,
+      "grad_norm": 0.21416999399662018,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 1.1686,
+      "step": 34
+    },
+    {
+      "epoch": 1.1965811965811965,
+      "grad_norm": 0.2810254693031311,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 1.2991,
+      "step": 35
+    },
+    {
+      "epoch": 1.2307692307692308,
+      "grad_norm": 0.37248972058296204,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 1.1737,
+      "step": 36
+    },
+    {
+      "epoch": 1.264957264957265,
+      "grad_norm": 0.18982478976249695,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 0.9194,
+      "step": 37
+    },
+    {
+      "epoch": 1.2991452991452992,
+      "grad_norm": 0.16235685348510742,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 1.0365,
+      "step": 38
+    },
+    {
+      "epoch": 1.3333333333333333,
+      "grad_norm": 0.16103604435920715,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 1.023,
+      "step": 39
+    },
+    {
+      "epoch": 1.3675213675213675,
+      "grad_norm": 0.17420010268688202,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 1.0827,
+      "step": 40
+    },
+    {
+      "epoch": 1.4017094017094016,
+      "grad_norm": 0.22135403752326965,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 1.1882,
+      "step": 41
+    },
+    {
+      "epoch": 1.435897435897436,
+      "grad_norm": 0.3032638430595398,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 1.2978,
+      "step": 42
+    },
+    {
+      "epoch": 1.4700854700854702,
+      "grad_norm": 0.27858826518058777,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 1.1255,
+      "step": 43
+    },
+    {
+      "epoch": 1.5042735042735043,
+      "grad_norm": 0.17081612348556519,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 0.8,
+      "step": 44
+    },
+    {
+      "epoch": 1.5384615384615383,
+      "grad_norm": 0.16506823897361755,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 1.1665,
+      "step": 45
+    },
+    {
+      "epoch": 1.5726495726495726,
+      "grad_norm": 0.14897824823856354,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 1.0224,
+      "step": 46
+    },
+    {
+      "epoch": 1.606837606837607,
+      "grad_norm": 0.1740272492170334,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 1.0301,
+      "step": 47
+    },
+    {
+      "epoch": 1.641025641025641,
+      "grad_norm": 0.18550682067871094,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 1.1196,
+      "step": 48
+    },
+    {
+      "epoch": 1.6752136752136753,
+      "grad_norm": 0.2793455421924591,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 1.2703,
+      "step": 49
+    },
+    {
+      "epoch": 1.7094017094017095,
+      "grad_norm": 0.2792409360408783,
+      "learning_rate": 1e-05,
+      "loss": 1.1318,
+      "step": 50
+    },
+    {
+      "epoch": 1.7094017094017095,
+      "eval_loss": 1.1214191913604736,
+      "eval_runtime": 4.431,
+      "eval_samples_per_second": 11.284,
+      "eval_steps_per_second": 2.934,
+      "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": 1.3287335330735718e+17,
+  "total_flos": 2.6566376489064858e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null