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:deaf0e509abafaf0766f834c74538aa42c0d378b83ebeadeba9b175c831796ea
+oid sha256:1712d0a4376d3f5c394fe7f75fc850cb994b1507f76c1564cb582c459f2b22e8
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f40dec5231675af44fbbe28c697d8701c16e0a233edbe7a05308cc252815a2bd
+oid sha256:552d081dd2d553ef433686e4114a65d150983478c546b256c98086e1ed14eec1
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5660b16fd65f57b217c5248cb5310400b6d098a9e60a336033293455ee66dd95
+oid sha256:9809359fe330d35344ae36a2843702135cb8651225d6e0d27b8d02b48f39483f
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e124c725f35816b87fc983ec553092f8be25b592da505b091da05e9e65e6a942
+oid sha256:fb1f80a53c39eecfa41fee20dd9e1d8c7cc453baec09f5cb00fc7100dc00cb48
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b3e7d34b827c5bc889304155c046fdae25ece08415080086fc97785dca870be
+oid sha256:f7c302a58708a988b8ecc2895d67da2bc94ea74233e6b35e34d9f59733ef30c4
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:af343ae9c8e4df9bdddf0193b5966646f74f59c0ad95a82fbeb78af3661b5f04
+oid sha256:5d4f847662f4088a7531e32f7522a992449263570dbb59ed57a5613a61a7d966
 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": 0.9397671222686768,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.8547008547008547,
+  "best_metric": 0.8936432003974915,
+  "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": 14.316,
       "eval_steps_per_second": 3.722,
       "step": 25
+    },
+    {
+      "epoch": 0.8888888888888888,
+      "grad_norm": 0.3003530502319336,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.9396,
+      "step": 26
+    },
+    {
+      "epoch": 0.9230769230769231,
+      "grad_norm": 0.38296979665756226,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 1.0315,
+      "step": 27
+    },
+    {
+      "epoch": 0.9572649572649573,
+      "grad_norm": 0.4535260498523712,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 0.9811,
+      "step": 28
+    },
+    {
+      "epoch": 0.9914529914529915,
+      "grad_norm": 0.6909157037734985,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 0.9657,
+      "step": 29
+    },
+    {
+      "epoch": 1.0256410256410255,
+      "grad_norm": 0.5730057954788208,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 1.4471,
+      "step": 30
+    },
+    {
+      "epoch": 1.0598290598290598,
+      "grad_norm": 0.23904989659786224,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 0.7712,
+      "step": 31
+    },
+    {
+      "epoch": 1.0940170940170941,
+      "grad_norm": 0.2702152729034424,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 0.803,
+      "step": 32
+    },
+    {
+      "epoch": 1.1282051282051282,
+      "grad_norm": 0.2781081795692444,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 0.8369,
+      "step": 33
+    },
+    {
+      "epoch": 1.1623931623931625,
+      "grad_norm": 0.2826618254184723,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 0.9031,
+      "step": 34
+    },
+    {
+      "epoch": 1.1965811965811965,
+      "grad_norm": 0.4115469455718994,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 1.0045,
+      "step": 35
+    },
+    {
+      "epoch": 1.2307692307692308,
+      "grad_norm": 0.5486916303634644,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 0.8591,
+      "step": 36
+    },
+    {
+      "epoch": 1.264957264957265,
+      "grad_norm": 0.27575865387916565,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 0.6631,
+      "step": 37
+    },
+    {
+      "epoch": 1.2991452991452992,
+      "grad_norm": 0.23719096183776855,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.7849,
+      "step": 38
+    },
+    {
+      "epoch": 1.3333333333333333,
+      "grad_norm": 0.23659953474998474,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 0.7611,
+      "step": 39
+    },
+    {
+      "epoch": 1.3675213675213675,
+      "grad_norm": 0.24429921805858612,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 0.8367,
+      "step": 40
+    },
+    {
+      "epoch": 1.4017094017094016,
+      "grad_norm": 0.3248053193092346,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 0.9198,
+      "step": 41
+    },
+    {
+      "epoch": 1.435897435897436,
+      "grad_norm": 0.4573812782764435,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 1.006,
+      "step": 42
+    },
+    {
+      "epoch": 1.4700854700854702,
+      "grad_norm": 0.4747590720653534,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 0.7927,
+      "step": 43
+    },
+    {
+      "epoch": 1.5042735042735043,
+      "grad_norm": 0.2991985082626343,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 0.5808,
+      "step": 44
+    },
+    {
+      "epoch": 1.5384615384615383,
+      "grad_norm": 0.26089948415756226,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 0.863,
+      "step": 45
+    },
+    {
+      "epoch": 1.5726495726495726,
+      "grad_norm": 0.23467212915420532,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 0.7654,
+      "step": 46
+    },
+    {
+      "epoch": 1.606837606837607,
+      "grad_norm": 0.2614939212799072,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 0.7831,
+      "step": 47
+    },
+    {
+      "epoch": 1.641025641025641,
+      "grad_norm": 0.3077352046966553,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 0.8956,
+      "step": 48
+    },
+    {
+      "epoch": 1.6752136752136753,
+      "grad_norm": 0.3929722011089325,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 0.9792,
+      "step": 49
+    },
+    {
+      "epoch": 1.7094017094017095,
+      "grad_norm": 0.4925636053085327,
+      "learning_rate": 1e-05,
+      "loss": 0.8144,
+      "step": 50
+    },
+    {
+      "epoch": 1.7094017094017095,
+      "eval_loss": 0.8936432003974915,
+      "eval_runtime": 3.4896,
+      "eval_samples_per_second": 14.328,
+      "eval_steps_per_second": 3.725,
+      "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": 2.984041808658432e+17,
+  "total_flos": 5.968083617316864e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null