Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16b7eeb12d5b0c55be27a06c130886a7ad5b201b9316edcef3cd2dff1d3601d2
+oid sha256:0a45224088c866cb88daf3764aac75da066c56b674d623ef59eaa5a3f97cd22e
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a59e61f077d15afaef3b15b07943e7ed2dfcfda70aa5175fc63149f854e532a9
+oid sha256:2e3fdaa2b57fe8534dfa4a58cc2f32f5ec675b15f3d1380f40736b056a1a83bb
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba7089b92a2b521c16182e4f0ed107241f8d6cc46cdc92f678316378bc87747c
+oid sha256:27326e23b653fcdd85ad1d1ad4deb0f95813eef518cc4c771c054eb8337caa7d
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f0f2554bf8ecd2d70b946a31a27927dfe3fd2b0502225bf4325dd36a7950ba2
+oid sha256:6851ac6b83f5ba4aa67e9bdbe461f1a860881712016ff93229873cb290b1f901
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb075bc3d46e854579fe58ba19c78996e1be36b6f428c65165b42a4f19ac07a1
+oid sha256:6816547d53b81f3d9bd08a47fd760d479a65bd96fb411699cca011ee9b04af86
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:596eab55cd20e853c6d47e765000c529f0297098f8cfcabea1b7a8be44d9bf8a
+oid sha256:6e1f689dbc5cad2b7de70d8841344079dcc97dcff5bd533afb708e6bd93e5a26
 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": 1.5251476764678955,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.5934718100890207,
+  "best_metric": 1.0515674352645874,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 1.1869436201780414,
   "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": 14.39,
       "eval_steps_per_second": 3.741,
       "step": 25
+    },
+    {
+      "epoch": 0.6172106824925816,
+      "grad_norm": 1.4022682905197144,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 1.1673,
+      "step": 26
+    },
+    {
+      "epoch": 0.6409495548961425,
+      "grad_norm": 1.360411286354065,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 1.2339,
+      "step": 27
+    },
+    {
+      "epoch": 0.6646884272997032,
+      "grad_norm": 1.5245141983032227,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 1.2553,
+      "step": 28
+    },
+    {
+      "epoch": 0.6884272997032641,
+      "grad_norm": 1.5429983139038086,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 1.3811,
+      "step": 29
+    },
+    {
+      "epoch": 0.712166172106825,
+      "grad_norm": 1.6180874109268188,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 1.0528,
+      "step": 30
+    },
+    {
+      "epoch": 0.7359050445103857,
+      "grad_norm": 2.2861862182617188,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 1.3014,
+      "step": 31
+    },
+    {
+      "epoch": 0.7596439169139466,
+      "grad_norm": 2.1236374378204346,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 1.0626,
+      "step": 32
+    },
+    {
+      "epoch": 0.7833827893175074,
+      "grad_norm": 1.7430927753448486,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 0.9247,
+      "step": 33
+    },
+    {
+      "epoch": 0.8071216617210683,
+      "grad_norm": 1.372740387916565,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 0.959,
+      "step": 34
+    },
+    {
+      "epoch": 0.8308605341246291,
+      "grad_norm": 1.3866841793060303,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 0.8239,
+      "step": 35
+    },
+    {
+      "epoch": 0.8545994065281899,
+      "grad_norm": 1.8122707605361938,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 0.9378,
+      "step": 36
+    },
+    {
+      "epoch": 0.8783382789317508,
+      "grad_norm": 1.5954991579055786,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 1.0473,
+      "step": 37
+    },
+    {
+      "epoch": 0.9020771513353115,
+      "grad_norm": 1.5977816581726074,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.9681,
+      "step": 38
+    },
+    {
+      "epoch": 0.9258160237388724,
+      "grad_norm": 1.6187400817871094,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 0.9797,
+      "step": 39
+    },
+    {
+      "epoch": 0.9495548961424333,
+      "grad_norm": 1.8072162866592407,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 0.8826,
+      "step": 40
+    },
+    {
+      "epoch": 0.973293768545994,
+      "grad_norm": 2.2397186756134033,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 1.0376,
+      "step": 41
+    },
+    {
+      "epoch": 0.9970326409495549,
+      "grad_norm": 2.8178083896636963,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 1.2337,
+      "step": 42
+    },
+    {
+      "epoch": 1.0207715133531157,
+      "grad_norm": 4.646073818206787,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 2.0149,
+      "step": 43
+    },
+    {
+      "epoch": 1.0445103857566767,
+      "grad_norm": 1.2922364473342896,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 0.8055,
+      "step": 44
+    },
+    {
+      "epoch": 1.0682492581602374,
+      "grad_norm": 1.1570236682891846,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 0.7687,
+      "step": 45
+    },
+    {
+      "epoch": 1.0919881305637982,
+      "grad_norm": 1.2567687034606934,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 0.7373,
+      "step": 46
+    },
+    {
+      "epoch": 1.115727002967359,
+      "grad_norm": 1.6276962757110596,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 0.8683,
+      "step": 47
+    },
+    {
+      "epoch": 1.13946587537092,
+      "grad_norm": 1.4849191904067993,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 0.9161,
+      "step": 48
+    },
+    {
+      "epoch": 1.1632047477744807,
+      "grad_norm": 1.447176456451416,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 0.8083,
+      "step": 49
+    },
+    {
+      "epoch": 1.1869436201780414,
+      "grad_norm": 1.6718727350234985,
+      "learning_rate": 1e-05,
+      "loss": 0.9247,
+      "step": 50
+    },
+    {
+      "epoch": 1.1869436201780414,
+      "eval_loss": 1.0515674352645874,
+      "eval_runtime": 3.4991,
+      "eval_samples_per_second": 14.29,
+      "eval_steps_per_second": 3.715,
+      "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