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:cbe34e695e76d5b30f41d096d807989203239ca7366f295626c8283e8bf4fd09
+oid sha256:664d04e28e1ec5d0ea18309cf0e57544d6e4f19bd3f0ce1c253a1447a0216aac
 size 432223744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:296297430cfba71e7d20bd1603b5ed299ef08417b329e1d3da4a252c21e45bd0
+oid sha256:9a3e4152c63477c0aaeaad4b7cb95db7f2eda55d949c12520c49f46786b9a6b3
 size 220139844

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b9b64a9e281b965dda04ae71f409e3f0bdc166ce9127dda0e53f12c2fcb5bf3
+oid sha256:6a2dc63ddf56ffc20e886a3cfca29f05d762b0ce663ef0ebf4dd2befb03eeb10
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6676fe28230ae15b45fb334c871c6fdf1a7984a935952b9f8650896c37a8c106
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.9391679763793945,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.020909566126502875,
+  "best_metric": 1.7563599348068237,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.04181913225300575,
   "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": 3.379,
       "eval_steps_per_second": 1.69,
       "step": 25
+    },
+    {
+      "epoch": 0.02174594877156299,
+      "grad_norm": 1.694573998451233,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 1.9518,
+      "step": 26
+    },
+    {
+      "epoch": 0.022582331416623105,
+      "grad_norm": 2.0041921138763428,
+      "learning_rate": 6.167226819279528e-05,
+      "loss": 1.9553,
+      "step": 27
+    },
+    {
+      "epoch": 0.02341871406168322,
+      "grad_norm": 1.6085962057113647,
+      "learning_rate": 5.782172325201155e-05,
+      "loss": 1.6961,
+      "step": 28
+    },
+    {
+      "epoch": 0.024255096706743334,
+      "grad_norm": 2.1220922470092773,
+      "learning_rate": 5.392295478639225e-05,
+      "loss": 1.9733,
+      "step": 29
+    },
+    {
+      "epoch": 0.02509147935180345,
+      "grad_norm": 1.6805081367492676,
+      "learning_rate": 5e-05,
+      "loss": 1.7083,
+      "step": 30
+    },
+    {
+      "epoch": 0.025927861996863564,
+      "grad_norm": 1.8382118940353394,
+      "learning_rate": 4.607704521360776e-05,
+      "loss": 1.7664,
+      "step": 31
+    },
+    {
+      "epoch": 0.02676424464192368,
+      "grad_norm": 1.6417231559753418,
+      "learning_rate": 4.2178276747988446e-05,
+      "loss": 1.6639,
+      "step": 32
+    },
+    {
+      "epoch": 0.027600627286983793,
+      "grad_norm": 2.0312328338623047,
+      "learning_rate": 3.832773180720475e-05,
+      "loss": 1.7982,
+      "step": 33
+    },
+    {
+      "epoch": 0.02843700993204391,
+      "grad_norm": 1.7858235836029053,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 1.8593,
+      "step": 34
+    },
+    {
+      "epoch": 0.029273392577104027,
+      "grad_norm": 1.8406282663345337,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 1.8249,
+      "step": 35
+    },
+    {
+      "epoch": 0.03010977522216414,
+      "grad_norm": 1.838815450668335,
+      "learning_rate": 2.7300475013022663e-05,
+      "loss": 1.8452,
+      "step": 36
+    },
+    {
+      "epoch": 0.030946157867224256,
+      "grad_norm": 1.991115927696228,
+      "learning_rate": 2.3875071764202563e-05,
+      "loss": 1.7201,
+      "step": 37
+    },
+    {
+      "epoch": 0.03178254051228437,
+      "grad_norm": 1.6236730813980103,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 1.5592,
+      "step": 38
+    },
+    {
+      "epoch": 0.032618923157344486,
+      "grad_norm": 1.7485631704330444,
+      "learning_rate": 1.7527597583490822e-05,
+      "loss": 1.5686,
+      "step": 39
+    },
+    {
+      "epoch": 0.0334553058024046,
+      "grad_norm": 1.8818488121032715,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.7336,
+      "step": 40
+    },
+    {
+      "epoch": 0.03429168844746471,
+      "grad_norm": 1.9881000518798828,
+      "learning_rate": 1.1979701719998453e-05,
+      "loss": 1.8232,
+      "step": 41
+    },
+    {
+      "epoch": 0.03512807109252483,
+      "grad_norm": 2.0539233684539795,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 1.8541,
+      "step": 42
+    },
+    {
+      "epoch": 0.035964453737584945,
+      "grad_norm": 2.123443365097046,
+      "learning_rate": 7.367991782295391e-06,
+      "loss": 1.8711,
+      "step": 43
+    },
+    {
+      "epoch": 0.03680083638264506,
+      "grad_norm": 1.6884969472885132,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 1.5576,
+      "step": 44
+    },
+    {
+      "epoch": 0.03763721902770518,
+      "grad_norm": 1.9117013216018677,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.6863,
+      "step": 45
+    },
+    {
+      "epoch": 0.03847360167276529,
+      "grad_norm": 1.8388051986694336,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 1.7621,
+      "step": 46
+    },
+    {
+      "epoch": 0.039309984317825404,
+      "grad_norm": 1.8650563955307007,
+      "learning_rate": 1.3815039801161721e-06,
+      "loss": 1.6786,
+      "step": 47
+    },
+    {
+      "epoch": 0.04014636696288552,
+      "grad_norm": 1.9526333808898926,
+      "learning_rate": 6.15582970243117e-07,
+      "loss": 1.7661,
+      "step": 48
+    },
+    {
+      "epoch": 0.04098274960794564,
+      "grad_norm": 2.419896364212036,
+      "learning_rate": 1.5413331334360182e-07,
+      "loss": 2.1558,
+      "step": 49
+    },
+    {
+      "epoch": 0.04181913225300575,
+      "grad_norm": 1.8293265104293823,
+      "learning_rate": 0.0,
+      "loss": 1.7244,
+      "step": 50
+    },
+    {
+      "epoch": 0.04181913225300575,
+      "eval_loss": 1.7563599348068237,
+      "eval_runtime": 596.0962,
+      "eval_samples_per_second": 3.379,
+      "eval_steps_per_second": 1.689,
+      "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": 8.2892273221632e+16,
+  "total_flos": 1.65784546443264e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null