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:fef8c707b31c9c7abf128001894140101824642a91c054496041d7787527b5bd
+oid sha256:2d91030270ac26c5d31e5b0e6f2524c2cdb21236b072c47cc198d3f88dea6330
 size 332316480

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1dc4dcb31e7c2d2616833f2cd712fa95c36c1992ea674b1ea724a4125865f371
+oid sha256:7293f95d9e26e12fb8909ae182e5911fdaf51f8d1711269770562736a8412af1
 size 169157892

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:775a76071c6ec076915b89f43f00d24cfd445c3b90b76f509b183f1329845711
+oid sha256:0f0815240b73dc1db88d2d1669a6a64c2aa8119c81e0220e98b45537473832ea
 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": 0.8926352858543396,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.06684491978609626,
+  "best_metric": 0.7940676212310791,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.13368983957219252,
   "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": 20.665,
       "eval_steps_per_second": 2.591,
       "step": 25
+    },
+    {
+      "epoch": 0.06951871657754011,
+      "grad_norm": 2.6327173709869385,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 0.9139,
+      "step": 26
+    },
+    {
+      "epoch": 0.07219251336898395,
+      "grad_norm": 2.566983222961426,
+      "learning_rate": 6.167226819279528e-05,
+      "loss": 0.8632,
+      "step": 27
+    },
+    {
+      "epoch": 0.0748663101604278,
+      "grad_norm": 2.66111159324646,
+      "learning_rate": 5.782172325201155e-05,
+      "loss": 0.8961,
+      "step": 28
+    },
+    {
+      "epoch": 0.07754010695187166,
+      "grad_norm": 2.4014999866485596,
+      "learning_rate": 5.392295478639225e-05,
+      "loss": 0.8594,
+      "step": 29
+    },
+    {
+      "epoch": 0.08021390374331551,
+      "grad_norm": 2.5496883392333984,
+      "learning_rate": 5e-05,
+      "loss": 0.9502,
+      "step": 30
+    },
+    {
+      "epoch": 0.08288770053475936,
+      "grad_norm": 2.623340368270874,
+      "learning_rate": 4.607704521360776e-05,
+      "loss": 0.8187,
+      "step": 31
+    },
+    {
+      "epoch": 0.0855614973262032,
+      "grad_norm": 2.894226551055908,
+      "learning_rate": 4.2178276747988446e-05,
+      "loss": 0.8912,
+      "step": 32
+    },
+    {
+      "epoch": 0.08823529411764706,
+      "grad_norm": 2.7737977504730225,
+      "learning_rate": 3.832773180720475e-05,
+      "loss": 0.851,
+      "step": 33
+    },
+    {
+      "epoch": 0.09090909090909091,
+      "grad_norm": 3.402663469314575,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 0.8979,
+      "step": 34
+    },
+    {
+      "epoch": 0.09358288770053476,
+      "grad_norm": 2.527940511703491,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.8144,
+      "step": 35
+    },
+    {
+      "epoch": 0.0962566844919786,
+      "grad_norm": 2.616532564163208,
+      "learning_rate": 2.7300475013022663e-05,
+      "loss": 0.8559,
+      "step": 36
+    },
+    {
+      "epoch": 0.09893048128342247,
+      "grad_norm": 2.637568473815918,
+      "learning_rate": 2.3875071764202563e-05,
+      "loss": 0.8393,
+      "step": 37
+    },
+    {
+      "epoch": 0.10160427807486631,
+      "grad_norm": 2.4025931358337402,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 0.821,
+      "step": 38
+    },
+    {
+      "epoch": 0.10427807486631016,
+      "grad_norm": 2.9822089672088623,
+      "learning_rate": 1.7527597583490822e-05,
+      "loss": 1.0798,
+      "step": 39
+    },
+    {
+      "epoch": 0.10695187165775401,
+      "grad_norm": 2.652627468109131,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.845,
+      "step": 40
+    },
+    {
+      "epoch": 0.10962566844919786,
+      "grad_norm": 2.6627089977264404,
+      "learning_rate": 1.1979701719998453e-05,
+      "loss": 0.9285,
+      "step": 41
+    },
+    {
+      "epoch": 0.11229946524064172,
+      "grad_norm": 2.631807327270508,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.8711,
+      "step": 42
+    },
+    {
+      "epoch": 0.11497326203208556,
+      "grad_norm": 2.398806571960449,
+      "learning_rate": 7.367991782295391e-06,
+      "loss": 0.8058,
+      "step": 43
+    },
+    {
+      "epoch": 0.11764705882352941,
+      "grad_norm": 2.3895256519317627,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 0.8576,
+      "step": 44
+    },
+    {
+      "epoch": 0.12032085561497326,
+      "grad_norm": 2.452927827835083,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.8259,
+      "step": 45
+    },
+    {
+      "epoch": 0.12299465240641712,
+      "grad_norm": 2.3350183963775635,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 0.7746,
+      "step": 46
+    },
+    {
+      "epoch": 0.12566844919786097,
+      "grad_norm": 2.2762725353240967,
+      "learning_rate": 1.3815039801161721e-06,
+      "loss": 0.7767,
+      "step": 47
+    },
+    {
+      "epoch": 0.12834224598930483,
+      "grad_norm": 2.786212682723999,
+      "learning_rate": 6.15582970243117e-07,
+      "loss": 0.9144,
+      "step": 48
+    },
+    {
+      "epoch": 0.13101604278074866,
+      "grad_norm": 2.353525161743164,
+      "learning_rate": 1.5413331334360182e-07,
+      "loss": 0.7969,
+      "step": 49
+    },
+    {
+      "epoch": 0.13368983957219252,
+      "grad_norm": 2.672391176223755,
+      "learning_rate": 0.0,
+      "loss": 0.7842,
+      "step": 50
+    },
+    {
+      "epoch": 0.13368983957219252,
+      "eval_loss": 0.7940676212310791,
+      "eval_runtime": 30.486,
+      "eval_samples_per_second": 20.665,
+      "eval_steps_per_second": 2.591,
+      "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": 1.0462792658190336e+16,
+  "total_flos": 2.0821993309863936e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null