Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:048f74e80b7f8bad82b3b322a5cfe524b57f93dee7c5e07c84ca7c7085d30a43
+oid sha256:cd359f74b9954f66c503aa145923ffcfc86ed5e41caa7bc891d343b570e8ea33
 size 70430032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ae1a398e6c2e89693ccd849d9ef79b9e58d84454e894eae8288a469418f73cf
+oid sha256:cac64bca19a6a704bd7fd99be576a907109e6d5b5919c57d7a379c89a100ff4e
 size 141053442

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dbb25504f0004d25d7bfb9ebb15cdcd8840d11db56cb16af66a24b2bdb9a1c42
+oid sha256:388f1505b0c413e6149fde8356d06e785e2b761d8d76adebf60c21dbbfdd49a6
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b32b4d62eeea293942a25e2e1551f00f8b5f61be534161487ff9f2319f81b77f
+oid sha256:08fb0cda51360753f1d816925b0df3b38d579e4e4b4aecccc10320d1877be30b
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:301e58dbd7898c4d706050c74b192470f84243e0d01cb81d124dc9d92546b0af
+oid sha256:1cca4201a22d3aa578da92ed10462c215ba40bf5a3eafaf7f08f14888a7702b2
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a3c4fdc2aaf60365f12fa1fb9e5b70f12c041088711874d3882127b9ec9d6edb
+oid sha256:c14efb9223d979124d2d87c664a50e87fa4b7f25f2db64fd921cb4dceb362248
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f37b2aa490ccb1598b01e14cda36e9081f7ce646deab4d3c2d03de0d2169a755
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.8079664707183838,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.017392060524370624,
+  "best_metric": 1.7661371231079102,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.03478412104874125,
   "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": 147.867,
       "eval_steps_per_second": 18.491,
       "step": 25
+    },
+    {
+      "epoch": 0.018087742945345448,
+      "grad_norm": 0.8424671292304993,
+      "learning_rate": 5e-05,
+      "loss": 1.3785,
+      "step": 26
+    },
+    {
+      "epoch": 0.018783425366320276,
+      "grad_norm": 1.016959309577942,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 1.5195,
+      "step": 27
+    },
+    {
+      "epoch": 0.0194791077872951,
+      "grad_norm": 1.0629756450653076,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 1.5556,
+      "step": 28
+    },
+    {
+      "epoch": 0.020174790208269924,
+      "grad_norm": 1.0436463356018066,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 1.6001,
+      "step": 29
+    },
+    {
+      "epoch": 0.02087047262924475,
+      "grad_norm": 1.0392799377441406,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 1.6913,
+      "step": 30
+    },
+    {
+      "epoch": 0.021566155050219575,
+      "grad_norm": 0.9874686598777771,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 1.6036,
+      "step": 31
+    },
+    {
+      "epoch": 0.0222618374711944,
+      "grad_norm": 0.922863781452179,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 1.6276,
+      "step": 32
+    },
+    {
+      "epoch": 0.022957519892169223,
+      "grad_norm": 0.9779465794563293,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 1.7493,
+      "step": 33
+    },
+    {
+      "epoch": 0.02365320231314405,
+      "grad_norm": 1.0955945253372192,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 1.8936,
+      "step": 34
+    },
+    {
+      "epoch": 0.024348884734118875,
+      "grad_norm": 1.216680884361267,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 1.8458,
+      "step": 35
+    },
+    {
+      "epoch": 0.0250445671550937,
+      "grad_norm": 1.559578537940979,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 2.0036,
+      "step": 36
+    },
+    {
+      "epoch": 0.025740249576068526,
+      "grad_norm": 2.015183925628662,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 2.1613,
+      "step": 37
+    },
+    {
+      "epoch": 0.02643593199704335,
+      "grad_norm": 0.7404354810714722,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.4749,
+      "step": 38
+    },
+    {
+      "epoch": 0.027131614418018174,
+      "grad_norm": 0.6674442291259766,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 1.5052,
+      "step": 39
+    },
+    {
+      "epoch": 0.027827296838992998,
+      "grad_norm": 0.6575154662132263,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 1.5306,
+      "step": 40
+    },
+    {
+      "epoch": 0.028522979259967825,
+      "grad_norm": 0.6969729661941528,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 1.6058,
+      "step": 41
+    },
+    {
+      "epoch": 0.02921866168094265,
+      "grad_norm": 0.6941806077957153,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 1.5187,
+      "step": 42
+    },
+    {
+      "epoch": 0.029914344101917473,
+      "grad_norm": 0.7898688316345215,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 1.6099,
+      "step": 43
+    },
+    {
+      "epoch": 0.0306100265228923,
+      "grad_norm": 0.8048236966133118,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.7066,
+      "step": 44
+    },
+    {
+      "epoch": 0.031305708943867125,
+      "grad_norm": 0.9454255700111389,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 1.7805,
+      "step": 45
+    },
+    {
+      "epoch": 0.03200139136484195,
+      "grad_norm": 1.020853877067566,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 1.7649,
+      "step": 46
+    },
+    {
+      "epoch": 0.03269707378581677,
+      "grad_norm": 1.219463586807251,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 1.9171,
+      "step": 47
+    },
+    {
+      "epoch": 0.0333927562067916,
+      "grad_norm": 1.4808721542358398,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 1.8327,
+      "step": 48
+    },
+    {
+      "epoch": 0.03408843862776643,
+      "grad_norm": 1.8531748056411743,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 1.9587,
+      "step": 49
+    },
+    {
+      "epoch": 0.03478412104874125,
+      "grad_norm": 2.548074245452881,
+      "learning_rate": 0.0,
+      "loss": 2.2593,
+      "step": 50
+    },
+    {
+      "epoch": 0.03478412104874125,
+      "eval_loss": 1.7661371231079102,
+      "eval_runtime": 112.9538,
+      "eval_samples_per_second": 85.734,
+      "eval_steps_per_second": 10.721,
+      "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": 1.4774273839202304e+16,
+  "total_flos": 2.9539319471407104e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null