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:cbbd233f07eeca33a92b12203530d6ac6dffbec0543684d8462f1f613d35b3c3
+oid sha256:b4b33828bb433245136e4eb70b59cd7f93ded180f3935b7fb3f59a5a99498337
 size 147770496

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43e275b573eaab7c914f711c8a0dd92169b0f5f490b6c9aee7fbf8d03cd8167e
+oid sha256:c200551b89c16455b6038d133a29eaba1a78025981dc4feb026e58d4bd98894e
 size 295765866

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:45402075fdfb1fcfbf8f07c4c2dbff44d792cb62f3edaf7c074fe214d36eb512
+oid sha256:4a91d4fb87de9d31a55025cfe0a5ed2d709ef7cbfaf5ae1ea399b123e73d0d27
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a6a5af60c7c33a735b1e735898fa28a5ecdd31fdd82cd58c7d886cff33657e9f
+oid sha256:ce37cf6b9e6065ca6d3fa200274f228221367383c249c2f18cffb2f3c52646b3
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e15706e5391861dbfa34e6969459cabd203a26d8e1b37a2f7123970fc3830140
+oid sha256:f0e4fab1019be288521d432f82f6a9e65d1156c068544e4f1c5986aefcd94519
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d9e96c0ccdc8d930e80d562fd494797f0079b2509a2370b12217e9f3f14cdda1
+oid sha256:109b911721a6fe9fd3da0ea6a769e6a0803b854857901e1cb4355d9483d4e5c6
 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": NaN,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.5997001499250375,
+  "epoch": 1.206896551724138,
   "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": 38.469,
       "eval_steps_per_second": 4.928,
       "step": 25
+    },
+    {
+      "epoch": 0.623688155922039,
+      "grad_norm": 2.2931978702545166,
+      "learning_rate": 5e-05,
+      "loss": 0.4088,
+      "step": 26
+    },
+    {
+      "epoch": 0.6476761619190404,
+      "grad_norm": 4.021605491638184,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.4037,
+      "step": 27
+    },
+    {
+      "epoch": 0.671664167916042,
+      "grad_norm": 3.1461658477783203,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.5003,
+      "step": 28
+    },
+    {
+      "epoch": 0.6956521739130435,
+      "grad_norm": 3.1163697242736816,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.5027,
+      "step": 29
+    },
+    {
+      "epoch": 0.719640179910045,
+      "grad_norm": 2.4896295070648193,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.3963,
+      "step": 30
+    },
+    {
+      "epoch": 0.7436281859070465,
+      "grad_norm": 2.6032440662384033,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.3874,
+      "step": 31
+    },
+    {
+      "epoch": 0.767616191904048,
+      "grad_norm": 2.020462989807129,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.3101,
+      "step": 32
+    },
+    {
+      "epoch": 0.7916041979010495,
+      "grad_norm": 1.9592450857162476,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.3533,
+      "step": 33
+    },
+    {
+      "epoch": 0.815592203898051,
+      "grad_norm": 2.000779151916504,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.3312,
+      "step": 34
+    },
+    {
+      "epoch": 0.8395802098950524,
+      "grad_norm": 2.860116958618164,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.4,
+      "step": 35
+    },
+    {
+      "epoch": 0.863568215892054,
+      "grad_norm": 3.1632578372955322,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.3844,
+      "step": 36
+    },
+    {
+      "epoch": 0.8875562218890555,
+      "grad_norm": 1.6567466259002686,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.3445,
+      "step": 37
+    },
+    {
+      "epoch": 0.9115442278860569,
+      "grad_norm": 3.800011396408081,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.4563,
+      "step": 38
+    },
+    {
+      "epoch": 0.9355322338830585,
+      "grad_norm": 4.2941741943359375,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.3852,
+      "step": 39
+    },
+    {
+      "epoch": 0.95952023988006,
+      "grad_norm": 3.70890212059021,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.4847,
+      "step": 40
+    },
+    {
+      "epoch": 0.9835082458770614,
+      "grad_norm": 3.93947696685791,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.5756,
+      "step": 41
+    },
+    {
+      "epoch": 1.014992503748126,
+      "grad_norm": 2.8971164226531982,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.3497,
+      "step": 42
+    },
+    {
+      "epoch": 1.0389805097451275,
+      "grad_norm": 3.1195619106292725,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.2846,
+      "step": 43
+    },
+    {
+      "epoch": 1.062968515742129,
+      "grad_norm": 1.7674708366394043,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.1979,
+      "step": 44
+    },
+    {
+      "epoch": 1.0869565217391304,
+      "grad_norm": 2.618422269821167,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.2861,
+      "step": 45
+    },
+    {
+      "epoch": 1.1109445277361318,
+      "grad_norm": 2.5724215507507324,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.2475,
+      "step": 46
+    },
+    {
+      "epoch": 1.1349325337331335,
+      "grad_norm": 2.017848014831543,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.3238,
+      "step": 47
+    },
+    {
+      "epoch": 1.158920539730135,
+      "grad_norm": 2.6160171031951904,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.2674,
+      "step": 48
+    },
+    {
+      "epoch": 1.1829085457271364,
+      "grad_norm": 1.9704896211624146,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.2627,
+      "step": 49
+    },
+    {
+      "epoch": 1.206896551724138,
+      "grad_norm": 4.044738292694092,
+      "learning_rate": 0.0,
+      "loss": 0.375,
+      "step": 50
+    },
+    {
+      "epoch": 1.206896551724138,
+      "eval_loss": NaN,
+      "eval_runtime": 7.2862,
+      "eval_samples_per_second": 38.566,
+      "eval_steps_per_second": 4.941,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -212,7 +395,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 0
+        "early_stopping_patience_counter": 1
       }
     },
     "TrainerControl": {
@@ -221,12 +404,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 5.29768176943104e+16,
+  "total_flos": 1.059536353886208e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null