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:b8257ece152fd51f7d0211df355872c403e01447fcda688e128760b6af98718e
+oid sha256:94ac9544b2bbeccf197383c2cd5caa2dc44202a4b2a154f9f61a1d64105ed97a
 size 319876032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2176838d87674045670069856f4bd795e44189e6058facc9e15d2400b3a486cd
+oid sha256:28e54390b8f852e65e3ea24d0745625b22b82a5c3ac61e3bd990790bcc3891f7
 size 640009682

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37ddf119adce9076b166af0272b29d188211b79ac72eec27ef6c0cee0de9de8f
+oid sha256:b4cb2f209dfe8277faa6d3b37211da5afff07cdb0c956f67b0bd700e1ff17539
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d6315d5288ee4c73f5e89231f0a54f75978299d65800cc60d9b38f6de8033459
+oid sha256:f2d7afe537d520ab9538d664a1da93e97afdde2fc7a6452cafe15bbb7d868e76
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07a27beeceb9e4b94d14506feec776956f66adc7820c40f554f78fc1b02cabf9
+oid sha256:dadcef96dfa74605f53a4fe4bcdb71d361b73df8b32c1aa228cd015739b6a63f
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d9187f238252647f0d8c153b1c2ffe64eb2e49797a5be0a28e0b691f40d497c
+oid sha256:35ccec1a1aa24de1cf64ad056e1dabebe6e48a128d190c1d7992feab1a5cffb7
 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": 0.13114991784095764,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.04326663061114116,
+  "best_metric": 0.11287513375282288,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.08653326122228232,
   "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": 15.456,
       "eval_steps_per_second": 1.933,
       "step": 25
+    },
+    {
+      "epoch": 0.0449972958355868,
+      "grad_norm": 0.3784489929676056,
+      "learning_rate": 5e-05,
+      "loss": 0.3095,
+      "step": 26
+    },
+    {
+      "epoch": 0.04672796106003245,
+      "grad_norm": 0.33651015162467957,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.3036,
+      "step": 27
+    },
+    {
+      "epoch": 0.0484586262844781,
+      "grad_norm": 0.3961086571216583,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.3139,
+      "step": 28
+    },
+    {
+      "epoch": 0.05018929150892374,
+      "grad_norm": 0.4263656735420227,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.3529,
+      "step": 29
+    },
+    {
+      "epoch": 0.05191995673336939,
+      "grad_norm": 0.46552321314811707,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.4548,
+      "step": 30
+    },
+    {
+      "epoch": 0.05365062195781504,
+      "grad_norm": 0.33770114183425903,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.4576,
+      "step": 31
+    },
+    {
+      "epoch": 0.05538128718226068,
+      "grad_norm": 0.4641321897506714,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.5966,
+      "step": 32
+    },
+    {
+      "epoch": 0.05711195240670633,
+      "grad_norm": 0.5943290591239929,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.8214,
+      "step": 33
+    },
+    {
+      "epoch": 0.05884261763115197,
+      "grad_norm": 1.117336392402649,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 1.4997,
+      "step": 34
+    },
+    {
+      "epoch": 0.06057328285559762,
+      "grad_norm": 2.4597384929656982,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 3.1596,
+      "step": 35
+    },
+    {
+      "epoch": 0.06230394808004327,
+      "grad_norm": 7.086680889129639,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 5.4416,
+      "step": 36
+    },
+    {
+      "epoch": 0.06403461330448891,
+      "grad_norm": 6.797247409820557,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 6.6489,
+      "step": 37
+    },
+    {
+      "epoch": 0.06576527852893456,
+      "grad_norm": 5.29379415512085,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 3.9137,
+      "step": 38
+    },
+    {
+      "epoch": 0.06749594375338021,
+      "grad_norm": 0.2345895767211914,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.2587,
+      "step": 39
+    },
+    {
+      "epoch": 0.06922660897782586,
+      "grad_norm": 0.2742256820201874,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.2752,
+      "step": 40
+    },
+    {
+      "epoch": 0.07095727420227149,
+      "grad_norm": 0.2429785281419754,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.293,
+      "step": 41
+    },
+    {
+      "epoch": 0.07268793942671714,
+      "grad_norm": 0.2798793613910675,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.3659,
+      "step": 42
+    },
+    {
+      "epoch": 0.07441860465116279,
+      "grad_norm": 0.3929751217365265,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.4205,
+      "step": 43
+    },
+    {
+      "epoch": 0.07614926987560844,
+      "grad_norm": 0.3679610788822174,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.4298,
+      "step": 44
+    },
+    {
+      "epoch": 0.07787993510005409,
+      "grad_norm": 0.5460615754127502,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.5886,
+      "step": 45
+    },
+    {
+      "epoch": 0.07961060032449974,
+      "grad_norm": 0.7755551934242249,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.88,
+      "step": 46
+    },
+    {
+      "epoch": 0.08134126554894537,
+      "grad_norm": 1.5932703018188477,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 1.6708,
+      "step": 47
+    },
+    {
+      "epoch": 0.08307193077339102,
+      "grad_norm": 4.295409679412842,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 3.8597,
+      "step": 48
+    },
+    {
+      "epoch": 0.08480259599783667,
+      "grad_norm": 6.057656288146973,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 5.9046,
+      "step": 49
+    },
+    {
+      "epoch": 0.08653326122228232,
+      "grad_norm": 7.730199813842773,
+      "learning_rate": 0.0,
+      "loss": 7.9757,
+      "step": 50
+    },
+    {
+      "epoch": 0.08653326122228232,
+      "eval_loss": 0.11287513375282288,
+      "eval_runtime": 253.0809,
+      "eval_samples_per_second": 15.382,
+      "eval_steps_per_second": 1.924,
+      "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": 3.26725086767743e+17,
+  "total_flos": 6.542719156695859e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null