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:e78183aed753a8a16fbddda81f562d91d397016c7876654fe5080a31e32c7a64
+oid sha256:878d369634353fce72fb42648bf153b3f98b9301be498c571f955bf97f8757b7
 size 70430032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49093008bdcce0b1293167466a64f2ba22798f3a56a3ea3f6b2e31291dbdf22d
+oid sha256:79543774c96d3a4341ea7927bef29254dcc3fabdbde2caae4d703ec5b911fd6a
 size 141053442

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:18df2fbf2f5953d7dca39e567f43729022afe3b373a0a850182b59691214e644
+oid sha256:1fcbc287a62919331c2024d57caf2d5ddb5bb5d72bc617a42570cd4ab73984bf
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:165c999623a3b67e8dccd892a700f58c10f702bad8d05a23e1637bc79865888e
+oid sha256:bfd2c0095734e7466906a7bb062051db4186d90f39b38c3ead8a93fd7aeaced3
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:29a4e952ec8191bc3f9266d40302dc1c1eb058d9d72876551b29c0ed1727b6ca
+oid sha256:8b25bc574d5018961ec7788885363f255b69666d3cc564859951331f0b8e17ee
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0baf6f9e56bd4c99a9a8e41d4193b35a00b406c23688566ee807a8bb3d9f399d
+oid sha256:5e071529d4fb6c092d9ed530aa582e7041e6f29798451289a11a6b014baa04b5
 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": 1.6095383167266846,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.05141388174807198,
+  "best_metric": 1.374308466911316,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.10282776349614396,
   "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": 107.126,
       "eval_steps_per_second": 13.407,
       "step": 25
+    },
+    {
+      "epoch": 0.05347043701799486,
+      "grad_norm": 0.6380476951599121,
+      "learning_rate": 5e-05,
+      "loss": 0.6109,
+      "step": 26
+    },
+    {
+      "epoch": 0.055526992287917736,
+      "grad_norm": 0.5205564498901367,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.6063,
+      "step": 27
+    },
+    {
+      "epoch": 0.05758354755784062,
+      "grad_norm": 0.4885164797306061,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 1.6047,
+      "step": 28
+    },
+    {
+      "epoch": 0.0596401028277635,
+      "grad_norm": 0.5374402403831482,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 1.701,
+      "step": 29
+    },
+    {
+      "epoch": 0.061696658097686374,
+      "grad_norm": 1.4350026845932007,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 1.1647,
+      "step": 30
+    },
+    {
+      "epoch": 0.06375321336760925,
+      "grad_norm": 1.5044260025024414,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 1.1382,
+      "step": 31
+    },
+    {
+      "epoch": 0.06580976863753213,
+      "grad_norm": 1.5621658563613892,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 1.0869,
+      "step": 32
+    },
+    {
+      "epoch": 0.067866323907455,
+      "grad_norm": 1.0276201963424683,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 1.485,
+      "step": 33
+    },
+    {
+      "epoch": 0.0699228791773779,
+      "grad_norm": 1.015711784362793,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 1.7278,
+      "step": 34
+    },
+    {
+      "epoch": 0.07197943444730077,
+      "grad_norm": 1.3744566440582275,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 2.1299,
+      "step": 35
+    },
+    {
+      "epoch": 0.07403598971722365,
+      "grad_norm": 5.565454959869385,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 2.0742,
+      "step": 36
+    },
+    {
+      "epoch": 0.07609254498714653,
+      "grad_norm": 8.212292671203613,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 2.5316,
+      "step": 37
+    },
+    {
+      "epoch": 0.0781491002570694,
+      "grad_norm": 0.34369704127311707,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.5871,
+      "step": 38
+    },
+    {
+      "epoch": 0.08020565552699228,
+      "grad_norm": 0.3409431576728821,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.5753,
+      "step": 39
+    },
+    {
+      "epoch": 0.08226221079691516,
+      "grad_norm": 0.29858067631721497,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.8785,
+      "step": 40
+    },
+    {
+      "epoch": 0.08431876606683805,
+      "grad_norm": 0.47956377267837524,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 1.6915,
+      "step": 41
+    },
+    {
+      "epoch": 0.08637532133676093,
+      "grad_norm": 0.5060607194900513,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 1.1406,
+      "step": 42
+    },
+    {
+      "epoch": 0.0884318766066838,
+      "grad_norm": 0.6011289358139038,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 1.0699,
+      "step": 43
+    },
+    {
+      "epoch": 0.09048843187660668,
+      "grad_norm": 0.6478893756866455,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.0172,
+      "step": 44
+    },
+    {
+      "epoch": 0.09254498714652956,
+      "grad_norm": 0.7206456661224365,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 1.1023,
+      "step": 45
+    },
+    {
+      "epoch": 0.09460154241645244,
+      "grad_norm": 1.079906702041626,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 1.8167,
+      "step": 46
+    },
+    {
+      "epoch": 0.09665809768637532,
+      "grad_norm": 1.0317572355270386,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 2.1526,
+      "step": 47
+    },
+    {
+      "epoch": 0.09871465295629821,
+      "grad_norm": 2.9713265895843506,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 1.8249,
+      "step": 48
+    },
+    {
+      "epoch": 0.10077120822622108,
+      "grad_norm": 4.130226135253906,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 1.6247,
+      "step": 49
+    },
+    {
+      "epoch": 0.10282776349614396,
+      "grad_norm": 6.861790657043457,
+      "learning_rate": 0.0,
+      "loss": 2.2831,
+      "step": 50
+    },
+    {
+      "epoch": 0.10282776349614396,
+      "eval_loss": 1.374308466911316,
+      "eval_runtime": 30.5227,
+      "eval_samples_per_second": 107.33,
+      "eval_steps_per_second": 13.433,
+      "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": 1.911150602931405e+16,
+  "total_flos": 3.813995866541261e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null