Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:33fbd6ed9cdb51889ac11a8d8f188d5b7df7c28cdecfd4e7b702d41990bcd78c
+oid sha256:371eb03c94d23702382f7d7257c3be158b0bea7f3d18de3402e172ab7f10c47f
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac0904bd09bb575280fcab4b6194482b5a75af63d333414592770861c1c7daa8
+oid sha256:6345887fa243bffff32d13454e37e67e1f24c1467076973aab8c938b7612f61b
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3fd7bd10617950724dfc1995a05302c0ea55e841c20879eb3993ddfcc8b173cf
+oid sha256:d3f1f95c13a1a76e0139efff17490d3b47ae1ed5ec425660f73f6e8cee31c131
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d089cf214d82e354b1b682050dcc6542220dd3589d6a60c12487879c9479a8a
+oid sha256:97e0f07ca914d9d589514f9f25452d58238045df10e7a0364270e90814b4440c
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:166f95c321d636645cc4b13a89625d8ea5be1ae694777acad76f59f9cc10846c
+oid sha256:98117577cd029a092b623809931453af7b2eb7d854394d6a26e37be9f116e66a
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f953eef242cd773fd1cccc0182abc03b15aeae41f28f47224a05191a315a584b
+oid sha256:b362716bd3384c410d6cffb7c795ed3b2090e8f924bfa7d84c0c1233c4e14b8f
 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": 0.5145310759544373,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.22922636103151864,
+  "best_metric": 0.43026846647262573,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.4584527220630373,
   "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": 34.789,
       "eval_steps_per_second": 4.355,
       "step": 25
+    },
+    {
+      "epoch": 0.23839541547277937,
+      "grad_norm": 3.7975339889526367,
+      "learning_rate": 5e-05,
+      "loss": 0.5815,
+      "step": 26
+    },
+    {
+      "epoch": 0.2475644699140401,
+      "grad_norm": 3.145819902420044,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.5265,
+      "step": 27
+    },
+    {
+      "epoch": 0.25673352435530084,
+      "grad_norm": 1.9554167985916138,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.4551,
+      "step": 28
+    },
+    {
+      "epoch": 0.2659025787965616,
+      "grad_norm": 2.1676225662231445,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.4737,
+      "step": 29
+    },
+    {
+      "epoch": 0.27507163323782235,
+      "grad_norm": 3.896536111831665,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.5187,
+      "step": 30
+    },
+    {
+      "epoch": 0.2842406876790831,
+      "grad_norm": 1.9137563705444336,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.4776,
+      "step": 31
+    },
+    {
+      "epoch": 0.2934097421203438,
+      "grad_norm": 1.6790127754211426,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.433,
+      "step": 32
+    },
+    {
+      "epoch": 0.3025787965616046,
+      "grad_norm": 1.8956066370010376,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.5206,
+      "step": 33
+    },
+    {
+      "epoch": 0.31174785100286534,
+      "grad_norm": 1.6820125579833984,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.4572,
+      "step": 34
+    },
+    {
+      "epoch": 0.3209169054441261,
+      "grad_norm": 2.292461633682251,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.5129,
+      "step": 35
+    },
+    {
+      "epoch": 0.3300859598853868,
+      "grad_norm": 2.118105411529541,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.4695,
+      "step": 36
+    },
+    {
+      "epoch": 0.33925501432664756,
+      "grad_norm": 1.4456408023834229,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.4419,
+      "step": 37
+    },
+    {
+      "epoch": 0.3484240687679083,
+      "grad_norm": 2.717830181121826,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.4682,
+      "step": 38
+    },
+    {
+      "epoch": 0.35759312320916903,
+      "grad_norm": 2.1756980419158936,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.4583,
+      "step": 39
+    },
+    {
+      "epoch": 0.3667621776504298,
+      "grad_norm": 2.1420400142669678,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.425,
+      "step": 40
+    },
+    {
+      "epoch": 0.37593123209169055,
+      "grad_norm": 2.0092952251434326,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.5095,
+      "step": 41
+    },
+    {
+      "epoch": 0.3851002865329513,
+      "grad_norm": 1.5908727645874023,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.4635,
+      "step": 42
+    },
+    {
+      "epoch": 0.394269340974212,
+      "grad_norm": 1.481441855430603,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.4087,
+      "step": 43
+    },
+    {
+      "epoch": 0.4034383954154728,
+      "grad_norm": 1.5329086780548096,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.4469,
+      "step": 44
+    },
+    {
+      "epoch": 0.41260744985673353,
+      "grad_norm": 1.787295937538147,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.4834,
+      "step": 45
+    },
+    {
+      "epoch": 0.4217765042979943,
+      "grad_norm": 1.4172388315200806,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.4725,
+      "step": 46
+    },
+    {
+      "epoch": 0.430945558739255,
+      "grad_norm": 1.452620267868042,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.4436,
+      "step": 47
+    },
+    {
+      "epoch": 0.44011461318051576,
+      "grad_norm": 1.2346012592315674,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.4279,
+      "step": 48
+    },
+    {
+      "epoch": 0.4492836676217765,
+      "grad_norm": 2.1931254863739014,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.4797,
+      "step": 49
+    },
+    {
+      "epoch": 0.4584527220630373,
+      "grad_norm": 2.076920747756958,
+      "learning_rate": 0.0,
+      "loss": 0.3643,
+      "step": 50
+    },
+    {
+      "epoch": 0.4584527220630373,
+      "eval_loss": 0.43026846647262573,
+      "eval_runtime": 33.0057,
+      "eval_samples_per_second": 22.269,
+      "eval_steps_per_second": 2.787,
+      "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": 2.9859068337822106e+17,
+  "total_flos": 5.969948642440643e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null