Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5774cab308dbe80d10435b1cf9a0aa08d0ffedc1e6a10ce3f468b455fbc871f4
+oid sha256:3a5fd2777359c43e974b9df67ee5dc153b762f90b00ea8c72b8fc7e1944f83e7
 size 524363632

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b6880373030581e11e5dcb495d44f1b98e9ac7d82636d530be877c01f25464b
+oid sha256:b6b6c13d7850d63b573dddc8adb0e2f98ef13e02da00fa93c728513d28eb21e0
 size 1049049122

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e80a4edd7b140b07fec5ff31f7714594e2ec328302fabd302dc8347ccbbd5d7
+oid sha256:2991c13ea38faf99e43335085098d98e4f7ea69bddad81dc135fbe82f31041b0
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a19170056d098a7d41e3ac9f1db8ab650ff257fdbfa6974871d2e053a0d24c2b
+oid sha256:c42fdbb2e78caa39e684638e7f39f3fa8eab06fcd78c9c405bc8bdf9a74168ca
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:709692988a41803b84bce611e1d7586bf2a273554d51df2c6a0edb5e8c0e0e47
+oid sha256:ed8983d6861c51e48def1b438751ad2e3a0627182c07da612fe01582862b7339
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:14706f9f28cb97807594736d01aea931b2255e077330224ef19a587e8d07a67e
+oid sha256:e0dab349d6802adae45f515c6b028a49fbc32656043c8617235585e95c7c58ef
 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": 1.335520625114441,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 1.3636363636363638,
+  "best_metric": 1.287821888923645,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 2.7272727272727275,
   "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": 19.831,
       "eval_steps_per_second": 2.538,
       "step": 25
+    },
+    {
+      "epoch": 1.4175084175084174,
+      "grad_norm": 6.170543670654297,
+      "learning_rate": 5e-05,
+      "loss": 1.342,
+      "step": 26
+    },
+    {
+      "epoch": 1.4713804713804715,
+      "grad_norm": 9.504968643188477,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 1.3388,
+      "step": 27
+    },
+    {
+      "epoch": 1.5252525252525253,
+      "grad_norm": 5.137529373168945,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 1.2618,
+      "step": 28
+    },
+    {
+      "epoch": 1.5791245791245792,
+      "grad_norm": 5.660238265991211,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 1.2721,
+      "step": 29
+    },
+    {
+      "epoch": 1.632996632996633,
+      "grad_norm": 6.462338924407959,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 1.2833,
+      "step": 30
+    },
+    {
+      "epoch": 1.6868686868686869,
+      "grad_norm": 8.593851089477539,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 1.3595,
+      "step": 31
+    },
+    {
+      "epoch": 1.7407407407407407,
+      "grad_norm": 8.528369903564453,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 1.2751,
+      "step": 32
+    },
+    {
+      "epoch": 1.7946127946127945,
+      "grad_norm": 5.623615741729736,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 1.2061,
+      "step": 33
+    },
+    {
+      "epoch": 1.8484848484848486,
+      "grad_norm": 6.242150783538818,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 1.3555,
+      "step": 34
+    },
+    {
+      "epoch": 1.9023569023569022,
+      "grad_norm": 6.943024635314941,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 1.3113,
+      "step": 35
+    },
+    {
+      "epoch": 1.9562289562289563,
+      "grad_norm": 7.993992805480957,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 1.2579,
+      "step": 36
+    },
+    {
+      "epoch": 2.026936026936027,
+      "grad_norm": 4.730837345123291,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 1.2512,
+      "step": 37
+    },
+    {
+      "epoch": 2.080808080808081,
+      "grad_norm": 4.84640645980835,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.2604,
+      "step": 38
+    },
+    {
+      "epoch": 2.1346801346801345,
+      "grad_norm": 5.229759216308594,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 1.2172,
+      "step": 39
+    },
+    {
+      "epoch": 2.1885521885521886,
+      "grad_norm": 6.82036828994751,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 1.2792,
+      "step": 40
+    },
+    {
+      "epoch": 2.242424242424242,
+      "grad_norm": 9.063141822814941,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 1.313,
+      "step": 41
+    },
+    {
+      "epoch": 2.2962962962962963,
+      "grad_norm": 5.071662425994873,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 1.1785,
+      "step": 42
+    },
+    {
+      "epoch": 2.3501683501683504,
+      "grad_norm": 4.716180801391602,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 1.3036,
+      "step": 43
+    },
+    {
+      "epoch": 2.404040404040404,
+      "grad_norm": 5.414945125579834,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.2882,
+      "step": 44
+    },
+    {
+      "epoch": 2.457912457912458,
+      "grad_norm": 9.923550605773926,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 1.2282,
+      "step": 45
+    },
+    {
+      "epoch": 2.5117845117845117,
+      "grad_norm": 5.375794887542725,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 1.2872,
+      "step": 46
+    },
+    {
+      "epoch": 2.5656565656565657,
+      "grad_norm": 4.690090179443359,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 1.2344,
+      "step": 47
+    },
+    {
+      "epoch": 2.6195286195286194,
+      "grad_norm": 5.754395961761475,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 1.2567,
+      "step": 48
+    },
+    {
+      "epoch": 2.6734006734006734,
+      "grad_norm": 6.473057270050049,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 1.2354,
+      "step": 49
+    },
+    {
+      "epoch": 2.7272727272727275,
+      "grad_norm": 8.637455940246582,
+      "learning_rate": 0.0,
+      "loss": 1.2458,
+      "step": 50
+    },
+    {
+      "epoch": 2.7272727272727275,
+      "eval_loss": 1.287821888923645,
+      "eval_runtime": 6.3123,
+      "eval_samples_per_second": 19.802,
+      "eval_steps_per_second": 2.535,
+      "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": 5.476375360176128e+17,
+  "total_flos": 1.0952750720352256e+18,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null