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:bb133f6d0e20049bc6abcfac08daebcb3875eb0db155038ea10f98cac508b8ab
+oid sha256:08236d767394b95c0ef03cb9d85770e1ec9a20bef502c3aa2e054b2a23ea0f4b
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ffc64ec5df363ac12284a08cecd2711bd70b7d40fd340538847f7f065931d3c
+oid sha256:ec59c8da2c55529d22a6c963d1e9b4e47cbce441ab9d51eac0f755a978d14371
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:532f0f245cca9ec64ae51526cc5e1612882bc1d5d62df4bc336310e00b71c6a3
+oid sha256:fab19e9d57d2343f999cbd33c0c95240336185c029fcaaee8821e713ddf94f72
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:af5b571293032fc6da1affbc9f86eac11bab9aa84d43a6e4ee938a4a856aff94
+oid sha256:4bce6514a724205802240199e4f1acc3f89b6aacfab809ec7d397cdee0f5ca82
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f67fca3186bfa47c726ee11f030f9bd768d6cdb83a85850fccbbe8950f8efcc7
+oid sha256:805b654ea4fb21ab2718981d433b2925268cb941f6625b6641ce62451c16344c
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eacf6e2d644fa60f7cfbe42e73a0f19c50e470291fd3274abe34b1b70274767d
+oid sha256:5c67547f53a8529213ab65f1d4d284f9c9dc2d9fd6c4b65dee9816858b820c7f
 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": 1.4364030361175537,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.0332944897619444,
+  "best_metric": 1.3974195718765259,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.0665889795238888,
   "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": 38.135,
       "eval_steps_per_second": 4.772,
       "step": 25
+    },
+    {
+      "epoch": 0.034626269352422176,
+      "grad_norm": 0.7670523524284363,
+      "learning_rate": 5e-05,
+      "loss": 1.6652,
+      "step": 26
+    },
+    {
+      "epoch": 0.03595804894289995,
+      "grad_norm": 0.7151476740837097,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 1.5839,
+      "step": 27
+    },
+    {
+      "epoch": 0.03728982853337773,
+      "grad_norm": 0.7840404510498047,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 1.4314,
+      "step": 28
+    },
+    {
+      "epoch": 0.038621608123855504,
+      "grad_norm": 0.7918953895568848,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 1.4365,
+      "step": 29
+    },
+    {
+      "epoch": 0.03995338771433328,
+      "grad_norm": 0.8279181718826294,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 1.3891,
+      "step": 30
+    },
+    {
+      "epoch": 0.041285167304811056,
+      "grad_norm": 0.8578282594680786,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 1.2858,
+      "step": 31
+    },
+    {
+      "epoch": 0.04261694689528883,
+      "grad_norm": 0.8482633829116821,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 1.1511,
+      "step": 32
+    },
+    {
+      "epoch": 0.04394872648576661,
+      "grad_norm": 0.8851420283317566,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 1.4296,
+      "step": 33
+    },
+    {
+      "epoch": 0.045280506076244384,
+      "grad_norm": 1.0721423625946045,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 1.4503,
+      "step": 34
+    },
+    {
+      "epoch": 0.04661228566672216,
+      "grad_norm": 1.0197111368179321,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 1.4107,
+      "step": 35
+    },
+    {
+      "epoch": 0.047944065257199936,
+      "grad_norm": 1.1104793548583984,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 1.236,
+      "step": 36
+    },
+    {
+      "epoch": 0.04927584484767771,
+      "grad_norm": 1.620796799659729,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 1.4854,
+      "step": 37
+    },
+    {
+      "epoch": 0.05060762443815549,
+      "grad_norm": 0.7224025726318359,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.7413,
+      "step": 38
+    },
+    {
+      "epoch": 0.051939404028633264,
+      "grad_norm": 0.6184026598930359,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 1.5911,
+      "step": 39
+    },
+    {
+      "epoch": 0.05327118361911104,
+      "grad_norm": 0.6563757658004761,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 1.5257,
+      "step": 40
+    },
+    {
+      "epoch": 0.054602963209588816,
+      "grad_norm": 0.7842867970466614,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 1.4908,
+      "step": 41
+    },
+    {
+      "epoch": 0.05593474280006659,
+      "grad_norm": 0.6858050227165222,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 1.3321,
+      "step": 42
+    },
+    {
+      "epoch": 0.05726652239054437,
+      "grad_norm": 0.7674694061279297,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 1.3322,
+      "step": 43
+    },
+    {
+      "epoch": 0.058598301981022144,
+      "grad_norm": 0.7808869481086731,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.2364,
+      "step": 44
+    },
+    {
+      "epoch": 0.05993008157149992,
+      "grad_norm": 0.9280687570571899,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 1.3535,
+      "step": 45
+    },
+    {
+      "epoch": 0.061261861161977696,
+      "grad_norm": 0.8980047702789307,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 1.2546,
+      "step": 46
+    },
+    {
+      "epoch": 0.06259364075245546,
+      "grad_norm": 0.9971718192100525,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 1.3707,
+      "step": 47
+    },
+    {
+      "epoch": 0.06392542034293325,
+      "grad_norm": 1.1494028568267822,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 1.1686,
+      "step": 48
+    },
+    {
+      "epoch": 0.06525719993341102,
+      "grad_norm": 1.1565730571746826,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 1.2963,
+      "step": 49
+    },
+    {
+      "epoch": 0.0665889795238888,
+      "grad_norm": 1.65233314037323,
+      "learning_rate": 0.0,
+      "loss": 1.5058,
+      "step": 50
+    },
+    {
+      "epoch": 0.0665889795238888,
+      "eval_loss": 1.3974195718765259,
+      "eval_runtime": 132.6366,
+      "eval_samples_per_second": 38.142,
+      "eval_steps_per_second": 4.772,
+      "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": 2.984041808658432e+17,
+  "total_flos": 5.968083617316864e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null