Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:938111c2c685a4f089e10d026758070b85b5c0c2da179b7272150194a7b2957d
+oid sha256:79c30da950852db227e56bcde63cfad2a151ae9c6847f096da264e6ba514adc9
 size 97728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b7793d5817b20f2960f9c52dc086209632c3d9a93a8bf985e65b7f65269463c
+oid sha256:7e10fc5ae7a5e855c3c288c92818778a3758b7697af2bd8c909e9997c70f9513
 size 212298

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f319445d127f4b3bd13976a0a95a36ff44a4801e65b70960ba052ecd8c72eca2
+oid sha256:3f09849918f9ed7567426b361656bc1d055224b895f3686c42d5c0b5097e7d2d
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e7e26045a988282b41f98232af076dda4b558ffbcedf26cafe2dfa80a600216
+oid sha256:c62431bb79bfb5bacb09deabb1223c938fbbcf2387d7c7ea0e033a016e277af7
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a512888f6a06225774f836ef5158057264cbee52bcaf0cbd40cc576801d831d2
+oid sha256:cc5bb11813f3513cb52533d33bfe096e50a6bd3e7bd2e97f39c3dce8725accca
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e84bc9e4695f43d8a7868b3eab0621498a874107a2a10446dcfe617b377fdec
+oid sha256:3bef13c8584c16a9db8a5ec82be0cc2c46a8cbd13bfb2b2dd29de19214637e55
 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": 10.374112129211426,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.03019095780813646,
+  "best_metric": 10.373128890991211,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.06038191561627292,
   "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": 327.129,
       "eval_steps_per_second": 40.928,
       "step": 25
+    },
+    {
+      "epoch": 0.03139859612046192,
+      "grad_norm": 0.024625129997730255,
+      "learning_rate": 5e-05,
+      "loss": 10.3753,
+      "step": 26
+    },
+    {
+      "epoch": 0.03260623443278738,
+      "grad_norm": 0.026763916015625,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 10.3739,
+      "step": 27
+    },
+    {
+      "epoch": 0.03381387274511284,
+      "grad_norm": 0.030746644362807274,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 10.374,
+      "step": 28
+    },
+    {
+      "epoch": 0.035021511057438295,
+      "grad_norm": 0.03364461660385132,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 10.3744,
+      "step": 29
+    },
+    {
+      "epoch": 0.036229149369763756,
+      "grad_norm": 0.033119410276412964,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 10.3735,
+      "step": 30
+    },
+    {
+      "epoch": 0.03743678768208922,
+      "grad_norm": 0.03178080543875694,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 10.3737,
+      "step": 31
+    },
+    {
+      "epoch": 0.03864442599441467,
+      "grad_norm": 0.036192599684000015,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 10.3739,
+      "step": 32
+    },
+    {
+      "epoch": 0.03985206430674013,
+      "grad_norm": 0.03531722351908684,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 10.3734,
+      "step": 33
+    },
+    {
+      "epoch": 0.04105970261906559,
+      "grad_norm": 0.03745344281196594,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 10.3732,
+      "step": 34
+    },
+    {
+      "epoch": 0.04226734093139105,
+      "grad_norm": 0.03681091219186783,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 10.3728,
+      "step": 35
+    },
+    {
+      "epoch": 0.04347497924371651,
+      "grad_norm": 0.03902368247509003,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 10.3737,
+      "step": 36
+    },
+    {
+      "epoch": 0.04468261755604196,
+      "grad_norm": 0.03727221488952637,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 10.3722,
+      "step": 37
+    },
+    {
+      "epoch": 0.045890255868367424,
+      "grad_norm": 0.03553437814116478,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 10.3739,
+      "step": 38
+    },
+    {
+      "epoch": 0.047097894180692886,
+      "grad_norm": 0.03101722151041031,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 10.3747,
+      "step": 39
+    },
+    {
+      "epoch": 0.04830553249301834,
+      "grad_norm": 0.034259457141160965,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 10.374,
+      "step": 40
+    },
+    {
+      "epoch": 0.0495131708053438,
+      "grad_norm": 0.036786723881959915,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 10.3732,
+      "step": 41
+    },
+    {
+      "epoch": 0.050720809117669255,
+      "grad_norm": 0.03839438781142235,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 10.3741,
+      "step": 42
+    },
+    {
+      "epoch": 0.051928447429994716,
+      "grad_norm": 0.037743955850601196,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 10.3733,
+      "step": 43
+    },
+    {
+      "epoch": 0.05313608574232018,
+      "grad_norm": 0.0409163199365139,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 10.3725,
+      "step": 44
+    },
+    {
+      "epoch": 0.05434372405464563,
+      "grad_norm": 0.03863488510251045,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 10.3723,
+      "step": 45
+    },
+    {
+      "epoch": 0.05555136236697109,
+      "grad_norm": 0.03931540250778198,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 10.3729,
+      "step": 46
+    },
+    {
+      "epoch": 0.05675900067929655,
+      "grad_norm": 0.04146362096071243,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 10.3724,
+      "step": 47
+    },
+    {
+      "epoch": 0.05796663899162201,
+      "grad_norm": 0.04202931001782417,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 10.3723,
+      "step": 48
+    },
+    {
+      "epoch": 0.05917427730394747,
+      "grad_norm": 0.041146498173475266,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 10.3726,
+      "step": 49
+    },
+    {
+      "epoch": 0.06038191561627292,
+      "grad_norm": 0.04683046415448189,
+      "learning_rate": 0.0,
+      "loss": 10.3726,
+      "step": 50
+    },
+    {
+      "epoch": 0.06038191561627292,
+      "eval_loss": 10.373128890991211,
+      "eval_runtime": 17.1121,
+      "eval_samples_per_second": 326.027,
+      "eval_steps_per_second": 40.79,
+      "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": 21397394817024.0,
+  "total_flos": 42781424615424.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null