Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05ac98f7572791ed109a86b36090f33a6a88fccf289467cf4f87f6d27e1ad9ec
+oid sha256:3dc01cc1c8922035e6b9fc96c7b52c142a63139b532b3e4bd820f42c44fd924f
 size 319876032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:38a7c8e151591a0e84017fef8e5bf381bea60b16e7e7aa520a691ebc059a56e6
+oid sha256:ffae26628a36ba49cf6313e47ce96aacde2b9b8b783e4c4dc7de913ba17f945e
 size 640009682

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a767a46666e58d1abd9446f6a7f1095d5135b5fd9745a05b22c127c3a5dfe4ea
+oid sha256:1c8d6d1c254edb7ef941443b5f744b8f46ee2678398cd4b815842f6776e004b4
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:adfe4f4f4904d0554e2aeb2cd4314ff030b75d48260649318f94f375f2d4f633
+oid sha256:c4cb38215e61f3fab87e5d2c614499cb7511f0fedfd3f0b54ca8c62053d571dc
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16bebfab4beb09692caf361b5dbdc34b14f745deddc6d88d42e7bf6ec27786f1
+oid sha256:963f39caf4c63231881e4b63523711f96269baa7877166f7a1a75339fa23da16
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e6aa13c06d84c4ad45051878e0448e6be449071c382fb17e0415f1b8ed14a129
+oid sha256:441837bb114899f00b431121055c50d707051b5e0733913da44d787fb9655f84
 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": 0.8621111512184143,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.05032079506856208,
+  "best_metric": 0.8354976773262024,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.10064159013712416,
   "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": 38.851,
       "eval_steps_per_second": 4.864,
       "step": 25
+    },
+    {
+      "epoch": 0.052333626871304564,
+      "grad_norm": 0.06657703965902328,
+      "learning_rate": 5e-05,
+      "loss": 0.5698,
+      "step": 26
+    },
+    {
+      "epoch": 0.05434645867404705,
+      "grad_norm": 0.0643615648150444,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.6294,
+      "step": 27
+    },
+    {
+      "epoch": 0.05635929047678953,
+      "grad_norm": 0.0836610421538353,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.7834,
+      "step": 28
+    },
+    {
+      "epoch": 0.058372122279532014,
+      "grad_norm": 0.08429832756519318,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.7824,
+      "step": 29
+    },
+    {
+      "epoch": 0.0603849540822745,
+      "grad_norm": 0.10203393548727036,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.8395,
+      "step": 30
+    },
+    {
+      "epoch": 0.06239778588501698,
+      "grad_norm": 0.12489169836044312,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.8605,
+      "step": 31
+    },
+    {
+      "epoch": 0.06441061768775946,
+      "grad_norm": 0.12347022444009781,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.8481,
+      "step": 32
+    },
+    {
+      "epoch": 0.06642344949050195,
+      "grad_norm": 0.13445475697517395,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.8294,
+      "step": 33
+    },
+    {
+      "epoch": 0.06843628129324443,
+      "grad_norm": 0.17572376132011414,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.9531,
+      "step": 34
+    },
+    {
+      "epoch": 0.07044911309598692,
+      "grad_norm": 0.18911412358283997,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.8658,
+      "step": 35
+    },
+    {
+      "epoch": 0.0724619448987294,
+      "grad_norm": 0.2541409432888031,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.9589,
+      "step": 36
+    },
+    {
+      "epoch": 0.07447477670147189,
+      "grad_norm": 0.2794831693172455,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 1.0321,
+      "step": 37
+    },
+    {
+      "epoch": 0.07648760850421436,
+      "grad_norm": 0.09590571373701096,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.5546,
+      "step": 38
+    },
+    {
+      "epoch": 0.07850044030695685,
+      "grad_norm": 0.06773649901151657,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.5526,
+      "step": 39
+    },
+    {
+      "epoch": 0.08051327210969933,
+      "grad_norm": 0.07989200949668884,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.752,
+      "step": 40
+    },
+    {
+      "epoch": 0.08252610391244182,
+      "grad_norm": 0.07869336754083633,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.7482,
+      "step": 41
+    },
+    {
+      "epoch": 0.0845389357151843,
+      "grad_norm": 0.08748956769704819,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.776,
+      "step": 42
+    },
+    {
+      "epoch": 0.08655176751792679,
+      "grad_norm": 0.09485366940498352,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.8254,
+      "step": 43
+    },
+    {
+      "epoch": 0.08856459932066926,
+      "grad_norm": 0.09823082387447357,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.8495,
+      "step": 44
+    },
+    {
+      "epoch": 0.09057743112341175,
+      "grad_norm": 0.10822151601314545,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.8291,
+      "step": 45
+    },
+    {
+      "epoch": 0.09259026292615423,
+      "grad_norm": 0.12954840064048767,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.8466,
+      "step": 46
+    },
+    {
+      "epoch": 0.09460309472889672,
+      "grad_norm": 0.15098819136619568,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.8472,
+      "step": 47
+    },
+    {
+      "epoch": 0.0966159265316392,
+      "grad_norm": 0.1865275502204895,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.9185,
+      "step": 48
+    },
+    {
+      "epoch": 0.09862875833438169,
+      "grad_norm": 0.2584550976753235,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 1.01,
+      "step": 49
+    },
+    {
+      "epoch": 0.10064159013712416,
+      "grad_norm": 0.40982845425605774,
+      "learning_rate": 0.0,
+      "loss": 1.0724,
+      "step": 50
+    },
+    {
+      "epoch": 0.10064159013712416,
+      "eval_loss": 0.8354976773262024,
+      "eval_runtime": 85.6715,
+      "eval_samples_per_second": 39.068,
+      "eval_steps_per_second": 4.891,
+      "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": 2.644369531165737e+17,
+  "total_flos": 5.2936695344634266e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null