Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:51318b239645b42fd5e98bbd36e1a4046e2e03b4b00a4a65697ecbdf5b39b8c8
+oid sha256:29c057b866296bb31f481b88bc062fe8c652ccad37356398728f718cce2b3aff
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:063d463c2b221bc7ef74b45bd5d39954e76b6fc458338f3cd947b8d28d603bed
+oid sha256:ec18a0086f24a4656ca20d5b8c3ba5fa7159fc883352cf58eb21dcf5ea328995
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c45901587523d23a0dfa4822f818bd93fcf182edb53eeb048ce27296cfb5e1b7
+oid sha256:db22975a4e9204f2f7dcc2372ea0f64f33f80db1bf33993cae47d4087ef8d02d
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6ccbc8e24e7d261fca5f8a3e6e9bd2cf94b9555f5dc99d0818d702f3fc5cd491
+oid sha256:5f3006d9fe932aa119d5c45c3bc11e8730591e50821c30f94fe76637f6b664c1
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a14bbb3bbe07ae0e613db76e191b03d8dbbd95fd7374288adee9fbc7797fea92
+oid sha256:2c6830603ecce9e2e936e2e8e39e4b35ca68e791c293134ae9001ac62ea801a0
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f943eb69fd83001e160cf26d242ce8a33f4f68c1ecfb697efcbc6b58f6c443b
+oid sha256:abbb65a878b71f2f7cb0e1c2b22f7156245fe6470c3ae1f7e32fd4d1b1b70e5b
 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": 1.7906460762023926,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.06557377049180328,
+  "best_metric": 1.7657822370529175,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.13114754098360656,
   "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": 32.893,
       "eval_steps_per_second": 4.123,
       "step": 25
+    },
+    {
+      "epoch": 0.06819672131147542,
+      "grad_norm": 0.4008367359638214,
+      "learning_rate": 5e-05,
+      "loss": 1.6841,
+      "step": 26
+    },
+    {
+      "epoch": 0.07081967213114754,
+      "grad_norm": 0.47332674264907837,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 1.6645,
+      "step": 27
+    },
+    {
+      "epoch": 0.07344262295081967,
+      "grad_norm": 0.5273999571800232,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 1.7063,
+      "step": 28
+    },
+    {
+      "epoch": 0.0760655737704918,
+      "grad_norm": 0.5393008589744568,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 1.6794,
+      "step": 29
+    },
+    {
+      "epoch": 0.07868852459016394,
+      "grad_norm": 0.5354189276695251,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 1.7778,
+      "step": 30
+    },
+    {
+      "epoch": 0.08131147540983606,
+      "grad_norm": 0.5957549810409546,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 1.6612,
+      "step": 31
+    },
+    {
+      "epoch": 0.0839344262295082,
+      "grad_norm": 0.675876796245575,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 1.7237,
+      "step": 32
+    },
+    {
+      "epoch": 0.08655737704918033,
+      "grad_norm": 0.8892999887466431,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 1.7072,
+      "step": 33
+    },
+    {
+      "epoch": 0.08918032786885247,
+      "grad_norm": 1.113625407218933,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 1.9251,
+      "step": 34
+    },
+    {
+      "epoch": 0.09180327868852459,
+      "grad_norm": 1.1677485704421997,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 1.7266,
+      "step": 35
+    },
+    {
+      "epoch": 0.09442622950819672,
+      "grad_norm": 1.2980530261993408,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 1.79,
+      "step": 36
+    },
+    {
+      "epoch": 0.09704918032786886,
+      "grad_norm": 2.261312484741211,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 2.1639,
+      "step": 37
+    },
+    {
+      "epoch": 0.09967213114754099,
+      "grad_norm": 0.3986207842826843,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.658,
+      "step": 38
+    },
+    {
+      "epoch": 0.10229508196721311,
+      "grad_norm": 0.3504493534564972,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 1.6005,
+      "step": 39
+    },
+    {
+      "epoch": 0.10491803278688525,
+      "grad_norm": 0.38177090883255005,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 1.6638,
+      "step": 40
+    },
+    {
+      "epoch": 0.10754098360655738,
+      "grad_norm": 0.4022206664085388,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 1.6546,
+      "step": 41
+    },
+    {
+      "epoch": 0.11016393442622952,
+      "grad_norm": 0.4212299883365631,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 1.6158,
+      "step": 42
+    },
+    {
+      "epoch": 0.11278688524590164,
+      "grad_norm": 0.4646033048629761,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 1.6439,
+      "step": 43
+    },
+    {
+      "epoch": 0.11540983606557377,
+      "grad_norm": 0.5602381229400635,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.7379,
+      "step": 44
+    },
+    {
+      "epoch": 0.1180327868852459,
+      "grad_norm": 0.716867983341217,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 1.7136,
+      "step": 45
+    },
+    {
+      "epoch": 0.12065573770491804,
+      "grad_norm": 0.814602792263031,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 1.6061,
+      "step": 46
+    },
+    {
+      "epoch": 0.12327868852459016,
+      "grad_norm": 0.9936143159866333,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 1.7135,
+      "step": 47
+    },
+    {
+      "epoch": 0.1259016393442623,
+      "grad_norm": 1.1382496356964111,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 1.8558,
+      "step": 48
+    },
+    {
+      "epoch": 0.12852459016393442,
+      "grad_norm": 1.3115148544311523,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 1.8683,
+      "step": 49
+    },
+    {
+      "epoch": 0.13114754098360656,
+      "grad_norm": 2.4471275806427,
+      "learning_rate": 0.0,
+      "loss": 2.2984,
+      "step": 50
+    },
+    {
+      "epoch": 0.13114754098360656,
+      "eval_loss": 1.7657822370529175,
+      "eval_runtime": 78.1055,
+      "eval_samples_per_second": 32.891,
+      "eval_steps_per_second": 4.123,
+      "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