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:b64a4c680872013e30a373ff9ff19bccfb40ae7fd5ebde8adf99d1f826b1b0e3
+oid sha256:d34b7dd074d7ecbd80213c37e3e200445dc2bf6ffd350c09c723e60cbc50b899
 size 60599872

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6be2b079e4f8bf6818e03b7a6629edba60d968709d9899b22932189d4bcbd64c
+oid sha256:c074573903eebb6ccff85203a2e0ee9e95779d7de9ecd2e17ac87ea2099cfb79
 size 121392706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f8d20540effcbe29a37ac986f210749062f820971496b1b60d8217c3cd151f29
+oid sha256:f38e3fe9987265f1e016eb8ebbb12a3546e50d8cb7f4b37065bba1b227aece03
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:332a230b4c2eaa5028b264e4ead0fee9f38b0ab46a5d1b2d0952a18f7c14b4ce
+oid sha256:2d9e48dcb3562ab4df0bf782546e235d81c04de3fce3ca738db19a6178709195
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d23a85090e47f0c86687c9f08eeffb5effafc0960875ba2595769aaef846c305
+oid sha256:5f2896215e652644ff4ddc382a3bedf25cc40c857dcd7eb1540371ea6a255dc9
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa6dce7bd6fa53d572b4760aa6cbfdb4d6cb1b1ceb02e915735097522eb13d26
+oid sha256:dbae3c8173181620843de876ffb26b4c6d94c00f8f22f7f05c18b32816878472
 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": 3.290347099304199,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.02979072019066061,
+  "best_metric": 3.1683356761932373,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.05958144038132122,
   "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": 68.384,
       "eval_steps_per_second": 8.551,
       "step": 25
+    },
+    {
+      "epoch": 0.030982348998287033,
+      "grad_norm": 1.1471669673919678,
+      "learning_rate": 5e-05,
+      "loss": 2.9983,
+      "step": 26
+    },
+    {
+      "epoch": 0.03217397780591346,
+      "grad_norm": 0.7571565508842468,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 3.0674,
+      "step": 27
+    },
+    {
+      "epoch": 0.033365606613539885,
+      "grad_norm": 0.7262929677963257,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 2.9491,
+      "step": 28
+    },
+    {
+      "epoch": 0.03455723542116631,
+      "grad_norm": 0.7116366028785706,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 2.967,
+      "step": 29
+    },
+    {
+      "epoch": 0.03574886422879273,
+      "grad_norm": 0.7353350520133972,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 3.0033,
+      "step": 30
+    },
+    {
+      "epoch": 0.03694049303641916,
+      "grad_norm": 0.754368245601654,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 2.9819,
+      "step": 31
+    },
+    {
+      "epoch": 0.03813212184404558,
+      "grad_norm": 0.7911145687103271,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 3.03,
+      "step": 32
+    },
+    {
+      "epoch": 0.039323750651672006,
+      "grad_norm": 0.962597131729126,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 3.022,
+      "step": 33
+    },
+    {
+      "epoch": 0.04051537945929843,
+      "grad_norm": 1.061014175415039,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 3.079,
+      "step": 34
+    },
+    {
+      "epoch": 0.041707008266924854,
+      "grad_norm": 1.3124785423278809,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 3.2342,
+      "step": 35
+    },
+    {
+      "epoch": 0.04289863707455128,
+      "grad_norm": 1.8970980644226074,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 3.5467,
+      "step": 36
+    },
+    {
+      "epoch": 0.0440902658821777,
+      "grad_norm": 2.5072548389434814,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 3.5404,
+      "step": 37
+    },
+    {
+      "epoch": 0.04528189468980413,
+      "grad_norm": 1.3016464710235596,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 3.235,
+      "step": 38
+    },
+    {
+      "epoch": 0.04647352349743055,
+      "grad_norm": 0.7815819382667542,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 2.9232,
+      "step": 39
+    },
+    {
+      "epoch": 0.047665152305056975,
+      "grad_norm": 0.7965614795684814,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 2.8481,
+      "step": 40
+    },
+    {
+      "epoch": 0.0488567811126834,
+      "grad_norm": 0.7972835898399353,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 3.0188,
+      "step": 41
+    },
+    {
+      "epoch": 0.05004840992030982,
+      "grad_norm": 0.8045832514762878,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 2.8789,
+      "step": 42
+    },
+    {
+      "epoch": 0.05124003872793625,
+      "grad_norm": 0.7895027995109558,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 3.074,
+      "step": 43
+    },
+    {
+      "epoch": 0.05243166753556267,
+      "grad_norm": 0.8068074584007263,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 2.9719,
+      "step": 44
+    },
+    {
+      "epoch": 0.053623296343189096,
+      "grad_norm": 0.8220405578613281,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 3.0224,
+      "step": 45
+    },
+    {
+      "epoch": 0.05481492515081552,
+      "grad_norm": 0.903792142868042,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 3.1393,
+      "step": 46
+    },
+    {
+      "epoch": 0.056006553958441944,
+      "grad_norm": 1.1391758918762207,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 3.3173,
+      "step": 47
+    },
+    {
+      "epoch": 0.05719818276606837,
+      "grad_norm": 1.2545311450958252,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 3.3547,
+      "step": 48
+    },
+    {
+      "epoch": 0.05838981157369479,
+      "grad_norm": 1.733869194984436,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 3.4317,
+      "step": 49
+    },
+    {
+      "epoch": 0.05958144038132122,
+      "grad_norm": 2.97579288482666,
+      "learning_rate": 0.0,
+      "loss": 3.7697,
+      "step": 50
+    },
+    {
+      "epoch": 0.05958144038132122,
+      "eval_loss": 3.1683356761932373,
+      "eval_runtime": 82.588,
+      "eval_samples_per_second": 68.46,
+      "eval_steps_per_second": 8.561,
+      "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": 1.27222702669824e+16,
+  "total_flos": 2.54445405339648e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null