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:b8fe666e3bc4476b11ee72def3a7922a399ab3d936963ce952ae4d5aa8c61d07
+oid sha256:aae1f772aaa546c9763c3beb6a9a28ad56bc26fd9dd6456bf1cac047750922a4
 size 156926880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ddcd0ae0db1c7a9b2d743fe712410f804e71f5de2837236a5a3534f89d3a6b2
+oid sha256:cead1b8cabc7e38bdb84692fb5323e8f49fe4c5fb8df06fa5b40046af2e4bbb7
 size 313998650

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab65a8236e0106102f6ab531b9cd1d4ee2d85128f254a6853a77a41771e44517
+oid sha256:f0d8ba5a9e78c0753c606011dec3f31c0e503c3794dd8d7c214a1a5c20e5e430
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce7144b5fe98fd026ba158494d14ddc959c9cff3a544e7ea585a6dd2876ce18a
+oid sha256:a2a983169eb30e523a8e526cceb0a1871445cfbbf7b67515c4fc5a7029ff0df8
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:74cf15380358e9fdfb0f1937df9e803b03ad877dd719067ccdf5aa9f4e113c4b
+oid sha256:c059f57f19b9d63d7e160e7020ed29538dca18c4107f8b33b61bff7ebd05ff97
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae44ee982a0ea2368ccb338184276354cf763a7c73ede9b9380a36a80a755b81
+oid sha256:7d6438cdbd738960a480370b00d8601974a6809eea2b7ab1b368c5904be3884e
 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": 0.9176837801933289,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.4489337822671156,
+  "best_metric": 0.8816373944282532,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.8978675645342312,
   "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": 34.332,
       "eval_steps_per_second": 4.303,
       "step": 25
+    },
+    {
+      "epoch": 0.4668911335578002,
+      "grad_norm": 0.6586840748786926,
+      "learning_rate": 5e-05,
+      "loss": 0.9306,
+      "step": 26
+    },
+    {
+      "epoch": 0.48484848484848486,
+      "grad_norm": 0.6180529594421387,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.9315,
+      "step": 27
+    },
+    {
+      "epoch": 0.5028058361391695,
+      "grad_norm": 0.43769389390945435,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.9108,
+      "step": 28
+    },
+    {
+      "epoch": 0.5207631874298541,
+      "grad_norm": 0.5514314770698547,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.9184,
+      "step": 29
+    },
+    {
+      "epoch": 0.5387205387205387,
+      "grad_norm": 0.3724231719970703,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.9071,
+      "step": 30
+    },
+    {
+      "epoch": 0.5566778900112234,
+      "grad_norm": 0.4815616309642792,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.9251,
+      "step": 31
+    },
+    {
+      "epoch": 0.574635241301908,
+      "grad_norm": 0.6298116445541382,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.9048,
+      "step": 32
+    },
+    {
+      "epoch": 0.5925925925925926,
+      "grad_norm": 0.43708935379981995,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.9012,
+      "step": 33
+    },
+    {
+      "epoch": 0.6105499438832772,
+      "grad_norm": 0.40635502338409424,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.9315,
+      "step": 34
+    },
+    {
+      "epoch": 0.6285072951739619,
+      "grad_norm": 0.3841124176979065,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.8967,
+      "step": 35
+    },
+    {
+      "epoch": 0.6464646464646465,
+      "grad_norm": 0.4346996247768402,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.878,
+      "step": 36
+    },
+    {
+      "epoch": 0.6644219977553311,
+      "grad_norm": 0.4562406539916992,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.8639,
+      "step": 37
+    },
+    {
+      "epoch": 0.6823793490460157,
+      "grad_norm": 0.436215877532959,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.8593,
+      "step": 38
+    },
+    {
+      "epoch": 0.7003367003367004,
+      "grad_norm": 0.4428524374961853,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.8816,
+      "step": 39
+    },
+    {
+      "epoch": 0.7182940516273849,
+      "grad_norm": 0.5406110882759094,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.8918,
+      "step": 40
+    },
+    {
+      "epoch": 0.7362514029180696,
+      "grad_norm": 0.44841742515563965,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.8867,
+      "step": 41
+    },
+    {
+      "epoch": 0.7542087542087542,
+      "grad_norm": 0.32828664779663086,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.9081,
+      "step": 42
+    },
+    {
+      "epoch": 0.7721661054994389,
+      "grad_norm": 0.600707471370697,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.8924,
+      "step": 43
+    },
+    {
+      "epoch": 0.7901234567901234,
+      "grad_norm": 0.35831689834594727,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.8868,
+      "step": 44
+    },
+    {
+      "epoch": 0.8080808080808081,
+      "grad_norm": 0.3134266138076782,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.8624,
+      "step": 45
+    },
+    {
+      "epoch": 0.8260381593714927,
+      "grad_norm": 0.3953910768032074,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.9129,
+      "step": 46
+    },
+    {
+      "epoch": 0.8439955106621774,
+      "grad_norm": 0.346354603767395,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.88,
+      "step": 47
+    },
+    {
+      "epoch": 0.8619528619528619,
+      "grad_norm": 0.3914426565170288,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.883,
+      "step": 48
+    },
+    {
+      "epoch": 0.8799102132435466,
+      "grad_norm": 0.3426049053668976,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.8724,
+      "step": 49
+    },
+    {
+      "epoch": 0.8978675645342312,
+      "grad_norm": 0.44009047746658325,
+      "learning_rate": 0.0,
+      "loss": 0.8439,
+      "step": 50
+    },
+    {
+      "epoch": 0.8978675645342312,
+      "eval_loss": 0.8816373944282532,
+      "eval_runtime": 10.9243,
+      "eval_samples_per_second": 34.327,
+      "eval_steps_per_second": 4.302,
+      "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": 7.94731890081792e+16,
+  "total_flos": 1.589463780163584e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null