Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9eff44801656c706e6a8b47a485b8deb43ee0fd459f207f2f4cfeb83d3322654
+oid sha256:01a9a921cad4502d06f6e7b8278ee26a21ceb5defefffac9e779e8294754e8eb
 size 194563400

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f311e26d0b0e682ac56487fe81239553dd50065e4f1f394c4cdcefa9899ca1f
+oid sha256:595badea7694145a77be46ea0571310e5ed9acd94e49fbcf6dd1dda1b9f189ae
 size 389352298

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a5fd257b0e8c0422f66a966e815708811c38b5601dc09cdb9fac52c7e3a78f99
+oid sha256:8bcea6f28ac586cdb9f8729164a430c225feb7dec3b436eb745b9a28dc2c2732
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8e472f7fecb94c9d3a45d6e5223f46ac5ffafc4b2c9a3bf287072a661cc6411
+oid sha256:ee9313b8e8e5b7f88a3888dbd52c3c45bde861cc2dbc71cc2d3b9e98594e8dfc
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:55060121c987036281d43732f67b40f5e62acf27c4c864f6a25dcdb4c4e80a42
+oid sha256:3a3b06310e5fbcc92024bafb1e55fcfa7368f6acbe11b5ef33cb26647e68181a
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ec7bba3dc29e607f5cefda25a6c676a6be740a29ec1db6ddd37f7b6576df36e
+oid sha256:c437ba354ecbda29549594eeb921be6f1eaed75453671c6ae3f363a8e92572c3
 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": 1.7160019874572754,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.321285140562249,
+  "best_metric": 1.689772367477417,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.642570281124498,
   "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": 50.785,
       "eval_steps_per_second": 6.384,
       "step": 25
+    },
+    {
+      "epoch": 0.334136546184739,
+      "grad_norm": 0.1902642697095871,
+      "learning_rate": 5e-05,
+      "loss": 0.65,
+      "step": 26
+    },
+    {
+      "epoch": 0.3469879518072289,
+      "grad_norm": 0.16424991190433502,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.7561,
+      "step": 27
+    },
+    {
+      "epoch": 0.3598393574297189,
+      "grad_norm": 0.2629182040691376,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 1.4481,
+      "step": 28
+    },
+    {
+      "epoch": 0.37269076305220883,
+      "grad_norm": 0.2820444405078888,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 1.7517,
+      "step": 29
+    },
+    {
+      "epoch": 0.3855421686746988,
+      "grad_norm": 0.28889456391334534,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 1.9896,
+      "step": 30
+    },
+    {
+      "epoch": 0.39839357429718875,
+      "grad_norm": 0.28293195366859436,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 2.1379,
+      "step": 31
+    },
+    {
+      "epoch": 0.41124497991967873,
+      "grad_norm": 0.2696903645992279,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 2.1418,
+      "step": 32
+    },
+    {
+      "epoch": 0.42409638554216866,
+      "grad_norm": 0.26562952995300293,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 2.0818,
+      "step": 33
+    },
+    {
+      "epoch": 0.43694779116465865,
+      "grad_norm": 0.2775939106941223,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 2.3808,
+      "step": 34
+    },
+    {
+      "epoch": 0.4497991967871486,
+      "grad_norm": 0.2679601013660431,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 2.096,
+      "step": 35
+    },
+    {
+      "epoch": 0.46265060240963857,
+      "grad_norm": 0.2895340323448181,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 2.0492,
+      "step": 36
+    },
+    {
+      "epoch": 0.4755020080321285,
+      "grad_norm": 0.3093947768211365,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 1.7036,
+      "step": 37
+    },
+    {
+      "epoch": 0.4883534136546185,
+      "grad_norm": 0.16105574369430542,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.7348,
+      "step": 38
+    },
+    {
+      "epoch": 0.5012048192771085,
+      "grad_norm": 0.13976486027240753,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.7403,
+      "step": 39
+    },
+    {
+      "epoch": 0.5140562248995983,
+      "grad_norm": 0.18453320860862732,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 1.1308,
+      "step": 40
+    },
+    {
+      "epoch": 0.5269076305220883,
+      "grad_norm": 0.23279649019241333,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 1.7185,
+      "step": 41
+    },
+    {
+      "epoch": 0.5397590361445783,
+      "grad_norm": 0.24272245168685913,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 1.9925,
+      "step": 42
+    },
+    {
+      "epoch": 0.5526104417670683,
+      "grad_norm": 0.25685063004493713,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 2.2126,
+      "step": 43
+    },
+    {
+      "epoch": 0.5654618473895582,
+      "grad_norm": 0.2558934986591339,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 2.1499,
+      "step": 44
+    },
+    {
+      "epoch": 0.5783132530120482,
+      "grad_norm": 0.25836342573165894,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 2.2424,
+      "step": 45
+    },
+    {
+      "epoch": 0.5911646586345382,
+      "grad_norm": 0.26719456911087036,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 2.1548,
+      "step": 46
+    },
+    {
+      "epoch": 0.6040160642570281,
+      "grad_norm": 0.2668452262878418,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 2.1691,
+      "step": 47
+    },
+    {
+      "epoch": 0.6168674698795181,
+      "grad_norm": 0.2741744816303253,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 1.921,
+      "step": 48
+    },
+    {
+      "epoch": 0.629718875502008,
+      "grad_norm": 0.2753572463989258,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 1.6133,
+      "step": 49
+    },
+    {
+      "epoch": 0.642570281124498,
+      "grad_norm": 0.4149574339389801,
+      "learning_rate": 0.0,
+      "loss": 1.5978,
+      "step": 50
+    },
+    {
+      "epoch": 0.642570281124498,
+      "eval_loss": 1.689772367477417,
+      "eval_runtime": 10.5107,
+      "eval_samples_per_second": 49.949,
+      "eval_steps_per_second": 6.279,
+      "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": 1.145114919436288e+17,
+  "total_flos": 2.2860017227425382e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null