Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:17c144e036341601cf2e9f9e16c4ad074f12e8ce2701cbddf940ec236f128187
+oid sha256:6cbdac7249786df3a9e4b5642e5f484c8abfccaf708491dc78334a9b5e837fb0
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a4189e8802c7201f46937b25d5f0487fb45b27484540bc4942f42e09a4f359b
+oid sha256:c1f2e31f3a321585a1bd3d91d35694ee9fd9492d56526ad566102dded83b490b
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a93d74c372bd885a79678fdab7e8bbb07971144f09798f0327edc9454ae0c22d
+oid sha256:c48ee7c55a44a8151bc24827df3b8fa214c5f234eb197343a47e5948fc81124b
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a94eaeb6423e3afa11fa811a01d764801cfe5bc5bac25c2337e81dbee0113bfd
+oid sha256:9e1579163e59ecb21ce53b10e906c18a45872ce26c44204a850ab8cbb975d27b
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:877f021d8f812c5bc14944a7d1a715996ad7357b3bb323b33bdc945f986a5a39
+oid sha256:f6165104040b78e194dbedbaa9312de2648794e337279a433550250f3ccbf5b4
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b1a99429ac363b443ca5c4fa8ac57d9f213987e6ef0cb4a607e0cc7dddac679
+oid sha256:22a51fd313517de614d16243bc1699eb935a2807fa0bd4bfeaa9d187eea793a0
 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": 0.6356422305107117,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.00819252432155658,
+  "best_metric": 0.5565019249916077,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.01638504864311316,
   "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": 38.231,
       "eval_steps_per_second": 4.779,
       "step": 25
+    },
+    {
+      "epoch": 0.008520225294418843,
+      "grad_norm": 0.059100646525621414,
+      "learning_rate": 5e-05,
+      "loss": 0.0004,
+      "step": 26
+    },
+    {
+      "epoch": 0.008847926267281106,
+      "grad_norm": 0.9721323847770691,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.0607,
+      "step": 27
+    },
+    {
+      "epoch": 0.00917562724014337,
+      "grad_norm": 0.023191077634692192,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.0003,
+      "step": 28
+    },
+    {
+      "epoch": 0.009503328213005632,
+      "grad_norm": 0.12030933797359467,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.0012,
+      "step": 29
+    },
+    {
+      "epoch": 0.009831029185867896,
+      "grad_norm": 0.2080373764038086,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.0216,
+      "step": 30
+    },
+    {
+      "epoch": 0.010158730158730159,
+      "grad_norm": 0.3661039173603058,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.0039,
+      "step": 31
+    },
+    {
+      "epoch": 0.010486431131592422,
+      "grad_norm": 0.04480292275547981,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.0006,
+      "step": 32
+    },
+    {
+      "epoch": 0.010814132104454685,
+      "grad_norm": 0.01847970113158226,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.0003,
+      "step": 33
+    },
+    {
+      "epoch": 0.011141833077316948,
+      "grad_norm": 0.010702378116548061,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.0002,
+      "step": 34
+    },
+    {
+      "epoch": 0.011469534050179211,
+      "grad_norm": 0.011056789197027683,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.0002,
+      "step": 35
+    },
+    {
+      "epoch": 0.011797235023041475,
+      "grad_norm": 0.013891864567995071,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.0002,
+      "step": 36
+    },
+    {
+      "epoch": 0.012124935995903738,
+      "grad_norm": 15.3453369140625,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 3.996,
+      "step": 37
+    },
+    {
+      "epoch": 0.012452636968766001,
+      "grad_norm": 15.295425415039062,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 3.3321,
+      "step": 38
+    },
+    {
+      "epoch": 0.012780337941628264,
+      "grad_norm": 1.5840622186660767,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.0517,
+      "step": 39
+    },
+    {
+      "epoch": 0.013108038914490527,
+      "grad_norm": 1.8281114101409912,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.1035,
+      "step": 40
+    },
+    {
+      "epoch": 0.01343573988735279,
+      "grad_norm": 0.43321263790130615,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.0072,
+      "step": 41
+    },
+    {
+      "epoch": 0.013763440860215054,
+      "grad_norm": 0.007399904541671276,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.0001,
+      "step": 42
+    },
+    {
+      "epoch": 0.014091141833077317,
+      "grad_norm": 0.011308839544653893,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.0001,
+      "step": 43
+    },
+    {
+      "epoch": 0.01441884280593958,
+      "grad_norm": 0.010303402319550514,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.0001,
+      "step": 44
+    },
+    {
+      "epoch": 0.014746543778801843,
+      "grad_norm": 0.022859793156385422,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.0002,
+      "step": 45
+    },
+    {
+      "epoch": 0.015074244751664106,
+      "grad_norm": 0.00979696772992611,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.0001,
+      "step": 46
+    },
+    {
+      "epoch": 0.01540194572452637,
+      "grad_norm": 0.008724894374608994,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.0001,
+      "step": 47
+    },
+    {
+      "epoch": 0.015729646697388633,
+      "grad_norm": 0.00915119331330061,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.0001,
+      "step": 48
+    },
+    {
+      "epoch": 0.016057347670250896,
+      "grad_norm": 1.035159945487976,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.2291,
+      "step": 49
+    },
+    {
+      "epoch": 0.01638504864311316,
+      "grad_norm": 16.994882583618164,
+      "learning_rate": 0.0,
+      "loss": 6.3963,
+      "step": 50
+    },
+    {
+      "epoch": 0.01638504864311316,
+      "eval_loss": 0.5565019249916077,
+      "eval_runtime": 537.8031,
+      "eval_samples_per_second": 38.226,
+      "eval_steps_per_second": 4.779,
+      "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