Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4aaceb99e8c42f4e79d1235a825990545a3eac15c13f403172dff247fa1b2364
+oid sha256:779dd393f1490bf5c8d9883bf5a68e6be4288c1b41c9b46661a83ec0f3b70472
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:053f69385a482e907cd67ae95ac0fa928af3a015bcfc1107285d19c2ee192437
+oid sha256:064cfc10b3c59ec8a07b13b80ab1dd8093e309d5eba632d9ee073bac7ce483fa
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a92f5fa6aca7ee1b855bfff804515d79f9328697332f1d1d915c59fb734ab9f
+oid sha256:360e299e4d845804d725deb4b15ed2ac5535b98a7d1287d36afbb9f2a3a91e2f
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d6488d59156ac33e9c015f06430be8b6738c9a0aad83c8faf0e0d30e540dca6d
+oid sha256:835a3f1f938d1c699ac7a768552a026a8e8c901ecc7b88701db5417027db57c4
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:35de3370db958abd6b4fef8c17fdd5ba667fa9faaa627cefbe3a644f43b36113
+oid sha256:37f4755f38ba2c33aed2a2c65fcb5191540636508aaaaac2bfe306fde9820f2d
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d26165ad0d5b8343609c44d5af25dff3ad3a6f0b55ea156db8c6bc99eb1e72e
+oid sha256:b0d0f9c2df0facaa9168a0b8c962bf7732c1e3e0dedd02f352cc4ddd39475b9a
 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": 1.1405298709869385,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.2994011976047904,
+  "best_metric": 1.1089757680892944,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.5988023952095808,
   "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": 34.508,
       "eval_steps_per_second": 4.352,
       "step": 25
+    },
+    {
+      "epoch": 0.31137724550898205,
+      "grad_norm": 41.0149040222168,
+      "learning_rate": 5e-05,
+      "loss": 1.117,
+      "step": 26
+    },
+    {
+      "epoch": 0.32335329341317365,
+      "grad_norm": 39.559505462646484,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 1.156,
+      "step": 27
+    },
+    {
+      "epoch": 0.33532934131736525,
+      "grad_norm": 41.511619567871094,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 1.1566,
+      "step": 28
+    },
+    {
+      "epoch": 0.3473053892215569,
+      "grad_norm": 40.3213996887207,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 1.1188,
+      "step": 29
+    },
+    {
+      "epoch": 0.3592814371257485,
+      "grad_norm": 40.15166091918945,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 1.1944,
+      "step": 30
+    },
+    {
+      "epoch": 0.3712574850299401,
+      "grad_norm": 47.10627746582031,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 1.2953,
+      "step": 31
+    },
+    {
+      "epoch": 0.38323353293413176,
+      "grad_norm": 37.89162826538086,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 1.1692,
+      "step": 32
+    },
+    {
+      "epoch": 0.39520958083832336,
+      "grad_norm": 42.15617752075195,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 1.139,
+      "step": 33
+    },
+    {
+      "epoch": 0.40718562874251496,
+      "grad_norm": 41.0139045715332,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 1.1132,
+      "step": 34
+    },
+    {
+      "epoch": 0.41916167664670656,
+      "grad_norm": 38.4742317199707,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 1.146,
+      "step": 35
+    },
+    {
+      "epoch": 0.4311377245508982,
+      "grad_norm": 42.0889892578125,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 1.1295,
+      "step": 36
+    },
+    {
+      "epoch": 0.4431137724550898,
+      "grad_norm": 40.50762176513672,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 1.1804,
+      "step": 37
+    },
+    {
+      "epoch": 0.4550898203592814,
+      "grad_norm": 39.38518524169922,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.1693,
+      "step": 38
+    },
+    {
+      "epoch": 0.46706586826347307,
+      "grad_norm": 38.45338821411133,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 1.0601,
+      "step": 39
+    },
+    {
+      "epoch": 0.47904191616766467,
+      "grad_norm": 36.42400360107422,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 1.1918,
+      "step": 40
+    },
+    {
+      "epoch": 0.49101796407185627,
+      "grad_norm": 35.215782165527344,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 1.0414,
+      "step": 41
+    },
+    {
+      "epoch": 0.5029940119760479,
+      "grad_norm": 35.746368408203125,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 1.085,
+      "step": 42
+    },
+    {
+      "epoch": 0.5149700598802395,
+      "grad_norm": 32.94198226928711,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 1.0317,
+      "step": 43
+    },
+    {
+      "epoch": 0.5269461077844312,
+      "grad_norm": 35.12628936767578,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.0717,
+      "step": 44
+    },
+    {
+      "epoch": 0.5389221556886228,
+      "grad_norm": 38.822975158691406,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 1.2117,
+      "step": 45
+    },
+    {
+      "epoch": 0.5508982035928144,
+      "grad_norm": 37.651458740234375,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 1.1421,
+      "step": 46
+    },
+    {
+      "epoch": 0.562874251497006,
+      "grad_norm": 38.9232177734375,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 1.1223,
+      "step": 47
+    },
+    {
+      "epoch": 0.5748502994011976,
+      "grad_norm": 39.312294006347656,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 1.0714,
+      "step": 48
+    },
+    {
+      "epoch": 0.5868263473053892,
+      "grad_norm": 44.792057037353516,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 1.1816,
+      "step": 49
+    },
+    {
+      "epoch": 0.5988023952095808,
+      "grad_norm": 39.32863235473633,
+      "learning_rate": 0.0,
+      "loss": 1.0068,
+      "step": 50
+    },
+    {
+      "epoch": 0.5988023952095808,
+      "eval_loss": 1.1089757680892944,
+      "eval_runtime": 16.3009,
+      "eval_samples_per_second": 34.538,
+      "eval_steps_per_second": 4.356,
+      "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": 2.830247619723264e+17,
+  "total_flos": 5.660495239446528e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null