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:ebbed7984bd4fe20262c73d58ca91925c9a5d3b79a053b302c1abb2e2399a0e1
+oid sha256:72e82195428826f8dfddb145878fe9fc701e6402fe62fdd959f4b7d19cdc37be
 size 194563400

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e481b668d056bd35d533859ed971a1128f17774f710cb2441224bfa924462e69
+oid sha256:b270b5372ff167fa4291be0172d31fcf9907fcf5cb158cc1712aa8b66f2197bd
 size 389352298

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3554b784b0f640a87ce6b4b0489d8f7048803a3aef40fdc2d03770b3cd5e5557
+oid sha256:3514869e5f0d8807d36de329f98deced0b339c3d24252dd2a6d7661ad07a73e9
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:57ff1eb22f8d7bf74711a1364a7bc4caf76e386bc90d62e523e0720fa4a6416b
+oid sha256:ab56ca4a57b925e8d8719c9b29e0efb52730b91a3d23046024fcbf118df498e9
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:accffa0f8f63b21b285bfc51781c17cdb569347b7bdb7c1a1b87153b49f8803d
+oid sha256:5124488ca506a6e3073d48d706f9aacfa2f29dafe54b118d10afd931ce9bd876
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0577ef2fceedf0914b833d7d87de74352458c92ff5b91de50cc64a4c1e528b53
+oid sha256:4d17c8f00cc3e603178a6014914a33539fcd9ad0385ba5ba79bc9e6e5034944d
 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": 3.54858136177063,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.43383947939262474,
+  "best_metric": 3.4749794006347656,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.8676789587852495,
   "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": 55.084,
       "eval_steps_per_second": 6.939,
       "step": 25
+    },
+    {
+      "epoch": 0.4511930585683297,
+      "grad_norm": 0.7839721441268921,
+      "learning_rate": 5e-05,
+      "loss": 3.274,
+      "step": 26
+    },
+    {
+      "epoch": 0.4685466377440347,
+      "grad_norm": 1.0139122009277344,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 3.4114,
+      "step": 27
+    },
+    {
+      "epoch": 0.48590021691973967,
+      "grad_norm": 1.1178371906280518,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 3.5445,
+      "step": 28
+    },
+    {
+      "epoch": 0.5032537960954447,
+      "grad_norm": 1.1927067041397095,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 3.5377,
+      "step": 29
+    },
+    {
+      "epoch": 0.5206073752711496,
+      "grad_norm": 1.1140047311782837,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 3.5414,
+      "step": 30
+    },
+    {
+      "epoch": 0.5379609544468547,
+      "grad_norm": 0.9414491653442383,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 3.4979,
+      "step": 31
+    },
+    {
+      "epoch": 0.5553145336225597,
+      "grad_norm": 0.9263672232627869,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 3.4948,
+      "step": 32
+    },
+    {
+      "epoch": 0.5726681127982647,
+      "grad_norm": 0.94609534740448,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 3.5357,
+      "step": 33
+    },
+    {
+      "epoch": 0.5900216919739696,
+      "grad_norm": 1.0813770294189453,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 3.5867,
+      "step": 34
+    },
+    {
+      "epoch": 0.6073752711496746,
+      "grad_norm": 1.2149401903152466,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 3.5374,
+      "step": 35
+    },
+    {
+      "epoch": 0.6247288503253796,
+      "grad_norm": 1.7587355375289917,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 3.7121,
+      "step": 36
+    },
+    {
+      "epoch": 0.6420824295010846,
+      "grad_norm": 2.5012454986572266,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 3.5036,
+      "step": 37
+    },
+    {
+      "epoch": 0.6594360086767896,
+      "grad_norm": 0.4415558874607086,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 3.2048,
+      "step": 38
+    },
+    {
+      "epoch": 0.6767895878524945,
+      "grad_norm": 0.4357939064502716,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 3.3426,
+      "step": 39
+    },
+    {
+      "epoch": 0.6941431670281996,
+      "grad_norm": 0.4549647867679596,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 3.3791,
+      "step": 40
+    },
+    {
+      "epoch": 0.7114967462039046,
+      "grad_norm": 0.5158963203430176,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 3.356,
+      "step": 41
+    },
+    {
+      "epoch": 0.7288503253796096,
+      "grad_norm": 0.5373722910881042,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 3.4483,
+      "step": 42
+    },
+    {
+      "epoch": 0.7462039045553145,
+      "grad_norm": 0.6123077273368835,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 3.411,
+      "step": 43
+    },
+    {
+      "epoch": 0.7635574837310195,
+      "grad_norm": 0.7094330191612244,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 3.4948,
+      "step": 44
+    },
+    {
+      "epoch": 0.7809110629067245,
+      "grad_norm": 0.7887084484100342,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 3.4448,
+      "step": 45
+    },
+    {
+      "epoch": 0.7982646420824295,
+      "grad_norm": 1.0100810527801514,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 3.4833,
+      "step": 46
+    },
+    {
+      "epoch": 0.8156182212581344,
+      "grad_norm": 1.1634279489517212,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 3.5579,
+      "step": 47
+    },
+    {
+      "epoch": 0.8329718004338394,
+      "grad_norm": 1.4692707061767578,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 3.4763,
+      "step": 48
+    },
+    {
+      "epoch": 0.8503253796095445,
+      "grad_norm": 2.0087335109710693,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 3.6189,
+      "step": 49
+    },
+    {
+      "epoch": 0.8676789587852495,
+      "grad_norm": 3.6939210891723633,
+      "learning_rate": 0.0,
+      "loss": 3.8107,
+      "step": 50
+    },
+    {
+      "epoch": 0.8676789587852495,
+      "eval_loss": 3.4749794006347656,
+      "eval_runtime": 7.061,
+      "eval_samples_per_second": 55.091,
+      "eval_steps_per_second": 6.94,
+      "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": 1.127497768894464e+17,
+  "total_flos": 2.254995537788928e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null