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:d83ed40e288eec88872aea64d21ea289669fe671de1017247b3783fc1fd51e3e
+oid sha256:4d5571305662da1fd4b46d80ca897060b2452c19cba6f061152b015a2dc230b8
 size 194563400

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:affb55df2440f11b8b2c85e94365d05121a205c17a34b5a140ff9eb29d8aa726
+oid sha256:8eea160aea117c1b08ac12b9b27ae950ecb14ff69cc7f8cf5c871a92e460d865
 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": 3.5544095039367676,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.43383947939262474,
+  "best_metric": 3.48060941696167,
+  "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": 55.535,
       "eval_steps_per_second": 6.995,
       "step": 25
+    },
+    {
+      "epoch": 0.4511930585683297,
+      "grad_norm": 0.786327064037323,
+      "learning_rate": 5e-05,
+      "loss": 3.2751,
+      "step": 26
+    },
+    {
+      "epoch": 0.4685466377440347,
+      "grad_norm": 1.0305312871932983,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 3.4125,
+      "step": 27
+    },
+    {
+      "epoch": 0.48590021691973967,
+      "grad_norm": 1.1478524208068848,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 3.5463,
+      "step": 28
+    },
+    {
+      "epoch": 0.5032537960954447,
+      "grad_norm": 1.2337690591812134,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 3.5402,
+      "step": 29
+    },
+    {
+      "epoch": 0.5206073752711496,
+      "grad_norm": 1.154429316520691,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 3.5452,
+      "step": 30
+    },
+    {
+      "epoch": 0.5379609544468547,
+      "grad_norm": 0.9768087863922119,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 3.5021,
+      "step": 31
+    },
+    {
+      "epoch": 0.5553145336225597,
+      "grad_norm": 0.9559707641601562,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 3.5008,
+      "step": 32
+    },
+    {
+      "epoch": 0.5726681127982647,
+      "grad_norm": 0.9601343870162964,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 3.5435,
+      "step": 33
+    },
+    {
+      "epoch": 0.5900216919739696,
+      "grad_norm": 1.1038984060287476,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 3.5946,
+      "step": 34
+    },
+    {
+      "epoch": 0.6073752711496746,
+      "grad_norm": 1.253346562385559,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 3.5455,
+      "step": 35
+    },
+    {
+      "epoch": 0.6247288503253796,
+      "grad_norm": 1.8003921508789062,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 3.7233,
+      "step": 36
+    },
+    {
+      "epoch": 0.6420824295010846,
+      "grad_norm": 2.6431398391723633,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 3.5173,
+      "step": 37
+    },
+    {
+      "epoch": 0.6594360086767896,
+      "grad_norm": 0.43522414565086365,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 3.2058,
+      "step": 38
+    },
+    {
+      "epoch": 0.6767895878524945,
+      "grad_norm": 0.4335356652736664,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 3.3444,
+      "step": 39
+    },
+    {
+      "epoch": 0.6941431670281996,
+      "grad_norm": 0.45088207721710205,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 3.3811,
+      "step": 40
+    },
+    {
+      "epoch": 0.7114967462039046,
+      "grad_norm": 0.5164139866828918,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 3.3587,
+      "step": 41
+    },
+    {
+      "epoch": 0.7288503253796096,
+      "grad_norm": 0.5385364294052124,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 3.4513,
+      "step": 42
+    },
+    {
+      "epoch": 0.7462039045553145,
+      "grad_norm": 0.6080254316329956,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 3.4158,
+      "step": 43
+    },
+    {
+      "epoch": 0.7635574837310195,
+      "grad_norm": 0.711311936378479,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 3.4986,
+      "step": 44
+    },
+    {
+      "epoch": 0.7809110629067245,
+      "grad_norm": 0.8071969747543335,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 3.45,
+      "step": 45
+    },
+    {
+      "epoch": 0.7982646420824295,
+      "grad_norm": 1.0393857955932617,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 3.4904,
+      "step": 46
+    },
+    {
+      "epoch": 0.8156182212581344,
+      "grad_norm": 1.210397720336914,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 3.5673,
+      "step": 47
+    },
+    {
+      "epoch": 0.8329718004338394,
+      "grad_norm": 1.5411838293075562,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 3.4864,
+      "step": 48
+    },
+    {
+      "epoch": 0.8503253796095445,
+      "grad_norm": 2.104750394821167,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 3.6277,
+      "step": 49
+    },
+    {
+      "epoch": 0.8676789587852495,
+      "grad_norm": 3.844982385635376,
+      "learning_rate": 0.0,
+      "loss": 3.8283,
+      "step": 50
+    },
+    {
+      "epoch": 0.8676789587852495,
+      "eval_loss": 3.48060941696167,
+      "eval_runtime": 6.9978,
+      "eval_samples_per_second": 55.589,
+      "eval_steps_per_second": 7.002,
+      "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