Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:09f4fec896d17cfdc425e4bdb94a2946e6622e087c19382f096953f8e0548039
+oid sha256:0d4926afff5f163b6bdabfd1679e983f85bb1b2d5ef09005d44fde1457294c2a
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b85fdc431e8aab3c4d0d2893f268c456042f4bf0bf9299ebc9780f347679d52
+oid sha256:825087d3be598deda5e97fde6ed02db81fda6381f9423fc0a13d4bc218db5258
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:34137122fd1ea3534996b9e7c98db336eedde5c7814979653b3172bdcd23ade6
+oid sha256:e39aea1f09020e623ba72560ea4a5d189bd5f14d70cf74abc5a68747301a9f5c
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:63dec7c2bab5ae6b6ab076673ac524f3221b82e3a001878f9899b4efc46a32dd
+oid sha256:19f7c6d539a13c765335b130cccc20a10f2be4e44313b52c2a3e3bbf93828711
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:af968884a8aff9c98fd898c3bcbb5e1cb4da16587e37438e5b87813f67eec809
+oid sha256:354b6429fa052d83f954b0e233218c3b28ea092f9565ef2f15be2944f8f60442
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a134345d3c0b799277bd6729ed8c1108e5e11a02689cbf947f4e6e1223f5000
+oid sha256:f18e449529cecbde1773be5e716480615b0781e8781d3aff892a8973aad5a7a4
 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": 1.121332049369812,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.028328611898016998,
+  "best_metric": 1.108001947402954,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.056657223796033995,
   "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": 32.972,
       "eval_steps_per_second": 4.126,
       "step": 25
+    },
+    {
+      "epoch": 0.029461756373937678,
+      "grad_norm": 0.37851259112358093,
+      "learning_rate": 5e-05,
+      "loss": 1.1602,
+      "step": 26
+    },
+    {
+      "epoch": 0.03059490084985836,
+      "grad_norm": 0.3290565311908722,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 1.1472,
+      "step": 27
+    },
+    {
+      "epoch": 0.03172804532577904,
+      "grad_norm": 0.2516811490058899,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 1.1543,
+      "step": 28
+    },
+    {
+      "epoch": 0.03286118980169972,
+      "grad_norm": 0.3208964467048645,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 1.135,
+      "step": 29
+    },
+    {
+      "epoch": 0.0339943342776204,
+      "grad_norm": 0.26425492763519287,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 1.151,
+      "step": 30
+    },
+    {
+      "epoch": 0.03512747875354107,
+      "grad_norm": 0.34969091415405273,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 1.1472,
+      "step": 31
+    },
+    {
+      "epoch": 0.036260623229461754,
+      "grad_norm": 0.2773855924606323,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 1.1479,
+      "step": 32
+    },
+    {
+      "epoch": 0.037393767705382434,
+      "grad_norm": 0.30572637915611267,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 1.119,
+      "step": 33
+    },
+    {
+      "epoch": 0.038526912181303115,
+      "grad_norm": 0.39220941066741943,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 1.1109,
+      "step": 34
+    },
+    {
+      "epoch": 0.039660056657223795,
+      "grad_norm": 0.300199419260025,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 1.0948,
+      "step": 35
+    },
+    {
+      "epoch": 0.040793201133144476,
+      "grad_norm": 0.25450271368026733,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 1.0864,
+      "step": 36
+    },
+    {
+      "epoch": 0.041926345609065156,
+      "grad_norm": 0.5626171827316284,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 1.0807,
+      "step": 37
+    },
+    {
+      "epoch": 0.04305949008498584,
+      "grad_norm": 0.2916627526283264,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.0341,
+      "step": 38
+    },
+    {
+      "epoch": 0.04419263456090652,
+      "grad_norm": 0.47983884811401367,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 1.1236,
+      "step": 39
+    },
+    {
+      "epoch": 0.0453257790368272,
+      "grad_norm": 0.7446145415306091,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 1.1391,
+      "step": 40
+    },
+    {
+      "epoch": 0.04645892351274788,
+      "grad_norm": 0.5644591450691223,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 1.1314,
+      "step": 41
+    },
+    {
+      "epoch": 0.04759206798866856,
+      "grad_norm": 0.4467518627643585,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 1.1334,
+      "step": 42
+    },
+    {
+      "epoch": 0.04872521246458923,
+      "grad_norm": 0.28938040137290955,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 1.0917,
+      "step": 43
+    },
+    {
+      "epoch": 0.04985835694050991,
+      "grad_norm": 0.2925053536891937,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.136,
+      "step": 44
+    },
+    {
+      "epoch": 0.05099150141643059,
+      "grad_norm": 0.2758999168872833,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 1.1402,
+      "step": 45
+    },
+    {
+      "epoch": 0.05212464589235127,
+      "grad_norm": 0.2369970977306366,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 1.1282,
+      "step": 46
+    },
+    {
+      "epoch": 0.053257790368271954,
+      "grad_norm": 0.2726738154888153,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 1.0924,
+      "step": 47
+    },
+    {
+      "epoch": 0.054390934844192634,
+      "grad_norm": 0.27999621629714966,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 1.1117,
+      "step": 48
+    },
+    {
+      "epoch": 0.055524079320113315,
+      "grad_norm": 0.34448206424713135,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 1.0974,
+      "step": 49
+    },
+    {
+      "epoch": 0.056657223796033995,
+      "grad_norm": 0.31993088126182556,
+      "learning_rate": 0.0,
+      "loss": 0.9778,
+      "step": 50
+    },
+    {
+      "epoch": 0.056657223796033995,
+      "eval_loss": 1.108001947402954,
+      "eval_runtime": 180.4135,
+      "eval_samples_per_second": 32.952,
+      "eval_steps_per_second": 4.124,
+      "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