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:e37651fcaf23f9c7f2f27954fc2a5c8de91f39dc9a8bd81d816dbefa96f4d64e
+oid sha256:db64ea2128b61bdde1ee45b36f8ac125ee0b4abb4a722453522c60cc971c4a77
 size 90207248

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:25348ee6ac49ae8340cc5802ac0f1331fdbfe18e2e37971467a2a2578121af80
+oid sha256:7afb168279cf3fec5496d9c0674670866a53d3c961717a0522ba8f156c22f2bf
 size 180543866

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7aa71463272730fe41624cdb310a7b836dd8aed0c658656ab0a6c87824081247
+oid sha256:f153a240eafa08b9b219e4f000d0e71b7dc419120a7adcc005f7e402b1622a5a
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9bed91762e7cea812063d7d32e15c74f33e55ebf3ae7fcc634ca806f47d7b906
+oid sha256:dc79bd94f9d0c23577cf54241e3163f74b08fa42e3040110bafad27c7979fc56
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a2432e0a12ea5366626f02419dee2145245e8eb6c5762a382147bf163c4eb8fa
+oid sha256:98340e4f5fa06ba3cc9970fbf11152db51aa582b5cd548137c2f2d0e8aa9905d
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43060ae52561cc6ec76fa7ef819555573c9400f1ac733021e831768d4c064b49
+oid sha256:fb7cedc2f33f0726081289dfe4a87cb8cd803d8f53cc1e360274f4131ae94b0b
 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": 0.27750980854034424,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.012952948414882938,
+  "best_metric": 0.21778494119644165,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.025905896829765875,
   "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": 51.439,
       "eval_steps_per_second": 6.432,
       "step": 25
+    },
+    {
+      "epoch": 0.013471066351478255,
+      "grad_norm": 5.945998191833496,
+      "learning_rate": 5e-05,
+      "loss": 0.3599,
+      "step": 26
+    },
+    {
+      "epoch": 0.013989184288073572,
+      "grad_norm": 5.562319755554199,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.3753,
+      "step": 27
+    },
+    {
+      "epoch": 0.01450730222466889,
+      "grad_norm": 6.375342845916748,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.3812,
+      "step": 28
+    },
+    {
+      "epoch": 0.015025420161264208,
+      "grad_norm": 4.818624019622803,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.3356,
+      "step": 29
+    },
+    {
+      "epoch": 0.015543538097859525,
+      "grad_norm": 3.2386670112609863,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.2768,
+      "step": 30
+    },
+    {
+      "epoch": 0.016061656034454842,
+      "grad_norm": 1.8856221437454224,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.2395,
+      "step": 31
+    },
+    {
+      "epoch": 0.01657977397105016,
+      "grad_norm": 1.1571811437606812,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.2164,
+      "step": 32
+    },
+    {
+      "epoch": 0.017097891907645477,
+      "grad_norm": 2.5876970291137695,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.2647,
+      "step": 33
+    },
+    {
+      "epoch": 0.017616009844240794,
+      "grad_norm": 2.0951273441314697,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.2326,
+      "step": 34
+    },
+    {
+      "epoch": 0.018134127780836114,
+      "grad_norm": 2.5257697105407715,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.2461,
+      "step": 35
+    },
+    {
+      "epoch": 0.01865224571743143,
+      "grad_norm": 2.7462198734283447,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.2181,
+      "step": 36
+    },
+    {
+      "epoch": 0.01917036365402675,
+      "grad_norm": 1.6443389654159546,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.1944,
+      "step": 37
+    },
+    {
+      "epoch": 0.019688481590622066,
+      "grad_norm": 0.9300404787063599,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.2297,
+      "step": 38
+    },
+    {
+      "epoch": 0.020206599527217383,
+      "grad_norm": 3.3914144039154053,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.2565,
+      "step": 39
+    },
+    {
+      "epoch": 0.0207247174638127,
+      "grad_norm": 2.4694724082946777,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.248,
+      "step": 40
+    },
+    {
+      "epoch": 0.021242835400408017,
+      "grad_norm": 2.6822378635406494,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.2499,
+      "step": 41
+    },
+    {
+      "epoch": 0.021760953337003335,
+      "grad_norm": 3.0302975177764893,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.2517,
+      "step": 42
+    },
+    {
+      "epoch": 0.02227907127359865,
+      "grad_norm": 2.641648054122925,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.2424,
+      "step": 43
+    },
+    {
+      "epoch": 0.02279718921019397,
+      "grad_norm": 1.5059698820114136,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.2396,
+      "step": 44
+    },
+    {
+      "epoch": 0.02331530714678929,
+      "grad_norm": 2.1479551792144775,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.2194,
+      "step": 45
+    },
+    {
+      "epoch": 0.023833425083384607,
+      "grad_norm": 1.320908546447754,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.2164,
+      "step": 46
+    },
+    {
+      "epoch": 0.024351543019979924,
+      "grad_norm": 2.0904932022094727,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.1895,
+      "step": 47
+    },
+    {
+      "epoch": 0.02486966095657524,
+      "grad_norm": 1.466928243637085,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.2183,
+      "step": 48
+    },
+    {
+      "epoch": 0.025387778893170558,
+      "grad_norm": 2.3504791259765625,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.1822,
+      "step": 49
+    },
+    {
+      "epoch": 0.025905896829765875,
+      "grad_norm": 3.4843292236328125,
+      "learning_rate": 0.0,
+      "loss": 0.195,
+      "step": 50
+    },
+    {
+      "epoch": 0.025905896829765875,
+      "eval_loss": 0.21778494119644165,
+      "eval_runtime": 252.7074,
+      "eval_samples_per_second": 51.455,
+      "eval_steps_per_second": 6.434,
+      "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": 3.91521434075136e+16,
+  "total_flos": 7.83042868150272e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null