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:f467579c9ecfb1d7710b8519b1f1672ef49a83925dfecce68626137c7f25b78c
+oid sha256:34688499001a06f8d14041dde96cf8253523860eace274f3c7678ed6d432f951
 size 500770656

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7458371a010182acfb86412cba24bdc82e05f3e4291925d75ee63aa58d5f71d
+oid sha256:a1f829f672d0190c596995f0a3066dd2bed9ebceb6472c91eca5956ca1ade133
 size 1001863522

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f1e5a0269fb77f18e3aceab5fac1fa5bf76f8e9a0652931915ce1c218d4968e0
+oid sha256:77366c5b0912fa56458010da901358791aaa2796f2cbae54ef844e1f493656b8
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f67f77e67876d6cfa255664a53d8a9eba8b45a78eac1576db27506d43c4d900
+oid sha256:80547ef4729b9177414a092feb2ba2e3e71ed2b079a7207fcbbaab3bc6d28d28
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d3fb96a29081398a6f085edcf4dbc751aa2abca1f4f1b427f38e11c24020466
+oid sha256:2e7c9063e5732fe73f6523dcfae64d929c2bbcb60b38bf913a3f84466abca2f9
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a4a3cf8f6339443cfe88b73e1e6572153b3e75d9ffbd8fa046c4bfe83bb245e0
+oid sha256:88ac0bf3af6e2d26476efc4ecf5b68aa017de1b5b67d2d99a0a855ac60342602
 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": 2.9710018634796143,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.018481726193226446,
+  "best_metric": 2.8776087760925293,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.03696345238645289,
   "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": 9.403,
       "eval_steps_per_second": 1.176,
       "step": 25
+    },
+    {
+      "epoch": 0.019220995240955507,
+      "grad_norm": 0.4898509681224823,
+      "learning_rate": 5e-05,
+      "loss": 2.6365,
+      "step": 26
+    },
+    {
+      "epoch": 0.019960264288684564,
+      "grad_norm": 0.6298810243606567,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 2.6809,
+      "step": 27
+    },
+    {
+      "epoch": 0.020699533336413622,
+      "grad_norm": 0.39488282799720764,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 2.7452,
+      "step": 28
+    },
+    {
+      "epoch": 0.02143880238414268,
+      "grad_norm": 0.5900229811668396,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 2.7869,
+      "step": 29
+    },
+    {
+      "epoch": 0.022178071431871737,
+      "grad_norm": 0.4614380896091461,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 2.8356,
+      "step": 30
+    },
+    {
+      "epoch": 0.022917340479600794,
+      "grad_norm": 0.3697441816329956,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 2.8268,
+      "step": 31
+    },
+    {
+      "epoch": 0.023656609527329852,
+      "grad_norm": 0.3978196084499359,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 2.8809,
+      "step": 32
+    },
+    {
+      "epoch": 0.02439587857505891,
+      "grad_norm": 0.44170308113098145,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 2.9129,
+      "step": 33
+    },
+    {
+      "epoch": 0.025135147622787967,
+      "grad_norm": 0.563273549079895,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 3.0687,
+      "step": 34
+    },
+    {
+      "epoch": 0.025874416670517025,
+      "grad_norm": 0.7094810009002686,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 3.0865,
+      "step": 35
+    },
+    {
+      "epoch": 0.026613685718246086,
+      "grad_norm": 0.7585165500640869,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 3.0847,
+      "step": 36
+    },
+    {
+      "epoch": 0.027352954765975143,
+      "grad_norm": 1.6270757913589478,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 3.1534,
+      "step": 37
+    },
+    {
+      "epoch": 0.0280922238137042,
+      "grad_norm": 0.6695430278778076,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 2.5163,
+      "step": 38
+    },
+    {
+      "epoch": 0.02883149286143326,
+      "grad_norm": 0.613318145275116,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 2.642,
+      "step": 39
+    },
+    {
+      "epoch": 0.029570761909162316,
+      "grad_norm": 0.6652768850326538,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 2.6482,
+      "step": 40
+    },
+    {
+      "epoch": 0.030310030956891373,
+      "grad_norm": 0.6474655270576477,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 2.7102,
+      "step": 41
+    },
+    {
+      "epoch": 0.03104930000462043,
+      "grad_norm": 0.7044395208358765,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 2.7681,
+      "step": 42
+    },
+    {
+      "epoch": 0.03178856905234949,
+      "grad_norm": 0.558677077293396,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 2.8322,
+      "step": 43
+    },
+    {
+      "epoch": 0.032527838100078546,
+      "grad_norm": 0.5612611770629883,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 2.8228,
+      "step": 44
+    },
+    {
+      "epoch": 0.033267107147807604,
+      "grad_norm": 0.3718057870864868,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 2.9401,
+      "step": 45
+    },
+    {
+      "epoch": 0.03400637619553666,
+      "grad_norm": 0.5113263726234436,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 3.0313,
+      "step": 46
+    },
+    {
+      "epoch": 0.03474564524326572,
+      "grad_norm": 0.666543185710907,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 2.9171,
+      "step": 47
+    },
+    {
+      "epoch": 0.035484914290994776,
+      "grad_norm": 0.9058085083961487,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 3.0978,
+      "step": 48
+    },
+    {
+      "epoch": 0.036224183338723834,
+      "grad_norm": 0.7812164425849915,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 3.1293,
+      "step": 49
+    },
+    {
+      "epoch": 0.03696345238645289,
+      "grad_norm": 2.9717793464660645,
+      "learning_rate": 0.0,
+      "loss": 3.3199,
+      "step": 50
+    },
+    {
+      "epoch": 0.03696345238645289,
+      "eval_loss": 2.8776087760925293,
+      "eval_runtime": 969.1036,
+      "eval_samples_per_second": 9.404,
+      "eval_steps_per_second": 1.176,
+      "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": 5.114180768104448e+17,
+  "total_flos": 1.0228361536208896e+18,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null