Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:44ba6144444a807d9550c601f3f035154160eae0703f811d5c0c3aa1a07696d1
+oid sha256:bee0680b633356afd46736e3d6597b53910b9196d49de6c283688ed06debf0d3
 size 48552

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:86f43f2670d0f5039ffdca5d70ebe654270852670ede200a610ced1f24a8aed7
+oid sha256:4f1a149f783db31121b13944d8d8c4bebbbc624486ab6c7c0dd5d7b7f2a6d6fb
 size 113994

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7875d5432ff8d4da0f42dcb806a6d87823cc0d656c3cd55903df63e3b7b89a4a
+oid sha256:04f6af6305ac637366ac47fa2f79e7317338a583685196b178b505ce7bc39608
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1449afb150d9f605add550dedf31ad0557e9d5001598df962afc2d48887c33f7
+oid sha256:4a1297d5e0d2b65b4349a407471e567a96e72c86b5ddf6a148613dd5f59703e3
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7204aba4111eaa27c8b758e0def475dc2df3f4bcfc815e1956636ca58c300c12
+oid sha256:a5367efaf423e0ffa373592fe9f859bc5124121a56010ef5d97f5e177f11a66b
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d9252f7ba236f7b3df04b0499ac3a2633d5410127cfec781338908deb603f07d
+oid sha256:b5e34304756927dcc13c4b3ecfca0ace0b631b3891d0c8997a3a60ede81fe487
 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": 11.929377555847168,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.02046349823502328,
+  "best_metric": 11.928548812866211,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.04092699647004656,
   "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": 438.248,
       "eval_steps_per_second": 54.794,
       "step": 25
+    },
+    {
+      "epoch": 0.02128203816442421,
+      "grad_norm": 0.056903108954429626,
+      "learning_rate": 5e-05,
+      "loss": 11.9294,
+      "step": 26
+    },
+    {
+      "epoch": 0.022100578093825138,
+      "grad_norm": 0.053392358124256134,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 11.9288,
+      "step": 27
+    },
+    {
+      "epoch": 0.02291911802322607,
+      "grad_norm": 0.05559993535280228,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 11.9294,
+      "step": 28
+    },
+    {
+      "epoch": 0.023737657952627,
+      "grad_norm": 0.05701728165149689,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 11.9294,
+      "step": 29
+    },
+    {
+      "epoch": 0.02455619788202793,
+      "grad_norm": 0.057807229459285736,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 11.9305,
+      "step": 30
+    },
+    {
+      "epoch": 0.025374737811428863,
+      "grad_norm": 0.05711260065436363,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 11.9283,
+      "step": 31
+    },
+    {
+      "epoch": 0.026193277740829794,
+      "grad_norm": 0.0587916374206543,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 11.9296,
+      "step": 32
+    },
+    {
+      "epoch": 0.027011817670230726,
+      "grad_norm": 0.06173417717218399,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 11.9291,
+      "step": 33
+    },
+    {
+      "epoch": 0.027830357599631657,
+      "grad_norm": 0.05909475311636925,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 11.9293,
+      "step": 34
+    },
+    {
+      "epoch": 0.028648897529032588,
+      "grad_norm": 0.058725230395793915,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 11.9288,
+      "step": 35
+    },
+    {
+      "epoch": 0.02946743745843352,
+      "grad_norm": 0.05278372764587402,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 11.93,
+      "step": 36
+    },
+    {
+      "epoch": 0.03028597738783445,
+      "grad_norm": 0.058989524841308594,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 11.9286,
+      "step": 37
+    },
+    {
+      "epoch": 0.031104517317235382,
+      "grad_norm": 0.0682770386338234,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 11.9284,
+      "step": 38
+    },
+    {
+      "epoch": 0.03192305724663631,
+      "grad_norm": 0.06626476347446442,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 11.9283,
+      "step": 39
+    },
+    {
+      "epoch": 0.032741597176037245,
+      "grad_norm": 0.0669265016913414,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 11.9275,
+      "step": 40
+    },
+    {
+      "epoch": 0.033560137105438176,
+      "grad_norm": 0.06591495126485825,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 11.929,
+      "step": 41
+    },
+    {
+      "epoch": 0.03437867703483911,
+      "grad_norm": 0.06877961754798889,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 11.9275,
+      "step": 42
+    },
+    {
+      "epoch": 0.03519721696424004,
+      "grad_norm": 0.06533712148666382,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 11.9286,
+      "step": 43
+    },
+    {
+      "epoch": 0.03601575689364097,
+      "grad_norm": 0.06201931834220886,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 11.929,
+      "step": 44
+    },
+    {
+      "epoch": 0.0368342968230419,
+      "grad_norm": 0.061079900711774826,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 11.9282,
+      "step": 45
+    },
+    {
+      "epoch": 0.03765283675244283,
+      "grad_norm": 0.06090058758854866,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 11.928,
+      "step": 46
+    },
+    {
+      "epoch": 0.038471376681843764,
+      "grad_norm": 0.06689566373825073,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 11.9286,
+      "step": 47
+    },
+    {
+      "epoch": 0.039289916611244695,
+      "grad_norm": 0.06943468004465103,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 11.928,
+      "step": 48
+    },
+    {
+      "epoch": 0.040108456540645626,
+      "grad_norm": 0.05866420269012451,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 11.9288,
+      "step": 49
+    },
+    {
+      "epoch": 0.04092699647004656,
+      "grad_norm": 0.05418151617050171,
+      "learning_rate": 0.0,
+      "loss": 11.929,
+      "step": 50
+    },
+    {
+      "epoch": 0.04092699647004656,
+      "eval_loss": 11.928548812866211,
+      "eval_runtime": 18.8301,
+      "eval_samples_per_second": 437.065,
+      "eval_steps_per_second": 54.646,
+      "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": 522550247424.0,
+  "total_flos": 1045100494848.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null