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:fe3b2476e99e83e9399b22d066d920d56135fa6cda09a950e734cc15fda80689
+oid sha256:4ff964722b16dcf6066892ea2b2f5a1e7ed49803f147a3ae76528f150f428920
 size 1521616

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:937b8ca97cbdd854ea75517cf7c719fdc8d3e669cfeead870ff91999772b4e9c
+oid sha256:be5dfd669994765dea55ab41fe132a2076884bc1bb67db1dd23426529c10b3ac
 size 3108666

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c23b659c2015d935fc2fb33bdba27b81982493a94c95d8e455c216972b4e1b9b
+oid sha256:39243204b56d431003e6e773c1c2d1cdb50080063a598d8fee14c9a88682118d
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e20d7174875fdad71de09acc717260d47fe3e1bb366fda48adcab4856d0b5254
+oid sha256:2cf0609556c2eb01e8432f5b060fd30bf661a79eca117a47e8dd6bd7d407f244
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0687166179c1e508c8c6d0aa253e6c17691da802b7318ea2bb2674055d2755d9
+oid sha256:e7f9a7f8ef7e623c3305d1581a2cd933bab8261a9f9a3a65bc6a1b41de4c9766
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a471f5a3670f365e2117994ff3caac483a40ab313e41d5b6459822c59201520
+oid sha256:04c83ecaac631b2612151829ef0e470dbcec9a75dcab8cc86455369697351366
 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": 7.122404098510742,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.06443298969072164,
+  "best_metric": 7.063704490661621,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.12886597938144329,
   "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": 195.968,
       "eval_steps_per_second": 24.515,
       "step": 25
+    },
+    {
+      "epoch": 0.06701030927835051,
+      "grad_norm": 2.843515634536743,
+      "learning_rate": 5e-05,
+      "loss": 7.2493,
+      "step": 26
+    },
+    {
+      "epoch": 0.06958762886597938,
+      "grad_norm": 1.6025389432907104,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 7.8308,
+      "step": 27
+    },
+    {
+      "epoch": 0.07216494845360824,
+      "grad_norm": 1.3303579092025757,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 7.5161,
+      "step": 28
+    },
+    {
+      "epoch": 0.07474226804123711,
+      "grad_norm": 1.0986202955245972,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 7.4137,
+      "step": 29
+    },
+    {
+      "epoch": 0.07731958762886598,
+      "grad_norm": 0.9372117519378662,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 7.3211,
+      "step": 30
+    },
+    {
+      "epoch": 0.07989690721649484,
+      "grad_norm": 1.0359989404678345,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 7.4251,
+      "step": 31
+    },
+    {
+      "epoch": 0.08247422680412371,
+      "grad_norm": 1.050330400466919,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 6.9601,
+      "step": 32
+    },
+    {
+      "epoch": 0.08505154639175258,
+      "grad_norm": 1.0149939060211182,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 7.0997,
+      "step": 33
+    },
+    {
+      "epoch": 0.08762886597938144,
+      "grad_norm": 0.8797879815101624,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 6.8525,
+      "step": 34
+    },
+    {
+      "epoch": 0.09020618556701031,
+      "grad_norm": 0.9121543169021606,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 6.8513,
+      "step": 35
+    },
+    {
+      "epoch": 0.09278350515463918,
+      "grad_norm": 0.9668096303939819,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 6.7363,
+      "step": 36
+    },
+    {
+      "epoch": 0.09536082474226804,
+      "grad_norm": 1.13383150100708,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 6.6522,
+      "step": 37
+    },
+    {
+      "epoch": 0.0979381443298969,
+      "grad_norm": 1.455060601234436,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 7.743,
+      "step": 38
+    },
+    {
+      "epoch": 0.10051546391752578,
+      "grad_norm": 1.4939161539077759,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 7.6736,
+      "step": 39
+    },
+    {
+      "epoch": 0.10309278350515463,
+      "grad_norm": 1.1243243217468262,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 7.5141,
+      "step": 40
+    },
+    {
+      "epoch": 0.1056701030927835,
+      "grad_norm": 1.0334477424621582,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 7.4467,
+      "step": 41
+    },
+    {
+      "epoch": 0.10824742268041238,
+      "grad_norm": 0.850965142250061,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 7.4166,
+      "step": 42
+    },
+    {
+      "epoch": 0.11082474226804123,
+      "grad_norm": 0.9271207451820374,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 7.2256,
+      "step": 43
+    },
+    {
+      "epoch": 0.1134020618556701,
+      "grad_norm": 0.924728512763977,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 7.1742,
+      "step": 44
+    },
+    {
+      "epoch": 0.11597938144329897,
+      "grad_norm": 0.8596798777580261,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 7.0014,
+      "step": 45
+    },
+    {
+      "epoch": 0.11855670103092783,
+      "grad_norm": 0.9014486074447632,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 6.9507,
+      "step": 46
+    },
+    {
+      "epoch": 0.1211340206185567,
+      "grad_norm": 0.8988224267959595,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 6.8728,
+      "step": 47
+    },
+    {
+      "epoch": 0.12371134020618557,
+      "grad_norm": 0.8983946442604065,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 6.6614,
+      "step": 48
+    },
+    {
+      "epoch": 0.12628865979381443,
+      "grad_norm": 0.9872623085975647,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 6.8147,
+      "step": 49
+    },
+    {
+      "epoch": 0.12886597938144329,
+      "grad_norm": 1.2063250541687012,
+      "learning_rate": 0.0,
+      "loss": 6.6433,
+      "step": 50
+    },
+    {
+      "epoch": 0.12886597938144329,
+      "eval_loss": 7.063704490661621,
+      "eval_runtime": 13.226,
+      "eval_samples_per_second": 197.64,
+      "eval_steps_per_second": 24.724,
+      "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": 119559610171392.0,
+  "total_flos": 239916767772672.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null