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:c903f253cddb1ca5b7f20f96385f13e7ea92e15622c3986cef85c011698ec98c
+oid sha256:e3dc02e7049f33b7005e68d30df2678387ea67fc75a6872439213c5de1be6806
 size 400084608

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f03549153451ec9980c2ed0be661c1bed62d63ffbaf932bb39a0ba5d7033040
+oid sha256:5e76adcba30bd201584571e89136b1dd0dddbb53016f5cf1345f960512462f4c
 size 800394282

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60d6a76342380077a0c7616e031b136bde18b8e8f9ab52683937e930c3695ec6
+oid sha256:a955f2a4ddcc969102ee5912647613f27f6b9bf13d72c3b3743babb1668835bf
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b6f94415feb72fa3b58c97ecd30d89d4f09a0b23eeb533de9d5a12d428b837da
+oid sha256:9ad2b17852e974ecd6e273c2b8b2b07b0f33871d72c3cb18531ec4b70d147a72
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:924e310534ee6bf5fe5fdbd5b0abdb48ec2142100e4695088337626827257f78
+oid sha256:09bc98e50adf39f9d93e534e4fa164a592187b45bc4eaa1c97fdd7bdbf4d2683
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:83688e2491decca5c91ae639c5595cdeff6eefbd6ae66cf86d676a9bd0ea774e
+oid sha256:e9b8743e76996808d2e708f9b4fc9f9da772da40e1b499f4687decc95f5bb13d
 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": 3.7597262859344482,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.10767160161507403,
+  "best_metric": 3.673874616622925,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.21534320323014805,
   "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": 30.02,
       "eval_steps_per_second": 3.76,
       "step": 25
+    },
+    {
+      "epoch": 0.11197846567967698,
+      "grad_norm": 1.8688342571258545,
+      "learning_rate": 5e-05,
+      "loss": 3.8387,
+      "step": 26
+    },
+    {
+      "epoch": 0.11628532974427995,
+      "grad_norm": 1.3678120374679565,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 3.7591,
+      "step": 27
+    },
+    {
+      "epoch": 0.1205921938088829,
+      "grad_norm": 1.2320159673690796,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 3.8064,
+      "step": 28
+    },
+    {
+      "epoch": 0.12489905787348587,
+      "grad_norm": 1.46751070022583,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 3.7541,
+      "step": 29
+    },
+    {
+      "epoch": 0.12920592193808883,
+      "grad_norm": 1.0058436393737793,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 3.673,
+      "step": 30
+    },
+    {
+      "epoch": 0.13351278600269179,
+      "grad_norm": 1.1568927764892578,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 3.6349,
+      "step": 31
+    },
+    {
+      "epoch": 0.13781965006729474,
+      "grad_norm": 1.2745643854141235,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 3.669,
+      "step": 32
+    },
+    {
+      "epoch": 0.14212651413189772,
+      "grad_norm": 1.0898311138153076,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 3.6504,
+      "step": 33
+    },
+    {
+      "epoch": 0.14643337819650068,
+      "grad_norm": 0.9707027077674866,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 3.6602,
+      "step": 34
+    },
+    {
+      "epoch": 0.15074024226110364,
+      "grad_norm": 1.464558482170105,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 3.6902,
+      "step": 35
+    },
+    {
+      "epoch": 0.1550471063257066,
+      "grad_norm": 1.6716910600662231,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 3.6462,
+      "step": 36
+    },
+    {
+      "epoch": 0.15935397039030955,
+      "grad_norm": 1.391884207725525,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 3.7975,
+      "step": 37
+    },
+    {
+      "epoch": 0.16366083445491253,
+      "grad_norm": 0.967711329460144,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 3.7192,
+      "step": 38
+    },
+    {
+      "epoch": 0.16796769851951548,
+      "grad_norm": 1.2279342412948608,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 3.7489,
+      "step": 39
+    },
+    {
+      "epoch": 0.17227456258411844,
+      "grad_norm": 1.1709775924682617,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 3.6942,
+      "step": 40
+    },
+    {
+      "epoch": 0.1765814266487214,
+      "grad_norm": 1.0664342641830444,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 3.7223,
+      "step": 41
+    },
+    {
+      "epoch": 0.18088829071332435,
+      "grad_norm": 0.8159927129745483,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 3.6485,
+      "step": 42
+    },
+    {
+      "epoch": 0.18519515477792733,
+      "grad_norm": 0.8708414435386658,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 3.6189,
+      "step": 43
+    },
+    {
+      "epoch": 0.1895020188425303,
+      "grad_norm": 0.8581545948982239,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 3.6428,
+      "step": 44
+    },
+    {
+      "epoch": 0.19380888290713325,
+      "grad_norm": 0.8968494534492493,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 3.6532,
+      "step": 45
+    },
+    {
+      "epoch": 0.1981157469717362,
+      "grad_norm": 0.9328946471214294,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 3.6412,
+      "step": 46
+    },
+    {
+      "epoch": 0.20242261103633916,
+      "grad_norm": 1.0675426721572876,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 3.546,
+      "step": 47
+    },
+    {
+      "epoch": 0.20672947510094214,
+      "grad_norm": 1.1364132165908813,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 3.6322,
+      "step": 48
+    },
+    {
+      "epoch": 0.2110363391655451,
+      "grad_norm": 1.1251806020736694,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 3.6173,
+      "step": 49
+    },
+    {
+      "epoch": 0.21534320323014805,
+      "grad_norm": 1.5030646324157715,
+      "learning_rate": 0.0,
+      "loss": 3.8635,
+      "step": 50
+    },
+    {
+      "epoch": 0.21534320323014805,
+      "eval_loss": 3.673874616622925,
+      "eval_runtime": 52.0871,
+      "eval_samples_per_second": 30.046,
+      "eval_steps_per_second": 3.763,
+      "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": 3.087239672233984e+17,
+  "total_flos": 6.174479344467968e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null