Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1edfbd09ebde6181b02fc97af7751453214545eb4545afcf10e6b4f65854c3ab
+oid sha256:d476d242c23c494f4de6d64cfadb3f0a0302c59871c443b8b566cc599a785eb2
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f286d9c5c732f19093f046530986912b9bbce0a1e9610eb1ba5c325cb4465f3
+oid sha256:d6dc85de9114ddafd05eabfee1134a9635751786281d228263d8ef30db8e0718
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1fd5eb7a54681907ff77e904ce5a1c790eb0cfc3b5679bbd418339c63df915ba
+oid sha256:684885edf140055a417153154fd80ea155af4712c29a37dc4fd2c40e169ae41a
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:92a5b6166ad508245a0abca427af239df71f8f5081bf170e704a7eaaa749cadc
+oid sha256:1ca912ff94dde732e796034876b7eb9bd3dafa47f4437c4766719a60b76b26d3
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e66bebdff894b40e5c8bb9aa4c618b484fcfbb2f6a75baf2784b9281da06f15f
+oid sha256:e4666e5207c7a5738fade8d99a57eebcaa23d5ecebf3f6a234e79d2dac564b18
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:986316a72c782fad2bb83224d33c3361944bc93ebbf15f8ed8d1fcd6d1900e9c
+oid sha256:3dfd4f770f4cb18f5b7344e7c18002ce842e70c37e65c6e3871310383b7cd78d
 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": NaN,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.8368200836820083,
+  "epoch": 1.6799163179916317,
   "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": 31.985,
       "eval_steps_per_second": 4.117,
       "step": 25
+    },
+    {
+      "epoch": 0.8702928870292888,
+      "grad_norm": 1.2969869375228882,
+      "learning_rate": 5e-05,
+      "loss": 0.1293,
+      "step": 26
+    },
+    {
+      "epoch": 0.9037656903765691,
+      "grad_norm": 1.183563470840454,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.1323,
+      "step": 27
+    },
+    {
+      "epoch": 0.9372384937238494,
+      "grad_norm": 0.6034805178642273,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.1447,
+      "step": 28
+    },
+    {
+      "epoch": 0.9707112970711297,
+      "grad_norm": 1.0187960863113403,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.1809,
+      "step": 29
+    },
+    {
+      "epoch": 1.010460251046025,
+      "grad_norm": 2.551266670227051,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.2435,
+      "step": 30
+    },
+    {
+      "epoch": 1.0439330543933054,
+      "grad_norm": 1.363511085510254,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.1345,
+      "step": 31
+    },
+    {
+      "epoch": 1.0774058577405858,
+      "grad_norm": 0.8237060308456421,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.1068,
+      "step": 32
+    },
+    {
+      "epoch": 1.110878661087866,
+      "grad_norm": 0.8394637107849121,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.1252,
+      "step": 33
+    },
+    {
+      "epoch": 1.1443514644351465,
+      "grad_norm": 1.3592426776885986,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.114,
+      "step": 34
+    },
+    {
+      "epoch": 1.1778242677824267,
+      "grad_norm": 0.8103972673416138,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.1411,
+      "step": 35
+    },
+    {
+      "epoch": 1.211297071129707,
+      "grad_norm": 0.5803283452987671,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.1132,
+      "step": 36
+    },
+    {
+      "epoch": 1.2447698744769875,
+      "grad_norm": 1.0763193368911743,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.1371,
+      "step": 37
+    },
+    {
+      "epoch": 1.2782426778242677,
+      "grad_norm": 1.7600771188735962,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.1414,
+      "step": 38
+    },
+    {
+      "epoch": 1.3117154811715481,
+      "grad_norm": 0.844605565071106,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.1074,
+      "step": 39
+    },
+    {
+      "epoch": 1.3451882845188283,
+      "grad_norm": 0.7922542095184326,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.1396,
+      "step": 40
+    },
+    {
+      "epoch": 1.3786610878661087,
+      "grad_norm": 0.7589727640151978,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.1046,
+      "step": 41
+    },
+    {
+      "epoch": 1.4121338912133892,
+      "grad_norm": 1.1158431768417358,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.1242,
+      "step": 42
+    },
+    {
+      "epoch": 1.4456066945606696,
+      "grad_norm": 0.8884672522544861,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.1562,
+      "step": 43
+    },
+    {
+      "epoch": 1.4790794979079498,
+      "grad_norm": 1.0795230865478516,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.1548,
+      "step": 44
+    },
+    {
+      "epoch": 1.51255230125523,
+      "grad_norm": 1.3964478969573975,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.1468,
+      "step": 45
+    },
+    {
+      "epoch": 1.5460251046025104,
+      "grad_norm": 0.47748827934265137,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.102,
+      "step": 46
+    },
+    {
+      "epoch": 1.5794979079497908,
+      "grad_norm": 0.47063204646110535,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.1303,
+      "step": 47
+    },
+    {
+      "epoch": 1.6129707112970713,
+      "grad_norm": 0.7242940068244934,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.1158,
+      "step": 48
+    },
+    {
+      "epoch": 1.6464435146443515,
+      "grad_norm": 0.6986421942710876,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.1134,
+      "step": 49
+    },
+    {
+      "epoch": 1.6799163179916317,
+      "grad_norm": 0.6429162621498108,
+      "learning_rate": 0.0,
+      "loss": 0.1399,
+      "step": 50
+    },
+    {
+      "epoch": 1.6799163179916317,
+      "eval_loss": NaN,
+      "eval_runtime": 6.3067,
+      "eval_samples_per_second": 32.029,
+      "eval_steps_per_second": 4.123,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -212,7 +395,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 0
+        "early_stopping_patience_counter": 1
       }
     },
     "TrainerControl": {
@@ -221,12 +404,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2.984041808658432e+17,
+  "total_flos": 5.968083617316864e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null