Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b64cb857c47d834d26d961411960b86fff104df978eddc2849624525e2f816f
+oid sha256:2140ee52d93fe1dfc008081af2b3c3e619a1d04f405ca1d70a6d635c859f8e86
 size 323014168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:14569a0b3412bcc681a4892333a75a7640ec0bbd9e6f45e106756dcc94898c2c
+oid sha256:e592f3337f73ae0e7541d07dd278f4a24b753a8a9d2f4d109583e7e858235f55
 size 646253418

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a634954dd892fb46c331e6997b73f282487fa4148d2643ef3a3f45d5c7cd32da
+oid sha256:2a71a437d8644cfa8be4dbede4bc584bac7bc61c9082ab1446b4dbb6adc33aba
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f46ead07a7cc8f24bde67af7158b9ec8794471d2bd8145497c279d6119ccb511
+oid sha256:3fe468bf4d05b63325f0c6634d95eaaa0cee7ed864cd67b15b406ddf7ca83784
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:039bc0be694dccde694f0d5e98a3c5508fbd31ce308f90bf950dd18f51f24afe
+oid sha256:2dbdb7aedb0ee90a0bb6efc0f26aba8ea6014a868ab81b2d91a1f30e000e913e
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c9bc607986704587d2f4702db16b9d5eb6787af0f5925675967bb65ce4393ca
+oid sha256:2cd83d49f6dcfbb9ca838bcd0f0f33dcb9898327deb5174ed93ac8ac7e0a9fb7
 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": 1.3114382028579712,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.1736111111111111,
+  "best_metric": 1.2489848136901855,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.3472222222222222,
   "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": 32.094,
       "eval_steps_per_second": 4.037,
       "step": 25
+    },
+    {
+      "epoch": 0.18055555555555555,
+      "grad_norm": 4.669939994812012,
+      "learning_rate": 5e-05,
+      "loss": 2.3008,
+      "step": 26
+    },
+    {
+      "epoch": 0.1875,
+      "grad_norm": 0.956480085849762,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 1.151,
+      "step": 27
+    },
+    {
+      "epoch": 0.19444444444444445,
+      "grad_norm": 1.0286616086959839,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 1.1746,
+      "step": 28
+    },
+    {
+      "epoch": 0.2013888888888889,
+      "grad_norm": 0.4344209134578705,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 1.1443,
+      "step": 29
+    },
+    {
+      "epoch": 0.20833333333333334,
+      "grad_norm": 0.7663750052452087,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 1.1566,
+      "step": 30
+    },
+    {
+      "epoch": 0.2152777777777778,
+      "grad_norm": 1.3293375968933105,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 1.2021,
+      "step": 31
+    },
+    {
+      "epoch": 0.2222222222222222,
+      "grad_norm": 0.8125392198562622,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 1.2006,
+      "step": 32
+    },
+    {
+      "epoch": 0.22916666666666666,
+      "grad_norm": 0.6639127731323242,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 1.1885,
+      "step": 33
+    },
+    {
+      "epoch": 0.2361111111111111,
+      "grad_norm": 0.349135160446167,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 1.1957,
+      "step": 34
+    },
+    {
+      "epoch": 0.24305555555555555,
+      "grad_norm": 0.347326397895813,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 1.174,
+      "step": 35
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 0.36792704463005066,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 1.18,
+      "step": 36
+    },
+    {
+      "epoch": 0.2569444444444444,
+      "grad_norm": 0.4151381850242615,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 1.219,
+      "step": 37
+    },
+    {
+      "epoch": 0.2638888888888889,
+      "grad_norm": 2.240403175354004,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 2.3103,
+      "step": 38
+    },
+    {
+      "epoch": 0.2708333333333333,
+      "grad_norm": 0.7299799919128418,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 1.1462,
+      "step": 39
+    },
+    {
+      "epoch": 0.2777777777777778,
+      "grad_norm": 0.6447272896766663,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 1.1402,
+      "step": 40
+    },
+    {
+      "epoch": 0.2847222222222222,
+      "grad_norm": 0.5773812532424927,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 1.1283,
+      "step": 41
+    },
+    {
+      "epoch": 0.2916666666666667,
+      "grad_norm": 0.5375441312789917,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 1.1535,
+      "step": 42
+    },
+    {
+      "epoch": 0.2986111111111111,
+      "grad_norm": 0.63286954164505,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 1.1698,
+      "step": 43
+    },
+    {
+      "epoch": 0.3055555555555556,
+      "grad_norm": 0.38500720262527466,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.1718,
+      "step": 44
+    },
+    {
+      "epoch": 0.3125,
+      "grad_norm": 0.33812084794044495,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 1.1934,
+      "step": 45
+    },
+    {
+      "epoch": 0.3194444444444444,
+      "grad_norm": 0.369324654340744,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 1.1793,
+      "step": 46
+    },
+    {
+      "epoch": 0.3263888888888889,
+      "grad_norm": 0.29939842224121094,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 1.1672,
+      "step": 47
+    },
+    {
+      "epoch": 0.3333333333333333,
+      "grad_norm": 0.29709550738334656,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 1.1617,
+      "step": 48
+    },
+    {
+      "epoch": 0.3402777777777778,
+      "grad_norm": 0.4721861481666565,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 1.1688,
+      "step": 49
+    },
+    {
+      "epoch": 0.3472222222222222,
+      "grad_norm": 0.4779790937900543,
+      "learning_rate": 0.0,
+      "loss": 1.2128,
+      "step": 50
+    },
+    {
+      "epoch": 0.3472222222222222,
+      "eval_loss": 1.2489848136901855,
+      "eval_runtime": 29.9675,
+      "eval_samples_per_second": 32.368,
+      "eval_steps_per_second": 4.071,
+      "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": 2.89638977248428e+17,
+  "total_flos": 5.805082167402824e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null