Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:77800094d3a149d473f9007427a8213cf27e9723b31a54473ae2bbb1d7c1f185
+oid sha256:1d71bd077ac869430f255dd330e291c1bdf99c75e286facf9f3e0f6b6f16387d
 size 70430032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c0a32315b6ea10193d6804ab98945db5b1a386e2279717690b728ff2c21c51a0
+oid sha256:6b3b22560f1ff032dd8b8283ad52dbe7ec6e350a190e7a7db6b2b557f3994fb6
 size 141053442

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6fa85092e90f302ad24c5e98cb7ed084b8d055a296fa1e894f21003c1b1ad4a0
+oid sha256:d2248df84b57f935ccc0bdb5bfc153b264ee4fae9afd2f6b23dd2047123c91f5
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:be4a2e0cf488fd57d402ccd670cdd3bc6920a09a14d2f58a1354ccce43b0591c
+oid sha256:986b0d4cdfb2192675660acede2f1d7bbe90c668b798a952804fa62109342c08
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87aa8219b3e749fc6aef6a1cf17f18b9abf013160ed061a421ed53d0e9a68853
+oid sha256:6566d13e56393457b7f5a05a372033cccdd615993787ed789895d44014fffd90
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0dfcbf1619856b5d26767af0e6a4d1beb659f7c3a65cfc34722dba1b047bda66
+oid sha256:9b5fd12a824876e202518b55075545e080f7c997157669ae9416431360cd2523
 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": 2.1353137493133545,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.74487895716946,
+  "best_metric": 1.9779502153396606,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 1.495344506517691,
   "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": 76.128,
       "eval_steps_per_second": 9.726,
       "step": 25
+    },
+    {
+      "epoch": 0.7746741154562383,
+      "grad_norm": 2.946615695953369,
+      "learning_rate": 5e-05,
+      "loss": 2.0212,
+      "step": 26
+    },
+    {
+      "epoch": 0.8044692737430168,
+      "grad_norm": 2.3928239345550537,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 2.0514,
+      "step": 27
+    },
+    {
+      "epoch": 0.8342644320297952,
+      "grad_norm": 2.0668535232543945,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 2.1217,
+      "step": 28
+    },
+    {
+      "epoch": 0.8640595903165735,
+      "grad_norm": 1.8767576217651367,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 1.8756,
+      "step": 29
+    },
+    {
+      "epoch": 0.8938547486033519,
+      "grad_norm": 3.1248583793640137,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 1.9879,
+      "step": 30
+    },
+    {
+      "epoch": 0.9236499068901304,
+      "grad_norm": 2.4403278827667236,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 1.9678,
+      "step": 31
+    },
+    {
+      "epoch": 0.9534450651769087,
+      "grad_norm": 2.0304882526397705,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 2.3779,
+      "step": 32
+    },
+    {
+      "epoch": 0.9832402234636871,
+      "grad_norm": 2.2402291297912598,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 2.5861,
+      "step": 33
+    },
+    {
+      "epoch": 1.0186219739292366,
+      "grad_norm": 3.376228094100952,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 3.2541,
+      "step": 34
+    },
+    {
+      "epoch": 1.048417132216015,
+      "grad_norm": 1.9267646074295044,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 1.9487,
+      "step": 35
+    },
+    {
+      "epoch": 1.0782122905027933,
+      "grad_norm": 1.7760834693908691,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 1.8374,
+      "step": 36
+    },
+    {
+      "epoch": 1.1080074487895717,
+      "grad_norm": 1.5164313316345215,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 1.8834,
+      "step": 37
+    },
+    {
+      "epoch": 1.13780260707635,
+      "grad_norm": 2.668070077896118,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.7881,
+      "step": 38
+    },
+    {
+      "epoch": 1.1675977653631284,
+      "grad_norm": 2.745457887649536,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 1.4016,
+      "step": 39
+    },
+    {
+      "epoch": 1.197392923649907,
+      "grad_norm": 2.1074106693267822,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 1.9102,
+      "step": 40
+    },
+    {
+      "epoch": 1.2271880819366854,
+      "grad_norm": 2.2203242778778076,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 2.6533,
+      "step": 41
+    },
+    {
+      "epoch": 1.2569832402234637,
+      "grad_norm": 1.5127211809158325,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 1.8591,
+      "step": 42
+    },
+    {
+      "epoch": 1.2867783985102421,
+      "grad_norm": 2.127408027648926,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 2.0432,
+      "step": 43
+    },
+    {
+      "epoch": 1.3165735567970205,
+      "grad_norm": 1.5922434329986572,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.8363,
+      "step": 44
+    },
+    {
+      "epoch": 1.3463687150837989,
+      "grad_norm": 1.5293318033218384,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 1.9234,
+      "step": 45
+    },
+    {
+      "epoch": 1.3761638733705772,
+      "grad_norm": 1.7801039218902588,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 1.6588,
+      "step": 46
+    },
+    {
+      "epoch": 1.4059590316573556,
+      "grad_norm": 2.720064640045166,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 1.6795,
+      "step": 47
+    },
+    {
+      "epoch": 1.435754189944134,
+      "grad_norm": 2.2383999824523926,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 2.1166,
+      "step": 48
+    },
+    {
+      "epoch": 1.4655493482309125,
+      "grad_norm": 2.0387301445007324,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 2.3229,
+      "step": 49
+    },
+    {
+      "epoch": 1.495344506517691,
+      "grad_norm": 1.6231642961502075,
+      "learning_rate": 0.0,
+      "loss": 1.8016,
+      "step": 50
+    },
+    {
+      "epoch": 1.495344506517691,
+      "eval_loss": 1.9779502153396606,
+      "eval_runtime": 2.9043,
+      "eval_samples_per_second": 78.16,
+      "eval_steps_per_second": 9.985,
+      "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": 2.4694538849222656e+16,
+  "total_flos": 4.927833981845504e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null