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:d70845e255f0abefacec4c2722c079c3bdecf256799fdee570ab3f8017ec871d
+oid sha256:077f7c55594ea68a6a9dc1b93b5af6de18049cb172a5473d3a9a4bc2461daab3
 size 239135488

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef2b74301c5d697ee142b2403788deaabc1cb2bd941975f6bdd332d89077f385
+oid sha256:0cb02cb6abb07e25bad9967db12765533f26417c80692d4188b6ef449459c91a
 size 478528978

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b72a814f563264cb5961e4a5cd8f61cc722f864837f2495b0b4156349dcb693
+oid sha256:58dadebec6f19282a3f5e4184d52607ff16d065da0b4bff7b6e7a0d90a7ae3d9
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:52ca683bc0e0c18bf2f886d451add3c4ead58bcb92d451268a35a43870f41861
+oid sha256:4f15c3bced3c00880ba8a576c1a08f787d5a9bf70329f6b0aef265830c4c5b9e
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0284e1baed8cf8d967702ba88822655b6b3abb6a397b61b059a5d07e75c64754
+oid sha256:607aaa2989735bcc1421d3cda2b044b0303f44edc75e0f052893030349159e96
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:31e506fb21c4a7fe6832985f75d8197f123d26c6cf7f5d44b50415daf25aa592
+oid sha256:8535c9080eab677dd91d31d43e09eb1af1b38d0d2a9e7d0c5cb73db78235d651
 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": 0.3158932328224182,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.5369127516778524,
+  "best_metric": 0.27144113183021545,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 1.076510067114094,
   "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": 20.402,
       "eval_steps_per_second": 2.599,
       "step": 25
+    },
+    {
+      "epoch": 0.5583892617449664,
+      "grad_norm": 28.777877807617188,
+      "learning_rate": 5e-05,
+      "loss": 0.4573,
+      "step": 26
+    },
+    {
+      "epoch": 0.5798657718120805,
+      "grad_norm": 17.136690139770508,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.287,
+      "step": 27
+    },
+    {
+      "epoch": 0.6013422818791946,
+      "grad_norm": 14.741988182067871,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.2617,
+      "step": 28
+    },
+    {
+      "epoch": 0.6228187919463087,
+      "grad_norm": 10.193075180053711,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.1994,
+      "step": 29
+    },
+    {
+      "epoch": 0.6442953020134228,
+      "grad_norm": 7.09152364730835,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.1473,
+      "step": 30
+    },
+    {
+      "epoch": 0.6657718120805369,
+      "grad_norm": 10.199577331542969,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.2079,
+      "step": 31
+    },
+    {
+      "epoch": 0.687248322147651,
+      "grad_norm": 9.366825103759766,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.2648,
+      "step": 32
+    },
+    {
+      "epoch": 0.7087248322147651,
+      "grad_norm": 10.735113143920898,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.3117,
+      "step": 33
+    },
+    {
+      "epoch": 0.7302013422818792,
+      "grad_norm": 7.8755316734313965,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.3043,
+      "step": 34
+    },
+    {
+      "epoch": 0.7516778523489933,
+      "grad_norm": 19.299285888671875,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.7202,
+      "step": 35
+    },
+    {
+      "epoch": 0.7731543624161074,
+      "grad_norm": 16.11593246459961,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.4716,
+      "step": 36
+    },
+    {
+      "epoch": 0.7946308724832215,
+      "grad_norm": 10.856176376342773,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.3398,
+      "step": 37
+    },
+    {
+      "epoch": 0.8161073825503355,
+      "grad_norm": 13.369665145874023,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.4083,
+      "step": 38
+    },
+    {
+      "epoch": 0.8375838926174497,
+      "grad_norm": 13.565021514892578,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.3234,
+      "step": 39
+    },
+    {
+      "epoch": 0.8590604026845637,
+      "grad_norm": 9.394250869750977,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.2066,
+      "step": 40
+    },
+    {
+      "epoch": 0.8805369127516779,
+      "grad_norm": 7.041374683380127,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.1839,
+      "step": 41
+    },
+    {
+      "epoch": 0.9020134228187919,
+      "grad_norm": 13.638995170593262,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.1963,
+      "step": 42
+    },
+    {
+      "epoch": 0.9234899328859061,
+      "grad_norm": 8.915301322937012,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.1899,
+      "step": 43
+    },
+    {
+      "epoch": 0.9449664429530201,
+      "grad_norm": 7.626116752624512,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.2316,
+      "step": 44
+    },
+    {
+      "epoch": 0.9664429530201343,
+      "grad_norm": 9.224981307983398,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.2937,
+      "step": 45
+    },
+    {
+      "epoch": 0.9879194630872483,
+      "grad_norm": 9.10223388671875,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.2994,
+      "step": 46
+    },
+    {
+      "epoch": 1.0120805369127517,
+      "grad_norm": 25.860401153564453,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.7044,
+      "step": 47
+    },
+    {
+      "epoch": 1.0335570469798658,
+      "grad_norm": 22.862300872802734,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.4963,
+      "step": 48
+    },
+    {
+      "epoch": 1.0550335570469798,
+      "grad_norm": 15.496158599853516,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.3009,
+      "step": 49
+    },
+    {
+      "epoch": 1.076510067114094,
+      "grad_norm": 15.115484237670898,
+      "learning_rate": 0.0,
+      "loss": 0.3819,
+      "step": 50
+    },
+    {
+      "epoch": 1.076510067114094,
+      "eval_loss": 0.27144113183021545,
+      "eval_runtime": 15.3658,
+      "eval_samples_per_second": 20.435,
+      "eval_steps_per_second": 2.603,
+      "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": 1.4965751695382938e+17,
+  "total_flos": 2.990361686604513e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null