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:bda382f09e694d9ce26bb168952cb4d4a9579e7c5b8167a734b842f7a7636803
+oid sha256:eaafccfdd88c6329d4b4f521dd93d872364900c818936269f924d631b1c71972
 size 100966336

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:36ed34a73bfe0433898f7976315f20e2c3e413641d2335ddb3bbaa3476bf70be
+oid sha256:661f1920f5f9125d47a37cd2aceb006dded1f4f826023a84c704ba67fe88c9c7
 size 202110330

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2809afac928613f24d222ae6863df0bddaa8207a726555e661b49335d3012517
+oid sha256:870f9d653a5c3c6c79e3a77894d2c7fecd064470b9b73b74dd4be28fa6cfa713
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f527c9577bd16b18c1b0a5ddd8c56f00d0a263421988cef5bf008a6963470e6a
+oid sha256:5777ebacd6ee1f8811db77d73fb67d549c3c51257a73678683c75916860eb515
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d46fd903a31dd776c8067ea4bad69ad46b6a0668a1dde848c55c32a8372b6dc0
+oid sha256:9f95d607bfa94856ff367b5ea9e06e71e39524dc0a49c9c7c2be66edf5123870
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:39ac9e951895cf1ccbc058805c6aab4dcf4ebe64127b7b2f9b9ecbbe45f745c0
+oid sha256:71aa6604a7c8d52fae0517b653b8cf753b425e3af5a56334fe15a33547caf5a9
 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": 1.0896035432815552,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.006489503228527856,
+  "best_metric": 1.0704972743988037,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.012979006457055712,
   "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": 48.269,
       "eval_steps_per_second": 6.035,
       "step": 25
+    },
+    {
+      "epoch": 0.00674908335766897,
+      "grad_norm": 0.21018411219120026,
+      "learning_rate": 5e-05,
+      "loss": 1.0873,
+      "step": 26
+    },
+    {
+      "epoch": 0.0070086634868100845,
+      "grad_norm": 0.26302167773246765,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 1.1213,
+      "step": 27
+    },
+    {
+      "epoch": 0.007268243615951199,
+      "grad_norm": 0.28120750188827515,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 1.127,
+      "step": 28
+    },
+    {
+      "epoch": 0.007527823745092313,
+      "grad_norm": 0.32956844568252563,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 1.2097,
+      "step": 29
+    },
+    {
+      "epoch": 0.007787403874233427,
+      "grad_norm": 0.34264886379241943,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 1.1,
+      "step": 30
+    },
+    {
+      "epoch": 0.008046984003374542,
+      "grad_norm": 0.3952774703502655,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 1.0939,
+      "step": 31
+    },
+    {
+      "epoch": 0.008306564132515655,
+      "grad_norm": 0.42787548899650574,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 1.1388,
+      "step": 32
+    },
+    {
+      "epoch": 0.00856614426165677,
+      "grad_norm": 0.4804704487323761,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 1.049,
+      "step": 33
+    },
+    {
+      "epoch": 0.008825724390797884,
+      "grad_norm": 0.5848066806793213,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 1.0445,
+      "step": 34
+    },
+    {
+      "epoch": 0.009085304519938999,
+      "grad_norm": 0.6109868884086609,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.9919,
+      "step": 35
+    },
+    {
+      "epoch": 0.009344884649080112,
+      "grad_norm": 0.7301526665687561,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.9818,
+      "step": 36
+    },
+    {
+      "epoch": 0.009604464778221227,
+      "grad_norm": 0.8971400856971741,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 1.1092,
+      "step": 37
+    },
+    {
+      "epoch": 0.009864044907362342,
+      "grad_norm": 0.2470068633556366,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.0186,
+      "step": 38
+    },
+    {
+      "epoch": 0.010123625036503455,
+      "grad_norm": 0.24352461099624634,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 1.0952,
+      "step": 39
+    },
+    {
+      "epoch": 0.01038320516564457,
+      "grad_norm": 0.24224068224430084,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 1.1043,
+      "step": 40
+    },
+    {
+      "epoch": 0.010642785294785684,
+      "grad_norm": 0.27325406670570374,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 1.1733,
+      "step": 41
+    },
+    {
+      "epoch": 0.010902365423926799,
+      "grad_norm": 0.28306472301483154,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 1.1438,
+      "step": 42
+    },
+    {
+      "epoch": 0.011161945553067912,
+      "grad_norm": 0.3500412404537201,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 1.1038,
+      "step": 43
+    },
+    {
+      "epoch": 0.011421525682209027,
+      "grad_norm": 0.3962816298007965,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.0506,
+      "step": 44
+    },
+    {
+      "epoch": 0.01168110581135014,
+      "grad_norm": 0.44881391525268555,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 1.059,
+      "step": 45
+    },
+    {
+      "epoch": 0.011940685940491256,
+      "grad_norm": 0.5522152185440063,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 1.0823,
+      "step": 46
+    },
+    {
+      "epoch": 0.012200266069632369,
+      "grad_norm": 0.6204373836517334,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 1.0627,
+      "step": 47
+    },
+    {
+      "epoch": 0.012459846198773484,
+      "grad_norm": 0.663255512714386,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 1.0783,
+      "step": 48
+    },
+    {
+      "epoch": 0.012719426327914599,
+      "grad_norm": 0.7815361022949219,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 1.0808,
+      "step": 49
+    },
+    {
+      "epoch": 0.012979006457055712,
+      "grad_norm": 1.1580921411514282,
+      "learning_rate": 0.0,
+      "loss": 1.1881,
+      "step": 50
+    },
+    {
+      "epoch": 0.012979006457055712,
+      "eval_loss": 1.0704972743988037,
+      "eval_runtime": 538.1147,
+      "eval_samples_per_second": 48.229,
+      "eval_steps_per_second": 6.03,
+      "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": 4.169686388310016e+16,
+  "total_flos": 8.336768348717056e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null