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:ddb27f5a2b925eb94c9abc10ca0af30329a97c7dd251e22f9a0830b54338071f
+oid sha256:8d1b61549a9e1f5895bdcadeef5892a66ebac56a7cb96eed1cb0ce05bbfdcbe9
 size 156926880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d5050748bbac8a6941c8b5d2b6a4af116ff71e745e7de782982885ed980ec62d
+oid sha256:d45da3f1e2682736ed8c1fc33b479c35c29195b36cd5458d06866c2d8fdda979
 size 313998650

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c2b5e30cdec9c13984eeaf858db471f718825db83ab3bc9d5d645f2aa4e6ab73
+oid sha256:794c81b5b5498a8f13b11133a44cb792b8341376f6d6b138af80dcbac1b085d2
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0eba082e7fd630dff12a5a74c5e7583758b41ff0404a46642e80dfabec27e75b
+oid sha256:eac404c6dd9cf056aa0b0b3c9ad5ab8b48a99dd23c5bd4f84bec40261f5f7271
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e60deb53d9efef32a659bb1327194dba762c1d7e213209e1317edf20b2740d97
+oid sha256:78185ce3ce73f502431b92f955896b2eb3f6731bc14434e850677c8bd93cf42e
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9fec94aa7b7809372658a30534c482a17ff447060d8c7544db1420ec8db2ea59
+oid sha256:216a9c2d8faacc1a3577050fed6140f07b5107c8ae44c6e93b30de134b29f60c
 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": 0.5837231874465942,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.005351600128438403,
+  "best_metric": 0.5221843123435974,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.010703200256876806,
   "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": 76.095,
       "eval_steps_per_second": 9.512,
       "step": 25
+    },
+    {
+      "epoch": 0.005565664133575939,
+      "grad_norm": 0.640296220779419,
+      "learning_rate": 5e-05,
+      "loss": 0.7466,
+      "step": 26
+    },
+    {
+      "epoch": 0.005779728138713475,
+      "grad_norm": 0.7037237882614136,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.7036,
+      "step": 27
+    },
+    {
+      "epoch": 0.005993792143851011,
+      "grad_norm": 0.6568624973297119,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.4916,
+      "step": 28
+    },
+    {
+      "epoch": 0.0062078561489885475,
+      "grad_norm": 0.7200050354003906,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.4905,
+      "step": 29
+    },
+    {
+      "epoch": 0.006421920154126084,
+      "grad_norm": 0.7330017685890198,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.7688,
+      "step": 30
+    },
+    {
+      "epoch": 0.00663598415926362,
+      "grad_norm": 0.7159467935562134,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.8877,
+      "step": 31
+    },
+    {
+      "epoch": 0.006850048164401156,
+      "grad_norm": 0.7296081781387329,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.7366,
+      "step": 32
+    },
+    {
+      "epoch": 0.007064112169538692,
+      "grad_norm": 0.7816036343574524,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.5173,
+      "step": 33
+    },
+    {
+      "epoch": 0.007278176174676228,
+      "grad_norm": 1.1695483922958374,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.5228,
+      "step": 34
+    },
+    {
+      "epoch": 0.007492240179813764,
+      "grad_norm": 0.8715795874595642,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.3878,
+      "step": 35
+    },
+    {
+      "epoch": 0.0077063041849513006,
+      "grad_norm": 1.052472472190857,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.3641,
+      "step": 36
+    },
+    {
+      "epoch": 0.007920368190088836,
+      "grad_norm": 1.44721519947052,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.4555,
+      "step": 37
+    },
+    {
+      "epoch": 0.008134432195226372,
+      "grad_norm": 0.487374484539032,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.6312,
+      "step": 38
+    },
+    {
+      "epoch": 0.008348496200363908,
+      "grad_norm": 0.5912758111953735,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.6912,
+      "step": 39
+    },
+    {
+      "epoch": 0.008562560205501444,
+      "grad_norm": 0.5722944736480713,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.4945,
+      "step": 40
+    },
+    {
+      "epoch": 0.00877662421063898,
+      "grad_norm": 0.6678009629249573,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.5147,
+      "step": 41
+    },
+    {
+      "epoch": 0.008990688215776517,
+      "grad_norm": 0.614799439907074,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.6939,
+      "step": 42
+    },
+    {
+      "epoch": 0.009204752220914053,
+      "grad_norm": 0.6046878099441528,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.869,
+      "step": 43
+    },
+    {
+      "epoch": 0.009418816226051589,
+      "grad_norm": 0.6420084238052368,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.8111,
+      "step": 44
+    },
+    {
+      "epoch": 0.009632880231189125,
+      "grad_norm": 0.6718961596488953,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.6321,
+      "step": 45
+    },
+    {
+      "epoch": 0.009846944236326661,
+      "grad_norm": 0.753416121006012,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.5342,
+      "step": 46
+    },
+    {
+      "epoch": 0.010061008241464197,
+      "grad_norm": 0.8455974459648132,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.4483,
+      "step": 47
+    },
+    {
+      "epoch": 0.010275072246601734,
+      "grad_norm": 0.9669787883758545,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.2876,
+      "step": 48
+    },
+    {
+      "epoch": 0.01048913625173927,
+      "grad_norm": 0.9800657629966736,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.3691,
+      "step": 49
+    },
+    {
+      "epoch": 0.010703200256876806,
+      "grad_norm": 1.7702556848526,
+      "learning_rate": 0.0,
+      "loss": 0.3645,
+      "step": 50
+    },
+    {
+      "epoch": 0.010703200256876806,
+      "eval_loss": 0.5221843123435974,
+      "eval_runtime": 413.6901,
+      "eval_samples_per_second": 76.074,
+      "eval_steps_per_second": 9.51,
+      "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": 7.952285976808653e+16,
+  "total_flos": 1.5899604877626573e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null