Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d140693b6f7f42c570fea6b17dfd76b0fccaa454a639b750c6972adc14e4258
+oid sha256:67a2c07de5961ed70dd6f925da64d2553dc2a02a2b717d6a6abfad3da375824d
 size 147770496

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ba09c38603f644bebce35c798e2a97c125ae45b455ede76a6fe1ebaa8fc66f1
+oid sha256:705d828efb6bd05b3f4854a040812e7cda3d04815735566ea081503387a3a97f
 size 295765866

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f7e0952e515b5b4e15a1ff0d159f31f6db18129ad8657c6609d6672c618fd392
+oid sha256:4fdb01eb0f6b719005222eabe90d2e8ecacfe9d14ddb0214436dc425115bff75
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:69b9008e8e014139161267e349edcf3e2bc22a76ea78a00e38fedf3b3a5d5ff6
+oid sha256:e5355f67e7aeea76ddc5ee67774840cc03c94b84c47d3c36c7fbedbe2742053b
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:61ea1e4a8f756714b9c700a2165f440d843a3bbeb3371c9c34ca14891d8bf359
+oid sha256:8c285224cc8b03cf8d25e2e78d584bafd720ebf41636d036f0c1e5e2c3efbf9b
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:acf31857c165f083d0b9b0e642a7478e16b2f4f104880015b80ac5040f06566b
+oid sha256:45a19eb6053b05a1509a4caf5d2f77f350dcb8ce3549496e7a88eadcb24ce677
 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": 0.7588818073272705,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 1.408450704225352,
+  "best_metric": 0.7373636960983276,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 2.816901408450704,
   "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": 89.38,
       "eval_steps_per_second": 11.173,
       "step": 25
+    },
+    {
+      "epoch": 1.4647887323943662,
+      "grad_norm": 1.7001279592514038,
+      "learning_rate": 5e-05,
+      "loss": 0.8627,
+      "step": 26
+    },
+    {
+      "epoch": 1.5211267605633803,
+      "grad_norm": 1.0881457328796387,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.7834,
+      "step": 27
+    },
+    {
+      "epoch": 1.5774647887323945,
+      "grad_norm": 1.3560937643051147,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.7894,
+      "step": 28
+    },
+    {
+      "epoch": 1.6338028169014085,
+      "grad_norm": 1.1216421127319336,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.8246,
+      "step": 29
+    },
+    {
+      "epoch": 1.6901408450704225,
+      "grad_norm": 1.5690072774887085,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.8028,
+      "step": 30
+    },
+    {
+      "epoch": 1.7464788732394365,
+      "grad_norm": 1.6674970388412476,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.8028,
+      "step": 31
+    },
+    {
+      "epoch": 1.8028169014084507,
+      "grad_norm": 1.2421163320541382,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.8152,
+      "step": 32
+    },
+    {
+      "epoch": 1.8591549295774648,
+      "grad_norm": 1.976396083831787,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.8078,
+      "step": 33
+    },
+    {
+      "epoch": 1.915492957746479,
+      "grad_norm": 1.6364705562591553,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.8123,
+      "step": 34
+    },
+    {
+      "epoch": 1.971830985915493,
+      "grad_norm": 1.5316513776779175,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.8613,
+      "step": 35
+    },
+    {
+      "epoch": 2.028169014084507,
+      "grad_norm": 1.5757020711898804,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.856,
+      "step": 36
+    },
+    {
+      "epoch": 2.084507042253521,
+      "grad_norm": 0.8843956589698792,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.7801,
+      "step": 37
+    },
+    {
+      "epoch": 2.140845070422535,
+      "grad_norm": 1.490215539932251,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.7651,
+      "step": 38
+    },
+    {
+      "epoch": 2.1971830985915495,
+      "grad_norm": 1.2212885618209839,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.7514,
+      "step": 39
+    },
+    {
+      "epoch": 2.2535211267605635,
+      "grad_norm": 2.2902417182922363,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.7644,
+      "step": 40
+    },
+    {
+      "epoch": 2.3098591549295775,
+      "grad_norm": 0.8333585262298584,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.7863,
+      "step": 41
+    },
+    {
+      "epoch": 2.3661971830985915,
+      "grad_norm": 1.7875335216522217,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.7201,
+      "step": 42
+    },
+    {
+      "epoch": 2.4225352112676055,
+      "grad_norm": 1.2753856182098389,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.7981,
+      "step": 43
+    },
+    {
+      "epoch": 2.4788732394366195,
+      "grad_norm": 1.1924065351486206,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.7627,
+      "step": 44
+    },
+    {
+      "epoch": 2.535211267605634,
+      "grad_norm": 2.2087767124176025,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.7358,
+      "step": 45
+    },
+    {
+      "epoch": 2.591549295774648,
+      "grad_norm": 2.043612003326416,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.7413,
+      "step": 46
+    },
+    {
+      "epoch": 2.647887323943662,
+      "grad_norm": 0.983856737613678,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.7159,
+      "step": 47
+    },
+    {
+      "epoch": 2.704225352112676,
+      "grad_norm": 2.1408305168151855,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.8566,
+      "step": 48
+    },
+    {
+      "epoch": 2.76056338028169,
+      "grad_norm": 1.3574248552322388,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.7231,
+      "step": 49
+    },
+    {
+      "epoch": 2.816901408450704,
+      "grad_norm": 2.1828038692474365,
+      "learning_rate": 0.0,
+      "loss": 0.8049,
+      "step": 50
+    },
+    {
+      "epoch": 2.816901408450704,
+      "eval_loss": 0.7373636960983276,
+      "eval_runtime": 1.3411,
+      "eval_samples_per_second": 89.477,
+      "eval_steps_per_second": 11.185,
+      "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": 5.29768176943104e+16,
+  "total_flos": 1.059536353886208e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null