Training in progress, step 209, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d6edb0539f97709cea271de72099d52c94bb0597166f3f4aa5b683b9d3a40338
+oid sha256:cb3c042fc05446cce42e8ba05c26d21f6a33fad1d276065c31751e9eb9b92c9a
 size 50503544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2499bbfa4e07b794c1813ff851011b0c63cdce04787dbd7aabaeb49ee1484df7
+oid sha256:d9161dc0d5b45d102a25e69107d79b474ed640e72b157f48abc64aaaed3deb54
 size 101184122

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e67e3986f9b5d21cf143e8fff112d872e8f773d9018b5fb314111df7f4592c35
+oid sha256:32f074aa0dc3bbbaf32ed9b3d0e52c2afafd75640cf1eb31d812ea245e926858
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b1b8e48d9009abc474691522115451b9e2ab07413f2618da36c748a460ecac4
+oid sha256:40297b54e197ed589332b6920de875b05d1178917ecfa4de495baf5faadb1bb0
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:59fda8ef542f982c7a174ffae9f10913c30cef756ee4217304ce41dd5c496953
+oid sha256:84f1f6e7cbd40691344b0f55583c6580c77c289b6e22a00d28c5c1f7ecb12ce0
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e8a9db533c3e04750882b6ad94d0935c91d30807f5a987a39b39bc075beb2051
+oid sha256:e2c49b3899e9febf007ca0e81d807f4d5855313b577082d469902339f58ac46d
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bf6c7c2e48585167b8ae09e4fab626fc8f2a4ca56cc9826daed29b7acb9cc601
+oid sha256:87c0a96fa3a122e63ba1eeeef721578b9cf44b040fe3f79eba83b9517ca4ac4c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.539456307888031,
   "best_model_checkpoint": "miner_id_24/checkpoint-200",
-  "epoch": 2.8793103448275863,
+  "epoch": 3.0114942528735633,
   "eval_steps": 25,
-  "global_step": 200,
+  "global_step": 209,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1479,6 +1479,69 @@
       "eval_samples_per_second": 57.511,
       "eval_steps_per_second": 3.451,
       "step": 200
+    },
+    {
+      "epoch": 2.8936781609195403,
+      "grad_norm": 0.3132757842540741,
+      "learning_rate": 2.0702642165868325e-05,
+      "loss": 0.3531,
+      "step": 201
+    },
+    {
+      "epoch": 2.9080459770114944,
+      "grad_norm": 0.49438345432281494,
+      "learning_rate": 2.053812474481016e-05,
+      "loss": 1.0436,
+      "step": 202
+    },
+    {
+      "epoch": 2.9224137931034484,
+      "grad_norm": 0.2360573410987854,
+      "learning_rate": 2.0395461618029175e-05,
+      "loss": 0.5821,
+      "step": 203
+    },
+    {
+      "epoch": 2.9367816091954024,
+      "grad_norm": 0.19015099108219147,
+      "learning_rate": 2.0274687636146892e-05,
+      "loss": 0.4832,
+      "step": 204
+    },
+    {
+      "epoch": 2.9511494252873565,
+      "grad_norm": 0.24269899725914001,
+      "learning_rate": 2.0175832302570575e-05,
+      "loss": 0.5398,
+      "step": 205
+    },
+    {
+      "epoch": 2.9655172413793105,
+      "grad_norm": 0.25860899686813354,
+      "learning_rate": 2.0098919766285978e-05,
+      "loss": 0.5282,
+      "step": 206
+    },
+    {
+      "epoch": 2.9798850574712645,
+      "grad_norm": 0.2763611674308777,
+      "learning_rate": 2.0043968815958072e-05,
+      "loss": 0.5299,
+      "step": 207
+    },
+    {
+      "epoch": 2.9942528735632186,
+      "grad_norm": 0.6282367706298828,
+      "learning_rate": 2.0010992875341232e-05,
+      "loss": 0.63,
+      "step": 208
+    },
+    {
+      "epoch": 3.0114942528735633,
+      "grad_norm": 0.7394906282424927,
+      "learning_rate": 2e-05,
+      "loss": 1.2121,
+      "step": 209
     }
   ],
   "logging_steps": 1,
@@ -1502,12 +1565,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 3.6169443950618214e+17,
+  "total_flos": 3.7867902377499034e+17,
   "train_batch_size": 6,
   "trial_name": null,
   "trial_params": null