Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e19fcb29b5d7ab4662b15b63d4a81edf9d856b2bbabf16b366e4c7c53d9d907f
+oid sha256:d14c2b22e0894ee5c43cadbe5cdb5ea65d46a5acf3e78bc302fe1e8741e3695c
 size 209760536

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:041e9da0826e45c3642ed1a83ba3705255e323cf9b13fbc44c9d7bdd5241f264
+oid sha256:81f6532d22596b1c49c44e23cae6ed6e27f1afa2c36b51e3f69866d9c2c2b30b
 size 419700154

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd0556fd141e38b6c049be180b325f90c359cc0dc60bd66e562a406dcc3480a8
+oid sha256:4f3f74229ca9a1519bcfccf5d2cfc80f9b7787d1625e9db765c84d69dc244615
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a62e6ea25099651400ff4a3142a50e40bef5b52ba883be53b2fcb9d1a5b0a98c
+oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.0497976541519165,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.0010390689941812137,
+  "best_metric": 1.002984881401062,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.0015586034912718205,
   "eval_steps": 5,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -89,6 +89,50 @@
       "eval_samples_per_second": 3.182,
       "eval_steps_per_second": 1.591,
       "step": 20
+    },
+    {
+      "epoch": 0.0010910224438902742,
+      "grad_norm": 1.0282012224197388,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 4.3566,
+      "step": 21
+    },
+    {
+      "epoch": 0.0012468827930174563,
+      "grad_norm": 1.050193428993225,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 4.1911,
+      "step": 24
+    },
+    {
+      "epoch": 0.001298836242726517,
+      "eval_loss": 1.0107142925262451,
+      "eval_runtime": 2544.8712,
+      "eval_samples_per_second": 3.185,
+      "eval_steps_per_second": 1.593,
+      "step": 25
+    },
+    {
+      "epoch": 0.0014027431421446384,
+      "grad_norm": 1.007144570350647,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 4.0247,
+      "step": 27
+    },
+    {
+      "epoch": 0.0015586034912718205,
+      "grad_norm": 0.9790642261505127,
+      "learning_rate": 0.0,
+      "loss": 3.8987,
+      "step": 30
+    },
+    {
+      "epoch": 0.0015586034912718205,
+      "eval_loss": 1.002984881401062,
+      "eval_runtime": 2546.0806,
+      "eval_samples_per_second": 3.183,
+      "eval_steps_per_second": 1.592,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -112,12 +156,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2.310669172998144e+16,
+  "total_flos": 3.473863178452992e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null