Training in progress, step 400, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a5f3717e398c9632e2a4e967562ba686bdef014a83f6bb3a4ce1a4f447179e25
+oid sha256:3d0ab9d950d70ece30bb6f23c7d6a25eba3ccd89ff2abe1c2eec36251e90b6ab
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca2d5368cd159fb827b59a4953a980f645d9e7f2cca6fd0a6230ba3c5279be17
+oid sha256:3fd38a4effccc714e7a9f2ddc7d689828e4fd4bd8b1b558a54130529bbef4c38
 size 341314644

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ed345d46c22829856d6e59bb67a296b6d7eaa3f14aacf9ecf2ef695d776ea15
+oid sha256:743823328bb3612f590ee4af3270c58a4c350ab4447d07101b5feccb05f46b1a
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d4724a4322486cf07c6f137f6430836b1a2cb9ae0cd696f1604a47814630e3ba
+oid sha256:6a53e373878af8696de39d4b7adb8634138f0e346e89bffc05bcb76c7b6de169
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 2.400266170501709,
   "best_model_checkpoint": "miner_id_24/checkpoint-350",
-  "epoch": 0.05378409527468306,
+  "epoch": 0.06146753745678064,
   "eval_steps": 50,
-  "global_step": 350,
+  "global_step": 400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -316,6 +316,49 @@
       "eval_samples_per_second": 15.358,
       "eval_steps_per_second": 3.84,
       "step": 350
+    },
+    {
+      "epoch": 0.05532078371110257,
+      "grad_norm": 3.9929511547088623,
+      "learning_rate": 4.5843938039042344e-05,
+      "loss": 4.4327,
+      "step": 360
+    },
+    {
+      "epoch": 0.05685747214752209,
+      "grad_norm": 5.959095478057861,
+      "learning_rate": 3.997120656613154e-05,
+      "loss": 4.501,
+      "step": 370
+    },
+    {
+      "epoch": 0.058394160583941604,
+      "grad_norm": 7.357118606567383,
+      "learning_rate": 3.441041693867878e-05,
+      "loss": 4.2774,
+      "step": 380
+    },
+    {
+      "epoch": 0.059930849020361124,
+      "grad_norm": 10.237184524536133,
+      "learning_rate": 2.9188660764780296e-05,
+      "loss": 4.8857,
+      "step": 390
+    },
+    {
+      "epoch": 0.06146753745678064,
+      "grad_norm": 14.245146751403809,
+      "learning_rate": 2.4331377915626298e-05,
+      "loss": 4.9947,
+      "step": 400
+    },
+    {
+      "epoch": 0.06146753745678064,
+      "eval_loss": 2.4386484622955322,
+      "eval_runtime": 175.8523,
+      "eval_samples_per_second": 15.581,
+      "eval_steps_per_second": 3.895,
+      "step": 400
     }
   ],
   "logging_steps": 10,
@@ -330,7 +373,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 0
+        "early_stopping_patience_counter": 1
       }
     },
     "TrainerControl": {
@@ -344,7 +387,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.886677918253056e+16,
+  "total_flos": 7.870489049432064e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null