Training in progress, step 392, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2942c604c402be0dd61661c70ff00f6d333c0f80999397e145dc919fba246f3b
+oid sha256:1c516b1e9c7e4751f11172a1f2788b8fe15a6d984b49314df352b266b4a3b99c
 size 15156512

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:773329a6306179af91c9bf8f1757dca5a5717f7e9dd3203e2bfb3c0cd8446d95
+oid sha256:ad56009dd80f321518e2e224a2db128272d42ca6dad581bb74297f3d385f8b57
 size 7826042

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e905d36ab2885c18b6bfd546ddde99117f7f4dab0bbce5a4c6de17d257b0dc5b
+oid sha256:fefe54528ecd53b3880f4e7a0bde1197bbd0a6d1b2a1c952b97b69592718970b
 size 14308

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10f7347a2afb1e470f457ae657ace2e239323389d3fe2906c06dcd2436150868
+oid sha256:1f0662b4545016260e8ea53dffdc5e9ecc7f70746e378850e5c4b6f3232abd98
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 8.457124710083008,
   "best_model_checkpoint": "miner_id_24/checkpoint-350",
-  "epoch": 0.8939974457215837,
+  "epoch": 1.0012771392081736,
   "eval_steps": 50,
-  "global_step": 350,
+  "global_step": 392,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -316,6 +316,34 @@
       "eval_samples_per_second": 109.217,
       "eval_steps_per_second": 27.801,
       "step": 350
+    },
+    {
+      "epoch": 0.9195402298850575,
+      "grad_norm": 1.0569088459014893,
+      "learning_rate": 4.611015057339232e-06,
+      "loss": 8.455,
+      "step": 360
+    },
+    {
+      "epoch": 0.9450830140485313,
+      "grad_norm": 0.7266004085540771,
+      "learning_rate": 2.1877252880858024e-06,
+      "loss": 8.4595,
+      "step": 370
+    },
+    {
+      "epoch": 0.9706257982120051,
+      "grad_norm": 0.9919468760490417,
+      "learning_rate": 6.524521883204303e-07,
+      "loss": 8.4392,
+      "step": 380
+    },
+    {
+      "epoch": 0.9961685823754789,
+      "grad_norm": 1.0076446533203125,
+      "learning_rate": 1.814152441780875e-08,
+      "loss": 8.3541,
+      "step": 390
     }
   ],
   "logging_steps": 10,
@@ -339,12 +367,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 3436534796648448.0,
+  "total_flos": 3851034999128064.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null