Training in progress, step 392, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2072adb64bf4f50b48418c52096cf79779fcaaf6e8413cf8be2acc91f7095217
+oid sha256:01778842841800df84e59a1b5d8478840de5f698ef4b74bcc998ba5d266f7532
 size 60576160

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a6315e6f80a70dcc3ec3fc68841684f4ce6815fbd126520b2393416bfe5b361
+oid sha256:eeabde6df48b19e4f88ea5d6d24e38c449e448c88bfc657892759abed65885a0
 size 30896058

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d232fa33de0a3f36fb8c3451d877ed11305baa6ced4ec91f5259002aadce72f2
+oid sha256:a38d84075b4aa7b2d8e347742ccf50ea165d1a502f96b35e9df1434a8c3aa5bd
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0bfba9f6f71d6bf8d4b22bdc118ed4ab52735b4c3d041fc8533613a4cc45feba
+oid sha256:f719ffdf1144f9138b05dbe566e3aa108061ab35c21fce6a3638170db860438b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 8.305614471435547,
   "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": 123.435,
       "eval_steps_per_second": 31.42,
       "step": 350
+    },
+    {
+      "epoch": 0.9195402298850575,
+      "grad_norm": 0.44001325964927673,
+      "learning_rate": 4.653908220663318e-06,
+      "loss": 8.3403,
+      "step": 360
+    },
+    {
+      "epoch": 0.9450830140485313,
+      "grad_norm": 0.5452269315719604,
+      "learning_rate": 2.208076220998228e-06,
+      "loss": 8.333,
+      "step": 370
+    },
+    {
+      "epoch": 0.9706257982120051,
+      "grad_norm": 1.2281514406204224,
+      "learning_rate": 6.585215110024809e-07,
+      "loss": 8.293,
+      "step": 380
+    },
+    {
+      "epoch": 0.9961685823754789,
+      "grad_norm": 0.7243633270263672,
+      "learning_rate": 1.8310282784486043e-08,
+      "loss": 8.2837,
+      "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": 3615550202707968.0,
+  "total_flos": 4054460525445120.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null