Training in progress, step 150, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d899b9b44828f0297b9f6217945ac2a339ec82ebeadfb4d8724b9e91572d050e
+oid sha256:1e73c8bf56282559f133d0e4fb62e79ad67320db484743a0a0b8a66ee39d2b5c
 size 295488936

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1117734ad619919636cf3a095e4e4502f42c834e375c5ec02aed5e2d67cdfe1a
+oid sha256:c1c2f229ad7e660fd7eafc22967a1439df1b51c5a7ad288e94a735d73300de90
 size 150486964

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:769f047583b2fcdc7aa25db8a01280cf2a8e77e7912e9cc9fef875a47cba852c
+oid sha256:ede8ad130a34125c7cfbac5ce6c21244f3f6d71049b1d147212e4c0c64fae3d7
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d4d0f57336dd58c2282a758b1873df2644647c71e8296b0dab58cb3a9f5f7c78
+oid sha256:7e45926e8bb4228c69b4b56f6b51f1445c0aeb3fb7bb09ed84764ec2b4c3a8ff
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.0001741647720337,
-  "best_model_checkpoint": "miner_id_24/checkpoint-100",
-  "epoch": 0.0034706556068441327,
+  "best_metric": 0.9768159985542297,
+  "best_model_checkpoint": "miner_id_24/checkpoint-150",
+  "epoch": 0.0052059834102661995,
   "eval_steps": 50,
-  "global_step": 100,
+  "global_step": 150,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -101,6 +101,49 @@
       "eval_samples_per_second": 44.262,
       "eval_steps_per_second": 11.065,
       "step": 100
+    },
+    {
+      "epoch": 0.003817721167528546,
+      "grad_norm": 0.7673032283782959,
+      "learning_rate": 3.1076923076923076e-06,
+      "loss": 0.4904,
+      "step": 110
+    },
+    {
+      "epoch": 0.00416478672821296,
+      "grad_norm": 1.0892831087112427,
+      "learning_rate": 2.330769230769231e-06,
+      "loss": 0.5508,
+      "step": 120
+    },
+    {
+      "epoch": 0.004511852288897372,
+      "grad_norm": 1.4933292865753174,
+      "learning_rate": 1.5538461538461538e-06,
+      "loss": 0.8418,
+      "step": 130
+    },
+    {
+      "epoch": 0.004858917849581786,
+      "grad_norm": 3.312762498855591,
+      "learning_rate": 7.769230769230769e-07,
+      "loss": 1.2403,
+      "step": 140
+    },
+    {
+      "epoch": 0.0052059834102661995,
+      "grad_norm": 29.821260452270508,
+      "learning_rate": 0.0,
+      "loss": 2.0093,
+      "step": 150
+    },
+    {
+      "epoch": 0.0052059834102661995,
+      "eval_loss": 0.9768159985542297,
+      "eval_runtime": 272.9548,
+      "eval_samples_per_second": 44.447,
+      "eval_steps_per_second": 11.112,
+      "step": 150
     }
   ],
   "logging_steps": 10,
@@ -124,12 +167,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 6939690632478720.0,
+  "total_flos": 1.040953594871808e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null