Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c24e3b1c702aabf0c1faf45f665e1055f5306f9e2716004c62aa76f771230ae
+oid sha256:e497d9b0c33f827bccafe47b16c03de1767d1504fdf8def356b66854fdf12c13
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:82a786828b15215118b13ddf55ec7887b21b4c045ed28c44ac849bc530a5fac8
+oid sha256:44edfbaa57f95850bbde4464df2c68cd6abb495ce4a0e5599789036128633ed5
 size 341314196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6928dd58ae198a057a3cb24e91583ecd19a5107fc7b70fe875d905f20f25aa4d
+oid sha256:e0b41842dd9aec4e2bb693c505fbb08dd2ba327c5a97955aeef2997596d3cb90
 size 14308

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff293d6444222bd1d89236cd1763caa87bb59d6363a546a504877debc45066aa
+oid sha256:aa1bfb19ac7a71e5a662427e7488d4a4d957109537750c19fd28e94a30346c50
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.7841286063194275,
   "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.030656039239730228,
+  "epoch": 0.061312078479460456,
   "eval_steps": 50,
-  "global_step": 50,
+  "global_step": 100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -58,6 +58,49 @@
       "eval_samples_per_second": 16.212,
       "eval_steps_per_second": 4.059,
       "step": 50
+    },
+    {
+      "epoch": 0.03678724708767627,
+      "grad_norm": 2.0683157444000244,
+      "learning_rate": 0.00021074300730241147,
+      "loss": 0.5761,
+      "step": 60
+    },
+    {
+      "epoch": 0.04291845493562232,
+      "grad_norm": 1.5029504299163818,
+      "learning_rate": 0.00020997328125223568,
+      "loss": 0.4392,
+      "step": 70
+    },
+    {
+      "epoch": 0.049049662783568364,
+      "grad_norm": 1.8249471187591553,
+      "learning_rate": 0.0002086945718774165,
+      "loss": 0.4728,
+      "step": 80
+    },
+    {
+      "epoch": 0.05518087063151441,
+      "grad_norm": 2.3122222423553467,
+      "learning_rate": 0.00020691310892149265,
+      "loss": 0.4777,
+      "step": 90
+    },
+    {
+      "epoch": 0.061312078479460456,
+      "grad_norm": 3.182551145553589,
+      "learning_rate": 0.00020463757149291335,
+      "loss": 0.5207,
+      "step": 100
+    },
+    {
+      "epoch": 0.061312078479460456,
+      "eval_loss": 0.784916877746582,
+      "eval_runtime": 42.3748,
+      "eval_samples_per_second": 16.212,
+      "eval_steps_per_second": 4.059,
+      "step": 100
     }
   ],
   "logging_steps": 10,
@@ -72,7 +115,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 0
+        "early_stopping_patience_counter": 1
       }
     },
     "TrainerControl": {
@@ -86,7 +129,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 9522491965833216.0,
+  "total_flos": 1.8950701832994816e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null