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:e0d81e62a3621d623189f9ad2e380ee1c448527f14726643b0e48da51970334c
+oid sha256:8234fba92739f9ba49d65e85141151ea3e3f941b1fc02a890d6f96c892e54c95
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed321703fc4f74ee06fad972f9130a13563a7c47ce29f6d988e253214a129d4f
+oid sha256:9b82b04ea09710aa4213cb03ab0b5cc1dd4aa0201bac4c985f2111eba665c109
 size 341314196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b56be38ab57c4702d9d602fd6a9c472b446581ddd86664396ab1e9e7e6a2d7c6
+oid sha256:43d2d8263b8cbac44fb13353f2a54b95985b179bd30ff324f943f58b6fa81a87
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:efceaa5c248a4d80b63fee15b42b7a10a2394777ecd3ca622c0d4a7cf33eef18
+oid sha256:697eb5c311706d748c20f07b0521bb9d1f71aee638eb745112aecf80a82e51da
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 2.351407289505005,
   "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.018040772145047807,
+  "epoch": 0.036081544290095614,
   "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": 15.883,
       "eval_steps_per_second": 3.974,
       "step": 50
+    },
+    {
+      "epoch": 0.02164892657405737,
+      "grad_norm": 1.5297818183898926,
+      "learning_rate": 0.00021773448147832086,
+      "loss": 2.0854,
+      "step": 60
+    },
+    {
+      "epoch": 0.025257081003066933,
+      "grad_norm": 1.3838398456573486,
+      "learning_rate": 0.0002169392194928312,
+      "loss": 2.0998,
+      "step": 70
+    },
+    {
+      "epoch": 0.028865235432076492,
+      "grad_norm": 2.074045181274414,
+      "learning_rate": 0.00021561808847998484,
+      "loss": 2.2113,
+      "step": 80
+    },
+    {
+      "epoch": 0.032473389861086055,
+      "grad_norm": 2.1741549968719482,
+      "learning_rate": 0.00021377752485727676,
+      "loss": 2.1485,
+      "step": 90
+    },
+    {
+      "epoch": 0.036081544290095614,
+      "grad_norm": 6.557363986968994,
+      "learning_rate": 0.00021142649566566402,
+      "loss": 2.1276,
+      "step": 100
+    },
+    {
+      "epoch": 0.036081544290095614,
+      "eval_loss": 2.3574182987213135,
+      "eval_runtime": 73.3643,
+      "eval_samples_per_second": 15.907,
+      "eval_steps_per_second": 3.98,
+      "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": 9711056163176448.0,
+  "total_flos": 1.9422112326352896e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null