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:efe16facb09233924f9cce3c382f6a8dc707aac6e3ff4e71f83faf047a7bdf55
+oid sha256:af2ac5f9f5a8afc2e8593a354e1ce27658149294c8a0f40656b51bdb30548427
 size 645975704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1bb4d6b01652e39505731016e02609671617baf61cc6fd63d43ba24d01bfee01
+oid sha256:580a06c4127fa8d71e3b8052907a41660172d23f22384c9c5b0defa79dbefabb
 size 328468404

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:144d2f0b66ae4e427ed7012bcd423c7ea2a6751e97b6b102313724577f6f8530
+oid sha256:5abd636d1fcde191adce24dac333f45255e5374fcf26e016a2e8b2fc91ca0902
 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": 1.7293239831924438,
   "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.0429553264604811,
+  "epoch": 0.0859106529209622,
   "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": 17.776,
       "eval_steps_per_second": 4.462,
       "step": 50
+    },
+    {
+      "epoch": 0.05154639175257732,
+      "grad_norm": 0.7793288230895996,
+      "learning_rate": 0.00021773448147832086,
+      "loss": 1.7899,
+      "step": 60
+    },
+    {
+      "epoch": 0.06013745704467354,
+      "grad_norm": 1.007460117340088,
+      "learning_rate": 0.0002169392194928312,
+      "loss": 1.6296,
+      "step": 70
+    },
+    {
+      "epoch": 0.06872852233676977,
+      "grad_norm": 1.0640578269958496,
+      "learning_rate": 0.00021561808847998484,
+      "loss": 1.6155,
+      "step": 80
+    },
+    {
+      "epoch": 0.07731958762886598,
+      "grad_norm": 1.191985011100769,
+      "learning_rate": 0.00021377752485727676,
+      "loss": 1.5215,
+      "step": 90
+    },
+    {
+      "epoch": 0.0859106529209622,
+      "grad_norm": 3.72426176071167,
+      "learning_rate": 0.00021142649566566402,
+      "loss": 1.4125,
+      "step": 100
+    },
+    {
+      "epoch": 0.0859106529209622,
+      "eval_loss": 1.7307857275009155,
+      "eval_runtime": 27.621,
+      "eval_samples_per_second": 17.74,
+      "eval_steps_per_second": 4.453,
+      "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": 8886804283392000.0,
+  "total_flos": 1.7773608566784e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null