Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b7b4fec99c119a6e9037ce65c40c51762c5d30cd9f53b0f65aae77f50122814c
+oid sha256:b0e1fdd19b2a1b1a30e4500a9199a3fb85bf69ecdae365e74dd701296beaa9a4
 size 94422368

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a1c1af8ba98e7f1ca7f83b7146db4a4d488489136c8eeb17daaf32cc770efbe5
+oid sha256:3896a2ddc49a523b63da9fe7500bd4b1669744f115956dc6bb79ea49f7686544
 size 189066386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ce944d1599d8f0670d98150881ef676a84157dc807356c153ae9813e4a057ee
+oid sha256:82b6326018595f5c0de7588328e3c1382f2ccd8857fc13296e3f9c1607f266ae
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:015707cb16790250630febca682498cb5d3456d5a13443b953687f19dc7d59ed
+oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.831789970397949,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.10973936899862825,
+  "best_metric": 2.823174476623535,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.1646090534979424,
   "eval_steps": 5,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -89,6 +89,50 @@
       "eval_samples_per_second": 12.565,
       "eval_steps_per_second": 3.182,
       "step": 20
+    },
+    {
+      "epoch": 0.11522633744855967,
+      "grad_norm": 1.9808909893035889,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 2.9112,
+      "step": 21
+    },
+    {
+      "epoch": 0.13168724279835392,
+      "grad_norm": 1.5520323514938354,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 2.8524,
+      "step": 24
+    },
+    {
+      "epoch": 0.13717421124828533,
+      "eval_loss": 2.8235270977020264,
+      "eval_runtime": 11.975,
+      "eval_samples_per_second": 12.86,
+      "eval_steps_per_second": 3.257,
+      "step": 25
+    },
+    {
+      "epoch": 0.14814814814814814,
+      "grad_norm": 1.4829930067062378,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 2.8688,
+      "step": 27
+    },
+    {
+      "epoch": 0.1646090534979424,
+      "grad_norm": 1.6260610818862915,
+      "learning_rate": 0.0,
+      "loss": 2.9289,
+      "step": 30
+    },
+    {
+      "epoch": 0.1646090534979424,
+      "eval_loss": 2.823174476623535,
+      "eval_runtime": 11.9834,
+      "eval_samples_per_second": 12.851,
+      "eval_steps_per_second": 3.255,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -112,12 +156,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 6107505780326400.0,
+  "total_flos": 8734389986918400.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null