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:b5c7e47588c3627d2d9d4eff9370f49a5c70dbda4e3a7c4307240b919977fee0
+oid sha256:c6271f120ec2c3cfb1fd7b56ff2bb5459fc3137f48f0c6535e99323041ad857a
 size 645975704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc7d0f83b44cf0ccb93f008d9d369f81901a5f0b8765d5e98cfd5e7043a21d9d
+oid sha256:fcddd6bd2cd6bc6faddcb21a03c8ec2e6547470e0ceee8c2ada3cd9be07fda33
 size 328468404

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6069c262ae1c977de720efbc7041ae7a796e99c03ebef59ad16e731210e11a8c
+oid sha256:f49cc70e43698962a43ee5f1e5ea93c76dbe4ce826f81dfbb789efeb8adbd88f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b2fd30f3b354b607634e22c75b4493073ee958ea49022a57afc742673e42d76
+oid sha256:cb28bb8cf2be6d829bc7d8d43fa28bbbd84fb8993a66e3e97cef2580889f0f5e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.2975257635116577,
-  "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.034916201117318434,
+  "best_metric": 1.2717502117156982,
+  "best_model_checkpoint": "miner_id_24/checkpoint-100",
+  "epoch": 0.06983240223463687,
   "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": 11.588,
       "eval_steps_per_second": 2.902,
       "step": 50
+    },
+    {
+      "epoch": 0.04189944134078212,
+      "grad_norm": 0.47768744826316833,
+      "learning_rate": 0.00020974422527728155,
+      "loss": 0.9301,
+      "step": 60
+    },
+    {
+      "epoch": 0.04888268156424581,
+      "grad_norm": 0.4488859176635742,
+      "learning_rate": 0.0002089781472178649,
+      "loss": 0.8632,
+      "step": 70
+    },
+    {
+      "epoch": 0.055865921787709494,
+      "grad_norm": 0.4876834750175476,
+      "learning_rate": 0.0002077054980770496,
+      "loss": 0.9053,
+      "step": 80
+    },
+    {
+      "epoch": 0.06284916201117319,
+      "grad_norm": 0.6040335893630981,
+      "learning_rate": 0.00020593247807352348,
+      "loss": 0.9912,
+      "step": 90
+    },
+    {
+      "epoch": 0.06983240223463687,
+      "grad_norm": 1.2908031940460205,
+      "learning_rate": 0.00020366772518252038,
+      "loss": 2.3175,
+      "step": 100
+    },
+    {
+      "epoch": 0.06983240223463687,
+      "eval_loss": 1.2717502117156982,
+      "eval_runtime": 52.2379,
+      "eval_samples_per_second": 11.543,
+      "eval_steps_per_second": 2.891,
+      "step": 100
     }
   ],
   "logging_steps": 10,
@@ -86,7 +129,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.395228272492544e+16,
+  "total_flos": 2.817116957835264e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null