Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:42bd274219d63640982c138874415d0dbb46f54021b1a612b4995487fb13c034
+oid sha256:a98895513053cc227b3de10e64bd8daccb80fdfdca7474d6b7e331bf417bc49c
 size 250422888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:02ec0571d58e1fb9ac84fb0c29516b7b473540dbe59a1e4e861bea36bf1faa51
+oid sha256:d3f65d987460c4a9f98a289a0bdd514d575a4ba9361a51bb2db6e6fc56d7e6ec
 size 501168482

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cbcad13575f758dc61bd8a01f755b4512fa7f1c5756316f25bb9e1762935e3ba
+oid sha256:664693f18b51064d5150fff2311d1a0677c024225f08a9157db2f8a29bdc449a
 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": 1.653077483177185,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.005494128150539112,
+  "best_metric": 1.6377606391906738,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.008241192225808667,
   "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": 4.104,
       "eval_steps_per_second": 1.027,
       "step": 20
+    },
+    {
+      "epoch": 0.005768834558066067,
+      "grad_norm": 0.18241733312606812,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 1.3919,
+      "step": 21
+    },
+    {
+      "epoch": 0.006592953780646934,
+      "grad_norm": 0.17207609117031097,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 1.413,
+      "step": 24
+    },
+    {
+      "epoch": 0.006867660188173889,
+      "eval_loss": 1.640599250793457,
+      "eval_runtime": 744.0975,
+      "eval_samples_per_second": 4.12,
+      "eval_steps_per_second": 1.031,
+      "step": 25
+    },
+    {
+      "epoch": 0.0074170730032278006,
+      "grad_norm": 0.19466657936573029,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 1.541,
+      "step": 27
+    },
+    {
+      "epoch": 0.008241192225808667,
+      "grad_norm": 0.22457623481750488,
+      "learning_rate": 0.0,
+      "loss": 1.6077,
+      "step": 30
+    },
+    {
+      "epoch": 0.008241192225808667,
+      "eval_loss": 1.6377606391906738,
+      "eval_runtime": 744.2512,
+      "eval_samples_per_second": 4.12,
+      "eval_steps_per_second": 1.031,
+      "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": 3.872153250299904e+16,
+  "total_flos": 5.141711693021184e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null