Training in progress, step 300, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c7fc37c4743d5bcc302db4de1bdd1e09036954935124b5f68f97897effd96fc
+oid sha256:215fbcf42cc76dceb00ab4eff8bfc8c9fde45953eeda55396171aea8efff9326
 size 997533656

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:680f98a7775785f0ea5444b8833b8817a18d87add55bbdfa0e83e38727fd21d6
-size 507180180
+oid sha256:c40eaf5e946f08d6504d6c5788c3e59b26fafbadcb948da3109be84e622713ff
+size 507180756

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc8fb98cb62eb41b8b5a0551eed70f6a159ade60589baf2dee1cfeed5c73760f
+oid sha256:9ccdc21eede641643dcacb904b84d9e5b079583b6d9465d0f18a2fbf9a91578c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5245962b37abe5debb29d3c0771306ab720257c32ca897672f6c78751ec6642f
+oid sha256:4e3407292f65425c0593f095883f5f3c050baccb28fc15b3c1ad88090d6c23ef
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.455014944076538,
-  "best_model_checkpoint": "miner_id_24/checkpoint-250",
-  "epoch": 0.09196247930844216,
+  "best_metric": 1.4276777505874634,
+  "best_model_checkpoint": "miner_id_24/checkpoint-300",
+  "epoch": 0.11035497517013058,
   "eval_steps": 50,
-  "global_step": 250,
+  "global_step": 300,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -230,6 +230,49 @@
       "eval_samples_per_second": 10.681,
       "eval_steps_per_second": 2.677,
       "step": 250
+    },
+    {
+      "epoch": 0.09564097848077985,
+      "grad_norm": 0.595523476600647,
+      "learning_rate": 0.00012039360249617425,
+      "loss": 1.582,
+      "step": 260
+    },
+    {
+      "epoch": 0.09931947765311752,
+      "grad_norm": 0.5969820618629456,
+      "learning_rate": 0.00011280404514057264,
+      "loss": 1.4637,
+      "step": 270
+    },
+    {
+      "epoch": 0.10299797682545521,
+      "grad_norm": 0.6512609124183655,
+      "learning_rate": 0.00010519595485942743,
+      "loss": 1.4196,
+      "step": 280
+    },
+    {
+      "epoch": 0.1066764759977929,
+      "grad_norm": 0.6744258403778076,
+      "learning_rate": 9.76063975038258e-05,
+      "loss": 1.3897,
+      "step": 290
+    },
+    {
+      "epoch": 0.11035497517013058,
+      "grad_norm": 0.8375758528709412,
+      "learning_rate": 9.00723486343046e-05,
+      "loss": 1.2334,
+      "step": 300
+    },
+    {
+      "epoch": 0.11035497517013058,
+      "eval_loss": 1.4276777505874634,
+      "eval_runtime": 107.3683,
+      "eval_samples_per_second": 10.664,
+      "eval_steps_per_second": 2.673,
+      "step": 300
     }
   ],
   "logging_steps": 10,
@@ -258,7 +301,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8.379241070592e+16,
+  "total_flos": 1.00550892847104e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null