Training in progress, step 800, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e288abafc2c3cea0015871a382f7a51dded5e5cd5458c5bb4df2fc216162fde2
+oid sha256:eab27a442053707a3f6362261bb0b2ba1c21906fd347ae9e38c2846aad860c09
 size 500770656

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b7c52a6a40977974af750230ec1751fd9c5b331d0ff37beccb418d1a5813a71
+oid sha256:616d57538b5f356aa4760a011e22fc28e67c199fc0f01391ba864a885de75471
 size 134320806

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:35a6d2cf966ab0e16fb93f8d45df1efd541d1aa6a8117be3ca9cb938b2babc67
+oid sha256:28f22fe94279dc5b4fc0860cf06ff132979d7d9cce6691fec29243b2df2a3eab
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b00bb9fde45e0630a7244ca815d2d61a6dbf25a1a1b403dd491700003e109bf9
+oid sha256:8d1867500d89be5276678cb80137dde3c5d6682d87aba4b3c93400957d5bb560
 size 2080

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 1.107336401939392,
   "best_model_checkpoint": "miner_id_24/checkpoint-500",
-  "epoch": 0.09696633882809254,
+  "epoch": 0.11081867294639147,
   "eval_steps": 100,
-  "global_step": 700,
+  "global_step": 800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -561,6 +561,84 @@
       "eval_samples_per_second": 3.126,
       "eval_steps_per_second": 3.126,
       "step": 700
+    },
+    {
+      "epoch": 0.09835157223992243,
+      "grad_norm": 7.35622501373291,
+      "learning_rate": 0.0001995125348912552,
+      "loss": 3.5653,
+      "step": 710
+    },
+    {
+      "epoch": 0.09973680565175232,
+      "grad_norm": 21.072219848632812,
+      "learning_rate": 0.00019949809939134866,
+      "loss": 3.8766,
+      "step": 720
+    },
+    {
+      "epoch": 0.10112203906358222,
+      "grad_norm": 35.778114318847656,
+      "learning_rate": 0.00019948346016462892,
+      "loss": 5.7792,
+      "step": 730
+    },
+    {
+      "epoch": 0.10250727247541211,
+      "grad_norm": 12.812899589538574,
+      "learning_rate": 0.00019946860265918076,
+      "loss": 5.0388,
+      "step": 740
+    },
+    {
+      "epoch": 0.103892505887242,
+      "grad_norm": 76.3056640625,
+      "learning_rate": 0.00019945355597883463,
+      "loss": 5.4607,
+      "step": 750
+    },
+    {
+      "epoch": 0.10527773929907189,
+      "grad_norm": 7.007827281951904,
+      "learning_rate": 0.00019943827646784484,
+      "loss": 3.4849,
+      "step": 760
+    },
+    {
+      "epoch": 0.10666297271090179,
+      "grad_norm": 12.457751274108887,
+      "learning_rate": 0.00019942279323004186,
+      "loss": 3.9192,
+      "step": 770
+    },
+    {
+      "epoch": 0.10804820612273168,
+      "grad_norm": 8.994271278381348,
+      "learning_rate": 0.00019940710626542568,
+      "loss": 4.6842,
+      "step": 780
+    },
+    {
+      "epoch": 0.10943343953456157,
+      "grad_norm": 13.488161087036133,
+      "learning_rate": 0.00019939120102208108,
+      "loss": 4.5099,
+      "step": 790
+    },
+    {
+      "epoch": 0.11081867294639147,
+      "grad_norm": 100.06396484375,
+      "learning_rate": 0.0001993751066038385,
+      "loss": 5.7456,
+      "step": 800
+    },
+    {
+      "epoch": 0.11081867294639147,
+      "eval_loss": 1.1453617811203003,
+      "eval_runtime": 46.7089,
+      "eval_samples_per_second": 3.126,
+      "eval_steps_per_second": 3.126,
+      "step": 800
     }
   ],
   "logging_steps": 10,
@@ -575,7 +653,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 2
+        "early_stopping_patience_counter": 3
       }
     },
     "TrainerControl": {
@@ -584,12 +662,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 8.19245323911168e+16,
+  "total_flos": 9.394411707039744e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null