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:e88435cd68a04ef0b07c51f66fc76d2cb37c4e1b47dfd2154af8638cd3e505ab
+oid sha256:ed56fc5094420c9e6fe9dc4a5612645430757be0de2c10fd96df13bbb61c0089
 size 403743472

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e22097f1648b0a1d2f1d1b5ec4e9daeca805feac9fffb041adb2883801fedd43
-size 205366948
+oid sha256:99edb23c958dc8c637f78eb0726eab3d2867d15e73ec544c32f2b2969f5698ee
+size 205367268

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f288629bb09b8b752b4b75bceb6f289481153f93aeed4ff79f6755b1c0d39df1
+oid sha256:611557bd99ff581460fbeda0fad211330fbeba00e09361bfbf98f7bb143b351d
 size 15984

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:af5dba9242c3905e87651a864558b3662c382afb0a3e9963e26d94d6dbc29adc
+oid sha256:33c0e865fc1620ec5583f5273c5fb0708ccf5ef59e324bfe04642dacb0f4e027
 size 15984

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e6a53b6859e422cf384738367381215d67857dd853d1bfec83e189333c9cf559
+oid sha256:c15229df8e26d1206a5a5d331bc74fbdebf171bcda3294b3fcdb8ad7179d0c57
 size 15984

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a6a56c402b3d7f24a730e99ddb5aa1ef8162b32abd55842b8f45ad799a09c9e
+oid sha256:6829364baebbd216ef25fa616f014a1deeb94b7666e2b3a4c8c4f9ad459acb76
 size 15984

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c22539d1c9d5bd239c2607ec42fa16c974e82508d283bc6917aa160614ae224
+oid sha256:a3a6d289787dafa9ef8d3b3c1dfbd3a4dd7834875e016c5e02ed8e2ea58fab64
 size 15984

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8234a394f524116534f60fdfea2acc06712b959769ccfbc016c63701166c374a
+oid sha256:b43432bbe4ed1a050ba3c232481002d3b6ed37b46d748ed25156883f2321485e
 size 15984

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6155c61bbd692fc3caa6738003f9d68c84a3a579eb4795ed691196a60f2fff4c
+oid sha256:44003f64be5427c7cdbf8f60cbbacadecd7e601f9bcba0233851b4d178db0794
 size 15984

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e803224d5c6daf4f3312d1861d0d6ad5321f6be439a3754ce688662d9779bc7c
+oid sha256:4fad1dbb7ebab1f3bb4123e55adfe4f4afb8d4e51d06946f97d83f6fbd8f25ff
 size 15984

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a0de66873daeaaf04f8a98eb3129e18cff5612bd1989f7c91708f58608531127
+oid sha256:0831e1c0820a2c38d98b00a5bf5f078ec48120c8eb27d4dfc76649a17f4267a8
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 1.3268142938613892,
   "best_model_checkpoint": "miner_id_24/checkpoint-150",
-  "epoch": 0.4655493482309125,
+  "epoch": 0.5586592178770949,
   "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": 66.781,
       "eval_steps_per_second": 8.4,
       "step": 250
+    },
+    {
+      "epoch": 0.48417132216014896,
+      "grad_norm": 3.249690055847168,
+      "learning_rate": 0.00015522388059701495,
+      "loss": 1.4629,
+      "step": 260
+    },
+    {
+      "epoch": 0.5027932960893855,
+      "grad_norm": 3.2629432678222656,
+      "learning_rate": 0.00016119402985074628,
+      "loss": 1.4387,
+      "step": 270
+    },
+    {
+      "epoch": 0.521415270018622,
+      "grad_norm": 4.808574676513672,
+      "learning_rate": 0.00016716417910447761,
+      "loss": 1.4205,
+      "step": 280
+    },
+    {
+      "epoch": 0.5400372439478585,
+      "grad_norm": 3.8548362255096436,
+      "learning_rate": 0.00017313432835820895,
+      "loss": 1.4286,
+      "step": 290
+    },
+    {
+      "epoch": 0.5586592178770949,
+      "grad_norm": 5.292648792266846,
+      "learning_rate": 0.0001791044776119403,
+      "loss": 1.3715,
+      "step": 300
+    },
+    {
+      "epoch": 0.5586592178770949,
+      "eval_loss": 1.346940517425537,
+      "eval_runtime": 7.1626,
+      "eval_samples_per_second": 66.596,
+      "eval_steps_per_second": 8.377,
+      "step": 300
     }
   ],
   "logging_steps": 10,
@@ -244,7 +287,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 2
+        "early_stopping_patience_counter": 3
       }
     },
     "TrainerControl": {
@@ -253,12 +296,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2.7918472298102784e+16,
+  "total_flos": 3.351332862610637e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null