Training in progress, step 36, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07a361d9115a3c58a51366f737efc00823640eb92adcaceb600d46d0e40c2c09
+oid sha256:e84e20f19da44d08325a9270f32ee68f3c4a0a97ff2a2c5f6eed91533ad99fbe
 size 70430032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:144bafda1a2e0b3413c24866f9febe351417795651859afb3db66d46856f8ecb
+oid sha256:89fe0a2fd7d0f95e9b205516861369468b3eea5334e9fb671d1801079487786e
 size 141053442

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:70ffcbbe4484b9976ff55de267067253c719e92a34906494539954f670b8f2b0
+oid sha256:d07aa0a3f5ba8b3845b197d91a20589e2ec3465135a67225e91306eba5c0cb15
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:649f5b8e9bbd18b4d8a30519c224e549bf0f0fa385593a26bc802bbe1d5b00e9
+oid sha256:0782db3f4885497f5c60af87e928c88a12f2843f132ca860ca433eeff7b31c46
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:41db0f7b558794ef9d59f8eb16a928c45648e7c751df0972a3b5bfd4f6d4462b
+oid sha256:856552b3f8e1a32391561df631a86445aba6f19b521fb84286f9892515c3680e
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ab26770d9c6b24408295f6603e3877cb83f15aba8dfe763585f7da25b8d564e
+oid sha256:91b26b696dd7fdf3c19b30106ead077b6a91d7e64fffb2bab4ef7d1a57f723ea
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:80ee0e3a85744dc5ab7c697968a5f553547d0d3855c554f1051966905d4f4d69
+oid sha256:28651c349f447d90467a1ab072123a42ef3fcd558c7e8a7b853a87ba29324613
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.5989376306533813,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 2.127659574468085,
+  "epoch": 3.0638297872340425,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 36,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,83 @@
       "eval_samples_per_second": 147.401,
       "eval_steps_per_second": 18.658,
       "step": 25
+    },
+    {
+      "epoch": 2.2127659574468086,
+      "grad_norm": 1.5322821140289307,
+      "learning_rate": 1.9868268181037185e-05,
+      "loss": 0.4246,
+      "step": 26
+    },
+    {
+      "epoch": 2.297872340425532,
+      "grad_norm": 1.5346146821975708,
+      "learning_rate": 1.631521781767214e-05,
+      "loss": 0.526,
+      "step": 27
+    },
+    {
+      "epoch": 2.382978723404255,
+      "grad_norm": 1.4425619840621948,
+      "learning_rate": 1.3049554138967051e-05,
+      "loss": 0.4616,
+      "step": 28
+    },
+    {
+      "epoch": 2.4680851063829787,
+      "grad_norm": 1.0223990678787231,
+      "learning_rate": 1.0099138635988026e-05,
+      "loss": 0.4379,
+      "step": 29
+    },
+    {
+      "epoch": 2.5531914893617023,
+      "grad_norm": 1.4977924823760986,
+      "learning_rate": 7.489143213519301e-06,
+      "loss": 0.5751,
+      "step": 30
+    },
+    {
+      "epoch": 2.6382978723404253,
+      "grad_norm": 1.4635932445526123,
+      "learning_rate": 5.241835432246889e-06,
+      "loss": 0.5067,
+      "step": 31
+    },
+    {
+      "epoch": 2.723404255319149,
+      "grad_norm": 1.7609386444091797,
+      "learning_rate": 3.376388529782215e-06,
+      "loss": 0.4576,
+      "step": 32
+    },
+    {
+      "epoch": 2.8085106382978724,
+      "grad_norm": 1.5040547847747803,
+      "learning_rate": 1.908717841359048e-06,
+      "loss": 0.5874,
+      "step": 33
+    },
+    {
+      "epoch": 2.8936170212765955,
+      "grad_norm": 1.596747875213623,
+      "learning_rate": 8.513450158049108e-07,
+      "loss": 0.4815,
+      "step": 34
+    },
+    {
+      "epoch": 2.978723404255319,
+      "grad_norm": 2.097698450088501,
+      "learning_rate": 2.1329118524827662e-07,
+      "loss": 0.4825,
+      "step": 35
+    },
+    {
+      "epoch": 3.0638297872340425,
+      "grad_norm": 2.1862497329711914,
+      "learning_rate": 0.0,
+      "loss": 0.6099,
+      "step": 36
     }
   ],
   "logging_steps": 1,
@@ -221,12 +298,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.47650456322048e+16,
+  "total_flos": 2.126166571037491e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null