Training in progress, step 43, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:12feb3ab3e3474402bab84cda946225fed02182ab4cdb5cfe31b3d428ece3a18
+oid sha256:b1ba7722a7bbd0f9958e0998ded3340a5480d468083d74e34b8fe6278ba86f38
 size 319876032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:34e352a6ba4b7b270d2e551a5f7df54eea4adc1170fb4a5b21db06fd915ca07c
+oid sha256:ab78131d549aa5d19c5164b9318eb19da1e6cbe46a5455cfde72c8748e0d4e12
 size 640009682

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:31943532d7b32b7b7d3d8fad34b62af919f3b7e5ff13b3e1a06c03c287caad0b
+oid sha256:bbcdcb233ff3f4e5e3e8bef252df94b78239db137c2943d20fa9eefbda6d99b4
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5dab5ea1737eda663aaf852ac05897b62e0912005c8cd133400ef9c0d4d8d1a9
+oid sha256:ee60faf9c0ed5349029ce578f2b7585fab1a9599965f6df3b8da1fb4bdcfd48e
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd27913d1af7608d9a161495a2ea6ae9d6e79be5a4e1dee51f31de8f0baaa49f
+oid sha256:4386b7e1bd7573993c6d34216164861d202ae1b48f647e86a4cc693a7262c032
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87ad26ca7de951fdedea40c2add1097730dc720b63aeb68fbcadd06f18009778
+oid sha256:420e2cbccb3e885ee80c4f6107e8d2781fd9437ebfe9a5ae2b1768aa6d7653b0
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f73e6deadf3f08547d8bef9e9b3d87995c0c2ef87d51b8801270b8b2d32ac55
+oid sha256:d9ca16dc5125aa616f8880e7477dabd4029e096d950b1e4b31474d314c00eace
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 2.1035513877868652,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 1.7614879649890591,
+  "epoch": 3.0437636761487963,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 43,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,132 @@
       "eval_samples_per_second": 15.227,
       "eval_steps_per_second": 3.959,
       "step": 25
+    },
+    {
+      "epoch": 1.8315098468271334,
+      "grad_norm": 0.3228803277015686,
+      "learning_rate": 4.307583240115024e-05,
+      "loss": 2.0718,
+      "step": 26
+    },
+    {
+      "epoch": 1.901531728665208,
+      "grad_norm": 0.43157458305358887,
+      "learning_rate": 3.9789240471617385e-05,
+      "loss": 1.9175,
+      "step": 27
+    },
+    {
+      "epoch": 1.9715536105032823,
+      "grad_norm": 0.6008814573287964,
+      "learning_rate": 3.659191132728971e-05,
+      "loss": 2.1905,
+      "step": 28
+    },
+    {
+      "epoch": 2.052516411378556,
+      "grad_norm": 0.7690155506134033,
+      "learning_rate": 3.350260816694816e-05,
+      "loss": 3.8515,
+      "step": 29
+    },
+    {
+      "epoch": 2.12253829321663,
+      "grad_norm": 0.3333316743373871,
+      "learning_rate": 3.0539460249945056e-05,
+      "loss": 1.8417,
+      "step": 30
+    },
+    {
+      "epoch": 2.192560175054705,
+      "grad_norm": 0.4248466491699219,
+      "learning_rate": 2.7719856506501306e-05,
+      "loss": 2.0182,
+      "step": 31
+    },
+    {
+      "epoch": 2.262582056892779,
+      "grad_norm": 0.28588610887527466,
+      "learning_rate": 2.5060343492549566e-05,
+      "loss": 1.595,
+      "step": 32
+    },
+    {
+      "epoch": 2.3326039387308533,
+      "grad_norm": 0.3386515974998474,
+      "learning_rate": 2.257652828796459e-05,
+      "loss": 2.166,
+      "step": 33
+    },
+    {
+      "epoch": 2.402625820568928,
+      "grad_norm": 0.34300777316093445,
+      "learning_rate": 2.0282986908012567e-05,
+      "loss": 1.8786,
+      "step": 34
+    },
+    {
+      "epoch": 2.472647702407002,
+      "grad_norm": 0.5166144967079163,
+      "learning_rate": 1.819317876549771e-05,
+      "loss": 2.2071,
+      "step": 35
+    },
+    {
+      "epoch": 2.5426695842450764,
+      "grad_norm": 0.30271419882774353,
+      "learning_rate": 1.631936768557596e-05,
+      "loss": 1.9849,
+      "step": 36
+    },
+    {
+      "epoch": 2.612691466083151,
+      "grad_norm": 0.3006140887737274,
+      "learning_rate": 1.4672549936752506e-05,
+      "loss": 1.79,
+      "step": 37
+    },
+    {
+      "epoch": 2.6827133479212253,
+      "grad_norm": 0.3940806984901428,
+      "learning_rate": 1.3262389700405744e-05,
+      "loss": 1.9845,
+      "step": 38
+    },
+    {
+      "epoch": 2.7527352297593,
+      "grad_norm": 0.28143924474716187,
+      "learning_rate": 1.2097162357528127e-05,
+      "loss": 1.5694,
+      "step": 39
+    },
+    {
+      "epoch": 2.822757111597374,
+      "grad_norm": 0.31365570425987244,
+      "learning_rate": 1.1183705925499948e-05,
+      "loss": 2.2253,
+      "step": 40
+    },
+    {
+      "epoch": 2.8927789934354484,
+      "grad_norm": 0.34873420000076294,
+      "learning_rate": 1.0527380929884324e-05,
+      "loss": 1.8256,
+      "step": 41
+    },
+    {
+      "epoch": 2.962800875273523,
+      "grad_norm": 0.5362803339958191,
+      "learning_rate": 1.013203894673168e-05,
+      "loss": 2.0108,
+      "step": 42
+    },
+    {
+      "epoch": 3.0437636761487963,
+      "grad_norm": 0.8738157153129578,
+      "learning_rate": 1e-05,
+      "loss": 3.6501,
+      "step": 43
     }
   ],
   "logging_steps": 1,
@@ -221,12 +347,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2.66009604784128e+17,
+  "total_flos": 4.5753652022870016e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null